From 60ed7951d0c9bf8de8588384134f16474367b410 Mon Sep 17 00:00:00 2001
From: Alex <mailinglist@miromico.ch>
Date: Mon, 17 Mar 2008 14:55:06 +0100
Subject: avr32: Allow board to define oscillator rates

On our custom board we have other oscillator rates than on atngw100 and
atstk100x.

Currently these rates are hardcoded in arch/avr32/mach-at32ap/at32ap700x.c.

This patch moves them into board specific code.

Signed-off-by: Alex Raimondi <raimondi@miromico.ch>
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
---
 include/asm-avr32/arch-at32ap/board.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/include/asm-avr32/arch-at32ap/board.h b/include/asm-avr32/arch-at32ap/board.h
index a4e2d28bfb5..cfd3060d5b2 100644
--- a/include/asm-avr32/arch-at32ap/board.h
+++ b/include/asm-avr32/arch-at32ap/board.h
@@ -8,6 +8,12 @@
 
 #define GPIO_PIN_NONE	(-1)
 
+/*
+ * Clock rates for various on-board oscillators. The number of entries
+ * in this array is chip-dependent.
+ */
+extern unsigned long at32_board_osc_rates[];
+  
 /* Add basic devices: system manager, interrupt controller, portmuxes, etc. */
 void at32_add_system_devices(void);
 
-- 
cgit v1.2.3-70-g09d2


From 47882cf620bcd7b014f6f7fc11be8c045787adac Mon Sep 17 00:00:00 2001
From: Hans-Christian Egtvedt <hcegtvedt@atmel.com>
Date: Tue, 5 Feb 2008 15:27:16 +0100
Subject: avr32: Add pin configuration choice to LCDC peripheral

This patch lets the board code choose which pin out to use for the LCD
interface.

On AT32AP7000 the LCDC is wired to two sets of pins, which lets the user
choose between dual ethernet and 32-bit EBI. For the ATNGW100 board it
is vital to have the choice to select the alternative pinout since this
pinout is routed to the external headers.

Update ATSTK1002 and ATSTK1004 to use the new interface.

Signed-off-by: Hans-Christian Egtvedt <hcegtvedt@atmel.com>
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
---
 arch/avr32/boards/atstk1000/atstk1002.c |   2 +-
 arch/avr32/boards/atstk1000/atstk1004.c |   2 +-
 arch/avr32/mach-at32ap/at32ap700x.c     | 105 ++++++++++++++++++++++----------
 include/asm-avr32/arch-at32ap/board.h   |   3 +-
 4 files changed, 77 insertions(+), 35 deletions(-)

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
index 0e133268686..86b363c1c25 100644
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ b/arch/avr32/boards/atstk1000/atstk1002.c
@@ -238,7 +238,7 @@ static int __init atstk1002_init(void)
 	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
 #else
 	at32_add_device_lcdc(0, &atstk1000_lcdc_data,
-			     fbmem_start, fbmem_size);
+			     fbmem_start, fbmem_size, 0);
 #endif
 	at32_add_device_usba(0, NULL);
 #ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
diff --git a/arch/avr32/boards/atstk1000/atstk1004.c b/arch/avr32/boards/atstk1000/atstk1004.c
index cbf09dd0db5..c7236df74d7 100644
--- a/arch/avr32/boards/atstk1000/atstk1004.c
+++ b/arch/avr32/boards/atstk1000/atstk1004.c
@@ -140,7 +140,7 @@ static int __init atstk1004_init(void)
 	at32_add_device_mci(0);
 #endif
 	at32_add_device_lcdc(0, &atstk1000_lcdc_data,
-			     fbmem_start, fbmem_size);
+			     fbmem_start, fbmem_size, 0);
 	at32_add_device_usba(0, NULL);
 #ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
 	at32_add_device_ssc(0, ATMEL_SSC_TX);
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 34b56de4ea6..08115f9243f 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1257,7 +1257,8 @@ static struct clk atmel_lcdfb0_pixclk = {
 
 struct platform_device *__init
 at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
-		     unsigned long fbmem_start, unsigned long fbmem_len)
+		     unsigned long fbmem_start, unsigned long fbmem_len,
+		     unsigned int pin_config)
 {
 	struct platform_device *pdev;
 	struct atmel_lcdfb_info *info;
@@ -1284,37 +1285,77 @@ at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
 	switch (id) {
 	case 0:
 		pdev = &atmel_lcdfb0_device;
-		select_peripheral(PC(19), PERIPH_A, 0);	/* CC	  */
-		select_peripheral(PC(20), PERIPH_A, 0);	/* HSYNC  */
-		select_peripheral(PC(21), PERIPH_A, 0);	/* PCLK	  */
-		select_peripheral(PC(22), PERIPH_A, 0);	/* VSYNC  */
-		select_peripheral(PC(23), PERIPH_A, 0);	/* DVAL	  */
-		select_peripheral(PC(24), PERIPH_A, 0);	/* MODE	  */
-		select_peripheral(PC(25), PERIPH_A, 0);	/* PWR	  */
-		select_peripheral(PC(26), PERIPH_A, 0);	/* DATA0  */
-		select_peripheral(PC(27), PERIPH_A, 0);	/* DATA1  */
-		select_peripheral(PC(28), PERIPH_A, 0);	/* DATA2  */
-		select_peripheral(PC(29), PERIPH_A, 0);	/* DATA3  */
-		select_peripheral(PC(30), PERIPH_A, 0);	/* DATA4  */
-		select_peripheral(PC(31), PERIPH_A, 0);	/* DATA5  */
-		select_peripheral(PD(0),  PERIPH_A, 0);	/* DATA6  */
-		select_peripheral(PD(1),  PERIPH_A, 0);	/* DATA7  */
-		select_peripheral(PD(2),  PERIPH_A, 0);	/* DATA8  */
-		select_peripheral(PD(3),  PERIPH_A, 0);	/* DATA9  */
-		select_peripheral(PD(4),  PERIPH_A, 0);	/* DATA10 */
-		select_peripheral(PD(5),  PERIPH_A, 0);	/* DATA11 */
-		select_peripheral(PD(6),  PERIPH_A, 0);	/* DATA12 */
-		select_peripheral(PD(7),  PERIPH_A, 0);	/* DATA13 */
-		select_peripheral(PD(8),  PERIPH_A, 0);	/* DATA14 */
-		select_peripheral(PD(9),  PERIPH_A, 0);	/* DATA15 */
-		select_peripheral(PD(10), PERIPH_A, 0);	/* DATA16 */
-		select_peripheral(PD(11), PERIPH_A, 0);	/* DATA17 */
-		select_peripheral(PD(12), PERIPH_A, 0);	/* DATA18 */
-		select_peripheral(PD(13), PERIPH_A, 0);	/* DATA19 */
-		select_peripheral(PD(14), PERIPH_A, 0);	/* DATA20 */
-		select_peripheral(PD(15), PERIPH_A, 0);	/* DATA21 */
-		select_peripheral(PD(16), PERIPH_A, 0);	/* DATA22 */
-		select_peripheral(PD(17), PERIPH_A, 0);	/* DATA23 */
+
+		switch (pin_config) {
+		case 0:
+			select_peripheral(PC(19), PERIPH_A, 0);	/* CC	  */
+			select_peripheral(PC(20), PERIPH_A, 0);	/* HSYNC  */
+			select_peripheral(PC(21), PERIPH_A, 0);	/* PCLK	  */
+			select_peripheral(PC(22), PERIPH_A, 0);	/* VSYNC  */
+			select_peripheral(PC(23), PERIPH_A, 0);	/* DVAL	  */
+			select_peripheral(PC(24), PERIPH_A, 0);	/* MODE	  */
+			select_peripheral(PC(25), PERIPH_A, 0);	/* PWR	  */
+			select_peripheral(PC(26), PERIPH_A, 0);	/* DATA0  */
+			select_peripheral(PC(27), PERIPH_A, 0);	/* DATA1  */
+			select_peripheral(PC(28), PERIPH_A, 0);	/* DATA2  */
+			select_peripheral(PC(29), PERIPH_A, 0);	/* DATA3  */
+			select_peripheral(PC(30), PERIPH_A, 0);	/* DATA4  */
+			select_peripheral(PC(31), PERIPH_A, 0);	/* DATA5  */
+			select_peripheral(PD(0),  PERIPH_A, 0);	/* DATA6  */
+			select_peripheral(PD(1),  PERIPH_A, 0);	/* DATA7  */
+			select_peripheral(PD(2),  PERIPH_A, 0);	/* DATA8  */
+			select_peripheral(PD(3),  PERIPH_A, 0);	/* DATA9  */
+			select_peripheral(PD(4),  PERIPH_A, 0);	/* DATA10 */
+			select_peripheral(PD(5),  PERIPH_A, 0);	/* DATA11 */
+			select_peripheral(PD(6),  PERIPH_A, 0);	/* DATA12 */
+			select_peripheral(PD(7),  PERIPH_A, 0);	/* DATA13 */
+			select_peripheral(PD(8),  PERIPH_A, 0);	/* DATA14 */
+			select_peripheral(PD(9),  PERIPH_A, 0);	/* DATA15 */
+			select_peripheral(PD(10), PERIPH_A, 0);	/* DATA16 */
+			select_peripheral(PD(11), PERIPH_A, 0);	/* DATA17 */
+			select_peripheral(PD(12), PERIPH_A, 0);	/* DATA18 */
+			select_peripheral(PD(13), PERIPH_A, 0);	/* DATA19 */
+			select_peripheral(PD(14), PERIPH_A, 0);	/* DATA20 */
+			select_peripheral(PD(15), PERIPH_A, 0);	/* DATA21 */
+			select_peripheral(PD(16), PERIPH_A, 0);	/* DATA22 */
+			select_peripheral(PD(17), PERIPH_A, 0);	/* DATA23 */
+			break;
+		case 1:
+			select_peripheral(PE(0),  PERIPH_B, 0);	/* CC	  */
+			select_peripheral(PC(20), PERIPH_A, 0);	/* HSYNC  */
+			select_peripheral(PC(21), PERIPH_A, 0);	/* PCLK	  */
+			select_peripheral(PC(22), PERIPH_A, 0);	/* VSYNC  */
+			select_peripheral(PE(1),  PERIPH_B, 0);	/* DVAL	  */
+			select_peripheral(PE(2),  PERIPH_B, 0);	/* MODE	  */
+			select_peripheral(PC(25), PERIPH_A, 0);	/* PWR	  */
+			select_peripheral(PE(3),  PERIPH_B, 0);	/* DATA0  */
+			select_peripheral(PE(4),  PERIPH_B, 0);	/* DATA1  */
+			select_peripheral(PE(5),  PERIPH_B, 0);	/* DATA2  */
+			select_peripheral(PE(6),  PERIPH_B, 0);	/* DATA3  */
+			select_peripheral(PE(7),  PERIPH_B, 0);	/* DATA4  */
+			select_peripheral(PC(31), PERIPH_A, 0);	/* DATA5  */
+			select_peripheral(PD(0),  PERIPH_A, 0);	/* DATA6  */
+			select_peripheral(PD(1),  PERIPH_A, 0);	/* DATA7  */
+			select_peripheral(PE(8),  PERIPH_B, 0);	/* DATA8  */
+			select_peripheral(PE(9),  PERIPH_B, 0);	/* DATA9  */
+			select_peripheral(PE(10), PERIPH_B, 0);	/* DATA10 */
+			select_peripheral(PE(11), PERIPH_B, 0);	/* DATA11 */
+			select_peripheral(PE(12), PERIPH_B, 0);	/* DATA12 */
+			select_peripheral(PD(7),  PERIPH_A, 0);	/* DATA13 */
+			select_peripheral(PD(8),  PERIPH_A, 0);	/* DATA14 */
+			select_peripheral(PD(9),  PERIPH_A, 0);	/* DATA15 */
+			select_peripheral(PE(13), PERIPH_B, 0);	/* DATA16 */
+			select_peripheral(PE(14), PERIPH_B, 0);	/* DATA17 */
+			select_peripheral(PE(15), PERIPH_B, 0);	/* DATA18 */
+			select_peripheral(PE(16), PERIPH_B, 0);	/* DATA19 */
+			select_peripheral(PE(17), PERIPH_B, 0);	/* DATA20 */
+			select_peripheral(PE(18), PERIPH_B, 0);	/* DATA21 */
+			select_peripheral(PD(16), PERIPH_A, 0);	/* DATA22 */
+			select_peripheral(PD(17), PERIPH_A, 0);	/* DATA23 */
+			break;
+		default:
+			goto err_invalid_id;
+		}
 
 		clk_set_parent(&atmel_lcdfb0_pixclk, &pll0);
 		clk_set_rate(&atmel_lcdfb0_pixclk, clk_get_rate(&pll0));
diff --git a/include/asm-avr32/arch-at32ap/board.h b/include/asm-avr32/arch-at32ap/board.h
index cfd3060d5b2..a78206cdb3d 100644
--- a/include/asm-avr32/arch-at32ap/board.h
+++ b/include/asm-avr32/arch-at32ap/board.h
@@ -42,7 +42,8 @@ at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n);
 struct atmel_lcdfb_info;
 struct platform_device *
 at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
-		     unsigned long fbmem_start, unsigned long fbmem_len);
+		     unsigned long fbmem_start, unsigned long fbmem_len,
+		     unsigned int pin_config);
 
 struct usba_platform_data;
 struct platform_device *
-- 
cgit v1.2.3-70-g09d2


From d86d314f67191011e6f494f6517b8cbd7dd3dc39 Mon Sep 17 00:00:00 2001
From: Hans-Christian Egtvedt <hcegtvedt@atmel.com>
Date: Mon, 25 Feb 2008 11:24:30 +0100
Subject: avr32: Add PSIF platform devices

This patch adds the PS/2 interface (PSIF) to the device code, split into
two platform devices, one for each port.

The function for adding the PSIF platform device is also added to the
board header file.

Signed-off-by: Hans-Christian Egtvedt <hcegtvedt@atmel.com>
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
---
 arch/avr32/mach-at32ap/at32ap700x.c   | 77 +++++++++++++++++++++++++++++++++++
 include/asm-avr32/arch-at32ap/board.h |  1 +
 2 files changed, 78 insertions(+)

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 08115f9243f..a9ae7bb108b 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -833,6 +833,81 @@ void __init at32_add_system_devices(void)
 	platform_device_register(&pio4_device);
 }
 
+/* --------------------------------------------------------------------
+ *  PSIF
+ * -------------------------------------------------------------------- */
+static struct resource atmel_psif0_resource[] __initdata = {
+	{
+		.start	= 0xffe03c00,
+		.end	= 0xffe03cff,
+		.flags	= IORESOURCE_MEM,
+	},
+	IRQ(18),
+};
+static struct clk atmel_psif0_pclk = {
+	.name		= "pclk",
+	.parent		= &pba_clk,
+	.mode		= pba_clk_mode,
+	.get_rate	= pba_clk_get_rate,
+	.index		= 15,
+};
+
+static struct resource atmel_psif1_resource[] __initdata = {
+	{
+		.start	= 0xffe03d00,
+		.end	= 0xffe03dff,
+		.flags	= IORESOURCE_MEM,
+	},
+	IRQ(18),
+};
+static struct clk atmel_psif1_pclk = {
+	.name		= "pclk",
+	.parent		= &pba_clk,
+	.mode		= pba_clk_mode,
+	.get_rate	= pba_clk_get_rate,
+	.index		= 15,
+};
+
+struct platform_device *__init at32_add_device_psif(unsigned int id)
+{
+	struct platform_device *pdev;
+
+	if (!(id == 0 || id == 1))
+		return NULL;
+
+	pdev = platform_device_alloc("atmel_psif", id);
+	if (!pdev)
+		return NULL;
+
+	switch (id) {
+	case 0:
+		if (platform_device_add_resources(pdev, atmel_psif0_resource,
+					ARRAY_SIZE(atmel_psif0_resource)))
+			goto err_add_resources;
+		atmel_psif0_pclk.dev = &pdev->dev;
+		select_peripheral(PA(8), PERIPH_A, 0); /* CLOCK */
+		select_peripheral(PA(9), PERIPH_A, 0); /* DATA  */
+		break;
+	case 1:
+		if (platform_device_add_resources(pdev, atmel_psif1_resource,
+					ARRAY_SIZE(atmel_psif1_resource)))
+			goto err_add_resources;
+		atmel_psif1_pclk.dev = &pdev->dev;
+		select_peripheral(PB(11), PERIPH_A, 0); /* CLOCK */
+		select_peripheral(PB(12), PERIPH_A, 0); /* DATA  */
+		break;
+	default:
+		return NULL;
+	}
+
+	platform_device_add(pdev);
+	return pdev;
+
+err_add_resources:
+	platform_device_put(pdev);
+	return NULL;
+}
+
 /* --------------------------------------------------------------------
  *  USART
  * -------------------------------------------------------------------- */
@@ -1934,6 +2009,8 @@ struct clk *at32_clock_list[] = {
 	&pio4_mck,
 	&at32_tcb0_t0_clk,
 	&at32_tcb1_t0_clk,
+	&atmel_psif0_pclk,
+	&atmel_psif1_pclk,
 	&atmel_usart0_usart,
 	&atmel_usart1_usart,
 	&atmel_usart2_usart,
diff --git a/include/asm-avr32/arch-at32ap/board.h b/include/asm-avr32/arch-at32ap/board.h
index a78206cdb3d..b4cddfaca90 100644
--- a/include/asm-avr32/arch-at32ap/board.h
+++ b/include/asm-avr32/arch-at32ap/board.h
@@ -80,6 +80,7 @@ struct platform_device *at32_add_device_twi(unsigned int id,
 struct platform_device *at32_add_device_mci(unsigned int id);
 struct platform_device *at32_add_device_ac97c(unsigned int id);
 struct platform_device *at32_add_device_abdac(unsigned int id);
+struct platform_device *at32_add_device_psif(unsigned int id);
 
 struct cf_platform_data {
 	int	detect_pin;
-- 
cgit v1.2.3-70-g09d2


From 65033ed740ef06eddf9fde7a992eab336cbddd56 Mon Sep 17 00:00:00 2001
From: Haavard Skinnemoen <hskinnemoen@atmel.com>
Date: Tue, 4 Mar 2008 15:15:00 +0100
Subject: avr32: Move setup_platform() into chip-specific file

Combine at32_clock_init() and at32_portmux_init() into
setup_platform() and remove setup_platform() from at32ap.c. No
functional change since all setup_platform() ever did was call those
two functions.

Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
---
 arch/avr32/mach-at32ap/at32ap.c      |  8 --------
 arch/avr32/mach-at32ap/at32ap700x.c  | 18 ++++++++----------
 include/asm-avr32/arch-at32ap/init.h |  4 ----
 3 files changed, 8 insertions(+), 22 deletions(-)

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/mach-at32ap/at32ap.c b/arch/avr32/mach-at32ap/at32ap.c
index 7c4987f3287..1040bda4fda 100644
--- a/arch/avr32/mach-at32ap/at32ap.c
+++ b/arch/avr32/mach-at32ap/at32ap.c
@@ -11,14 +11,6 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 
-#include <asm/arch/init.h>
-
-void __init setup_platform(void)
-{
-	at32_clock_init();
-	at32_portmux_init();
-}
-
 static int __init pdc_probe(struct platform_device *pdev)
 {
 	struct clk *pclk, *hclk;
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 2f208eb4d3c..baf4680b498 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -2048,16 +2048,7 @@ struct clk *at32_clock_list[] = {
 };
 unsigned int at32_nr_clocks = ARRAY_SIZE(at32_clock_list);
 
-void __init at32_portmux_init(void)
-{
-	at32_init_pio(&pio0_device);
-	at32_init_pio(&pio1_device);
-	at32_init_pio(&pio2_device);
-	at32_init_pio(&pio3_device);
-	at32_init_pio(&pio4_device);
-}
-
-void __init at32_clock_init(void)
+void __init setup_platform(void)
 {
 	u32 cpu_mask = 0, hsb_mask = 0, pba_mask = 0, pbb_mask = 0;
 	int i;
@@ -2112,4 +2103,11 @@ void __init at32_clock_init(void)
 	pm_writel(HSB_MASK, hsb_mask);
 	pm_writel(PBA_MASK, pba_mask);
 	pm_writel(PBB_MASK, pbb_mask);
+
+	/* Initialize the port muxes */
+	at32_init_pio(&pio0_device);
+	at32_init_pio(&pio1_device);
+	at32_init_pio(&pio2_device);
+	at32_init_pio(&pio3_device);
+	at32_init_pio(&pio4_device);
 }
diff --git a/include/asm-avr32/arch-at32ap/init.h b/include/asm-avr32/arch-at32ap/init.h
index 5e75d850d70..bc40e3d4615 100644
--- a/include/asm-avr32/arch-at32ap/init.h
+++ b/include/asm-avr32/arch-at32ap/init.h
@@ -13,10 +13,6 @@
 void setup_platform(void);
 void setup_board(void);
 
-/* Called by setup_platform */
-void at32_clock_init(void);
-void at32_portmux_init(void);
-
 void at32_setup_serial_console(unsigned int usart_id);
 
 #endif /* __ASM_AVR32_AT32AP_INIT_H__ */
-- 
cgit v1.2.3-70-g09d2


From b83d6ee17588f1a4fbfc8ef0451b0900a5ef5950 Mon Sep 17 00:00:00 2001
From: Haavard Skinnemoen <hskinnemoen@atmel.com>
Date: Wed, 5 Mar 2008 10:00:28 +0100
Subject: avr32: Add simple SRAM allocator

Add SRAM allocator for avr32, which is just a thin wrapper around
genalloc.

Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
---
 arch/avr32/Kconfig                   |  1 +
 arch/avr32/mach-at32ap/at32ap700x.c  | 26 ++++++++++++++++++++++++++
 include/asm-avr32/arch-at32ap/sram.h | 30 ++++++++++++++++++++++++++++++
 3 files changed, 57 insertions(+)
 create mode 100644 include/asm-avr32/arch-at32ap/sram.h

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index a5793c13f50..e8ee5fa017b 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -88,6 +88,7 @@ config PLATFORM_AT32AP
 	select MMU
 	select PERFORMANCE_COUNTERS
 	select HAVE_GPIO_LIB
+	select GENERIC_ALLOCATOR
 
 #
 # CPU types
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 3ee5e727879..07b21b121ee 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -20,6 +20,7 @@
 #include <asm/arch/at32ap700x.h>
 #include <asm/arch/board.h>
 #include <asm/arch/portmux.h>
+#include <asm/arch/sram.h>
 
 #include <video/atmel_lcdc.h>
 
@@ -2120,3 +2121,28 @@ void __init setup_platform(void)
 	at32_init_pio(&pio3_device);
 	at32_init_pio(&pio4_device);
 }
+
+struct gen_pool *sram_pool;
+
+static int __init sram_init(void)
+{
+	struct gen_pool *pool;
+
+	/* 1KiB granularity */
+	pool = gen_pool_create(10, -1);
+	if (!pool)
+		goto fail;
+
+	if (gen_pool_add(pool, 0x24000000, 0x8000, -1))
+		goto err_pool_add;
+
+	sram_pool = pool;
+	return 0;
+
+err_pool_add:
+	gen_pool_destroy(pool);
+fail:
+	pr_err("Failed to create SRAM pool\n");
+	return -ENOMEM;
+}
+core_initcall(sram_init);
diff --git a/include/asm-avr32/arch-at32ap/sram.h b/include/asm-avr32/arch-at32ap/sram.h
new file mode 100644
index 00000000000..4838dae7601
--- /dev/null
+++ b/include/asm-avr32/arch-at32ap/sram.h
@@ -0,0 +1,30 @@
+/*
+ * Simple SRAM allocator
+ *
+ * Copyright (C) 2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_AVR32_ARCH_SRAM_H
+#define __ASM_AVR32_ARCH_SRAM_H
+
+#include <linux/genalloc.h>
+
+extern struct gen_pool *sram_pool;
+
+static inline unsigned long sram_alloc(size_t len)
+{
+	if (!sram_pool)
+		return 0UL;
+
+	return gen_pool_alloc(sram_pool, len);
+}
+
+static inline void sram_free(unsigned long addr, size_t len)
+{
+	return gen_pool_free(sram_pool, addr, len);
+}
+
+#endif /* __ASM_AVR32_ARCH_SRAM_H */
-- 
cgit v1.2.3-70-g09d2


From 02a00cf672a37292c31bbdde191712bfa40a4f1d Mon Sep 17 00:00:00 2001
From: Haavard Skinnemoen <hskinnemoen@atmel.com>
Date: Sun, 24 Feb 2008 13:51:38 +0100
Subject: avr32: Power Management support ("standby" and "mem" modes)

Implement Standby support. In this mode, we'll suspend all drivers,
put the SDRAM in self-refresh mode and switch off the HSB bus
("frozen" mode.)

Implement Suspend-to-mem support. In this mode, we suspend all
drivers, put the SDRAM into self-refresh mode and switch off all
internal clocks except the 32 kHz oscillator ("stop" mode.)

The lowest-level suspend code runs from a small portion of SRAM
allocated at startup time. This gets rid of a small potential race
with the SDRAM where we might try to enter self-refresh mode in the
middle of an icache burst. We also relocate all interrupt and
exception handlers to SRAM during the small window when we enter and
exit the low-power modes.

We don't need to do any special tricks to start and stop the PLL. The
main clock is automatically gated by hardware until the PLL is stable.

Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
---
 arch/avr32/Kconfig                     |   5 +
 arch/avr32/mach-at32ap/Makefile        |   5 +
 arch/avr32/mach-at32ap/intc.c          |  54 +++++++-
 arch/avr32/mach-at32ap/pm-at32ap700x.S | 108 +++++++++++++++
 arch/avr32/mach-at32ap/pm.c            | 245 +++++++++++++++++++++++++++++++++
 arch/avr32/mach-at32ap/sdramc.h        |  76 ++++++++++
 include/asm-avr32/arch-at32ap/pm.h     |   3 +
 include/asm-avr32/thread_info.h        |   1 +
 8 files changed, 496 insertions(+), 1 deletion(-)
 create mode 100644 arch/avr32/mach-at32ap/pm.c
 create mode 100644 arch/avr32/mach-at32ap/sdramc.h

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index e8ee5fa017b..45d63c98601 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -205,6 +205,11 @@ endmenu
 
 menu "Power management options"
 
+source "kernel/power/Kconfig"
+
+config ARCH_SUSPEND_POSSIBLE
+	def_bool y
+
 menu "CPU Frequency scaling"
 
 source "drivers/cpufreq/Kconfig"
diff --git a/arch/avr32/mach-at32ap/Makefile b/arch/avr32/mach-at32ap/Makefile
index cb44182d386..d5018e2eed2 100644
--- a/arch/avr32/mach-at32ap/Makefile
+++ b/arch/avr32/mach-at32ap/Makefile
@@ -1,3 +1,8 @@
 obj-y				+= pdc.o clock.o intc.o extint.o pio.o hsmc.o
 obj-$(CONFIG_CPU_AT32AP700X)	+= at32ap700x.o pm-at32ap700x.o
 obj-$(CONFIG_CPU_FREQ_AT32AP)	+= cpufreq.o
+obj-$(CONFIG_PM)		+= pm.o
+
+ifeq ($(CONFIG_PM_DEBUG),y)
+CFLAGS_pm.o	+= -DDEBUG
+endif
diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c
index 644a3fb8c16..994c4545e2b 100644
--- a/arch/avr32/mach-at32ap/intc.c
+++ b/arch/avr32/mach-at32ap/intc.c
@@ -22,6 +22,10 @@ struct intc {
 	void __iomem		*regs;
 	struct irq_chip		chip;
 	struct sys_device	sysdev;
+#ifdef CONFIG_PM
+	unsigned long		suspend_ipr;
+	unsigned long		saved_ipr[64];
+#endif
 };
 
 extern struct platform_device at32_intc0_device;
@@ -138,8 +142,56 @@ fail:
 	panic("Interrupt controller initialization failed!\n");
 }
 
+#ifdef CONFIG_PM
+void intc_set_suspend_handler(unsigned long offset)
+{
+	intc0.suspend_ipr = offset;
+}
+
+static int intc_suspend(struct sys_device *sdev, pm_message_t state)
+{
+	struct intc *intc = container_of(sdev, struct intc, sysdev);
+	int i;
+
+	if (unlikely(!irqs_disabled())) {
+		pr_err("intc_suspend: called with interrupts enabled\n");
+		return -EINVAL;
+	}
+
+	if (unlikely(!intc->suspend_ipr)) {
+		pr_err("intc_suspend: suspend_ipr not initialized\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < 64; i++) {
+		intc->saved_ipr[i] = intc_readl(intc, INTPR0 + 4 * i);
+		intc_writel(intc, INTPR0 + 4 * i, intc->suspend_ipr);
+	}
+
+	return 0;
+}
+
+static int intc_resume(struct sys_device *sdev)
+{
+	struct intc *intc = container_of(sdev, struct intc, sysdev);
+	int i;
+
+	WARN_ON(!irqs_disabled());
+
+	for (i = 0; i < 64; i++)
+		intc_writel(intc, INTPR0 + 4 * i, intc->saved_ipr[i]);
+
+	return 0;
+}
+#else
+#define intc_suspend	NULL
+#define intc_resume	NULL
+#endif
+
 static struct sysdev_class intc_class = {
-	.name	= "intc",
+	.name		= "intc",
+	.suspend	= intc_suspend,
+	.resume		= intc_resume,
 };
 
 static int __init intc_init_sysdev(void)
diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S
index 949e2485e27..0a53ad314ff 100644
--- a/arch/avr32/mach-at32ap/pm-at32ap700x.S
+++ b/arch/avr32/mach-at32ap/pm-at32ap700x.S
@@ -12,6 +12,12 @@
 #include <asm/thread_info.h>
 #include <asm/arch/pm.h>
 
+#include "pm.h"
+#include "sdramc.h"
+
+/* Same as 0xfff00000 but fits in a 21 bit signed immediate */
+#define PM_BASE	-0x100000
+
 	.section .bss, "wa", @nobits
 	.global	disable_idle_sleep
 	.type	disable_idle_sleep, @object
@@ -64,3 +70,105 @@ cpu_idle_skip_sleep:
 	unmask_interrupts
 	retal	r12
 	.size	cpu_idle_skip_sleep, . - cpu_idle_skip_sleep
+
+#ifdef CONFIG_PM
+	.section .init.text, "ax", @progbits
+
+	.global	pm_exception
+	.type	pm_exception, @function
+pm_exception:
+	/*
+	 * Exceptions are masked when we switch to this handler, so
+	 * we'll only get "unrecoverable" exceptions (offset 0.)
+	 */
+	sub	r12, pc, . - .Lpanic_msg
+	lddpc	pc, .Lpanic_addr
+
+	.align	2
+.Lpanic_addr:
+	.long	panic
+.Lpanic_msg:
+	.asciz	"Unrecoverable exception during suspend\n"
+	.size	pm_exception, . - pm_exception
+
+	.global	pm_irq0
+	.type	pm_irq0, @function
+pm_irq0:
+	/* Disable interrupts and return after the sleep instruction */
+	mfsr	r9, SYSREG_RSR_INT0
+	mtsr	SYSREG_RAR_INT0, r8
+	sbr	r9, SYSREG_GM_OFFSET
+	mtsr	SYSREG_RSR_INT0, r9
+	rete
+
+	/*
+	 * void cpu_enter_standby(unsigned long sdramc_base)
+	 *
+	 * Enter PM_SUSPEND_STANDBY mode. At this point, all drivers
+	 * are suspended and interrupts are disabled. Interrupts
+	 * marked as 'wakeup' event sources may still come along and
+	 * get us out of here.
+	 *
+	 * The SDRAM will be put into self-refresh mode (which does
+	 * not require a clock from the CPU), and the CPU will be put
+	 * into "frozen" mode (HSB bus stopped). The SDRAM controller
+	 * will automatically bring the SDRAM into normal mode on the
+	 * first access, and the power manager will automatically
+	 * start the HSB and CPU clocks upon a wakeup event.
+	 *
+	 * This code uses the same "skip sleep" technique as above.
+	 * It is very important that we jump directly to
+	 * cpu_after_sleep after the sleep instruction since that's
+	 * where we'll end up if the interrupt handler decides that we
+	 * need to skip the sleep instruction.
+	 */
+	.global	pm_standby
+	.type	pm_standby, @function
+pm_standby:
+	/*
+	 * interrupts are already masked at this point, and EVBA
+	 * points to pm_exception above.
+	 */
+	ld.w	r10, r12[SDRAMC_LPR]
+	sub	r8, pc, . - 1f		/* return address for irq handler */
+	mov	r11, SDRAMC_LPR_LPCB_SELF_RFR
+	bfins	r10, r11, 0, 2		/* LPCB <- self Refresh */
+	sync	0			/* flush write buffer */
+	st.w	r12[SDRAMC_LPR], r11	/* put SDRAM in self-refresh mode */
+	ld.w	r11, r12[SDRAMC_LPR]
+	unmask_interrupts
+	sleep	CPU_SLEEP_FROZEN
+1:	mask_interrupts
+	retal	r12
+	.size	pm_standby, . - pm_standby
+
+	.global	pm_suspend_to_ram
+	.type	pm_suspend_to_ram, @function
+pm_suspend_to_ram:
+	/*
+	 * interrupts are already masked at this point, and EVBA
+	 * points to pm_exception above.
+	 */
+	mov	r11, 0
+	cache	r11[2], 8		/* clean all dcache lines */
+	sync	0			/* flush write buffer */
+	ld.w	r10, r12[SDRAMC_LPR]
+	sub	r8, pc, . - 1f		/* return address for irq handler */
+	mov	r11, SDRAMC_LPR_LPCB_SELF_RFR
+	bfins	r10, r11, 0, 2		/* LPCB <- self refresh */
+	st.w	r12[SDRAMC_LPR], r10	/* put SDRAM in self-refresh mode */
+	ld.w	r11, r12[SDRAMC_LPR]
+
+	unmask_interrupts
+	sleep	CPU_SLEEP_STOP
+1:	mask_interrupts
+
+	retal	r12
+	.size	pm_suspend_to_ram, . - pm_suspend_to_ram
+
+	.global	pm_sram_end
+	.type	pm_sram_end, @function
+pm_sram_end:
+	.size	pm_sram_end, 0
+
+#endif /* CONFIG_PM */
diff --git a/arch/avr32/mach-at32ap/pm.c b/arch/avr32/mach-at32ap/pm.c
new file mode 100644
index 00000000000..0b764320135
--- /dev/null
+++ b/arch/avr32/mach-at32ap/pm.c
@@ -0,0 +1,245 @@
+/*
+ * AVR32 AP Power Management
+ *
+ * Copyright (C) 2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+#include <linux/io.h>
+#include <linux/suspend.h>
+#include <linux/vmalloc.h>
+
+#include <asm/cacheflush.h>
+#include <asm/sysreg.h>
+
+#include <asm/arch/pm.h>
+#include <asm/arch/sram.h>
+
+/* FIXME: This is only valid for AP7000 */
+#define SDRAMC_BASE	0xfff03800
+
+#include "sdramc.h"
+
+#define SRAM_PAGE_FLAGS	(SYSREG_BIT(TLBELO_D) | SYSREG_BF(SZ, 1)	\
+				| SYSREG_BF(AP, 3) | SYSREG_BIT(G))
+
+
+static unsigned long	pm_sram_start;
+static size_t		pm_sram_size;
+static struct vm_struct	*pm_sram_area;
+
+static void (*avr32_pm_enter_standby)(unsigned long sdramc_base);
+static void (*avr32_pm_enter_str)(unsigned long sdramc_base);
+
+/*
+ * Must be called with interrupts disabled. Exceptions will be masked
+ * on return (i.e. all exceptions will be "unrecoverable".)
+ */
+static void *avr32_pm_map_sram(void)
+{
+	unsigned long	vaddr;
+	unsigned long	page_addr;
+	u32		tlbehi;
+	u32		mmucr;
+
+	vaddr = (unsigned long)pm_sram_area->addr;
+	page_addr = pm_sram_start & PAGE_MASK;
+
+	/*
+	 * Mask exceptions and grab the first TLB entry. We won't be
+	 * needing it while sleeping.
+	 */
+	asm volatile("ssrf	%0" : : "i"(SYSREG_EM_OFFSET) : "memory");
+
+	mmucr = sysreg_read(MMUCR);
+	tlbehi = sysreg_read(TLBEHI);
+	sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
+
+	tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
+	tlbehi |= vaddr & PAGE_MASK;
+	tlbehi |= SYSREG_BIT(TLBEHI_V);
+
+	sysreg_write(TLBELO, page_addr | SRAM_PAGE_FLAGS);
+	sysreg_write(TLBEHI, tlbehi);
+	__builtin_tlbw();
+
+	return (void *)(vaddr + pm_sram_start - page_addr);
+}
+
+/*
+ * Must be called with interrupts disabled. Exceptions will be
+ * unmasked on return.
+ */
+static void avr32_pm_unmap_sram(void)
+{
+	u32	mmucr;
+	u32	tlbehi;
+	u32	tlbarlo;
+
+	/* Going to update TLB entry at index 0 */
+	mmucr = sysreg_read(MMUCR);
+	tlbehi = sysreg_read(TLBEHI);
+	sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
+
+	/* Clear the "valid" bit */
+	tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
+	sysreg_write(TLBEHI, tlbehi);
+
+	/* Mark it as "not accessed" */
+	tlbarlo = sysreg_read(TLBARLO);
+	sysreg_write(TLBARLO, tlbarlo | 0x80000000U);
+
+	/* Update the TLB */
+	__builtin_tlbw();
+
+	/* Unmask exceptions */
+	asm volatile("csrf	%0" : : "i"(SYSREG_EM_OFFSET) : "memory");
+}
+
+static int avr32_pm_valid_state(suspend_state_t state)
+{
+	switch (state) {
+	case PM_SUSPEND_ON:
+	case PM_SUSPEND_STANDBY:
+	case PM_SUSPEND_MEM:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
+
+static int avr32_pm_enter(suspend_state_t state)
+{
+	u32		lpr_saved;
+	u32		evba_saved;
+	void		*sram;
+
+	switch (state) {
+	case PM_SUSPEND_STANDBY:
+		sram = avr32_pm_map_sram();
+
+		/* Switch to in-sram exception handlers */
+		evba_saved = sysreg_read(EVBA);
+		sysreg_write(EVBA, (unsigned long)sram);
+
+		/*
+		 * Save the LPR register so that we can re-enable
+		 * SDRAM Low Power mode on resume.
+		 */
+		lpr_saved = sdramc_readl(LPR);
+		pr_debug("%s: Entering standby...\n", __func__);
+		avr32_pm_enter_standby(SDRAMC_BASE);
+		sdramc_writel(LPR, lpr_saved);
+
+		/* Switch back to regular exception handlers */
+		sysreg_write(EVBA, evba_saved);
+
+		avr32_pm_unmap_sram();
+		break;
+
+	case PM_SUSPEND_MEM:
+		sram = avr32_pm_map_sram();
+
+		/* Switch to in-sram exception handlers */
+		evba_saved = sysreg_read(EVBA);
+		sysreg_write(EVBA, (unsigned long)sram);
+
+		/*
+		 * Save the LPR register so that we can re-enable
+		 * SDRAM Low Power mode on resume.
+		 */
+		lpr_saved = sdramc_readl(LPR);
+		pr_debug("%s: Entering suspend-to-ram...\n", __func__);
+		avr32_pm_enter_str(SDRAMC_BASE);
+		sdramc_writel(LPR, lpr_saved);
+
+		/* Switch back to regular exception handlers */
+		sysreg_write(EVBA, evba_saved);
+
+		avr32_pm_unmap_sram();
+		break;
+
+	case PM_SUSPEND_ON:
+		pr_debug("%s: Entering idle...\n", __func__);
+		cpu_enter_idle();
+		break;
+
+	default:
+		pr_debug("%s: Invalid suspend state %d\n", __func__, state);
+		goto out;
+	}
+
+	pr_debug("%s: wakeup\n", __func__);
+
+out:
+	return 0;
+}
+
+static struct platform_suspend_ops avr32_pm_ops = {
+	.valid	= avr32_pm_valid_state,
+	.enter	= avr32_pm_enter,
+};
+
+static unsigned long avr32_pm_offset(void *symbol)
+{
+	extern u8 pm_exception[];
+
+	return (unsigned long)symbol - (unsigned long)pm_exception;
+}
+
+static int __init avr32_pm_init(void)
+{
+	extern u8 pm_exception[];
+	extern u8 pm_irq0[];
+	extern u8 pm_standby[];
+	extern u8 pm_suspend_to_ram[];
+	extern u8 pm_sram_end[];
+	void *dst;
+
+	/*
+	 * To keep things simple, we depend on not needing more than a
+	 * single page.
+	 */
+	pm_sram_size = avr32_pm_offset(pm_sram_end);
+	if (pm_sram_size > PAGE_SIZE)
+		goto err;
+
+	pm_sram_start = sram_alloc(pm_sram_size);
+	if (!pm_sram_start)
+		goto err_alloc_sram;
+
+	/* Grab a virtual area we can use later on. */
+	pm_sram_area = get_vm_area(pm_sram_size, VM_IOREMAP);
+	if (!pm_sram_area)
+		goto err_vm_area;
+	pm_sram_area->phys_addr = pm_sram_start;
+
+	local_irq_disable();
+	dst = avr32_pm_map_sram();
+	memcpy(dst, pm_exception, pm_sram_size);
+	flush_dcache_region(dst, pm_sram_size);
+	invalidate_icache_region(dst, pm_sram_size);
+	avr32_pm_unmap_sram();
+	local_irq_enable();
+
+	avr32_pm_enter_standby = dst + avr32_pm_offset(pm_standby);
+	avr32_pm_enter_str = dst + avr32_pm_offset(pm_suspend_to_ram);
+	intc_set_suspend_handler(avr32_pm_offset(pm_irq0));
+
+	suspend_set_ops(&avr32_pm_ops);
+
+	printk("AVR32 AP Power Management enabled\n");
+
+	return 0;
+
+err_vm_area:
+	sram_free(pm_sram_start, pm_sram_size);
+err_alloc_sram:
+err:
+	pr_err("AVR32 Power Management initialization failed\n");
+	return -ENOMEM;
+}
+arch_initcall(avr32_pm_init);
diff --git a/arch/avr32/mach-at32ap/sdramc.h b/arch/avr32/mach-at32ap/sdramc.h
new file mode 100644
index 00000000000..66eeaed4907
--- /dev/null
+++ b/arch/avr32/mach-at32ap/sdramc.h
@@ -0,0 +1,76 @@
+/*
+ * Register definitions for the AT32AP SDRAM Controller
+ *
+ * Copyright (C) 2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+/* Register offsets */
+#define SDRAMC_MR			0x0000
+#define SDRAMC_TR			0x0004
+#define SDRAMC_CR			0x0008
+#define SDRAMC_HSR			0x000c
+#define SDRAMC_LPR			0x0010
+#define SDRAMC_IER			0x0014
+#define SDRAMC_IDR			0x0018
+#define SDRAMC_IMR			0x001c
+#define SDRAMC_ISR			0x0020
+#define SDRAMC_MDR			0x0024
+
+/* MR - Mode Register */
+#define SDRAMC_MR_MODE_NORMAL		(  0 <<  0)
+#define SDRAMC_MR_MODE_NOP		(  1 <<  0)
+#define SDRAMC_MR_MODE_BANKS_PRECHARGE	(  2 <<  0)
+#define SDRAMC_MR_MODE_LOAD_MODE	(  3 <<  0)
+#define SDRAMC_MR_MODE_AUTO_REFRESH	(  4 <<  0)
+#define SDRAMC_MR_MODE_EXT_LOAD_MODE	(  5 <<  0)
+#define SDRAMC_MR_MODE_POWER_DOWN	(  6 <<  0)
+
+/* CR - Configuration Register */
+#define SDRAMC_CR_NC_8_BITS		(  0 <<  0)
+#define SDRAMC_CR_NC_9_BITS		(  1 <<  0)
+#define SDRAMC_CR_NC_10_BITS		(  2 <<  0)
+#define SDRAMC_CR_NC_11_BITS		(  3 <<  0)
+#define SDRAMC_CR_NR_11_BITS		(  0 <<  2)
+#define SDRAMC_CR_NR_12_BITS		(  1 <<  2)
+#define SDRAMC_CR_NR_13_BITS		(  2 <<  2)
+#define SDRAMC_CR_NB_2_BANKS		(  0 <<  4)
+#define SDRAMC_CR_NB_4_BANKS		(  1 <<  4)
+#define SDRAMC_CR_CAS(x)		((x) <<  5)
+#define SDRAMC_CR_DBW_32_BITS		(  0 <<  7)
+#define SDRAMC_CR_DBW_16_BITS		(  1 <<  7)
+#define SDRAMC_CR_TWR(x)		((x) <<  8)
+#define SDRAMC_CR_TRC(x)		((x) << 12)
+#define SDRAMC_CR_TRP(x)		((x) << 16)
+#define SDRAMC_CR_TRCD(x)		((x) << 20)
+#define SDRAMC_CR_TRAS(x)		((x) << 24)
+#define SDRAMC_CR_TXSR(x)		((x) << 28)
+
+/* HSR - High Speed Register */
+#define SDRAMC_HSR_DA			(  1 <<  0)
+
+/* LPR - Low Power Register */
+#define SDRAMC_LPR_LPCB_INHIBIT		(  0 <<  0)
+#define SDRAMC_LPR_LPCB_SELF_RFR	(  1 <<  0)
+#define SDRAMC_LPR_LPCB_PDOWN		(  2 <<  0)
+#define SDRAMC_LPR_LPCB_DEEP_PDOWN	(  3 <<  0)
+#define SDRAMC_LPR_PASR(x)		((x) <<  4)
+#define SDRAMC_LPR_TCSR(x)		((x) <<  8)
+#define SDRAMC_LPR_DS(x)		((x) << 10)
+#define SDRAMC_LPR_TIMEOUT(x)		((x) << 12)
+
+/* IER/IDR/IMR/ISR - Interrupt Enable/Disable/Mask/Status Register */
+#define SDRAMC_ISR_RES			(  1 <<  0)
+
+/* MDR - Memory Device Register */
+#define SDRAMC_MDR_MD_SDRAM		(  0 <<  0)
+#define SDRAMC_MDR_MD_LOW_PWR_SDRAM	(  1 <<  0)
+
+/* Register access macros */
+#define sdramc_readl(reg) \
+	__raw_readl((void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
+#define sdramc_writel(reg, value) \
+	__raw_writel(value, (void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
diff --git a/include/asm-avr32/arch-at32ap/pm.h b/include/asm-avr32/arch-at32ap/pm.h
index 356e4306490..979b355b77b 100644
--- a/include/asm-avr32/arch-at32ap/pm.h
+++ b/include/asm-avr32/arch-at32ap/pm.h
@@ -19,6 +19,7 @@
 
 #ifndef __ASSEMBLY__
 extern void cpu_enter_idle(void);
+extern void cpu_enter_standby(unsigned long sdramc_base);
 
 extern bool disable_idle_sleep;
 
@@ -43,6 +44,8 @@ static inline void cpu_idle_sleep(void)
 	else
 		cpu_enter_idle();
 }
+
+void intc_set_suspend_handler(unsigned long offset);
 #endif
 
 #endif /* __ASM_AVR32_ARCH_PM_H */
diff --git a/include/asm-avr32/thread_info.h b/include/asm-avr32/thread_info.h
index 07049f6c0d4..df68631b7b2 100644
--- a/include/asm-avr32/thread_info.h
+++ b/include/asm-avr32/thread_info.h
@@ -88,6 +88,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		6
 #define TIF_RESTORE_SIGMASK	7	/* restore signal mask in do_signal */
 #define TIF_CPU_GOING_TO_SLEEP	8	/* CPU is entering sleep 0 mode */
+#define TIF_FREEZE		29
 #define TIF_DEBUG		30	/* debugging enabled */
 #define TIF_USERSPACE		31      /* true if FS sets userspace */
 
-- 
cgit v1.2.3-70-g09d2


From 3bfb1d20b547a5071d01344581eac5846ea84491 Mon Sep 17 00:00:00 2001
From: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Date: Tue, 8 Jul 2008 11:59:42 -0700
Subject: dmaengine: Driver for the Synopsys DesignWare DMA controller

This adds a driver for the Synopsys DesignWare DMA controller (aka
DMACA on AVR32 systems.) This DMA controller can be found integrated
on the AT32AP7000 chip and is primarily meant for peripheral DMA
transfer, but can also be used for memory-to-memory transfers.

This patch is based on a driver from David Brownell which was based on
an older version of the DMA Engine framework. It also implements the
proposed extensions to the DMA Engine API for slave DMA operations.

The dmatest client shows no problems, but there may still be room for
improvement performance-wise. DMA slave transfer performance is
definitely "good enough"; reading 100 MiB from an SD card running at ~20
MHz yields ~7.2 MiB/s average transfer rate.

Full documentation for this controller can be found in the Synopsys
DW AHB DMAC Databook:

http://www.synopsys.com/designware/docs/iip/DW_ahb_dmac/latest/doc/dw_ahb_dmac_db.pdf

The controller has lots of implementation options, so it's usually a
good idea to check the data sheet of the chip it's intergrated on as
well. The AT32AP7000 data sheet can be found here:

http://www.atmel.com/dyn/products/datasheets.asp?family_id=682


Changes since v4:
  * Use client_count instead of dma_chan_is_in_use()
  * Add missing include
  * Unmap buffers unless client told us not to

Changes since v3:
  * Update to latest DMA engine and DMA slave APIs
  * Embed the hw descriptor into the sw descriptor
  * Clean up and update MODULE_DESCRIPTION, copyright date, etc.

Changes since v2:
  * Dequeue all pending transfers in terminate_all()
  * Rename dw_dmac.h -> dw_dmac_regs.h
  * Define and use controller-specific dma_slave data
  * Fix up a few outdated comments
  * Define hardware registers as structs (doesn't generate better
    code, unfortunately, but it looks nicer.)
  * Get number of channels from platform_data instead of hardcoding it
    based on CONFIG_WHATEVER_CPU.
  * Give slave clients exclusive access to the channel

Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>,
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/avr32/mach-at32ap/at32ap700x.c        |   27 +-
 drivers/dma/Kconfig                        |    9 +
 drivers/dma/Makefile                       |    1 +
 drivers/dma/dw_dmac.c                      | 1122 ++++++++++++++++++++++++++++
 drivers/dma/dw_dmac_regs.h                 |  225 ++++++
 include/asm-avr32/arch-at32ap/at32ap700x.h |   16 +
 include/linux/dw_dmac.h                    |   62 ++
 7 files changed, 1449 insertions(+), 13 deletions(-)
 create mode 100644 drivers/dma/dw_dmac.c
 create mode 100644 drivers/dma/dw_dmac_regs.h
 create mode 100644 include/linux/dw_dmac.h

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 0f24b4f85c1..892e27e0d58 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -7,6 +7,7 @@
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/dw_dmac.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
@@ -599,6 +600,17 @@ static void __init genclk_init_parent(struct clk *clk)
 	clk->parent = parent;
 }
 
+static struct dw_dma_platform_data dw_dmac0_data = {
+	.nr_channels	= 3,
+};
+
+static struct resource dw_dmac0_resource[] = {
+	PBMEM(0xff200000),
+	IRQ(2),
+};
+DEFINE_DEV_DATA(dw_dmac, 0);
+DEV_CLK(hclk, dw_dmac0, hsb, 10);
+
 /* --------------------------------------------------------------------
  *  System peripherals
  * -------------------------------------------------------------------- */
@@ -705,17 +717,6 @@ static struct clk pico_clk = {
 	.users		= 1,
 };
 
-static struct resource dmaca0_resource[] = {
-	{
-		.start	= 0xff200000,
-		.end	= 0xff20ffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	IRQ(2),
-};
-DEFINE_DEV(dmaca, 0);
-DEV_CLK(hclk, dmaca0, hsb, 10);
-
 /* --------------------------------------------------------------------
  * HMATRIX
  * -------------------------------------------------------------------- */
@@ -828,7 +829,7 @@ void __init at32_add_system_devices(void)
 	platform_device_register(&at32_eic0_device);
 	platform_device_register(&smc0_device);
 	platform_device_register(&pdc_device);
-	platform_device_register(&dmaca0_device);
+	platform_device_register(&dw_dmac0_device);
 
 	platform_device_register(&at32_tcb0_device);
 	platform_device_register(&at32_tcb1_device);
@@ -1891,7 +1892,7 @@ struct clk *at32_clock_list[] = {
 	&smc0_mck,
 	&pdc_hclk,
 	&pdc_pclk,
-	&dmaca0_hclk,
+	&dw_dmac0_hclk,
 	&pico_clk,
 	&pio0_mck,
 	&pio1_mck,
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 4b6bd3d099c..cd303901eb5 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -38,6 +38,15 @@ config INTEL_IOP_ADMA
 	help
 	  Enable support for the Intel(R) IOP Series RAID engines.
 
+config DW_DMAC
+	tristate "Synopsys DesignWare AHB DMA support"
+	depends on AVR32
+	select DMA_ENGINE
+	default y if CPU_AT32AP7000
+	help
+	  Support the Synopsys DesignWare AHB DMA controller.  This
+	  can be integrated in chips such as the Atmel AT32ap7000.
+
 config FSL_DMA
 	bool "Freescale MPC85xx/MPC83xx DMA support"
 	depends on PPC
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 181e3646fbf..14f59527d4f 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -6,3 +6,4 @@ ioatdma-objs := ioat.o ioat_dma.o ioat_dca.o
 obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_MV_XOR) += mv_xor.o
+obj-$(CONFIG_DW_DMAC) += dw_dmac.o
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
new file mode 100644
index 00000000000..94df9177124
--- /dev/null
+++ b/drivers/dma/dw_dmac.c
@@ -0,0 +1,1122 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller (aka DMACA on
+ * AVR32 systems.)
+ *
+ * Copyright (C) 2007-2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "dw_dmac_regs.h"
+
+/*
+ * This supports the Synopsys "DesignWare AHB Central DMA Controller",
+ * (DW_ahb_dmac) which is used with various AMBA 2.0 systems (not all
+ * of which use ARM any more).  See the "Databook" from Synopsys for
+ * information beyond what licensees probably provide.
+ *
+ * The driver has currently been tested only with the Atmel AT32AP7000,
+ * which does not support descriptor writeback.
+ */
+
+/* NOTE:  DMS+SMS is system-specific. We should get this information
+ * from the platform code somehow.
+ */
+#define DWC_DEFAULT_CTLLO	(DWC_CTLL_DST_MSIZE(0)		\
+				| DWC_CTLL_SRC_MSIZE(0)		\
+				| DWC_CTLL_DMS(0)		\
+				| DWC_CTLL_SMS(1)		\
+				| DWC_CTLL_LLP_D_EN		\
+				| DWC_CTLL_LLP_S_EN)
+
+/*
+ * This is configuration-dependent and usually a funny size like 4095.
+ * Let's round it down to the nearest power of two.
+ *
+ * Note that this is a transfer count, i.e. if we transfer 32-bit
+ * words, we can do 8192 bytes per descriptor.
+ *
+ * This parameter is also system-specific.
+ */
+#define DWC_MAX_COUNT	2048U
+
+/*
+ * Number of descriptors to allocate for each channel. This should be
+ * made configurable somehow; preferably, the clients (at least the
+ * ones using slave transfers) should be able to give us a hint.
+ */
+#define NR_DESCS_PER_CHANNEL	64
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Because we're not relying on writeback from the controller (it may not
+ * even be configured into the core!) we don't need to use dma_pool.  These
+ * descriptors -- and associated data -- are cacheable.  We do need to make
+ * sure their dcache entries are written back before handing them off to
+ * the controller, though.
+ */
+
+static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
+{
+	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
+}
+
+static struct dw_desc *dwc_first_queued(struct dw_dma_chan *dwc)
+{
+	return list_entry(dwc->queue.next, struct dw_desc, desc_node);
+}
+
+static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc, *_desc;
+	struct dw_desc *ret = NULL;
+	unsigned int i = 0;
+
+	spin_lock_bh(&dwc->lock);
+	list_for_each_entry_safe(desc, _desc, &dwc->free_list, desc_node) {
+		if (async_tx_test_ack(&desc->txd)) {
+			list_del(&desc->desc_node);
+			ret = desc;
+			break;
+		}
+		dev_dbg(&dwc->chan.dev, "desc %p not ACKed\n", desc);
+		i++;
+	}
+	spin_unlock_bh(&dwc->lock);
+
+	dev_vdbg(&dwc->chan.dev, "scanned %u descriptors on freelist\n", i);
+
+	return ret;
+}
+
+static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	struct dw_desc	*child;
+
+	list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		dma_sync_single_for_cpu(dwc->chan.dev.parent,
+				child->txd.phys, sizeof(child->lli),
+				DMA_TO_DEVICE);
+	dma_sync_single_for_cpu(dwc->chan.dev.parent,
+			desc->txd.phys, sizeof(desc->lli),
+			DMA_TO_DEVICE);
+}
+
+/*
+ * Move a descriptor, including any children, to the free list.
+ * `desc' must not be on any lists.
+ */
+static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	if (desc) {
+		struct dw_desc *child;
+
+		dwc_sync_desc_for_cpu(dwc, desc);
+
+		spin_lock_bh(&dwc->lock);
+		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+			dev_vdbg(&dwc->chan.dev,
+					"moving child desc %p to freelist\n",
+					child);
+		list_splice_init(&desc->txd.tx_list, &dwc->free_list);
+		dev_vdbg(&dwc->chan.dev, "moving desc %p to freelist\n", desc);
+		list_add(&desc->desc_node, &dwc->free_list);
+		spin_unlock_bh(&dwc->lock);
+	}
+}
+
+/* Called with dwc->lock held and bh disabled */
+static dma_cookie_t
+dwc_assign_cookie(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	dma_cookie_t cookie = dwc->chan.cookie;
+
+	if (++cookie < 0)
+		cookie = 1;
+
+	dwc->chan.cookie = cookie;
+	desc->txd.cookie = cookie;
+
+	return cookie;
+}
+
+/*----------------------------------------------------------------------*/
+
+/* Called with dwc->lock held and bh disabled */
+static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
+{
+	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+
+	/* ASSERT:  channel is idle */
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(&dwc->chan.dev,
+			"BUG: Attempted to start non-idle channel\n");
+		dev_err(&dwc->chan.dev,
+			"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
+			channel_readl(dwc, SAR),
+			channel_readl(dwc, DAR),
+			channel_readl(dwc, LLP),
+			channel_readl(dwc, CTL_HI),
+			channel_readl(dwc, CTL_LO));
+
+		/* The tasklet will hopefully advance the queue... */
+		return;
+	}
+
+	channel_writel(dwc, LLP, first->txd.phys);
+	channel_writel(dwc, CTL_LO,
+			DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	channel_writel(dwc, CTL_HI, 0);
+	channel_set_bit(dw, CH_EN, dwc->mask);
+}
+
+/*----------------------------------------------------------------------*/
+
+static void
+dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	dma_async_tx_callback		callback;
+	void				*param;
+	struct dma_async_tx_descriptor	*txd = &desc->txd;
+
+	dev_vdbg(&dwc->chan.dev, "descriptor %u complete\n", txd->cookie);
+
+	dwc->completed = txd->cookie;
+	callback = txd->callback;
+	param = txd->callback_param;
+
+	dwc_sync_desc_for_cpu(dwc, desc);
+	list_splice_init(&txd->tx_list, &dwc->free_list);
+	list_move(&desc->desc_node, &dwc->free_list);
+
+	/*
+	 * We use dma_unmap_page() regardless of how the buffers were
+	 * mapped before they were submitted...
+	 */
+	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
+		dma_unmap_page(dwc->chan.dev.parent, desc->lli.dar, desc->len,
+				DMA_FROM_DEVICE);
+	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
+		dma_unmap_page(dwc->chan.dev.parent, desc->lli.sar, desc->len,
+				DMA_TO_DEVICE);
+
+	/*
+	 * The API requires that no submissions are done from a
+	 * callback, so we don't need to drop the lock here
+	 */
+	if (callback)
+		callback(param);
+}
+
+static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc, *_desc;
+	LIST_HEAD(list);
+
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(&dwc->chan.dev,
+			"BUG: XFER bit set, but channel not idle!\n");
+
+		/* Try to continue after resetting the channel... */
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+		while (dma_readl(dw, CH_EN) & dwc->mask)
+			cpu_relax();
+	}
+
+	/*
+	 * Submit queued descriptors ASAP, i.e. before we go through
+	 * the completed ones.
+	 */
+	if (!list_empty(&dwc->queue))
+		dwc_dostart(dwc, dwc_first_queued(dwc));
+	list_splice_init(&dwc->active_list, &list);
+	list_splice_init(&dwc->queue, &dwc->active_list);
+
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		dwc_descriptor_complete(dwc, desc);
+}
+
+static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	dma_addr_t llp;
+	struct dw_desc *desc, *_desc;
+	struct dw_desc *child;
+	u32 status_xfer;
+
+	/*
+	 * Clear block interrupt flag before scanning so that we don't
+	 * miss any, and read LLP before RAW_XFER to ensure it is
+	 * valid if we decide to scan the list.
+	 */
+	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
+	llp = channel_readl(dwc, LLP);
+	status_xfer = dma_readl(dw, RAW.XFER);
+
+	if (status_xfer & dwc->mask) {
+		/* Everything we've submitted is done */
+		dma_writel(dw, CLEAR.XFER, dwc->mask);
+		dwc_complete_all(dw, dwc);
+		return;
+	}
+
+	dev_vdbg(&dwc->chan.dev, "scan_descriptors: llp=0x%x\n", llp);
+
+	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
+		if (desc->lli.llp == llp)
+			/* This one is currently in progress */
+			return;
+
+		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+			if (child->lli.llp == llp)
+				/* Currently in progress */
+				return;
+
+		/*
+		 * No descriptors so far seem to be in progress, i.e.
+		 * this one must be done.
+		 */
+		dwc_descriptor_complete(dwc, desc);
+	}
+
+	dev_err(&dwc->chan.dev,
+		"BUG: All descriptors done, but channel not idle!\n");
+
+	/* Try to continue after resetting the channel... */
+	channel_clear_bit(dw, CH_EN, dwc->mask);
+	while (dma_readl(dw, CH_EN) & dwc->mask)
+		cpu_relax();
+
+	if (!list_empty(&dwc->queue)) {
+		dwc_dostart(dwc, dwc_first_queued(dwc));
+		list_splice_init(&dwc->queue, &dwc->active_list);
+	}
+}
+
+static void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
+{
+	dev_printk(KERN_CRIT, &dwc->chan.dev,
+			"  desc: s0x%x d0x%x l0x%x c0x%x:%x\n",
+			lli->sar, lli->dar, lli->llp,
+			lli->ctlhi, lli->ctllo);
+}
+
+static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	struct dw_desc *bad_desc;
+	struct dw_desc *child;
+
+	dwc_scan_descriptors(dw, dwc);
+
+	/*
+	 * The descriptor currently at the head of the active list is
+	 * borked. Since we don't have any way to report errors, we'll
+	 * just have to scream loudly and try to carry on.
+	 */
+	bad_desc = dwc_first_active(dwc);
+	list_del_init(&bad_desc->desc_node);
+	list_splice_init(&dwc->queue, dwc->active_list.prev);
+
+	/* Clear the error flag and try to restart the controller */
+	dma_writel(dw, CLEAR.ERROR, dwc->mask);
+	if (!list_empty(&dwc->active_list))
+		dwc_dostart(dwc, dwc_first_active(dwc));
+
+	/*
+	 * KERN_CRITICAL may seem harsh, but since this only happens
+	 * when someone submits a bad physical address in a
+	 * descriptor, we should consider ourselves lucky that the
+	 * controller flagged an error instead of scribbling over
+	 * random memory locations.
+	 */
+	dev_printk(KERN_CRIT, &dwc->chan.dev,
+			"Bad descriptor submitted for DMA!\n");
+	dev_printk(KERN_CRIT, &dwc->chan.dev,
+			"  cookie: %d\n", bad_desc->txd.cookie);
+	dwc_dump_lli(dwc, &bad_desc->lli);
+	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+		dwc_dump_lli(dwc, &child->lli);
+
+	/* Pretend the descriptor completed successfully */
+	dwc_descriptor_complete(dwc, bad_desc);
+}
+
+static void dw_dma_tasklet(unsigned long data)
+{
+	struct dw_dma *dw = (struct dw_dma *)data;
+	struct dw_dma_chan *dwc;
+	u32 status_block;
+	u32 status_xfer;
+	u32 status_err;
+	int i;
+
+	status_block = dma_readl(dw, RAW.BLOCK);
+	status_xfer = dma_readl(dw, RAW.BLOCK);
+	status_err = dma_readl(dw, RAW.ERROR);
+
+	dev_vdbg(dw->dma.dev, "tasklet: status_block=%x status_err=%x\n",
+			status_block, status_err);
+
+	for (i = 0; i < dw->dma.chancnt; i++) {
+		dwc = &dw->chan[i];
+		spin_lock(&dwc->lock);
+		if (status_err & (1 << i))
+			dwc_handle_error(dw, dwc);
+		else if ((status_block | status_xfer) & (1 << i))
+			dwc_scan_descriptors(dw, dwc);
+		spin_unlock(&dwc->lock);
+	}
+
+	/*
+	 * Re-enable interrupts. Block Complete interrupts are only
+	 * enabled if the INT_EN bit in the descriptor is set. This
+	 * will trigger a scan before the whole list is done.
+	 */
+	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
+}
+
+static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
+{
+	struct dw_dma *dw = dev_id;
+	u32 status;
+
+	dev_vdbg(dw->dma.dev, "interrupt: status=0x%x\n",
+			dma_readl(dw, STATUS_INT));
+
+	/*
+	 * Just disable the interrupts. We'll turn them back on in the
+	 * softirq handler.
+	 */
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	status = dma_readl(dw, STATUS_INT);
+	if (status) {
+		dev_err(dw->dma.dev,
+			"BUG: Unexpected interrupts pending: 0x%x\n",
+			status);
+
+		/* Try to recover */
+		channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1);
+	}
+
+	tasklet_schedule(&dw->tasklet);
+
+	return IRQ_HANDLED;
+}
+
+/*----------------------------------------------------------------------*/
+
+static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct dw_desc		*desc = txd_to_dw_desc(tx);
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(tx->chan);
+	dma_cookie_t		cookie;
+
+	spin_lock_bh(&dwc->lock);
+	cookie = dwc_assign_cookie(dwc, desc);
+
+	/*
+	 * REVISIT: We should attempt to chain as many descriptors as
+	 * possible, perhaps even appending to those already submitted
+	 * for DMA. But this is hard to do in a race-free manner.
+	 */
+	if (list_empty(&dwc->active_list)) {
+		dev_vdbg(&tx->chan->dev, "tx_submit: started %u\n",
+				desc->txd.cookie);
+		dwc_dostart(dwc, desc);
+		list_add_tail(&desc->desc_node, &dwc->active_list);
+	} else {
+		dev_vdbg(&tx->chan->dev, "tx_submit: queued %u\n",
+				desc->txd.cookie);
+
+		list_add_tail(&desc->desc_node, &dwc->queue);
+	}
+
+	spin_unlock_bh(&dwc->lock);
+
+	return cookie;
+}
+
+static struct dma_async_tx_descriptor *
+dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_desc		*desc;
+	struct dw_desc		*first;
+	struct dw_desc		*prev;
+	size_t			xfer_count;
+	size_t			offset;
+	unsigned int		src_width;
+	unsigned int		dst_width;
+	u32			ctllo;
+
+	dev_vdbg(&chan->dev, "prep_dma_memcpy d0x%x s0x%x l0x%zx f0x%lx\n",
+			dest, src, len, flags);
+
+	if (unlikely(!len)) {
+		dev_dbg(&chan->dev, "prep_dma_memcpy: length is zero!\n");
+		return NULL;
+	}
+
+	/*
+	 * We can be a lot more clever here, but this should take care
+	 * of the most common optimization.
+	 */
+	if (!((src | dest  | len) & 3))
+		src_width = dst_width = 2;
+	else if (!((src | dest | len) & 1))
+		src_width = dst_width = 1;
+	else
+		src_width = dst_width = 0;
+
+	ctllo = DWC_DEFAULT_CTLLO
+			| DWC_CTLL_DST_WIDTH(dst_width)
+			| DWC_CTLL_SRC_WIDTH(src_width)
+			| DWC_CTLL_DST_INC
+			| DWC_CTLL_SRC_INC
+			| DWC_CTLL_FC_M2M;
+	prev = first = NULL;
+
+	for (offset = 0; offset < len; offset += xfer_count << src_width) {
+		xfer_count = min_t(size_t, (len - offset) >> src_width,
+				DWC_MAX_COUNT);
+
+		desc = dwc_desc_get(dwc);
+		if (!desc)
+			goto err_desc_get;
+
+		desc->lli.sar = src + offset;
+		desc->lli.dar = dest + offset;
+		desc->lli.ctllo = ctllo;
+		desc->lli.ctlhi = xfer_count;
+
+		if (!first) {
+			first = desc;
+		} else {
+			prev->lli.llp = desc->txd.phys;
+			dma_sync_single_for_device(chan->dev.parent,
+					prev->txd.phys, sizeof(prev->lli),
+					DMA_TO_DEVICE);
+			list_add_tail(&desc->desc_node,
+					&first->txd.tx_list);
+		}
+		prev = desc;
+	}
+
+
+	if (flags & DMA_PREP_INTERRUPT)
+		/* Trigger interrupt after last block */
+		prev->lli.ctllo |= DWC_CTLL_INT_EN;
+
+	prev->lli.llp = 0;
+	dma_sync_single_for_device(chan->dev.parent,
+			prev->txd.phys, sizeof(prev->lli),
+			DMA_TO_DEVICE);
+
+	first->txd.flags = flags;
+	first->len = len;
+
+	return &first->txd;
+
+err_desc_get:
+	dwc_desc_put(dwc, first);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_data_direction direction,
+		unsigned long flags)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma_slave	*dws = dwc->dws;
+	struct dw_desc		*prev;
+	struct dw_desc		*first;
+	u32			ctllo;
+	dma_addr_t		reg;
+	unsigned int		reg_width;
+	unsigned int		mem_width;
+	unsigned int		i;
+	struct scatterlist	*sg;
+	size_t			total_len = 0;
+
+	dev_vdbg(&chan->dev, "prep_dma_slave\n");
+
+	if (unlikely(!dws || !sg_len))
+		return NULL;
+
+	reg_width = dws->slave.reg_width;
+	prev = first = NULL;
+
+	sg_len = dma_map_sg(chan->dev.parent, sgl, sg_len, direction);
+
+	switch (direction) {
+	case DMA_TO_DEVICE:
+		ctllo = (DWC_DEFAULT_CTLLO
+				| DWC_CTLL_DST_WIDTH(reg_width)
+				| DWC_CTLL_DST_FIX
+				| DWC_CTLL_SRC_INC
+				| DWC_CTLL_FC_M2P);
+		reg = dws->slave.tx_reg;
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct dw_desc	*desc;
+			u32		len;
+			u32		mem;
+
+			desc = dwc_desc_get(dwc);
+			if (!desc) {
+				dev_err(&chan->dev,
+					"not enough descriptors available\n");
+				goto err_desc_get;
+			}
+
+			mem = sg_phys(sg);
+			len = sg_dma_len(sg);
+			mem_width = 2;
+			if (unlikely(mem & 3 || len & 3))
+				mem_width = 0;
+
+			desc->lli.sar = mem;
+			desc->lli.dar = reg;
+			desc->lli.ctllo = ctllo | DWC_CTLL_SRC_WIDTH(mem_width);
+			desc->lli.ctlhi = len >> mem_width;
+
+			if (!first) {
+				first = desc;
+			} else {
+				prev->lli.llp = desc->txd.phys;
+				dma_sync_single_for_device(chan->dev.parent,
+						prev->txd.phys,
+						sizeof(prev->lli),
+						DMA_TO_DEVICE);
+				list_add_tail(&desc->desc_node,
+						&first->txd.tx_list);
+			}
+			prev = desc;
+			total_len += len;
+		}
+		break;
+	case DMA_FROM_DEVICE:
+		ctllo = (DWC_DEFAULT_CTLLO
+				| DWC_CTLL_SRC_WIDTH(reg_width)
+				| DWC_CTLL_DST_INC
+				| DWC_CTLL_SRC_FIX
+				| DWC_CTLL_FC_P2M);
+
+		reg = dws->slave.rx_reg;
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct dw_desc	*desc;
+			u32		len;
+			u32		mem;
+
+			desc = dwc_desc_get(dwc);
+			if (!desc) {
+				dev_err(&chan->dev,
+					"not enough descriptors available\n");
+				goto err_desc_get;
+			}
+
+			mem = sg_phys(sg);
+			len = sg_dma_len(sg);
+			mem_width = 2;
+			if (unlikely(mem & 3 || len & 3))
+				mem_width = 0;
+
+			desc->lli.sar = reg;
+			desc->lli.dar = mem;
+			desc->lli.ctllo = ctllo | DWC_CTLL_DST_WIDTH(mem_width);
+			desc->lli.ctlhi = len >> reg_width;
+
+			if (!first) {
+				first = desc;
+			} else {
+				prev->lli.llp = desc->txd.phys;
+				dma_sync_single_for_device(chan->dev.parent,
+						prev->txd.phys,
+						sizeof(prev->lli),
+						DMA_TO_DEVICE);
+				list_add_tail(&desc->desc_node,
+						&first->txd.tx_list);
+			}
+			prev = desc;
+			total_len += len;
+		}
+		break;
+	default:
+		return NULL;
+	}
+
+	if (flags & DMA_PREP_INTERRUPT)
+		/* Trigger interrupt after last block */
+		prev->lli.ctllo |= DWC_CTLL_INT_EN;
+
+	prev->lli.llp = 0;
+	dma_sync_single_for_device(chan->dev.parent,
+			prev->txd.phys, sizeof(prev->lli),
+			DMA_TO_DEVICE);
+
+	first->len = total_len;
+
+	return &first->txd;
+
+err_desc_get:
+	dwc_desc_put(dwc, first);
+	return NULL;
+}
+
+static void dwc_terminate_all(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc, *_desc;
+	LIST_HEAD(list);
+
+	/*
+	 * This is only called when something went wrong elsewhere, so
+	 * we don't really care about the data. Just disable the
+	 * channel. We still have to poll the channel enable bit due
+	 * to AHB/HSB limitations.
+	 */
+	spin_lock_bh(&dwc->lock);
+
+	channel_clear_bit(dw, CH_EN, dwc->mask);
+
+	while (dma_readl(dw, CH_EN) & dwc->mask)
+		cpu_relax();
+
+	/* active_list entries will end up before queued entries */
+	list_splice_init(&dwc->queue, &list);
+	list_splice_init(&dwc->active_list, &list);
+
+	spin_unlock_bh(&dwc->lock);
+
+	/* Flush all pending and queued descriptors */
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		dwc_descriptor_complete(dwc, desc);
+}
+
+static enum dma_status
+dwc_is_tx_complete(struct dma_chan *chan,
+		dma_cookie_t cookie,
+		dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	dma_cookie_t		last_used;
+	dma_cookie_t		last_complete;
+	int			ret;
+
+	last_complete = dwc->completed;
+	last_used = chan->cookie;
+
+	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	if (ret != DMA_SUCCESS) {
+		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+
+		last_complete = dwc->completed;
+		last_used = chan->cookie;
+
+		ret = dma_async_is_complete(cookie, last_complete, last_used);
+	}
+
+	if (done)
+		*done = last_complete;
+	if (used)
+		*used = last_used;
+
+	return ret;
+}
+
+static void dwc_issue_pending(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+
+	spin_lock_bh(&dwc->lock);
+	if (!list_empty(&dwc->queue))
+		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+	spin_unlock_bh(&dwc->lock);
+}
+
+static int dwc_alloc_chan_resources(struct dma_chan *chan,
+		struct dma_client *client)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc;
+	struct dma_slave	*slave;
+	struct dw_dma_slave	*dws;
+	int			i;
+	u32			cfghi;
+	u32			cfglo;
+
+	dev_vdbg(&chan->dev, "alloc_chan_resources\n");
+
+	/* Channels doing slave DMA can only handle one client. */
+	if (dwc->dws || client->slave) {
+		if (chan->client_count)
+			return -EBUSY;
+	}
+
+	/* ASSERT:  channel is idle */
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_dbg(&chan->dev, "DMA channel not idle?\n");
+		return -EIO;
+	}
+
+	dwc->completed = chan->cookie = 1;
+
+	cfghi = DWC_CFGH_FIFO_MODE;
+	cfglo = 0;
+
+	slave = client->slave;
+	if (slave) {
+		/*
+		 * We need controller-specific data to set up slave
+		 * transfers.
+		 */
+		BUG_ON(!slave->dma_dev || slave->dma_dev != dw->dma.dev);
+
+		dws = container_of(slave, struct dw_dma_slave, slave);
+
+		dwc->dws = dws;
+		cfghi = dws->cfg_hi;
+		cfglo = dws->cfg_lo;
+	} else {
+		dwc->dws = NULL;
+	}
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+
+	/*
+	 * NOTE: some controllers may have additional features that we
+	 * need to initialize here, like "scatter-gather" (which
+	 * doesn't mean what you think it means), and status writeback.
+	 */
+
+	spin_lock_bh(&dwc->lock);
+	i = dwc->descs_allocated;
+	while (dwc->descs_allocated < NR_DESCS_PER_CHANNEL) {
+		spin_unlock_bh(&dwc->lock);
+
+		desc = kzalloc(sizeof(struct dw_desc), GFP_KERNEL);
+		if (!desc) {
+			dev_info(&chan->dev,
+				"only allocated %d descriptors\n", i);
+			spin_lock_bh(&dwc->lock);
+			break;
+		}
+
+		dma_async_tx_descriptor_init(&desc->txd, chan);
+		desc->txd.tx_submit = dwc_tx_submit;
+		desc->txd.flags = DMA_CTRL_ACK;
+		INIT_LIST_HEAD(&desc->txd.tx_list);
+		desc->txd.phys = dma_map_single(chan->dev.parent, &desc->lli,
+				sizeof(desc->lli), DMA_TO_DEVICE);
+		dwc_desc_put(dwc, desc);
+
+		spin_lock_bh(&dwc->lock);
+		i = ++dwc->descs_allocated;
+	}
+
+	/* Enable interrupts */
+	channel_set_bit(dw, MASK.XFER, dwc->mask);
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
+	channel_set_bit(dw, MASK.ERROR, dwc->mask);
+
+	spin_unlock_bh(&dwc->lock);
+
+	dev_dbg(&chan->dev,
+		"alloc_chan_resources allocated %d descriptors\n", i);
+
+	return i;
+}
+
+static void dwc_free_chan_resources(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc, *_desc;
+	LIST_HEAD(list);
+
+	dev_dbg(&chan->dev, "free_chan_resources (descs allocated=%u)\n",
+			dwc->descs_allocated);
+
+	/* ASSERT:  channel is idle */
+	BUG_ON(!list_empty(&dwc->active_list));
+	BUG_ON(!list_empty(&dwc->queue));
+	BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
+
+	spin_lock_bh(&dwc->lock);
+	list_splice_init(&dwc->free_list, &list);
+	dwc->descs_allocated = 0;
+	dwc->dws = NULL;
+
+	/* Disable interrupts */
+	channel_clear_bit(dw, MASK.XFER, dwc->mask);
+	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
+	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
+
+	spin_unlock_bh(&dwc->lock);
+
+	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
+		dev_vdbg(&chan->dev, "  freeing descriptor %p\n", desc);
+		dma_unmap_single(chan->dev.parent, desc->txd.phys,
+				sizeof(desc->lli), DMA_TO_DEVICE);
+		kfree(desc);
+	}
+
+	dev_vdbg(&chan->dev, "free_chan_resources done\n");
+}
+
+/*----------------------------------------------------------------------*/
+
+static void dw_dma_off(struct dw_dma *dw)
+{
+	dma_writel(dw, CFG, 0);
+
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
+		cpu_relax();
+}
+
+static int __init dw_probe(struct platform_device *pdev)
+{
+	struct dw_dma_platform_data *pdata;
+	struct resource		*io;
+	struct dw_dma		*dw;
+	size_t			size;
+	int			irq;
+	int			err;
+	int			i;
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
+		return -EINVAL;
+
+	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!io)
+		return -EINVAL;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	size = sizeof(struct dw_dma);
+	size += pdata->nr_channels * sizeof(struct dw_dma_chan);
+	dw = kzalloc(size, GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	if (!request_mem_region(io->start, DW_REGLEN, pdev->dev.driver->name)) {
+		err = -EBUSY;
+		goto err_kfree;
+	}
+
+	memset(dw, 0, sizeof *dw);
+
+	dw->regs = ioremap(io->start, DW_REGLEN);
+	if (!dw->regs) {
+		err = -ENOMEM;
+		goto err_release_r;
+	}
+
+	dw->clk = clk_get(&pdev->dev, "hclk");
+	if (IS_ERR(dw->clk)) {
+		err = PTR_ERR(dw->clk);
+		goto err_clk;
+	}
+	clk_enable(dw->clk);
+
+	/* force dma off, just in case */
+	dw_dma_off(dw);
+
+	err = request_irq(irq, dw_dma_interrupt, 0, "dw_dmac", dw);
+	if (err)
+		goto err_irq;
+
+	platform_set_drvdata(pdev, dw);
+
+	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
+
+	dw->all_chan_mask = (1 << pdata->nr_channels) - 1;
+
+	INIT_LIST_HEAD(&dw->dma.channels);
+	for (i = 0; i < pdata->nr_channels; i++, dw->dma.chancnt++) {
+		struct dw_dma_chan	*dwc = &dw->chan[i];
+
+		dwc->chan.device = &dw->dma;
+		dwc->chan.cookie = dwc->completed = 1;
+		dwc->chan.chan_id = i;
+		list_add_tail(&dwc->chan.device_node, &dw->dma.channels);
+
+		dwc->ch_regs = &__dw_regs(dw)->CHAN[i];
+		spin_lock_init(&dwc->lock);
+		dwc->mask = 1 << i;
+
+		INIT_LIST_HEAD(&dwc->active_list);
+		INIT_LIST_HEAD(&dwc->queue);
+		INIT_LIST_HEAD(&dwc->free_list);
+
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+	}
+
+	/* Clear/disable all interrupts on all channels. */
+	dma_writel(dw, CLEAR.XFER, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.BLOCK, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.SRC_TRAN, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.DST_TRAN, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.ERROR, dw->all_chan_mask);
+
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	dw->dma.dev = &pdev->dev;
+	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
+	dw->dma.device_free_chan_resources = dwc_free_chan_resources;
+
+	dw->dma.device_prep_dma_memcpy = dwc_prep_dma_memcpy;
+
+	dw->dma.device_prep_slave_sg = dwc_prep_slave_sg;
+	dw->dma.device_terminate_all = dwc_terminate_all;
+
+	dw->dma.device_is_tx_complete = dwc_is_tx_complete;
+	dw->dma.device_issue_pending = dwc_issue_pending;
+
+	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+
+	printk(KERN_INFO "%s: DesignWare DMA Controller, %d channels\n",
+			pdev->dev.bus_id, dw->dma.chancnt);
+
+	dma_async_device_register(&dw->dma);
+
+	return 0;
+
+err_irq:
+	clk_disable(dw->clk);
+	clk_put(dw->clk);
+err_clk:
+	iounmap(dw->regs);
+	dw->regs = NULL;
+err_release_r:
+	release_resource(io);
+err_kfree:
+	kfree(dw);
+	return err;
+}
+
+static int __exit dw_remove(struct platform_device *pdev)
+{
+	struct dw_dma		*dw = platform_get_drvdata(pdev);
+	struct dw_dma_chan	*dwc, *_dwc;
+	struct resource		*io;
+
+	dw_dma_off(dw);
+	dma_async_device_unregister(&dw->dma);
+
+	free_irq(platform_get_irq(pdev, 0), dw);
+	tasklet_kill(&dw->tasklet);
+
+	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
+			chan.device_node) {
+		list_del(&dwc->chan.device_node);
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+	}
+
+	clk_disable(dw->clk);
+	clk_put(dw->clk);
+
+	iounmap(dw->regs);
+	dw->regs = NULL;
+
+	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(io->start, DW_REGLEN);
+
+	kfree(dw);
+
+	return 0;
+}
+
+static void dw_shutdown(struct platform_device *pdev)
+{
+	struct dw_dma	*dw = platform_get_drvdata(pdev);
+
+	dw_dma_off(platform_get_drvdata(pdev));
+	clk_disable(dw->clk);
+}
+
+static int dw_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+{
+	struct dw_dma	*dw = platform_get_drvdata(pdev);
+
+	dw_dma_off(platform_get_drvdata(pdev));
+	clk_disable(dw->clk);
+	return 0;
+}
+
+static int dw_resume_early(struct platform_device *pdev)
+{
+	struct dw_dma	*dw = platform_get_drvdata(pdev);
+
+	clk_enable(dw->clk);
+	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+	return 0;
+
+}
+
+static struct platform_driver dw_driver = {
+	.remove		= __exit_p(dw_remove),
+	.shutdown	= dw_shutdown,
+	.suspend_late	= dw_suspend_late,
+	.resume_early	= dw_resume_early,
+	.driver = {
+		.name	= "dw_dmac",
+	},
+};
+
+static int __init dw_init(void)
+{
+	return platform_driver_probe(&dw_driver, dw_probe);
+}
+module_init(dw_init);
+
+static void __exit dw_exit(void)
+{
+	platform_driver_unregister(&dw_driver);
+}
+module_exit(dw_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller driver");
+MODULE_AUTHOR("Haavard Skinnemoen <haavard.skinnemoen@atmel.com>");
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
new file mode 100644
index 00000000000..00fdd187bb0
--- /dev/null
+++ b/drivers/dma/dw_dmac_regs.h
@@ -0,0 +1,225 @@
+/*
+ * Driver for the Synopsys DesignWare AHB DMA Controller
+ *
+ * Copyright (C) 2005-2007 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/dw_dmac.h>
+
+#define DW_DMA_MAX_NR_CHANNELS	8
+
+/*
+ * Redefine this macro to handle differences between 32- and 64-bit
+ * addressing, big vs. little endian, etc.
+ */
+#define DW_REG(name)		u32 name; u32 __pad_##name
+
+/* Hardware register definitions. */
+struct dw_dma_chan_regs {
+	DW_REG(SAR);		/* Source Address Register */
+	DW_REG(DAR);		/* Destination Address Register */
+	DW_REG(LLP);		/* Linked List Pointer */
+	u32	CTL_LO;		/* Control Register Low */
+	u32	CTL_HI;		/* Control Register High */
+	DW_REG(SSTAT);
+	DW_REG(DSTAT);
+	DW_REG(SSTATAR);
+	DW_REG(DSTATAR);
+	u32	CFG_LO;		/* Configuration Register Low */
+	u32	CFG_HI;		/* Configuration Register High */
+	DW_REG(SGR);
+	DW_REG(DSR);
+};
+
+struct dw_dma_irq_regs {
+	DW_REG(XFER);
+	DW_REG(BLOCK);
+	DW_REG(SRC_TRAN);
+	DW_REG(DST_TRAN);
+	DW_REG(ERROR);
+};
+
+struct dw_dma_regs {
+	/* per-channel registers */
+	struct dw_dma_chan_regs	CHAN[DW_DMA_MAX_NR_CHANNELS];
+
+	/* irq handling */
+	struct dw_dma_irq_regs	RAW;		/* r */
+	struct dw_dma_irq_regs	STATUS;		/* r (raw & mask) */
+	struct dw_dma_irq_regs	MASK;		/* rw (set = irq enabled) */
+	struct dw_dma_irq_regs	CLEAR;		/* w (ack, affects "raw") */
+
+	DW_REG(STATUS_INT);			/* r */
+
+	/* software handshaking */
+	DW_REG(REQ_SRC);
+	DW_REG(REQ_DST);
+	DW_REG(SGL_REQ_SRC);
+	DW_REG(SGL_REQ_DST);
+	DW_REG(LAST_SRC);
+	DW_REG(LAST_DST);
+
+	/* miscellaneous */
+	DW_REG(CFG);
+	DW_REG(CH_EN);
+	DW_REG(ID);
+	DW_REG(TEST);
+
+	/* optional encoded params, 0x3c8..0x3 */
+};
+
+/* Bitfields in CTL_LO */
+#define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
+#define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
+#define DWC_CTLL_SRC_WIDTH(n)	((n)<<4)
+#define DWC_CTLL_DST_INC	(0<<7)		/* DAR update/not */
+#define DWC_CTLL_DST_DEC	(1<<7)
+#define DWC_CTLL_DST_FIX	(2<<7)
+#define DWC_CTLL_SRC_INC	(0<<7)		/* SAR update/not */
+#define DWC_CTLL_SRC_DEC	(1<<9)
+#define DWC_CTLL_SRC_FIX	(2<<9)
+#define DWC_CTLL_DST_MSIZE(n)	((n)<<11)	/* burst, #elements */
+#define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
+#define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
+#define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
+#define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
+#define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
+#define DWC_CTLL_FC_P2P		(3 << 20)	/* periph-to-periph */
+/* plus 4 transfer types for peripheral-as-flow-controller */
+#define DWC_CTLL_DMS(n)		((n)<<23)	/* dst master select */
+#define DWC_CTLL_SMS(n)		((n)<<25)	/* src master select */
+#define DWC_CTLL_LLP_D_EN	(1 << 27)	/* dest block chain */
+#define DWC_CTLL_LLP_S_EN	(1 << 28)	/* src block chain */
+
+/* Bitfields in CTL_HI */
+#define DWC_CTLH_DONE		0x00001000
+#define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
+
+/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
+#define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
+#define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
+#define DWC_CFGL_HS_SRC		(1 << 11)	/* handshake w/src */
+#define DWC_CFGL_MAX_BURST(x)	((x) << 20)
+#define DWC_CFGL_RELOAD_SAR	(1 << 30)
+#define DWC_CFGL_RELOAD_DAR	(1 << 31)
+
+/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGH_DS_UPD_EN	(1 << 5)
+#define DWC_CFGH_SS_UPD_EN	(1 << 6)
+
+/* Bitfields in SGR */
+#define DWC_SGR_SGI(x)		((x) << 0)
+#define DWC_SGR_SGC(x)		((x) << 20)
+
+/* Bitfields in DSR */
+#define DWC_DSR_DSI(x)		((x) << 0)
+#define DWC_DSR_DSC(x)		((x) << 20)
+
+/* Bitfields in CFG */
+#define DW_CFG_DMA_EN		(1 << 0)
+
+#define DW_REGLEN		0x400
+
+struct dw_dma_chan {
+	struct dma_chan		chan;
+	void __iomem		*ch_regs;
+	u8			mask;
+
+	spinlock_t		lock;
+
+	/* these other elements are all protected by lock */
+	dma_cookie_t		completed;
+	struct list_head	active_list;
+	struct list_head	queue;
+	struct list_head	free_list;
+
+	struct dw_dma_slave	*dws;
+
+	unsigned int		descs_allocated;
+};
+
+static inline struct dw_dma_chan_regs __iomem *
+__dwc_regs(struct dw_dma_chan *dwc)
+{
+	return dwc->ch_regs;
+}
+
+#define channel_readl(dwc, name) \
+	__raw_readl(&(__dwc_regs(dwc)->name))
+#define channel_writel(dwc, name, val) \
+	__raw_writel((val), &(__dwc_regs(dwc)->name))
+
+static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct dw_dma_chan, chan);
+}
+
+
+struct dw_dma {
+	struct dma_device	dma;
+	void __iomem		*regs;
+	struct tasklet_struct	tasklet;
+	struct clk		*clk;
+
+	u8			all_chan_mask;
+
+	struct dw_dma_chan	chan[0];
+};
+
+static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
+{
+	return dw->regs;
+}
+
+#define dma_readl(dw, name) \
+	__raw_readl(&(__dw_regs(dw)->name))
+#define dma_writel(dw, name, val) \
+	__raw_writel((val), &(__dw_regs(dw)->name))
+
+#define channel_set_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | (mask))
+#define channel_clear_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | 0)
+
+static inline struct dw_dma *to_dw_dma(struct dma_device *ddev)
+{
+	return container_of(ddev, struct dw_dma, dma);
+}
+
+/* LLI == Linked List Item; a.k.a. DMA block descriptor */
+struct dw_lli {
+	/* values that are not changed by hardware */
+	dma_addr_t	sar;
+	dma_addr_t	dar;
+	dma_addr_t	llp;		/* chain to next lli */
+	u32		ctllo;
+	/* values that may get written back: */
+	u32		ctlhi;
+	/* sstat and dstat can snapshot peripheral register state.
+	 * silicon config may discard either or both...
+	 */
+	u32		sstat;
+	u32		dstat;
+};
+
+struct dw_desc {
+	/* FIRST values the hardware uses */
+	struct dw_lli			lli;
+
+	/* THEN values for driver housekeeping */
+	struct list_head		desc_node;
+	struct dma_async_tx_descriptor	txd;
+	size_t				len;
+};
+
+static inline struct dw_desc *
+txd_to_dw_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct dw_desc, txd);
+}
diff --git a/include/asm-avr32/arch-at32ap/at32ap700x.h b/include/asm-avr32/arch-at32ap/at32ap700x.h
index 31e48b0e732..d18a3053be0 100644
--- a/include/asm-avr32/arch-at32ap/at32ap700x.h
+++ b/include/asm-avr32/arch-at32ap/at32ap700x.h
@@ -30,4 +30,20 @@
 #define GPIO_PIN_PD(N)	(GPIO_PIOD_BASE + (N))
 #define GPIO_PIN_PE(N)	(GPIO_PIOE_BASE + (N))
 
+
+/*
+ * DMAC peripheral hardware handshaking interfaces, used with dw_dmac
+ */
+#define DMAC_MCI_RX		0
+#define DMAC_MCI_TX		1
+#define DMAC_DAC_TX		2
+#define DMAC_AC97_A_RX		3
+#define DMAC_AC97_A_TX		4
+#define DMAC_AC97_B_RX		5
+#define DMAC_AC97_B_TX		6
+#define DMAC_DMAREQ_0		7
+#define DMAC_DMAREQ_1		8
+#define DMAC_DMAREQ_2		9
+#define DMAC_DMAREQ_3		10
+
 #endif /* __ASM_ARCH_AT32AP700X_H__ */
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
new file mode 100644
index 00000000000..04d217b442b
--- /dev/null
+++ b/include/linux/dw_dmac.h
@@ -0,0 +1,62 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller (aka DMACA on
+ * AVR32 systems.)
+ *
+ * Copyright (C) 2007 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef DW_DMAC_H
+#define DW_DMAC_H
+
+#include <linux/dmaengine.h>
+
+/**
+ * struct dw_dma_platform_data - Controller configuration parameters
+ * @nr_channels: Number of channels supported by hardware (max 8)
+ */
+struct dw_dma_platform_data {
+	unsigned int	nr_channels;
+};
+
+/**
+ * struct dw_dma_slave - Controller-specific information about a slave
+ * @slave: Generic information about the slave
+ * @ctl_lo: Platform-specific initializer for the CTL_LO register
+ * @cfg_hi: Platform-specific initializer for the CFG_HI register
+ * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ */
+struct dw_dma_slave {
+	struct dma_slave	slave;
+	u32			cfg_hi;
+	u32			cfg_lo;
+};
+
+/* Platform-configurable bits in CFG_HI */
+#define DWC_CFGH_FCMODE		(1 << 0)
+#define DWC_CFGH_FIFO_MODE	(1 << 1)
+#define DWC_CFGH_PROTCTL(x)	((x) << 2)
+#define DWC_CFGH_SRC_PER(x)	((x) << 7)
+#define DWC_CFGH_DST_PER(x)	((x) << 11)
+
+/* Platform-configurable bits in CFG_LO */
+#define DWC_CFGL_PRIO(x)	((x) << 5)	/* priority */
+#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
+#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
+#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
+#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
+#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
+#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
+#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
+#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
+#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
+#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
+
+static inline struct dw_dma_slave *to_dw_dma_slave(struct dma_slave *slave)
+{
+	return container_of(slave, struct dw_dma_slave, slave);
+}
+
+#endif /* DW_DMAC_H */
-- 
cgit v1.2.3-70-g09d2


From 7d2be0749a59096a334c94dc48f43294193cb8ed Mon Sep 17 00:00:00 2001
From: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Date: Mon, 30 Jun 2008 18:35:03 +0200
Subject: atmel-mci: Driver for Atmel on-chip MMC controllers

This is a driver for the MMC controller on the AP7000 chips from
Atmel. It should in theory work on AT91 systems too with some
tweaking, but since the DMA interface is quite different, it's not
entirely clear if it's worth merging this with the at91_mci driver.

This driver has been around for a while in BSPs and kernel sources
provided by Atmel, but this particular version uses the generic DMA
Engine framework (with the slave extensions) instead of an
avr32-only DMA controller framework.

This driver can also use PIO transfers when no DMA channels are
available, and for transfers where using DMA may be difficult or
impractical for some reason (e.g. the DMA setup overhead is usually
not worth it for very short transfers, and badly aligned buffers or
lengths are difficult to handle.)

Currently, the driver only support PIO transfers. DMA support has been
split out to a separate patch to hopefully make it easier to review.

The driver has been tested using mmc-block and ext3fs on several SD,
SDHC and MMC+ cards. Reads and writes work fine, with read transfer
rates up to 3.5 MiB/s on fast cards with debugging disabled.

The driver has also been tested using the mmc_test module on the same
cards. All tests except 7, 9, 15 and 17 succeed. The first two are
unsupported by all the cards I have, so I don't know if the driver
handles this correctly. The last two fail because the hardware flags a
Data CRC Error instead of a Data Timeout error. I'm not sure how to deal
with that.

Documentation for this controller can be found in many data sheets from
Atmel, including the AT32AP7000 data sheet which can be found here:

http://www.atmel.com/dyn/products/datasheets.asp?family_id=682

Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Signed-off-by: Pierre Ossman <drzeus@drzeus.cx>
---
 arch/avr32/boards/atngw100/setup.c      |   7 +
 arch/avr32/boards/atstk1000/atstk1002.c |   3 +
 arch/avr32/mach-at32ap/at32ap700x.c     |  30 +-
 drivers/mmc/host/Kconfig                |  10 +
 drivers/mmc/host/Makefile               |   1 +
 drivers/mmc/host/atmel-mci-regs.h       |  91 +++
 drivers/mmc/host/atmel-mci.c            | 981 ++++++++++++++++++++++++++++++++
 include/asm-avr32/arch-at32ap/board.h   |   6 +-
 include/asm-avr32/atmel-mci.h           |   9 +
 9 files changed, 1132 insertions(+), 6 deletions(-)
 create mode 100644 drivers/mmc/host/atmel-mci-regs.h
 create mode 100644 drivers/mmc/host/atmel-mci.c
 create mode 100644 include/asm-avr32/atmel-mci.h

(limited to 'include/asm-avr32/arch-at32ap')

diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c
index a51bb9fb3c8..c7fe94d03a1 100644
--- a/arch/avr32/boards/atngw100/setup.c
+++ b/arch/avr32/boards/atngw100/setup.c
@@ -19,6 +19,7 @@
 #include <linux/leds.h>
 #include <linux/spi/spi.h>
 
+#include <asm/atmel-mci.h>
 #include <asm/io.h>
 #include <asm/setup.h>
 
@@ -51,6 +52,11 @@ static struct spi_board_info spi0_board_info[] __initdata = {
 	},
 };
 
+static struct mci_platform_data __initdata mci0_data = {
+	.detect_pin	= GPIO_PIN_PC(25),
+	.wp_pin		= GPIO_PIN_PE(0),
+};
+
 /*
  * The next two functions should go away as the boot loader is
  * supposed to initialize the macb address registers with a valid
@@ -170,6 +176,7 @@ static int __init atngw100_init(void)
 	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
 
 	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
+	at32_add_device_mci(0, &mci0_data);
 	at32_add_device_usba(0, NULL);
 
 	for (i = 0; i < ARRAY_SIZE(ngw_leds); i++) {
diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
index 86b363c1c25..e11659b732f 100644
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ b/arch/avr32/boards/atstk1000/atstk1002.c
@@ -234,6 +234,9 @@ static int __init atstk1002_init(void)
 #ifdef CONFIG_BOARD_ATSTK100X_SPI1
 	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
 #endif
+#ifndef CONFIG_BOARD_ATSTK1002_SW2_CUSTOM
+	at32_add_device_mci(0, NULL);
+#endif
 #ifdef CONFIG_BOARD_ATSTK1002_SW5_CUSTOM
 	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
 #else
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 07b21b121ee..021d5121718 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -14,6 +14,7 @@
 #include <linux/spi/spi.h>
 #include <linux/usb/atmel_usba_udc.h>
 
+#include <asm/atmel-mci.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
@@ -1278,20 +1279,32 @@ static struct clk atmel_mci0_pclk = {
 	.index		= 9,
 };
 
-struct platform_device *__init at32_add_device_mci(unsigned int id)
+struct platform_device *__init
+at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 {
-	struct platform_device *pdev;
+	struct mci_platform_data	_data;
+	struct platform_device		*pdev;
+	struct dw_dma_slave		*dws;
 
 	if (id != 0)
 		return NULL;
 
 	pdev = platform_device_alloc("atmel_mci", id);
 	if (!pdev)
-		return NULL;
+		goto fail;
 
 	if (platform_device_add_resources(pdev, atmel_mci0_resource,
 				ARRAY_SIZE(atmel_mci0_resource)))
-		goto err_add_resources;
+		goto fail;
+
+	if (!data) {
+		data = &_data;
+		memset(data, 0, sizeof(struct mci_platform_data));
+	}
+
+	if (platform_device_add_data(pdev, data,
+				sizeof(struct mci_platform_data)))
+		goto fail;
 
 	select_peripheral(PA(10), PERIPH_A, 0);	/* CLK	 */
 	select_peripheral(PA(11), PERIPH_A, 0);	/* CMD	 */
@@ -1300,12 +1313,19 @@ struct platform_device *__init at32_add_device_mci(unsigned int id)
 	select_peripheral(PA(14), PERIPH_A, 0);	/* DATA2 */
 	select_peripheral(PA(15), PERIPH_A, 0);	/* DATA3 */
 
+	if (data) {
+		if (data->detect_pin != GPIO_PIN_NONE)
+			at32_select_gpio(data->detect_pin, 0);
+		if (data->wp_pin != GPIO_PIN_NONE)
+			at32_select_gpio(data->wp_pin, 0);
+	}
+
 	atmel_mci0_pclk.dev = &pdev->dev;
 
 	platform_device_add(pdev);
 	return pdev;
 
-err_add_resources:
+fail:
 	platform_device_put(pdev);
 	return NULL;
 }
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index dc88c03662a..198df423435 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -104,6 +104,16 @@ config MMC_AT91
 
 	  If unsure, say N.
 
+config MMC_ATMELMCI
+	tristate "Atmel Multimedia Card Interface support"
+	depends on AVR32
+	help
+	  This selects the Atmel Multimedia Card Interface driver. If
+	  you have an AT32 (AVR32) platform with a Multimedia Card
+	  slot, say Y or M here.
+
+	  If unsure, say N.
+
 config MMC_IMX
 	tristate "Motorola i.MX Multimedia Card Interface support"
 	depends on ARCH_IMX
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index b3e023bf8c7..2dc9ff23cfb 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_MMC_WBSD)		+= wbsd.o
 obj-$(CONFIG_MMC_AU1X)		+= au1xmmc.o
 obj-$(CONFIG_MMC_OMAP)		+= omap.o
 obj-$(CONFIG_MMC_AT91)		+= at91_mci.o
+obj-$(CONFIG_MMC_ATMELMCI)	+= atmel-mci.o
 obj-$(CONFIG_MMC_TIFM_SD)	+= tifm_sd.o
 obj-$(CONFIG_MMC_SPI)		+= mmc_spi.o
 obj-$(CONFIG_MMC_S3C)   	+= s3cmci.o
diff --git a/drivers/mmc/host/atmel-mci-regs.h b/drivers/mmc/host/atmel-mci-regs.h
new file mode 100644
index 00000000000..a9a5657706c
--- /dev/null
+++ b/drivers/mmc/host/atmel-mci-regs.h
@@ -0,0 +1,91 @@
+/*
+ * Atmel MultiMedia Card Interface driver
+ *
+ * Copyright (C) 2004-2006 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __DRIVERS_MMC_ATMEL_MCI_H__
+#define __DRIVERS_MMC_ATMEL_MCI_H__
+
+/* MCI Register Definitions */
+#define MCI_CR			0x0000	/* Control */
+# define MCI_CR_MCIEN		(  1 <<  0)	/* MCI Enable */
+# define MCI_CR_MCIDIS		(  1 <<  1)	/* MCI Disable */
+# define MCI_CR_SWRST		(  1 <<  7)	/* Software Reset */
+#define MCI_MR			0x0004	/* Mode */
+# define MCI_MR_CLKDIV(x)	((x) <<  0)	/* Clock Divider */
+# define MCI_MR_RDPROOF		(  1 << 11)	/* Read Proof */
+# define MCI_MR_WRPROOF		(  1 << 12)	/* Write Proof */
+#define MCI_DTOR		0x0008	/* Data Timeout */
+# define MCI_DTOCYC(x)		((x) <<  0)	/* Data Timeout Cycles */
+# define MCI_DTOMUL(x)		((x) <<  4)	/* Data Timeout Multiplier */
+#define MCI_SDCR		0x000c	/* SD Card / SDIO */
+# define MCI_SDCSEL_SLOT_A	(  0 <<  0)	/* Select SD slot A */
+# define MCI_SDCSEL_SLOT_B	(  1 <<  0)	/* Select SD slot A */
+# define MCI_SDCBUS_1BIT	(  0 <<  7)	/* 1-bit data bus */
+# define MCI_SDCBUS_4BIT	(  1 <<  7)	/* 4-bit data bus */
+#define MCI_ARGR		0x0010	/* Command Argument */
+#define MCI_CMDR		0x0014	/* Command */
+# define MCI_CMDR_CMDNB(x)	((x) <<  0)	/* Command Opcode */
+# define MCI_CMDR_RSPTYP_NONE	(  0 <<  6)	/* No response */
+# define MCI_CMDR_RSPTYP_48BIT	(  1 <<  6)	/* 48-bit response */
+# define MCI_CMDR_RSPTYP_136BIT	(  2 <<  6)	/* 136-bit response */
+# define MCI_CMDR_SPCMD_INIT	(  1 <<  8)	/* Initialization command */
+# define MCI_CMDR_SPCMD_SYNC	(  2 <<  8)	/* Synchronized command */
+# define MCI_CMDR_SPCMD_INT	(  4 <<  8)	/* Interrupt command */
+# define MCI_CMDR_SPCMD_INTRESP	(  5 <<  8)	/* Interrupt response */
+# define MCI_CMDR_OPDCMD	(  1 << 11)	/* Open Drain */
+# define MCI_CMDR_MAXLAT_5CYC	(  0 << 12)	/* Max latency 5 cycles */
+# define MCI_CMDR_MAXLAT_64CYC	(  1 << 12)	/* Max latency 64 cycles */
+# define MCI_CMDR_START_XFER	(  1 << 16)	/* Start data transfer */
+# define MCI_CMDR_STOP_XFER	(  2 << 16)	/* Stop data transfer */
+# define MCI_CMDR_TRDIR_WRITE	(  0 << 18)	/* Write data */
+# define MCI_CMDR_TRDIR_READ	(  1 << 18)	/* Read data */
+# define MCI_CMDR_BLOCK		(  0 << 19)	/* Single-block transfer */
+# define MCI_CMDR_MULTI_BLOCK	(  1 << 19)	/* Multi-block transfer */
+# define MCI_CMDR_STREAM	(  2 << 19)	/* MMC Stream transfer */
+# define MCI_CMDR_SDIO_BYTE	(  4 << 19)	/* SDIO Byte transfer */
+# define MCI_CMDR_SDIO_BLOCK	(  5 << 19)	/* SDIO Block transfer */
+# define MCI_CMDR_SDIO_SUSPEND	(  1 << 24)	/* SDIO Suspend Command */
+# define MCI_CMDR_SDIO_RESUME	(  2 << 24)	/* SDIO Resume Command */
+#define MCI_BLKR		0x0018	/* Block */
+# define MCI_BCNT(x)		((x) <<  0)	/* Data Block Count */
+# define MCI_BLKLEN(x)		((x) << 16)	/* Data Block Length */
+#define MCI_RSPR		0x0020	/* Response 0 */
+#define MCI_RSPR1		0x0024	/* Response 1 */
+#define MCI_RSPR2		0x0028	/* Response 2 */
+#define MCI_RSPR3		0x002c	/* Response 3 */
+#define MCI_RDR			0x0030	/* Receive Data */
+#define MCI_TDR			0x0034	/* Transmit Data */
+#define MCI_SR			0x0040	/* Status */
+#define MCI_IER			0x0044	/* Interrupt Enable */
+#define MCI_IDR			0x0048	/* Interrupt Disable */
+#define MCI_IMR			0x004c	/* Interrupt Mask */
+# define MCI_CMDRDY		(  1 <<   0)	/* Command Ready */
+# define MCI_RXRDY		(  1 <<   1)	/* Receiver Ready */
+# define MCI_TXRDY		(  1 <<   2)	/* Transmitter Ready */
+# define MCI_BLKE		(  1 <<   3)	/* Data Block Ended */
+# define MCI_DTIP		(  1 <<   4)	/* Data Transfer In Progress */
+# define MCI_NOTBUSY		(  1 <<   5)	/* Data Not Busy */
+# define MCI_SDIOIRQA		(  1 <<   8)	/* SDIO IRQ in slot A */
+# define MCI_SDIOIRQB		(  1 <<   9)	/* SDIO IRQ in slot B */
+# define MCI_RINDE		(  1 <<  16)	/* Response Index Error */
+# define MCI_RDIRE		(  1 <<  17)	/* Response Direction Error */
+# define MCI_RCRCE		(  1 <<  18)	/* Response CRC Error */
+# define MCI_RENDE		(  1 <<  19)	/* Response End Bit Error */
+# define MCI_RTOE		(  1 <<  20)	/* Response Time-Out Error */
+# define MCI_DCRCE		(  1 <<  21)	/* Data CRC Error */
+# define MCI_DTOE		(  1 <<  22)	/* Data Time-Out Error */
+# define MCI_OVRE		(  1 <<  30)	/* RX Overrun Error */
+# define MCI_UNRE		(  1 <<  31)	/* TX Underrun Error */
+
+/* Register access macros */
+#define mci_readl(port,reg)				\
+	__raw_readl((port)->regs + MCI_##reg)
+#define mci_writel(port,reg,value)			\
+	__raw_writel((value), (port)->regs + MCI_##reg)
+
+#endif /* __DRIVERS_MMC_ATMEL_MCI_H__ */
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
new file mode 100644
index 00000000000..25d5324ab7e
--- /dev/null
+++ b/drivers/mmc/host/atmel-mci.c
@@ -0,0 +1,981 @@
+/*
+ * Atmel MultiMedia Card Interface driver
+ *
+ * Copyright (C) 2004-2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/blkdev.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+
+#include <linux/mmc/host.h>
+
+#include <asm/atmel-mci.h>
+#include <asm/io.h>
+#include <asm/unaligned.h>
+
+#include <asm/arch/board.h>
+#include <asm/arch/gpio.h>
+
+#include "atmel-mci-regs.h"
+
+#define ATMCI_DATA_ERROR_FLAGS	(MCI_DCRCE | MCI_DTOE | MCI_OVRE | MCI_UNRE)
+
+enum {
+	EVENT_CMD_COMPLETE = 0,
+	EVENT_DATA_ERROR,
+	EVENT_DATA_COMPLETE,
+	EVENT_STOP_SENT,
+	EVENT_STOP_COMPLETE,
+	EVENT_XFER_COMPLETE,
+};
+
+struct atmel_mci {
+	struct mmc_host		*mmc;
+	void __iomem		*regs;
+
+	struct scatterlist	*sg;
+	unsigned int		pio_offset;
+
+	struct mmc_request	*mrq;
+	struct mmc_command	*cmd;
+	struct mmc_data		*data;
+
+	u32			cmd_status;
+	u32			data_status;
+	u32			stop_status;
+	u32			stop_cmdr;
+
+	u32			mode_reg;
+	u32			sdc_reg;
+
+	struct tasklet_struct	tasklet;
+	unsigned long		pending_events;
+	unsigned long		completed_events;
+
+	int			present;
+	int			detect_pin;
+	int			wp_pin;
+
+	/* For detect pin debouncing */
+	struct timer_list	detect_timer;
+
+	unsigned long		bus_hz;
+	unsigned long		mapbase;
+	struct clk		*mck;
+	struct platform_device	*pdev;
+};
+
+#define atmci_is_completed(host, event)				\
+	test_bit(event, &host->completed_events)
+#define atmci_test_and_clear_pending(host, event)		\
+	test_and_clear_bit(event, &host->pending_events)
+#define atmci_test_and_set_completed(host, event)		\
+	test_and_set_bit(event, &host->completed_events)
+#define atmci_set_completed(host, event)			\
+	set_bit(event, &host->completed_events)
+#define atmci_set_pending(host, event)				\
+	set_bit(event, &host->pending_events)
+#define atmci_clear_pending(host, event)			\
+	clear_bit(event, &host->pending_events)
+
+
+static void atmci_enable(struct atmel_mci *host)
+{
+	clk_enable(host->mck);
+	mci_writel(host, CR, MCI_CR_MCIEN);
+	mci_writel(host, MR, host->mode_reg);
+	mci_writel(host, SDCR, host->sdc_reg);
+}
+
+static void atmci_disable(struct atmel_mci *host)
+{
+	mci_writel(host, CR, MCI_CR_SWRST);
+
+	/* Stall until write is complete, then disable the bus clock */
+	mci_readl(host, SR);
+	clk_disable(host->mck);
+}
+
+static inline unsigned int ns_to_clocks(struct atmel_mci *host,
+					unsigned int ns)
+{
+	return (ns * (host->bus_hz / 1000000) + 999) / 1000;
+}
+
+static void atmci_set_timeout(struct atmel_mci *host,
+			      struct mmc_data *data)
+{
+	static unsigned	dtomul_to_shift[] = {
+		0, 4, 7, 8, 10, 12, 16, 20
+	};
+	unsigned	timeout;
+	unsigned	dtocyc;
+	unsigned	dtomul;
+
+	timeout = ns_to_clocks(host, data->timeout_ns) + data->timeout_clks;
+
+	for (dtomul = 0; dtomul < 8; dtomul++) {
+		unsigned shift = dtomul_to_shift[dtomul];
+		dtocyc = (timeout + (1 << shift) - 1) >> shift;
+		if (dtocyc < 15)
+			break;
+	}
+
+	if (dtomul >= 8) {
+		dtomul = 7;
+		dtocyc = 15;
+	}
+
+	dev_vdbg(&host->mmc->class_dev, "setting timeout to %u cycles\n",
+			dtocyc << dtomul_to_shift[dtomul]);
+	mci_writel(host, DTOR, (MCI_DTOMUL(dtomul) | MCI_DTOCYC(dtocyc)));
+}
+
+/*
+ * Return mask with command flags to be enabled for this command.
+ */
+static u32 atmci_prepare_command(struct mmc_host *mmc,
+				 struct mmc_command *cmd)
+{
+	struct mmc_data	*data;
+	u32		cmdr;
+
+	cmd->error = -EINPROGRESS;
+
+	cmdr = MCI_CMDR_CMDNB(cmd->opcode);
+
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		if (cmd->flags & MMC_RSP_136)
+			cmdr |= MCI_CMDR_RSPTYP_136BIT;
+		else
+			cmdr |= MCI_CMDR_RSPTYP_48BIT;
+	}
+
+	/*
+	 * This should really be MAXLAT_5 for CMD2 and ACMD41, but
+	 * it's too difficult to determine whether this is an ACMD or
+	 * not. Better make it 64.
+	 */
+	cmdr |= MCI_CMDR_MAXLAT_64CYC;
+
+	if (mmc->ios.bus_mode == MMC_BUSMODE_OPENDRAIN)
+		cmdr |= MCI_CMDR_OPDCMD;
+
+	data = cmd->data;
+	if (data) {
+		cmdr |= MCI_CMDR_START_XFER;
+		if (data->flags & MMC_DATA_STREAM)
+			cmdr |= MCI_CMDR_STREAM;
+		else if (data->blocks > 1)
+			cmdr |= MCI_CMDR_MULTI_BLOCK;
+		else
+			cmdr |= MCI_CMDR_BLOCK;
+
+		if (data->flags & MMC_DATA_READ)
+			cmdr |= MCI_CMDR_TRDIR_READ;
+	}
+
+	return cmdr;
+}
+
+static void atmci_start_command(struct atmel_mci *host,
+				struct mmc_command *cmd,
+				u32 cmd_flags)
+{
+	/* Must read host->cmd after testing event flags */
+	smp_rmb();
+	WARN_ON(host->cmd);
+	host->cmd = cmd;
+
+	dev_vdbg(&host->mmc->class_dev,
+			"start command: ARGR=0x%08x CMDR=0x%08x\n",
+			cmd->arg, cmd_flags);
+
+	mci_writel(host, ARGR, cmd->arg);
+	mci_writel(host, CMDR, cmd_flags);
+}
+
+static void send_stop_cmd(struct mmc_host *mmc, struct mmc_data *data)
+{
+	struct atmel_mci *host = mmc_priv(mmc);
+
+	atmci_start_command(host, data->stop, host->stop_cmdr);
+	mci_writel(host, IER, MCI_CMDRDY);
+}
+
+static void atmci_request_end(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct atmel_mci *host = mmc_priv(mmc);
+
+	WARN_ON(host->cmd || host->data);
+	host->mrq = NULL;
+
+	atmci_disable(host);
+
+	mmc_request_done(mmc, mrq);
+}
+
+/*
+ * Returns a mask of interrupt flags to be enabled after the whole
+ * request has been prepared.
+ */
+static u32 atmci_submit_data(struct mmc_host *mmc, struct mmc_data *data)
+{
+	struct atmel_mci	*host = mmc_priv(mmc);
+	u32			iflags;
+
+	data->error = -EINPROGRESS;
+
+	WARN_ON(host->data);
+	host->sg = NULL;
+	host->data = data;
+
+	mci_writel(host, BLKR, MCI_BCNT(data->blocks)
+			| MCI_BLKLEN(data->blksz));
+	dev_vdbg(&mmc->class_dev, "BLKR=0x%08x\n",
+			MCI_BCNT(data->blocks) | MCI_BLKLEN(data->blksz));
+
+	iflags = ATMCI_DATA_ERROR_FLAGS;
+	host->sg = data->sg;
+	host->pio_offset = 0;
+	if (data->flags & MMC_DATA_READ)
+		iflags |= MCI_RXRDY;
+	else
+		iflags |= MCI_TXRDY;
+
+	return iflags;
+}
+
+static void atmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct atmel_mci	*host = mmc_priv(mmc);
+	struct mmc_data		*data;
+	struct mmc_command	*cmd;
+	u32			iflags;
+	u32			cmdflags = 0;
+
+	iflags = mci_readl(host, IMR);
+	if (iflags)
+		dev_warn(&mmc->class_dev, "WARNING: IMR=0x%08x\n",
+				mci_readl(host, IMR));
+
+	WARN_ON(host->mrq != NULL);
+
+	/*
+	 * We may "know" the card is gone even though there's still an
+	 * electrical connection. If so, we really need to communicate
+	 * this to the MMC core since there won't be any more
+	 * interrupts as the card is completely removed. Otherwise,
+	 * the MMC core might believe the card is still there even
+	 * though the card was just removed very slowly.
+	 */
+	if (!host->present) {
+		mrq->cmd->error = -ENOMEDIUM;
+		mmc_request_done(mmc, mrq);
+		return;
+	}
+
+	host->mrq = mrq;
+	host->pending_events = 0;
+	host->completed_events = 0;
+
+	atmci_enable(host);
+
+	/* We don't support multiple blocks of weird lengths. */
+	data = mrq->data;
+	if (data) {
+		if (data->blocks > 1 && data->blksz & 3)
+			goto fail;
+		atmci_set_timeout(host, data);
+	}
+
+	iflags = MCI_CMDRDY;
+	cmd = mrq->cmd;
+	cmdflags = atmci_prepare_command(mmc, cmd);
+	atmci_start_command(host, cmd, cmdflags);
+
+	if (data)
+		iflags |= atmci_submit_data(mmc, data);
+
+	if (mrq->stop) {
+		host->stop_cmdr = atmci_prepare_command(mmc, mrq->stop);
+		host->stop_cmdr |= MCI_CMDR_STOP_XFER;
+		if (!(data->flags & MMC_DATA_WRITE))
+			host->stop_cmdr |= MCI_CMDR_TRDIR_READ;
+		if (data->flags & MMC_DATA_STREAM)
+			host->stop_cmdr |= MCI_CMDR_STREAM;
+		else
+			host->stop_cmdr |= MCI_CMDR_MULTI_BLOCK;
+	}
+
+	/*
+	 * We could have enabled interrupts earlier, but I suspect
+	 * that would open up a nice can of interesting race
+	 * conditions (e.g. command and data complete, but stop not
+	 * prepared yet.)
+	 */
+	mci_writel(host, IER, iflags);
+
+	return;
+
+fail:
+	atmci_disable(host);
+	host->mrq = NULL;
+	mrq->cmd->error = -EINVAL;
+	mmc_request_done(mmc, mrq);
+}
+
+static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct atmel_mci	*host = mmc_priv(mmc);
+
+	if (ios->clock) {
+		u32 clkdiv;
+
+		/* Set clock rate */
+		clkdiv = DIV_ROUND_UP(host->bus_hz, 2 * ios->clock) - 1;
+		if (clkdiv > 255) {
+			dev_warn(&mmc->class_dev,
+				"clock %u too slow; using %lu\n",
+				ios->clock, host->bus_hz / (2 * 256));
+			clkdiv = 255;
+		}
+
+		host->mode_reg = MCI_MR_CLKDIV(clkdiv) | MCI_MR_WRPROOF
+					| MCI_MR_RDPROOF;
+	}
+
+	switch (ios->bus_width) {
+	case MMC_BUS_WIDTH_1:
+		host->sdc_reg = 0;
+		break;
+	case MMC_BUS_WIDTH_4:
+		host->sdc_reg = MCI_SDCBUS_4BIT;
+		break;
+	}
+
+	switch (ios->power_mode) {
+	case MMC_POWER_ON:
+		/* Send init sequence (74 clock cycles) */
+		atmci_enable(host);
+		mci_writel(host, CMDR, MCI_CMDR_SPCMD_INIT);
+		while (!(mci_readl(host, SR) & MCI_CMDRDY))
+			cpu_relax();
+		atmci_disable(host);
+		break;
+	default:
+		/*
+		 * TODO: None of the currently available AVR32-based
+		 * boards allow MMC power to be turned off. Implement
+		 * power control when this can be tested properly.
+		 */
+		break;
+	}
+}
+
+static int atmci_get_ro(struct mmc_host *mmc)
+{
+	int			read_only = 0;
+	struct atmel_mci	*host = mmc_priv(mmc);
+
+	if (host->wp_pin >= 0) {
+		read_only = gpio_get_value(host->wp_pin);
+		dev_dbg(&mmc->class_dev, "card is %s\n",
+				read_only ? "read-only" : "read-write");
+	} else {
+		dev_dbg(&mmc->class_dev,
+			"no pin for checking read-only switch."
+			" Assuming write-enable.\n");
+	}
+
+	return read_only;
+}
+
+static struct mmc_host_ops atmci_ops = {
+	.request	= atmci_request,
+	.set_ios	= atmci_set_ios,
+	.get_ro		= atmci_get_ro,
+};
+
+static void atmci_command_complete(struct atmel_mci *host,
+			struct mmc_command *cmd, u32 status)
+{
+	/* Read the response from the card (up to 16 bytes) */
+	cmd->resp[0] = mci_readl(host, RSPR);
+	cmd->resp[1] = mci_readl(host, RSPR);
+	cmd->resp[2] = mci_readl(host, RSPR);
+	cmd->resp[3] = mci_readl(host, RSPR);
+
+	if (status & MCI_RTOE)
+		cmd->error = -ETIMEDOUT;
+	else if ((cmd->flags & MMC_RSP_CRC) && (status & MCI_RCRCE))
+		cmd->error = -EILSEQ;
+	else if (status & (MCI_RINDE | MCI_RDIRE | MCI_RENDE))
+		cmd->error = -EIO;
+	else
+		cmd->error = 0;
+
+	if (cmd->error) {
+		dev_dbg(&host->mmc->class_dev,
+			"command error: status=0x%08x\n", status);
+
+		if (cmd->data) {
+			host->data = NULL;
+			mci_writel(host, IDR, MCI_NOTBUSY
+					| MCI_TXRDY | MCI_RXRDY
+					| ATMCI_DATA_ERROR_FLAGS);
+		}
+	}
+}
+
+static void atmci_detect_change(unsigned long data)
+{
+	struct atmel_mci *host = (struct atmel_mci *)data;
+	struct mmc_request *mrq = host->mrq;
+	int present;
+
+	/*
+	 * atmci_remove() sets detect_pin to -1 before freeing the
+	 * interrupt. We must not re-enable the interrupt if it has
+	 * been freed.
+	 */
+	smp_rmb();
+	if (host->detect_pin < 0)
+		return;
+
+	enable_irq(gpio_to_irq(host->detect_pin));
+	present = !gpio_get_value(host->detect_pin);
+
+	dev_vdbg(&host->pdev->dev, "detect change: %d (was %d)\n",
+			present, host->present);
+
+	if (present != host->present) {
+		dev_dbg(&host->mmc->class_dev, "card %s\n",
+			present ? "inserted" : "removed");
+		host->present = present;
+
+		/* Reset controller if card is gone */
+		if (!present) {
+			mci_writel(host, CR, MCI_CR_SWRST);
+			mci_writel(host, IDR, ~0UL);
+			mci_writel(host, CR, MCI_CR_MCIEN);
+		}
+
+		/* Clean up queue if present */
+		if (mrq) {
+			/*
+			 * Reset controller to terminate any ongoing
+			 * commands or data transfers.
+			 */
+			mci_writel(host, CR, MCI_CR_SWRST);
+
+			if (!atmci_is_completed(host, EVENT_CMD_COMPLETE))
+				mrq->cmd->error = -ENOMEDIUM;
+
+			if (mrq->data && !atmci_is_completed(host,
+						EVENT_DATA_COMPLETE)) {
+				host->data = NULL;
+				mrq->data->error = -ENOMEDIUM;
+			}
+			if (mrq->stop && !atmci_is_completed(host,
+						EVENT_STOP_COMPLETE))
+				mrq->stop->error = -ENOMEDIUM;
+
+			host->cmd = NULL;
+			atmci_request_end(host->mmc, mrq);
+		}
+
+		mmc_detect_change(host->mmc, 0);
+	}
+}
+
+static void atmci_tasklet_func(unsigned long priv)
+{
+	struct mmc_host		*mmc = (struct mmc_host *)priv;
+	struct atmel_mci	*host = mmc_priv(mmc);
+	struct mmc_request	*mrq = host->mrq;
+	struct mmc_data		*data = host->data;
+
+	dev_vdbg(&mmc->class_dev,
+		"tasklet: pending/completed/mask %lx/%lx/%x\n",
+		host->pending_events, host->completed_events,
+		mci_readl(host, IMR));
+
+	if (atmci_test_and_clear_pending(host, EVENT_CMD_COMPLETE)) {
+		/*
+		 * host->cmd must be set to NULL before the interrupt
+		 * handler sees EVENT_CMD_COMPLETE
+		 */
+		host->cmd = NULL;
+		smp_wmb();
+		atmci_set_completed(host, EVENT_CMD_COMPLETE);
+		atmci_command_complete(host, mrq->cmd, host->cmd_status);
+
+		if (!mrq->cmd->error && mrq->stop
+				&& atmci_is_completed(host, EVENT_XFER_COMPLETE)
+				&& !atmci_test_and_set_completed(host,
+					EVENT_STOP_SENT))
+			send_stop_cmd(host->mmc, mrq->data);
+	}
+	if (atmci_test_and_clear_pending(host, EVENT_STOP_COMPLETE)) {
+		/*
+		 * host->cmd must be set to NULL before the interrupt
+		 * handler sees EVENT_STOP_COMPLETE
+		 */
+		host->cmd = NULL;
+		smp_wmb();
+		atmci_set_completed(host, EVENT_STOP_COMPLETE);
+		atmci_command_complete(host, mrq->stop, host->stop_status);
+	}
+	if (atmci_test_and_clear_pending(host, EVENT_DATA_ERROR)) {
+		u32 status = host->data_status;
+
+		dev_vdbg(&mmc->class_dev, "data error: status=%08x\n", status);
+
+		atmci_set_completed(host, EVENT_DATA_ERROR);
+		atmci_set_completed(host, EVENT_DATA_COMPLETE);
+
+		if (status & MCI_DTOE) {
+			dev_dbg(&mmc->class_dev,
+					"data timeout error\n");
+			data->error = -ETIMEDOUT;
+		} else if (status & MCI_DCRCE) {
+			dev_dbg(&mmc->class_dev, "data CRC error\n");
+			data->error = -EILSEQ;
+		} else {
+			dev_dbg(&mmc->class_dev,
+					"data FIFO error (status=%08x)\n",
+					status);
+			data->error = -EIO;
+		}
+
+		if (host->present && data->stop
+				&& atmci_is_completed(host, EVENT_CMD_COMPLETE)
+				&& !atmci_test_and_set_completed(
+					host, EVENT_STOP_SENT))
+			send_stop_cmd(host->mmc, data);
+
+		host->data = NULL;
+	}
+	if (atmci_test_and_clear_pending(host, EVENT_DATA_COMPLETE)) {
+		atmci_set_completed(host, EVENT_DATA_COMPLETE);
+
+		if (!atmci_is_completed(host, EVENT_DATA_ERROR)) {
+			data->bytes_xfered = data->blocks * data->blksz;
+			data->error = 0;
+		}
+
+		host->data = NULL;
+	}
+
+	if (host->mrq && !host->cmd && !host->data)
+		atmci_request_end(mmc, host->mrq);
+}
+
+static void atmci_read_data_pio(struct atmel_mci *host)
+{
+	struct scatterlist	*sg = host->sg;
+	void			*buf = sg_virt(sg);
+	unsigned int		offset = host->pio_offset;
+	struct mmc_data		*data = host->data;
+	u32			value;
+	u32			status;
+	unsigned int		nbytes = 0;
+
+	do {
+		value = mci_readl(host, RDR);
+		if (likely(offset + 4 <= sg->length)) {
+			put_unaligned(value, (u32 *)(buf + offset));
+
+			offset += 4;
+			nbytes += 4;
+
+			if (offset == sg->length) {
+				host->sg = sg = sg_next(sg);
+				if (!sg)
+					goto done;
+
+				offset = 0;
+				buf = sg_virt(sg);
+			}
+		} else {
+			unsigned int remaining = sg->length - offset;
+			memcpy(buf + offset, &value, remaining);
+			nbytes += remaining;
+
+			flush_dcache_page(sg_page(sg));
+			host->sg = sg = sg_next(sg);
+			if (!sg)
+				goto done;
+
+			offset = 4 - remaining;
+			buf = sg_virt(sg);
+			memcpy(buf, (u8 *)&value + remaining, offset);
+			nbytes += offset;
+		}
+
+		status = mci_readl(host, SR);
+		if (status & ATMCI_DATA_ERROR_FLAGS) {
+			mci_writel(host, IDR, (MCI_NOTBUSY | MCI_RXRDY
+						| ATMCI_DATA_ERROR_FLAGS));
+			host->data_status = status;
+			atmci_set_pending(host, EVENT_DATA_ERROR);
+			tasklet_schedule(&host->tasklet);
+			break;
+		}
+	} while (status & MCI_RXRDY);
+
+	host->pio_offset = offset;
+	data->bytes_xfered += nbytes;
+
+	return;
+
+done:
+	mci_writel(host, IDR, MCI_RXRDY);
+	mci_writel(host, IER, MCI_NOTBUSY);
+	data->bytes_xfered += nbytes;
+	atmci_set_completed(host, EVENT_XFER_COMPLETE);
+	if (data->stop && atmci_is_completed(host, EVENT_CMD_COMPLETE)
+			&& !atmci_test_and_set_completed(host, EVENT_STOP_SENT))
+		send_stop_cmd(host->mmc, data);
+}
+
+static void atmci_write_data_pio(struct atmel_mci *host)
+{
+	struct scatterlist	*sg = host->sg;
+	void			*buf = sg_virt(sg);
+	unsigned int		offset = host->pio_offset;
+	struct mmc_data		*data = host->data;
+	u32			value;
+	u32			status;
+	unsigned int		nbytes = 0;
+
+	do {
+		if (likely(offset + 4 <= sg->length)) {
+			value = get_unaligned((u32 *)(buf + offset));
+			mci_writel(host, TDR, value);
+
+			offset += 4;
+			nbytes += 4;
+			if (offset == sg->length) {
+				host->sg = sg = sg_next(sg);
+				if (!sg)
+					goto done;
+
+				offset = 0;
+				buf = sg_virt(sg);
+			}
+		} else {
+			unsigned int remaining = sg->length - offset;
+
+			value = 0;
+			memcpy(&value, buf + offset, remaining);
+			nbytes += remaining;
+
+			host->sg = sg = sg_next(sg);
+			if (!sg) {
+				mci_writel(host, TDR, value);
+				goto done;
+			}
+
+			offset = 4 - remaining;
+			buf = sg_virt(sg);
+			memcpy((u8 *)&value + remaining, buf, offset);
+			mci_writel(host, TDR, value);
+			nbytes += offset;
+		}
+
+		status = mci_readl(host, SR);
+		if (status & ATMCI_DATA_ERROR_FLAGS) {
+			mci_writel(host, IDR, (MCI_NOTBUSY | MCI_TXRDY
+						| ATMCI_DATA_ERROR_FLAGS));
+			host->data_status = status;
+			atmci_set_pending(host, EVENT_DATA_ERROR);
+			tasklet_schedule(&host->tasklet);
+			break;
+		}
+	} while (status & MCI_TXRDY);
+
+	host->pio_offset = offset;
+	data->bytes_xfered += nbytes;
+
+	return;
+
+done:
+	mci_writel(host, IDR, MCI_TXRDY);
+	mci_writel(host, IER, MCI_NOTBUSY);
+	data->bytes_xfered += nbytes;
+	atmci_set_completed(host, EVENT_XFER_COMPLETE);
+	if (data->stop && atmci_is_completed(host, EVENT_CMD_COMPLETE)
+			&& !atmci_test_and_set_completed(host, EVENT_STOP_SENT))
+		send_stop_cmd(host->mmc, data);
+}
+
+static void atmci_cmd_interrupt(struct mmc_host *mmc, u32 status)
+{
+	struct atmel_mci	*host = mmc_priv(mmc);
+
+	mci_writel(host, IDR, MCI_CMDRDY);
+
+	if (atmci_is_completed(host, EVENT_STOP_SENT)) {
+		host->stop_status = status;
+		atmci_set_pending(host, EVENT_STOP_COMPLETE);
+	} else {
+		host->cmd_status = status;
+		atmci_set_pending(host, EVENT_CMD_COMPLETE);
+	}
+
+	tasklet_schedule(&host->tasklet);
+}
+
+static irqreturn_t atmci_interrupt(int irq, void *dev_id)
+{
+	struct mmc_host		*mmc = dev_id;
+	struct atmel_mci	*host = mmc_priv(mmc);
+	u32			status, mask, pending;
+	unsigned int		pass_count = 0;
+
+	spin_lock(&mmc->lock);
+
+	do {
+		status = mci_readl(host, SR);
+		mask = mci_readl(host, IMR);
+		pending = status & mask;
+		if (!pending)
+			break;
+
+		if (pending & ATMCI_DATA_ERROR_FLAGS) {
+			mci_writel(host, IDR, ATMCI_DATA_ERROR_FLAGS
+					| MCI_RXRDY | MCI_TXRDY);
+			pending &= mci_readl(host, IMR);
+			host->data_status = status;
+			atmci_set_pending(host, EVENT_DATA_ERROR);
+			tasklet_schedule(&host->tasklet);
+		}
+		if (pending & MCI_NOTBUSY) {
+			mci_writel(host, IDR, (MCI_NOTBUSY
+					       | ATMCI_DATA_ERROR_FLAGS));
+			atmci_set_pending(host, EVENT_DATA_COMPLETE);
+			tasklet_schedule(&host->tasklet);
+		}
+		if (pending & MCI_RXRDY)
+			atmci_read_data_pio(host);
+		if (pending & MCI_TXRDY)
+			atmci_write_data_pio(host);
+
+		if (pending & MCI_CMDRDY)
+			atmci_cmd_interrupt(mmc, status);
+	} while (pass_count++ < 5);
+
+	spin_unlock(&mmc->lock);
+
+	return pass_count ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static irqreturn_t atmci_detect_interrupt(int irq, void *dev_id)
+{
+	struct mmc_host		*mmc = dev_id;
+	struct atmel_mci	*host = mmc_priv(mmc);
+
+	/*
+	 * Disable interrupts until the pin has stabilized and check
+	 * the state then. Use mod_timer() since we may be in the
+	 * middle of the timer routine when this interrupt triggers.
+	 */
+	disable_irq_nosync(irq);
+	mod_timer(&host->detect_timer, jiffies + msecs_to_jiffies(20));
+
+	return IRQ_HANDLED;
+}
+
+static int __init atmci_probe(struct platform_device *pdev)
+{
+	struct mci_platform_data	*pdata;
+	struct atmel_mci *host;
+	struct mmc_host *mmc;
+	struct resource *regs;
+	int irq;
+	int ret;
+
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!regs)
+		return -ENXIO;
+	pdata = pdev->dev.platform_data;
+	if (!pdata)
+		return -ENXIO;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	mmc = mmc_alloc_host(sizeof(struct atmel_mci), &pdev->dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	host = mmc_priv(mmc);
+	host->pdev = pdev;
+	host->mmc = mmc;
+	host->detect_pin = pdata->detect_pin;
+	host->wp_pin = pdata->wp_pin;
+
+	host->mck = clk_get(&pdev->dev, "mci_clk");
+	if (IS_ERR(host->mck)) {
+		ret = PTR_ERR(host->mck);
+		goto err_clk_get;
+	}
+
+	ret = -ENOMEM;
+	host->regs = ioremap(regs->start, regs->end - regs->start + 1);
+	if (!host->regs)
+		goto err_ioremap;
+
+	clk_enable(host->mck);
+	mci_writel(host, CR, MCI_CR_SWRST);
+	host->bus_hz = clk_get_rate(host->mck);
+	clk_disable(host->mck);
+
+	host->mapbase = regs->start;
+
+	mmc->ops = &atmci_ops;
+	mmc->f_min = (host->bus_hz + 511) / 512;
+	mmc->f_max = host->bus_hz / 2;
+	mmc->ocr_avail	= MMC_VDD_32_33 | MMC_VDD_33_34;
+	mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_MULTIWRITE;
+
+	mmc->max_hw_segs = 64;
+	mmc->max_phys_segs = 64;
+	mmc->max_req_size = 32768 * 512;
+	mmc->max_blk_size = 32768;
+	mmc->max_blk_count = 512;
+
+	tasklet_init(&host->tasklet, atmci_tasklet_func, (unsigned long)mmc);
+
+	ret = request_irq(irq, atmci_interrupt, 0, pdev->dev.bus_id, mmc);
+	if (ret)
+		goto err_request_irq;
+
+	/* Assume card is present if we don't have a detect pin */
+	host->present = 1;
+	if (host->detect_pin >= 0) {
+		if (gpio_request(host->detect_pin, "mmc_detect")) {
+			dev_dbg(&mmc->class_dev, "no detect pin available\n");
+			host->detect_pin = -1;
+		} else {
+			host->present = !gpio_get_value(host->detect_pin);
+		}
+	}
+	if (host->wp_pin >= 0) {
+		if (gpio_request(host->wp_pin, "mmc_wp")) {
+			dev_dbg(&mmc->class_dev, "no WP pin available\n");
+			host->wp_pin = -1;
+		}
+	}
+
+	platform_set_drvdata(pdev, host);
+
+	mmc_add_host(mmc);
+
+	if (host->detect_pin >= 0) {
+		setup_timer(&host->detect_timer, atmci_detect_change,
+				(unsigned long)host);
+
+		ret = request_irq(gpio_to_irq(host->detect_pin),
+				atmci_detect_interrupt,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+				"mmc-detect", mmc);
+		if (ret) {
+			dev_dbg(&mmc->class_dev,
+				"could not request IRQ %d for detect pin\n",
+				gpio_to_irq(host->detect_pin));
+			gpio_free(host->detect_pin);
+			host->detect_pin = -1;
+		}
+	}
+
+	dev_info(&mmc->class_dev,
+			"Atmel MCI controller at 0x%08lx irq %d\n",
+			host->mapbase, irq);
+
+	return 0;
+
+err_request_irq:
+	iounmap(host->regs);
+err_ioremap:
+	clk_put(host->mck);
+err_clk_get:
+	mmc_free_host(mmc);
+	return ret;
+}
+
+static int __exit atmci_remove(struct platform_device *pdev)
+{
+	struct atmel_mci *host = platform_get_drvdata(pdev);
+
+	platform_set_drvdata(pdev, NULL);
+
+	if (host) {
+		if (host->detect_pin >= 0) {
+			int pin = host->detect_pin;
+
+			/* Make sure the timer doesn't enable the interrupt */
+			host->detect_pin = -1;
+			smp_wmb();
+
+			free_irq(gpio_to_irq(pin), host->mmc);
+			del_timer_sync(&host->detect_timer);
+			gpio_free(pin);
+		}
+
+		mmc_remove_host(host->mmc);
+
+		clk_enable(host->mck);
+		mci_writel(host, IDR, ~0UL);
+		mci_writel(host, CR, MCI_CR_MCIDIS);
+		mci_readl(host, SR);
+		clk_disable(host->mck);
+
+		if (host->wp_pin >= 0)
+			gpio_free(host->wp_pin);
+
+		free_irq(platform_get_irq(pdev, 0), host->mmc);
+		iounmap(host->regs);
+
+		clk_put(host->mck);
+
+		mmc_free_host(host->mmc);
+	}
+	return 0;
+}
+
+static struct platform_driver atmci_driver = {
+	.remove		= __exit_p(atmci_remove),
+	.driver		= {
+		.name		= "atmel_mci",
+	},
+};
+
+static int __init atmci_init(void)
+{
+	return platform_driver_probe(&atmci_driver, atmci_probe);
+}
+
+static void __exit atmci_exit(void)
+{
+	platform_driver_unregister(&atmci_driver);
+}
+
+module_init(atmci_init);
+module_exit(atmci_exit);
+
+MODULE_DESCRIPTION("Atmel Multimedia Card Interface driver");
+MODULE_AUTHOR("Haavard Skinnemoen <haavard.skinnemoen@atmel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/asm-avr32/arch-at32ap/board.h b/include/asm-avr32/arch-at32ap/board.h
index b4cddfaca90..a3783861cdd 100644
--- a/include/asm-avr32/arch-at32ap/board.h
+++ b/include/asm-avr32/arch-at32ap/board.h
@@ -77,7 +77,11 @@ struct i2c_board_info;
 struct platform_device *at32_add_device_twi(unsigned int id,
 					    struct i2c_board_info *b,
 					    unsigned int n);
-struct platform_device *at32_add_device_mci(unsigned int id);
+
+struct mci_platform_data;
+struct platform_device *
+at32_add_device_mci(unsigned int id, struct mci_platform_data *data);
+
 struct platform_device *at32_add_device_ac97c(unsigned int id);
 struct platform_device *at32_add_device_abdac(unsigned int id);
 struct platform_device *at32_add_device_psif(unsigned int id);
diff --git a/include/asm-avr32/atmel-mci.h b/include/asm-avr32/atmel-mci.h
new file mode 100644
index 00000000000..c2ea6e1c9aa
--- /dev/null
+++ b/include/asm-avr32/atmel-mci.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_AVR32_ATMEL_MCI_H
+#define __ASM_AVR32_ATMEL_MCI_H
+
+struct mci_platform_data {
+	int			detect_pin;
+	int			wp_pin;
+};
+
+#endif /* __ASM_AVR32_ATMEL_MCI_H */
-- 
cgit v1.2.3-70-g09d2