Merge branch 'linus' into release

28 files changed, 3040 insertions, 1365 deletions

diff --git a/drivers/net/sfc/Kconfig b/drivers/net/sfc/Kconfig
index 3be13b592b4..c535408ad6b 100644
--- a/drivers/net/sfc/Kconfig
+++ b/drivers/net/sfc/Kconfig
@@ -12,3 +12,11 @@ config SFC
 
 	  To compile this driver as a module, choose M here.  The module
 	  will be called sfc.
+config SFC_MTD
+	bool "Solarflare Solarstorm SFC4000 flash MTD support"
+	depends on SFC && MTD && !(SFC=y && MTD=m)
+	default y
+	help
+	  This exposes the on-board flash memory as an MTD device (e.g.
+          /dev/mtd1).  This makes it possible to upload new boot code
+          to the NIC.
diff --git a/drivers/net/sfc/Makefile b/drivers/net/sfc/Makefile
index c8f5704c8fb..b89f9be3cb1 100644
--- a/drivers/net/sfc/Makefile
+++ b/drivers/net/sfc/Makefile
@@ -1,5 +1,6 @@
-sfc-y			+= efx.o falcon.o tx.o rx.o falcon_xmac.o \
-			   selftest.o ethtool.o xfp_phy.o \
+sfc-y			+= efx.o falcon.o tx.o rx.o falcon_gmac.o \
+			   falcon_xmac.o selftest.o ethtool.o xfp_phy.o \
 			   mdio_10g.o tenxpress.o boards.o sfe4001.o
+sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/sfc/boards.c b/drivers/net/sfc/boards.c
index 99e60237326..64903496aa9 100644
--- a/drivers/net/sfc/boards.c
+++ b/drivers/net/sfc/boards.c
@@ -1,6 +1,6 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007 Solarflare Communications Inc.
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -11,6 +11,7 @@
 #include "phy.h"
 #include "boards.h"
 #include "efx.h"
+#include "workarounds.h"
 
 /* Macros for unpacking the board revision */
 /* The revision info is in host byte order. */
@@ -52,9 +53,128 @@ static void board_blink(struct efx_nic *efx, bool blink)
 }
 
 /*****************************************************************************
+ * Support for LM87 sensor chip used on several boards
+ */
+#define LM87_REG_ALARMS1		0x41
+#define LM87_REG_ALARMS2		0x42
+#define LM87_IN_LIMITS(nr, _min, _max)			\
+	0x2B + (nr) * 2, _max, 0x2C + (nr) * 2, _min
+#define LM87_AIN_LIMITS(nr, _min, _max)			\
+	0x3B + (nr), _max, 0x1A + (nr), _min
+#define LM87_TEMP_INT_LIMITS(_min, _max)		\
+	0x39, _max, 0x3A, _min
+#define LM87_TEMP_EXT1_LIMITS(_min, _max)		\
+	0x37, _max, 0x38, _min
+
+#define LM87_ALARM_TEMP_INT		0x10
+#define LM87_ALARM_TEMP_EXT1		0x20
+
+#if defined(CONFIG_SENSORS_LM87) || defined(CONFIG_SENSORS_LM87_MODULE)
+
+static int efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info,
+			 const u8 *reg_values)
+{
+	struct i2c_client *client = i2c_new_device(&efx->i2c_adap, info);
+	int rc;
+
+	if (!client)
+		return -EIO;
+
+	while (*reg_values) {
+		u8 reg = *reg_values++;
+		u8 value = *reg_values++;
+		rc = i2c_smbus_write_byte_data(client, reg, value);
+		if (rc)
+			goto err;
+	}
+
+	efx->board_info.hwmon_client = client;
+	return 0;
+
+err:
+	i2c_unregister_device(client);
+	return rc;
+}
+
+static void efx_fini_lm87(struct efx_nic *efx)
+{
+	i2c_unregister_device(efx->board_info.hwmon_client);
+}
+
+static int efx_check_lm87(struct efx_nic *efx, unsigned mask)
+{
+	struct i2c_client *client = efx->board_info.hwmon_client;
+	s32 alarms1, alarms2;
+
+	/* If link is up then do not monitor temperature */
+	if (EFX_WORKAROUND_7884(efx) && efx->link_up)
+		return 0;
+
+	alarms1 = i2c_smbus_read_byte_data(client, LM87_REG_ALARMS1);
+	alarms2 = i2c_smbus_read_byte_data(client, LM87_REG_ALARMS2);
+	if (alarms1 < 0)
+		return alarms1;
+	if (alarms2 < 0)
+		return alarms2;
+	alarms1 &= mask;
+	alarms2 &= mask >> 8;
+	if (alarms1 || alarms2) {
+		EFX_ERR(efx,
+			"LM87 detected a hardware failure (status %02x:%02x)"
+			"%s%s\n",
+			alarms1, alarms2,
+			(alarms1 & LM87_ALARM_TEMP_INT) ? " INTERNAL" : "",
+			(alarms1 & LM87_ALARM_TEMP_EXT1) ? " EXTERNAL" : "");
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+#else /* !CONFIG_SENSORS_LM87 */
+
+static inline int
+efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info,
+	      const u8 *reg_values)
+{
+	return 0;
+}
+static inline void efx_fini_lm87(struct efx_nic *efx)
+{
+}
+static inline int efx_check_lm87(struct efx_nic *efx, unsigned mask)
+{
+	return 0;
+}
+
+#endif /* CONFIG_SENSORS_LM87 */
+
+/*****************************************************************************
  * Support for the SFE4002
  *
  */
+static u8 sfe4002_lm87_channel = 0x03; /* use AIN not FAN inputs */
+
+static const u8 sfe4002_lm87_regs[] = {
+	LM87_IN_LIMITS(0, 0x83, 0x91),		/* 2.5V:  1.8V +/- 5% */
+	LM87_IN_LIMITS(1, 0x51, 0x5a),		/* Vccp1: 1.2V +/- 5% */
+	LM87_IN_LIMITS(2, 0xb6, 0xca),		/* 3.3V:  3.3V +/- 5% */
+	LM87_IN_LIMITS(3, 0xb0, 0xc9),		/* 5V:    4.6-5.2V */
+	LM87_IN_LIMITS(4, 0xb0, 0xe0),		/* 12V:   11-14V */
+	LM87_IN_LIMITS(5, 0x44, 0x4b),		/* Vccp2: 1.0V +/- 5% */
+	LM87_AIN_LIMITS(0, 0xa0, 0xb2),		/* AIN1:  1.66V +/- 5% */
+	LM87_AIN_LIMITS(1, 0x91, 0xa1),		/* AIN2:  1.5V +/- 5% */
+	LM87_TEMP_INT_LIMITS(10, 60),		/* board */
+	LM87_TEMP_EXT1_LIMITS(10, 70),		/* Falcon */
+	0
+};
+
+static struct i2c_board_info sfe4002_hwmon_info = {
+	I2C_BOARD_INFO("lm87", 0x2e),
+	.platform_data	= &sfe4002_lm87_channel,
+	.irq		= -1,
+};
+
 /****************************************************************************/
 /* LED allocations. Note that on rev A0 boards the schematic and the reality
  * differ: red and green are swapped. Below is the fixed (A1) layout (there
@@ -84,81 +204,67 @@ static void sfe4002_fault_led(struct efx_nic *efx, bool state)
 			QUAKE_LED_OFF);
 }
 
+static int sfe4002_check_hw(struct efx_nic *efx)
+{
+	/* A0 board rev. 4002s report a temperature fault the whole time
+	 * (bad sensor) so we mask it out. */
+	unsigned alarm_mask =
+		(efx->board_info.major == 0 && efx->board_info.minor == 0) ?
+		~LM87_ALARM_TEMP_EXT1 : ~0;
+
+	return efx_check_lm87(efx, alarm_mask);
+}
+
 static int sfe4002_init(struct efx_nic *efx)
 {
+	int rc = efx_init_lm87(efx, &sfe4002_hwmon_info, sfe4002_lm87_regs);
+	if (rc)
+		return rc;
+	efx->board_info.monitor = sfe4002_check_hw;
 	efx->board_info.init_leds = sfe4002_init_leds;
 	efx->board_info.set_fault_led = sfe4002_fault_led;
 	efx->board_info.blink = board_blink;
+	efx->board_info.fini = efx_fini_lm87;
 	return 0;
 }
 
 /* This will get expanded as board-specific details get moved out of the
  * PHY drivers. */
 struct efx_board_data {
+	enum efx_board_type type;
 	const char *ref_model;
 	const char *gen_type;
 	int (*init) (struct efx_nic *nic);
 };
 
-static int dummy_init(struct efx_nic *nic)
-{
-	return 0;
-}
 
 static struct efx_board_data board_data[] = {
-	[EFX_BOARD_INVALID] =
-	{NULL,	    NULL,                  dummy_init},
-	[EFX_BOARD_SFE4001] =
-	{"SFE4001", "10GBASE-T adapter",   sfe4001_init},
-	[EFX_BOARD_SFE4002] =
-	{"SFE4002", "XFP adapter",         sfe4002_init},
+	{ EFX_BOARD_SFE4001, "SFE4001", "10GBASE-T adapter", sfe4001_init },
+	{ EFX_BOARD_SFE4002, "SFE4002", "XFP adapter", sfe4002_init },
+	{ EFX_BOARD_SFN4111T, "SFN4111T", "100/1000/10GBASE-T adapter",
+	  sfn4111t_init },
 };
 
-int efx_set_board_info(struct efx_nic *efx, u16 revision_info)
+void efx_set_board_info(struct efx_nic *efx, u16 revision_info)
 {
-	int rc = 0;
-	struct efx_board_data *data;
-
-	if (BOARD_TYPE(revision_info) >= EFX_BOARD_MAX) {
-		EFX_ERR(efx, "squashing unknown board type %d\n",
-			BOARD_TYPE(revision_info));
-		revision_info = 0;
-	}
+	struct efx_board_data *data = NULL;
+	int i;
 
-	if (BOARD_TYPE(revision_info) == 0) {
-		efx->board_info.major = 0;
-		efx->board_info.minor = 0;
-		/* For early boards that don't have revision info. there is
-		 * only 1 board for each PHY type, so we can work it out, with
-		 * the exception of the PHY-less boards. */
-		switch (efx->phy_type) {
-		case PHY_TYPE_10XPRESS:
-			efx->board_info.type = EFX_BOARD_SFE4001;
-			break;
-		case PHY_TYPE_XFP:
-			efx->board_info.type = EFX_BOARD_SFE4002;
-			break;
-		default:
-			efx->board_info.type = 0;
-			break;
-		}
-	} else {
-		efx->board_info.type = BOARD_TYPE(revision_info);
-		efx->board_info.major = BOARD_MAJOR(revision_info);
-		efx->board_info.minor = BOARD_MINOR(revision_info);
-	}
+	efx->board_info.type = BOARD_TYPE(revision_info);
+	efx->board_info.major = BOARD_MAJOR(revision_info);
+	efx->board_info.minor = BOARD_MINOR(revision_info);
 
-	data = &board_data[efx->board_info.type];
+	for (i = 0; i < ARRAY_SIZE(board_data); i++)
+		if (board_data[i].type == efx->board_info.type)
+			data = &board_data[i];
 
-	/* Report the board model number or generic type for recognisable
-	 * boards. */
-	if (efx->board_info.type != 0)
+	if (data) {
 		EFX_INFO(efx, "board is %s rev %c%d\n",
 			 (efx->pci_dev->subsystem_vendor == EFX_VENDID_SFC)
 			 ? data->ref_model : data->gen_type,
 			 'A' + efx->board_info.major, efx->board_info.minor);
-
-	efx->board_info.init = data->init;
-
-	return rc;
+		efx->board_info.init = data->init;
+	} else {
+		EFX_ERR(efx, "unknown board type %d\n", efx->board_info.type);
+	}
 }
diff --git a/drivers/net/sfc/boards.h b/drivers/net/sfc/boards.h
index c6e01b64bfb..d93c6c6a754 100644
--- a/drivers/net/sfc/boards.h
+++ b/drivers/net/sfc/boards.h
@@ -1,6 +1,6 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007 Solarflare Communications Inc.
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -12,14 +12,16 @@
 
 /* Board IDs (must fit in 8 bits) */
 enum efx_board_type {
-	EFX_BOARD_INVALID = 0,
-	EFX_BOARD_SFE4001 = 1,   /* SFE4001 (10GBASE-T) */
+	EFX_BOARD_SFE4001 = 1,
 	EFX_BOARD_SFE4002 = 2,
-	/* Insert new types before here */
-	EFX_BOARD_MAX
+	EFX_BOARD_SFN4111T = 0x51,
 };
 
-extern int efx_set_board_info(struct efx_nic *efx, u16 revision_info);
+extern void efx_set_board_info(struct efx_nic *efx, u16 revision_info);
+
+/* SFE4001 (10GBASE-T) */
 extern int sfe4001_init(struct efx_nic *efx);
+/* SFN4111T (100/1000/10GBASE-T) */
+extern int sfn4111t_init(struct efx_nic *efx);
 
 #endif
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 06ea71c7e34..7673fd92eaf 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -21,14 +21,12 @@
 #include <linux/ethtool.h>
 #include <linux/topology.h>
 #include "net_driver.h"
-#include "gmii.h"
 #include "ethtool.h"
 #include "tx.h"
 #include "rx.h"
 #include "efx.h"
 #include "mdio_10g.h"
 #include "falcon.h"
-#include "mac.h"
 
 #define EFX_MAX_MTU (9 * 1024)
 
@@ -39,6 +37,12 @@
  */
 static struct workqueue_struct *refill_workqueue;
 
+/* Reset workqueue. If any NIC has a hardware failure then a reset will be
+ * queued onto this work queue. This is not a per-nic work queue, because
+ * efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
+ */
+static struct workqueue_struct *reset_workqueue;
+
 /**************************************************************************
  *
  * Configurable values
@@ -58,13 +62,15 @@ MODULE_PARM_DESC(lro, "Large receive offload acceleration");
 /*
  * Use separate channels for TX and RX events
  *
- * Set this to 1 to use separate channels for TX and RX. It allows us to
- * apply a higher level of interrupt moderation to TX events.
+ * Set this to 1 to use separate channels for TX and RX. It allows us
+ * to control interrupt affinity separately for TX and RX.
  *
- * This is forced to 0 for MSI interrupt mode as the interrupt vector
- * is not written
+ * This is only used in MSI-X interrupt mode
  */
-static unsigned int separate_tx_and_rx_channels = true;
+static unsigned int separate_tx_channels;
+module_param(separate_tx_channels, uint, 0644);
+MODULE_PARM_DESC(separate_tx_channels,
+		 "Use separate channels for TX and RX");
 
 /* This is the weight assigned to each of the (per-channel) virtual
  * NAPI devices.
@@ -77,11 +83,6 @@ static int napi_weight = 64;
  */
 unsigned int efx_monitor_interval = 1 * HZ;
 
-/* This controls whether or not the hardware monitor will trigger a
- * reset when it detects an error condition.
- */
-static unsigned int monitor_reset = true;
-
 /* This controls whether or not the driver will initialise devices
  * with invalid MAC addresses stored in the EEPROM or flash.  If true,
  * such devices will be initialised with a random locally-generated
@@ -128,6 +129,10 @@ static unsigned int rss_cpus;
 module_param(rss_cpus, uint, 0444);
 MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
 
+static int phy_flash_cfg;
+module_param(phy_flash_cfg, int, 0644);
+MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
+
 /**************************************************************************
  *
  * Utility functions and prototypes
@@ -211,7 +216,6 @@ static int efx_poll(struct napi_struct *napi, int budget)
 {
 	struct efx_channel *channel =
 		container_of(napi, struct efx_channel, napi_str);
-	struct net_device *napi_dev = channel->napi_dev;
 	int rx_packets;
 
 	EFX_TRACE(channel->efx, "channel %d NAPI poll executing on CPU %d\n",
@@ -225,7 +229,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		 * since efx_channel_processed() will have no effect if
 		 * interrupts have already been disabled.
 		 */
-		netif_rx_complete(napi_dev, napi);
+		netif_rx_complete(napi);
 		efx_channel_processed(channel);
 	}
 
@@ -349,6 +353,27 @@ static int efx_probe_channel(struct efx_channel *channel)
 }
 
 
+static void efx_set_channel_names(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	const char *type = "";
+	int number;
+
+	efx_for_each_channel(channel, efx) {
+		number = channel->channel;
+		if (efx->n_channels > efx->n_rx_queues) {
+			if (channel->channel < efx->n_rx_queues) {
+				type = "-rx";
+			} else {
+				type = "-tx";
+				number -= efx->n_rx_queues;
+			}
+		}
+		snprintf(channel->name, sizeof(channel->name),
+			 "%s%s-%d", efx->name, type, number);
+	}
+}
+
 /* Channels are shutdown and reinitialised whilst the NIC is running
  * to propagate configuration changes (mtu, checksum offload), or
  * to clear hardware error conditions
@@ -523,26 +548,8 @@ static void efx_link_status_changed(struct efx_nic *efx)
 
 	/* Status message for kernel log */
 	if (efx->link_up) {
-		struct mii_if_info *gmii = &efx->mii;
-		unsigned adv, lpa;
-		/* NONE here means direct XAUI from the controller, with no
-		 * MDIO-attached device we can query. */
-		if (efx->phy_type != PHY_TYPE_NONE) {
-			adv = gmii_advertised(gmii);
-			lpa = gmii_lpa(gmii);
-		} else {
-			lpa = GM_LPA_10000 | LPA_DUPLEX;
-			adv = lpa;
-		}
-		EFX_INFO(efx, "link up at %dMbps %s-duplex "
-			 "(adv %04x lpa %04x) (MTU %d)%s\n",
-			 (efx->link_options & GM_LPA_10000 ? 10000 :
-			  (efx->link_options & GM_LPA_1000 ? 1000 :
-			   (efx->link_options & GM_LPA_100 ? 100 :
-			    10))),
-			 (efx->link_options & GM_LPA_DUPLEX ?
-			  "full" : "half"),
-			 adv, lpa,
+		EFX_INFO(efx, "link up at %uMbps %s-duplex (MTU %d)%s\n",
+			 efx->link_speed, efx->link_fd ? "full" : "half",
 			 efx->net_dev->mtu,
 			 (efx->promiscuous ? " [PROMISC]" : ""));
 	} else {
@@ -566,10 +573,28 @@ void __efx_reconfigure_port(struct efx_nic *efx)
 		netif_addr_unlock_bh(efx->net_dev);
 	}
 
-	falcon_reconfigure_xmac(efx);
+	falcon_deconfigure_mac_wrapper(efx);
+
+	/* Reconfigure the PHY, disabling transmit in mac level loopback. */
+	if (LOOPBACK_INTERNAL(efx))
+		efx->phy_mode |= PHY_MODE_TX_DISABLED;
+	else
+		efx->phy_mode &= ~PHY_MODE_TX_DISABLED;
+	efx->phy_op->reconfigure(efx);
+
+	if (falcon_switch_mac(efx))
+		goto fail;
+
+	efx->mac_op->reconfigure(efx);
 
 	/* Inform kernel of loss/gain of carrier */
 	efx_link_status_changed(efx);
+	return;
+
+fail:
+	EFX_ERR(efx, "failed to reconfigure MAC\n");
+	efx->phy_op->fini(efx);
+	efx->port_initialized = false;
 }
 
 /* Reinitialise the MAC to pick up new PHY settings, even if the port is
@@ -586,10 +611,9 @@ void efx_reconfigure_port(struct efx_nic *efx)
 /* Asynchronous efx_reconfigure_port work item. To speed up efx_flush_all()
  * we don't efx_reconfigure_port() if the port is disabled. Care is taken
  * in efx_stop_all() and efx_start_port() to prevent PHY events being lost */
-static void efx_reconfigure_work(struct work_struct *data)
+static void efx_phy_work(struct work_struct *data)
 {
-	struct efx_nic *efx = container_of(data, struct efx_nic,
-					   reconfigure_work);
+	struct efx_nic *efx = container_of(data, struct efx_nic, phy_work);
 
 	mutex_lock(&efx->mac_lock);
 	if (efx->port_enabled)
@@ -597,6 +621,16 @@ static void efx_reconfigure_work(struct work_struct *data)
 	mutex_unlock(&efx->mac_lock);
 }
 
+static void efx_mac_work(struct work_struct *data)
+{
+	struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
+
+	mutex_lock(&efx->mac_lock);
+	if (efx->port_enabled)
+		efx->mac_op->irq(efx);
+	mutex_unlock(&efx->mac_lock);
+}
+
 static int efx_probe_port(struct efx_nic *efx)
 {
 	int rc;
@@ -608,21 +642,22 @@ static int efx_probe_port(struct efx_nic *efx)
 	if (rc)
 		goto err;
 
+	if (phy_flash_cfg)
+		efx->phy_mode = PHY_MODE_SPECIAL;
+
 	/* Sanity check MAC address */
 	if (is_valid_ether_addr(efx->mac_address)) {
 		memcpy(efx->net_dev->dev_addr, efx->mac_address, ETH_ALEN);
 	} else {
-		DECLARE_MAC_BUF(mac);
-
-		EFX_ERR(efx, "invalid MAC address %s\n",
-			print_mac(mac, efx->mac_address));
+		EFX_ERR(efx, "invalid MAC address %pM\n",
+			efx->mac_address);
 		if (!allow_bad_hwaddr) {
 			rc = -EINVAL;
 			goto err;
 		}
 		random_ether_addr(efx->net_dev->dev_addr);
-		EFX_INFO(efx, "using locally-generated MAC %s\n",
-			 print_mac(mac, efx->net_dev->dev_addr));
+		EFX_INFO(efx, "using locally-generated MAC %pM\n",
+			 efx->net_dev->dev_addr);
 	}
 
 	return 0;
@@ -638,23 +673,30 @@ static int efx_init_port(struct efx_nic *efx)
 
 	EFX_LOG(efx, "init port\n");
 
-	/* Initialise the MAC and PHY */
-	rc = falcon_init_xmac(efx);
+	rc = efx->phy_op->init(efx);
 	if (rc)
 		return rc;
+	efx->phy_op->reconfigure(efx);
+
+	mutex_lock(&efx->mac_lock);
+	rc = falcon_switch_mac(efx);
+	mutex_unlock(&efx->mac_lock);
+	if (rc)
+		goto fail;
+	efx->mac_op->reconfigure(efx);
 
 	efx->port_initialized = true;
 	efx->stats_enabled = true;
-
-	/* Reconfigure port to program MAC registers */
-	falcon_reconfigure_xmac(efx);
-
 	return 0;
+
+fail:
+	efx->phy_op->fini(efx);
+	return rc;
 }
 
 /* Allow efx_reconfigure_port() to be scheduled, and close the window
  * between efx_stop_port and efx_flush_all whereby a previously scheduled
- * efx_reconfigure_port() may have been cancelled */
+ * efx_phy_work()/efx_mac_work() may have been cancelled */
 static void efx_start_port(struct efx_nic *efx)
 {
 	EFX_LOG(efx, "start port\n");
@@ -663,13 +705,14 @@ static void efx_start_port(struct efx_nic *efx)
 	mutex_lock(&efx->mac_lock);
 	efx->port_enabled = true;
 	__efx_reconfigure_port(efx);
+	efx->mac_op->irq(efx);
 	mutex_unlock(&efx->mac_lock);
 }
 
-/* Prevent efx_reconfigure_work and efx_monitor() from executing, and
- * efx_set_multicast_list() from scheduling efx_reconfigure_work.
- * efx_reconfigure_work can still be scheduled via NAPI processing
- * until efx_flush_all() is called */
+/* Prevent efx_phy_work, efx_mac_work, and efx_monitor() from executing,
+ * and efx_set_multicast_list() from scheduling efx_phy_work. efx_phy_work
+ * and efx_mac_work may still be scheduled via NAPI processing until
+ * efx_flush_all() is called */
 static void efx_stop_port(struct efx_nic *efx)
 {
 	EFX_LOG(efx, "stop port\n");
@@ -692,7 +735,7 @@ static void efx_fini_port(struct efx_nic *efx)
 	if (!efx->port_initialized)
 		return;
 
-	falcon_fini_xmac(efx);
+	efx->phy_op->fini(efx);
 	efx->port_initialized = false;
 
 	efx->link_up = false;
@@ -840,26 +883,33 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 	if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
 		struct msix_entry xentries[EFX_MAX_CHANNELS];
 		int wanted_ints;
+		int rx_queues;
 
 		/* We want one RX queue and interrupt per CPU package
 		 * (or as specified by the rss_cpus module parameter).
 		 * We will need one channel per interrupt.
 		 */
-		wanted_ints = rss_cpus ? rss_cpus : efx_wanted_rx_queues();
-		efx->n_rx_queues = min(wanted_ints, max_channels);
+		rx_queues = rss_cpus ? rss_cpus : efx_wanted_rx_queues();
+		wanted_ints = rx_queues + (separate_tx_channels ? 1 : 0);
+		wanted_ints = min(wanted_ints, max_channels);
 
-		for (i = 0; i < efx->n_rx_queues; i++)
+		for (i = 0; i < wanted_ints; i++)
 			xentries[i].entry = i;
-		rc = pci_enable_msix(efx->pci_dev, xentries, efx->n_rx_queues);
+		rc = pci_enable_msix(efx->pci_dev, xentries, wanted_ints);
 		if (rc > 0) {
-			EFX_BUG_ON_PARANOID(rc >= efx->n_rx_queues);
-			efx->n_rx_queues = rc;
+			EFX_ERR(efx, "WARNING: Insufficient MSI-X vectors"
+				" available (%d < %d).\n", rc, wanted_ints);
+			EFX_ERR(efx, "WARNING: Performance may be reduced.\n");
+			EFX_BUG_ON_PARANOID(rc >= wanted_ints);
+			wanted_ints = rc;
 			rc = pci_enable_msix(efx->pci_dev, xentries,
-					     efx->n_rx_queues);
+					     wanted_ints);
 		}
 
 		if (rc == 0) {
-			for (i = 0; i < efx->n_rx_queues; i++)
+			efx->n_rx_queues = min(rx_queues, wanted_ints);
+			efx->n_channels = wanted_ints;
+			for (i = 0; i < wanted_ints; i++)
 				efx->channel[i].irq = xentries[i].vector;
 		} else {
 			/* Fall back to single channel MSI */
@@ -871,6 +921,7 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 	/* Try single interrupt MSI */
 	if (efx->interrupt_mode == EFX_INT_MODE_MSI) {
 		efx->n_rx_queues = 1;
+		efx->n_channels = 1;
 		rc = pci_enable_msi(efx->pci_dev);
 		if (rc == 0) {
 			efx->channel[0].irq = efx->pci_dev->irq;
@@ -883,6 +934,7 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 	/* Assume legacy interrupts */
 	if (efx->interrupt_mode == EFX_INT_MODE_LEGACY) {
 		efx->n_rx_queues = 1;
+		efx->n_channels = 1 + (separate_tx_channels ? 1 : 0);
 		efx->legacy_irq = efx->pci_dev->irq;
 	}
 }
@@ -907,8 +959,8 @@ static void efx_set_channels(struct efx_nic *efx)
 	struct efx_rx_queue *rx_queue;
 
 	efx_for_each_tx_queue(tx_queue, efx) {
-		if (!EFX_INT_MODE_USE_MSI(efx) && separate_tx_and_rx_channels)
-			tx_queue->channel = &efx->channel[1];
+		if (separate_tx_channels)
+			tx_queue->channel = &efx->channel[efx->n_channels-1];
 		else
 			tx_queue->channel = &efx->channel[0];
 		tx_queue->channel->used_flags |= EFX_USED_BY_TX;
@@ -985,6 +1037,7 @@ static int efx_probe_all(struct efx_nic *efx)
 			goto fail3;
 		}
 	}
+	efx_set_channel_names(efx);
 
 	return 0;
 
@@ -1050,7 +1103,8 @@ static void efx_flush_all(struct efx_nic *efx)
 		cancel_delayed_work_sync(&rx_queue->work);
 
 	/* Stop scheduled port reconfigurations */
-	cancel_work_sync(&efx->reconfigure_work);
+	cancel_work_sync(&efx->mac_work);
+	cancel_work_sync(&efx->phy_work);
 
 }
 
@@ -1087,7 +1141,7 @@ static void efx_stop_all(struct efx_nic *efx)
 	 * window to loose phy events */
 	efx_stop_port(efx);
 
-	/* Flush reconfigure_work, refill_workqueue, monitor_work */
+	/* Flush efx_phy_work, efx_mac_work, refill_workqueue, monitor_work */
 	efx_flush_all(efx);
 
 	/* Isolate the MAC from the TX and RX engines, so that queue
@@ -1159,36 +1213,31 @@ static void efx_monitor(struct work_struct *data)
 {
 	struct efx_nic *efx = container_of(data, struct efx_nic,
 					   monitor_work.work);
-	int rc = 0;
+	int rc;
 
 	EFX_TRACE(efx, "hardware monitor executing on CPU %d\n",
 		  raw_smp_processor_id());
 
-
 	/* If the mac_lock is already held then it is likely a port
 	 * reconfiguration is already in place, which will likely do
 	 * most of the work of check_hw() anyway. */
-	if (!mutex_trylock(&efx->mac_lock)) {
-		queue_delayed_work(efx->workqueue, &efx->monitor_work,
-				   efx_monitor_interval);
-		return;
-	}
-
-	if (efx->port_enabled)
-		rc = falcon_check_xmac(efx);
-	mutex_unlock(&efx->mac_lock);
-
+	if (!mutex_trylock(&efx->mac_lock))
+		goto out_requeue;
+	if (!efx->port_enabled)
+		goto out_unlock;
+	rc = efx->board_info.monitor(efx);
 	if (rc) {
-		if (monitor_reset) {
-			EFX_ERR(efx, "hardware monitor detected a fault: "
-				"triggering reset\n");
-			efx_schedule_reset(efx, RESET_TYPE_MONITOR);
-		} else {
-			EFX_ERR(efx, "hardware monitor detected a fault, "
-				"skipping reset\n");
-		}
+		EFX_ERR(efx, "Board sensor %s; shutting down PHY\n",
+			(rc == -ERANGE) ? "reported fault" : "failed");
+		efx->phy_mode |= PHY_MODE_LOW_POWER;
+		falcon_sim_phy_event(efx);
 	}
+	efx->phy_op->poll(efx);
+	efx->mac_op->poll(efx);
 
+out_unlock:
+	mutex_unlock(&efx->mac_lock);
+out_requeue:
 	queue_delayed_work(efx->workqueue, &efx->monitor_work,
 			   efx_monitor_interval);
 }
@@ -1282,6 +1331,8 @@ static int efx_net_open(struct net_device *net_dev)
 	EFX_LOG(efx, "opening device %s on CPU %d\n", net_dev->name,
 		raw_smp_processor_id());
 
+	if (efx->state == STATE_DISABLED)
+		return -EIO;
 	if (efx->phy_mode & PHY_MODE_SPECIAL)
 		return -EBUSY;
 
@@ -1300,10 +1351,12 @@ static int efx_net_stop(struct net_device *net_dev)
 	EFX_LOG(efx, "closing %s on CPU %d\n", net_dev->name,
 		raw_smp_processor_id());
 
-	/* Stop the device and flush all the channels */
-	efx_stop_all(efx);
-	efx_fini_channels(efx);
-	efx_init_channels(efx);
+	if (efx->state != STATE_DISABLED) {
+		/* Stop the device and flush all the channels */
+		efx_stop_all(efx);
+		efx_fini_channels(efx);
+		efx_init_channels(efx);
+	}
 
 	return 0;
 }
@@ -1322,7 +1375,7 @@ static struct net_device_stats *efx_net_stats(struct net_device *net_dev)
 	if (!spin_trylock(&efx->stats_lock))
 		return stats;
 	if (efx->stats_enabled) {
-		falcon_update_stats_xmac(efx);
+		efx->mac_op->update_stats(efx);
 		falcon_update_nic_stats(efx);
 	}
 	spin_unlock(&efx->stats_lock);
@@ -1360,12 +1413,11 @@ static void efx_watchdog(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d: %s\n",
-		atomic_read(&efx->netif_stop_count), efx->port_enabled,
-		monitor_reset ? "resetting channels" : "skipping reset");
+	EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d:"
+		" resetting channels\n",
+		atomic_read(&efx->netif_stop_count), efx->port_enabled);
 
-	if (monitor_reset)
-		efx_schedule_reset(efx, RESET_TYPE_MONITOR);
+	efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG);
 }
 
 
@@ -1401,9 +1453,8 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
 	if (!is_valid_ether_addr(new_addr)) {
-		DECLARE_MAC_BUF(mac);
-		EFX_ERR(efx, "invalid ethernet MAC address requested: %s\n",
-			print_mac(mac, new_addr));
+		EFX_ERR(efx, "invalid ethernet MAC address requested: %pM\n",
+			new_addr);
 		return -EINVAL;
 	}
 
@@ -1447,22 +1498,43 @@ static void efx_set_multicast_list(struct net_device *net_dev)
 		return;
 
 	if (changed)
-		queue_work(efx->workqueue, &efx->reconfigure_work);
+		queue_work(efx->workqueue, &efx->phy_work);
 
 	/* Create and activate new global multicast hash table */
 	falcon_set_multicast_hash(efx);
 }
 
+static const struct net_device_ops efx_netdev_ops = {
+	.ndo_open		= efx_net_open,
+	.ndo_stop		= efx_net_stop,
+	.ndo_get_stats		= efx_net_stats,
+	.ndo_tx_timeout		= efx_watchdog,
+	.ndo_start_xmit		= efx_hard_start_xmit,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_do_ioctl		= efx_ioctl,
+	.ndo_change_mtu		= efx_change_mtu,
+	.ndo_set_mac_address	= efx_set_mac_address,
+	.ndo_set_multicast_list = efx_set_multicast_list,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller = efx_netpoll,
+#endif
+};
+
+static void efx_update_name(struct efx_nic *efx)
+{
+	strcpy(efx->name, efx->net_dev->name);
+	efx_mtd_rename(efx);
+	efx_set_channel_names(efx);
+}
+
 static int efx_netdev_event(struct notifier_block *this,
 			    unsigned long event, void *ptr)
 {
 	struct net_device *net_dev = ptr;
 
-	if (net_dev->open == efx_net_open && event == NETDEV_CHANGENAME) {
-		struct efx_nic *efx = netdev_priv(net_dev);
-
-		strcpy(efx->name, net_dev->name);
-	}
+	if (net_dev->netdev_ops == &efx_netdev_ops &&
+	    event == NETDEV_CHANGENAME)
+		efx_update_name(netdev_priv(net_dev));
 
 	return NOTIFY_DONE;
 }
@@ -1471,6 +1543,14 @@ static struct notifier_block efx_netdev_notifier = {
 	.notifier_call = efx_netdev_event,
 };
 
+static ssize_t
+show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	return sprintf(buf, "%d\n", efx->phy_type);
+}
+static DEVICE_ATTR(phy_type, 0644, show_phy_type, NULL);
+
 static int efx_register_netdev(struct efx_nic *efx)
 {
 	struct net_device *net_dev = efx->net_dev;
@@ -1478,18 +1558,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 	net_dev->watchdog_timeo = 5 * HZ;
 	net_dev->irq = efx->pci_dev->irq;
-	net_dev->open = efx_net_open;
-	net_dev->stop = efx_net_stop;
-	net_dev->get_stats = efx_net_stats;
-	net_dev->tx_timeout = &efx_watchdog;
-	net_dev->hard_start_xmit = efx_hard_start_xmit;
-	net_dev->do_ioctl = efx_ioctl;
-	net_dev->change_mtu = efx_change_mtu;
-	net_dev->set_mac_address = efx_set_mac_address;
-	net_dev->set_multicast_list = efx_set_multicast_list;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	net_dev->poll_controller = efx_netpoll;
-#endif
+	net_dev->netdev_ops = &efx_netdev_ops;
 	SET_NETDEV_DEV(net_dev, &efx->pci_dev->dev);
 	SET_ETHTOOL_OPS(net_dev, &efx_ethtool_ops);
 
@@ -1497,7 +1566,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 	netif_carrier_off(efx->net_dev);
 
 	/* Clear MAC statistics */
-	falcon_update_stats_xmac(efx);
+	efx->mac_op->update_stats(efx);
 	memset(&efx->mac_stats, 0, sizeof(efx->mac_stats));
 
 	rc = register_netdev(net_dev);
@@ -1505,9 +1574,22 @@ static int efx_register_netdev(struct efx_nic *efx)
 		EFX_ERR(efx, "could not register net dev\n");
 		return rc;
 	}
-	strcpy(efx->name, net_dev->name);
+
+	rtnl_lock();
+	efx_update_name(efx);
+	rtnl_unlock();
+
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+	if (rc) {
+		EFX_ERR(efx, "failed to init net dev attributes\n");
+		goto fail_registered;
+	}
 
 	return 0;
+
+fail_registered:
+	unregister_netdev(net_dev);
+	return rc;
 }
 
 static void efx_unregister_netdev(struct efx_nic *efx)
@@ -1527,6 +1609,7 @@ static void efx_unregister_netdev(struct efx_nic *efx)
 
 	if (efx_dev_registered(efx)) {
 		strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
+		device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
 		unregister_netdev(efx->net_dev);
 	}
 }
@@ -1541,8 +1624,6 @@ static void efx_unregister_netdev(struct efx_nic *efx)
  * before reset.  */
 void efx_reset_down(struct efx_nic *efx, struct ethtool_cmd *ecmd)
 {
-	int rc;
-
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
 	/* The net_dev->get_stats handler is quite slow, and will fail
@@ -1553,10 +1634,9 @@ void efx_reset_down(struct efx_nic *efx, struct ethtool_cmd *ecmd)
 
 	efx_stop_all(efx);
 	mutex_lock(&efx->mac_lock);
+	mutex_lock(&efx->spi_lock);
 
-	rc = falcon_xmac_get_settings(efx, ecmd);
-	if (rc)
-		EFX_ERR(efx, "could not back up PHY settings\n");
+	efx->phy_op->get_settings(efx, ecmd);
 
 	efx_fini_channels(efx);
 }
@@ -1581,10 +1661,11 @@ int efx_reset_up(struct efx_nic *efx, struct ethtool_cmd *ecmd, bool ok)
 	if (ok) {
 		efx_init_channels(efx);
 
-		if (falcon_xmac_set_settings(efx, ecmd))
+		if (efx->phy_op->set_settings(efx, ecmd))
 			EFX_ERR(efx, "could not restore PHY settings\n");
 	}
 
+	mutex_unlock(&efx->spi_lock);
 	mutex_unlock(&efx->mac_lock);
 
 	if (ok) {
@@ -1607,7 +1688,7 @@ static int efx_reset(struct efx_nic *efx)
 {
 	struct ethtool_cmd ecmd;
 	enum reset_type method = efx->reset_pending;
-	int rc;
+	int rc = 0;
 
 	/* Serialise with kernel interfaces */
 	rtnl_lock();
@@ -1616,7 +1697,7 @@ static int efx_reset(struct efx_nic *efx)
 	 * flag set so that efx_pci_probe_main will be retried */
 	if (efx->state != STATE_RUNNING) {
 		EFX_INFO(efx, "scheduled reset quenched. NIC not RUNNING\n");
-		goto unlock_rtnl;
+		goto out_unlock;
 	}
 
 	EFX_INFO(efx, "resetting (%d)\n", method);
@@ -1626,7 +1707,7 @@ static int efx_reset(struct efx_nic *efx)
 	rc = falcon_reset_hw(efx, method);
 	if (rc) {
 		EFX_ERR(efx, "failed to reset hardware\n");
-		goto fail;
+		goto out_disable;
 	}
 
 	/* Allow resets to be rescheduled. */
@@ -1640,28 +1721,23 @@ static int efx_reset(struct efx_nic *efx)
 
 	/* Leave device stopped if necessary */
 	if (method == RESET_TYPE_DISABLE) {
+		efx_reset_up(efx, &ecmd, false);
 		rc = -EIO;
-		goto fail;
+	} else {
+		rc = efx_reset_up(efx, &ecmd, true);
 	}
 
-	rc = efx_reset_up(efx, &ecmd, true);
-	if (rc)
-		goto disable;
-
-	EFX_LOG(efx, "reset complete\n");
- unlock_rtnl:
-	rtnl_unlock();
-	return 0;
-
- fail:
-	efx_reset_up(efx, &ecmd, false);
- disable:
-	EFX_ERR(efx, "has been disabled\n");
-	efx->state = STATE_DISABLED;
+out_disable:
+	if (rc) {
+		EFX_ERR(efx, "has been disabled\n");
+		efx->state = STATE_DISABLED;
+		dev_close(efx->net_dev);
+	} else {
+		EFX_LOG(efx, "reset complete\n");
+	}
 
+out_unlock:
 	rtnl_unlock();
-	efx_unregister_netdev(efx);
-	efx_fini_port(efx);
 	return rc;
 }
 
@@ -1709,7 +1785,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
 
 	efx->reset_pending = method;
 
-	queue_work(efx->reset_workqueue, &efx->reset_work);
+	queue_work(reset_workqueue, &efx->reset_work);
 }
 
 /**************************************************************************
@@ -1743,10 +1819,16 @@ int efx_port_dummy_op_int(struct efx_nic *efx)
 void efx_port_dummy_op_void(struct efx_nic *efx) {}
 void efx_port_dummy_op_blink(struct efx_nic *efx, bool blink) {}
 
+static struct efx_mac_operations efx_dummy_mac_operations = {
+	.reconfigure	= efx_port_dummy_op_void,
+	.poll		= efx_port_dummy_op_void,
+	.irq		= efx_port_dummy_op_void,
+};
+
 static struct efx_phy_operations efx_dummy_phy_operations = {
 	.init		 = efx_port_dummy_op_int,
 	.reconfigure	 = efx_port_dummy_op_void,
-	.check_hw        = efx_port_dummy_op_int,
+	.poll		 = efx_port_dummy_op_void,
 	.fini		 = efx_port_dummy_op_void,
 	.clear_interrupt = efx_port_dummy_op_void,
 };
@@ -1755,6 +1837,7 @@ static struct efx_board efx_dummy_board_info = {
 	.init		= efx_port_dummy_op_int,
 	.init_leds	= efx_port_dummy_op_int,
 	.set_fault_led	= efx_port_dummy_op_blink,
+	.monitor	= efx_port_dummy_op_int,
 	.blink		= efx_port_dummy_op_blink,
 	.fini		= efx_port_dummy_op_void,
 };
@@ -1774,12 +1857,13 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type,
 	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
-	int i, rc;
+	int i;
 
 	/* Initialise common structures */
 	memset(efx, 0, sizeof(*efx));
 	spin_lock_init(&efx->biu_lock);
 	spin_lock_init(&efx->phy_lock);
+	mutex_init(&efx->spi_lock);
 	INIT_WORK(&efx->reset_work, efx_reset_work);
 	INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
 	efx->pci_dev = pci_dev;
@@ -1793,9 +1877,11 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type,
 	spin_lock_init(&efx->netif_stop_lock);
 	spin_lock_init(&efx->stats_lock);
 	mutex_init(&efx->mac_lock);
+	efx->mac_op = &efx_dummy_mac_operations;
 	efx->phy_op = &efx_dummy_phy_operations;
 	efx->mii.dev = net_dev;
-	INIT_WORK(&efx->reconfigure_work, efx_reconfigure_work);
+	INIT_WORK(&efx->phy_work, efx_phy_work);
+	INIT_WORK(&efx->mac_work, efx_mac_work);
 	atomic_set(&efx->netif_stop_count, 1);
 
 	for (i = 0; i < EFX_MAX_CHANNELS; i++) {
@@ -1841,34 +1927,18 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type,
 	efx->interrupt_mode = max(efx->type->max_interrupt_mode,
 				  interrupt_mode);
 
-	efx->workqueue = create_singlethread_workqueue("sfc_work");
-	if (!efx->workqueue) {
-		rc = -ENOMEM;
-		goto fail1;
-	}
-
-	efx->reset_workqueue = create_singlethread_workqueue("sfc_reset");
-	if (!efx->reset_workqueue) {
-		rc = -ENOMEM;
-		goto fail2;
-	}
+	/* Would be good to use the net_dev name, but we're too early */
+	snprintf(efx->workqueue_name, sizeof(efx->workqueue_name), "sfc%s",
+		 pci_name(pci_dev));
+	efx->workqueue = create_singlethread_workqueue(efx->workqueue_name);
+	if (!efx->workqueue)
+		return -ENOMEM;
 
 	return 0;
-
- fail2:
-	destroy_workqueue(efx->workqueue);
-	efx->workqueue = NULL;
-
- fail1:
-	return rc;
 }
 
 static void efx_fini_struct(struct efx_nic *efx)
 {
-	if (efx->reset_workqueue) {
-		destroy_workqueue(efx->reset_workqueue);
-		efx->reset_workqueue = NULL;
-	}
 	if (efx->workqueue) {
 		destroy_workqueue(efx->workqueue);
 		efx->workqueue = NULL;
@@ -1927,11 +1997,13 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 
 	efx_unregister_netdev(efx);
 
+	efx_mtd_remove(efx);
+
 	/* Wait for any scheduled resets to complete. No more will be
 	 * scheduled from this point because efx_stop_all() has been
 	 * called, we are no longer registered with driverlink, and
 	 * the net_device's have been removed. */
-	flush_workqueue(efx->reset_workqueue);
+	cancel_work_sync(&efx->reset_work);
 
 	efx_pci_remove_main(efx);
 
@@ -1992,6 +2064,7 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 	efx_fini_port(efx);
  fail5:
  fail4:
+	efx->board_info.fini(efx);
  fail3:
 	efx_fini_napi(efx);
  fail2:
@@ -2045,14 +2118,23 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	 * we're in STATE_INIT. */
 	for (i = 0; i < 5; i++) {
 		rc = efx_pci_probe_main(efx);
-		if (rc == 0)
-			break;
 
 		/* Serialise against efx_reset(). No more resets will be
 		 * scheduled since efx_stop_all() has been called, and we
 		 * have not and never have been registered with either
 		 * the rtnetlink or driverlink layers. */
-		flush_workqueue(efx->reset_workqueue);
+		cancel_work_sync(&efx->reset_work);
+
+		if (rc == 0) {
+			if (efx->reset_pending != RESET_TYPE_NONE) {
+				/* If there was a scheduled reset during
+				 * probe, the NIC is probably hosed anyway */
+				efx_pci_remove_main(efx);
+				rc = -EIO;
+			} else {
+				break;
+			}
+		}
 
 		/* Retry if a recoverably reset event has been scheduled */
 		if ((efx->reset_pending != RESET_TYPE_INVISIBLE) &&
@@ -2070,16 +2152,15 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	/* Switch to the running state before we expose the device to
 	 * the OS.  This is to ensure that the initial gathering of
 	 * MAC stats succeeds. */
-	rtnl_lock();
 	efx->state = STATE_RUNNING;
-	rtnl_unlock();
+
+	efx_mtd_probe(efx); /* allowed to fail */
 
 	rc = efx_register_netdev(efx);
 	if (rc)
 		goto fail5;
 
 	EFX_LOG(efx, "initialisation successful\n");
-
 	return 0;
 
  fail5:
@@ -2127,6 +2208,11 @@ static int __init efx_init_module(void)
 		rc = -ENOMEM;
 		goto err_refill;
 	}
+	reset_workqueue = create_singlethread_workqueue("sfc_reset");
+	if (!reset_workqueue) {
+		rc = -ENOMEM;
+		goto err_reset;
+	}
 
 	rc = pci_register_driver(&efx_pci_driver);
 	if (rc < 0)
@@ -2135,6 +2221,8 @@ static int __init efx_init_module(void)
 	return 0;
 
  err_pci:
+	destroy_workqueue(reset_workqueue);
+ err_reset:
 	destroy_workqueue(refill_workqueue);
  err_refill:
 	unregister_netdevice_notifier(&efx_netdev_notifier);
@@ -2147,6 +2235,7 @@ static void __exit efx_exit_module(void)
 	printk(KERN_INFO "Solarflare NET driver unloading\n");
 
 	pci_unregister_driver(&efx_pci_driver);
+	destroy_workqueue(reset_workqueue);
 	destroy_workqueue(refill_workqueue);
 	unregister_netdevice_notifier(&efx_netdev_notifier);
 
diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h
index d02937b70ee..0dd7a532c78 100644
--- a/drivers/net/sfc/efx.h
+++ b/drivers/net/sfc/efx.h
@@ -58,6 +58,16 @@ extern int efx_port_dummy_op_int(struct efx_nic *efx);
 extern void efx_port_dummy_op_void(struct efx_nic *efx);
 extern void efx_port_dummy_op_blink(struct efx_nic *efx, bool blink);
 
+/* MTD */
+#ifdef CONFIG_SFC_MTD
+extern int efx_mtd_probe(struct efx_nic *efx);
+extern void efx_mtd_rename(struct efx_nic *efx);
+extern void efx_mtd_remove(struct efx_nic *efx);
+#else
+static inline int efx_mtd_probe(struct efx_nic *efx) { return 0; }
+static inline void efx_mtd_rename(struct efx_nic *efx) {}
+static inline void efx_mtd_remove(struct efx_nic *efx) {}
+#endif
 
 extern unsigned int efx_monitor_interval;
 
@@ -67,7 +77,7 @@ static inline void efx_schedule_channel(struct efx_channel *channel)
 		  channel->channel, raw_smp_processor_id());
 	channel->work_pending = true;
 
-	netif_rx_schedule(channel->napi_dev, &channel->napi_str);
+	netif_rx_schedule(&channel->napi_str);
 }
 
 #endif /* EFX_EFX_H */
diff --git a/drivers/net/sfc/enum.h b/drivers/net/sfc/enum.h
index cec15dbb88e..60cbc6e1e66 100644
--- a/drivers/net/sfc/enum.h
+++ b/drivers/net/sfc/enum.h
@@ -1,6 +1,6 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007 Solarflare Communications Inc.
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -13,22 +13,24 @@
 /**
  * enum efx_loopback_mode - loopback modes
  * @LOOPBACK_NONE: no loopback
- * @LOOPBACK_XGMII: loopback within MAC at XGMII level
- * @LOOPBACK_XGXS: loopback within MAC at XGXS level
- * @LOOPBACK_XAUI: loopback within MAC at XAUI level
- * @LOOPBACK_PHYXS: loopback within PHY at PHYXS level
- * @LOOPBACK_PCS: loopback within PHY at PCS level
- * @LOOPBACK_PMAPMD: loopback within PHY at PMAPMD level
+ * @LOOPBACK_GMAC: loopback within GMAC at unspecified level
+ * @LOOPBACK_XGMII: loopback within XMAC at XGMII level
+ * @LOOPBACK_XGXS: loopback within XMAC at XGXS level
+ * @LOOPBACK_XAUI: loopback within XMAC at XAUI level
+ * @LOOPBACK_GPHY: loopback within 1G PHY at unspecified level
+ * @LOOPBACK_PHYXS: loopback within 10G PHY at PHYXS level
+ * @LOOPBACK_PCS: loopback within 10G PHY at PCS level
+ * @LOOPBACK_PMAPMD: loopback within 10G PHY at PMAPMD level
  * @LOOPBACK_NETWORK: reflecting loopback (even further than furthest!)
  */
 /* Please keep in order and up-to-date w.r.t the following two #defines */
 enum efx_loopback_mode {
 	LOOPBACK_NONE = 0,
-	LOOPBACK_MAC = 1,
+	LOOPBACK_GMAC = 1,
 	LOOPBACK_XGMII = 2,
 	LOOPBACK_XGXS = 3,
 	LOOPBACK_XAUI = 4,
-	LOOPBACK_PHY = 5,
+	LOOPBACK_GPHY = 5,
 	LOOPBACK_PHYXS = 6,
 	LOOPBACK_PCS = 7,
 	LOOPBACK_PMAPMD = 8,
@@ -45,15 +47,19 @@ extern const char *efx_loopback_mode_names[];
 	LOOPBACK_MODE_NAME(efx->loopback_mode)
 
 /* These loopbacks occur within the controller */
-#define LOOPBACKS_10G_INTERNAL ((1 << LOOPBACK_XGMII)| \
-				(1 << LOOPBACK_XGXS) | \
-				(1 << LOOPBACK_XAUI))
+#define LOOPBACKS_INTERNAL ((1 << LOOPBACK_GMAC) |     \
+			    (1 << LOOPBACK_XGMII)|     \
+			    (1 << LOOPBACK_XGXS) |     \
+			    (1 << LOOPBACK_XAUI))
 
 #define LOOPBACK_MASK(_efx)			\
 	(1 << (_efx)->loopback_mode)
 
 #define LOOPBACK_INTERNAL(_efx)				\
-	(!!(LOOPBACKS_10G_INTERNAL & LOOPBACK_MASK(_efx)))
+	(!!(LOOPBACKS_INTERNAL & LOOPBACK_MASK(_efx)))
+
+#define LOOPBACK_CHANGED(_from, _to, _mask)				\
+	(!!((LOOPBACK_MASK(_from) ^ LOOPBACK_MASK(_to)) & (_mask)))
 
 #define LOOPBACK_OUT_OF(_from, _to, _mask)				\
 	((LOOPBACK_MASK(_from) & (_mask)) && !(LOOPBACK_MASK(_to) & (_mask)))
@@ -72,7 +78,7 @@ extern const char *efx_loopback_mode_names[];
  * @RESET_TYPE_ALL: reset everything but PCI core blocks
  * @RESET_TYPE_WORLD: reset everything, save & restore PCI config
  * @RESET_TYPE_DISABLE: disable NIC
- * @RESET_TYPE_MONITOR: reset due to hardware monitor
+ * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog
  * @RESET_TYPE_INT_ERROR: reset due to internal error
  * @RESET_TYPE_RX_RECOVERY: reset to recover from RX datapath errors
  * @RESET_TYPE_RX_DESC_FETCH: pcie error during rx descriptor fetch
@@ -86,7 +92,7 @@ enum reset_type {
 	RESET_TYPE_WORLD = 2,
 	RESET_TYPE_DISABLE = 3,
 	RESET_TYPE_MAX_METHOD,
-	RESET_TYPE_MONITOR,
+	RESET_TYPE_TX_WATCHDOG,
 	RESET_TYPE_INT_ERROR,
 	RESET_TYPE_RX_RECOVERY,
 	RESET_TYPE_RX_DESC_FETCH,
diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c
index cd0d0873d97..53d259e9018 100644
--- a/drivers/net/sfc/ethtool.c
+++ b/drivers/net/sfc/ethtool.c
@@ -12,24 +12,24 @@
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include "net_driver.h"
+#include "workarounds.h"
 #include "selftest.h"
 #include "efx.h"
 #include "ethtool.h"
 #include "falcon.h"
-#include "gmii.h"
 #include "spi.h"
-#include "mac.h"
+#include "mdio_10g.h"
 
 const char *efx_loopback_mode_names[] = {
 	[LOOPBACK_NONE]		= "NONE",
-	[LOOPBACK_MAC]		= "MAC",
+	[LOOPBACK_GMAC]		= "GMAC",
 	[LOOPBACK_XGMII]	= "XGMII",
 	[LOOPBACK_XGXS]		= "XGXS",
 	[LOOPBACK_XAUI] 	= "XAUI",
-	[LOOPBACK_PHY]		= "PHY",
-	[LOOPBACK_PHYXS]	= "PHY(XS)",
-	[LOOPBACK_PCS]	 	= "PHY(PCS)",
-	[LOOPBACK_PMAPMD]	= "PHY(PMAPMD)",
+	[LOOPBACK_GPHY]		= "GPHY",
+	[LOOPBACK_PHYXS]	= "PHYXS",
+	[LOOPBACK_PCS]	 	= "PCS",
+	[LOOPBACK_PMAPMD]	= "PMA/PMD",
 	[LOOPBACK_NETWORK]	= "NETWORK",
 };
 
@@ -172,10 +172,7 @@ static struct efx_ethtool_stat efx_ethtool_stats[] = {
 /* Number of ethtool statistics */
 #define EFX_ETHTOOL_NUM_STATS ARRAY_SIZE(efx_ethtool_stats)
 
-/* EEPROM range with gPXE configuration */
 #define EFX_ETHTOOL_EEPROM_MAGIC 0xEFAB
-#define EFX_ETHTOOL_EEPROM_MIN 0x800U
-#define EFX_ETHTOOL_EEPROM_MAX 0x1800U
 
 /**************************************************************************
  *
@@ -185,12 +182,16 @@ static struct efx_ethtool_stat efx_ethtool_stats[] = {
  */
 
 /* Identify device by flashing LEDs */
-static int efx_ethtool_phys_id(struct net_device *net_dev, u32 seconds)
+static int efx_ethtool_phys_id(struct net_device *net_dev, u32 count)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
 	efx->board_info.blink(efx, 1);
-	schedule_timeout_interruptible(seconds * HZ);
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (count)
+		schedule_timeout(count * HZ);
+	else
+		schedule();
 	efx->board_info.blink(efx, 0);
 	return 0;
 }
@@ -200,13 +201,15 @@ int efx_ethtool_get_settings(struct net_device *net_dev,
 			     struct ethtool_cmd *ecmd)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	int rc;
 
 	mutex_lock(&efx->mac_lock);
-	rc = falcon_xmac_get_settings(efx, ecmd);
+	efx->phy_op->get_settings(efx, ecmd);
 	mutex_unlock(&efx->mac_lock);
 
-	return rc;
+	/* Falcon GMAC does not support 1000Mbps HD */
+	ecmd->supported &= ~SUPPORTED_1000baseT_Half;
+
+	return 0;
 }
 
 /* This must be called with rtnl_lock held. */
@@ -216,8 +219,18 @@ int efx_ethtool_set_settings(struct net_device *net_dev,
 	struct efx_nic *efx = netdev_priv(net_dev);
 	int rc;
 
+	if (EFX_WORKAROUND_13963(efx) && !ecmd->autoneg)
+		return -EINVAL;
+
+	/* Falcon GMAC does not support 1000Mbps HD */
+	if (ecmd->speed == SPEED_1000 && ecmd->duplex != DUPLEX_FULL) {
+		EFX_LOG(efx, "rejecting unsupported 1000Mbps HD"
+			" setting\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&efx->mac_lock);
-	rc = falcon_xmac_set_settings(efx, ecmd);
+	rc = efx->phy_op->set_settings(efx, ecmd);
 	mutex_unlock(&efx->mac_lock);
 	if (!rc)
 		efx_reconfigure_port(efx);
@@ -241,10 +254,10 @@ static void efx_ethtool_get_drvinfo(struct net_device *net_dev,
  * @strings:		Ethtool strings, or %NULL
  * @data:		Ethtool test results, or %NULL
  * @test:		Pointer to test result (used only if data != %NULL)
- * @unit_format:	Unit name format (e.g. "channel\%d")
- * @unit_id:		Unit id (e.g. 0 for "channel0")
+ * @unit_format:	Unit name format (e.g. "chan\%d")
+ * @unit_id:		Unit id (e.g. 0 for "chan0")
  * @test_format:	Test name format (e.g. "loopback.\%s.tx.sent")
- * @test_id:		Test id (e.g. "PHY" for "loopback.PHY.tx_sent")
+ * @test_id:		Test id (e.g. "PHYXS" for "loopback.PHYXS.tx_sent")
  *
  * Fill in an individual self-test entry.
  */
@@ -261,18 +274,20 @@ static void efx_fill_test(unsigned int test_index,
 
 	/* Fill string, if applicable */
 	if (strings) {
-		snprintf(unit_str.name, sizeof(unit_str.name),
-			 unit_format, unit_id);
+		if (strchr(unit_format, '%'))
+			snprintf(unit_str.name, sizeof(unit_str.name),
+				 unit_format, unit_id);
+		else
+			strcpy(unit_str.name, unit_format);
 		snprintf(test_str.name, sizeof(test_str.name),
 			 test_format, test_id);
 		snprintf(strings[test_index].name,
 			 sizeof(strings[test_index].name),
-			 "%-9s%-17s", unit_str.name, test_str.name);
+			 "%-6s %-24s", unit_str.name, test_str.name);
 	}
 }
 
-#define EFX_PORT_NAME "port%d", 0
-#define EFX_CHANNEL_NAME(_channel) "channel%d", _channel->channel
+#define EFX_CHANNEL_NAME(_channel) "chan%d", _channel->channel
 #define EFX_TX_QUEUE_NAME(_tx_queue) "txq%d", _tx_queue->queue
 #define EFX_RX_QUEUE_NAME(_rx_queue) "rxq%d", _rx_queue->queue
 #define EFX_LOOPBACK_NAME(_mode, _counter)			\
@@ -307,11 +322,11 @@ static int efx_fill_loopback_test(struct efx_nic *efx,
 	}
 	efx_fill_test(test_index++, strings, data,
 		      &lb_tests->rx_good,
-		      EFX_PORT_NAME,
+		      "rx", 0,
 		      EFX_LOOPBACK_NAME(mode, "rx_good"));
 	efx_fill_test(test_index++, strings, data,
 		      &lb_tests->rx_bad,
-		      EFX_PORT_NAME,
+		      "rx", 0,
 		      EFX_LOOPBACK_NAME(mode, "rx_bad"));
 
 	return test_index;
@@ -330,7 +345,7 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
 				       u64 *data)
 {
 	struct efx_channel *channel;
-	unsigned int n = 0;
+	unsigned int n = 0, i;
 	enum efx_loopback_mode mode;
 
 	efx_fill_test(n++, strings, data, &tests->mii,
@@ -358,14 +373,12 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
 
 	efx_fill_test(n++, strings, data, &tests->registers,
 		      "core", 0, "registers", NULL);
-	efx_fill_test(n++, strings, data, &tests->phy,
-		      EFX_PORT_NAME, "phy", NULL);
+
+	for (i = 0; i < efx->phy_op->num_tests; i++)
+		efx_fill_test(n++, strings, data, &tests->phy[i],
+			      "phy", 0, efx->phy_op->test_names[i], NULL);
 
 	/* Loopback tests */
-	efx_fill_test(n++, strings, data, &tests->loopback_speed,
-		      EFX_PORT_NAME, "loopback.speed", NULL);
-	efx_fill_test(n++, strings, data, &tests->loopback_full_duplex,
-		      EFX_PORT_NAME, "loopback.full_duplex", NULL);
 	for (mode = LOOPBACK_NONE; mode <= LOOPBACK_TEST_MAX; mode++) {
 		if (!(efx->loopback_modes & (1 << mode)))
 			continue;
@@ -429,7 +442,7 @@ static void efx_ethtool_get_stats(struct net_device *net_dev,
 	EFX_BUG_ON_PARANOID(stats->n_stats != EFX_ETHTOOL_NUM_STATS);
 
 	/* Update MAC and NIC statistics */
-	net_dev->get_stats(net_dev);
+	dev_get_stats(net_dev);
 
 	/* Fill detailed statistics buffer */
 	for (i = 0; i < EFX_ETHTOOL_NUM_STATS; i++) {
@@ -476,7 +489,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_self_tests efx_tests;
-	int offline, already_up;
+	int already_up;
 	int rc;
 
 	ASSERT_RTNL();
@@ -496,24 +509,15 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
 	}
 
 	memset(&efx_tests, 0, sizeof(efx_tests));
-	offline = (test->flags & ETH_TEST_FL_OFFLINE);
-
-	/* Perform online self tests first */
-	rc = efx_online_test(efx, &efx_tests);
-	if (rc)
-		goto out;
 
-	/* Perform offline tests only if online tests passed */
-	if (offline)
-		rc = efx_offline_test(efx, &efx_tests,
-				      efx->loopback_modes);
+	rc = efx_selftest(efx, &efx_tests, test->flags);
 
- out:
 	if (!already_up)
 		dev_close(efx->net_dev);
 
-	EFX_LOG(efx, "%s all %sline self-tests\n",
-		rc == 0 ? "passed" : "failed", offline ? "off" : "on");
+	EFX_LOG(efx, "%s %sline self-tests\n",
+		rc == 0 ? "passed" : "failed",
+		(test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on");
 
  fail2:
  fail1:
@@ -545,8 +549,8 @@ static int efx_ethtool_get_eeprom_len(struct net_device *net_dev)
 
 	if (!spi)
 		return 0;
-	return min(spi->size, EFX_ETHTOOL_EEPROM_MAX) -
-		min(spi->size, EFX_ETHTOOL_EEPROM_MIN);
+	return min(spi->size, EFX_EEPROM_BOOTCONFIG_END) -
+		min(spi->size, EFX_EEPROM_BOOTCONFIG_START);
 }
 
 static int efx_ethtool_get_eeprom(struct net_device *net_dev,
@@ -557,8 +561,13 @@ static int efx_ethtool_get_eeprom(struct net_device *net_dev,
 	size_t len;
 	int rc;
 
-	rc = falcon_spi_read(spi, eeprom->offset + EFX_ETHTOOL_EEPROM_MIN,
+	rc = mutex_lock_interruptible(&efx->spi_lock);
+	if (rc)
+		return rc;
+	rc = falcon_spi_read(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START,
 			     eeprom->len, &len, buf);
+	mutex_unlock(&efx->spi_lock);
+
 	eeprom->magic = EFX_ETHTOOL_EEPROM_MAGIC;
 	eeprom->len = len;
 	return rc;
@@ -575,8 +584,13 @@ static int efx_ethtool_set_eeprom(struct net_device *net_dev,
 	if (eeprom->magic != EFX_ETHTOOL_EEPROM_MAGIC)
 		return -EINVAL;
 
-	rc = falcon_spi_write(spi, eeprom->offset + EFX_ETHTOOL_EEPROM_MIN,
+	rc = mutex_lock_interruptible(&efx->spi_lock);
+	if (rc)
+		return rc;
+	rc = falcon_spi_write(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START,
 			      eeprom->len, &len, buf);
+	mutex_unlock(&efx->spi_lock);
+
 	eeprom->len = len;
 	return rc;
 }
@@ -666,23 +680,52 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
 				      struct ethtool_pauseparam *pause)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	enum efx_fc_type flow_control = efx->flow_control;
-	int rc;
+	enum efx_fc_type wanted_fc;
+	bool reset;
 
-	flow_control &= ~(EFX_FC_RX | EFX_FC_TX | EFX_FC_AUTO);
-	flow_control |= pause->rx_pause ? EFX_FC_RX : 0;
-	flow_control |= pause->tx_pause ? EFX_FC_TX : 0;
-	flow_control |= pause->autoneg ? EFX_FC_AUTO : 0;
+	wanted_fc = ((pause->rx_pause ? EFX_FC_RX : 0) |
+		     (pause->tx_pause ? EFX_FC_TX : 0) |
+		     (pause->autoneg ? EFX_FC_AUTO : 0));
+
+	if ((wanted_fc & EFX_FC_TX) && !(wanted_fc & EFX_FC_RX)) {
+		EFX_LOG(efx, "Flow control unsupported: tx ON rx OFF\n");
+		return -EINVAL;
+	}
+
+	if (!(efx->phy_op->mmds & DEV_PRESENT_BIT(MDIO_MMD_AN)) &&
+	    (wanted_fc & EFX_FC_AUTO)) {
+		EFX_LOG(efx, "PHY does not support flow control "
+			"autonegotiation\n");
+		return -EINVAL;
+	}
+
+	/* TX flow control may automatically turn itself off if the
+	 * link partner (intermittently) stops responding to pause
+	 * frames. There isn't any indication that this has happened,
+	 * so the best we do is leave it up to the user to spot this
+	 * and fix it be cycling transmit flow control on this end. */
+	reset = (wanted_fc & EFX_FC_TX) && !(efx->wanted_fc & EFX_FC_TX);
+	if (EFX_WORKAROUND_11482(efx) && reset) {
+		if (falcon_rev(efx) >= FALCON_REV_B0) {
+			/* Recover by resetting the EM block */
+			if (efx->link_up)
+				falcon_drain_tx_fifo(efx);
+		} else {
+			/* Schedule a reset to recover */
+			efx_schedule_reset(efx, RESET_TYPE_INVISIBLE);
+		}
+	}
 
 	/* Try to push the pause parameters */
 	mutex_lock(&efx->mac_lock);
-	rc = falcon_xmac_set_pause(efx, flow_control);
-	mutex_unlock(&efx->mac_lock);
 
-	if (!rc)
-		efx_reconfigure_port(efx);
+	efx->wanted_fc = wanted_fc;
+	mdio_clause45_set_pause(efx);
+	__efx_reconfigure_port(efx);
 
-	return rc;
+	mutex_unlock(&efx->mac_lock);
+
+	return 0;
 }
 
 static void efx_ethtool_get_pauseparam(struct net_device *net_dev,
@@ -690,9 +733,9 @@ static void efx_ethtool_get_pauseparam(struct net_device *net_dev,
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	pause->rx_pause = !!(efx->flow_control & EFX_FC_RX);
-	pause->tx_pause = !!(efx->flow_control & EFX_FC_TX);
-	pause->autoneg = !!(efx->flow_control & EFX_FC_AUTO);
+	pause->rx_pause = !!(efx->wanted_fc & EFX_FC_RX);
+	pause->tx_pause = !!(efx->wanted_fc & EFX_FC_TX);
+	pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO);
 }
 
 
diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c
index 31ed1f49de0..5b9f2d9cc4e 100644
--- a/drivers/net/sfc/falcon.c
+++ b/drivers/net/sfc/falcon.c
@@ -15,11 +15,11 @@
 #include <linux/seq_file.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
+#include <linux/mii.h>
 #include "net_driver.h"
 #include "bitfield.h"
 #include "efx.h"
 #include "mac.h"
-#include "gmii.h"
 #include "spi.h"
 #include "falcon.h"
 #include "falcon_hwdefs.h"
@@ -70,6 +70,20 @@ static int disable_dma_stats;
 #define RX_DC_ENTRIES_ORDER 2
 #define RX_DC_BASE 0x100000
 
+static const unsigned int
+/* "Large" EEPROM device: Atmel AT25640 or similar
+ * 8 KB, 16-bit address, 32 B write block */
+large_eeprom_type = ((13 << SPI_DEV_TYPE_SIZE_LBN)
+		     | (2 << SPI_DEV_TYPE_ADDR_LEN_LBN)
+		     | (5 << SPI_DEV_TYPE_BLOCK_SIZE_LBN)),
+/* Default flash device: Atmel AT25F1024
+ * 128 KB, 24-bit address, 32 KB erase block, 256 B write block */
+default_flash_type = ((17 << SPI_DEV_TYPE_SIZE_LBN)
+		      | (3 << SPI_DEV_TYPE_ADDR_LEN_LBN)
+		      | (0x52 << SPI_DEV_TYPE_ERASE_CMD_LBN)
+		      | (15 << SPI_DEV_TYPE_ERASE_SIZE_LBN)
+		      | (8 << SPI_DEV_TYPE_BLOCK_SIZE_LBN));
+
 /* RX FIFO XOFF watermark
  *
  * When the amount of the RX FIFO increases used increases past this
@@ -770,15 +784,18 @@ static void falcon_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
 			   rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
 			   rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);
 
-	/* Count errors that are not in MAC stats. */
+	/* Count errors that are not in MAC stats.  Ignore expected
+	 * checksum errors during self-test. */
 	if (rx_ev_frm_trunc)
 		++rx_queue->channel->n_rx_frm_trunc;
 	else if (rx_ev_tobe_disc)
 		++rx_queue->channel->n_rx_tobe_disc;
-	else if (rx_ev_ip_hdr_chksum_err)
-		++rx_queue->channel->n_rx_ip_hdr_chksum_err;
-	else if (rx_ev_tcp_udp_chksum_err)
-		++rx_queue->channel->n_rx_tcp_udp_chksum_err;
+	else if (!efx->loopback_selftest) {
+		if (rx_ev_ip_hdr_chksum_err)
+			++rx_queue->channel->n_rx_ip_hdr_chksum_err;
+		else if (rx_ev_tcp_udp_chksum_err)
+			++rx_queue->channel->n_rx_tcp_udp_chksum_err;
+	}
 	if (rx_ev_ip_frag_err)
 		++rx_queue->channel->n_rx_ip_frag_err;
 
@@ -809,7 +826,7 @@ static void falcon_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
 #endif
 
 	if (unlikely(rx_ev_eth_crc_err && EFX_WORKAROUND_10750(efx) &&
-		     efx->phy_type == PHY_TYPE_10XPRESS))
+		     efx->phy_type == PHY_TYPE_SFX7101))
 		tenxpress_crc_err(efx);
 }
 
@@ -893,22 +910,20 @@ static void falcon_handle_global_event(struct efx_channel *channel,
 				       efx_qword_t *event)
 {
 	struct efx_nic *efx = channel->efx;
-	bool is_phy_event = false, handled = false;
+	bool handled = false;
 
-	/* Check for interrupt on either port.  Some boards have a
-	 * single PHY wired to the interrupt line for port 1. */
 	if (EFX_QWORD_FIELD(*event, G_PHY0_INTR) ||
 	    EFX_QWORD_FIELD(*event, G_PHY1_INTR) ||
-	    EFX_QWORD_FIELD(*event, XG_PHY_INTR))
-		is_phy_event = true;
+	    EFX_QWORD_FIELD(*event, XG_PHY_INTR) ||
+	    EFX_QWORD_FIELD(*event, XFP_PHY_INTR)) {
+		efx->phy_op->clear_interrupt(efx);
+		queue_work(efx->workqueue, &efx->phy_work);
+		handled = true;
+	}
 
 	if ((falcon_rev(efx) >= FALCON_REV_B0) &&
-	    EFX_QWORD_FIELD(*event, XG_MNT_INTR_B0))
-		is_phy_event = true;
-
-	if (is_phy_event) {
-		efx->phy_op->clear_interrupt(efx);
-		queue_work(efx->workqueue, &efx->reconfigure_work);
+	    EFX_QWORD_FIELD(*event, XG_MNT_INTR_B0)) {
+		queue_work(efx->workqueue, &efx->mac_work);
 		handled = true;
 	}
 
@@ -1151,6 +1166,19 @@ void falcon_generate_test_event(struct efx_channel *channel, unsigned int magic)
 	falcon_generate_event(channel, &test_event);
 }
 
+void falcon_sim_phy_event(struct efx_nic *efx)
+{
+	efx_qword_t phy_event;
+
+	EFX_POPULATE_QWORD_1(phy_event, EV_CODE, GLOBAL_EV_DECODE);
+	if (EFX_IS10G(efx))
+		EFX_SET_OWORD_FIELD(phy_event, XG_PHY_INTR, 1);
+	else
+		EFX_SET_OWORD_FIELD(phy_event, G_PHY0_INTR, 1);
+
+	falcon_generate_event(&efx->channel[0], &phy_event);
+}
+
 /**************************************************************************
  *
  * Flush handling
@@ -1375,9 +1403,9 @@ static irqreturn_t falcon_fatal_interrupt(struct efx_nic *efx)
 	}
 
 	/* Disable both devices */
-	pci_disable_device(efx->pci_dev);
+	pci_clear_master(efx->pci_dev);
 	if (FALCON_IS_DUAL_FUNC(efx))
-		pci_disable_device(nic_data->pci_dev2);
+		pci_clear_master(nic_data->pci_dev2);
 	falcon_disable_interrupts(efx);
 
 	if (++n_int_errors < FALCON_MAX_INT_ERRORS) {
@@ -1560,7 +1588,7 @@ int falcon_init_interrupt(struct efx_nic *efx)
 	efx_for_each_channel(channel, efx) {
 		rc = request_irq(channel->irq, falcon_msi_interrupt,
 				 IRQF_PROBE_SHARED, /* Not shared */
-				 efx->name, channel);
+				 channel->name, channel);
 		if (rc) {
 			EFX_ERR(efx, "failed to hook IRQ %d\n", channel->irq);
 			goto fail2;
@@ -1605,32 +1633,45 @@ void falcon_fini_interrupt(struct efx_nic *efx)
  **************************************************************************
  */
 
-#define FALCON_SPI_MAX_LEN ((unsigned) sizeof(efx_oword_t))
+#define FALCON_SPI_MAX_LEN sizeof(efx_oword_t)
+
+static int falcon_spi_poll(struct efx_nic *efx)
+{
+	efx_oword_t reg;
+	falcon_read(efx, &reg, EE_SPI_HCMD_REG_KER);
+	return EFX_OWORD_FIELD(reg, EE_SPI_HCMD_CMD_EN) ? -EBUSY : 0;
+}
 
 /* Wait for SPI command completion */
 static int falcon_spi_wait(struct efx_nic *efx)
 {
-	unsigned long timeout = jiffies + DIV_ROUND_UP(HZ, 10);
-	efx_oword_t reg;
-	bool cmd_en, timer_active;
+	/* Most commands will finish quickly, so we start polling at
+	 * very short intervals.  Sometimes the command may have to
+	 * wait for VPD or expansion ROM access outside of our
+	 * control, so we allow up to 100 ms. */
+	unsigned long timeout = jiffies + 1 + DIV_ROUND_UP(HZ, 10);
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		if (!falcon_spi_poll(efx))
+			return 0;
+		udelay(10);
+	}
 
 	for (;;) {
-		falcon_read(efx, &reg, EE_SPI_HCMD_REG_KER);
-		cmd_en = EFX_OWORD_FIELD(reg, EE_SPI_HCMD_CMD_EN);
-		timer_active = EFX_OWORD_FIELD(reg, EE_WR_TIMER_ACTIVE);
-		if (!cmd_en && !timer_active)
+		if (!falcon_spi_poll(efx))
 			return 0;
 		if (time_after_eq(jiffies, timeout)) {
 			EFX_ERR(efx, "timed out waiting for SPI\n");
 			return -ETIMEDOUT;
 		}
-		cpu_relax();
+		schedule_timeout_uninterruptible(1);
 	}
 }
 
-static int falcon_spi_cmd(const struct efx_spi_device *spi,
-			  unsigned int command, int address,
-			  const void *in, void *out, unsigned int len)
+int falcon_spi_cmd(const struct efx_spi_device *spi,
+		   unsigned int command, int address,
+		   const void *in, void *out, size_t len)
 {
 	struct efx_nic *efx = spi->efx;
 	bool addressed = (address >= 0);
@@ -1641,9 +1682,10 @@ static int falcon_spi_cmd(const struct efx_spi_device *spi,
 	/* Input validation */
 	if (len > FALCON_SPI_MAX_LEN)
 		return -EINVAL;
+	BUG_ON(!mutex_is_locked(&efx->spi_lock));
 
-	/* Check SPI not currently being accessed */
-	rc = falcon_spi_wait(efx);
+	/* Check that previous command is not still running */
+	rc = falcon_spi_poll(efx);
 	if (rc)
 		return rc;
 
@@ -1685,8 +1727,8 @@ static int falcon_spi_cmd(const struct efx_spi_device *spi,
 	return 0;
 }
 
-static unsigned int
-falcon_spi_write_limit(const struct efx_spi_device *spi, unsigned int start)
+static size_t
+falcon_spi_write_limit(const struct efx_spi_device *spi, size_t start)
 {
 	return min(FALCON_SPI_MAX_LEN,
 		   (spi->block_size - (start & (spi->block_size - 1))));
@@ -1699,38 +1741,40 @@ efx_spi_munge_command(const struct efx_spi_device *spi,
 	return command | (((address >> 8) & spi->munge_address) << 3);
 }
 
-
-static int falcon_spi_fast_wait(const struct efx_spi_device *spi)
+/* Wait up to 10 ms for buffered write completion */
+int falcon_spi_wait_write(const struct efx_spi_device *spi)
 {
+	struct efx_nic *efx = spi->efx;
+	unsigned long timeout = jiffies + 1 + DIV_ROUND_UP(HZ, 100);
 	u8 status;
-	int i, rc;
-
-	/* Wait up to 1000us for flash/EEPROM to finish a fast operation. */
-	for (i = 0; i < 50; i++) {
-		udelay(20);
+	int rc;
 
+	for (;;) {
 		rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL,
 				    &status, sizeof(status));
 		if (rc)
 			return rc;
 		if (!(status & SPI_STATUS_NRDY))
 			return 0;
+		if (time_after_eq(jiffies, timeout)) {
+			EFX_ERR(efx, "SPI write timeout on device %d"
+				" last status=0x%02x\n",
+				spi->device_id, status);
+			return -ETIMEDOUT;
+		}
+		schedule_timeout_uninterruptible(1);
 	}
-	EFX_ERR(spi->efx,
-		"timed out waiting for device %d last status=0x%02x\n",
-		spi->device_id, status);
-	return -ETIMEDOUT;
 }
 
 int falcon_spi_read(const struct efx_spi_device *spi, loff_t start,
 		    size_t len, size_t *retlen, u8 *buffer)
 {
-	unsigned int command, block_len, pos = 0;
+	size_t block_len, pos = 0;
+	unsigned int command;
 	int rc = 0;
 
 	while (pos < len) {
-		block_len = min((unsigned int)len - pos,
-				FALCON_SPI_MAX_LEN);
+		block_len = min(len - pos, FALCON_SPI_MAX_LEN);
 
 		command = efx_spi_munge_command(spi, SPI_READ, start + pos);
 		rc = falcon_spi_cmd(spi, command, start + pos, NULL,
@@ -1756,7 +1800,8 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start,
 		     size_t len, size_t *retlen, const u8 *buffer)
 {
 	u8 verify_buffer[FALCON_SPI_MAX_LEN];
-	unsigned int command, block_len, pos = 0;
+	size_t block_len, pos = 0;
+	unsigned int command;
 	int rc = 0;
 
 	while (pos < len) {
@@ -1764,7 +1809,7 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start,
 		if (rc)
 			break;
 
-		block_len = min((unsigned int)len - pos,
+		block_len = min(len - pos,
 				falcon_spi_write_limit(spi, start + pos));
 		command = efx_spi_munge_command(spi, SPI_WRITE, start + pos);
 		rc = falcon_spi_cmd(spi, command, start + pos,
@@ -1772,7 +1817,7 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start,
 		if (rc)
 			break;
 
-		rc = falcon_spi_fast_wait(spi);
+		rc = falcon_spi_wait_write(spi);
 		if (rc)
 			break;
 
@@ -1805,40 +1850,61 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start,
  *
  **************************************************************************
  */
-void falcon_drain_tx_fifo(struct efx_nic *efx)
+
+static int falcon_reset_macs(struct efx_nic *efx)
 {
-	efx_oword_t temp;
+	efx_oword_t reg;
 	int count;
 
-	if ((falcon_rev(efx) < FALCON_REV_B0) ||
-	    (efx->loopback_mode != LOOPBACK_NONE))
-		return;
+	if (falcon_rev(efx) < FALCON_REV_B0) {
+		/* It's not safe to use GLB_CTL_REG to reset the
+		 * macs, so instead use the internal MAC resets
+		 */
+		if (!EFX_IS10G(efx)) {
+			EFX_POPULATE_OWORD_1(reg, GM_SW_RST, 1);
+			falcon_write(efx, &reg, GM_CFG1_REG);
+			udelay(1000);
+
+			EFX_POPULATE_OWORD_1(reg, GM_SW_RST, 0);
+			falcon_write(efx, &reg, GM_CFG1_REG);
+			udelay(1000);
+			return 0;
+		} else {
+			EFX_POPULATE_OWORD_1(reg, XM_CORE_RST, 1);
+			falcon_write(efx, &reg, XM_GLB_CFG_REG);
+
+			for (count = 0; count < 10000; count++) {
+				falcon_read(efx, &reg, XM_GLB_CFG_REG);
+				if (EFX_OWORD_FIELD(reg, XM_CORE_RST) == 0)
+					return 0;
+				udelay(10);
+			}
 
-	falcon_read(efx, &temp, MAC0_CTRL_REG_KER);
-	/* There is no point in draining more than once */
-	if (EFX_OWORD_FIELD(temp, TXFIFO_DRAIN_EN_B0))
-		return;
+			EFX_ERR(efx, "timed out waiting for XMAC core reset\n");
+			return -ETIMEDOUT;
+		}
+	}
 
 	/* MAC stats will fail whilst the TX fifo is draining. Serialise
 	 * the drain sequence with the statistics fetch */
 	spin_lock(&efx->stats_lock);
 
-	EFX_SET_OWORD_FIELD(temp, TXFIFO_DRAIN_EN_B0, 1);
-	falcon_write(efx, &temp, MAC0_CTRL_REG_KER);
+	falcon_read(efx, &reg, MAC0_CTRL_REG_KER);
+	EFX_SET_OWORD_FIELD(reg, TXFIFO_DRAIN_EN_B0, 1);
+	falcon_write(efx, &reg, MAC0_CTRL_REG_KER);
 
-	/* Reset the MAC and EM block. */
-	falcon_read(efx, &temp, GLB_CTL_REG_KER);
-	EFX_SET_OWORD_FIELD(temp, RST_XGTX, 1);
-	EFX_SET_OWORD_FIELD(temp, RST_XGRX, 1);
-	EFX_SET_OWORD_FIELD(temp, RST_EM, 1);
-	falcon_write(efx, &temp, GLB_CTL_REG_KER);
+	falcon_read(efx, &reg, GLB_CTL_REG_KER);
+	EFX_SET_OWORD_FIELD(reg, RST_XGTX, 1);
+	EFX_SET_OWORD_FIELD(reg, RST_XGRX, 1);
+	EFX_SET_OWORD_FIELD(reg, RST_EM, 1);
+	falcon_write(efx, &reg, GLB_CTL_REG_KER);
 
 	count = 0;
 	while (1) {
-		falcon_read(efx, &temp, GLB_CTL_REG_KER);
-		if (!EFX_OWORD_FIELD(temp, RST_XGTX) &&
-		    !EFX_OWORD_FIELD(temp, RST_XGRX) &&
-		    !EFX_OWORD_FIELD(temp, RST_EM)) {
+		falcon_read(efx, &reg, GLB_CTL_REG_KER);
+		if (!EFX_OWORD_FIELD(reg, RST_XGTX) &&
+		    !EFX_OWORD_FIELD(reg, RST_XGRX) &&
+		    !EFX_OWORD_FIELD(reg, RST_EM)) {
 			EFX_LOG(efx, "Completed MAC reset after %d loops\n",
 				count);
 			break;
@@ -1855,21 +1921,39 @@ void falcon_drain_tx_fifo(struct efx_nic *efx)
 
 	/* If we've reset the EM block and the link is up, then
 	 * we'll have to kick the XAUI link so the PHY can recover */
-	if (efx->link_up && EFX_WORKAROUND_5147(efx))
+	if (efx->link_up && EFX_IS10G(efx) && EFX_WORKAROUND_5147(efx))
 		falcon_reset_xaui(efx);
+
+	return 0;
+}
+
+void falcon_drain_tx_fifo(struct efx_nic *efx)
+{
+	efx_oword_t reg;
+
+	if ((falcon_rev(efx) < FALCON_REV_B0) ||
+	    (efx->loopback_mode != LOOPBACK_NONE))
+		return;
+
+	falcon_read(efx, &reg, MAC0_CTRL_REG_KER);
+	/* There is no point in draining more than once */
+	if (EFX_OWORD_FIELD(reg, TXFIFO_DRAIN_EN_B0))
+		return;
+
+	falcon_reset_macs(efx);
 }
 
 void falcon_deconfigure_mac_wrapper(struct efx_nic *efx)
 {
-	efx_oword_t temp;
+	efx_oword_t reg;
 
 	if (falcon_rev(efx) < FALCON_REV_B0)
 		return;
 
 	/* Isolate the MAC -> RX */
-	falcon_read(efx, &temp, RX_CFG_REG_KER);
-	EFX_SET_OWORD_FIELD(temp, RX_INGR_EN_B0, 0);
-	falcon_write(efx, &temp, RX_CFG_REG_KER);
+	falcon_read(efx, &reg, RX_CFG_REG_KER);
+	EFX_SET_OWORD_FIELD(reg, RX_INGR_EN_B0, 0);
+	falcon_write(efx, &reg, RX_CFG_REG_KER);
 
 	if (!efx->link_up)
 		falcon_drain_tx_fifo(efx);
@@ -1881,14 +1965,12 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
 	int link_speed;
 	bool tx_fc;
 
-	if (efx->link_options & GM_LPA_10000)
-		link_speed = 0x3;
-	else if (efx->link_options & GM_LPA_1000)
-		link_speed = 0x2;
-	else if (efx->link_options & GM_LPA_100)
-		link_speed = 0x1;
-	else
-		link_speed = 0x0;
+	switch (efx->link_speed) {
+	case 10000: link_speed = 3; break;
+	case 1000:  link_speed = 2; break;
+	case 100:   link_speed = 1; break;
+	default:    link_speed = 0; break;
+	}
 	/* MAC_LINK_STATUS controls MAC backpressure but doesn't work
 	 * as advertised.  Disable to ensure packets are not
 	 * indefinitely held and TX queue can be flushed at any point
@@ -1914,7 +1996,7 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
 	/* Transmission of pause frames when RX crosses the threshold is
 	 * covered by RX_XOFF_MAC_EN and XM_TX_CFG_REG:XM_FCNTL.
 	 * Action on receipt of pause frames is controller by XM_DIS_FCNTL */
-	tx_fc = !!(efx->flow_control & EFX_FC_TX);
+	tx_fc = !!(efx->link_fc & EFX_FC_TX);
 	falcon_read(efx, &reg, RX_CFG_REG_KER);
 	EFX_SET_OWORD_FIELD_VER(efx, reg, RX_XOFF_MAC_EN, tx_fc);
 
@@ -1998,7 +2080,8 @@ static int falcon_gmii_wait(struct efx_nic *efx)
 	efx_dword_t md_stat;
 	int count;
 
-	for (count = 0; count < 1000; count++) {	/* wait upto 10ms */
+	/* wait upto 50ms - taken max from datasheet */
+	for (count = 0; count < 5000; count++) {
 		falcon_readl(efx, &md_stat, MD_STAT_REG_KER);
 		if (EFX_DWORD_FIELD(md_stat, MD_BSY) == 0) {
 			if (EFX_DWORD_FIELD(md_stat, MD_LNFL) != 0 ||
@@ -2162,10 +2245,14 @@ static void falcon_init_mdio(struct mii_if_info *gmii)
 static int falcon_probe_phy(struct efx_nic *efx)
 {
 	switch (efx->phy_type) {
-	case PHY_TYPE_10XPRESS:
-		efx->phy_op = &falcon_tenxpress_phy_ops;
+	case PHY_TYPE_SFX7101:
+		efx->phy_op = &falcon_sfx7101_phy_ops;
+		break;
+	case PHY_TYPE_SFT9001A:
+	case PHY_TYPE_SFT9001B:
+		efx->phy_op = &falcon_sft9001_phy_ops;
 		break;
-	case PHY_TYPE_XFP:
+	case PHY_TYPE_QT2022C2:
 		efx->phy_op = &falcon_xfp_phy_ops;
 		break;
 	default:
@@ -2174,10 +2261,59 @@ static int falcon_probe_phy(struct efx_nic *efx)
 		return -1;
 	}
 
-	efx->loopback_modes = LOOPBACKS_10G_INTERNAL | efx->phy_op->loopbacks;
+	if (efx->phy_op->macs & EFX_XMAC)
+		efx->loopback_modes |= ((1 << LOOPBACK_XGMII) |
+					(1 << LOOPBACK_XGXS) |
+					(1 << LOOPBACK_XAUI));
+	if (efx->phy_op->macs & EFX_GMAC)
+		efx->loopback_modes |= (1 << LOOPBACK_GMAC);
+	efx->loopback_modes |= efx->phy_op->loopbacks;
+
 	return 0;
 }
 
+int falcon_switch_mac(struct efx_nic *efx)
+{
+	struct efx_mac_operations *old_mac_op = efx->mac_op;
+	efx_oword_t nic_stat;
+	unsigned strap_val;
+
+	/* Internal loopbacks override the phy speed setting */
+	if (efx->loopback_mode == LOOPBACK_GMAC) {
+		efx->link_speed = 1000;
+		efx->link_fd = true;
+	} else if (LOOPBACK_INTERNAL(efx)) {
+		efx->link_speed = 10000;
+		efx->link_fd = true;
+	}
+
+	efx->mac_op = (EFX_IS10G(efx) ?
+		       &falcon_xmac_operations : &falcon_gmac_operations);
+	if (old_mac_op == efx->mac_op)
+		return 0;
+
+	WARN_ON(!mutex_is_locked(&efx->mac_lock));
+
+	/* Not all macs support a mac-level link state */
+	efx->mac_up = true;
+
+	falcon_read(efx, &nic_stat, NIC_STAT_REG);
+	strap_val = EFX_IS10G(efx) ? 5 : 3;
+	if (falcon_rev(efx) >= FALCON_REV_B0) {
+		EFX_SET_OWORD_FIELD(nic_stat, EE_STRAP_EN, 1);
+		EFX_SET_OWORD_FIELD(nic_stat, EE_STRAP_OVR, strap_val);
+		falcon_write(efx, &nic_stat, NIC_STAT_REG);
+	} else {
+		/* Falcon A1 does not support 1G/10G speed switching
+		 * and must not be used with a PHY that does. */
+		BUG_ON(EFX_OWORD_FIELD(nic_stat, STRAP_PINS) != strap_val);
+	}
+
+
+	EFX_LOG(efx, "selected %cMAC\n", EFX_IS10G(efx) ? 'X' : 'G');
+	return falcon_reset_macs(efx);
+}
+
 /* This call is responsible for hooking in the MAC and PHY operations */
 int falcon_probe_port(struct efx_nic *efx)
 {
@@ -2194,9 +2330,9 @@ int falcon_probe_port(struct efx_nic *efx)
 
 	/* Hardware flow ctrl. FalconA RX FIFO too small for pause generation */
 	if (falcon_rev(efx) >= FALCON_REV_B0)
-		efx->flow_control = EFX_FC_RX | EFX_FC_TX;
+		efx->wanted_fc = EFX_FC_RX | EFX_FC_TX;
 	else
-		efx->flow_control = EFX_FC_RX;
+		efx->wanted_fc = EFX_FC_RX;
 
 	/* Allocate buffer for stats */
 	rc = falcon_alloc_buffer(efx, &efx->stats_buffer,
@@ -2253,13 +2389,18 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out)
 	__le16 *word, *limit;
 	u32 csum;
 
-	region = kmalloc(NVCONFIG_END, GFP_KERNEL);
+	spi = efx->spi_flash ? efx->spi_flash : efx->spi_eeprom;
+	if (!spi)
+		return -EINVAL;
+
+	region = kmalloc(FALCON_NVCONFIG_END, GFP_KERNEL);
 	if (!region)
 		return -ENOMEM;
 	nvconfig = region + NVCONFIG_OFFSET;
 
-	spi = efx->spi_flash ? efx->spi_flash : efx->spi_eeprom;
-	rc = falcon_spi_read(spi, 0, NVCONFIG_END, NULL, region);
+	mutex_lock(&efx->spi_lock);
+	rc = falcon_spi_read(spi, 0, FALCON_NVCONFIG_END, NULL, region);
+	mutex_unlock(&efx->spi_lock);
 	if (rc) {
 		EFX_ERR(efx, "Failed to read %s\n",
 			efx->spi_flash ? "flash" : "EEPROM");
@@ -2283,7 +2424,7 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out)
 		limit = (__le16 *) (nvconfig + 1);
 	} else {
 		word = region;
-		limit = region + NVCONFIG_END;
+		limit = region + FALCON_NVCONFIG_END;
 	}
 	for (csum = 0; word < limit; ++word)
 		csum += le16_to_cpu(*word);
@@ -2325,6 +2466,10 @@ static struct {
 	  EFX_OWORD32(0x000003FF, 0x00000000, 0x00000000, 0x00000000) },
 	{ DP_CTRL_REG,
 	  EFX_OWORD32(0x00000FFF, 0x00000000, 0x00000000, 0x00000000) },
+	{ GM_CFG2_REG,
+	  EFX_OWORD32(0x00007337, 0x00000000, 0x00000000, 0x00000000) },
+	{ GMF_CFG0_REG,
+	  EFX_OWORD32(0x00001F1F, 0x00000000, 0x00000000, 0x00000000) },
 	{ XM_GLB_CFG_REG,
 	  EFX_OWORD32(0x00000C68, 0x00000000, 0x00000000, 0x00000000) },
 	{ XM_TX_CFG_REG,
@@ -2545,7 +2690,7 @@ static int falcon_spi_device_init(struct efx_nic *efx,
 	struct efx_spi_device *spi_device;
 
 	if (device_type != 0) {
-		spi_device = kmalloc(sizeof(*spi_device), GFP_KERNEL);
+		spi_device = kzalloc(sizeof(*spi_device), GFP_KERNEL);
 		if (!spi_device)
 			return -ENOMEM;
 		spi_device->device_id = device_id;
@@ -2555,6 +2700,11 @@ static int falcon_spi_device_init(struct efx_nic *efx,
 			SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_ADDR_LEN);
 		spi_device->munge_address = (spi_device->size == 1 << 9 &&
 					     spi_device->addr_len == 1);
+		spi_device->erase_command =
+			SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_ERASE_CMD);
+		spi_device->erase_size =
+			1 << SPI_DEV_TYPE_FIELD(device_type,
+						SPI_DEV_TYPE_ERASE_SIZE);
 		spi_device->block_size =
 			1 << SPI_DEV_TYPE_FIELD(device_type,
 						SPI_DEV_TYPE_BLOCK_SIZE);
@@ -2645,6 +2795,7 @@ static int falcon_probe_nvconfig(struct efx_nic *efx)
 static int falcon_probe_nic_variant(struct efx_nic *efx)
 {
 	efx_oword_t altera_build;
+	efx_oword_t nic_stat;
 
 	falcon_read(efx, &altera_build, ALTERA_BUILD_REG_KER);
 	if (EFX_OWORD_FIELD(altera_build, VER_ALL)) {
@@ -2652,27 +2803,20 @@ static int falcon_probe_nic_variant(struct efx_nic *efx)
 		return -ENODEV;
 	}
 
+	falcon_read(efx, &nic_stat, NIC_STAT_REG);
+
 	switch (falcon_rev(efx)) {
 	case FALCON_REV_A0:
 	case 0xff:
 		EFX_ERR(efx, "Falcon rev A0 not supported\n");
 		return -ENODEV;
 
-	case FALCON_REV_A1:{
-		efx_oword_t nic_stat;
-
-		falcon_read(efx, &nic_stat, NIC_STAT_REG);
-
+	case FALCON_REV_A1:
 		if (EFX_OWORD_FIELD(nic_stat, STRAP_PCIE) == 0) {
 			EFX_ERR(efx, "Falcon rev A1 PCI-X not supported\n");
 			return -ENODEV;
 		}
-		if (!EFX_OWORD_FIELD(nic_stat, STRAP_10G)) {
-			EFX_ERR(efx, "1G mode not supported\n");
-			return -ENODEV;
-		}
 		break;
-	}
 
 	case FALCON_REV_B0:
 		break;
@@ -2682,6 +2826,9 @@ static int falcon_probe_nic_variant(struct efx_nic *efx)
 		return -ENODEV;
 	}
 
+	/* Initial assumed speed */
+	efx->link_speed = EFX_OWORD_FIELD(nic_stat, STRAP_10G) ? 10000 : 1000;
+
 	return 0;
 }
 
@@ -2689,80 +2836,37 @@ static int falcon_probe_nic_variant(struct efx_nic *efx)
 static void falcon_probe_spi_devices(struct efx_nic *efx)
 {
 	efx_oword_t nic_stat, gpio_ctl, ee_vpd_cfg;
-	bool has_flash, has_eeprom, boot_is_external;
+	int boot_dev;
 
 	falcon_read(efx, &gpio_ctl, GPIO_CTL_REG_KER);
 	falcon_read(efx, &nic_stat, NIC_STAT_REG);
 	falcon_read(efx, &ee_vpd_cfg, EE_VPD_CFG_REG_KER);
 
-	has_flash = EFX_OWORD_FIELD(nic_stat, SF_PRST);
-	has_eeprom = EFX_OWORD_FIELD(nic_stat, EE_PRST);
-	boot_is_external = EFX_OWORD_FIELD(gpio_ctl, BOOTED_USING_NVDEVICE);
-
-	if (has_flash) {
-		/* Default flash SPI device: Atmel AT25F1024
-		 * 128 KB, 24-bit address, 32 KB erase block,
-		 * 256 B write block
-		 */
-		u32 flash_device_type =
-			(17 << SPI_DEV_TYPE_SIZE_LBN)
-			| (3 << SPI_DEV_TYPE_ADDR_LEN_LBN)
-			| (0x52 << SPI_DEV_TYPE_ERASE_CMD_LBN)
-			| (15 << SPI_DEV_TYPE_ERASE_SIZE_LBN)
-			| (8 << SPI_DEV_TYPE_BLOCK_SIZE_LBN);
-
-		falcon_spi_device_init(efx, &efx->spi_flash,
-				       EE_SPI_FLASH, flash_device_type);
-
-		if (!boot_is_external) {
-			/* Disable VPD and set clock dividers to safe
-			 * values for initial programming.
-			 */
-			EFX_LOG(efx, "Booted from internal ASIC settings;"
-				" setting SPI config\n");
-			EFX_POPULATE_OWORD_3(ee_vpd_cfg, EE_VPD_EN, 0,
-					     /* 125 MHz / 7 ~= 20 MHz */
-					     EE_SF_CLOCK_DIV, 7,
-					     /* 125 MHz / 63 ~= 2 MHz */
-					     EE_EE_CLOCK_DIV, 63);
-			falcon_write(efx, &ee_vpd_cfg, EE_VPD_CFG_REG_KER);
-		}
-	}
-
-	if (has_eeprom) {
-		u32 eeprom_device_type;
-
-		/* If it has no flash, it must have a large EEPROM
-		 * for chip config; otherwise check whether 9-bit
-		 * addressing is used for VPD configuration
-		 */
-		if (has_flash &&
-		    (!boot_is_external ||
-		     EFX_OWORD_FIELD(ee_vpd_cfg, EE_VPD_EN_AD9_MODE))) {
-			/* Default SPI device: Atmel AT25040 or similar
-			 * 512 B, 9-bit address, 8 B write block
-			 */
-			eeprom_device_type =
-				(9 << SPI_DEV_TYPE_SIZE_LBN)
-				| (1 << SPI_DEV_TYPE_ADDR_LEN_LBN)
-				| (3 << SPI_DEV_TYPE_BLOCK_SIZE_LBN);
-		} else {
-			/* "Large" SPI device: Atmel AT25640 or similar
-			 * 8 KB, 16-bit address, 32 B write block
-			 */
-			eeprom_device_type =
-				(13 << SPI_DEV_TYPE_SIZE_LBN)
-				| (2 << SPI_DEV_TYPE_ADDR_LEN_LBN)
-				| (5 << SPI_DEV_TYPE_BLOCK_SIZE_LBN);
-		}
-
-		falcon_spi_device_init(efx, &efx->spi_eeprom,
-				       EE_SPI_EEPROM, eeprom_device_type);
-	}
-
-	EFX_LOG(efx, "flash is %s, EEPROM is %s\n",
-		(has_flash ? "present" : "absent"),
-		(has_eeprom ? "present" : "absent"));
+	if (EFX_OWORD_FIELD(gpio_ctl, BOOTED_USING_NVDEVICE)) {
+		boot_dev = (EFX_OWORD_FIELD(nic_stat, SF_PRST) ?
+			    EE_SPI_FLASH : EE_SPI_EEPROM);
+		EFX_LOG(efx, "Booted from %s\n",
+			boot_dev == EE_SPI_FLASH ? "flash" : "EEPROM");
+	} else {
+		/* Disable VPD and set clock dividers to safe
+		 * values for initial programming. */
+		boot_dev = -1;
+		EFX_LOG(efx, "Booted from internal ASIC settings;"
+			" setting SPI config\n");
+		EFX_POPULATE_OWORD_3(ee_vpd_cfg, EE_VPD_EN, 0,
+				     /* 125 MHz / 7 ~= 20 MHz */
+				     EE_SF_CLOCK_DIV, 7,
+				     /* 125 MHz / 63 ~= 2 MHz */
+				     EE_EE_CLOCK_DIV, 63);
+		falcon_write(efx, &ee_vpd_cfg, EE_VPD_CFG_REG_KER);
+	}
+
+	if (boot_dev == EE_SPI_FLASH)
+		falcon_spi_device_init(efx, &efx->spi_flash, EE_SPI_FLASH,
+				       default_flash_type);
+	if (boot_dev == EE_SPI_EEPROM)
+		falcon_spi_device_init(efx, &efx->spi_eeprom, EE_SPI_EEPROM,
+				       large_eeprom_type);
 }
 
 int falcon_probe_nic(struct efx_nic *efx)
@@ -2825,10 +2929,10 @@ int falcon_probe_nic(struct efx_nic *efx)
 		goto fail5;
 
 	/* Initialise I2C adapter */
- 	efx->i2c_adap.owner = THIS_MODULE;
+	efx->i2c_adap.owner = THIS_MODULE;
 	nic_data->i2c_data = falcon_i2c_bit_operations;
 	nic_data->i2c_data.data = efx;
- 	efx->i2c_adap.algo_data = &nic_data->i2c_data;
+	efx->i2c_adap.algo_data = &nic_data->i2c_data;
 	efx->i2c_adap.dev.parent = &efx->pci_dev->dev;
 	strlcpy(efx->i2c_adap.name, "SFC4000 GPIO", sizeof(efx->i2c_adap.name));
 	rc = i2c_bit_add_bus(&efx->i2c_adap);
@@ -2862,20 +2966,18 @@ int falcon_init_nic(struct efx_nic *efx)
 	unsigned thresh;
 	int rc;
 
-	/* Set up the address region register. This is only needed
-	 * for the B0 FPGA, but since we are just pushing in the
-	 * reset defaults this may as well be unconditional. */
-	EFX_POPULATE_OWORD_4(temp, ADR_REGION0, 0,
-				   ADR_REGION1, (1 << 16),
-				   ADR_REGION2, (2 << 16),
-				   ADR_REGION3, (3 << 16));
-	falcon_write(efx, &temp, ADR_REGION_REG_KER);
-
 	/* Use on-chip SRAM */
 	falcon_read(efx, &temp, NIC_STAT_REG);
 	EFX_SET_OWORD_FIELD(temp, ONCHIP_SRAM, 1);
 	falcon_write(efx, &temp, NIC_STAT_REG);
 
+	/* Set the source of the GMAC clock */
+	if (falcon_rev(efx) == FALCON_REV_B0) {
+		falcon_read(efx, &temp, GPIO_CTL_REG_KER);
+		EFX_SET_OWORD_FIELD(temp, GPIO_USE_NIC_CLK, true);
+		falcon_write(efx, &temp, GPIO_CTL_REG_KER);
+	}
+
 	/* Set buffer table mode */
 	EFX_POPULATE_OWORD_1(temp, BUF_TBL_MODE, BUF_TBL_MODE_FULL);
 	falcon_write(efx, &temp, BUF_TBL_CFG_REG_KER);
diff --git a/drivers/net/sfc/falcon.h b/drivers/net/sfc/falcon.h
index be025ba7a6c..7869c3d7438 100644
--- a/drivers/net/sfc/falcon.h
+++ b/drivers/net/sfc/falcon.h
@@ -12,6 +12,7 @@
 #define EFX_FALCON_H
 
 #include "net_driver.h"
+#include "efx.h"
 
 /*
  * Falcon hardware control
@@ -65,6 +66,7 @@ extern int falcon_probe_port(struct efx_nic *efx);
 extern void falcon_remove_port(struct efx_nic *efx);
 
 /* MAC/PHY */
+extern int falcon_switch_mac(struct efx_nic *efx);
 extern bool falcon_xaui_link_ok(struct efx_nic *efx);
 extern int falcon_dma_stats(struct efx_nic *efx,
 			    unsigned int done_offset);
@@ -77,6 +79,7 @@ extern int falcon_init_interrupt(struct efx_nic *efx);
 extern void falcon_enable_interrupts(struct efx_nic *efx);
 extern void falcon_generate_test_event(struct efx_channel *channel,
 				       unsigned int magic);
+extern void falcon_sim_phy_event(struct efx_nic *efx);
 extern void falcon_generate_interrupt(struct efx_nic *efx);
 extern void falcon_set_int_moderation(struct efx_channel *channel);
 extern void falcon_disable_interrupts(struct efx_nic *efx);
diff --git a/drivers/net/sfc/falcon_gmac.c b/drivers/net/sfc/falcon_gmac.c
new file mode 100644
index 00000000000..8865eae20ac
--- /dev/null
+++ b/drivers/net/sfc/falcon_gmac.c
@@ -0,0 +1,229 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2006-2008 Solarflare Communications Inc.
+ *
+ * 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, incorporated herein by reference.
+ */
+
+#include <linux/delay.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "falcon.h"
+#include "mac.h"
+#include "falcon_hwdefs.h"
+#include "falcon_io.h"
+#include "gmii.h"
+
+/**************************************************************************
+ *
+ * MAC operations
+ *
+ *************************************************************************/
+
+static void falcon_reconfigure_gmac(struct efx_nic *efx)
+{
+	bool loopback, tx_fc, rx_fc, bytemode;
+	int if_mode;
+	unsigned int max_frame_len;
+	efx_oword_t reg;
+
+	/* Configuration register 1 */
+	tx_fc = (efx->link_fc & EFX_FC_TX) || !efx->link_fd;
+	rx_fc = !!(efx->link_fc & EFX_FC_RX);
+	loopback = (efx->loopback_mode == LOOPBACK_GMAC);
+	bytemode = (efx->link_speed == 1000);
+
+	EFX_POPULATE_OWORD_5(reg,
+			     GM_LOOP, loopback,
+			     GM_TX_EN, 1,
+			     GM_TX_FC_EN, tx_fc,
+			     GM_RX_EN, 1,
+			     GM_RX_FC_EN, rx_fc);
+	falcon_write(efx, &reg, GM_CFG1_REG);
+	udelay(10);
+
+	/* Configuration register 2 */
+	if_mode = (bytemode) ? 2 : 1;
+	EFX_POPULATE_OWORD_5(reg,
+			     GM_IF_MODE, if_mode,
+			     GM_PAD_CRC_EN, 1,
+			     GM_LEN_CHK, 1,
+			     GM_FD, efx->link_fd,
+			     GM_PAMBL_LEN, 0x7/*datasheet recommended */);
+
+	falcon_write(efx, &reg, GM_CFG2_REG);
+	udelay(10);
+
+	/* Max frame len register */
+	max_frame_len = EFX_MAX_FRAME_LEN(efx->net_dev->mtu);
+	EFX_POPULATE_OWORD_1(reg, GM_MAX_FLEN, max_frame_len);
+	falcon_write(efx, &reg, GM_MAX_FLEN_REG);
+	udelay(10);
+
+	/* FIFO configuration register 0 */
+	EFX_POPULATE_OWORD_5(reg,
+			     GMF_FTFENREQ, 1,
+			     GMF_STFENREQ, 1,
+			     GMF_FRFENREQ, 1,
+			     GMF_SRFENREQ, 1,
+			     GMF_WTMENREQ, 1);
+	falcon_write(efx, &reg, GMF_CFG0_REG);
+	udelay(10);
+
+	/* FIFO configuration register 1 */
+	EFX_POPULATE_OWORD_2(reg,
+			     GMF_CFGFRTH, 0x12,
+			     GMF_CFGXOFFRTX, 0xffff);
+	falcon_write(efx, &reg, GMF_CFG1_REG);
+	udelay(10);
+
+	/* FIFO configuration register 2 */
+	EFX_POPULATE_OWORD_2(reg,
+			     GMF_CFGHWM, 0x3f,
+			     GMF_CFGLWM, 0xa);
+	falcon_write(efx, &reg, GMF_CFG2_REG);
+	udelay(10);
+
+	/* FIFO configuration register 3 */
+	EFX_POPULATE_OWORD_2(reg,
+			     GMF_CFGHWMFT, 0x1c,
+			     GMF_CFGFTTH, 0x08);
+	falcon_write(efx, &reg, GMF_CFG3_REG);
+	udelay(10);
+
+	/* FIFO configuration register 4 */
+	EFX_POPULATE_OWORD_1(reg, GMF_HSTFLTRFRM_PAUSE, 1);
+	falcon_write(efx, &reg, GMF_CFG4_REG);
+	udelay(10);
+
+	/* FIFO configuration register 5 */
+	falcon_read(efx, &reg, GMF_CFG5_REG);
+	EFX_SET_OWORD_FIELD(reg, GMF_CFGBYTMODE, bytemode);
+	EFX_SET_OWORD_FIELD(reg, GMF_CFGHDPLX, !efx->link_fd);
+	EFX_SET_OWORD_FIELD(reg, GMF_HSTDRPLT64, !efx->link_fd);
+	EFX_SET_OWORD_FIELD(reg, GMF_HSTFLTRFRMDC_PAUSE, 0);
+	falcon_write(efx, &reg, GMF_CFG5_REG);
+	udelay(10);
+
+	/* MAC address */
+	EFX_POPULATE_OWORD_4(reg,
+			     GM_HWADDR_5, efx->net_dev->dev_addr[5],
+			     GM_HWADDR_4, efx->net_dev->dev_addr[4],
+			     GM_HWADDR_3, efx->net_dev->dev_addr[3],
+			     GM_HWADDR_2, efx->net_dev->dev_addr[2]);
+	falcon_write(efx, &reg, GM_ADR1_REG);
+	udelay(10);
+	EFX_POPULATE_OWORD_2(reg,
+			     GM_HWADDR_1, efx->net_dev->dev_addr[1],
+			     GM_HWADDR_0, efx->net_dev->dev_addr[0]);
+	falcon_write(efx, &reg, GM_ADR2_REG);
+	udelay(10);
+
+	falcon_reconfigure_mac_wrapper(efx);
+}
+
+static void falcon_update_stats_gmac(struct efx_nic *efx)
+{
+	struct efx_mac_stats *mac_stats = &efx->mac_stats;
+	unsigned long old_rx_pause, old_tx_pause;
+	unsigned long new_rx_pause, new_tx_pause;
+	int rc;
+
+	rc = falcon_dma_stats(efx, GDmaDone_offset);
+	if (rc)
+		return;
+
+	/* Pause frames are erroneously counted as errors (SFC bug 3269) */
+	old_rx_pause = mac_stats->rx_pause;
+	old_tx_pause = mac_stats->tx_pause;
+
+	/* Update MAC stats from DMAed values */
+	FALCON_STAT(efx, GRxGoodOct, rx_good_bytes);
+	FALCON_STAT(efx, GRxBadOct, rx_bad_bytes);
+	FALCON_STAT(efx, GRxMissPkt, rx_missed);
+	FALCON_STAT(efx, GRxFalseCRS, rx_false_carrier);
+	FALCON_STAT(efx, GRxPausePkt, rx_pause);
+	FALCON_STAT(efx, GRxBadPkt, rx_bad);
+	FALCON_STAT(efx, GRxUcastPkt, rx_unicast);
+	FALCON_STAT(efx, GRxMcastPkt, rx_multicast);
+	FALCON_STAT(efx, GRxBcastPkt, rx_broadcast);
+	FALCON_STAT(efx, GRxGoodLt64Pkt, rx_good_lt64);
+	FALCON_STAT(efx, GRxBadLt64Pkt, rx_bad_lt64);
+	FALCON_STAT(efx, GRx64Pkt, rx_64);
+	FALCON_STAT(efx, GRx65to127Pkt, rx_65_to_127);
+	FALCON_STAT(efx, GRx128to255Pkt, rx_128_to_255);
+	FALCON_STAT(efx, GRx256to511Pkt, rx_256_to_511);
+	FALCON_STAT(efx, GRx512to1023Pkt, rx_512_to_1023);
+	FALCON_STAT(efx, GRx1024to15xxPkt, rx_1024_to_15xx);
+	FALCON_STAT(efx, GRx15xxtoJumboPkt, rx_15xx_to_jumbo);
+	FALCON_STAT(efx, GRxGtJumboPkt, rx_gtjumbo);
+	FALCON_STAT(efx, GRxFcsErr64to15xxPkt, rx_bad_64_to_15xx);
+	FALCON_STAT(efx, GRxFcsErr15xxtoJumboPkt, rx_bad_15xx_to_jumbo);
+	FALCON_STAT(efx, GRxFcsErrGtJumboPkt, rx_bad_gtjumbo);
+	FALCON_STAT(efx, GTxGoodBadOct, tx_bytes);
+	FALCON_STAT(efx, GTxGoodOct, tx_good_bytes);
+	FALCON_STAT(efx, GTxSglColPkt, tx_single_collision);
+	FALCON_STAT(efx, GTxMultColPkt, tx_multiple_collision);
+	FALCON_STAT(efx, GTxExColPkt, tx_excessive_collision);
+	FALCON_STAT(efx, GTxDefPkt, tx_deferred);
+	FALCON_STAT(efx, GTxLateCol, tx_late_collision);
+	FALCON_STAT(efx, GTxExDefPkt, tx_excessive_deferred);
+	FALCON_STAT(efx, GTxPausePkt, tx_pause);
+	FALCON_STAT(efx, GTxBadPkt, tx_bad);
+	FALCON_STAT(efx, GTxUcastPkt, tx_unicast);
+	FALCON_STAT(efx, GTxMcastPkt, tx_multicast);
+	FALCON_STAT(efx, GTxBcastPkt, tx_broadcast);
+	FALCON_STAT(efx, GTxLt64Pkt, tx_lt64);
+	FALCON_STAT(efx, GTx64Pkt, tx_64);
+	FALCON_STAT(efx, GTx65to127Pkt, tx_65_to_127);
+	FALCON_STAT(efx, GTx128to255Pkt, tx_128_to_255);
+	FALCON_STAT(efx, GTx256to511Pkt, tx_256_to_511);
+	FALCON_STAT(efx, GTx512to1023Pkt, tx_512_to_1023);
+	FALCON_STAT(efx, GTx1024to15xxPkt, tx_1024_to_15xx);
+	FALCON_STAT(efx, GTx15xxtoJumboPkt, tx_15xx_to_jumbo);
+	FALCON_STAT(efx, GTxGtJumboPkt, tx_gtjumbo);
+	FALCON_STAT(efx, GTxNonTcpUdpPkt, tx_non_tcpudp);
+	FALCON_STAT(efx, GTxMacSrcErrPkt, tx_mac_src_error);
+	FALCON_STAT(efx, GTxIpSrcErrPkt, tx_ip_src_error);
+
+	/* Pause frames are erroneously counted as errors (SFC bug 3269) */
+	new_rx_pause = mac_stats->rx_pause;
+	new_tx_pause = mac_stats->tx_pause;
+	mac_stats->rx_bad -= (new_rx_pause - old_rx_pause);
+	mac_stats->tx_bad -= (new_tx_pause - old_tx_pause);
+
+	/* Derive stats that the MAC doesn't provide directly */
+	mac_stats->tx_bad_bytes =
+		mac_stats->tx_bytes - mac_stats->tx_good_bytes;
+	mac_stats->tx_packets =
+		mac_stats->tx_lt64 + mac_stats->tx_64 +
+		mac_stats->tx_65_to_127 + mac_stats->tx_128_to_255 +
+		mac_stats->tx_256_to_511 + mac_stats->tx_512_to_1023 +
+		mac_stats->tx_1024_to_15xx + mac_stats->tx_15xx_to_jumbo +
+		mac_stats->tx_gtjumbo;
+	mac_stats->tx_collision =
+		mac_stats->tx_single_collision +
+		mac_stats->tx_multiple_collision +
+		mac_stats->tx_excessive_collision +
+		mac_stats->tx_late_collision;
+	mac_stats->rx_bytes =
+		mac_stats->rx_good_bytes + mac_stats->rx_bad_bytes;
+	mac_stats->rx_packets =
+		mac_stats->rx_good_lt64 + mac_stats->rx_bad_lt64 +
+		mac_stats->rx_64 + mac_stats->rx_65_to_127 +
+		mac_stats->rx_128_to_255 + mac_stats->rx_256_to_511 +
+		mac_stats->rx_512_to_1023 + mac_stats->rx_1024_to_15xx +
+		mac_stats->rx_15xx_to_jumbo + mac_stats->rx_gtjumbo;
+	mac_stats->rx_good = mac_stats->rx_packets - mac_stats->rx_bad;
+	mac_stats->rx_lt64 = mac_stats->rx_good_lt64 + mac_stats->rx_bad_lt64;
+}
+
+struct efx_mac_operations falcon_gmac_operations = {
+	.reconfigure	= falcon_reconfigure_gmac,
+	.update_stats	= falcon_update_stats_gmac,
+	.irq		= efx_port_dummy_op_void,
+	.poll		= efx_port_dummy_op_void,
+};
diff --git a/drivers/net/sfc/falcon_hwdefs.h b/drivers/net/sfc/falcon_hwdefs.h
index 5d584b0dbb5..bda8d5bb72e 100644
--- a/drivers/net/sfc/falcon_hwdefs.h
+++ b/drivers/net/sfc/falcon_hwdefs.h
@@ -111,12 +111,18 @@
 
 /* NIC status register */
 #define NIC_STAT_REG 0x0200
+#define EE_STRAP_EN_LBN 31
+#define EE_STRAP_EN_WIDTH 1
+#define EE_STRAP_OVR_LBN 24
+#define EE_STRAP_OVR_WIDTH 4
 #define ONCHIP_SRAM_LBN 16
 #define ONCHIP_SRAM_WIDTH 1
 #define SF_PRST_LBN 9
 #define SF_PRST_WIDTH 1
 #define EE_PRST_LBN 8
 #define EE_PRST_WIDTH 1
+#define STRAP_PINS_LBN 0
+#define STRAP_PINS_WIDTH 3
 /* These bit definitions are extrapolated from the list of numerical
  * values for STRAP_PINS.
  */
@@ -130,6 +136,8 @@
 
 /* GPIO control register */
 #define GPIO_CTL_REG_KER 0x0210
+#define GPIO_USE_NIC_CLK_LBN (30)
+#define GPIO_USE_NIC_CLK_WIDTH (1)
 #define GPIO_OUTPUTS_LBN   (16)
 #define GPIO_OUTPUTS_WIDTH (4)
 #define GPIO_INPUTS_LBN (8)
@@ -492,6 +500,107 @@
 #define MAC_MCAST_HASH_REG0_KER 0xca0
 #define MAC_MCAST_HASH_REG1_KER 0xcb0
 
+/* GMAC configuration register 1 */
+#define GM_CFG1_REG 0xe00
+#define GM_SW_RST_LBN 31
+#define GM_SW_RST_WIDTH 1
+#define GM_LOOP_LBN 8
+#define GM_LOOP_WIDTH 1
+#define GM_RX_FC_EN_LBN 5
+#define GM_RX_FC_EN_WIDTH 1
+#define GM_TX_FC_EN_LBN 4
+#define GM_TX_FC_EN_WIDTH 1
+#define GM_RX_EN_LBN 2
+#define GM_RX_EN_WIDTH 1
+#define GM_TX_EN_LBN 0
+#define GM_TX_EN_WIDTH 1
+
+/* GMAC configuration register 2 */
+#define GM_CFG2_REG 0xe10
+#define GM_PAMBL_LEN_LBN 12
+#define GM_PAMBL_LEN_WIDTH 4
+#define GM_IF_MODE_LBN 8
+#define GM_IF_MODE_WIDTH 2
+#define GM_LEN_CHK_LBN 4
+#define GM_LEN_CHK_WIDTH 1
+#define GM_PAD_CRC_EN_LBN 2
+#define GM_PAD_CRC_EN_WIDTH 1
+#define GM_FD_LBN 0
+#define GM_FD_WIDTH 1
+
+/* GMAC maximum frame length register */
+#define GM_MAX_FLEN_REG 0xe40
+#define GM_MAX_FLEN_LBN 0
+#define GM_MAX_FLEN_WIDTH 16
+
+/* GMAC station address register 1 */
+#define GM_ADR1_REG 0xf00
+#define GM_HWADDR_5_LBN 24
+#define GM_HWADDR_5_WIDTH 8
+#define GM_HWADDR_4_LBN 16
+#define GM_HWADDR_4_WIDTH 8
+#define GM_HWADDR_3_LBN 8
+#define GM_HWADDR_3_WIDTH 8
+#define GM_HWADDR_2_LBN 0
+#define GM_HWADDR_2_WIDTH 8
+
+/* GMAC station address register 2 */
+#define GM_ADR2_REG 0xf10
+#define GM_HWADDR_1_LBN 24
+#define GM_HWADDR_1_WIDTH 8
+#define GM_HWADDR_0_LBN 16
+#define GM_HWADDR_0_WIDTH 8
+
+/* GMAC FIFO configuration register 0 */
+#define GMF_CFG0_REG 0xf20
+#define GMF_FTFENREQ_LBN 12
+#define GMF_FTFENREQ_WIDTH 1
+#define GMF_STFENREQ_LBN 11
+#define GMF_STFENREQ_WIDTH 1
+#define GMF_FRFENREQ_LBN 10
+#define GMF_FRFENREQ_WIDTH 1
+#define GMF_SRFENREQ_LBN 9
+#define GMF_SRFENREQ_WIDTH 1
+#define GMF_WTMENREQ_LBN 8
+#define GMF_WTMENREQ_WIDTH 1
+
+/* GMAC FIFO configuration register 1 */
+#define GMF_CFG1_REG 0xf30
+#define GMF_CFGFRTH_LBN 16
+#define GMF_CFGFRTH_WIDTH 5
+#define GMF_CFGXOFFRTX_LBN 0
+#define GMF_CFGXOFFRTX_WIDTH 16
+
+/* GMAC FIFO configuration register 2 */
+#define GMF_CFG2_REG 0xf40
+#define GMF_CFGHWM_LBN 16
+#define GMF_CFGHWM_WIDTH 6
+#define GMF_CFGLWM_LBN 0
+#define GMF_CFGLWM_WIDTH 6
+
+/* GMAC FIFO configuration register 3 */
+#define GMF_CFG3_REG 0xf50
+#define GMF_CFGHWMFT_LBN 16
+#define GMF_CFGHWMFT_WIDTH 6
+#define GMF_CFGFTTH_LBN 0
+#define GMF_CFGFTTH_WIDTH 6
+
+/* GMAC FIFO configuration register 4 */
+#define GMF_CFG4_REG 0xf60
+#define GMF_HSTFLTRFRM_PAUSE_LBN 12
+#define GMF_HSTFLTRFRM_PAUSE_WIDTH 12
+
+/* GMAC FIFO configuration register 5 */
+#define GMF_CFG5_REG 0xf70
+#define GMF_CFGHDPLX_LBN 22
+#define GMF_CFGHDPLX_WIDTH 1
+#define GMF_CFGBYTMODE_LBN 19
+#define GMF_CFGBYTMODE_WIDTH 1
+#define GMF_HSTDRPLT64_LBN 18
+#define GMF_HSTDRPLT64_WIDTH 1
+#define GMF_HSTFLTRFRMDC_PAUSE_LBN 12
+#define GMF_HSTFLTRFRMDC_PAUSE_WIDTH 1
+
 /* XGMAC address register low */
 #define XM_ADR_LO_REG 0x1200
 #define XM_ADR_3_LBN 24
@@ -944,6 +1053,8 @@
 #define XG_MNT_INTR_B0_WIDTH 1
 #define RX_RECOVERY_A1_LBN 11
 #define RX_RECOVERY_A1_WIDTH 1
+#define XFP_PHY_INTR_LBN 10
+#define XFP_PHY_INTR_WIDTH 1
 #define XG_PHY_INTR_LBN 9
 #define XG_PHY_INTR_WIDTH 1
 #define G_PHY1_INTR_LBN 8
@@ -962,54 +1073,103 @@
  **************************************************************************
  *
  */
+
 #define GRxGoodOct_offset 0x0
+#define GRxGoodOct_WIDTH 48
 #define GRxBadOct_offset 0x8
+#define GRxBadOct_WIDTH 48
 #define GRxMissPkt_offset 0x10
+#define GRxMissPkt_WIDTH 32
 #define GRxFalseCRS_offset 0x14
+#define GRxFalseCRS_WIDTH 32
 #define GRxPausePkt_offset 0x18
+#define GRxPausePkt_WIDTH 32
 #define GRxBadPkt_offset 0x1C
+#define GRxBadPkt_WIDTH 32
 #define GRxUcastPkt_offset 0x20
+#define GRxUcastPkt_WIDTH 32
 #define GRxMcastPkt_offset 0x24
+#define GRxMcastPkt_WIDTH 32
 #define GRxBcastPkt_offset 0x28
+#define GRxBcastPkt_WIDTH 32
 #define GRxGoodLt64Pkt_offset 0x2C
+#define GRxGoodLt64Pkt_WIDTH 32
 #define GRxBadLt64Pkt_offset 0x30
+#define GRxBadLt64Pkt_WIDTH 32
 #define GRx64Pkt_offset 0x34
+#define GRx64Pkt_WIDTH 32
 #define GRx65to127Pkt_offset 0x38
+#define GRx65to127Pkt_WIDTH 32
 #define GRx128to255Pkt_offset 0x3C
+#define GRx128to255Pkt_WIDTH 32
 #define GRx256to511Pkt_offset 0x40
+#define GRx256to511Pkt_WIDTH 32
 #define GRx512to1023Pkt_offset 0x44
+#define GRx512to1023Pkt_WIDTH 32
 #define GRx1024to15xxPkt_offset 0x48
+#define GRx1024to15xxPkt_WIDTH 32
 #define GRx15xxtoJumboPkt_offset 0x4C
+#define GRx15xxtoJumboPkt_WIDTH 32
 #define GRxGtJumboPkt_offset 0x50
+#define GRxGtJumboPkt_WIDTH 32
 #define GRxFcsErr64to15xxPkt_offset 0x54
+#define GRxFcsErr64to15xxPkt_WIDTH 32
 #define GRxFcsErr15xxtoJumboPkt_offset 0x58
+#define GRxFcsErr15xxtoJumboPkt_WIDTH 32
 #define GRxFcsErrGtJumboPkt_offset 0x5C
+#define GRxFcsErrGtJumboPkt_WIDTH 32
 #define GTxGoodBadOct_offset 0x80
+#define GTxGoodBadOct_WIDTH 48
 #define GTxGoodOct_offset 0x88
+#define GTxGoodOct_WIDTH 48
 #define GTxSglColPkt_offset 0x90
+#define GTxSglColPkt_WIDTH 32
 #define GTxMultColPkt_offset 0x94
+#define GTxMultColPkt_WIDTH 32
 #define GTxExColPkt_offset 0x98
+#define GTxExColPkt_WIDTH 32
 #define GTxDefPkt_offset 0x9C
+#define GTxDefPkt_WIDTH 32
 #define GTxLateCol_offset 0xA0
+#define GTxLateCol_WIDTH 32
 #define GTxExDefPkt_offset 0xA4
+#define GTxExDefPkt_WIDTH 32
 #define GTxPausePkt_offset 0xA8
+#define GTxPausePkt_WIDTH 32
 #define GTxBadPkt_offset 0xAC
+#define GTxBadPkt_WIDTH 32
 #define GTxUcastPkt_offset 0xB0
+#define GTxUcastPkt_WIDTH 32
 #define GTxMcastPkt_offset 0xB4
+#define GTxMcastPkt_WIDTH 32
 #define GTxBcastPkt_offset 0xB8
+#define GTxBcastPkt_WIDTH 32
 #define GTxLt64Pkt_offset 0xBC
+#define GTxLt64Pkt_WIDTH 32
 #define GTx64Pkt_offset 0xC0
+#define GTx64Pkt_WIDTH 32
 #define GTx65to127Pkt_offset 0xC4
+#define GTx65to127Pkt_WIDTH 32
 #define GTx128to255Pkt_offset 0xC8
+#define GTx128to255Pkt_WIDTH 32
 #define GTx256to511Pkt_offset 0xCC
+#define GTx256to511Pkt_WIDTH 32
 #define GTx512to1023Pkt_offset 0xD0
+#define GTx512to1023Pkt_WIDTH 32
 #define GTx1024to15xxPkt_offset 0xD4
+#define GTx1024to15xxPkt_WIDTH 32
 #define GTx15xxtoJumboPkt_offset 0xD8
+#define GTx15xxtoJumboPkt_WIDTH 32
 #define GTxGtJumboPkt_offset 0xDC
+#define GTxGtJumboPkt_WIDTH 32
 #define GTxNonTcpUdpPkt_offset 0xE0
+#define GTxNonTcpUdpPkt_WIDTH 16
 #define GTxMacSrcErrPkt_offset 0xE4
+#define GTxMacSrcErrPkt_WIDTH 16
 #define GTxIpSrcErrPkt_offset 0xE8
+#define GTxIpSrcErrPkt_WIDTH 16
 #define GDmaDone_offset 0xEC
+#define GDmaDone_WIDTH 32
 
 #define XgRxOctets_offset 0x0
 #define XgRxOctets_WIDTH 48
@@ -1150,7 +1310,6 @@ struct falcon_nvconfig_board_v3 {
 	(((type) >> EFX_LOW_BIT(field)) & EFX_MASK32(EFX_WIDTH(field)))
 
 #define NVCONFIG_OFFSET 0x300
-#define NVCONFIG_END 0x400
 
 #define NVCONFIG_BOARD_MAGIC_NUM 0xFA1C
 struct falcon_nvconfig {
diff --git a/drivers/net/sfc/falcon_xmac.c b/drivers/net/sfc/falcon_xmac.c
index d4012314dd0..5a03713685a 100644
--- a/drivers/net/sfc/falcon_xmac.c
+++ b/drivers/net/sfc/falcon_xmac.c
@@ -15,7 +15,6 @@
 #include "falcon_hwdefs.h"
 #include "falcon_io.h"
 #include "mac.h"
-#include "gmii.h"
 #include "mdio_10g.h"
 #include "phy.h"
 #include "boards.h"
@@ -26,24 +25,6 @@
  * MAC operations
  *
  *************************************************************************/
-static int falcon_reset_xmac(struct efx_nic *efx)
-{
-	efx_oword_t reg;
-	int count;
-
-	EFX_POPULATE_OWORD_1(reg, XM_CORE_RST, 1);
-	falcon_write(efx, &reg, XM_GLB_CFG_REG);
-
-	for (count = 0; count < 10000; count++) {	/* wait upto 100ms */
-		falcon_read(efx, &reg, XM_GLB_CFG_REG);
-		if (EFX_OWORD_FIELD(reg, XM_CORE_RST) == 0)
-			return 0;
-		udelay(10);
-	}
-
-	EFX_ERR(efx, "timed out waiting for XMAC core reset\n");
-	return -ETIMEDOUT;
-}
 
 /* Configure the XAUI driver that is an output from Falcon */
 static void falcon_setup_xaui(struct efx_nic *efx)
@@ -99,31 +80,20 @@ int falcon_reset_xaui(struct efx_nic *efx)
 	return -ETIMEDOUT;
 }
 
-static bool falcon_xgmii_status(struct efx_nic *efx)
+static void falcon_mask_status_intr(struct efx_nic *efx, bool enable)
 {
 	efx_oword_t reg;
 
-	if (falcon_rev(efx) < FALCON_REV_B0)
-		return true;
-
-	/* The ISR latches, so clear it and re-read */
-	falcon_read(efx, &reg, XM_MGT_INT_REG_B0);
-	falcon_read(efx, &reg, XM_MGT_INT_REG_B0);
-
-	if (EFX_OWORD_FIELD(reg, XM_LCLFLT) ||
-	    EFX_OWORD_FIELD(reg, XM_RMTFLT)) {
-		EFX_INFO(efx, "MGT_INT: "EFX_DWORD_FMT"\n", EFX_DWORD_VAL(reg));
-		return false;
-	}
-
-	return true;
-}
+	if ((falcon_rev(efx) != FALCON_REV_B0) || LOOPBACK_INTERNAL(efx))
+		return;
 
-static void falcon_mask_status_intr(struct efx_nic *efx, bool enable)
-{
-	efx_oword_t reg;
+	/* We expect xgmii faults if the wireside link is up */
+	if (!EFX_WORKAROUND_5147(efx) || !efx->link_up)
+		return;
 
-	if ((falcon_rev(efx) < FALCON_REV_B0) || LOOPBACK_INTERNAL(efx))
+	/* We can only use this interrupt to signal the negative edge of
+	 * xaui_align [we have to poll the positive edge]. */
+	if (!efx->mac_up)
 		return;
 
 	/* Flush the ISR */
@@ -136,35 +106,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, bool enable)
 	falcon_write(efx, &reg, XM_MGT_INT_MSK_REG_B0);
 }
 
-int falcon_init_xmac(struct efx_nic *efx)
-{
-	int rc;
-
-	/* Initialize the PHY first so the clock is around */
-	rc = efx->phy_op->init(efx);
-	if (rc)
-		goto fail1;
-
-	rc = falcon_reset_xaui(efx);
-	if (rc)
-		goto fail2;
-
-	/* Wait again. Give the PHY and MAC time to come back */
-	schedule_timeout_uninterruptible(HZ / 10);
-
-	rc = falcon_reset_xmac(efx);
-	if (rc)
-		goto fail2;
-
-	falcon_mask_status_intr(efx, true);
-	return 0;
-
- fail2:
-	efx->phy_op->fini(efx);
- fail1:
-	return rc;
-}
-
+/* Get status of XAUI link */
 bool falcon_xaui_link_ok(struct efx_nic *efx)
 {
 	efx_oword_t reg;
@@ -188,18 +130,10 @@ bool falcon_xaui_link_ok(struct efx_nic *efx)
 	EFX_SET_OWORD_FIELD(reg, XX_DISPERR, XX_DISPERR_RESET);
 	falcon_write(efx, &reg, XX_CORE_STAT_REG);
 
-	/* If the link is up, then check the phy side of the xaui link
-	 * (error conditions from the wire side propoagate back through
-	 * the phy to the xaui side). */
-	if (efx->link_up && link_ok) {
+	/* If the link is up, then check the phy side of the xaui link */
+	if (efx->link_up && link_ok)
 		if (efx->phy_op->mmds & (1 << MDIO_MMD_PHYXS))
 			link_ok = mdio_clause45_phyxgxs_lane_sync(efx);
-	}
-
-	/* If the PHY and XAUI links are up, then check the mac's xgmii
-	 * fault state */
-	if (efx->link_up && link_ok)
-		link_ok = falcon_xgmii_status(efx);
 
 	return link_ok;
 }
@@ -208,7 +142,7 @@ static void falcon_reconfigure_xmac_core(struct efx_nic *efx)
 {
 	unsigned int max_frame_len;
 	efx_oword_t reg;
-	bool rx_fc = !!(efx->flow_control & EFX_FC_RX);
+	bool rx_fc = !!(efx->link_fc & EFX_FC_RX);
 
 	/* Configure MAC  - cut-thru mode is hard wired on */
 	EFX_POPULATE_DWORD_3(reg,
@@ -311,70 +245,39 @@ static void falcon_reconfigure_xgxs_core(struct efx_nic *efx)
 
 /* Try and bring the Falcon side of the Falcon-Phy XAUI link fails
  * to come back up. Bash it until it comes back up */
-static bool falcon_check_xaui_link_up(struct efx_nic *efx)
+static void falcon_check_xaui_link_up(struct efx_nic *efx, int tries)
 {
-	int max_tries, tries;
-	tries = EFX_WORKAROUND_5147(efx) ? 5 : 1;
-	max_tries = tries;
+	efx->mac_up = falcon_xaui_link_ok(efx);
 
 	if ((efx->loopback_mode == LOOPBACK_NETWORK) ||
-	    (efx->phy_type == PHY_TYPE_NONE) ||
 	    efx_phy_mode_disabled(efx->phy_mode))
-		return false;
-
-	while (tries) {
-		if (falcon_xaui_link_ok(efx))
-			return true;
+		/* XAUI link is expected to be down */
+		return;
 
-		EFX_LOG(efx, "%s Clobbering XAUI (%d tries left).\n",
-			__func__, tries);
+	while (!efx->mac_up && tries) {
+		EFX_LOG(efx, "bashing xaui\n");
 		falcon_reset_xaui(efx);
 		udelay(200);
-		tries--;
-	}
 
-	EFX_LOG(efx, "Failed to bring XAUI link back up in %d tries!\n",
-		max_tries);
-	return false;
+		efx->mac_up = falcon_xaui_link_ok(efx);
+		--tries;
+	}
 }
 
-void falcon_reconfigure_xmac(struct efx_nic *efx)
+static void falcon_reconfigure_xmac(struct efx_nic *efx)
 {
-	bool xaui_link_ok;
-
 	falcon_mask_status_intr(efx, false);
 
-	falcon_deconfigure_mac_wrapper(efx);
-
-	/* Reconfigure the PHY, disabling transmit in mac level loopback. */
-	if (LOOPBACK_INTERNAL(efx))
-		efx->phy_mode |= PHY_MODE_TX_DISABLED;
-	else
-		efx->phy_mode &= ~PHY_MODE_TX_DISABLED;
-	efx->phy_op->reconfigure(efx);
-
 	falcon_reconfigure_xgxs_core(efx);
 	falcon_reconfigure_xmac_core(efx);
 
 	falcon_reconfigure_mac_wrapper(efx);
 
-	/* Ensure XAUI link is up */
-	xaui_link_ok = falcon_check_xaui_link_up(efx);
-
-	if (xaui_link_ok && efx->link_up)
-		falcon_mask_status_intr(efx, true);
-}
-
-void falcon_fini_xmac(struct efx_nic *efx)
-{
-	/* Isolate the MAC - PHY */
-	falcon_deconfigure_mac_wrapper(efx);
-
-	/* Potentially power down the PHY */
-	efx->phy_op->fini(efx);
+	falcon_check_xaui_link_up(efx, 5);
+	falcon_mask_status_intr(efx, true);
 }
 
-void falcon_update_stats_xmac(struct efx_nic *efx)
+static void falcon_update_stats_xmac(struct efx_nic *efx)
 {
 	struct efx_mac_stats *mac_stats = &efx->mac_stats;
 	int rc;
@@ -439,97 +342,35 @@ void falcon_update_stats_xmac(struct efx_nic *efx)
 		 mac_stats->rx_control * 64);
 }
 
-int falcon_check_xmac(struct efx_nic *efx)
+static void falcon_xmac_irq(struct efx_nic *efx)
 {
-	bool xaui_link_ok;
-	int rc;
-
-	if ((efx->loopback_mode == LOOPBACK_NETWORK) ||
-	    efx_phy_mode_disabled(efx->phy_mode))
-		return 0;
-
-	falcon_mask_status_intr(efx, false);
-	xaui_link_ok = falcon_xaui_link_ok(efx);
-
-	if (EFX_WORKAROUND_5147(efx) && !xaui_link_ok)
-		falcon_reset_xaui(efx);
-
-	/* Call the PHY check_hw routine */
-	rc = efx->phy_op->check_hw(efx);
-
-	/* Unmask interrupt if everything was (and still is) ok */
-	if (xaui_link_ok && efx->link_up)
-		falcon_mask_status_intr(efx, true);
-
-	return rc;
-}
-
-/* Simulate a PHY event */
-void falcon_xmac_sim_phy_event(struct efx_nic *efx)
-{
-	efx_qword_t phy_event;
-
-	EFX_POPULATE_QWORD_2(phy_event,
-			     EV_CODE, GLOBAL_EV_DECODE,
-			     XG_PHY_INTR, 1);
-	falcon_generate_event(&efx->channel[0], &phy_event);
+	/* The XGMII link has a transient fault, which indicates either:
+	 *   - there's a transient xgmii fault
+	 *   - falcon's end of the xaui link may need a kick
+	 *   - the wire-side link may have gone down, but the lasi/poll()
+	 *     hasn't noticed yet.
+	 *
+	 * We only want to even bother polling XAUI if we're confident it's
+	 * not (1) or (3). In both cases, the only reliable way to spot this
+	 * is to wait a bit. We do this here by forcing the mac link state
+	 * to down, and waiting for the mac poll to come round and check
+	 */
+	efx->mac_up = false;
 }
 
-int falcon_xmac_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+static void falcon_poll_xmac(struct efx_nic *efx)
 {
-	mdio_clause45_get_settings(efx, ecmd);
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->phy_address = efx->mii.phy_id;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->duplex = DUPLEX_FULL;
-	return 0;
-}
+	if (!EFX_WORKAROUND_5147(efx) || !efx->link_up || efx->mac_up)
+		return;
 
-int falcon_xmac_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
-{
-	if (ecmd->transceiver != XCVR_INTERNAL)
-		return -EINVAL;
-	if (ecmd->autoneg != AUTONEG_DISABLE)
-		return -EINVAL;
-	if (ecmd->duplex != DUPLEX_FULL)
-		return -EINVAL;
-
-	return mdio_clause45_set_settings(efx, ecmd);
+	falcon_mask_status_intr(efx, false);
+	falcon_check_xaui_link_up(efx, 1);
+	falcon_mask_status_intr(efx, true);
 }
 
-
-int falcon_xmac_set_pause(struct efx_nic *efx, enum efx_fc_type flow_control)
-{
-	bool reset;
-
-	if (flow_control & EFX_FC_AUTO) {
-		EFX_LOG(efx, "10G does not support flow control "
-			"autonegotiation\n");
-		return -EINVAL;
-	}
-
-	if ((flow_control & EFX_FC_TX) && !(flow_control & EFX_FC_RX))
-		return -EINVAL;
-
-	/* TX flow control may automatically turn itself off if the
-	 * link partner (intermittently) stops responding to pause
-	 * frames. There isn't any indication that this has happened,
-	 * so the best we do is leave it up to the user to spot this
-	 * and fix it be cycling transmit flow control on this end. */
-	reset = ((flow_control & EFX_FC_TX) &&
-		 !(efx->flow_control & EFX_FC_TX));
-	if (EFX_WORKAROUND_11482(efx) && reset) {
-		if (falcon_rev(efx) >= FALCON_REV_B0) {
-			/* Recover by resetting the EM block */
-			if (efx->link_up)
-				falcon_drain_tx_fifo(efx);
-		} else {
-			/* Schedule a reset to recover */
-			efx_schedule_reset(efx, RESET_TYPE_INVISIBLE);
-		}
-	}
-
-	efx->flow_control = flow_control;
-
-	return 0;
-}
+struct efx_mac_operations falcon_xmac_operations = {
+	.reconfigure	= falcon_reconfigure_xmac,
+	.update_stats	= falcon_update_stats_xmac,
+	.irq		= falcon_xmac_irq,
+	.poll		= falcon_poll_xmac,
+};
diff --git a/drivers/net/sfc/gmii.h b/drivers/net/sfc/gmii.h
index d25bbd1297f..dfccaa7b573 100644
--- a/drivers/net/sfc/gmii.h
+++ b/drivers/net/sfc/gmii.h
@@ -1,7 +1,7 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006 Solarflare Communications Inc.
+ * Copyright 2006-2008 Solarflare Communications Inc.
  *
  * 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
@@ -57,139 +57,4 @@
 #define ISR_POLARITY_CHG	0x0002	/* Bit 1 - polarity changed */
 #define ISR_JABBER		0x0001	/* Bit 0 - jabber */
 
-/* Logically extended advertisement register */
-#define GM_ADVERTISE_SLCT		ADVERTISE_SLCT
-#define GM_ADVERTISE_CSMA		ADVERTISE_CSMA
-#define GM_ADVERTISE_10HALF		ADVERTISE_10HALF
-#define GM_ADVERTISE_1000XFULL		ADVERTISE_1000XFULL
-#define GM_ADVERTISE_10FULL		ADVERTISE_10FULL
-#define GM_ADVERTISE_1000XHALF		ADVERTISE_1000XHALF
-#define GM_ADVERTISE_100HALF		ADVERTISE_100HALF
-#define GM_ADVERTISE_1000XPAUSE		ADVERTISE_1000XPAUSE
-#define GM_ADVERTISE_100FULL		ADVERTISE_100FULL
-#define GM_ADVERTISE_1000XPSE_ASYM	ADVERTISE_1000XPSE_ASYM
-#define GM_ADVERTISE_100BASE4		ADVERTISE_100BASE4
-#define GM_ADVERTISE_PAUSE_CAP		ADVERTISE_PAUSE_CAP
-#define GM_ADVERTISE_PAUSE_ASYM		ADVERTISE_PAUSE_ASYM
-#define GM_ADVERTISE_RESV		ADVERTISE_RESV
-#define GM_ADVERTISE_RFAULT		ADVERTISE_RFAULT
-#define GM_ADVERTISE_LPACK		ADVERTISE_LPACK
-#define GM_ADVERTISE_NPAGE		ADVERTISE_NPAGE
-#define GM_ADVERTISE_1000FULL		(ADVERTISE_1000FULL << 8)
-#define GM_ADVERTISE_1000HALF		(ADVERTISE_1000HALF << 8)
-#define GM_ADVERTISE_1000		(GM_ADVERTISE_1000FULL | \
-					 GM_ADVERTISE_1000HALF)
-#define GM_ADVERTISE_FULL		(GM_ADVERTISE_1000FULL | \
-					 ADVERTISE_FULL)
-#define GM_ADVERTISE_ALL		(GM_ADVERTISE_1000FULL | \
-					 GM_ADVERTISE_1000HALF | \
-					 ADVERTISE_ALL)
-
-/* Logically extended link partner ability register */
-#define GM_LPA_SLCT			LPA_SLCT
-#define GM_LPA_10HALF			LPA_10HALF
-#define GM_LPA_1000XFULL		LPA_1000XFULL
-#define GM_LPA_10FULL			LPA_10FULL
-#define GM_LPA_1000XHALF		LPA_1000XHALF
-#define GM_LPA_100HALF			LPA_100HALF
-#define GM_LPA_1000XPAUSE		LPA_1000XPAUSE
-#define GM_LPA_100FULL			LPA_100FULL
-#define GM_LPA_1000XPAUSE_ASYM		LPA_1000XPAUSE_ASYM
-#define GM_LPA_100BASE4			LPA_100BASE4
-#define GM_LPA_PAUSE_CAP		LPA_PAUSE_CAP
-#define GM_LPA_PAUSE_ASYM		LPA_PAUSE_ASYM
-#define GM_LPA_RESV			LPA_RESV
-#define GM_LPA_RFAULT			LPA_RFAULT
-#define GM_LPA_LPACK			LPA_LPACK
-#define GM_LPA_NPAGE			LPA_NPAGE
-#define GM_LPA_1000FULL			(LPA_1000FULL << 6)
-#define GM_LPA_1000HALF			(LPA_1000HALF << 6)
-#define GM_LPA_10000FULL		0x00040000
-#define GM_LPA_10000HALF		0x00080000
-#define GM_LPA_DUPLEX			(GM_LPA_1000FULL | GM_LPA_10000FULL \
-					 | LPA_DUPLEX)
-#define GM_LPA_10			(LPA_10FULL | LPA_10HALF)
-#define GM_LPA_100			LPA_100
-#define GM_LPA_1000			(GM_LPA_1000FULL | GM_LPA_1000HALF)
-#define GM_LPA_10000			(GM_LPA_10000FULL | GM_LPA_10000HALF)
-
-/* Retrieve GMII autonegotiation advertised abilities
- *
- * The MII advertisment register (MII_ADVERTISE) is logically extended
- * to include advertisement bits ADVERTISE_1000FULL and
- * ADVERTISE_1000HALF from MII_CTRL1000.  The result can be tested
- * against the GM_ADVERTISE_xxx constants.
- */
-static inline unsigned int gmii_advertised(struct mii_if_info *gmii)
-{
-	unsigned int advertise;
-	unsigned int ctrl1000;
-
-	advertise = gmii->mdio_read(gmii->dev, gmii->phy_id, MII_ADVERTISE);
-	ctrl1000 = gmii->mdio_read(gmii->dev, gmii->phy_id, MII_CTRL1000);
-	return (((ctrl1000 << 8) & GM_ADVERTISE_1000) | advertise);
-}
-
-/* Retrieve GMII autonegotiation link partner abilities
- *
- * The MII link partner ability register (MII_LPA) is logically
- * extended by adding bits LPA_1000HALF and LPA_1000FULL from
- * MII_STAT1000.  The result can be tested against the GM_LPA_xxx
- * constants.
- */
-static inline unsigned int gmii_lpa(struct mii_if_info *gmii)
-{
-	unsigned int lpa;
-	unsigned int stat1000;
-
-	lpa = gmii->mdio_read(gmii->dev, gmii->phy_id, MII_LPA);
-	stat1000 = gmii->mdio_read(gmii->dev, gmii->phy_id, MII_STAT1000);
-	return (((stat1000 << 6) & GM_LPA_1000) | lpa);
-}
-
-/* Calculate GMII autonegotiated link technology
- *
- * "negotiated" should be the result of gmii_advertised() logically
- * ANDed with the result of gmii_lpa().
- *
- * "tech" will be negotiated with the unused bits masked out.  For
- * example, if both ends of the link are capable of both
- * GM_LPA_1000FULL and GM_LPA_100FULL, GM_LPA_100FULL will be masked
- * out.
- */
-static inline unsigned int gmii_nway_result(unsigned int negotiated)
-{
-	unsigned int other_bits;
-
-	/* Mask out the speed and duplexity bits */
-	other_bits = negotiated & ~(GM_LPA_10 | GM_LPA_100 | GM_LPA_1000);
-
-	if (negotiated & GM_LPA_1000FULL)
-		return (other_bits | GM_LPA_1000FULL);
-	else if (negotiated & GM_LPA_1000HALF)
-		return (other_bits | GM_LPA_1000HALF);
-	else
-		return (other_bits | mii_nway_result(negotiated));
-}
-
-/* Calculate GMII non-autonegotiated link technology
- *
- * This provides an equivalent to gmii_nway_result for the case when
- * autonegotiation is disabled.
- */
-static inline unsigned int gmii_forced_result(unsigned int bmcr)
-{
-	unsigned int result;
-	int full_duplex;
-
-	full_duplex = bmcr & BMCR_FULLDPLX;
-	if (bmcr & BMCR_SPEED1000)
-		result = full_duplex ? GM_LPA_1000FULL : GM_LPA_1000HALF;
-	else if (bmcr & BMCR_SPEED100)
-		result = full_duplex ? GM_LPA_100FULL : GM_LPA_100HALF;
-	else
-		result = full_duplex ? GM_LPA_10FULL : GM_LPA_10HALF;
-	return result;
-}
-
 #endif /* EFX_GMII_H */
diff --git a/drivers/net/sfc/mac.h b/drivers/net/sfc/mac.h
index a31571c6913..4e7074278fe 100644
--- a/drivers/net/sfc/mac.h
+++ b/drivers/net/sfc/mac.h
@@ -1,7 +1,7 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2007 Solarflare Communications Inc.
+ * Copyright 2006-2008 Solarflare Communications Inc.
  *
  * 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
@@ -13,17 +13,7 @@
 
 #include "net_driver.h"
 
-extern int falcon_init_xmac(struct efx_nic *efx);
-extern void falcon_reconfigure_xmac(struct efx_nic *efx);
-extern void falcon_update_stats_xmac(struct efx_nic *efx);
-extern void falcon_fini_xmac(struct efx_nic *efx);
-extern int falcon_check_xmac(struct efx_nic *efx);
-extern void falcon_xmac_sim_phy_event(struct efx_nic *efx);
-extern int falcon_xmac_get_settings(struct efx_nic *efx,
-				    struct ethtool_cmd *ecmd);
-extern int falcon_xmac_set_settings(struct efx_nic *efx,
-				    struct ethtool_cmd *ecmd);
-extern int falcon_xmac_set_pause(struct efx_nic *efx,
-				 enum efx_fc_type pause_params);
+extern struct efx_mac_operations falcon_gmac_operations;
+extern struct efx_mac_operations falcon_xmac_operations;
 
 #endif
diff --git a/drivers/net/sfc/mdio_10g.c b/drivers/net/sfc/mdio_10g.c
index 003e48dcb2f..f6a16428113 100644
--- a/drivers/net/sfc/mdio_10g.c
+++ b/drivers/net/sfc/mdio_10g.c
@@ -47,13 +47,16 @@ static int mdio_clause45_check_mmd(struct efx_nic *efx, int mmd,
 	if (LOOPBACK_INTERNAL(efx))
 		return 0;
 
-	/* Read MMD STATUS2 to check it is responding. */
-	status = mdio_clause45_read(efx, phy_id, mmd, MDIO_MMDREG_STAT2);
-	if (((status >> MDIO_MMDREG_STAT2_PRESENT_LBN) &
-	     ((1 << MDIO_MMDREG_STAT2_PRESENT_WIDTH) - 1)) !=
-	    MDIO_MMDREG_STAT2_PRESENT_VAL) {
-		EFX_ERR(efx, "PHY MMD %d not responding.\n", mmd);
-		return -EIO;
+	if (mmd != MDIO_MMD_AN) {
+		/* Read MMD STATUS2 to check it is responding. */
+		status = mdio_clause45_read(efx, phy_id, mmd,
+					    MDIO_MMDREG_STAT2);
+		if (((status >> MDIO_MMDREG_STAT2_PRESENT_LBN) &
+		     ((1 << MDIO_MMDREG_STAT2_PRESENT_WIDTH) - 1)) !=
+		    MDIO_MMDREG_STAT2_PRESENT_VAL) {
+			EFX_ERR(efx, "PHY MMD %d not responding.\n", mmd);
+			return -EIO;
+		}
 	}
 
 	/* Read MMD STATUS 1 to check for fault. */
@@ -121,16 +124,18 @@ int mdio_clause45_wait_reset_mmds(struct efx_nic *efx,
 int mdio_clause45_check_mmds(struct efx_nic *efx,
 			     unsigned int mmd_mask, unsigned int fatal_mask)
 {
-	int devices, mmd = 0;
-	int probe_mmd;
+	u32 devices;
+	int mmd = 0, probe_mmd;
 
 	/* Historically we have probed the PHYXS to find out what devices are
 	 * present,but that doesn't work so well if the PHYXS isn't expected
 	 * to exist, if so just find the first item in the list supplied. */
-	probe_mmd = (mmd_mask & MDIO_MMDREG_DEVS0_PHYXS) ? MDIO_MMD_PHYXS :
+	probe_mmd = (mmd_mask & MDIO_MMDREG_DEVS_PHYXS) ? MDIO_MMD_PHYXS :
 	    __ffs(mmd_mask);
-	devices = mdio_clause45_read(efx, efx->mii.phy_id,
-				     probe_mmd, MDIO_MMDREG_DEVS0);
+	devices = (mdio_clause45_read(efx, efx->mii.phy_id,
+				      probe_mmd, MDIO_MMDREG_DEVS0) |
+		   mdio_clause45_read(efx, efx->mii.phy_id,
+				      probe_mmd, MDIO_MMDREG_DEVS1) << 16);
 
 	/* Check all the expected MMDs are present */
 	if (devices < 0) {
@@ -162,7 +167,7 @@ int mdio_clause45_check_mmds(struct efx_nic *efx,
 bool mdio_clause45_links_ok(struct efx_nic *efx, unsigned int mmd_mask)
 {
 	int phy_id = efx->mii.phy_id;
-	int status;
+	u32 reg;
 	bool ok = true;
 	int mmd = 0;
 
@@ -174,26 +179,33 @@ bool mdio_clause45_links_ok(struct efx_nic *efx, unsigned int mmd_mask)
 		return false;
 	else if (efx_phy_mode_disabled(efx->phy_mode))
 		return false;
-	else if (efx->loopback_mode == LOOPBACK_PHYXS)
-		mmd_mask &= ~(MDIO_MMDREG_DEVS0_PHYXS |
-			      MDIO_MMDREG_DEVS0_PCS |
-			      MDIO_MMDREG_DEVS0_PMAPMD);
-	else if (efx->loopback_mode == LOOPBACK_PCS)
-		mmd_mask &= ~(MDIO_MMDREG_DEVS0_PCS |
-			      MDIO_MMDREG_DEVS0_PMAPMD);
+	else if (efx->loopback_mode == LOOPBACK_PHYXS) {
+		mmd_mask &= ~(MDIO_MMDREG_DEVS_PHYXS |
+			      MDIO_MMDREG_DEVS_PCS |
+			      MDIO_MMDREG_DEVS_PMAPMD |
+			      MDIO_MMDREG_DEVS_AN);
+		if (!mmd_mask) {
+			reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PHYXS,
+						 MDIO_PHYXS_STATUS2);
+			return !(reg & (1 << MDIO_PHYXS_STATUS2_RX_FAULT_LBN));
+		}
+	} else if (efx->loopback_mode == LOOPBACK_PCS)
+		mmd_mask &= ~(MDIO_MMDREG_DEVS_PCS |
+			      MDIO_MMDREG_DEVS_PMAPMD |
+			      MDIO_MMDREG_DEVS_AN);
 	else if (efx->loopback_mode == LOOPBACK_PMAPMD)
-		mmd_mask &= ~MDIO_MMDREG_DEVS0_PMAPMD;
+		mmd_mask &= ~(MDIO_MMDREG_DEVS_PMAPMD |
+			      MDIO_MMDREG_DEVS_AN);
 
 	while (mmd_mask) {
 		if (mmd_mask & 1) {
 			/* Double reads because link state is latched, and a
 			 * read moves the current state into the register */
-			status = mdio_clause45_read(efx, phy_id,
-						    mmd, MDIO_MMDREG_STAT1);
-			status = mdio_clause45_read(efx, phy_id,
-						    mmd, MDIO_MMDREG_STAT1);
-
-			ok = ok && (status & (1 << MDIO_MMDREG_STAT1_LINK_LBN));
+			reg = mdio_clause45_read(efx, phy_id,
+						 mmd, MDIO_MMDREG_STAT1);
+			reg = mdio_clause45_read(efx, phy_id,
+						 mmd, MDIO_MMDREG_STAT1);
+			ok = ok && (reg & (1 << MDIO_MMDREG_STAT1_LINK_LBN));
 		}
 		mmd_mask = (mmd_mask >> 1);
 		mmd++;
@@ -203,61 +215,73 @@ bool mdio_clause45_links_ok(struct efx_nic *efx, unsigned int mmd_mask)
 
 void mdio_clause45_transmit_disable(struct efx_nic *efx)
 {
-	int phy_id = efx->mii.phy_id;
-	int ctrl1, ctrl2;
-
-	ctrl1 = ctrl2 = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
-					   MDIO_MMDREG_TXDIS);
-	if (efx->phy_mode & PHY_MODE_TX_DISABLED)
-		ctrl2 |= (1 << MDIO_MMDREG_TXDIS_GLOBAL_LBN);
-	else
-		ctrl1 &= ~(1 << MDIO_MMDREG_TXDIS_GLOBAL_LBN);
-	if (ctrl1 != ctrl2)
-		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
-				    MDIO_MMDREG_TXDIS, ctrl2);
+	mdio_clause45_set_flag(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
+			       MDIO_MMDREG_TXDIS, MDIO_MMDREG_TXDIS_GLOBAL_LBN,
+			       efx->phy_mode & PHY_MODE_TX_DISABLED);
 }
 
 void mdio_clause45_phy_reconfigure(struct efx_nic *efx)
 {
 	int phy_id = efx->mii.phy_id;
-	int ctrl1, ctrl2;
 
-	/* Handle (with debouncing) PMA/PMD loopback */
-	ctrl1 = ctrl2 = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
-					   MDIO_MMDREG_CTRL1);
-
-	if (efx->loopback_mode == LOOPBACK_PMAPMD)
-		ctrl2 |= (1 << MDIO_PMAPMD_CTRL1_LBACK_LBN);
-	else
-		ctrl2 &= ~(1 << MDIO_PMAPMD_CTRL1_LBACK_LBN);
+	mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_PMAPMD,
+			       MDIO_MMDREG_CTRL1, MDIO_PMAPMD_CTRL1_LBACK_LBN,
+			       efx->loopback_mode == LOOPBACK_PMAPMD);
+	mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_PCS,
+			       MDIO_MMDREG_CTRL1, MDIO_MMDREG_CTRL1_LBACK_LBN,
+			       efx->loopback_mode == LOOPBACK_PCS);
+	mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_PHYXS,
+			       MDIO_MMDREG_CTRL1, MDIO_MMDREG_CTRL1_LBACK_LBN,
+			       efx->loopback_mode == LOOPBACK_NETWORK);
+}
 
-	if (ctrl1 != ctrl2)
-		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
-				    MDIO_MMDREG_CTRL1, ctrl2);
+static void mdio_clause45_set_mmd_lpower(struct efx_nic *efx,
+					 int lpower, int mmd)
+{
+	int phy = efx->mii.phy_id;
+	int stat = mdio_clause45_read(efx, phy, mmd, MDIO_MMDREG_STAT1);
 
-	/* Handle (with debouncing) PCS loopback */
-	ctrl1 = ctrl2 = mdio_clause45_read(efx, phy_id, MDIO_MMD_PCS,
-					   MDIO_MMDREG_CTRL1);
-	if (efx->loopback_mode == LOOPBACK_PCS)
-		ctrl2 |= (1 << MDIO_MMDREG_CTRL1_LBACK_LBN);
-	else
-		ctrl2 &= ~(1 << MDIO_MMDREG_CTRL1_LBACK_LBN);
+	EFX_TRACE(efx, "Setting low power mode for MMD %d to %d\n",
+		  mmd, lpower);
 
-	if (ctrl1 != ctrl2)
-		mdio_clause45_write(efx, phy_id, MDIO_MMD_PCS,
-				    MDIO_MMDREG_CTRL1, ctrl2);
+	if (stat & (1 << MDIO_MMDREG_STAT1_LPABLE_LBN)) {
+		mdio_clause45_set_flag(efx, phy, mmd, MDIO_MMDREG_CTRL1,
+				       MDIO_MMDREG_CTRL1_LPOWER_LBN, lpower);
+	}
+}
 
-	/* Handle (with debouncing) PHYXS network loopback */
-	ctrl1 = ctrl2 = mdio_clause45_read(efx, phy_id, MDIO_MMD_PHYXS,
-					   MDIO_MMDREG_CTRL1);
-	if (efx->loopback_mode == LOOPBACK_NETWORK)
-		ctrl2 |= (1 << MDIO_MMDREG_CTRL1_LBACK_LBN);
-	else
-		ctrl2 &= ~(1 << MDIO_MMDREG_CTRL1_LBACK_LBN);
+void mdio_clause45_set_mmds_lpower(struct efx_nic *efx,
+				   int low_power, unsigned int mmd_mask)
+{
+	int mmd = 0;
+	mmd_mask &= ~MDIO_MMDREG_DEVS_AN;
+	while (mmd_mask) {
+		if (mmd_mask & 1)
+			mdio_clause45_set_mmd_lpower(efx, low_power, mmd);
+		mmd_mask = (mmd_mask >> 1);
+		mmd++;
+	}
+}
 
-	if (ctrl1 != ctrl2)
-		mdio_clause45_write(efx, phy_id, MDIO_MMD_PHYXS,
-				    MDIO_MMDREG_CTRL1, ctrl2);
+static u32 mdio_clause45_get_an(struct efx_nic *efx, u16 addr, u32 xnp)
+{
+	int phy_id = efx->mii.phy_id;
+	u32 result = 0;
+	int reg;
+
+	reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN, addr);
+	if (reg & ADVERTISE_10HALF)
+		result |= ADVERTISED_10baseT_Half;
+	if (reg & ADVERTISE_10FULL)
+		result |= ADVERTISED_10baseT_Full;
+	if (reg & ADVERTISE_100HALF)
+		result |= ADVERTISED_100baseT_Half;
+	if (reg & ADVERTISE_100FULL)
+		result |= ADVERTISED_100baseT_Full;
+	if (reg & LPA_RESV)
+		result |= xnp;
+
+	return result;
 }
 
 /**
@@ -266,95 +290,290 @@ void mdio_clause45_phy_reconfigure(struct efx_nic *efx)
  * @ecmd: 		Buffer for settings
  *
  * On return the 'port', 'speed', 'supported' and 'advertising' fields of
- * ecmd have been filled out based on the PMA type.
+ * ecmd have been filled out.
  */
 void mdio_clause45_get_settings(struct efx_nic *efx,
 				struct ethtool_cmd *ecmd)
 {
-	int pma_type;
+	mdio_clause45_get_settings_ext(efx, ecmd, 0, 0);
+}
 
-	/* If no PMA is present we are presumably talking something XAUI-ish
-	 * like CX4. Which we report as FIBRE (see below) */
-	if ((efx->phy_op->mmds & DEV_PRESENT_BIT(MDIO_MMD_PMAPMD)) == 0) {
-		ecmd->speed = SPEED_10000;
-		ecmd->port = PORT_FIBRE;
-		ecmd->supported = SUPPORTED_FIBRE;
-		ecmd->advertising = ADVERTISED_FIBRE;
-		return;
-	}
+/**
+ * mdio_clause45_get_settings_ext - Read (some of) the PHY settings over MDIO.
+ * @efx:		Efx NIC
+ * @ecmd: 		Buffer for settings
+ * @xnp:		Advertised Extended Next Page state
+ * @xnp_lpa:		Link Partner's advertised XNP state
+ *
+ * On return the 'port', 'speed', 'supported' and 'advertising' fields of
+ * ecmd have been filled out.
+ */
+void mdio_clause45_get_settings_ext(struct efx_nic *efx,
+				    struct ethtool_cmd *ecmd,
+				    u32 xnp, u32 xnp_lpa)
+{
+	int phy_id = efx->mii.phy_id;
+	int reg;
 
-	pma_type = mdio_clause45_read(efx, efx->mii.phy_id,
-				      MDIO_MMD_PMAPMD, MDIO_MMDREG_CTRL2);
-	pma_type &= MDIO_PMAPMD_CTRL2_TYPE_MASK;
+	ecmd->transceiver = XCVR_INTERNAL;
+	ecmd->phy_address = phy_id;
 
-	switch (pma_type) {
-		/* We represent CX4 as fibre in the absence of anything
-		   better. */
-	case MDIO_PMAPMD_CTRL2_10G_CX4:
-		ecmd->speed = SPEED_10000;
-		ecmd->port = PORT_FIBRE;
-		ecmd->supported = SUPPORTED_FIBRE;
-		ecmd->advertising = ADVERTISED_FIBRE;
-		break;
-		/* 10G Base-T */
+	reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+				 MDIO_MMDREG_CTRL2);
+	switch (reg & MDIO_PMAPMD_CTRL2_TYPE_MASK) {
 	case MDIO_PMAPMD_CTRL2_10G_BT:
-		ecmd->speed = SPEED_10000;
-		ecmd->port = PORT_TP;
-		ecmd->supported = SUPPORTED_TP | SUPPORTED_10000baseT_Full;
-		ecmd->advertising = (ADVERTISED_FIBRE
-				     | ADVERTISED_10000baseT_Full);
-		break;
 	case MDIO_PMAPMD_CTRL2_1G_BT:
-		ecmd->speed = SPEED_1000;
-		ecmd->port = PORT_TP;
-		ecmd->supported = SUPPORTED_TP | SUPPORTED_1000baseT_Full;
-		ecmd->advertising = (ADVERTISED_FIBRE
-				     | ADVERTISED_1000baseT_Full);
-		break;
 	case MDIO_PMAPMD_CTRL2_100_BT:
-		ecmd->speed = SPEED_100;
-		ecmd->port = PORT_TP;
-		ecmd->supported = SUPPORTED_TP | SUPPORTED_100baseT_Full;
-		ecmd->advertising = (ADVERTISED_FIBRE
-				     | ADVERTISED_100baseT_Full);
-		break;
 	case MDIO_PMAPMD_CTRL2_10_BT:
-		ecmd->speed = SPEED_10;
 		ecmd->port = PORT_TP;
-		ecmd->supported = SUPPORTED_TP | SUPPORTED_10baseT_Full;
-		ecmd->advertising = ADVERTISED_FIBRE | ADVERTISED_10baseT_Full;
+		ecmd->supported = SUPPORTED_TP;
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+					 MDIO_MMDREG_SPEED);
+		if (reg & (1 << MDIO_MMDREG_SPEED_10G_LBN))
+			ecmd->supported |= SUPPORTED_10000baseT_Full;
+		if (reg & (1 << MDIO_MMDREG_SPEED_1000M_LBN))
+			ecmd->supported |= (SUPPORTED_1000baseT_Full |
+					    SUPPORTED_1000baseT_Half);
+		if (reg & (1 << MDIO_MMDREG_SPEED_100M_LBN))
+			ecmd->supported |= (SUPPORTED_100baseT_Full |
+					    SUPPORTED_100baseT_Half);
+		if (reg & (1 << MDIO_MMDREG_SPEED_10M_LBN))
+			ecmd->supported |= (SUPPORTED_10baseT_Full |
+					    SUPPORTED_10baseT_Half);
+		ecmd->advertising = ADVERTISED_TP;
 		break;
-	/* All the other defined modes are flavours of
-	 * 10G optical */
+
+	/* We represent CX4 as fibre in the absence of anything better */
+	case MDIO_PMAPMD_CTRL2_10G_CX4:
+	/* All the other defined modes are flavours of optical */
 	default:
-		ecmd->speed = SPEED_10000;
 		ecmd->port = PORT_FIBRE;
 		ecmd->supported = SUPPORTED_FIBRE;
 		ecmd->advertising = ADVERTISED_FIBRE;
 		break;
 	}
+
+	if (efx->phy_op->mmds & DEV_PRESENT_BIT(MDIO_MMD_AN)) {
+		ecmd->supported |= SUPPORTED_Autoneg;
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+					 MDIO_MMDREG_CTRL1);
+		if (reg & BMCR_ANENABLE) {
+			ecmd->autoneg = AUTONEG_ENABLE;
+			ecmd->advertising |=
+				ADVERTISED_Autoneg |
+				mdio_clause45_get_an(efx,
+						     MDIO_AN_ADVERTISE, xnp);
+		} else
+			ecmd->autoneg = AUTONEG_DISABLE;
+	} else
+		ecmd->autoneg = AUTONEG_DISABLE;
+
+	if (ecmd->autoneg) {
+		/* If AN is complete, report best common mode,
+		 * otherwise report best advertised mode. */
+		u32 common = ecmd->advertising;
+		if (mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+				       MDIO_MMDREG_STAT1) &
+		    (1 << MDIO_AN_STATUS_AN_DONE_LBN)) {
+			common &= mdio_clause45_get_an(efx, MDIO_AN_LPA,
+						       xnp_lpa);
+		}
+		if (common & ADVERTISED_10000baseT_Full) {
+			ecmd->speed = SPEED_10000;
+			ecmd->duplex = DUPLEX_FULL;
+		} else if (common & (ADVERTISED_1000baseT_Full |
+				     ADVERTISED_1000baseT_Half)) {
+			ecmd->speed = SPEED_1000;
+			ecmd->duplex = !!(common & ADVERTISED_1000baseT_Full);
+		} else if (common & (ADVERTISED_100baseT_Full |
+				     ADVERTISED_100baseT_Half)) {
+			ecmd->speed = SPEED_100;
+			ecmd->duplex = !!(common & ADVERTISED_100baseT_Full);
+		} else {
+			ecmd->speed = SPEED_10;
+			ecmd->duplex = !!(common & ADVERTISED_10baseT_Full);
+		}
+	} else {
+		/* Report forced settings */
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+					 MDIO_MMDREG_CTRL1);
+		ecmd->speed = (((reg & BMCR_SPEED1000) ? 100 : 1) *
+			       ((reg & BMCR_SPEED100) ? 100 : 10));
+		ecmd->duplex = (reg & BMCR_FULLDPLX ||
+				ecmd->speed == SPEED_10000);
+	}
 }
 
 /**
  * mdio_clause45_set_settings - Set (some of) the PHY settings over MDIO.
  * @efx:		Efx NIC
  * @ecmd: 		New settings
- *
- * Currently this just enforces that we are _not_ changing the
- * 'port', 'speed', 'supported' or 'advertising' settings as these
- * cannot be changed on any currently supported PHY.
  */
 int mdio_clause45_set_settings(struct efx_nic *efx,
 			       struct ethtool_cmd *ecmd)
 {
-	struct ethtool_cmd tmpcmd;
-	mdio_clause45_get_settings(efx, &tmpcmd);
-	/* None of the current PHYs support more than one mode
-	 * of operation (and only 10GBT ever will), so keep things
-	 * simple for now */
-	if ((ecmd->speed == tmpcmd.speed) && (ecmd->port == tmpcmd.port) &&
-	    (ecmd->supported == tmpcmd.supported) &&
-	    (ecmd->advertising == tmpcmd.advertising))
+	int phy_id = efx->mii.phy_id;
+	struct ethtool_cmd prev;
+	u32 required;
+	int ctrl1_bits, reg;
+
+	efx->phy_op->get_settings(efx, &prev);
+
+	if (ecmd->advertising == prev.advertising &&
+	    ecmd->speed == prev.speed &&
+	    ecmd->duplex == prev.duplex &&
+	    ecmd->port == prev.port &&
+	    ecmd->autoneg == prev.autoneg)
 		return 0;
-	return -EOPNOTSUPP;
+
+	/* We can only change these settings for -T PHYs */
+	if (prev.port != PORT_TP || ecmd->port != PORT_TP)
+		return -EINVAL;
+
+	/* Check that PHY supports these settings and work out the
+	 * basic control bits */
+	if (ecmd->duplex) {
+		switch (ecmd->speed) {
+		case SPEED_10:
+			ctrl1_bits = BMCR_FULLDPLX;
+			required = SUPPORTED_10baseT_Full;
+			break;
+		case SPEED_100:
+			ctrl1_bits = BMCR_SPEED100 | BMCR_FULLDPLX;
+			required = SUPPORTED_100baseT_Full;
+			break;
+		case SPEED_1000:
+			ctrl1_bits = BMCR_SPEED1000 | BMCR_FULLDPLX;
+			required = SUPPORTED_1000baseT_Full;
+			break;
+		case SPEED_10000:
+			ctrl1_bits = (BMCR_SPEED1000 | BMCR_SPEED100 |
+				      BMCR_FULLDPLX);
+			required = SUPPORTED_10000baseT_Full;
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		switch (ecmd->speed) {
+		case SPEED_10:
+			ctrl1_bits = 0;
+			required = SUPPORTED_10baseT_Half;
+			break;
+		case SPEED_100:
+			ctrl1_bits = BMCR_SPEED100;
+			required = SUPPORTED_100baseT_Half;
+			break;
+		case SPEED_1000:
+			ctrl1_bits = BMCR_SPEED1000;
+			required = SUPPORTED_1000baseT_Half;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	if (ecmd->autoneg)
+		required |= SUPPORTED_Autoneg;
+	required |= ecmd->advertising;
+	if (required & ~prev.supported)
+		return -EINVAL;
+
+	/* Set the basic control bits */
+	reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+				 MDIO_MMDREG_CTRL1);
+	reg &= ~(BMCR_SPEED1000 | BMCR_SPEED100 | BMCR_FULLDPLX | 0x003c);
+	reg |= ctrl1_bits;
+	mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD, MDIO_MMDREG_CTRL1,
+			    reg);
+
+	/* Set the AN registers */
+	if (ecmd->autoneg != prev.autoneg ||
+	    ecmd->advertising != prev.advertising) {
+		bool xnp = false;
+
+		if (efx->phy_op->set_xnp_advertise)
+			xnp = efx->phy_op->set_xnp_advertise(efx,
+							     ecmd->advertising);
+
+		if (ecmd->autoneg) {
+			reg = 0;
+			if (ecmd->advertising & ADVERTISED_10baseT_Half)
+				reg |= ADVERTISE_10HALF;
+			if (ecmd->advertising & ADVERTISED_10baseT_Full)
+				reg |= ADVERTISE_10FULL;
+			if (ecmd->advertising & ADVERTISED_100baseT_Half)
+				reg |= ADVERTISE_100HALF;
+			if (ecmd->advertising & ADVERTISED_100baseT_Full)
+				reg |= ADVERTISE_100FULL;
+			if (xnp)
+				reg |= ADVERTISE_RESV;
+			mdio_clause45_write(efx, phy_id, MDIO_MMD_AN,
+					    MDIO_AN_ADVERTISE, reg);
+		}
+
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+					 MDIO_MMDREG_CTRL1);
+		if (ecmd->autoneg)
+			reg |= BMCR_ANENABLE | BMCR_ANRESTART;
+		else
+			reg &= ~BMCR_ANENABLE;
+		if (xnp)
+			reg |= 1 << MDIO_AN_CTRL_XNP_LBN;
+		else
+			reg &= ~(1 << MDIO_AN_CTRL_XNP_LBN);
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_AN,
+				    MDIO_MMDREG_CTRL1, reg);
+	}
+
+	return 0;
+}
+
+void mdio_clause45_set_pause(struct efx_nic *efx)
+{
+	int phy_id = efx->mii.phy_id;
+	int reg;
+
+	if (efx->phy_op->mmds & DEV_PRESENT_BIT(MDIO_MMD_AN)) {
+		/* Set pause capability advertising */
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+					 MDIO_AN_ADVERTISE);
+		reg &= ~(ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM);
+		reg |= efx_fc_advertise(efx->wanted_fc);
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_AN,
+				    MDIO_AN_ADVERTISE, reg);
+
+		/* Restart auto-negotiation */
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+					 MDIO_MMDREG_CTRL1);
+		if (reg & BMCR_ANENABLE) {
+			reg |= BMCR_ANRESTART;
+			mdio_clause45_write(efx, phy_id, MDIO_MMD_AN,
+					    MDIO_MMDREG_CTRL1, reg);
+		}
+	}
+}
+
+enum efx_fc_type mdio_clause45_get_pause(struct efx_nic *efx)
+{
+	int phy_id = efx->mii.phy_id;
+	int lpa;
+
+	if (!(efx->phy_op->mmds & DEV_PRESENT_BIT(MDIO_MMD_AN)))
+		return efx->wanted_fc;
+	lpa = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN, MDIO_AN_LPA);
+	return efx_fc_resolve(efx->wanted_fc, lpa);
+}
+
+void mdio_clause45_set_flag(struct efx_nic *efx, u8 prt, u8 dev,
+			    u16 addr, int bit, bool sense)
+{
+	int old_val = mdio_clause45_read(efx, prt, dev, addr);
+	int new_val;
+
+	if (sense)
+		new_val = old_val | (1 << bit);
+	else
+		new_val = old_val & ~(1 << bit);
+	if (old_val != new_val)
+		mdio_clause45_write(efx, prt, dev, addr, new_val);
 }
diff --git a/drivers/net/sfc/mdio_10g.h b/drivers/net/sfc/mdio_10g.h
index 19c42eaf7fb..09bf801d056 100644
--- a/drivers/net/sfc/mdio_10g.h
+++ b/drivers/net/sfc/mdio_10g.h
@@ -33,6 +33,8 @@
 #define MDIO_MMD_TC	(6)
 /* Auto negotiation */
 #define MDIO_MMD_AN	(7)
+/* Clause 22 extension */
+#define MDIO_MMD_C22EXT	29
 
 /* Generic register locations */
 #define MDIO_MMDREG_CTRL1	(0)
@@ -54,6 +56,9 @@
 /* Loopback bit for WIS, PCS, PHYSX and DTEXS */
 #define MDIO_MMDREG_CTRL1_LBACK_LBN	(14)
 #define MDIO_MMDREG_CTRL1_LBACK_WIDTH	(1)
+/* Low power */
+#define MDIO_MMDREG_CTRL1_LPOWER_LBN	(11)
+#define MDIO_MMDREG_CTRL1_LPOWER_WIDTH	(1)
 
 /* Bits in MMDREG_STAT1 */
 #define MDIO_MMDREG_STAT1_FAULT_LBN	(7)
@@ -70,14 +75,26 @@
 #define MDIO_ID_MODEL(_id32)	((_id32 >> 4) & 0x3f)
 #define MDIO_ID_OUI(_id32)	(_id32 >> 10)
 
-/* Bits in MMDREG_DEVS0. Someone thoughtfully layed things out
+/* Bits in MMDREG_DEVS0/1. Someone thoughtfully layed things out
  * so the 'bit present' bit number of an MMD is the number of
  * that MMD */
 #define DEV_PRESENT_BIT(_b) (1 << _b)
 
-#define MDIO_MMDREG_DEVS0_PHYXS	 DEV_PRESENT_BIT(MDIO_MMD_PHYXS)
-#define MDIO_MMDREG_DEVS0_PCS	 DEV_PRESENT_BIT(MDIO_MMD_PCS)
-#define MDIO_MMDREG_DEVS0_PMAPMD DEV_PRESENT_BIT(MDIO_MMD_PMAPMD)
+#define MDIO_MMDREG_DEVS_PHYXS	DEV_PRESENT_BIT(MDIO_MMD_PHYXS)
+#define MDIO_MMDREG_DEVS_PCS	DEV_PRESENT_BIT(MDIO_MMD_PCS)
+#define MDIO_MMDREG_DEVS_PMAPMD	DEV_PRESENT_BIT(MDIO_MMD_PMAPMD)
+#define MDIO_MMDREG_DEVS_AN	DEV_PRESENT_BIT(MDIO_MMD_AN)
+#define MDIO_MMDREG_DEVS_C22EXT	DEV_PRESENT_BIT(MDIO_MMD_C22EXT)
+
+/* Bits in MMDREG_SPEED */
+#define MDIO_MMDREG_SPEED_10G_LBN	0
+#define MDIO_MMDREG_SPEED_10G_WIDTH	1
+#define MDIO_MMDREG_SPEED_1000M_LBN	4
+#define MDIO_MMDREG_SPEED_1000M_WIDTH	1
+#define MDIO_MMDREG_SPEED_100M_LBN	5
+#define MDIO_MMDREG_SPEED_100M_WIDTH	1
+#define MDIO_MMDREG_SPEED_10M_LBN	6
+#define MDIO_MMDREG_SPEED_10M_WIDTH	1
 
 /* Bits in MMDREG_STAT2 */
 #define MDIO_MMDREG_STAT2_PRESENT_VAL	(2)
@@ -111,17 +128,34 @@
 #define MDIO_PMAPMD_CTRL2_10_BT		(0xf)
 #define MDIO_PMAPMD_CTRL2_TYPE_MASK	(0xf)
 
+/* PMA 10GBT registers */
+#define MDIO_PMAPMD_10GBT_TXPWR		(131)
+#define MDIO_PMAPMD_10GBT_TXPWR_SHORT_LBN (0)
+#define MDIO_PMAPMD_10GBT_TXPWR_SHORT_WIDTH (1)
+
+/* PHY XGXS Status 2 */
+#define MDIO_PHYXS_STATUS2              (8)
+#define MDIO_PHYXS_STATUS2_RX_FAULT_LBN 10
+
 /* PHY XGXS lane state */
 #define MDIO_PHYXS_LANE_STATE		(0x18)
 #define MDIO_PHYXS_LANE_ALIGNED_LBN	(12)
 
 /* AN registers */
+#define MDIO_AN_CTRL_XNP_LBN		13
 #define MDIO_AN_STATUS			(1)
 #define MDIO_AN_STATUS_XNP_LBN		(7)
 #define MDIO_AN_STATUS_PAGE_LBN		(6)
 #define MDIO_AN_STATUS_AN_DONE_LBN	(5)
 #define MDIO_AN_STATUS_LP_AN_CAP_LBN	(0)
 
+#define MDIO_AN_ADVERTISE		16
+#define MDIO_AN_ADVERTISE_XNP_LBN	12
+#define MDIO_AN_LPA			19
+#define MDIO_AN_XNP			22
+#define MDIO_AN_LPA_XNP			25
+
+#define MDIO_AN_10GBT_ADVERTISE		32
 #define MDIO_AN_10GBT_STATUS		(33)
 #define MDIO_AN_10GBT_STATUS_MS_FLT_LBN (15) /* MASTER/SLAVE config fault */
 #define MDIO_AN_10GBT_STATUS_MS_LBN     (14) /* MASTER/SLAVE config */
@@ -240,16 +274,37 @@ extern void mdio_clause45_transmit_disable(struct efx_nic *efx);
 /* Generic part of reconfigure: set/clear loopback bits */
 extern void mdio_clause45_phy_reconfigure(struct efx_nic *efx);
 
+/* Set the power state of the specified MMDs */
+extern void mdio_clause45_set_mmds_lpower(struct efx_nic *efx,
+					  int low_power, unsigned int mmd_mask);
+
 /* Read (some of) the PHY settings over MDIO */
 extern void mdio_clause45_get_settings(struct efx_nic *efx,
 				       struct ethtool_cmd *ecmd);
 
+/* Read (some of) the PHY settings over MDIO */
+extern void
+mdio_clause45_get_settings_ext(struct efx_nic *efx, struct ethtool_cmd *ecmd,
+			       u32 xnp, u32 xnp_lpa);
+
 /* Set (some of) the PHY settings over MDIO */
 extern int mdio_clause45_set_settings(struct efx_nic *efx,
 				      struct ethtool_cmd *ecmd);
 
+/* Set pause parameters to be advertised through AN (if available) */
+extern void mdio_clause45_set_pause(struct efx_nic *efx);
+
+/* Get pause parameters from AN if available (otherwise return
+ * requested pause parameters)
+ */
+enum efx_fc_type mdio_clause45_get_pause(struct efx_nic *efx);
+
 /* Wait for specified MMDs to exit reset within a timeout */
 extern int mdio_clause45_wait_reset_mmds(struct efx_nic *efx,
 					 unsigned int mmd_mask);
 
+/* Set or clear flag, debouncing */
+extern void mdio_clause45_set_flag(struct efx_nic *efx, u8 prt, u8 dev,
+				   u16 addr, int bit, bool sense);
+
 #endif /* EFX_MDIO_10G_H */
diff --git a/drivers/net/sfc/mtd.c b/drivers/net/sfc/mtd.c
new file mode 100644
index 00000000000..665cafb88d6
--- /dev/null
+++ b/drivers/net/sfc/mtd.c
@@ -0,0 +1,268 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2006-2008 Solarflare Communications Inc.
+ *
+ * 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, incorporated herein by reference.
+ */
+
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/delay.h>
+
+#define EFX_DRIVER_NAME "sfc_mtd"
+#include "net_driver.h"
+#include "spi.h"
+
+#define EFX_SPI_VERIFY_BUF_LEN 16
+
+struct efx_mtd {
+	const struct efx_spi_device *spi;
+	struct mtd_info mtd;
+	char name[IFNAMSIZ + 20];
+};
+
+/* SPI utilities */
+
+static int efx_spi_slow_wait(struct efx_mtd *efx_mtd, bool uninterruptible)
+{
+	const struct efx_spi_device *spi = efx_mtd->spi;
+	struct efx_nic *efx = spi->efx;
+	u8 status;
+	int rc, i;
+
+	/* Wait up to 4s for flash/EEPROM to finish a slow operation. */
+	for (i = 0; i < 40; i++) {
+		__set_current_state(uninterruptible ?
+				    TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE);
+		schedule_timeout(HZ / 10);
+		rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL,
+				    &status, sizeof(status));
+		if (rc)
+			return rc;
+		if (!(status & SPI_STATUS_NRDY))
+			return 0;
+		if (signal_pending(current))
+			return -EINTR;
+	}
+	EFX_ERR(efx, "timed out waiting for %s\n", efx_mtd->name);
+	return -ETIMEDOUT;
+}
+
+static int efx_spi_unlock(const struct efx_spi_device *spi)
+{
+	const u8 unlock_mask = (SPI_STATUS_BP2 | SPI_STATUS_BP1 |
+				SPI_STATUS_BP0);
+	u8 status;
+	int rc;
+
+	rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, &status, sizeof(status));
+	if (rc)
+		return rc;
+
+	if (!(status & unlock_mask))
+		return 0; /* already unlocked */
+
+	rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0);
+	if (rc)
+		return rc;
+	rc = falcon_spi_cmd(spi, SPI_SST_EWSR, -1, NULL, NULL, 0);
+	if (rc)
+		return rc;
+
+	status &= ~unlock_mask;
+	rc = falcon_spi_cmd(spi, SPI_WRSR, -1, &status, NULL, sizeof(status));
+	if (rc)
+		return rc;
+	rc = falcon_spi_wait_write(spi);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len)
+{
+	const struct efx_spi_device *spi = efx_mtd->spi;
+	unsigned pos, block_len;
+	u8 empty[EFX_SPI_VERIFY_BUF_LEN];
+	u8 buffer[EFX_SPI_VERIFY_BUF_LEN];
+	int rc;
+
+	if (len != spi->erase_size)
+		return -EINVAL;
+
+	if (spi->erase_command == 0)
+		return -EOPNOTSUPP;
+
+	rc = efx_spi_unlock(spi);
+	if (rc)
+		return rc;
+	rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0);
+	if (rc)
+		return rc;
+	rc = falcon_spi_cmd(spi, spi->erase_command, start, NULL, NULL, 0);
+	if (rc)
+		return rc;
+	rc = efx_spi_slow_wait(efx_mtd, false);
+
+	/* Verify the entire region has been wiped */
+	memset(empty, 0xff, sizeof(empty));
+	for (pos = 0; pos < len; pos += block_len) {
+		block_len = min(len - pos, sizeof(buffer));
+		rc = falcon_spi_read(spi, start + pos, block_len, NULL, buffer);
+		if (rc)
+			return rc;
+		if (memcmp(empty, buffer, block_len))
+			return -EIO;
+
+		/* Avoid locking up the system */
+		cond_resched();
+		if (signal_pending(current))
+			return -EINTR;
+	}
+
+	return rc;
+}
+
+/* MTD interface */
+
+static int efx_mtd_read(struct mtd_info *mtd, loff_t start, size_t len,
+			size_t *retlen, u8 *buffer)
+{
+	struct efx_mtd *efx_mtd = mtd->priv;
+	const struct efx_spi_device *spi = efx_mtd->spi;
+	struct efx_nic *efx = spi->efx;
+	int rc;
+
+	rc = mutex_lock_interruptible(&efx->spi_lock);
+	if (rc)
+		return rc;
+	rc = falcon_spi_read(spi, FALCON_FLASH_BOOTCODE_START + start,
+			     len, retlen, buffer);
+	mutex_unlock(&efx->spi_lock);
+	return rc;
+}
+
+static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase)
+{
+	struct efx_mtd *efx_mtd = mtd->priv;
+	struct efx_nic *efx = efx_mtd->spi->efx;
+	int rc;
+
+	rc = mutex_lock_interruptible(&efx->spi_lock);
+	if (rc)
+		return rc;
+	rc = efx_spi_erase(efx_mtd, FALCON_FLASH_BOOTCODE_START + erase->addr,
+			   erase->len);
+	mutex_unlock(&efx->spi_lock);
+
+	if (rc == 0) {
+		erase->state = MTD_ERASE_DONE;
+	} else {
+		erase->state = MTD_ERASE_FAILED;
+		erase->fail_addr = 0xffffffff;
+	}
+	mtd_erase_callback(erase);
+	return rc;
+}
+
+static int efx_mtd_write(struct mtd_info *mtd, loff_t start,
+			 size_t len, size_t *retlen, const u8 *buffer)
+{
+	struct efx_mtd *efx_mtd = mtd->priv;
+	const struct efx_spi_device *spi = efx_mtd->spi;
+	struct efx_nic *efx = spi->efx;
+	int rc;
+
+	rc = mutex_lock_interruptible(&efx->spi_lock);
+	if (rc)
+		return rc;
+	rc = falcon_spi_write(spi, FALCON_FLASH_BOOTCODE_START + start,
+			      len, retlen, buffer);
+	mutex_unlock(&efx->spi_lock);
+	return rc;
+}
+
+static void efx_mtd_sync(struct mtd_info *mtd)
+{
+	struct efx_mtd *efx_mtd = mtd->priv;
+	struct efx_nic *efx = efx_mtd->spi->efx;
+	int rc;
+
+	mutex_lock(&efx->spi_lock);
+	rc = efx_spi_slow_wait(efx_mtd, true);
+	mutex_unlock(&efx->spi_lock);
+
+	if (rc)
+		EFX_ERR(efx, "%s sync failed (%d)\n", efx_mtd->name, rc);
+	return;
+}
+
+void efx_mtd_remove(struct efx_nic *efx)
+{
+	if (efx->spi_flash && efx->spi_flash->mtd) {
+		struct efx_mtd *efx_mtd = efx->spi_flash->mtd;
+		int rc;
+
+		for (;;) {
+			rc = del_mtd_device(&efx_mtd->mtd);
+			if (rc != -EBUSY)
+				break;
+			ssleep(1);
+		}
+		WARN_ON(rc);
+		kfree(efx_mtd);
+	}
+}
+
+void efx_mtd_rename(struct efx_nic *efx)
+{
+	if (efx->spi_flash && efx->spi_flash->mtd) {
+		struct efx_mtd *efx_mtd = efx->spi_flash->mtd;
+		snprintf(efx_mtd->name, sizeof(efx_mtd->name),
+			 "%s sfc_flash_bootrom", efx->name);
+	}
+}
+
+int efx_mtd_probe(struct efx_nic *efx)
+{
+	struct efx_spi_device *spi = efx->spi_flash;
+	struct efx_mtd *efx_mtd;
+
+	if (!spi || spi->size <= FALCON_FLASH_BOOTCODE_START)
+		return -ENODEV;
+
+	efx_mtd = kzalloc(sizeof(*efx_mtd), GFP_KERNEL);
+	if (!efx_mtd)
+		return -ENOMEM;
+
+	efx_mtd->spi = spi;
+	spi->mtd = efx_mtd;
+
+	efx_mtd->mtd.type = MTD_NORFLASH;
+	efx_mtd->mtd.flags = MTD_CAP_NORFLASH;
+	efx_mtd->mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START;
+	efx_mtd->mtd.erasesize = spi->erase_size;
+	efx_mtd->mtd.writesize = 1;
+	efx_mtd_rename(efx);
+
+	efx_mtd->mtd.owner = THIS_MODULE;
+	efx_mtd->mtd.priv = efx_mtd;
+	efx_mtd->mtd.name = efx_mtd->name;
+	efx_mtd->mtd.erase = efx_mtd_erase;
+	efx_mtd->mtd.read = efx_mtd_read;
+	efx_mtd->mtd.write = efx_mtd_write;
+	efx_mtd->mtd.sync = efx_mtd_sync;
+
+	if (add_mtd_device(&efx_mtd->mtd)) {
+		kfree(efx_mtd);
+		spi->mtd = NULL;
+		/* add_mtd_device() returns 1 if the MTD table is full */
+		return -ENOMEM;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index cdb11fad605..5f255f75754 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -42,7 +42,7 @@
 #ifndef EFX_DRIVER_NAME
 #define EFX_DRIVER_NAME	"sfc"
 #endif
-#define EFX_DRIVER_VERSION	"2.2"
+#define EFX_DRIVER_VERSION	"2.3"
 
 #ifdef EFX_ENABLE_DEBUG
 #define EFX_BUG_ON_PARANOID(x) BUG_ON(x)
@@ -327,6 +327,7 @@ enum efx_rx_alloc_method {
  *
  * @efx: Associated Efx NIC
  * @channel: Channel instance number
+ * @name: Name for channel and IRQ
  * @used_flags: Channel is used by net driver
  * @enabled: Channel enabled indicator
  * @irq: IRQ number (MSI and MSI-X only)
@@ -357,6 +358,7 @@ enum efx_rx_alloc_method {
 struct efx_channel {
 	struct efx_nic *efx;
 	int channel;
+	char name[IFNAMSIZ + 6];
 	int used_flags;
 	bool enabled;
 	int irq;
@@ -414,6 +416,7 @@ struct efx_blinker {
  * @init_leds: Sets up board LEDs
  * @set_fault_led: Turns the fault LED on or off
  * @blink: Starts/stops blinking
+ * @monitor: Board-specific health check function
  * @fini: Cleanup function
  * @blinker: used to blink LEDs in software
  * @hwmon_client: I2C client for hardware monitor
@@ -428,6 +431,7 @@ struct efx_board {
 	 * have a separate init callback that happens later than
 	 * board init. */
 	int (*init_leds)(struct efx_nic *efx);
+	int (*monitor) (struct efx_nic *nic);
 	void (*set_fault_led) (struct efx_nic *efx, bool state);
 	void (*blink) (struct efx_nic *efx, bool start);
 	void (*fini) (struct efx_nic *nic);
@@ -449,16 +453,20 @@ enum efx_int_mode {
 
 enum phy_type {
 	PHY_TYPE_NONE = 0,
-	PHY_TYPE_CX4_RTMR = 1,
-	PHY_TYPE_1G_ALASKA = 2,
-	PHY_TYPE_10XPRESS = 3,
-	PHY_TYPE_XFP = 4,
+	PHY_TYPE_TXC43128 = 1,
+	PHY_TYPE_88E1111 = 2,
+	PHY_TYPE_SFX7101 = 3,
+	PHY_TYPE_QT2022C2 = 4,
 	PHY_TYPE_PM8358 = 6,
+	PHY_TYPE_SFT9001A = 8,
+	PHY_TYPE_SFT9001B = 10,
 	PHY_TYPE_MAX	/* Insert any new items before this */
 };
 
 #define PHY_ADDR_INVALID 0xff
 
+#define EFX_IS10G(efx) ((efx)->link_speed == 10000)
+
 enum nic_state {
 	STATE_INIT = 0,
 	STATE_RUNNING = 1,
@@ -499,6 +507,55 @@ enum efx_fc_type {
 	EFX_FC_AUTO = 4,
 };
 
+/* Supported MAC bit-mask */
+enum efx_mac_type {
+	EFX_GMAC = 1,
+	EFX_XMAC = 2,
+};
+
+static inline unsigned int efx_fc_advertise(enum efx_fc_type wanted_fc)
+{
+	unsigned int adv = 0;
+	if (wanted_fc & EFX_FC_RX)
+		adv = ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
+	if (wanted_fc & EFX_FC_TX)
+		adv ^= ADVERTISE_PAUSE_ASYM;
+	return adv;
+}
+
+static inline enum efx_fc_type efx_fc_resolve(enum efx_fc_type wanted_fc,
+					      unsigned int lpa)
+{
+	unsigned int adv = efx_fc_advertise(wanted_fc);
+
+	if (!(wanted_fc & EFX_FC_AUTO))
+		return wanted_fc;
+
+	if (adv & lpa & ADVERTISE_PAUSE_CAP)
+		return EFX_FC_RX | EFX_FC_TX;
+	if (adv & lpa & ADVERTISE_PAUSE_ASYM) {
+		if (adv & ADVERTISE_PAUSE_CAP)
+			return EFX_FC_RX;
+		if (lpa & ADVERTISE_PAUSE_CAP)
+			return EFX_FC_TX;
+	}
+	return 0;
+}
+
+/**
+ * struct efx_mac_operations - Efx MAC operations table
+ * @reconfigure: Reconfigure MAC. Serialised by the mac_lock
+ * @update_stats: Update statistics
+ * @irq: Hardware MAC event callback. Serialised by the mac_lock
+ * @poll: Poll for hardware state. Serialised by the mac_lock
+ */
+struct efx_mac_operations {
+	void (*reconfigure) (struct efx_nic *efx);
+	void (*update_stats) (struct efx_nic *efx);
+	void (*irq) (struct efx_nic *efx);
+	void (*poll) (struct efx_nic *efx);
+};
+
 /**
  * struct efx_phy_operations - Efx PHY operations table
  * @init: Initialise PHY
@@ -506,17 +563,33 @@ enum efx_fc_type {
  * @reconfigure: Reconfigure PHY (e.g. for new link parameters)
  * @clear_interrupt: Clear down interrupt
  * @blink: Blink LEDs
- * @check_hw: Check hardware
+ * @poll: Poll for hardware state. Serialised by the mac_lock.
+ * @get_settings: Get ethtool settings. Serialised by the mac_lock.
+ * @set_settings: Set ethtool settings. Serialised by the mac_lock.
+ * @set_xnp_advertise: Set abilities advertised in Extended Next Page
+ *	(only needed where AN bit is set in mmds)
+ * @num_tests: Number of PHY-specific tests/results
+ * @test_names: Names of the tests/results
+ * @run_tests: Run tests and record results as appropriate.
+ *	Flags are the ethtool tests flags.
  * @mmds: MMD presence mask
  * @loopbacks: Supported loopback modes mask
  */
 struct efx_phy_operations {
+	enum efx_mac_type macs;
 	int (*init) (struct efx_nic *efx);
 	void (*fini) (struct efx_nic *efx);
 	void (*reconfigure) (struct efx_nic *efx);
 	void (*clear_interrupt) (struct efx_nic *efx);
-	int (*check_hw) (struct efx_nic *efx);
-	int (*test) (struct efx_nic *efx);
+	void (*poll) (struct efx_nic *efx);
+	void (*get_settings) (struct efx_nic *efx,
+			      struct ethtool_cmd *ecmd);
+	int (*set_settings) (struct efx_nic *efx,
+			     struct ethtool_cmd *ecmd);
+	bool (*set_xnp_advertise) (struct efx_nic *efx, u32);
+	u32 num_tests;
+	const char *const *test_names;
+	int (*run_tests) (struct efx_nic *efx, int *results, unsigned flags);
 	int mmds;
 	unsigned loopbacks;
 };
@@ -525,11 +598,15 @@ struct efx_phy_operations {
  * @enum efx_phy_mode - PHY operating mode flags
  * @PHY_MODE_NORMAL: on and should pass traffic
  * @PHY_MODE_TX_DISABLED: on with TX disabled
+ * @PHY_MODE_LOW_POWER: set to low power through MDIO
+ * @PHY_MODE_OFF: switched off through external control
  * @PHY_MODE_SPECIAL: on but will not pass traffic
  */
 enum efx_phy_mode {
 	PHY_MODE_NORMAL		= 0,
 	PHY_MODE_TX_DISABLED	= 1,
+	PHY_MODE_LOW_POWER	= 2,
+	PHY_MODE_OFF		= 4,
 	PHY_MODE_SPECIAL	= 8,
 };
 
@@ -629,7 +706,7 @@ union efx_multicast_hash {
  * @legacy_irq: IRQ number
  * @workqueue: Workqueue for port reconfigures and the HW monitor.
  *	Work items do not hold and must not acquire RTNL.
- * @reset_workqueue: Workqueue for resets.  Work item will acquire RTNL.
+ * @workqueue_name: Name of workqueue
  * @reset_work: Scheduled reset workitem
  * @monitor_work: Hardware monitor workitem
  * @membase_phys: Memory BAR value as physical address
@@ -644,6 +721,7 @@ union efx_multicast_hash {
  * @rx_queue: RX DMA queues
  * @channel: Channels
  * @n_rx_queues: Number of RX queues
+ * @n_channels: Number of channels in use
  * @rx_buffer_len: RX buffer length
  * @rx_buffer_order: Order (log2) of number of pages for each RX buffer
  * @irq_status: Interrupt status buffer
@@ -655,15 +733,16 @@ union efx_multicast_hash {
  *	This field will be %NULL if no flash device is present.
  * @spi_eeprom: SPI EEPROM device
  *	This field will be %NULL if no EEPROM device is present.
+ * @spi_lock: SPI bus lock
  * @n_rx_nodesc_drop_cnt: RX no descriptor drop count
  * @nic_data: Hardware dependant state
  * @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode,
  *	@port_inhibited, efx_monitor() and efx_reconfigure_port()
  * @port_enabled: Port enabled indicator.
- *	Serialises efx_stop_all(), efx_start_all() and efx_monitor() and
- *	efx_reconfigure_work with kernel interfaces. Safe to read under any
- *	one of the rtnl_lock, mac_lock, or netif_tx_lock, but all three must
- *	be held to modify it.
+ *	Serialises efx_stop_all(), efx_start_all(), efx_monitor(),
+ *	efx_phy_work(), and efx_mac_work() with kernel interfaces. Safe to read
+ *	under any one of the rtnl_lock, mac_lock, or netif_tx_lock, but all
+ *	three must be held to modify it.
  * @port_inhibited: If set, the netif_carrier is always off. Hold the mac_lock
  * @port_initialized: Port initialized?
  * @net_dev: Operating system network device. Consider holding the rtnl lock
@@ -677,6 +756,7 @@ union efx_multicast_hash {
  * @stats_lock: Statistics update lock. Serialises statistics fetches
  * @stats_enabled: Temporarily disable statistics fetches.
  *	Serialised by @stats_lock
+ * @mac_op: MAC interface
  * @mac_address: Permanent MAC address
  * @phy_type: PHY type
  * @phy_lock: PHY access lock
@@ -684,13 +764,17 @@ union efx_multicast_hash {
  * @phy_data: PHY private data (including PHY-specific stats)
  * @mii: PHY interface
  * @phy_mode: PHY operating mode. Serialised by @mac_lock.
+ * @mac_up: MAC link state
  * @link_up: Link status
- * @link_options: Link options (MII/GMII format)
+ * @link_fd: Link is full duplex
+ * @link_fc: Actualy flow control flags
+ * @link_speed: Link speed (Mbps)
  * @n_link_state_changes: Number of times the link has changed state
  * @promiscuous: Promiscuous flag. Protected by netif_tx_lock.
  * @multicast_hash: Multicast hash table
- * @flow_control: Flow control flags - separate RX/TX so can't use link_options
- * @reconfigure_work: work item for dealing with PHY events
+ * @wanted_fc: Wanted flow control flags
+ * @phy_work: work item for dealing with PHY events
+ * @mac_work: work item for dealing with MAC events
  * @loopback_mode: Loopback status
  * @loopback_modes: Supported loopback mode bitmask
  * @loopback_selftest: Offline self-test private state
@@ -704,7 +788,7 @@ struct efx_nic {
 	const struct efx_nic_type *type;
 	int legacy_irq;
 	struct workqueue_struct *workqueue;
-	struct workqueue_struct *reset_workqueue;
+	char workqueue_name[16];
 	struct work_struct reset_work;
 	struct delayed_work monitor_work;
 	resource_size_t membase_phys;
@@ -723,6 +807,7 @@ struct efx_nic {
 	struct efx_channel channel[EFX_MAX_CHANNELS];
 
 	int n_rx_queues;
+	int n_channels;
 	unsigned int rx_buffer_len;
 	unsigned int rx_buffer_order;
 
@@ -731,12 +816,14 @@ struct efx_nic {
 
 	struct efx_spi_device *spi_flash;
 	struct efx_spi_device *spi_eeprom;
+	struct mutex spi_lock;
 
 	unsigned n_rx_nodesc_drop_cnt;
 
 	struct falcon_nic_data *nic_data;
 
 	struct mutex mac_lock;
+	struct work_struct mac_work;
 	bool port_enabled;
 	bool port_inhibited;
 
@@ -752,23 +839,27 @@ struct efx_nic {
 	spinlock_t stats_lock;
 	bool stats_enabled;
 
+	struct efx_mac_operations *mac_op;
 	unsigned char mac_address[ETH_ALEN];
 
 	enum phy_type phy_type;
 	spinlock_t phy_lock;
+	struct work_struct phy_work;
 	struct efx_phy_operations *phy_op;
 	void *phy_data;
 	struct mii_if_info mii;
 	enum efx_phy_mode phy_mode;
 
+	bool mac_up;
 	bool link_up;
-	unsigned int link_options;
+	bool link_fd;
+	enum efx_fc_type link_fc;
+	unsigned int link_speed;
 	unsigned int n_link_state_changes;
 
 	bool promiscuous;
 	union efx_multicast_hash multicast_hash;
-	enum efx_fc_type flow_control;
-	struct work_struct reconfigure_work;
+	enum efx_fc_type wanted_fc;
 
 	atomic_t rx_reset;
 	enum efx_loopback_mode loopback_mode;
diff --git a/drivers/net/sfc/phy.h b/drivers/net/sfc/phy.h
index f746536f4ff..58c493ef81b 100644
--- a/drivers/net/sfc/phy.h
+++ b/drivers/net/sfc/phy.h
@@ -1,6 +1,6 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007 Solarflare Communications Inc.
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -11,9 +11,10 @@
 #define EFX_PHY_H
 
 /****************************************************************************
- * 10Xpress (SFX7101) PHY
+ * 10Xpress (SFX7101 and SFT9001) PHYs
  */
-extern struct efx_phy_operations falcon_tenxpress_phy_ops;
+extern struct efx_phy_operations falcon_sfx7101_phy_ops;
+extern struct efx_phy_operations falcon_sft9001_phy_ops;
 
 extern void tenxpress_phy_blink(struct efx_nic *efx, bool blink);
 extern void tenxpress_crc_err(struct efx_nic *efx);
diff --git a/drivers/net/sfc/rx.c b/drivers/net/sfc/rx.c
index 0f805da4ce5..b8ba4bbad88 100644
--- a/drivers/net/sfc/rx.c
+++ b/drivers/net/sfc/rx.c
@@ -752,7 +752,7 @@ void __efx_rx_packet(struct efx_channel *channel,
 	channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
 
 done:
-	efx->net_dev->last_rx = jiffies;
+	;
 }
 
 void efx_rx_strategy(struct efx_channel *channel)
diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c
index 362956e3fe1..dba0d64d50c 100644
--- a/drivers/net/sfc/selftest.c
+++ b/drivers/net/sfc/selftest.c
@@ -26,7 +26,6 @@
 #include "selftest.h"
 #include "boards.h"
 #include "workarounds.h"
-#include "mac.h"
 #include "spi.h"
 #include "falcon_io.h"
 #include "mdio_10g.h"
@@ -105,9 +104,11 @@ static int efx_test_mii(struct efx_nic *efx, struct efx_self_tests *tests)
 		goto out;
 	}
 
-	rc = mdio_clause45_check_mmds(efx, efx->phy_op->mmds, 0);
-	if (rc)
-		goto out;
+	if (EFX_IS10G(efx)) {
+		rc = mdio_clause45_check_mmds(efx, efx->phy_op->mmds, 0);
+		if (rc)
+			goto out;
+	}
 
 out:
 	mutex_unlock(&efx->mac_lock);
@@ -246,17 +247,20 @@ static int efx_test_eventq_irq(struct efx_channel *channel,
 	return 0;
 }
 
-static int efx_test_phy(struct efx_nic *efx, struct efx_self_tests *tests)
+static int efx_test_phy(struct efx_nic *efx, struct efx_self_tests *tests,
+			unsigned flags)
 {
 	int rc;
 
-	if (!efx->phy_op->test)
+	if (!efx->phy_op->run_tests)
 		return 0;
 
+	EFX_BUG_ON_PARANOID(efx->phy_op->num_tests == 0 ||
+			    efx->phy_op->num_tests > EFX_MAX_PHY_TESTS);
+
 	mutex_lock(&efx->mac_lock);
-	rc = efx->phy_op->test(efx);
+	rc = efx->phy_op->run_tests(efx, tests->phy, flags);
 	mutex_unlock(&efx->mac_lock);
-	tests->phy = rc ? -1 : 1;
 	return rc;
 }
 
@@ -563,8 +567,7 @@ efx_test_loopback(struct efx_tx_queue *tx_queue,
 	return 0;
 }
 
-static int efx_test_loopbacks(struct efx_nic *efx, struct ethtool_cmd ecmd,
-			      struct efx_self_tests *tests,
+static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests,
 			      unsigned int loopback_modes)
 {
 	enum efx_loopback_mode mode;
@@ -593,12 +596,14 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct ethtool_cmd ecmd,
 		efx->loopback_mode = mode;
 		efx_reconfigure_port(efx);
 
-		/* Wait for the PHY to signal the link is up */
+		/* Wait for the PHY to signal the link is up. Interrupts
+		 * are enabled for PHY's using LASI, otherwise we poll()
+		 * quickly */
 		count = 0;
 		do {
 			struct efx_channel *channel = &efx->channel[0];
 
-			falcon_check_xmac(efx);
+			efx->phy_op->poll(efx);
 			schedule_timeout_uninterruptible(HZ / 10);
 			if (channel->work_pending)
 				efx_process_channel_now(channel);
@@ -606,13 +611,12 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct ethtool_cmd ecmd,
 			flush_workqueue(efx->workqueue);
 			rmb();
 
-			/* efx->link_up can be 1 even if the XAUI link is down,
-			 * (bug5762). Usually, it's not worth bothering with the
-			 * difference, but for selftests, we need that extra
-			 * guarantee that the link is really, really, up.
-			 */
+			/* We need both the phy and xaui links to be ok.
+			 * rather than relying on the falcon_xmac irq/poll
+			 * regime, just poll xaui directly */
 			link_up = efx->link_up;
-			if (!falcon_xaui_link_ok(efx))
+			if (link_up && EFX_IS10G(efx) &&
+			    !falcon_xaui_link_ok(efx))
 				link_up = false;
 
 		} while ((++count < 20) && !link_up);
@@ -652,47 +656,48 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct ethtool_cmd ecmd,
 
 /**************************************************************************
  *
- * Entry points
+ * Entry point
  *
  *************************************************************************/
 
-/* Online (i.e. non-disruptive) testing
- * This checks interrupt generation, event delivery and PHY presence. */
-int efx_online_test(struct efx_nic *efx, struct efx_self_tests *tests)
+int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
+		 unsigned flags)
 {
+	enum efx_loopback_mode loopback_mode = efx->loopback_mode;
+	int phy_mode = efx->phy_mode;
+	struct ethtool_cmd ecmd;
 	struct efx_channel *channel;
-	int rc, rc2 = 0;
+	int rc_test = 0, rc_reset = 0, rc;
+
+	/* Online (i.e. non-disruptive) testing
+	 * This checks interrupt generation, event delivery and PHY presence. */
 
 	rc = efx_test_mii(efx, tests);
-	if (rc && !rc2)
-		rc2 = rc;
+	if (rc && !rc_test)
+		rc_test = rc;
 
 	rc = efx_test_nvram(efx, tests);
-	if (rc && !rc2)
-		rc2 = rc;
+	if (rc && !rc_test)
+		rc_test = rc;
 
 	rc = efx_test_interrupts(efx, tests);
-	if (rc && !rc2)
-		rc2 = rc;
+	if (rc && !rc_test)
+		rc_test = rc;
 
 	efx_for_each_channel(channel, efx) {
 		rc = efx_test_eventq_irq(channel, tests);
-		if (rc && !rc2)
-			rc2 = rc;
+		if (rc && !rc_test)
+			rc_test = rc;
 	}
 
-	return rc2;
-}
+	if (rc_test)
+		return rc_test;
 
-/* Offline (i.e. disruptive) testing
- * This checks MAC and PHY loopback on the specified port. */
-int efx_offline_test(struct efx_nic *efx,
-		     struct efx_self_tests *tests, unsigned int loopback_modes)
-{
-	enum efx_loopback_mode loopback_mode = efx->loopback_mode;
-	int phy_mode = efx->phy_mode;
-	struct ethtool_cmd ecmd, ecmd_test;
-	int rc, rc2 = 0;
+	if (!(flags & ETH_TEST_FL_OFFLINE))
+		return efx_test_phy(efx, tests, flags);
+
+	/* Offline (i.e. disruptive) testing
+	 * This checks MAC and PHY loopback on the specified port. */
 
 	/* force the carrier state off so the kernel doesn't transmit during
 	 * the loopback test, and the watchdog timeout doesn't fire. Also put
@@ -700,8 +705,15 @@ int efx_offline_test(struct efx_nic *efx,
 	 */
 	mutex_lock(&efx->mac_lock);
 	efx->port_inhibited = true;
-	if (efx->loopback_modes)
-		efx->loopback_mode = __ffs(efx->loopback_modes);
+	if (efx->loopback_modes) {
+		/* We need the 312 clock from the PHY to test the XMAC
+		 * registers, so move into XGMII loopback if available */
+		if (efx->loopback_modes & (1 << LOOPBACK_XGMII))
+			efx->loopback_mode = LOOPBACK_XGMII;
+		else
+			efx->loopback_mode = __ffs(efx->loopback_modes);
+	}
+
 	__efx_reconfigure_port(efx);
 	mutex_unlock(&efx->mac_lock);
 
@@ -709,39 +721,34 @@ int efx_offline_test(struct efx_nic *efx,
 	efx_reset_down(efx, &ecmd);
 
 	rc = efx_test_chip(efx, tests);
-	if (rc && !rc2)
-		rc2 = rc;
+	if (rc && !rc_test)
+		rc_test = rc;
 
 	/* reset the chip to recover from the register test */
-	rc = falcon_reset_hw(efx, RESET_TYPE_ALL);
-
-	/* Modify the saved ecmd so that when efx_reset_up() restores the phy
-	 * state, AN is disabled, and the phy is powered, and out of loopback */
-	memcpy(&ecmd_test, &ecmd, sizeof(ecmd_test));
-	if (ecmd_test.autoneg == AUTONEG_ENABLE) {
-		ecmd_test.autoneg = AUTONEG_DISABLE;
-		ecmd_test.duplex = DUPLEX_FULL;
-		ecmd_test.speed = SPEED_10000;
-	}
+	rc_reset = falcon_reset_hw(efx, RESET_TYPE_ALL);
+
+	/* Ensure that the phy is powered and out of loopback
+	 * for the bist and loopback tests */
+	efx->phy_mode &= ~PHY_MODE_LOW_POWER;
 	efx->loopback_mode = LOOPBACK_NONE;
 
-	rc = efx_reset_up(efx, &ecmd_test, rc == 0);
-	if (rc) {
+	rc = efx_reset_up(efx, &ecmd, rc_reset == 0);
+	if (rc && !rc_reset)
+		rc_reset = rc;
+
+	if (rc_reset) {
 		EFX_ERR(efx, "Unable to recover from chip test\n");
 		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
-		return rc;
+		return rc_reset;
 	}
 
-	tests->loopback_speed = ecmd_test.speed;
-	tests->loopback_full_duplex = ecmd_test.duplex;
-
-	rc = efx_test_phy(efx, tests);
-	if (rc && !rc2)
-		rc2 = rc;
+	rc = efx_test_phy(efx, tests, flags);
+	if (rc && !rc_test)
+		rc_test = rc;
 
-	rc = efx_test_loopbacks(efx, ecmd_test, tests, loopback_modes);
-	if (rc && !rc2)
-		rc2 = rc;
+	rc = efx_test_loopbacks(efx, tests, efx->loopback_modes);
+	if (rc && !rc_test)
+		rc_test = rc;
 
 	/* restore the PHY to the previous state */
 	efx->loopback_mode = loopback_mode;
@@ -749,6 +756,6 @@ int efx_offline_test(struct efx_nic *efx,
 	efx->port_inhibited = false;
 	efx_ethtool_set_settings(efx->net_dev, &ecmd);
 
-	return rc2;
+	return rc_test;
 }
 
diff --git a/drivers/net/sfc/selftest.h b/drivers/net/sfc/selftest.h
index fc15df15d76..39451cf938c 100644
--- a/drivers/net/sfc/selftest.h
+++ b/drivers/net/sfc/selftest.h
@@ -24,6 +24,8 @@ struct efx_loopback_self_tests {
 	int rx_bad;
 };
 
+#define EFX_MAX_PHY_TESTS 20
+
 /* Efx self test results
  * For fields which are not counters, 1 indicates success and -1
  * indicates failure.
@@ -38,18 +40,14 @@ struct efx_self_tests {
 	int eventq_poll[EFX_MAX_CHANNELS];
 	/* offline tests */
 	int registers;
-	int phy;
-	int loopback_speed;
-	int loopback_full_duplex;
+	int phy[EFX_MAX_PHY_TESTS];
 	struct efx_loopback_self_tests loopback[LOOPBACK_TEST_MAX + 1];
 };
 
 extern void efx_loopback_rx_packet(struct efx_nic *efx,
 				   const char *buf_ptr, int pkt_len);
-extern int efx_online_test(struct efx_nic *efx,
-			   struct efx_self_tests *tests);
-extern int efx_offline_test(struct efx_nic *efx,
-			    struct efx_self_tests *tests,
-			    unsigned int loopback_modes);
+extern int efx_selftest(struct efx_nic *efx,
+			struct efx_self_tests *tests,
+			unsigned flags);
 
 #endif /* EFX_SELFTEST_H */
diff --git a/drivers/net/sfc/sfe4001.c b/drivers/net/sfc/sfe4001.c
index fe4e3fd2233..16b80acb999 100644
--- a/drivers/net/sfc/sfe4001.c
+++ b/drivers/net/sfc/sfe4001.c
@@ -1,6 +1,6 @@
 /****************************************************************************
  * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007 Solarflare Communications Inc.
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -8,10 +8,21 @@
  */
 
 /*****************************************************************************
- * Support for the SFE4001 NIC: driver code for the PCA9539 I/O expander that
- * controls the PHY power rails, and for the MAX6647 temp. sensor used to check
- * the PHY
+ * Support for the SFE4001 and SFN4111T NICs.
+ *
+ * The SFE4001 does not power-up fully at reset due to its high power
+ * consumption.  We control its power via a PCA9539 I/O expander.
+ * Both boards have a MAX6647 temperature monitor which we expose to
+ * the lm90 driver.
+ *
+ * This also provides minimal support for reflashing the PHY, which is
+ * initiated by resetting it with the FLASH_CFG_1 pin pulled down.
+ * On SFE4001 rev A2 and later this is connected to the 3V3X output of
+ * the IO-expander; on the SFN4111T it is connected to Falcon's GPIO3.
+ * We represent reflash mode as PHY_MODE_SPECIAL and make it mutually
+ * exclusive with the network device being open.
  */
+
 #include <linux/delay.h>
 #include "net_driver.h"
 #include "efx.h"
@@ -21,6 +32,7 @@
 #include "falcon_hwdefs.h"
 #include "falcon_io.h"
 #include "mac.h"
+#include "workarounds.h"
 
 /**************************************************************************
  *
@@ -65,48 +77,9 @@
 #define	P1_SPARE_LBN 4
 #define	P1_SPARE_WIDTH 4
 
-
-/**************************************************************************
- *
- * Temperature Sensor
- *
- **************************************************************************/
-#define	MAX6647	0x4e
-
-#define	RLTS	0x00
-#define	RLTE	0x01
-#define	RSL	0x02
-#define	RCL	0x03
-#define	RCRA	0x04
-#define	RLHN	0x05
-#define	RLLI	0x06
-#define	RRHI	0x07
-#define	RRLS	0x08
-#define	WCRW	0x0a
-#define	WLHO	0x0b
-#define	WRHA	0x0c
-#define	WRLN	0x0e
-#define	OSHT	0x0f
-#define	REET	0x10
-#define	RIET	0x11
-#define	RWOE	0x19
-#define	RWOI	0x20
-#define	HYS	0x21
-#define	QUEUE	0x22
-#define	MFID	0xfe
-#define	REVID	0xff
-
-/* Status bits */
-#define MAX6647_BUSY	(1 << 7)	/* ADC is converting */
-#define MAX6647_LHIGH	(1 << 6)	/* Local high temp. alarm */
-#define MAX6647_LLOW	(1 << 5)	/* Local low temp. alarm */
-#define MAX6647_RHIGH	(1 << 4)	/* Remote high temp. alarm */
-#define MAX6647_RLOW	(1 << 3)	/* Remote low temp. alarm */
-#define MAX6647_FAULT	(1 << 2)	/* DXN/DXP short/open circuit */
-#define MAX6647_EOT	(1 << 1)	/* Remote junction overtemp. */
-#define MAX6647_IOT	(1 << 0)	/* Local junction overtemp. */
-
-static const u8 xgphy_max_temperature = 90;
+/* Temperature Sensor */
+#define MAX664X_REG_RSL		0x02
+#define MAX664X_REG_WLHO	0x0B
 
 static void sfe4001_poweroff(struct efx_nic *efx)
 {
@@ -119,7 +92,7 @@ static void sfe4001_poweroff(struct efx_nic *efx)
 	i2c_smbus_write_byte_data(ioexp_client, P0_CONFIG, 0xff);
 
 	/* Clear any over-temperature alert */
-	i2c_smbus_read_byte_data(hwmon_client, RSL);
+	i2c_smbus_read_byte_data(hwmon_client, MAX664X_REG_RSL);
 }
 
 static int sfe4001_poweron(struct efx_nic *efx)
@@ -131,7 +104,7 @@ static int sfe4001_poweron(struct efx_nic *efx)
 	u8 out;
 
 	/* Clear any previous over-temperature alert */
-	rc = i2c_smbus_read_byte_data(hwmon_client, RSL);
+	rc = i2c_smbus_read_byte_data(hwmon_client, MAX664X_REG_RSL);
 	if (rc < 0)
 		return rc;
 
@@ -209,10 +182,29 @@ fail_on:
 	return rc;
 }
 
-/* On SFE4001 rev A2 and later, we can control the FLASH_CFG_1 pin
- * using the 3V3X output of the IO-expander.  Allow the user to set
- * this when the device is stopped, and keep it stopped then.
- */
+static int sfn4111t_reset(struct efx_nic *efx)
+{
+	efx_oword_t reg;
+
+	/* GPIO pins are also used for I2C, so block that temporarily */
+	mutex_lock(&efx->i2c_adap.bus_lock);
+
+	falcon_read(efx, &reg, GPIO_CTL_REG_KER);
+	EFX_SET_OWORD_FIELD(reg, GPIO2_OEN, true);
+	EFX_SET_OWORD_FIELD(reg, GPIO2_OUT, false);
+	falcon_write(efx, &reg, GPIO_CTL_REG_KER);
+	msleep(1000);
+	EFX_SET_OWORD_FIELD(reg, GPIO2_OUT, true);
+	EFX_SET_OWORD_FIELD(reg, GPIO3_OEN, true);
+	EFX_SET_OWORD_FIELD(reg, GPIO3_OUT,
+			    !(efx->phy_mode & PHY_MODE_SPECIAL));
+	falcon_write(efx, &reg, GPIO_CTL_REG_KER);
+
+	mutex_unlock(&efx->i2c_adap.bus_lock);
+
+	ssleep(1);
+	return 0;
+}
 
 static ssize_t show_phy_flash_cfg(struct device *dev,
 				  struct device_attribute *attr, char *buf)
@@ -241,7 +233,10 @@ static ssize_t set_phy_flash_cfg(struct device *dev,
 		err = -EBUSY;
 	} else {
 		efx->phy_mode = new_mode;
-		err = sfe4001_poweron(efx);
+		if (efx->board_info.type == EFX_BOARD_SFE4001)
+			err = sfe4001_poweron(efx);
+		else
+			err = sfn4111t_reset(efx);
 		efx_reconfigure_port(efx);
 	}
 	rtnl_unlock();
@@ -261,35 +256,62 @@ static void sfe4001_fini(struct efx_nic *efx)
 	i2c_unregister_device(efx->board_info.hwmon_client);
 }
 
+static int sfe4001_check_hw(struct efx_nic *efx)
+{
+	s32 status;
+
+	/* If XAUI link is up then do not monitor */
+	if (EFX_WORKAROUND_7884(efx) && efx->mac_up)
+		return 0;
+
+	/* Check the powered status of the PHY. Lack of power implies that
+	 * the MAX6647 has shut down power to it, probably due to a temp.
+	 * alarm. Reading the power status rather than the MAX6647 status
+	 * directly because the later is read-to-clear and would thus
+	 * start to power up the PHY again when polled, causing us to blip
+	 * the power undesirably.
+	 * We know we can read from the IO expander because we did
+	 * it during power-on. Assume failure now is bad news. */
+	status = i2c_smbus_read_byte_data(efx->board_info.ioexp_client, P1_IN);
+	if (status >= 0 &&
+	    (status & ((1 << P1_AFE_PWD_LBN) | (1 << P1_DSP_PWD25_LBN))) != 0)
+		return 0;
+
+	/* Use board power control, not PHY power control */
+	sfe4001_poweroff(efx);
+	efx->phy_mode = PHY_MODE_OFF;
+
+	return (status < 0) ? -EIO : -ERANGE;
+}
+
+static struct i2c_board_info sfe4001_hwmon_info = {
+	I2C_BOARD_INFO("max6647", 0x4e),
+	.irq		= -1,
+};
+
 /* This board uses an I2C expander to provider power to the PHY, which needs to
  * be turned on before the PHY can be used.
  * Context: Process context, rtnl lock held
  */
 int sfe4001_init(struct efx_nic *efx)
 {
-	struct i2c_client *hwmon_client;
 	int rc;
 
-	hwmon_client = i2c_new_dummy(&efx->i2c_adap, MAX6647);
-	if (!hwmon_client)
+#if defined(CONFIG_SENSORS_LM90) || defined(CONFIG_SENSORS_LM90_MODULE)
+	efx->board_info.hwmon_client =
+		i2c_new_device(&efx->i2c_adap, &sfe4001_hwmon_info);
+#else
+	efx->board_info.hwmon_client =
+		i2c_new_dummy(&efx->i2c_adap, sfe4001_hwmon_info.addr);
+#endif
+	if (!efx->board_info.hwmon_client)
 		return -EIO;
-	efx->board_info.hwmon_client = hwmon_client;
 
-	/* Set DSP over-temperature alert threshold */
-	EFX_INFO(efx, "DSP cut-out at %dC\n", xgphy_max_temperature);
-	rc = i2c_smbus_write_byte_data(hwmon_client, WLHO,
-				       xgphy_max_temperature);
+	/* Raise board/PHY high limit from 85 to 90 degrees Celsius */
+	rc = i2c_smbus_write_byte_data(efx->board_info.hwmon_client,
+				       MAX664X_REG_WLHO, 90);
 	if (rc)
-		goto fail_ioexp;
-
-	/* Read it back and verify */
-	rc = i2c_smbus_read_byte_data(hwmon_client, RLHN);
-	if (rc < 0)
-		goto fail_ioexp;
-	if (rc != xgphy_max_temperature) {
-		rc = -EFAULT;
-		goto fail_ioexp;
-	}
+		goto fail_hwmon;
 
 	efx->board_info.ioexp_client = i2c_new_dummy(&efx->i2c_adap, PCA9539);
 	if (!efx->board_info.ioexp_client) {
@@ -301,6 +323,7 @@ int sfe4001_init(struct efx_nic *efx)
 	 * blink code. */
 	efx->board_info.blink = tenxpress_phy_blink;
 
+	efx->board_info.monitor = sfe4001_check_hw;
 	efx->board_info.fini = sfe4001_fini;
 
 	rc = sfe4001_poweron(efx);
@@ -319,6 +342,64 @@ fail_on:
 fail_ioexp:
 	i2c_unregister_device(efx->board_info.ioexp_client);
 fail_hwmon:
-	i2c_unregister_device(hwmon_client);
+	i2c_unregister_device(efx->board_info.hwmon_client);
+	return rc;
+}
+
+static int sfn4111t_check_hw(struct efx_nic *efx)
+{
+	s32 status;
+
+	/* If XAUI link is up then do not monitor */
+	if (EFX_WORKAROUND_7884(efx) && efx->mac_up)
+		return 0;
+
+	/* Test LHIGH, RHIGH, FAULT, EOT and IOT alarms */
+	status = i2c_smbus_read_byte_data(efx->board_info.hwmon_client,
+					  MAX664X_REG_RSL);
+	if (status < 0)
+		return -EIO;
+	if (status & 0x57)
+		return -ERANGE;
+	return 0;
+}
+
+static void sfn4111t_fini(struct efx_nic *efx)
+{
+	EFX_INFO(efx, "%s\n", __func__);
+
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_flash_cfg);
+	i2c_unregister_device(efx->board_info.hwmon_client);
+}
+
+static struct i2c_board_info sfn4111t_hwmon_info = {
+	I2C_BOARD_INFO("max6647", 0x4e),
+	.irq		= -1,
+};
+
+int sfn4111t_init(struct efx_nic *efx)
+{
+	int rc;
+
+	efx->board_info.hwmon_client =
+		i2c_new_device(&efx->i2c_adap, &sfn4111t_hwmon_info);
+	if (!efx->board_info.hwmon_client)
+		return -EIO;
+
+	efx->board_info.blink = tenxpress_phy_blink;
+	efx->board_info.monitor = sfn4111t_check_hw;
+	efx->board_info.fini = sfn4111t_fini;
+
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_flash_cfg);
+	if (rc)
+		goto fail_hwmon;
+
+	if (efx->phy_mode & PHY_MODE_SPECIAL)
+		sfn4111t_reset(efx);
+
+	return 0;
+
+fail_hwmon:
+	i2c_unregister_device(efx->board_info.hwmon_client);
 	return rc;
 }
diff --git a/drivers/net/sfc/spi.h b/drivers/net/sfc/spi.h
index feef6194237..1b1ceb41167 100644
--- a/drivers/net/sfc/spi.h
+++ b/drivers/net/sfc/spi.h
@@ -25,6 +25,7 @@
 #define SPI_WRDI 0x04		/* Reset write enable latch */
 #define SPI_RDSR 0x05		/* Read status register */
 #define SPI_WREN 0x06		/* Set write enable latch */
+#define SPI_SST_EWSR 0x50	/* SST: Enable write to status register */
 
 #define SPI_STATUS_WPEN 0x80	/* Write-protect pin enabled */
 #define SPI_STATUS_BP2 0x10	/* Block protection bit 2 */
@@ -36,6 +37,7 @@
 /**
  * struct efx_spi_device - an Efx SPI (Serial Peripheral Interface) device
  * @efx:		The Efx controller that owns this device
+ * @mtd:		MTD state
  * @device_id:		Controller's id for the device
  * @size:		Size (in bytes)
  * @addr_len:		Number of address bytes in read/write commands
@@ -44,23 +46,51 @@
  *	use bit 3 of the command byte as address bit A8, rather
  *	than having a two-byte address.  If this flag is set, then
  *	commands should be munged in this way.
+ * @erase_command:	Erase command (or 0 if sector erase not needed).
+ * @erase_size:		Erase sector size (in bytes)
+ *	Erase commands affect sectors with this size and alignment.
+ *	This must be a power of two.
  * @block_size:		Write block size (in bytes).
  *	Write commands are limited to blocks with this size and alignment.
- * @read:		Read function for the device
- * @write:		Write function for the device
  */
 struct efx_spi_device {
 	struct efx_nic *efx;
+#ifdef CONFIG_SFC_MTD
+	void *mtd;
+#endif
 	int device_id;
 	unsigned int size;
 	unsigned int addr_len;
 	unsigned int munge_address:1;
+	u8 erase_command;
+	unsigned int erase_size;
 	unsigned int block_size;
 };
 
+int falcon_spi_cmd(const struct efx_spi_device *spi, unsigned int command,
+		   int address, const void* in, void *out, size_t len);
+int falcon_spi_wait_write(const struct efx_spi_device *spi);
 int falcon_spi_read(const struct efx_spi_device *spi, loff_t start,
 		    size_t len, size_t *retlen, u8 *buffer);
 int falcon_spi_write(const struct efx_spi_device *spi, loff_t start,
 		     size_t len, size_t *retlen, const u8 *buffer);
 
+/*
+ * SFC4000 flash is partitioned into:
+ *     0-0x400       chip and board config (see falcon_hwdefs.h)
+ *     0x400-0x8000  unused (or may contain VPD if EEPROM not present)
+ *     0x8000-end    boot code (mapped to PCI expansion ROM)
+ * SFC4000 small EEPROM (size < 0x400) is used for VPD only.
+ * SFC4000 large EEPROM (size >= 0x400) is partitioned into:
+ *     0-0x400       chip and board config
+ *     configurable  VPD
+ *     0x800-0x1800  boot config
+ * Aside from the chip and board config, all of these are optional and may
+ * be absent or truncated depending on the devices used.
+ */
+#define FALCON_NVCONFIG_END 0x400U
+#define FALCON_FLASH_BOOTCODE_START 0x8000U
+#define EFX_EEPROM_BOOTCONFIG_START 0x800U
+#define EFX_EEPROM_BOOTCONFIG_END 0x1800U
+
 #endif /* EFX_SPI_H */
diff --git a/drivers/net/sfc/tenxpress.c b/drivers/net/sfc/tenxpress.c
index d507c93d666..b9768760fae 100644
--- a/drivers/net/sfc/tenxpress.c
+++ b/drivers/net/sfc/tenxpress.c
@@ -1,6 +1,6 @@
 /****************************************************************************
- * Driver for Solarflare 802.3an compliant PHY
- * Copyright 2007 Solarflare Communications Inc.
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2007-2008 Solarflare Communications Inc.
  *
  * 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
@@ -10,45 +10,76 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include "efx.h"
-#include "gmii.h"
 #include "mdio_10g.h"
 #include "falcon.h"
 #include "phy.h"
 #include "falcon_hwdefs.h"
 #include "boards.h"
-#include "mac.h"
+#include "workarounds.h"
+#include "selftest.h"
 
-/* We expect these MMDs to be in the package */
-/* AN not here as mdio_check_mmds() requires STAT2 support */
-#define TENXPRESS_REQUIRED_DEVS (MDIO_MMDREG_DEVS0_PMAPMD | \
-				 MDIO_MMDREG_DEVS0_PCS    | \
-				 MDIO_MMDREG_DEVS0_PHYXS)
-
-#define TENXPRESS_LOOPBACKS ((1 << LOOPBACK_PHYXS) |	\
-			     (1 << LOOPBACK_PCS) |	\
-			     (1 << LOOPBACK_PMAPMD) |	\
-			     (1 << LOOPBACK_NETWORK))
+/* We expect these MMDs to be in the package.  SFT9001 also has a
+ * clause 22 extension MMD, but since it doesn't have all the generic
+ * MMD registers it is pointless to include it here.
+ */
+#define TENXPRESS_REQUIRED_DEVS (MDIO_MMDREG_DEVS_PMAPMD	| \
+				 MDIO_MMDREG_DEVS_PCS		| \
+				 MDIO_MMDREG_DEVS_PHYXS		| \
+				 MDIO_MMDREG_DEVS_AN)
+
+#define SFX7101_LOOPBACKS ((1 << LOOPBACK_PHYXS) |	\
+			   (1 << LOOPBACK_PCS) |	\
+			   (1 << LOOPBACK_PMAPMD) |	\
+			   (1 << LOOPBACK_NETWORK))
+
+#define SFT9001_LOOPBACKS ((1 << LOOPBACK_GPHY) |	\
+			   (1 << LOOPBACK_PHYXS) |	\
+			   (1 << LOOPBACK_PCS) |	\
+			   (1 << LOOPBACK_PMAPMD) |	\
+			   (1 << LOOPBACK_NETWORK))
 
 /* We complain if we fail to see the link partner as 10G capable this many
  * times in a row (must be > 1 as sampling the autoneg. registers is racy)
  */
 #define MAX_BAD_LP_TRIES	(5)
 
+/* LASI Control */
+#define PMA_PMD_LASI_CTRL	36866
+#define PMA_PMD_LASI_STATUS	36869
+#define PMA_PMD_LS_ALARM_LBN	0
+#define PMA_PMD_LS_ALARM_WIDTH	1
+#define PMA_PMD_TX_ALARM_LBN	1
+#define PMA_PMD_TX_ALARM_WIDTH	1
+#define PMA_PMD_RX_ALARM_LBN	2
+#define PMA_PMD_RX_ALARM_WIDTH	1
+#define PMA_PMD_AN_ALARM_LBN	3
+#define PMA_PMD_AN_ALARM_WIDTH	1
+
 /* Extended control register */
-#define	PMA_PMD_XCONTROL_REG 0xc000
-#define	PMA_PMD_LNPGA_POWERDOWN_LBN 8
-#define	PMA_PMD_LNPGA_POWERDOWN_WIDTH 1
+#define PMA_PMD_XCONTROL_REG	49152
+#define PMA_PMD_EXT_GMII_EN_LBN	1
+#define PMA_PMD_EXT_GMII_EN_WIDTH 1
+#define PMA_PMD_EXT_CLK_OUT_LBN	2
+#define PMA_PMD_EXT_CLK_OUT_WIDTH 1
+#define PMA_PMD_LNPGA_POWERDOWN_LBN 8	/* SFX7101 only */
+#define PMA_PMD_LNPGA_POWERDOWN_WIDTH 1
+#define PMA_PMD_EXT_CLK312_LBN	8	/* SFT9001 only */
+#define PMA_PMD_EXT_CLK312_WIDTH 1
+#define PMA_PMD_EXT_LPOWER_LBN  12
+#define PMA_PMD_EXT_LPOWER_WIDTH 1
+#define PMA_PMD_EXT_SSR_LBN	15
+#define PMA_PMD_EXT_SSR_WIDTH	1
 
 /* extended status register */
-#define PMA_PMD_XSTATUS_REG 0xc001
+#define PMA_PMD_XSTATUS_REG	49153
 #define PMA_PMD_XSTAT_FLP_LBN   (12)
 
 /* LED control register */
-#define PMA_PMD_LED_CTRL_REG	(0xc007)
+#define PMA_PMD_LED_CTRL_REG	49159
 #define PMA_PMA_LED_ACTIVITY_LBN	(3)
 
 /* LED function override register */
-#define PMA_PMD_LED_OVERR_REG	(0xc009)
+#define PMA_PMD_LED_OVERR_REG	49161
 /* Bit positions for different LEDs (there are more but not wired on SFE4001)*/
 #define PMA_PMD_LED_LINK_LBN	(0)
 #define PMA_PMD_LED_SPEED_LBN	(2)
@@ -59,41 +90,99 @@
 #define	PMA_PMD_LED_ON		(1)
 #define	PMA_PMD_LED_OFF		(2)
 #define PMA_PMD_LED_FLASH	(3)
+#define PMA_PMD_LED_MASK	3
 /* All LEDs under hardware control */
 #define PMA_PMD_LED_FULL_AUTO	(0)
 /* Green and Amber under hardware control, Red off */
 #define PMA_PMD_LED_DEFAULT	(PMA_PMD_LED_OFF << PMA_PMD_LED_RX_LBN)
 
-
-/* Special Software reset register */
-#define PMA_PMD_EXT_CTRL_REG 49152
-#define PMA_PMD_EXT_SSR_LBN 15
-
-/* Misc register defines */
-#define PCS_CLOCK_CTRL_REG 0xd801
+#define PMA_PMD_SPEED_ENABLE_REG 49192
+#define PMA_PMD_100TX_ADV_LBN    1
+#define PMA_PMD_100TX_ADV_WIDTH  1
+#define PMA_PMD_1000T_ADV_LBN    2
+#define PMA_PMD_1000T_ADV_WIDTH  1
+#define PMA_PMD_10000T_ADV_LBN   3
+#define PMA_PMD_10000T_ADV_WIDTH 1
+#define PMA_PMD_SPEED_LBN        4
+#define PMA_PMD_SPEED_WIDTH      4
+
+/* Cable diagnostics - SFT9001 only */
+#define PMA_PMD_CDIAG_CTRL_REG  49213
+#define CDIAG_CTRL_IMMED_LBN    15
+#define CDIAG_CTRL_BRK_LINK_LBN 12
+#define CDIAG_CTRL_IN_PROG_LBN  11
+#define CDIAG_CTRL_LEN_UNIT_LBN 10
+#define CDIAG_CTRL_LEN_METRES   1
+#define PMA_PMD_CDIAG_RES_REG   49174
+#define CDIAG_RES_A_LBN         12
+#define CDIAG_RES_B_LBN         8
+#define CDIAG_RES_C_LBN         4
+#define CDIAG_RES_D_LBN         0
+#define CDIAG_RES_WIDTH         4
+#define CDIAG_RES_OPEN          2
+#define CDIAG_RES_OK            1
+#define CDIAG_RES_INVALID       0
+/* Set of 4 registers for pairs A-D */
+#define PMA_PMD_CDIAG_LEN_REG   49175
+
+/* Serdes control registers - SFT9001 only */
+#define PMA_PMD_CSERDES_CTRL_REG 64258
+/* Set the 156.25 MHz output to 312.5 MHz to drive Falcon's XMAC */
+#define PMA_PMD_CSERDES_DEFAULT	0x000f
+
+/* Misc register defines - SFX7101 only */
+#define PCS_CLOCK_CTRL_REG	55297
 #define PLL312_RST_N_LBN 2
 
-#define PCS_SOFT_RST2_REG 0xd806
+#define PCS_SOFT_RST2_REG	55302
 #define SERDES_RST_N_LBN 13
 #define XGXS_RST_N_LBN 12
 
-#define	PCS_TEST_SELECT_REG 0xd807	/* PRM 10.5.8 */
+#define	PCS_TEST_SELECT_REG	55303	/* PRM 10.5.8 */
 #define	CLK312_EN_LBN 3
 
 /* PHYXS registers */
+#define PHYXS_XCONTROL_REG	49152
+#define PHYXS_RESET_LBN		15
+#define PHYXS_RESET_WIDTH	1
+
 #define PHYXS_TEST1         (49162)
 #define LOOPBACK_NEAR_LBN   (8)
 #define LOOPBACK_NEAR_WIDTH (1)
 
+#define PCS_10GBASET_STAT1       32
+#define PCS_10GBASET_BLKLK_LBN   0
+#define PCS_10GBASET_BLKLK_WIDTH 1
+
 /* Boot status register */
-#define PCS_BOOT_STATUS_REG	(0xd000)
+#define PCS_BOOT_STATUS_REG	53248
 #define PCS_BOOT_FATAL_ERR_LBN	(0)
 #define PCS_BOOT_PROGRESS_LBN	(1)
 #define PCS_BOOT_PROGRESS_WIDTH	(2)
 #define PCS_BOOT_COMPLETE_LBN	(3)
+
 #define PCS_BOOT_MAX_DELAY	(100)
 #define PCS_BOOT_POLL_DELAY	(10)
 
+/* 100M/1G PHY registers */
+#define GPHY_XCONTROL_REG	49152
+#define GPHY_ISOLATE_LBN	10
+#define GPHY_ISOLATE_WIDTH	1
+#define GPHY_DUPLEX_LBN	  	8
+#define GPHY_DUPLEX_WIDTH	1
+#define GPHY_LOOPBACK_NEAR_LBN	14
+#define GPHY_LOOPBACK_NEAR_WIDTH 1
+
+#define C22EXT_STATUS_REG       49153
+#define C22EXT_STATUS_LINK_LBN  2
+#define C22EXT_STATUS_LINK_WIDTH 1
+
+#define C22EXT_MSTSLV_REG       49162
+#define C22EXT_MSTSLV_1000_HD_LBN 10
+#define C22EXT_MSTSLV_1000_HD_WIDTH 1
+#define C22EXT_MSTSLV_1000_FD_LBN 11
+#define C22EXT_MSTSLV_1000_FD_WIDTH 1
+
 /* Time to wait between powering down the LNPGA and turning off the power
  * rails */
 #define LNPGA_PDOWN_WAIT	(HZ / 5)
@@ -117,6 +206,38 @@ void tenxpress_crc_err(struct efx_nic *efx)
 		atomic_inc(&phy_data->bad_crc_count);
 }
 
+static ssize_t show_phy_short_reach(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	int reg;
+
+	reg = mdio_clause45_read(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
+				 MDIO_PMAPMD_10GBT_TXPWR);
+	return sprintf(buf, "%d\n",
+		       !!(reg & (1 << MDIO_PMAPMD_10GBT_TXPWR_SHORT_LBN)));
+}
+
+static ssize_t set_phy_short_reach(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+
+	rtnl_lock();
+	mdio_clause45_set_flag(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
+			       MDIO_PMAPMD_10GBT_TXPWR,
+			       MDIO_PMAPMD_10GBT_TXPWR_SHORT_LBN,
+			       count != 0 && *buf != '0');
+	efx_reconfigure_port(efx);
+	rtnl_unlock();
+
+	return count;
+}
+
+static DEVICE_ATTR(phy_short_reach, 0644, show_phy_short_reach,
+		   set_phy_short_reach);
+
 /* Check that the C166 has booted successfully */
 static int tenxpress_phy_check(struct efx_nic *efx)
 {
@@ -148,27 +269,42 @@ static int tenxpress_phy_check(struct efx_nic *efx)
 
 static int tenxpress_init(struct efx_nic *efx)
 {
-	int rc, reg;
+	int phy_id = efx->mii.phy_id;
+	int reg;
+	int rc;
 
-	/* Turn on the clock  */
-	reg = (1 << CLK312_EN_LBN);
-	mdio_clause45_write(efx, efx->mii.phy_id,
-			    MDIO_MMD_PCS, PCS_TEST_SELECT_REG, reg);
+	if (efx->phy_type == PHY_TYPE_SFX7101) {
+		/* Enable 312.5 MHz clock */
+		mdio_clause45_write(efx, phy_id,
+				    MDIO_MMD_PCS, PCS_TEST_SELECT_REG,
+				    1 << CLK312_EN_LBN);
+	} else {
+		/* Enable 312.5 MHz clock and GMII */
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+					 PMA_PMD_XCONTROL_REG);
+		reg |= ((1 << PMA_PMD_EXT_GMII_EN_LBN) |
+			(1 << PMA_PMD_EXT_CLK_OUT_LBN) |
+			(1 << PMA_PMD_EXT_CLK312_LBN));
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
+				    PMA_PMD_XCONTROL_REG, reg);
+		mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_C22EXT,
+				       GPHY_XCONTROL_REG, GPHY_ISOLATE_LBN,
+				       false);
+	}
 
 	rc = tenxpress_phy_check(efx);
 	if (rc < 0)
 		return rc;
 
 	/* Set the LEDs up as: Green = Link, Amber = Link/Act, Red = Off */
-	reg = mdio_clause45_read(efx, efx->mii.phy_id,
-				 MDIO_MMD_PMAPMD, PMA_PMD_LED_CTRL_REG);
-	reg |= (1 << PMA_PMA_LED_ACTIVITY_LBN);
-	mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
-			    PMA_PMD_LED_CTRL_REG, reg);
-
-	reg = PMA_PMD_LED_DEFAULT;
-	mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
-			    PMA_PMD_LED_OVERR_REG, reg);
+	if (efx->phy_type == PHY_TYPE_SFX7101) {
+		mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_PMAPMD,
+				       PMA_PMD_LED_CTRL_REG,
+				       PMA_PMA_LED_ACTIVITY_LBN,
+				       true);
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
+				    PMA_PMD_LED_OVERR_REG, PMA_PMD_LED_DEFAULT);
+	}
 
 	return rc;
 }
@@ -184,22 +320,43 @@ static int tenxpress_phy_init(struct efx_nic *efx)
 	efx->phy_data = phy_data;
 	phy_data->phy_mode = efx->phy_mode;
 
-	rc = mdio_clause45_wait_reset_mmds(efx,
-					   TENXPRESS_REQUIRED_DEVS);
-	if (rc < 0)
-		goto fail;
+	if (!(efx->phy_mode & PHY_MODE_SPECIAL)) {
+		if (efx->phy_type == PHY_TYPE_SFT9001A) {
+			int reg;
+			reg = mdio_clause45_read(efx, efx->mii.phy_id,
+						 MDIO_MMD_PMAPMD,
+						 PMA_PMD_XCONTROL_REG);
+			reg |= (1 << PMA_PMD_EXT_SSR_LBN);
+			mdio_clause45_write(efx, efx->mii.phy_id,
+					    MDIO_MMD_PMAPMD,
+					    PMA_PMD_XCONTROL_REG, reg);
+			mdelay(200);
+		}
 
-	rc = mdio_clause45_check_mmds(efx, TENXPRESS_REQUIRED_DEVS, 0);
-	if (rc < 0)
-		goto fail;
+		rc = mdio_clause45_wait_reset_mmds(efx,
+						   TENXPRESS_REQUIRED_DEVS);
+		if (rc < 0)
+			goto fail;
+
+		rc = mdio_clause45_check_mmds(efx, TENXPRESS_REQUIRED_DEVS, 0);
+		if (rc < 0)
+			goto fail;
+	}
 
 	rc = tenxpress_init(efx);
 	if (rc < 0)
 		goto fail;
 
+	if (efx->phy_type == PHY_TYPE_SFT9001B) {
+		rc = device_create_file(&efx->pci_dev->dev,
+					&dev_attr_phy_short_reach);
+		if (rc)
+			goto fail;
+	}
+
 	schedule_timeout_uninterruptible(HZ / 5); /* 200ms */
 
-	/* Let XGXS and SerDes out of reset and resets 10XPress */
+	/* Let XGXS and SerDes out of reset */
 	falcon_reset_xaui(efx);
 
 	return 0;
@@ -210,21 +367,24 @@ static int tenxpress_phy_init(struct efx_nic *efx)
 	return rc;
 }
 
+/* Perform a "special software reset" on the PHY. The caller is
+ * responsible for saving and restoring the PHY hardware registers
+ * properly, and masking/unmasking LASI */
 static int tenxpress_special_reset(struct efx_nic *efx)
 {
 	int rc, reg;
 
 	/* The XGMAC clock is driven from the SFC7101/SFT9001 312MHz clock, so
 	 * a special software reset can glitch the XGMAC sufficiently for stats
-	 * requests to fail. Since we don't ofen special_reset, just lock. */
+	 * requests to fail. Since we don't often special_reset, just lock. */
 	spin_lock(&efx->stats_lock);
 
 	/* Initiate reset */
 	reg = mdio_clause45_read(efx, efx->mii.phy_id,
-				 MDIO_MMD_PMAPMD, PMA_PMD_EXT_CTRL_REG);
+				 MDIO_MMD_PMAPMD, PMA_PMD_XCONTROL_REG);
 	reg |= (1 << PMA_PMD_EXT_SSR_LBN);
 	mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
-			    PMA_PMD_EXT_CTRL_REG, reg);
+			    PMA_PMD_XCONTROL_REG, reg);
 
 	mdelay(200);
 
@@ -239,174 +399,257 @@ static int tenxpress_special_reset(struct efx_nic *efx)
 	if (rc < 0)
 		goto unlock;
 
+	/* Wait for the XGXS state machine to churn */
+	mdelay(10);
 unlock:
 	spin_unlock(&efx->stats_lock);
 	return rc;
 }
 
-static void tenxpress_set_bad_lp(struct efx_nic *efx, bool bad_lp)
+static void sfx7101_check_bad_lp(struct efx_nic *efx, bool link_ok)
 {
 	struct tenxpress_phy_data *pd = efx->phy_data;
+	int phy_id = efx->mii.phy_id;
+	bool bad_lp;
 	int reg;
 
+	if (link_ok) {
+		bad_lp = false;
+	} else {
+		/* Check that AN has started but not completed. */
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
+					 MDIO_AN_STATUS);
+		if (!(reg & (1 << MDIO_AN_STATUS_LP_AN_CAP_LBN)))
+			return; /* LP status is unknown */
+		bad_lp = !(reg & (1 << MDIO_AN_STATUS_AN_DONE_LBN));
+		if (bad_lp)
+			pd->bad_lp_tries++;
+	}
+
 	/* Nothing to do if all is well and was previously so. */
-	if (!(bad_lp || pd->bad_lp_tries))
+	if (!pd->bad_lp_tries)
 		return;
 
-	reg = mdio_clause45_read(efx, efx->mii.phy_id,
-				 MDIO_MMD_PMAPMD, PMA_PMD_LED_OVERR_REG);
+	/* Use the RX (red) LED as an error indicator once we've seen AN
+	 * failure several times in a row, and also log a message. */
+	if (!bad_lp || pd->bad_lp_tries == MAX_BAD_LP_TRIES) {
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+					 PMA_PMD_LED_OVERR_REG);
+		reg &= ~(PMA_PMD_LED_MASK << PMA_PMD_LED_RX_LBN);
+		if (!bad_lp) {
+			reg |= PMA_PMD_LED_OFF << PMA_PMD_LED_RX_LBN;
+		} else {
+			reg |= PMA_PMD_LED_FLASH << PMA_PMD_LED_RX_LBN;
+			EFX_ERR(efx, "appears to be plugged into a port"
+				" that is not 10GBASE-T capable. The PHY"
+				" supports 10GBASE-T ONLY, so no link can"
+				" be established\n");
+		}
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
+				    PMA_PMD_LED_OVERR_REG, reg);
+		pd->bad_lp_tries = bad_lp;
+	}
+}
 
-	if (bad_lp)
-		pd->bad_lp_tries++;
-	else
-		pd->bad_lp_tries = 0;
-
-	if (pd->bad_lp_tries == MAX_BAD_LP_TRIES) {
-		pd->bad_lp_tries = 0;	/* Restart count */
-		reg &= ~(PMA_PMD_LED_FLASH << PMA_PMD_LED_RX_LBN);
-		reg |= (PMA_PMD_LED_FLASH << PMA_PMD_LED_RX_LBN);
-		EFX_ERR(efx, "This NIC appears to be plugged into"
-			" a port that is not 10GBASE-T capable.\n"
-			" This PHY is 10GBASE-T ONLY, so no link can"
-			" be established.\n");
+static bool sfx7101_link_ok(struct efx_nic *efx)
+{
+	return mdio_clause45_links_ok(efx,
+				      MDIO_MMDREG_DEVS_PMAPMD |
+				      MDIO_MMDREG_DEVS_PCS |
+				      MDIO_MMDREG_DEVS_PHYXS);
+}
+
+static bool sft9001_link_ok(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+{
+	int phy_id = efx->mii.phy_id;
+	u32 reg;
+
+	if (efx_phy_mode_disabled(efx->phy_mode))
+		return false;
+	else if (efx->loopback_mode == LOOPBACK_GPHY)
+		return true;
+	else if (efx->loopback_mode)
+		return mdio_clause45_links_ok(efx,
+					      MDIO_MMDREG_DEVS_PMAPMD |
+					      MDIO_MMDREG_DEVS_PHYXS);
+
+	/* We must use the same definition of link state as LASI,
+	 * otherwise we can miss a link state transition
+	 */
+	if (ecmd->speed == 10000) {
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PCS,
+					 PCS_10GBASET_STAT1);
+		return reg & (1 << PCS_10GBASET_BLKLK_LBN);
 	} else {
-		reg |= (PMA_PMD_LED_OFF << PMA_PMD_LED_RX_LBN);
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_C22EXT,
+					 C22EXT_STATUS_REG);
+		return reg & (1 << C22EXT_STATUS_LINK_LBN);
 	}
-	mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
-			    PMA_PMD_LED_OVERR_REG, reg);
 }
 
-/* Check link status and return a boolean OK value. If the link is NOT
- * OK we have a quick rummage round to see if we appear to be plugged
- * into a non-10GBT port and if so warn the user that they won't get
- * link any time soon as we are 10GBT only, unless caller specified
- * not to do this check (it isn't useful in loopback) */
-static bool tenxpress_link_ok(struct efx_nic *efx, bool check_lp)
+static void tenxpress_ext_loopback(struct efx_nic *efx)
 {
-	bool ok = mdio_clause45_links_ok(efx, TENXPRESS_REQUIRED_DEVS);
-
-	if (ok) {
-		tenxpress_set_bad_lp(efx, false);
-	} else if (check_lp) {
-		/* Are we plugged into the wrong sort of link? */
-		bool bad_lp = false;
-		int phy_id = efx->mii.phy_id;
-		int an_stat = mdio_clause45_read(efx, phy_id, MDIO_MMD_AN,
-						 MDIO_AN_STATUS);
-		int xphy_stat = mdio_clause45_read(efx, phy_id,
-						   MDIO_MMD_PMAPMD,
-						   PMA_PMD_XSTATUS_REG);
-		/* Are we plugged into anything that sends FLPs? If
-		 * not we can't distinguish between not being plugged
-		 * in and being plugged into a non-AN antique. The FLP
-		 * bit has the advantage of not clearing when autoneg
-		 * restarts. */
-		if (!(xphy_stat & (1 << PMA_PMD_XSTAT_FLP_LBN))) {
-			tenxpress_set_bad_lp(efx, false);
-			return ok;
-		}
+	int phy_id = efx->mii.phy_id;
 
-		/* If it can do 10GBT it must be XNP capable */
-		bad_lp = !(an_stat & (1 << MDIO_AN_STATUS_XNP_LBN));
-		if (!bad_lp && (an_stat & (1 << MDIO_AN_STATUS_PAGE_LBN))) {
-			bad_lp = !(mdio_clause45_read(efx, phy_id,
-					MDIO_MMD_AN, MDIO_AN_10GBT_STATUS) &
-					(1 << MDIO_AN_10GBT_STATUS_LP_10G_LBN));
-		}
-		tenxpress_set_bad_lp(efx, bad_lp);
-	}
-	return ok;
+	mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_PHYXS,
+			       PHYXS_TEST1, LOOPBACK_NEAR_LBN,
+			       efx->loopback_mode == LOOPBACK_PHYXS);
+	if (efx->phy_type != PHY_TYPE_SFX7101)
+		mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_C22EXT,
+				       GPHY_XCONTROL_REG,
+				       GPHY_LOOPBACK_NEAR_LBN,
+				       efx->loopback_mode == LOOPBACK_GPHY);
 }
 
-static void tenxpress_phyxs_loopback(struct efx_nic *efx)
+static void tenxpress_low_power(struct efx_nic *efx)
 {
 	int phy_id = efx->mii.phy_id;
-	int ctrl1, ctrl2;
 
-	ctrl1 = ctrl2 = mdio_clause45_read(efx, phy_id, MDIO_MMD_PHYXS,
-					   PHYXS_TEST1);
-	if (efx->loopback_mode == LOOPBACK_PHYXS)
-		ctrl2 |= (1 << LOOPBACK_NEAR_LBN);
+	if (efx->phy_type == PHY_TYPE_SFX7101)
+		mdio_clause45_set_mmds_lpower(
+			efx, !!(efx->phy_mode & PHY_MODE_LOW_POWER),
+			TENXPRESS_REQUIRED_DEVS);
 	else
-		ctrl2 &= ~(1 << LOOPBACK_NEAR_LBN);
-	if (ctrl1 != ctrl2)
-		mdio_clause45_write(efx, phy_id, MDIO_MMD_PHYXS,
-				    PHYXS_TEST1, ctrl2);
+		mdio_clause45_set_flag(
+			efx, phy_id, MDIO_MMD_PMAPMD,
+			PMA_PMD_XCONTROL_REG, PMA_PMD_EXT_LPOWER_LBN,
+			!!(efx->phy_mode & PHY_MODE_LOW_POWER));
 }
 
 static void tenxpress_phy_reconfigure(struct efx_nic *efx)
 {
 	struct tenxpress_phy_data *phy_data = efx->phy_data;
-	bool loop_change = LOOPBACK_OUT_OF(phy_data, efx,
-					   TENXPRESS_LOOPBACKS);
+	struct ethtool_cmd ecmd;
+	bool phy_mode_change, loop_reset, loop_toggle, loopback;
 
-	if (efx->phy_mode & PHY_MODE_SPECIAL) {
+	if (efx->phy_mode & (PHY_MODE_OFF | PHY_MODE_SPECIAL)) {
 		phy_data->phy_mode = efx->phy_mode;
 		return;
 	}
 
-	/* When coming out of transmit disable, coming out of low power
-	 * mode, or moving out of any PHY internal loopback mode,
-	 * perform a special software reset */
-	if ((efx->phy_mode == PHY_MODE_NORMAL &&
-	     phy_data->phy_mode != PHY_MODE_NORMAL) ||
-	    loop_change) {
-		tenxpress_special_reset(efx);
-		falcon_reset_xaui(efx);
+	tenxpress_low_power(efx);
+
+	phy_mode_change = (efx->phy_mode == PHY_MODE_NORMAL &&
+			   phy_data->phy_mode != PHY_MODE_NORMAL);
+	loopback = LOOPBACK_MASK(efx) & efx->phy_op->loopbacks;
+	loop_toggle = LOOPBACK_CHANGED(phy_data, efx, efx->phy_op->loopbacks);
+	loop_reset = (LOOPBACK_OUT_OF(phy_data, efx, efx->phy_op->loopbacks) ||
+		      LOOPBACK_CHANGED(phy_data, efx, 1 << LOOPBACK_GPHY));
+
+	if (loop_reset || loop_toggle || loopback || phy_mode_change) {
+		int rc;
+
+		efx->phy_op->get_settings(efx, &ecmd);
+
+		if (loop_reset || phy_mode_change) {
+			tenxpress_special_reset(efx);
+
+			/* Reset XAUI if we were in 10G, and are staying
+			 * in 10G. If we're moving into and out of 10G
+			 * then xaui will be reset anyway */
+			if (EFX_IS10G(efx))
+				falcon_reset_xaui(efx);
+		}
+
+		if (efx->phy_type != PHY_TYPE_SFX7101) {
+			/* Only change autoneg once, on coming out or
+			 * going into loopback */
+			if (loop_toggle)
+				ecmd.autoneg = !loopback;
+			if (loopback) {
+				ecmd.duplex = DUPLEX_FULL;
+				if (efx->loopback_mode == LOOPBACK_GPHY)
+					ecmd.speed = SPEED_1000;
+				else
+					ecmd.speed = SPEED_10000;
+			}
+		}
+
+		rc = efx->phy_op->set_settings(efx, &ecmd);
+		WARN_ON(rc);
 	}
 
 	mdio_clause45_transmit_disable(efx);
 	mdio_clause45_phy_reconfigure(efx);
-	tenxpress_phyxs_loopback(efx);
+	tenxpress_ext_loopback(efx);
 
 	phy_data->loopback_mode = efx->loopback_mode;
 	phy_data->phy_mode = efx->phy_mode;
-	efx->link_up = tenxpress_link_ok(efx, false);
-	efx->link_options = GM_LPA_10000FULL;
-}
 
-static void tenxpress_phy_clear_interrupt(struct efx_nic *efx)
-{
-	/* Nothing done here - LASI interrupts aren't reliable so poll  */
+	if (efx->phy_type == PHY_TYPE_SFX7101) {
+		efx->link_speed = 10000;
+		efx->link_fd = true;
+		efx->link_up = sfx7101_link_ok(efx);
+	} else {
+		efx->phy_op->get_settings(efx, &ecmd);
+		efx->link_speed = ecmd.speed;
+		efx->link_fd = ecmd.duplex == DUPLEX_FULL;
+		efx->link_up = sft9001_link_ok(efx, &ecmd);
+	}
+	efx->link_fc = mdio_clause45_get_pause(efx);
 }
 
-
 /* Poll PHY for interrupt */
-static int tenxpress_phy_check_hw(struct efx_nic *efx)
+static void tenxpress_phy_poll(struct efx_nic *efx)
 {
 	struct tenxpress_phy_data *phy_data = efx->phy_data;
-	bool link_ok;
-
-	link_ok = tenxpress_link_ok(efx, true);
+	bool change = false, link_ok;
+	unsigned link_fc;
+
+	if (efx->phy_type == PHY_TYPE_SFX7101) {
+		link_ok = sfx7101_link_ok(efx);
+		if (link_ok != efx->link_up) {
+			change = true;
+		} else {
+			link_fc = mdio_clause45_get_pause(efx);
+			if (link_fc != efx->link_fc)
+				change = true;
+		}
+		sfx7101_check_bad_lp(efx, link_ok);
+	} else if (efx->loopback_mode) {
+		bool link_ok = sft9001_link_ok(efx, NULL);
+		if (link_ok != efx->link_up)
+			change = true;
+	} else {
+		u32 status = mdio_clause45_read(efx, efx->mii.phy_id,
+						MDIO_MMD_PMAPMD,
+						PMA_PMD_LASI_STATUS);
+		if (status & (1 << PMA_PMD_LS_ALARM_LBN))
+			change = true;
+	}
 
-	if (link_ok != efx->link_up)
-		falcon_xmac_sim_phy_event(efx);
+	if (change)
+		falcon_sim_phy_event(efx);
 
 	if (phy_data->phy_mode != PHY_MODE_NORMAL)
-		return 0;
+		return;
 
-	if (atomic_read(&phy_data->bad_crc_count) > crc_error_reset_threshold) {
+	if (EFX_WORKAROUND_10750(efx) &&
+	    atomic_read(&phy_data->bad_crc_count) > crc_error_reset_threshold) {
 		EFX_ERR(efx, "Resetting XAUI due to too many CRC errors\n");
 		falcon_reset_xaui(efx);
 		atomic_set(&phy_data->bad_crc_count, 0);
 	}
-
-	return 0;
 }
 
 static void tenxpress_phy_fini(struct efx_nic *efx)
 {
 	int reg;
 
-	/* Power down the LNPGA */
-	reg = (1 << PMA_PMD_LNPGA_POWERDOWN_LBN);
-	mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
-			    PMA_PMD_XCONTROL_REG, reg);
-
-	/* Waiting here ensures that the board fini, which can turn off the
-	 * power to the PHY, won't get run until the LNPGA powerdown has been
-	 * given long enough to complete. */
-	schedule_timeout_uninterruptible(LNPGA_PDOWN_WAIT); /* 200 ms */
+	if (efx->phy_type == PHY_TYPE_SFT9001B) {
+		device_remove_file(&efx->pci_dev->dev,
+				   &dev_attr_phy_short_reach);
+	} else {
+		/* Power down the LNPGA */
+		reg = (1 << PMA_PMD_LNPGA_POWERDOWN_LBN);
+		mdio_clause45_write(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
+				    PMA_PMD_XCONTROL_REG, reg);
+
+		/* Waiting here ensures that the board fini, which can turn
+		 * off the power to the PHY, won't get run until the LNPGA
+		 * powerdown has been given long enough to complete. */
+		schedule_timeout_uninterruptible(LNPGA_PDOWN_WAIT); /* 200 ms */
+	}
 
 	kfree(efx->phy_data);
 	efx->phy_data = NULL;
@@ -430,19 +673,236 @@ void tenxpress_phy_blink(struct efx_nic *efx, bool blink)
 			    PMA_PMD_LED_OVERR_REG, reg);
 }
 
-static int tenxpress_phy_test(struct efx_nic *efx)
+static const char *const sfx7101_test_names[] = {
+	"bist"
+};
+
+static int
+sfx7101_run_tests(struct efx_nic *efx, int *results, unsigned flags)
 {
+	int rc;
+
+	if (!(flags & ETH_TEST_FL_OFFLINE))
+		return 0;
+
 	/* BIST is automatically run after a special software reset */
-	return tenxpress_special_reset(efx);
+	rc = tenxpress_special_reset(efx);
+	results[0] = rc ? -1 : 1;
+	return rc;
 }
 
-struct efx_phy_operations falcon_tenxpress_phy_ops = {
+static const char *const sft9001_test_names[] = {
+	"bist",
+	"cable.pairA.status",
+	"cable.pairB.status",
+	"cable.pairC.status",
+	"cable.pairD.status",
+	"cable.pairA.length",
+	"cable.pairB.length",
+	"cable.pairC.length",
+	"cable.pairD.length",
+};
+
+static int sft9001_run_tests(struct efx_nic *efx, int *results, unsigned flags)
+{
+	struct ethtool_cmd ecmd;
+	int phy_id = efx->mii.phy_id;
+	int rc = 0, rc2, i, res_reg;
+
+	if (!(flags & ETH_TEST_FL_OFFLINE))
+		return 0;
+
+	efx->phy_op->get_settings(efx, &ecmd);
+
+	/* Initialise cable diagnostic results to unknown failure */
+	for (i = 1; i < 9; ++i)
+		results[i] = -1;
+
+	/* Run cable diagnostics; wait up to 5 seconds for them to complete.
+	 * A cable fault is not a self-test failure, but a timeout is. */
+	mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
+			    PMA_PMD_CDIAG_CTRL_REG,
+			    (1 << CDIAG_CTRL_IMMED_LBN) |
+			    (1 << CDIAG_CTRL_BRK_LINK_LBN) |
+			    (CDIAG_CTRL_LEN_METRES << CDIAG_CTRL_LEN_UNIT_LBN));
+	i = 0;
+	while (mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+				  PMA_PMD_CDIAG_CTRL_REG) &
+	       (1 << CDIAG_CTRL_IN_PROG_LBN)) {
+		if (++i == 50) {
+			rc = -ETIMEDOUT;
+			goto reset;
+		}
+		msleep(100);
+	}
+	res_reg = mdio_clause45_read(efx, efx->mii.phy_id, MDIO_MMD_PMAPMD,
+				     PMA_PMD_CDIAG_RES_REG);
+	for (i = 0; i < 4; i++) {
+		int pair_res =
+			(res_reg >> (CDIAG_RES_A_LBN - i * CDIAG_RES_WIDTH))
+			& ((1 << CDIAG_RES_WIDTH) - 1);
+		int len_reg = mdio_clause45_read(efx, efx->mii.phy_id,
+						 MDIO_MMD_PMAPMD,
+						 PMA_PMD_CDIAG_LEN_REG + i);
+		if (pair_res == CDIAG_RES_OK)
+			results[1 + i] = 1;
+		else if (pair_res == CDIAG_RES_INVALID)
+			results[1 + i] = -1;
+		else
+			results[1 + i] = -pair_res;
+		if (pair_res != CDIAG_RES_INVALID &&
+		    pair_res != CDIAG_RES_OPEN &&
+		    len_reg != 0xffff)
+			results[5 + i] = len_reg;
+	}
+
+	/* We must reset to exit cable diagnostic mode.  The BIST will
+	 * also run when we do this. */
+reset:
+	rc2 = tenxpress_special_reset(efx);
+	results[0] = rc2 ? -1 : 1;
+	if (!rc)
+		rc = rc2;
+
+	rc2 = efx->phy_op->set_settings(efx, &ecmd);
+	if (!rc)
+		rc = rc2;
+
+	return rc;
+}
+
+static u32 tenxpress_get_xnp_lpa(struct efx_nic *efx)
+{
+	int phy = efx->mii.phy_id;
+	u32 lpa = 0;
+	int reg;
+
+	if (efx->phy_type != PHY_TYPE_SFX7101) {
+		reg = mdio_clause45_read(efx, phy, MDIO_MMD_C22EXT,
+					 C22EXT_MSTSLV_REG);
+		if (reg & (1 << C22EXT_MSTSLV_1000_HD_LBN))
+			lpa |= ADVERTISED_1000baseT_Half;
+		if (reg & (1 << C22EXT_MSTSLV_1000_FD_LBN))
+			lpa |= ADVERTISED_1000baseT_Full;
+	}
+	reg = mdio_clause45_read(efx, phy, MDIO_MMD_AN, MDIO_AN_10GBT_STATUS);
+	if (reg & (1 << MDIO_AN_10GBT_STATUS_LP_10G_LBN))
+		lpa |= ADVERTISED_10000baseT_Full;
+	return lpa;
+}
+
+static void sfx7101_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+{
+	mdio_clause45_get_settings_ext(efx, ecmd, ADVERTISED_10000baseT_Full,
+				       tenxpress_get_xnp_lpa(efx));
+	ecmd->supported |= SUPPORTED_10000baseT_Full;
+	ecmd->advertising |= ADVERTISED_10000baseT_Full;
+}
+
+static void sft9001_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+{
+	int phy_id = efx->mii.phy_id;
+	u32 xnp_adv = 0;
+	int reg;
+
+	reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_PMAPMD,
+				 PMA_PMD_SPEED_ENABLE_REG);
+	if (EFX_WORKAROUND_13204(efx) && (reg & (1 << PMA_PMD_100TX_ADV_LBN)))
+		xnp_adv |= ADVERTISED_100baseT_Full;
+	if (reg & (1 << PMA_PMD_1000T_ADV_LBN))
+		xnp_adv |= ADVERTISED_1000baseT_Full;
+	if (reg & (1 << PMA_PMD_10000T_ADV_LBN))
+		xnp_adv |= ADVERTISED_10000baseT_Full;
+
+	mdio_clause45_get_settings_ext(efx, ecmd, xnp_adv,
+				       tenxpress_get_xnp_lpa(efx));
+
+	ecmd->supported |= (SUPPORTED_100baseT_Half |
+			    SUPPORTED_100baseT_Full |
+			    SUPPORTED_1000baseT_Full);
+
+	/* Use the vendor defined C22ext register for duplex settings */
+	if (ecmd->speed != SPEED_10000 && !ecmd->autoneg) {
+		reg = mdio_clause45_read(efx, phy_id, MDIO_MMD_C22EXT,
+					 GPHY_XCONTROL_REG);
+		ecmd->duplex = (reg & (1 << GPHY_DUPLEX_LBN) ?
+				DUPLEX_FULL : DUPLEX_HALF);
+	}
+}
+
+static int sft9001_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+{
+	int phy_id = efx->mii.phy_id;
+	int rc;
+
+	rc = mdio_clause45_set_settings(efx, ecmd);
+	if (rc)
+		return rc;
+
+	if (ecmd->speed != SPEED_10000 && !ecmd->autoneg)
+		mdio_clause45_set_flag(efx, phy_id, MDIO_MMD_C22EXT,
+				       GPHY_XCONTROL_REG, GPHY_DUPLEX_LBN,
+				       ecmd->duplex == DUPLEX_FULL);
+
+	return rc;
+}
+
+static bool sft9001_set_xnp_advertise(struct efx_nic *efx, u32 advertising)
+{
+	int phy = efx->mii.phy_id;
+	int reg = mdio_clause45_read(efx, phy, MDIO_MMD_PMAPMD,
+				     PMA_PMD_SPEED_ENABLE_REG);
+	bool enabled;
+
+	reg &= ~((1 << 2) | (1 << 3));
+	if (EFX_WORKAROUND_13204(efx) &&
+	    (advertising & ADVERTISED_100baseT_Full))
+		reg |= 1 << PMA_PMD_100TX_ADV_LBN;
+	if (advertising & ADVERTISED_1000baseT_Full)
+		reg |= 1 << PMA_PMD_1000T_ADV_LBN;
+	if (advertising & ADVERTISED_10000baseT_Full)
+		reg |= 1 << PMA_PMD_10000T_ADV_LBN;
+	mdio_clause45_write(efx, phy, MDIO_MMD_PMAPMD,
+			    PMA_PMD_SPEED_ENABLE_REG, reg);
+
+	enabled = (advertising &
+		   (ADVERTISED_1000baseT_Half |
+		    ADVERTISED_1000baseT_Full |
+		    ADVERTISED_10000baseT_Full));
+	if (EFX_WORKAROUND_13204(efx))
+		enabled |= (advertising & ADVERTISED_100baseT_Full);
+	return enabled;
+}
+
+struct efx_phy_operations falcon_sfx7101_phy_ops = {
+	.macs		  = EFX_XMAC,
+	.init             = tenxpress_phy_init,
+	.reconfigure      = tenxpress_phy_reconfigure,
+	.poll             = tenxpress_phy_poll,
+	.fini             = tenxpress_phy_fini,
+	.clear_interrupt  = efx_port_dummy_op_void,
+	.get_settings	  = sfx7101_get_settings,
+	.set_settings	  = mdio_clause45_set_settings,
+	.num_tests	  = ARRAY_SIZE(sfx7101_test_names),
+	.test_names	  = sfx7101_test_names,
+	.run_tests	  = sfx7101_run_tests,
+	.mmds             = TENXPRESS_REQUIRED_DEVS,
+	.loopbacks        = SFX7101_LOOPBACKS,
+};
+
+struct efx_phy_operations falcon_sft9001_phy_ops = {
+	.macs		  = EFX_GMAC | EFX_XMAC,
 	.init             = tenxpress_phy_init,
 	.reconfigure      = tenxpress_phy_reconfigure,
-	.check_hw         = tenxpress_phy_check_hw,
+	.poll             = tenxpress_phy_poll,
 	.fini             = tenxpress_phy_fini,
-	.clear_interrupt  = tenxpress_phy_clear_interrupt,
-	.test             = tenxpress_phy_test,
+	.clear_interrupt  = efx_port_dummy_op_void,
+	.get_settings	  = sft9001_get_settings,
+	.set_settings	  = sft9001_set_settings,
+	.set_xnp_advertise = sft9001_set_xnp_advertise,
+	.num_tests	  = ARRAY_SIZE(sft9001_test_names),
+	.test_names	  = sft9001_test_names,
+	.run_tests	  = sft9001_run_tests,
 	.mmds             = TENXPRESS_REQUIRED_DEVS,
-	.loopbacks        = TENXPRESS_LOOPBACKS,
+	.loopbacks        = SFT9001_LOOPBACKS,
 };
diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h
index fa7b49d6928..82e03e1d737 100644
--- a/drivers/net/sfc/workarounds.h
+++ b/drivers/net/sfc/workarounds.h
@@ -17,15 +17,20 @@
 
 #define EFX_WORKAROUND_ALWAYS(efx) 1
 #define EFX_WORKAROUND_FALCON_A(efx) (falcon_rev(efx) <= FALCON_REV_A1)
+#define EFX_WORKAROUND_10G(efx) EFX_IS10G(efx)
+#define EFX_WORKAROUND_SFX7101(efx) ((efx)->phy_type == PHY_TYPE_SFX7101)
+#define EFX_WORKAROUND_SFT9001A(efx) ((efx)->phy_type == PHY_TYPE_SFT9001A)
 
 /* XAUI resets if link not detected */
 #define EFX_WORKAROUND_5147 EFX_WORKAROUND_ALWAYS
 /* RX PCIe double split performance issue */
 #define EFX_WORKAROUND_7575 EFX_WORKAROUND_ALWAYS
+/* Bit-bashed I2C reads cause performance drop */
+#define EFX_WORKAROUND_7884 EFX_WORKAROUND_10G
 /* TX pkt parser problem with <= 16 byte TXes */
 #define EFX_WORKAROUND_9141 EFX_WORKAROUND_ALWAYS
 /* Low rate CRC errors require XAUI reset */
-#define EFX_WORKAROUND_10750 EFX_WORKAROUND_ALWAYS
+#define EFX_WORKAROUND_10750 EFX_WORKAROUND_SFX7101
 /* TX_EV_PKT_ERR can be caused by a dangling TX descriptor
  * or a PCIe error (bug 11028) */
 #define EFX_WORKAROUND_10727 EFX_WORKAROUND_ALWAYS
@@ -49,4 +54,9 @@
 /* Leak overlength packets rather than free */
 #define EFX_WORKAROUND_8071 EFX_WORKAROUND_FALCON_A
 
+/* Need to send XNP pages for 100BaseT */
+#define EFX_WORKAROUND_13204 EFX_WORKAROUND_SFT9001A
+/* Need to keep AN enabled */
+#define EFX_WORKAROUND_13963 EFX_WORKAROUND_SFT9001A
+
 #endif /* EFX_WORKAROUNDS_H */
diff --git a/drivers/net/sfc/xfp_phy.c b/drivers/net/sfc/xfp_phy.c
index 276151df3a7..2d50b6ecf5f 100644
--- a/drivers/net/sfc/xfp_phy.c
+++ b/drivers/net/sfc/xfp_phy.c
@@ -7,22 +7,21 @@
  * by the Free Software Foundation, incorporated herein by reference.
  */
 /*
- * Driver for XFP optical PHYs (plus some support specific to the Quake 2032)
+ * Driver for XFP optical PHYs (plus some support specific to the Quake 2022/32)
  * See www.amcc.com for details (search for qt2032)
  */
 
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include "efx.h"
-#include "gmii.h"
 #include "mdio_10g.h"
 #include "xenpack.h"
 #include "phy.h"
-#include "mac.h"
+#include "falcon.h"
 
-#define XFP_REQUIRED_DEVS (MDIO_MMDREG_DEVS0_PCS |	\
-			   MDIO_MMDREG_DEVS0_PMAPMD |	\
-			   MDIO_MMDREG_DEVS0_PHYXS)
+#define XFP_REQUIRED_DEVS (MDIO_MMDREG_DEVS_PCS |	\
+			   MDIO_MMDREG_DEVS_PMAPMD |	\
+			   MDIO_MMDREG_DEVS_PHYXS)
 
 #define XFP_LOOPBACKS ((1 << LOOPBACK_PCS) |		\
 		       (1 << LOOPBACK_PMAPMD) |		\
@@ -65,7 +64,7 @@ static int xfp_reset_phy(struct efx_nic *efx)
 	/* Check that all the MMDs we expect are present and responding. We
 	 * expect faults on some if the link is down, but not on the PHY XS */
 	rc = mdio_clause45_check_mmds(efx, XFP_REQUIRED_DEVS,
-				      MDIO_MMDREG_DEVS0_PHYXS);
+				      MDIO_MMDREG_DEVS_PHYXS);
 	if (rc < 0)
 		goto fail;
 
@@ -120,15 +119,12 @@ static int xfp_link_ok(struct efx_nic *efx)
 	return mdio_clause45_links_ok(efx, XFP_REQUIRED_DEVS);
 }
 
-static int xfp_phy_check_hw(struct efx_nic *efx)
+static void xfp_phy_poll(struct efx_nic *efx)
 {
-	int rc = 0;
 	int link_up = xfp_link_ok(efx);
 	/* Simulate a PHY event if link state has changed */
 	if (link_up != efx->link_up)
-		falcon_xmac_sim_phy_event(efx);
-
-	return rc;
+		falcon_sim_phy_event(efx);
 }
 
 static void xfp_phy_reconfigure(struct efx_nic *efx)
@@ -145,7 +141,9 @@ static void xfp_phy_reconfigure(struct efx_nic *efx)
 
 	phy_data->phy_mode = efx->phy_mode;
 	efx->link_up = xfp_link_ok(efx);
-	efx->link_options = GM_LPA_10000FULL;
+	efx->link_speed = 10000;
+	efx->link_fd = true;
+	efx->link_fc = efx->wanted_fc;
 }
 
 
@@ -160,11 +158,14 @@ static void xfp_phy_fini(struct efx_nic *efx)
 }
 
 struct efx_phy_operations falcon_xfp_phy_ops = {
+	.macs		 = EFX_XMAC,
 	.init            = xfp_phy_init,
 	.reconfigure     = xfp_phy_reconfigure,
-	.check_hw        = xfp_phy_check_hw,
+	.poll            = xfp_phy_poll,
 	.fini            = xfp_phy_fini,
 	.clear_interrupt = xfp_phy_clear_interrupt,
+	.get_settings    = mdio_clause45_get_settings,
+	.set_settings	 = mdio_clause45_set_settings,
 	.mmds            = XFP_REQUIRED_DEVS,
 	.loopbacks       = XFP_LOOPBACKS,
 };