Merge branch 'upstream-davem' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6

MAINTAINERS

@@ -2104,12 +2104,10 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 
 INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/ixgb/ixgbe)
-P:	Auke Kok
-M:	auke-jan.h.kok@intel.com
-P:	Jesse Brandeburg
-M:	jesse.brandeburg@intel.com
 P:	Jeff Kirsher
 M:	jeffrey.t.kirsher@intel.com
+P:	Jesse Brandeburg
+M:	jesse.brandeburg@intel.com
 P:	Bruce Allan
 M:	bruce.w.allan@intel.com
 P:	John Ronciak

drivers/base/memory.c

@@ -53,11 +53,13 @@ int register_memory_notifier(struct notifier_block *nb)
 {
         return blocking_notifier_chain_register(&memory_chain, nb);
 }
+EXPORT_SYMBOL(register_memory_notifier);
 
 void unregister_memory_notifier(struct notifier_block *nb)
 {
         blocking_notifier_chain_unregister(&memory_chain, nb);
 }
+EXPORT_SYMBOL(unregister_memory_notifier);
 
 /*
  * register_memory - Setup a sysfs device for a memory block

drivers/net/Kconfig

@@ -2426,7 +2426,7 @@ config CHELSIO_T3
 
 config EHEA
 	tristate "eHEA Ethernet support"
-	depends on IBMEBUS && INET && SPARSEMEM
+	depends on IBMEBUS && INET && SPARSEMEM && MEMORY_HOTPLUG
 	select INET_LRO
 	---help---
 	  This driver supports the IBM pSeries eHEA ethernet adapter.

drivers/net/atlx/atl1.c

 /*
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
- * Copyright(c) 2006 Jay Cliburn <jcliburn@gmail.com>
+ * Copyright(c) 2006 - 2008 Jay Cliburn <jcliburn@gmail.com>
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
@@ -36,7 +36,6 @@
  * A very incomplete list of things that need to be dealt with:
  *
  * TODO:
- * Wake on LAN.
  * Add more ethtool functions.
  * Fix abstruse irq enable/disable condition described here:
  *	http://marc.theaimsgroup.com/?l=linux-netdev&m=116398508500553&w=2
@@ -638,21 +637,18 @@ static s32 atl1_phy_leave_power_saving(struct atl1_hw *hw)
 }
 
 /*
- *TODO: do something or get rid of this
+ * Force the PHY into power saving mode using vendor magic.
  */
 #ifdef CONFIG_PM
-static s32 atl1_phy_enter_power_saving(struct atl1_hw *hw)
+static void atl1_phy_enter_power_saving(struct atl1_hw *hw)
 {
-/*    s32 ret_val;
- *    u16 phy_data;
- */
+	atl1_write_phy_reg(hw, MII_DBG_ADDR, 0);
+	atl1_write_phy_reg(hw, MII_DBG_DATA, 0x124E);
+	atl1_write_phy_reg(hw, MII_DBG_ADDR, 2);
+	atl1_write_phy_reg(hw, MII_DBG_DATA, 0x3000);
+	atl1_write_phy_reg(hw, MII_DBG_ADDR, 3);
+	atl1_write_phy_reg(hw, MII_DBG_DATA, 0);
 
-/*
-    ret_val = atl1_write_phy_reg(hw, ...);
-    ret_val = atl1_write_phy_reg(hw, ...);
-    ....
-*/
-	return 0;
 }
 #endif
 
@@ -2784,64 +2780,93 @@ static int atl1_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct atl1_hw *hw = &adapter->hw;
 	u32 ctrl = 0;
 	u32 wufc = adapter->wol;
+	u32 val;
+	int retval;
+	u16 speed;
+	u16 duplex;
 
 	netif_device_detach(netdev);
 	if (netif_running(netdev))
 		atl1_down(adapter);
 
+	retval = pci_save_state(pdev);
+	if (retval)
+		return retval;
+
 	atl1_read_phy_reg(hw, MII_BMSR, (u16 *) & ctrl);
 	atl1_read_phy_reg(hw, MII_BMSR, (u16 *) & ctrl);
-	if (ctrl & BMSR_LSTATUS)
+	val = ctrl & BMSR_LSTATUS;
+	if (val)
 		wufc &= ~ATLX_WUFC_LNKC;
 
-	/* reduce speed to 10/100M */
-	if (wufc) {
-		atl1_phy_enter_power_saving(hw);
-		/* if resume, let driver to re- setup link */
-		hw->phy_configured = false;
-		atl1_set_mac_addr(hw);
-		atlx_set_multi(netdev);
+	if (val && wufc) {
+		val = atl1_get_speed_and_duplex(hw, &speed, &duplex);
+		if (val) {
+			if (netif_msg_ifdown(adapter))
+				dev_printk(KERN_DEBUG, &pdev->dev,
+					"error getting speed/duplex\n");
+			goto disable_wol;
+		}
 
 		ctrl = 0;
-		/* turn on magic packet wol */
-		if (wufc & ATLX_WUFC_MAG)
-			ctrl = WOL_MAGIC_EN | WOL_MAGIC_PME_EN;
 
-		/* turn on Link change WOL */
-		if (wufc & ATLX_WUFC_LNKC)
-			ctrl |= (WOL_LINK_CHG_EN | WOL_LINK_CHG_PME_EN);
+		/* enable magic packet WOL */
+		if (wufc & ATLX_WUFC_MAG)
+			ctrl |= (WOL_MAGIC_EN | WOL_MAGIC_PME_EN);
 		iowrite32(ctrl, hw->hw_addr + REG_WOL_CTRL);
-
-		/* turn on all-multi mode if wake on multicast is enabled */
-		ctrl = ioread32(hw->hw_addr + REG_MAC_CTRL);
-		ctrl &= ~MAC_CTRL_DBG;
-		ctrl &= ~MAC_CTRL_PROMIS_EN;
-		if (wufc & ATLX_WUFC_MC)
-			ctrl |= MAC_CTRL_MC_ALL_EN;
-		else
-			ctrl &= ~MAC_CTRL_MC_ALL_EN;
-
-		/* turn on broadcast mode if wake on-BC is enabled */
-		if (wufc & ATLX_WUFC_BC)
+		ioread32(hw->hw_addr + REG_WOL_CTRL);
+
+		/* configure the mac */
+		ctrl = MAC_CTRL_RX_EN;
+		ctrl |= ((u32)((speed == SPEED_1000) ? MAC_CTRL_SPEED_1000 :
+			MAC_CTRL_SPEED_10_100) << MAC_CTRL_SPEED_SHIFT);
+		if (duplex == FULL_DUPLEX)
+			ctrl |= MAC_CTRL_DUPLX;
+		ctrl |= (((u32)adapter->hw.preamble_len &
+			MAC_CTRL_PRMLEN_MASK) << MAC_CTRL_PRMLEN_SHIFT);
+		if (adapter->vlgrp)
+			ctrl |= MAC_CTRL_RMV_VLAN;
+		if (wufc & ATLX_WUFC_MAG)
 			ctrl |= MAC_CTRL_BC_EN;
-		else
-			ctrl &= ~MAC_CTRL_BC_EN;
-
-		/* enable RX */
-		ctrl |= MAC_CTRL_RX_EN;
 		iowrite32(ctrl, hw->hw_addr + REG_MAC_CTRL);
-		pci_enable_wake(pdev, PCI_D3hot, 1);
-		pci_enable_wake(pdev, PCI_D3cold, 1);
-	} else {
-		iowrite32(0, hw->hw_addr + REG_WOL_CTRL);
-		pci_enable_wake(pdev, PCI_D3hot, 0);
-		pci_enable_wake(pdev, PCI_D3cold, 0);
+		ioread32(hw->hw_addr + REG_MAC_CTRL);
+
+		/* poke the PHY */
+		ctrl = ioread32(hw->hw_addr + REG_PCIE_PHYMISC);
+		ctrl |= PCIE_PHYMISC_FORCE_RCV_DET;
+		iowrite32(ctrl, hw->hw_addr + REG_PCIE_PHYMISC);
+		ioread32(hw->hw_addr + REG_PCIE_PHYMISC);
+
+		pci_enable_wake(pdev, pci_choose_state(pdev, state), 1);
+		goto exit;
 	}
 
-	pci_save_state(pdev);
+	if (!val && wufc) {
+		ctrl |= (WOL_LINK_CHG_EN | WOL_LINK_CHG_PME_EN);
+		iowrite32(ctrl, hw->hw_addr + REG_WOL_CTRL);
+		ioread32(hw->hw_addr + REG_WOL_CTRL);
+		iowrite32(0, hw->hw_addr + REG_MAC_CTRL);
+		ioread32(hw->hw_addr + REG_MAC_CTRL);
+		hw->phy_configured = false;
+		pci_enable_wake(pdev, pci_choose_state(pdev, state), 1);
+		goto exit;
+	}
+
+disable_wol:
+	iowrite32(0, hw->hw_addr + REG_WOL_CTRL);
+	ioread32(hw->hw_addr + REG_WOL_CTRL);
+	ctrl = ioread32(hw->hw_addr + REG_PCIE_PHYMISC);
+	ctrl |= PCIE_PHYMISC_FORCE_RCV_DET;
+	iowrite32(ctrl, hw->hw_addr + REG_PCIE_PHYMISC);
+	ioread32(hw->hw_addr + REG_PCIE_PHYMISC);
+	atl1_phy_enter_power_saving(hw);
+	hw->phy_configured = false;
+	pci_enable_wake(pdev, pci_choose_state(pdev, state), 0);
+exit:
+	if (netif_running(netdev))
+		pci_disable_msi(adapter->pdev);
 	pci_disable_device(pdev);
-
-	pci_set_power_state(pdev, PCI_D3hot);
+	pci_set_power_state(pdev, pci_choose_state(pdev, state));
 
 	return 0;
 }
@@ -2855,20 +2880,26 @@ static int atl1_resume(struct pci_dev *pdev)
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
 
-	/* FIXME: check and handle */
 	err = pci_enable_device(pdev);
+	if (err) {
+		if (netif_msg_ifup(adapter))
+			dev_printk(KERN_DEBUG, &pdev->dev,
+				"error enabling pci device\n");
+		return err;
+	}
+
+	pci_set_master(pdev);
+	iowrite32(0, adapter->hw.hw_addr + REG_WOL_CTRL);
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
-	iowrite32(0, adapter->hw.hw_addr + REG_WOL_CTRL);
-	atl1_reset(adapter);
+	atl1_reset_hw(&adapter->hw);
+	adapter->cmb.cmb->int_stats = 0;
 
 	if (netif_running(netdev))
 		atl1_up(adapter);
 	netif_device_attach(netdev);
 
-	atl1_via_workaround(adapter);
-
 	return 0;
 }
 #else
@@ -2876,6 +2907,13 @@ static int atl1_resume(struct pci_dev *pdev)
 #define atl1_resume NULL
 #endif
 
+static void atl1_shutdown(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PM
+	atl1_suspend(pdev, PMSG_SUSPEND);
+#endif
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void atl1_poll_controller(struct net_device *netdev)
 {
@@ -3122,7 +3160,8 @@ static struct pci_driver atl1_driver = {
 	.probe = atl1_probe,
 	.remove = __devexit_p(atl1_remove),
 	.suspend = atl1_suspend,
-	.resume = atl1_resume
+	.resume = atl1_resume,
+	.shutdown = atl1_shutdown
 };
 
 /*

drivers/net/atlx/atl1.h

 /*
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
- * Copyright(c) 2006 Jay Cliburn <jcliburn@gmail.com>
+ * Copyright(c) 2006 - 2008 Jay Cliburn <jcliburn@gmail.com>
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.

drivers/net/atlx/atlx.c

@@ -2,7 +2,7 @@
  *
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
- * Copyright(c) 2006 Jay Cliburn <jcliburn@gmail.com>
+ * Copyright(c) 2006 - 2008 Jay Cliburn <jcliburn@gmail.com>
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver

drivers/net/atlx/atlx.h

@@ -2,7 +2,7 @@
  *
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
- * Copyright(c) 2006 Jay Cliburn <jcliburn@gmail.com>
+ * Copyright(c) 2006 - 2008 Jay Cliburn <jcliburn@gmail.com>
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
@@ -29,7 +29,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 
-#define ATLX_DRIVER_VERSION "2.1.1"
+#define ATLX_DRIVER_VERSION "2.1.3"
 MODULE_AUTHOR("Xiong Huang <xiong.huang@atheros.com>, \
 	Chris Snook <csnook@redhat.com>, Jay Cliburn <jcliburn@gmail.com>");
 MODULE_LICENSE("GPL");
@@ -460,6 +460,9 @@ MODULE_VERSION(ATLX_DRIVER_VERSION);
 #define MII_ATLX_PSSR_100MBS		0x4000	/* 01=100Mbs */
 #define MII_ATLX_PSSR_1000MBS		0x8000	/* 10=1000Mbs */
 
+#define MII_DBG_ADDR			0x1D
+#define MII_DBG_DATA			0x1E
+
 /* PCI Command Register Bit Definitions */
 #define PCI_REG_COMMAND			0x04	/* PCI Command Register */
 #define CMD_IO_SPACE			0x0001

drivers/net/cxgb3/adapter.h

@@ -71,6 +71,7 @@ enum {				/* adapter flags */
 	USING_MSIX = (1 << 2),
 	QUEUES_BOUND = (1 << 3),
 	TP_PARITY_INIT = (1 << 4),
+	NAPI_INIT = (1 << 5),
 };
 
 struct fl_pg_chunk {

drivers/net/cxgb3/common.h

@@ -698,6 +698,7 @@ void mac_prep(struct cmac *mac, struct adapter *adapter, int index);
 void early_hw_init(struct adapter *adapter, const struct adapter_info *ai);
 int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai,
 		    int reset);
+int t3_replay_prep_adapter(struct adapter *adapter);
 void t3_led_ready(struct adapter *adapter);
 void t3_fatal_err(struct adapter *adapter);
 void t3_set_vlan_accel(struct adapter *adapter, unsigned int ports, int on);

drivers/net/cxgb3/cxgb3_main.c

@@ -421,6 +421,13 @@ static void init_napi(struct adapter *adap)
 			netif_napi_add(qs->netdev, &qs->napi, qs->napi.poll,
 				       64);
 	}
+
+	/*
+	 * netif_napi_add() can be called only once per napi_struct because it
+	 * adds each new napi_struct to a list.  Be careful not to call it a
+	 * second time, e.g., during EEH recovery, by making a note of it.
+	 */
+	adap->flags |= NAPI_INIT;
 }
 
 /*
@@ -896,7 +903,8 @@ static int cxgb_up(struct adapter *adap)
 			goto out;
 
 		setup_rss(adap);
-		init_napi(adap);
+		if (!(adap->flags & NAPI_INIT))
+			init_napi(adap);
 		adap->flags |= FULL_INIT_DONE;
 	}
 
@@ -999,7 +1007,7 @@ static int offload_open(struct net_device *dev)
 		return 0;
 
 	if (!adap_up && (err = cxgb_up(adapter)) < 0)
-		return err;
+		goto out;
 
 	t3_tp_set_offload_mode(adapter, 1);
 	tdev->lldev = adapter->port[0];
@@ -1061,10 +1069,8 @@ static int cxgb_open(struct net_device *dev)
 	int other_ports = adapter->open_device_map & PORT_MASK;
 	int err;
 
-	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0) {
-		quiesce_rx(adapter);
+	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0)
 		return err;
-	}
 
 	set_bit(pi->port_id, &adapter->open_device_map);
 	if (is_offload(adapter) && !ofld_disable) {
@@ -2424,14 +2430,11 @@ static pci_ers_result_t t3_io_error_detected(struct pci_dev *pdev,
 	    test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map))
 		offload_close(&adapter->tdev);
 
-	/* Free sge resources */
-	t3_free_sge_resources(adapter);
-
 	adapter->flags &= ~FULL_INIT_DONE;
 
 	pci_disable_device(pdev);
 
-	/* Request a slot slot reset. */
+	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
@@ -2448,13 +2451,20 @@ static pci_ers_result_t t3_io_slot_reset(struct pci_dev *pdev)
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev,
 			"Cannot re-enable PCI device after reset.\n");
-		return PCI_ERS_RESULT_DISCONNECT;
+		goto err;
 	}
 	pci_set_master(pdev);
+	pci_restore_state(pdev);
 
-	t3_prep_adapter(adapter, adapter->params.info, 1);
+	/* Free sge resources */
+	t3_free_sge_resources(adapter);
+
+	if (t3_replay_prep_adapter(adapter))
+		goto err;
 
 	return PCI_ERS_RESULT_RECOVERED;
+err:
+	return PCI_ERS_RESULT_DISCONNECT;
 }
 
 /**
@@ -2483,13 +2493,6 @@ static void t3_io_resume(struct pci_dev *pdev)
 			netif_device_attach(netdev);
 		}
 	}
-
-	if (is_offload(adapter)) {
-		__set_bit(OFFLOAD_DEVMAP_BIT, &adapter->registered_device_map);
-		if (offload_open(adapter->port[0]))
-			printk(KERN_WARNING
-			       "Could not bring back offload capabilities\n");
-	}
 }
 
 static struct pci_error_handlers t3_err_handler = {
@@ -2608,6 +2611,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 	}
 
 	pci_set_master(pdev);
+	pci_save_state(pdev);
 
 	mmio_start = pci_resource_start(pdev, 0);
 	mmio_len = pci_resource_len(pdev, 0);

drivers/net/cxgb3/regs.h

@@ -444,6 +444,14 @@
 
 #define A_PCIE_CFG 0x88
 
+#define S_ENABLELINKDWNDRST    21
+#define V_ENABLELINKDWNDRST(x) ((x) << S_ENABLELINKDWNDRST)
+#define F_ENABLELINKDWNDRST    V_ENABLELINKDWNDRST(1U)
+
+#define S_ENABLELINKDOWNRST    20
+#define V_ENABLELINKDOWNRST(x) ((x) << S_ENABLELINKDOWNRST)
+#define F_ENABLELINKDOWNRST    V_ENABLELINKDOWNRST(1U)
+
 #define S_PCIE_CLIDECEN    16
 #define V_PCIE_CLIDECEN(x) ((x) << S_PCIE_CLIDECEN)
 #define F_PCIE_CLIDECEN    V_PCIE_CLIDECEN(1U)

drivers/net/cxgb3/sge.c

@@ -538,6 +538,31 @@ static void *alloc_ring(struct pci_dev *pdev, size_t nelem, size_t elem_size,
 	return p;
 }
 
+/**
+ *	t3_reset_qset - reset a sge qset
+ *	@q: the queue set
+ *
+ *	Reset the qset structure.
+ *	the NAPI structure is preserved in the event of
+ *	the qset's reincarnation, for example during EEH recovery.
+ */
+static void t3_reset_qset(struct sge_qset *q)
+{
+	if (q->adap &&
+	    !(q->adap->flags & NAPI_INIT)) {
+		memset(q, 0, sizeof(*q));
+		return;
+	}
+
+	q->adap = NULL;
+	memset(&q->rspq, 0, sizeof(q->rspq));
+	memset(q->fl, 0, sizeof(struct sge_fl) * SGE_RXQ_PER_SET);
+	memset(q->txq, 0, sizeof(struct sge_txq) * SGE_TXQ_PER_SET);
+	q->txq_stopped = 0;
+	memset(&q->tx_reclaim_timer, 0, sizeof(q->tx_reclaim_timer));
+}
+
+
 /**
  *	free_qset - free the resources of an SGE queue set
  *	@adapter: the adapter owning the queue set
@@ -594,7 +619,7 @@ static void t3_free_qset(struct adapter *adapter, struct sge_qset *q)
 				  q->rspq.desc, q->rspq.phys_addr);
 	}
 
-	memset(q, 0, sizeof(*q));
+	t3_reset_qset(q);
 }
 
 /**
@@ -1365,7 +1390,7 @@ static void restart_ctrlq(unsigned long data)
  */
 int t3_mgmt_tx(struct adapter *adap, struct sk_buff *skb)
 {
-	int ret; 
+	int ret;
 	local_bh_disable();
 	ret = ctrl_xmit(adap, &adap->sge.qs[0].txq[TXQ_CTRL], skb);
 	local_bh_enable();

drivers/net/cxgb3/t3_hw.c

@@ -3264,6 +3264,7 @@ static void config_pcie(struct adapter *adap)
 
 	t3_write_reg(adap, A_PCIE_PEX_ERR, 0xffffffff);
 	t3_set_reg_field(adap, A_PCIE_CFG, 0,
+			 F_ENABLELINKDWNDRST | F_ENABLELINKDOWNRST |
 			 F_PCIE_DMASTOPEN | F_PCIE_CLIDECEN);
 }
 
@@ -3655,3 +3656,30 @@ void t3_led_ready(struct adapter *adapter)
 	t3_set_reg_field(adapter, A_T3DBG_GPIO_EN, F_GPIO0_OUT_VAL,
 			 F_GPIO0_OUT_VAL);
 }
+
+int t3_replay_prep_adapter(struct adapter *adapter)
+{
+	const struct adapter_info *ai = adapter->params.info;
+	unsigned int i, j = 0;
+	int ret;
+
+	early_hw_init(adapter, ai);
+	ret = init_parity(adapter);
+	if (ret)
+		return ret;
+
+	for_each_port(adapter, i) {
+		struct port_info *p = adap2pinfo(adapter, i);
+		while (!adapter->params.vpd.port_type[j])
+			++j;
+
+		p->port_type->phy_prep(&p->phy, adapter, ai->phy_base_addr + j,
+					ai->mdio_ops);
+
+		p->phy.ops->power_down(&p->phy, 1);
+		++j;
+	}
+
+return 0;
+}
+

drivers/net/dm9000.c

@@ -117,6 +117,9 @@ typedef struct board_info {
 
 	struct mutex	 addr_lock;	/* phy and eeprom access lock */
 
+	struct delayed_work phy_poll;
+	struct net_device  *ndev;
+
 	spinlock_t lock;
 
 	struct mii_if_info mii;
@@ -297,6 +300,10 @@ static void dm9000_set_io(struct board_info *db, int byte_width)
 	}
 }
 
+static void dm9000_schedule_poll(board_info_t *db)
+{
+	schedule_delayed_work(&db->phy_poll, HZ * 2);
+}
 
 /* Our watchdog timed out. Called by the networking layer */
 static void dm9000_timeout(struct net_device *dev)
@@ -465,6 +472,17 @@ static const struct ethtool_ops dm9000_ethtool_ops = {
  	.set_eeprom		= dm9000_set_eeprom,
 };
 
+static void
+dm9000_poll_work(struct work_struct *w)
+{
+	struct delayed_work *dw = container_of(w, struct delayed_work, work);
+	board_info_t *db = container_of(dw, board_info_t, phy_poll);
+
+	mii_check_media(&db->mii, netif_msg_link(db), 0);
+	
+	if (netif_running(db->ndev))
+		dm9000_schedule_poll(db);
+}
 
 /* dm9000_release_board
  *
@@ -503,7 +521,7 @@ dm9000_release_board(struct platform_device *pdev, struct board_info *db)
 /*
  * Search DM9000 board, allocate space and register it
  */
-static int
+static int __devinit
 dm9000_probe(struct platform_device *pdev)
 {
 	struct dm9000_plat_data *pdata = pdev->dev.platform_data;
@@ -525,17 +543,21 @@ dm9000_probe(struct platform_device *pdev)
 
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
-	dev_dbg(&pdev->dev, "dm9000_probe()");
+	dev_dbg(&pdev->dev, "dm9000_probe()\n");
 
 	/* setup board info structure */
 	db = (struct board_info *) ndev->priv;
 	memset(db, 0, sizeof (*db));
 
 	db->dev = &pdev->dev;
+	db->ndev = ndev;
 
 	spin_lock_init(&db->lock);
 	mutex_init(&db->addr_lock);
 
+	INIT_DELAYED_WORK(&db->phy_poll, dm9000_poll_work);
+
+
 	if (pdev->num_resources < 2) {
 		ret = -ENODEV;
 		goto out;
@@ -761,6 +783,8 @@ dm9000_open(struct net_device *dev)
 
 	mii_check_media(&db->mii, netif_msg_link(db), 1);
 	netif_start_queue(dev);
+	
+	dm9000_schedule_poll(db);
 
 	return 0;
 }
@@ -879,6 +903,8 @@ dm9000_stop(struct net_device *ndev)
 	if (netif_msg_ifdown(db))
 		dev_dbg(db->dev, "shutting down %s\n", ndev->name);
 
+	cancel_delayed_work(&db->phy_poll);
+
 	netif_stop_queue(ndev);
 	netif_carrier_off(ndev);
 
@@ -1288,6 +1314,8 @@ dm9000_phy_read(struct net_device *dev, int phy_reg_unused, int reg)
 	spin_unlock_irqrestore(&db->lock,flags);
 
 	mutex_unlock(&db->addr_lock);
+
+	dm9000_dbg(db, 5, "phy_read[%02x] -> %04x\n", reg, ret);
 	return ret;
 }
 
@@ -1301,6 +1329,7 @@ dm9000_phy_write(struct net_device *dev, int phyaddr_unused, int reg, int value)
 	unsigned long flags;
 	unsigned long reg_save;
 
+	dm9000_dbg(db, 5, "phy_write[%02x] = %04x\n", reg, value);
 	mutex_lock(&db->addr_lock);
 
 	spin_lock_irqsave(&db->lock,flags);
@@ -1372,7 +1401,7 @@ dm9000_drv_resume(struct platform_device *dev)
 	return 0;
 }
 
-static int
+static int __devexit
 dm9000_drv_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
@@ -1393,7 +1422,7 @@ static struct platform_driver dm9000_driver = {
 		.owner	 = THIS_MODULE,
 	},
 	.probe   = dm9000_probe,
-	.remove  = dm9000_drv_remove,
+	.remove  = __devexit_p(dm9000_drv_remove),
 	.suspend = dm9000_drv_suspend,
 	.resume  = dm9000_drv_resume,
 };

drivers/net/ehea/ehea.h

@@ -40,7 +40,7 @@
 #include <asm/io.h>
 
 #define DRV_NAME	"ehea"
-#define DRV_VERSION	"EHEA_0090"
+#define DRV_VERSION	"EHEA_0091"
 
 /* eHEA capability flags */
 #define DLPAR_PORT_ADD_REM 1
@@ -118,6 +118,13 @@
 #define EHEA_MR_ACC_CTRL       0x00800000
 
 #define EHEA_BUSMAP_START      0x8000000000000000ULL
+#define EHEA_INVAL_ADDR        0xFFFFFFFFFFFFFFFFULL
+#define EHEA_DIR_INDEX_SHIFT 13                   /* 8k Entries in 64k block */
+#define EHEA_TOP_INDEX_SHIFT (EHEA_DIR_INDEX_SHIFT * 2)
+#define EHEA_MAP_ENTRIES (1 << EHEA_DIR_INDEX_SHIFT)
+#define EHEA_MAP_SIZE (0x10000)                   /* currently fixed map size */
+#define EHEA_INDEX_MASK (EHEA_MAP_ENTRIES - 1)
+
 
 #define EHEA_WATCH_DOG_TIMEOUT 10*HZ
 
@@ -192,10 +199,20 @@ struct h_epas {
 				   set to 0 if unused */
 };
 
-struct ehea_busmap {
-	unsigned int entries;		/* total number of entries */
-	unsigned int valid_sections;	/* number of valid sections */
-	u64 *vaddr;
+/*
+ * Memory map data structures
+ */
+struct ehea_dir_bmap
+{
+	u64 ent[EHEA_MAP_ENTRIES];
+};
+struct ehea_top_bmap
+{
+	struct ehea_dir_bmap *dir[EHEA_MAP_ENTRIES];
+};
+struct ehea_bmap
+{
+	struct ehea_top_bmap *top[EHEA_MAP_ENTRIES];
 };
 
 struct ehea_qp;

drivers/net/ehea/ehea_main.c

@@ -35,6 +35,7 @@
 #include <linux/if_ether.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
+#include <linux/memory.h>
 #include <asm/kexec.h>
 #include <linux/mutex.h>
 
@@ -3503,6 +3504,24 @@ void ehea_crash_handler(void)
 					      0, H_DEREG_BCMC);
 }
 
+static int ehea_mem_notifier(struct notifier_block *nb,
+                             unsigned long action, void *data)
+{
+	switch (action) {
+	case MEM_OFFLINE:
+		ehea_info("memory has been removed");
+		ehea_rereg_mrs(NULL);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ehea_mem_nb = {
+	.notifier_call = ehea_mem_notifier,
+};
+
 static int ehea_reboot_notifier(struct notifier_block *nb,
 				unsigned long action, void *unused)
 {
@@ -3581,6 +3600,10 @@ int __init ehea_module_init(void)
 	if (ret)
 		ehea_info("failed registering reboot notifier");
 
+	ret = register_memory_notifier(&ehea_mem_nb);
+	if (ret)
+		ehea_info("failed registering memory remove notifier");
+
 	ret = crash_shutdown_register(&ehea_crash_handler);
 	if (ret)
 		ehea_info("failed registering crash handler");
@@ -3604,6 +3627,7 @@ int __init ehea_module_init(void)
 out3:
 	ibmebus_unregister_driver(&ehea_driver);
 out2:
+	unregister_memory_notifier(&ehea_mem_nb);
 	unregister_reboot_notifier(&ehea_reboot_nb);
 	crash_shutdown_unregister(&ehea_crash_handler);
 out:
@@ -3621,6 +3645,7 @@ static void __exit ehea_module_exit(void)
 	ret = crash_shutdown_unregister(&ehea_crash_handler);
 	if (ret)
 		ehea_info("failed unregistering crash handler");
+	unregister_memory_notifier(&ehea_mem_nb);
 	kfree(ehea_fw_handles.arr);
 	kfree(ehea_bcmc_regs.arr);
 	ehea_destroy_busmap();

drivers/net/ehea/ehea_qmr.c

@@ -31,8 +31,8 @@
 #include "ehea_phyp.h"
 #include "ehea_qmr.h"
 
+struct ehea_bmap *ehea_bmap = NULL;
 
-struct ehea_busmap ehea_bmap = { 0, 0, NULL };
 
 
 static void *hw_qpageit_get_inc(struct hw_queue *queue)
@@ -559,125 +559,253 @@ int ehea_destroy_qp(struct ehea_qp *qp)
 	return 0;
 }
 
-int ehea_create_busmap(void)
+static inline int ehea_calc_index(unsigned long i, unsigned long s)
 {
-	u64 vaddr = EHEA_BUSMAP_START;
-	unsigned long high_section_index = 0;
-	int i;
+	return (i >> s) & EHEA_INDEX_MASK;
+}
 
-	/*
-	 * Sections are not in ascending order -> Loop over all sections and
-	 * find the highest PFN to compute the required map size.
-	*/
-	ehea_bmap.valid_sections = 0;
+static inline int ehea_init_top_bmap(struct ehea_top_bmap *ehea_top_bmap,
+				     int dir)
+{
+	if(!ehea_top_bmap->dir[dir]) {
+		ehea_top_bmap->dir[dir] =
+			kzalloc(sizeof(struct ehea_dir_bmap), GFP_KERNEL);
+		if (!ehea_top_bmap->dir[dir])
+			return -ENOMEM;
+	}
+	return 0;
+}
 
-	for (i = 0; i < NR_MEM_SECTIONS; i++)
-		if (valid_section_nr(i))
-			high_section_index = i;
+static inline int ehea_init_bmap(struct ehea_bmap *ehea_bmap, int top, int dir)
+{
+	if(!ehea_bmap->top[top]) {
+		ehea_bmap->top[top] =
+			kzalloc(sizeof(struct ehea_top_bmap), GFP_KERNEL);
+		if (!ehea_bmap->top[top])
+			return -ENOMEM;
+	}
+	return ehea_init_top_bmap(ehea_bmap->top[top], dir);
+}
 
-	ehea_bmap.entries = high_section_index + 1;
-	ehea_bmap.vaddr = vmalloc(ehea_bmap.entries * sizeof(*ehea_bmap.vaddr));
+static int ehea_create_busmap_callback(unsigned long pfn,
+				       unsigned long nr_pages, void *arg)
+{
+	unsigned long i, mr_len, start_section, end_section;
+	start_section = (pfn * PAGE_SIZE) / EHEA_SECTSIZE;
+	end_section = start_section + ((nr_pages * PAGE_SIZE) / EHEA_SECTSIZE);
+	mr_len = *(unsigned long *)arg;
 
-	if (!ehea_bmap.vaddr)
+	ehea_bmap = kzalloc(sizeof(struct ehea_bmap), GFP_KERNEL);
+	if (!ehea_bmap)
 		return -ENOMEM;
 
-	for (i = 0 ; i < ehea_bmap.entries; i++) {
-		unsigned long pfn = section_nr_to_pfn(i);
+	for (i = start_section; i < end_section; i++) {
+		int ret;
+		int top, dir, idx;
+		u64 vaddr;
+
+		top = ehea_calc_index(i, EHEA_TOP_INDEX_SHIFT);
+		dir = ehea_calc_index(i, EHEA_DIR_INDEX_SHIFT);
+
+		ret = ehea_init_bmap(ehea_bmap, top, dir);
+		if(ret)
+			return ret;
 
-		if (pfn_valid(pfn)) {
-			ehea_bmap.vaddr[i] = vaddr;
-			vaddr += EHEA_SECTSIZE;
-			ehea_bmap.valid_sections++;
-		} else
-			ehea_bmap.vaddr[i] = 0;
+		idx = i & EHEA_INDEX_MASK;
+		vaddr = EHEA_BUSMAP_START + mr_len + i * EHEA_SECTSIZE;
+
+		ehea_bmap->top[top]->dir[dir]->ent[idx] = vaddr;
 	}
 
+	mr_len += nr_pages * PAGE_SIZE;
+	*(unsigned long *)arg = mr_len;
+
 	return 0;
 }
 
+static unsigned long ehea_mr_len;
+
+static DEFINE_MUTEX(ehea_busmap_mutex);
+
+int ehea_create_busmap(void)
+{
+	int ret;
+	mutex_lock(&ehea_busmap_mutex);
+	ehea_mr_len = 0;
+	ret = walk_memory_resource(0, 1ULL << MAX_PHYSMEM_BITS, &ehea_mr_len,
+				   ehea_create_busmap_callback);
+	mutex_unlock(&ehea_busmap_mutex);
+	return ret;
+}
+
 void ehea_destroy_busmap(void)
 {
-	vfree(ehea_bmap.vaddr);
+	int top, dir;
+	mutex_lock(&ehea_busmap_mutex);
+	if (!ehea_bmap)
+		goto out_destroy;
+
+	for (top = 0; top < EHEA_MAP_ENTRIES; top++) {
+		if (!ehea_bmap->top[top])
+			continue;
+
+		for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) {
+			if (!ehea_bmap->top[top]->dir[dir])
+				continue;
+
+			kfree(ehea_bmap->top[top]->dir[dir]);
+		}
+
+		kfree(ehea_bmap->top[top]);
+	}
+
+	kfree(ehea_bmap);
+	ehea_bmap = NULL;
+out_destroy:	
+	mutex_unlock(&ehea_busmap_mutex);
 }
 
 u64 ehea_map_vaddr(void *caddr)
 {
-	u64 mapped_addr;
-	unsigned long index = __pa(caddr) >> SECTION_SIZE_BITS;
-
-	if (likely(index < ehea_bmap.entries)) {
-		mapped_addr = ehea_bmap.vaddr[index];
-		if (likely(mapped_addr))
-			mapped_addr |= (((unsigned long)caddr)
-					& (EHEA_SECTSIZE - 1));
-		else
-			mapped_addr = -1;
-	} else
-		mapped_addr = -1;
-
-	if (unlikely(mapped_addr == -1))
-		if (!test_and_set_bit(__EHEA_STOP_XFER, &ehea_driver_flags))
-			schedule_work(&ehea_rereg_mr_task);
-
-	return mapped_addr;
+	int top, dir, idx;
+	unsigned long index, offset;
+
+	if (!ehea_bmap)
+		return EHEA_INVAL_ADDR;
+
+	index = virt_to_abs(caddr) >> SECTION_SIZE_BITS;
+	top = (index >> EHEA_TOP_INDEX_SHIFT) & EHEA_INDEX_MASK;
+	if (!ehea_bmap->top[top])
+		return EHEA_INVAL_ADDR;
+
+	dir = (index >> EHEA_DIR_INDEX_SHIFT) & EHEA_INDEX_MASK;
+	if (!ehea_bmap->top[top]->dir[dir])
+		return EHEA_INVAL_ADDR;
+
+	idx = index & EHEA_INDEX_MASK;
+	if (!ehea_bmap->top[top]->dir[dir]->ent[idx])
+		return EHEA_INVAL_ADDR;
+
+	offset = (unsigned long)caddr & (EHEA_SECTSIZE - 1);
+	return ehea_bmap->top[top]->dir[dir]->ent[idx] | offset;
+}
+
+static inline void *ehea_calc_sectbase(int top, int dir, int idx)
+{
+	unsigned long ret = idx;
+	ret |= dir << EHEA_DIR_INDEX_SHIFT;
+	ret |= top << EHEA_TOP_INDEX_SHIFT;
+	return abs_to_virt(ret << SECTION_SIZE_BITS);
+}
+
+static u64 ehea_reg_mr_section(int top, int dir, int idx, u64 *pt,
+			       struct ehea_adapter *adapter,
+			       struct ehea_mr *mr)
+{
+	void *pg;
+	u64 j, m, hret;
+	unsigned long k = 0;
+	u64 pt_abs = virt_to_abs(pt);
+
+	void *sectbase = ehea_calc_sectbase(top, dir, idx);
+
+	for (j = 0; j < (EHEA_PAGES_PER_SECTION / EHEA_MAX_RPAGE); j++) {
+
+		for (m = 0; m < EHEA_MAX_RPAGE; m++) {
+			pg = sectbase + ((k++) * EHEA_PAGESIZE);
+			pt[m] = virt_to_abs(pg);
+		}
+		hret = ehea_h_register_rpage_mr(adapter->handle, mr->handle, 0,
+						0, pt_abs, EHEA_MAX_RPAGE);
+
+		if ((hret != H_SUCCESS)
+		    && (hret != H_PAGE_REGISTERED)) {
+			ehea_h_free_resource(adapter->handle, mr->handle,
+					     FORCE_FREE);
+			ehea_error("register_rpage_mr failed");
+			return hret;
+		}
+	}
+	return hret;
+}
+
+static u64 ehea_reg_mr_sections(int top, int dir, u64 *pt,
+				struct ehea_adapter *adapter,
+				struct ehea_mr *mr)
+{
+	u64 hret = H_SUCCESS;
+	int idx;
+
+	for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) {
+		if (!ehea_bmap->top[top]->dir[dir]->ent[idx])
+			continue;
+		
+		hret = ehea_reg_mr_section(top, dir, idx, pt, adapter, mr);
+		if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED))
+			    	return hret;
+	}
+	return hret;
+}
+
+static u64 ehea_reg_mr_dir_sections(int top, u64 *pt,
+				    struct ehea_adapter *adapter,
+				    struct ehea_mr *mr)
+{
+	u64 hret = H_SUCCESS;
+	int dir;
+
+	for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) {
+		if (!ehea_bmap->top[top]->dir[dir])
+			continue;
+
+		hret = ehea_reg_mr_sections(top, dir, pt, adapter, mr);
+		if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED))
+			    	return hret;
+	}
+	return hret;
 }
 
 int ehea_reg_kernel_mr(struct ehea_adapter *adapter, struct ehea_mr *mr)
 {
 	int ret;
 	u64 *pt;
-	void *pg;
-	u64 hret, pt_abs, i, j, m, mr_len;
+	u64 hret;
 	u32 acc_ctrl = EHEA_MR_ACC_CTRL;
 
-	mr_len = ehea_bmap.valid_sections * EHEA_SECTSIZE;
+	unsigned long top;
 
-	pt =  kzalloc(PAGE_SIZE, GFP_KERNEL);
+	pt = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!pt) {
 		ehea_error("no mem");
 		ret = -ENOMEM;
 		goto out;
 	}
-	pt_abs = virt_to_abs(pt);
 
-	hret = ehea_h_alloc_resource_mr(adapter->handle,
-					EHEA_BUSMAP_START, mr_len,
-					acc_ctrl, adapter->pd,
+	hret = ehea_h_alloc_resource_mr(adapter->handle, EHEA_BUSMAP_START,
+					ehea_mr_len, acc_ctrl, adapter->pd,
 					&mr->handle, &mr->lkey);
+
 	if (hret != H_SUCCESS) {
 		ehea_error("alloc_resource_mr failed");
 		ret = -EIO;
 		goto out;
 	}
 
-	for (i = 0 ; i < ehea_bmap.entries; i++)
-		if (ehea_bmap.vaddr[i]) {
-			void *sectbase = __va(i << SECTION_SIZE_BITS);
-			unsigned long k = 0;
-
-			for (j = 0; j < (EHEA_PAGES_PER_SECTION /
-					 EHEA_MAX_RPAGE); j++) {
-
-				for (m = 0; m < EHEA_MAX_RPAGE; m++) {
-					pg = sectbase + ((k++) * EHEA_PAGESIZE);
-					pt[m] = virt_to_abs(pg);
-				}
-
-				hret = ehea_h_register_rpage_mr(adapter->handle,
-								mr->handle,
-								0, 0, pt_abs,
-								EHEA_MAX_RPAGE);
-				if ((hret != H_SUCCESS)
-				    && (hret != H_PAGE_REGISTERED)) {
-					ehea_h_free_resource(adapter->handle,
-							     mr->handle,
-							     FORCE_FREE);
-					ehea_error("register_rpage_mr failed");
-					ret = -EIO;
-					goto out;
-				}
-			}
-		}
+	if (!ehea_bmap) {
+		ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE);
+		ehea_error("no busmap available");
+		ret = -EIO;
+		goto out;
+	}
+
+	for (top = 0; top < EHEA_MAP_ENTRIES; top++) {
+		if (!ehea_bmap->top[top])
+			continue;
+
+		hret = ehea_reg_mr_dir_sections(top, pt, adapter, mr);
+		if((hret != H_PAGE_REGISTERED) && (hret != H_SUCCESS))
+			break;
+	}
 
 	if (hret != H_SUCCESS) {
 		ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE);

drivers/net/gianfar.c

@@ -635,6 +635,8 @@ static void free_skb_resources(struct gfar_private *priv)
 			dev_kfree_skb_any(priv->tx_skbuff[i]);
 			priv->tx_skbuff[i] = NULL;
 		}
+
+		txbdp++;
 	}
 
 	kfree(priv->tx_skbuff);

drivers/net/myri10ge/myri10ge_mcp.h

@@ -10,7 +10,7 @@ struct mcp_dma_addr {
 	__be32 low;
 };
 
-/* 4 Bytes.  8 Bytes for NDIS drivers. */
+/* 4 Bytes */
 struct mcp_slot {
 	__sum16 checksum;
 	__be16 length;
@@ -144,6 +144,7 @@ enum myri10ge_mcp_cmd_type {
 	 * a power of 2 number of entries.  */
 
 	MXGEFW_CMD_SET_INTRQ_SIZE,	/* in bytes */
+#define MXGEFW_CMD_SET_INTRQ_SIZE_FLAG_NO_STRICT_SIZE_CHECK  (1 << 31)
 
 	/* command to bring ethernet interface up.  Above parameters
 	 * (plus mtu & mac address) must have been exchanged prior
@@ -221,10 +222,14 @@ enum myri10ge_mcp_cmd_type {
 	MXGEFW_CMD_GET_MAX_RSS_QUEUES,
 	MXGEFW_CMD_ENABLE_RSS_QUEUES,
 	/* data0 = number of slices n (0, 1, ..., n-1) to enable
-	 * data1 = interrupt mode. 0=share one INTx/MSI, 1=use one MSI-X per queue.
+	 * data1 = interrupt mode.
+	 * 0=share one INTx/MSI, 1=use one MSI-X per queue.
 	 * If all queues share one interrupt, the driver must have set
 	 * RSS_SHARED_INTERRUPT_DMA before enabling queues.
 	 */
+#define MXGEFW_SLICE_INTR_MODE_SHARED 0
+#define MXGEFW_SLICE_INTR_MODE_ONE_PER_SLICE 1
+
 	MXGEFW_CMD_GET_RSS_SHARED_INTERRUPT_MASK_OFFSET,
 	MXGEFW_CMD_SET_RSS_SHARED_INTERRUPT_DMA,
 	/* data0, data1 = bus address lsw, msw */
@@ -241,10 +246,14 @@ enum myri10ge_mcp_cmd_type {
 	 * 0: disable rss.  nic does not distribute receive packets.
 	 * 1: enable rss.  nic distributes receive packets among queues.
 	 * data1 = hash type
-	 * 1: IPV4
-	 * 2: TCP_IPV4
-	 * 3: IPV4 | TCP_IPV4
+	 * 1: IPV4            (required by RSS)
+	 * 2: TCP_IPV4        (required by RSS)
+	 * 3: IPV4 | TCP_IPV4 (required by RSS)
+	 * 4: source port
 	 */
+#define MXGEFW_RSS_HASH_TYPE_IPV4      0x1
+#define MXGEFW_RSS_HASH_TYPE_TCP_IPV4  0x2
+#define MXGEFW_RSS_HASH_TYPE_SRC_PORT  0x4
 
 	MXGEFW_CMD_GET_MAX_TSO6_HDR_SIZE,
 	/* Return data = the max. size of the entire headers of a IPv6 TSO packet.
@@ -260,6 +269,8 @@ enum myri10ge_mcp_cmd_type {
 	 * 0: Linux/FreeBSD style (NIC default)
 	 * 1: NDIS/NetBSD style
 	 */
+#define MXGEFW_TSO_MODE_LINUX  0
+#define MXGEFW_TSO_MODE_NDIS   1
 
 	MXGEFW_CMD_MDIO_READ,
 	/* data0 = dev_addr (PMA/PMD or PCS ...), data1 = register/addr */
@@ -286,6 +297,38 @@ enum myri10ge_mcp_cmd_type {
 	/* Return data = NIC memory offset of mcp_vpump_public_global */
 	MXGEFW_CMD_RESET_VPUMP,
 	/* Resets the VPUMP state */
+
+	MXGEFW_CMD_SET_RSS_MCP_SLOT_TYPE,
+	/* data0 = mcp_slot type to use.
+	 * 0 = the default 4B mcp_slot
+	 * 1 = 8B mcp_slot_8
+	 */
+#define MXGEFW_RSS_MCP_SLOT_TYPE_MIN        0
+#define MXGEFW_RSS_MCP_SLOT_TYPE_WITH_HASH  1
+
+	MXGEFW_CMD_SET_THROTTLE_FACTOR,
+	/* set the throttle factor for ethp_z8e
+	 * data0 = throttle_factor
+	 * throttle_factor = 256 * pcie-raw-speed / tx_speed
+	 * tx_speed = 256 * pcie-raw-speed / throttle_factor
+	 *
+	 * For PCI-E x8: pcie-raw-speed == 16Gb/s
+	 * For PCI-E x4: pcie-raw-speed == 8Gb/s
+	 *
+	 * ex1: throttle_factor == 0x1a0 (416), tx_speed == 1.23GB/s == 9.846 Gb/s
+	 * ex2: throttle_factor == 0x200 (512), tx_speed == 1.0GB/s == 8 Gb/s
+	 *
+	 * with tx_boundary == 2048, max-throttle-factor == 8191 => min-speed == 500Mb/s
+	 * with tx_boundary == 4096, max-throttle-factor == 4095 => min-speed == 1Gb/s
+	 */
+
+	MXGEFW_CMD_VPUMP_UP,
+	/* Allocates VPump Connection, Send Request and Zero copy buffer address tables */
+	MXGEFW_CMD_GET_VPUMP_CLK,
+	/* Get the lanai clock */
+
+	MXGEFW_CMD_GET_DCA_OFFSET,
+	/* offset of dca control for WDMAs */
 };
 
 enum myri10ge_mcp_cmd_status {
@@ -302,7 +345,8 @@ enum myri10ge_mcp_cmd_status {
 	MXGEFW_CMD_ERROR_UNALIGNED,
 	MXGEFW_CMD_ERROR_NO_MDIO,
 	MXGEFW_CMD_ERROR_XFP_FAILURE,
-	MXGEFW_CMD_ERROR_XFP_ABSENT
+	MXGEFW_CMD_ERROR_XFP_ABSENT,
+	MXGEFW_CMD_ERROR_BAD_PCIE_LINK
 };
 
 #define MXGEFW_OLD_IRQ_DATA_LEN 40

drivers/net/myri10ge/myri10ge_mcp_gen_header.h

 #ifndef __MYRI10GE_MCP_GEN_HEADER_H__
 #define __MYRI10GE_MCP_GEN_HEADER_H__
 
-/* this file define a standard header used as a first entry point to
- * exchange information between firmware/driver and driver.  The
- * header structure can be anywhere in the mcp. It will usually be in
- * the .data section, because some fields needs to be initialized at
- * compile time.
- * The 32bit word at offset MX_HEADER_PTR_OFFSET in the mcp must
- * contains the location of the header.
- *
- * Typically a MCP will start with the following:
- * .text
- * .space 52    ! to help catch MEMORY_INT errors
- * bt start     ! jump to real code
- * nop
- * .long _gen_mcp_header
- *
- * The source will have a definition like:
- *
- * mcp_gen_header_t gen_mcp_header = {
- * .header_length = sizeof(mcp_gen_header_t),
- * .mcp_type = MCP_TYPE_XXX,
- * .version = "something $Id: mcp_gen_header.h,v 1.2 2006/05/13 10:04:35 bgoglin Exp $",
- * .mcp_globals = (unsigned)&Globals
- * };
- */
 
 #define MCP_HEADER_PTR_OFFSET  0x3c
 
@@ -32,13 +8,14 @@
 #define MCP_TYPE_PCIE 0x70636965	/* "PCIE" pcie-only MCP */
 #define MCP_TYPE_ETH 0x45544820	/* "ETH " */
 #define MCP_TYPE_MCP0 0x4d435030	/* "MCP0" */
+#define MCP_TYPE_DFLT 0x20202020	/* "    " */
 
 struct mcp_gen_header {
 	/* the first 4 fields are filled at compile time */
 	unsigned header_length;
 	__be32 mcp_type;
 	char version[128];
-	unsigned mcp_globals;	/* pointer to mcp-type specific structure */
+	unsigned mcp_private;	/* pointer to mcp-type specific structure */
 
 	/* filled by the MCP at run-time */
 	unsigned sram_size;
@@ -53,6 +30,18 @@ struct mcp_gen_header {
 	 *
 	 * Never remove any field.  Keep everything naturally align.
 	 */
+
+	/* Specifies if the running mcp is mcp0, 1, or 2. */
+	unsigned char mcp_index;
+	unsigned char disable_rabbit;
+	unsigned char unaligned_tlp;
+	unsigned char pad1;
+	unsigned counters_addr;
+	unsigned copy_block_info;	/* for small mcps loaded with "lload -d" */
+	unsigned short handoff_id_major;	/* must be equal */
+	unsigned short handoff_id_caps;	/* bitfield: new mcp must have superset */
+	unsigned msix_table_addr;	/* start address of msix table in firmware */
+	/* 8 */
 };
 
 #endif				/* __MYRI10GE_MCP_GEN_HEADER_H__ */

drivers/net/sfc/Makefile

 sfc-y			+= efx.o falcon.o tx.o rx.o falcon_xmac.o \
-			   i2c-direct.o ethtool.o xfp_phy.o mdio_10g.o \
-			   tenxpress.o boards.o sfe4001.o
+			   i2c-direct.o selftest.o ethtool.o xfp_phy.o \
+			   mdio_10g.o tenxpress.o boards.o sfe4001.o
 
 obj-$(CONFIG_SFC)	+= sfc.o

drivers/net/sfc/boards.h

@@ -22,5 +22,7 @@ enum efx_board_type {
 extern int efx_set_board_info(struct efx_nic *efx, u16 revision_info);
 extern int sfe4001_poweron(struct efx_nic *efx);
 extern void sfe4001_poweroff(struct efx_nic *efx);
+/* Are we putting the PHY into flash config mode */
+extern unsigned int sfe4001_phy_flash_cfg;
 
 #endif

drivers/net/sfc/efx.c

@@ -1873,6 +1873,7 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type,
 		tx_queue->queue = i;
 		tx_queue->buffer = NULL;
 		tx_queue->channel = &efx->channel[0]; /* for safety */
+		tx_queue->tso_headers_free = NULL;
 	}
 	for (i = 0; i < EFX_MAX_RX_QUEUES; i++) {
 		rx_queue = &efx->rx_queue[i];
@@ -2071,7 +2072,8 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	net_dev = alloc_etherdev(sizeof(*efx));
 	if (!net_dev)
 		return -ENOMEM;
-	net_dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA;
+	net_dev->features |= (NETIF_F_IP_CSUM | NETIF_F_SG |
+			      NETIF_F_HIGHDMA | NETIF_F_TSO);
 	if (lro)
 		net_dev->features |= NETIF_F_LRO;
 	efx = net_dev->priv;

drivers/net/sfc/enum.h

@@ -10,6 +10,55 @@
 #ifndef EFX_ENUM_H
 #define EFX_ENUM_H
 
+/**
+ * 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_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_XGMII = 2,
+	LOOPBACK_XGXS = 3,
+	LOOPBACK_XAUI = 4,
+	LOOPBACK_PHY = 5,
+	LOOPBACK_PHYXS = 6,
+	LOOPBACK_PCS = 7,
+	LOOPBACK_PMAPMD = 8,
+	LOOPBACK_NETWORK = 9,
+	LOOPBACK_MAX
+};
+
+#define LOOPBACK_TEST_MAX LOOPBACK_PMAPMD
+
+extern const char *efx_loopback_mode_names[];
+#define LOOPBACK_MODE_NAME(mode)			\
+	STRING_TABLE_LOOKUP(mode, efx_loopback_mode)
+#define LOOPBACK_MODE(efx)				\
+	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 LOOPBACK_MASK(_efx)			\
+	(1 << (_efx)->loopback_mode)
+
+#define LOOPBACK_INTERNAL(_efx)						\
+	((LOOPBACKS_10G_INTERNAL & LOOPBACK_MASK(_efx)) ? 1 : 0)
+
+#define LOOPBACK_OUT_OF(_from, _to, _mask)		\
+	(((LOOPBACK_MASK(_from) & (_mask)) &&		\
+	  ((LOOPBACK_MASK(_to) & (_mask)) == 0)) ? 1 : 0)
+
 /*****************************************************************************/
 
 /**

drivers/net/sfc/ethtool.c

@@ -12,12 +12,26 @@
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include "net_driver.h"
+#include "selftest.h"
 #include "efx.h"
 #include "ethtool.h"
 #include "falcon.h"
 #include "gmii.h"
 #include "mac.h"
 
+const char *efx_loopback_mode_names[] = {
+	[LOOPBACK_NONE]		= "NONE",
+	[LOOPBACK_MAC]		= "MAC",
+	[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_NETWORK]	= "NETWORK",
+};
+
 static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable);
 
 struct ethtool_string {
@@ -217,23 +231,179 @@ static void efx_ethtool_get_drvinfo(struct net_device *net_dev,
 	strlcpy(info->bus_info, pci_name(efx->pci_dev), sizeof(info->bus_info));
 }
 
+/**
+ * efx_fill_test - fill in an individual self-test entry
+ * @test_index:		Index of the test
+ * @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")
+ * @test_format:	Test name format (e.g. "loopback.\%s.tx.sent")
+ * @test_id:		Test id (e.g. "PHY" for "loopback.PHY.tx_sent")
+ *
+ * Fill in an individual self-test entry.
+ */
+static void efx_fill_test(unsigned int test_index,
+			  struct ethtool_string *strings, u64 *data,
+			  int *test, const char *unit_format, int unit_id,
+			  const char *test_format, const char *test_id)
+{
+	struct ethtool_string unit_str, test_str;
+
+	/* Fill data value, if applicable */
+	if (data)
+		data[test_index] = *test;
+
+	/* Fill string, if applicable */
+	if (strings) {
+		snprintf(unit_str.name, sizeof(unit_str.name),
+			 unit_format, unit_id);
+		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);
+	}
+}
+
+#define EFX_PORT_NAME "port%d", 0
+#define EFX_CHANNEL_NAME(_channel) "channel%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)			\
+	"loopback.%s." _counter, LOOPBACK_MODE_NAME(mode)
+
+/**
+ * efx_fill_loopback_test - fill in a block of loopback self-test entries
+ * @efx:		Efx NIC
+ * @lb_tests:		Efx loopback self-test results structure
+ * @mode:		Loopback test mode
+ * @test_index:		Starting index of the test
+ * @strings:		Ethtool strings, or %NULL
+ * @data:		Ethtool test results, or %NULL
+ */
+static int efx_fill_loopback_test(struct efx_nic *efx,
+				  struct efx_loopback_self_tests *lb_tests,
+				  enum efx_loopback_mode mode,
+				  unsigned int test_index,
+				  struct ethtool_string *strings, u64 *data)
+{
+	struct efx_tx_queue *tx_queue;
+
+	efx_for_each_tx_queue(tx_queue, efx) {
+		efx_fill_test(test_index++, strings, data,
+			      &lb_tests->tx_sent[tx_queue->queue],
+			      EFX_TX_QUEUE_NAME(tx_queue),
+			      EFX_LOOPBACK_NAME(mode, "tx_sent"));
+		efx_fill_test(test_index++, strings, data,
+			      &lb_tests->tx_done[tx_queue->queue],
+			      EFX_TX_QUEUE_NAME(tx_queue),
+			      EFX_LOOPBACK_NAME(mode, "tx_done"));
+	}
+	efx_fill_test(test_index++, strings, data,
+		      &lb_tests->rx_good,
+		      EFX_PORT_NAME,
+		      EFX_LOOPBACK_NAME(mode, "rx_good"));
+	efx_fill_test(test_index++, strings, data,
+		      &lb_tests->rx_bad,
+		      EFX_PORT_NAME,
+		      EFX_LOOPBACK_NAME(mode, "rx_bad"));
+
+	return test_index;
+}
+
+/**
+ * efx_ethtool_fill_self_tests - get self-test details
+ * @efx:		Efx NIC
+ * @tests:		Efx self-test results structure, or %NULL
+ * @strings:		Ethtool strings, or %NULL
+ * @data:		Ethtool test results, or %NULL
+ */
+static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
+				       struct efx_self_tests *tests,
+				       struct ethtool_string *strings,
+				       u64 *data)
+{
+	struct efx_channel *channel;
+	unsigned int n = 0;
+	enum efx_loopback_mode mode;
+
+	/* Interrupt */
+	efx_fill_test(n++, strings, data, &tests->interrupt,
+		      "core", 0, "interrupt", NULL);
+
+	/* Event queues */
+	efx_for_each_channel(channel, efx) {
+		efx_fill_test(n++, strings, data,
+			      &tests->eventq_dma[channel->channel],
+			      EFX_CHANNEL_NAME(channel),
+			      "eventq.dma", NULL);
+		efx_fill_test(n++, strings, data,
+			      &tests->eventq_int[channel->channel],
+			      EFX_CHANNEL_NAME(channel),
+			      "eventq.int", NULL);
+		efx_fill_test(n++, strings, data,
+			      &tests->eventq_poll[channel->channel],
+			      EFX_CHANNEL_NAME(channel),
+			      "eventq.poll", NULL);
+	}
+
+	/* PHY presence */
+	efx_fill_test(n++, strings, data, &tests->phy_ok,
+		      EFX_PORT_NAME, "phy_ok", 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;
+		n = efx_fill_loopback_test(efx,
+					   &tests->loopback[mode], mode, n,
+					   strings, data);
+	}
+
+	return n;
+}
+
 static int efx_ethtool_get_stats_count(struct net_device *net_dev)
 {
 	return EFX_ETHTOOL_NUM_STATS;
 }
 
+static int efx_ethtool_self_test_count(struct net_device *net_dev)
+{
+	struct efx_nic *efx = net_dev->priv;
+
+	return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL);
+}
+
 static void efx_ethtool_get_strings(struct net_device *net_dev,
 				    u32 string_set, u8 *strings)
 {
+	struct efx_nic *efx = net_dev->priv;
 	struct ethtool_string *ethtool_strings =
 		(struct ethtool_string *)strings;
 	int i;
 
-	if (string_set == ETH_SS_STATS)
+	switch (string_set) {
+	case ETH_SS_STATS:
 		for (i = 0; i < EFX_ETHTOOL_NUM_STATS; i++)
 			strncpy(ethtool_strings[i].name,
 				efx_ethtool_stats[i].name,
 				sizeof(ethtool_strings[i].name));
+		break;
+	case ETH_SS_TEST:
+		efx_ethtool_fill_self_tests(efx, NULL,
+					    ethtool_strings, NULL);
+		break;
+	default:
+		/* No other string sets */
+		break;
+	}
 }
 
 static void efx_ethtool_get_stats(struct net_device *net_dev,
@@ -272,6 +442,22 @@ static void efx_ethtool_get_stats(struct net_device *net_dev,
 	}
 }
 
+static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable)
+{
+	int rc;
+
+	/* Our TSO requires TX checksumming, so force TX checksumming
+	 * on when TSO is enabled.
+	 */
+	if (enable) {
+		rc = efx_ethtool_set_tx_csum(net_dev, 1);
+		if (rc)
+			return rc;
+	}
+
+	return ethtool_op_set_tso(net_dev, enable);
+}
+
 static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable)
 {
 	struct efx_nic *efx = net_dev->priv;
@@ -283,6 +469,15 @@ static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable)
 
 	efx_flush_queues(efx);
 
+	/* Our TSO requires TX checksumming, so disable TSO when
+	 * checksumming is disabled
+	 */
+	if (!enable) {
+		rc = efx_ethtool_set_tso(net_dev, 0);
+		if (rc)
+			return rc;
+	}
+
 	return 0;
 }
 
@@ -305,6 +500,64 @@ static u32 efx_ethtool_get_rx_csum(struct net_device *net_dev)
 	return efx->rx_checksum_enabled;
 }
 
+static void efx_ethtool_self_test(struct net_device *net_dev,
+				  struct ethtool_test *test, u64 *data)
+{
+	struct efx_nic *efx = net_dev->priv;
+	struct efx_self_tests efx_tests;
+	int offline, already_up;
+	int rc;
+
+	ASSERT_RTNL();
+	if (efx->state != STATE_RUNNING) {
+		rc = -EIO;
+		goto fail1;
+	}
+
+	/* We need rx buffers and interrupts. */
+	already_up = (efx->net_dev->flags & IFF_UP);
+	if (!already_up) {
+		rc = dev_open(efx->net_dev);
+		if (rc) {
+			EFX_ERR(efx, "failed opening device.\n");
+			goto fail2;
+		}
+	}
+
+	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) {
+		/* Stop the kernel from sending packets during the test. */
+		efx_stop_queue(efx);
+		rc = efx_flush_queues(efx);
+		if (!rc)
+			rc = efx_offline_test(efx, &efx_tests,
+					      efx->loopback_modes);
+		efx_wake_queue(efx);
+	}
+
+ 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");
+
+ fail2:
+ fail1:
+	/* Fill ethtool results structures */
+	efx_ethtool_fill_self_tests(efx, &efx_tests, NULL, data);
+	if (rc)
+		test->flags |= ETH_TEST_FL_FAILED;
+}
+
 /* Restart autonegotiation */
 static int efx_ethtool_nway_reset(struct net_device *net_dev)
 {
@@ -451,8 +704,12 @@ struct ethtool_ops efx_ethtool_ops = {
 	.set_tx_csum		= efx_ethtool_set_tx_csum,
 	.get_sg			= ethtool_op_get_sg,
 	.set_sg			= ethtool_op_set_sg,
+	.get_tso		= ethtool_op_get_tso,
+	.set_tso		= efx_ethtool_set_tso,
 	.get_flags		= ethtool_op_get_flags,
 	.set_flags		= ethtool_op_set_flags,
+	.self_test_count	= efx_ethtool_self_test_count,
+	.self_test		= efx_ethtool_self_test,
 	.get_strings		= efx_ethtool_get_strings,
 	.phys_id		= efx_ethtool_phys_id,
 	.get_stats_count	= efx_ethtool_get_stats_count,

drivers/net/sfc/falcon.c

@@ -1129,6 +1129,7 @@ static void falcon_handle_driver_event(struct efx_channel *channel,
 	case RX_RECOVERY_EV_DECODE:
 		EFX_ERR(efx, "channel %d seen DRIVER RX_RESET event. "
 			"Resetting.\n", channel->channel);
+		atomic_inc(&efx->rx_reset);
 		efx_schedule_reset(efx,
 				   EFX_WORKAROUND_6555(efx) ?
 				   RESET_TYPE_RX_RECOVERY :
@@ -1731,7 +1732,8 @@ void falcon_drain_tx_fifo(struct efx_nic *efx)
 	efx_oword_t temp;
 	int count;
 
-	if (FALCON_REV(efx) < FALCON_REV_B0)
+	if ((FALCON_REV(efx) < FALCON_REV_B0) ||
+	    (efx->loopback_mode != LOOPBACK_NONE))
 		return;
 
 	falcon_read(efx, &temp, MAC0_CTRL_REG_KER);
@@ -2091,6 +2093,8 @@ static int falcon_probe_phy(struct efx_nic *efx)
 			efx->phy_type);
 		return -1;
 	}
+
+	efx->loopback_modes = LOOPBACKS_10G_INTERNAL | efx->phy_op->loopbacks;
 	return 0;
 }
 
@@ -2468,14 +2472,12 @@ int falcon_probe_nic(struct efx_nic *efx)
  fail5:
 	falcon_free_buffer(efx, &efx->irq_status);
  fail4:
-	/* fall-thru */
  fail3:
 	if (nic_data->pci_dev2) {
 		pci_dev_put(nic_data->pci_dev2);
 		nic_data->pci_dev2 = NULL;
 	}
  fail2:
-	/* fall-thru */
  fail1:
 	kfree(efx->nic_data);
 	return rc;

drivers/net/sfc/falcon_hwdefs.h

@@ -636,6 +636,14 @@
 #define XX_HIDRVA_WIDTH 1
 #define XX_LODRVA_LBN 8
 #define XX_LODRVA_WIDTH 1
+#define XX_LPBKD_LBN 3
+#define XX_LPBKD_WIDTH 1
+#define XX_LPBKC_LBN 2
+#define XX_LPBKC_WIDTH 1
+#define XX_LPBKB_LBN 1
+#define XX_LPBKB_WIDTH 1
+#define XX_LPBKA_LBN 0
+#define XX_LPBKA_WIDTH 1
 
 #define XX_TXDRV_CTL_REG_MAC 0x12
 #define XX_DEQD_LBN 28
@@ -656,8 +664,14 @@
 #define XX_DTXA_WIDTH 4
 
 /* XAUI XGXS core status register */
-#define XX_FORCE_SIG_DECODE_FORCED 0xff
 #define XX_CORE_STAT_REG_MAC 0x16
+#define XX_FORCE_SIG_LBN 24
+#define XX_FORCE_SIG_WIDTH 8
+#define XX_FORCE_SIG_DECODE_FORCED 0xff
+#define XX_XGXS_LB_EN_LBN 23
+#define XX_XGXS_LB_EN_WIDTH 1
+#define XX_XGMII_LB_EN_LBN 22
+#define XX_XGMII_LB_EN_WIDTH 1
 #define XX_ALIGN_DONE_LBN 20
 #define XX_ALIGN_DONE_WIDTH 1
 #define XX_SYNC_STAT_LBN 16

drivers/net/sfc/falcon_xmac.c

@@ -32,7 +32,7 @@
 	(FALCON_XMAC_REGBANK + ((mac_reg) * FALCON_XMAC_REG_SIZE))
 
 void falcon_xmac_writel(struct efx_nic *efx,
-			efx_dword_t *value, unsigned int mac_reg)
+			 efx_dword_t *value, unsigned int mac_reg)
 {
 	efx_oword_t temp;
 
@@ -69,6 +69,10 @@ static int falcon_reset_xmac(struct efx_nic *efx)
 		udelay(10);
 	}
 
+	/* This often fails when DSP is disabled, ignore it */
+	if (sfe4001_phy_flash_cfg != 0)
+		return 0;
+
 	EFX_ERR(efx, "timed out waiting for XMAC core reset\n");
 	return -ETIMEDOUT;
 }
@@ -223,7 +227,7 @@ static int falcon_xgmii_status(struct efx_nic *efx)
 	/* The ISR latches, so clear it and re-read */
 	falcon_xmac_readl(efx, &reg, XM_MGT_INT_REG_MAC_B0);
 	falcon_xmac_readl(efx, &reg, XM_MGT_INT_REG_MAC_B0);
-	
+
 	if (EFX_DWORD_FIELD(reg, XM_LCLFLT) ||
 	    EFX_DWORD_FIELD(reg, XM_RMTFLT)) {
 		EFX_INFO(efx, "MGT_INT: "EFX_DWORD_FMT"\n", EFX_DWORD_VAL(reg));
@@ -237,7 +241,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, int enable)
 {
 	efx_dword_t reg;
 
-	if (FALCON_REV(efx) < FALCON_REV_B0)
+	if ((FALCON_REV(efx) < FALCON_REV_B0) || LOOPBACK_INTERNAL(efx))
 		return;
 
 	/* Flush the ISR */
@@ -284,6 +288,9 @@ int falcon_xaui_link_ok(struct efx_nic *efx)
 	efx_dword_t reg;
 	int align_done, sync_status, link_ok = 0;
 
+	if (LOOPBACK_INTERNAL(efx))
+		return 1;
+
 	/* Read link status */
 	falcon_xmac_readl(efx, &reg, XX_CORE_STAT_REG_MAC);
 
@@ -374,6 +381,61 @@ static void falcon_reconfigure_xmac_core(struct efx_nic *efx)
 	falcon_xmac_writel(efx, &reg, XM_ADR_HI_REG_MAC);
 }
 
+static void falcon_reconfigure_xgxs_core(struct efx_nic *efx)
+{
+	efx_dword_t reg;
+	int xgxs_loopback = (efx->loopback_mode == LOOPBACK_XGXS) ? 1 : 0;
+	int xaui_loopback = (efx->loopback_mode == LOOPBACK_XAUI) ? 1 : 0;
+	int xgmii_loopback =
+		(efx->loopback_mode == LOOPBACK_XGMII) ? 1 : 0;
+
+	/* XGXS block is flaky and will need to be reset if moving
+	 * into our out of XGMII, XGXS or XAUI loopbacks. */
+	if (EFX_WORKAROUND_5147(efx)) {
+		int old_xgmii_loopback, old_xgxs_loopback, old_xaui_loopback;
+		int reset_xgxs;
+
+		falcon_xmac_readl(efx, &reg, XX_CORE_STAT_REG_MAC);
+		old_xgxs_loopback = EFX_DWORD_FIELD(reg, XX_XGXS_LB_EN);
+		old_xgmii_loopback = EFX_DWORD_FIELD(reg, XX_XGMII_LB_EN);
+
+		falcon_xmac_readl(efx, &reg, XX_SD_CTL_REG_MAC);
+		old_xaui_loopback = EFX_DWORD_FIELD(reg, XX_LPBKA);
+
+		/* The PHY driver may have turned XAUI off */
+		reset_xgxs = ((xgxs_loopback != old_xgxs_loopback) ||
+			      (xaui_loopback != old_xaui_loopback) ||
+			      (xgmii_loopback != old_xgmii_loopback));
+		if (reset_xgxs) {
+			falcon_xmac_readl(efx, &reg, XX_PWR_RST_REG_MAC);
+			EFX_SET_DWORD_FIELD(reg, XX_RSTXGXSTX_EN, 1);
+			EFX_SET_DWORD_FIELD(reg, XX_RSTXGXSRX_EN, 1);
+			falcon_xmac_writel(efx, &reg, XX_PWR_RST_REG_MAC);
+			udelay(1);
+			EFX_SET_DWORD_FIELD(reg, XX_RSTXGXSTX_EN, 0);
+			EFX_SET_DWORD_FIELD(reg, XX_RSTXGXSRX_EN, 0);
+			falcon_xmac_writel(efx, &reg, XX_PWR_RST_REG_MAC);
+			udelay(1);
+		}
+	}
+
+	falcon_xmac_readl(efx, &reg, XX_CORE_STAT_REG_MAC);
+	EFX_SET_DWORD_FIELD(reg, XX_FORCE_SIG,
+			    (xgxs_loopback || xaui_loopback) ?
+			    XX_FORCE_SIG_DECODE_FORCED : 0);
+	EFX_SET_DWORD_FIELD(reg, XX_XGXS_LB_EN, xgxs_loopback);
+	EFX_SET_DWORD_FIELD(reg, XX_XGMII_LB_EN, xgmii_loopback);
+	falcon_xmac_writel(efx, &reg, XX_CORE_STAT_REG_MAC);
+
+	falcon_xmac_readl(efx, &reg, XX_SD_CTL_REG_MAC);
+	EFX_SET_DWORD_FIELD(reg, XX_LPBKD, xaui_loopback);
+	EFX_SET_DWORD_FIELD(reg, XX_LPBKC, xaui_loopback);
+	EFX_SET_DWORD_FIELD(reg, XX_LPBKB, xaui_loopback);
+	EFX_SET_DWORD_FIELD(reg, XX_LPBKA, xaui_loopback);
+	falcon_xmac_writel(efx, &reg, XX_SD_CTL_REG_MAC);
+}
+
+
 /* 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 int falcon_check_xaui_link_up(struct efx_nic *efx)
@@ -382,7 +444,8 @@ static int falcon_check_xaui_link_up(struct efx_nic *efx)
 	tries = EFX_WORKAROUND_5147(efx) ? 5 : 1;
 	max_tries = tries;
 
-	if (efx->phy_type == PHY_TYPE_NONE)
+	if ((efx->loopback_mode == LOOPBACK_NETWORK) ||
+	    (efx->phy_type == PHY_TYPE_NONE))
 		return 0;
 
 	while (tries) {
@@ -408,8 +471,13 @@ void falcon_reconfigure_xmac(struct efx_nic *efx)
 	falcon_mask_status_intr(efx, 0);
 
 	falcon_deconfigure_mac_wrapper(efx);
+
+	efx->tx_disabled = LOOPBACK_INTERNAL(efx);
 	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 */
@@ -491,13 +559,15 @@ void falcon_update_stats_xmac(struct efx_nic *efx)
 		(mac_stats->rx_bytes - mac_stats->rx_good_bytes);
 }
 
-#define EFX_XAUI_RETRAIN_MAX 8
-
 int falcon_check_xmac(struct efx_nic *efx)
 {
 	unsigned xaui_link_ok;
 	int rc;
 
+	if ((efx->loopback_mode == LOOPBACK_NETWORK) ||
+	    (efx->phy_type == PHY_TYPE_NONE))
+		return 0;
+
 	falcon_mask_status_intr(efx, 0);
 	xaui_link_ok = falcon_xaui_link_ok(efx);
 

drivers/net/sfc/mdio_10g.c

@@ -44,6 +44,9 @@ static int mdio_clause45_check_mmd(struct efx_nic *efx, int mmd,
 	int status;
 	int phy_id = efx->mii.phy_id;
 
+	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) &
@@ -164,6 +167,22 @@ int mdio_clause45_links_ok(struct efx_nic *efx, unsigned int mmd_mask)
 	int mmd = 0;
 	int good;
 
+	/* If the port is in loopback, then we should only consider a subset
+	 * of mmd's */
+	if (LOOPBACK_INTERNAL(efx))
+		return 1;
+	else if (efx->loopback_mode == LOOPBACK_NETWORK)
+		return 0;
+	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_PMAPMD)
+		mmd_mask &= ~MDIO_MMDREG_DEVS0_PMAPMD;
+
 	while (mmd_mask) {
 		if (mmd_mask & 1) {
 			/* Double reads because link state is latched, and a
@@ -182,6 +201,65 @@ int mdio_clause45_links_ok(struct efx_nic *efx, unsigned int mmd_mask)
 	return ok;
 }
 
+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->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);
+}
+
+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);
+
+	if (ctrl1 != ctrl2)
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PMAPMD,
+				    MDIO_MMDREG_CTRL1, ctrl2);
+
+	/* 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);
+
+	if (ctrl1 != ctrl2)
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PCS,
+				    MDIO_MMDREG_CTRL1, ctrl2);
+
+	/* 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);
+
+	if (ctrl1 != ctrl2)
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PHYXS,
+				    MDIO_MMDREG_CTRL1, ctrl2);
+}
+
 /**
  * mdio_clause45_get_settings - Read (some of) the PHY settings over MDIO.
  * @efx:		Efx NIC

drivers/net/sfc/mdio_10g.h

@@ -44,11 +44,16 @@
 #define MDIO_MMDREG_DEVS1	(6)
 #define MDIO_MMDREG_CTRL2	(7)
 #define MDIO_MMDREG_STAT2	(8)
+#define MDIO_MMDREG_TXDIS	(9)
 
 /* Bits in MMDREG_CTRL1 */
 /* Reset */
 #define MDIO_MMDREG_CTRL1_RESET_LBN	(15)
 #define MDIO_MMDREG_CTRL1_RESET_WIDTH	(1)
+/* Loopback */
+/* Loopback bit for WIS, PCS, PHYSX and DTEXS */
+#define MDIO_MMDREG_CTRL1_LBACK_LBN	(14)
+#define MDIO_MMDREG_CTRL1_LBACK_WIDTH	(1)
 
 /* Bits in MMDREG_STAT1 */
 #define MDIO_MMDREG_STAT1_FAULT_LBN	(7)
@@ -56,6 +61,9 @@
 /* Link state */
 #define MDIO_MMDREG_STAT1_LINK_LBN	(2)
 #define MDIO_MMDREG_STAT1_LINK_WIDTH	(1)
+/* Low power ability */
+#define MDIO_MMDREG_STAT1_LPABLE_LBN	(1)
+#define MDIO_MMDREG_STAT1_LPABLE_WIDTH	(1)
 
 /* Bits in ID reg */
 #define MDIO_ID_REV(_id32)	(_id32 & 0xf)
@@ -76,6 +84,14 @@
 #define MDIO_MMDREG_STAT2_PRESENT_LBN	(14)
 #define MDIO_MMDREG_STAT2_PRESENT_WIDTH (2)
 
+/* Bits in MMDREG_TXDIS */
+#define MDIO_MMDREG_TXDIS_GLOBAL_LBN    (0)
+#define MDIO_MMDREG_TXDIS_GLOBAL_WIDTH  (1)
+
+/* MMD-specific bits, ordered by MMD, then register */
+#define MDIO_PMAPMD_CTRL1_LBACK_LBN	(0)
+#define MDIO_PMAPMD_CTRL1_LBACK_WIDTH	(1)
+
 /* PMA type (4 bits) */
 #define MDIO_PMAPMD_CTRL2_10G_CX4	(0x0)
 #define MDIO_PMAPMD_CTRL2_10G_EW	(0x1)
@@ -95,7 +111,7 @@
 #define MDIO_PMAPMD_CTRL2_10_BT		(0xf)
 #define MDIO_PMAPMD_CTRL2_TYPE_MASK	(0xf)
 
-/* /\* PHY XGXS lane state *\/ */
+/* PHY XGXS lane state */
 #define MDIO_PHYXS_LANE_STATE		(0x18)
 #define MDIO_PHYXS_LANE_ALIGNED_LBN	(12)
 
@@ -217,6 +233,12 @@ int mdio_clause45_check_mmds(struct efx_nic *efx,
 extern int mdio_clause45_links_ok(struct efx_nic *efx,
 				  unsigned int mmd_mask);
 
+/* Generic transmit disable support though PMAPMD */
+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);
+
 /* Read (some of) the PHY settings over MDIO */
 extern void mdio_clause45_get_settings(struct efx_nic *efx,
 				       struct ethtool_cmd *ecmd);

drivers/net/sfc/net_driver.h

@@ -134,6 +134,8 @@ struct efx_special_buffer {
  *	Set only on the final fragment of a packet; %NULL for all other
  *	fragments.  When this fragment completes, then we can free this
  *	skb.
+ * @tsoh: The associated TSO header structure, or %NULL if this
+ *	buffer is not a TSO header.
  * @dma_addr: DMA address of the fragment.
  * @len: Length of this fragment.
  *	This field is zero when the queue slot is empty.
@@ -144,6 +146,7 @@ struct efx_special_buffer {
  */
 struct efx_tx_buffer {
 	const struct sk_buff *skb;
+	struct efx_tso_header *tsoh;
 	dma_addr_t dma_addr;
 	unsigned short len;
 	unsigned char continuation;
@@ -187,6 +190,13 @@ struct efx_tx_buffer {
  *	variable indicates that the queue is full.  This is to
  *	avoid cache-line ping-pong between the xmit path and the
  *	completion path.
+ * @tso_headers_free: A list of TSO headers allocated for this TX queue
+ *	that are not in use, and so available for new TSO sends. The list
+ *	is protected by the TX queue lock.
+ * @tso_bursts: Number of times TSO xmit invoked by kernel
+ * @tso_long_headers: Number of packets with headers too long for standard
+ *	blocks
+ * @tso_packets: Number of packets via the TSO xmit path
  */
 struct efx_tx_queue {
 	/* Members which don't change on the fast path */
@@ -206,6 +216,10 @@ struct efx_tx_queue {
 	unsigned int insert_count ____cacheline_aligned_in_smp;
 	unsigned int write_count;
 	unsigned int old_read_count;
+	struct efx_tso_header *tso_headers_free;
+	unsigned int tso_bursts;
+	unsigned int tso_long_headers;
+	unsigned int tso_packets;
 };
 
 /**
@@ -434,6 +448,9 @@ struct efx_board {
 	struct efx_blinker blinker;
 };
 
+#define STRING_TABLE_LOOKUP(val, member)	\
+	member ## _names[val]
+
 enum efx_int_mode {
 	/* Be careful if altering to correct macro below */
 	EFX_INT_MODE_MSIX = 0,
@@ -506,6 +523,7 @@ enum efx_fc_type {
  * @check_hw: Check hardware
  * @reset_xaui: Reset XAUI side of PHY for (software sequenced reset)
  * @mmds: MMD presence mask
+ * @loopbacks: Supported loopback modes mask
  */
 struct efx_phy_operations {
 	int (*init) (struct efx_nic *efx);
@@ -515,6 +533,7 @@ struct efx_phy_operations {
 	int (*check_hw) (struct efx_nic *efx);
 	void (*reset_xaui) (struct efx_nic *efx);
 	int mmds;
+	unsigned loopbacks;
 };
 
 /*
@@ -653,7 +672,6 @@ union efx_multicast_hash {
  * @phy_op: PHY interface
  * @phy_data: PHY private data (including PHY-specific stats)
  * @mii: PHY interface
- * @phy_powered: PHY power state
  * @tx_disabled: PHY transmitter turned off
  * @link_up: Link status
  * @link_options: Link options (MII/GMII format)
@@ -662,6 +680,9 @@ union efx_multicast_hash {
  * @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
+ * @loopback_mode: Loopback status
+ * @loopback_modes: Supported loopback mode bitmask
+ * @loopback_selftest: Offline self-test private state
  *
  * The @priv field of the corresponding &struct net_device points to
  * this.
@@ -721,6 +742,7 @@ struct efx_nic {
 	struct efx_phy_operations *phy_op;
 	void *phy_data;
 	struct mii_if_info mii;
+	unsigned tx_disabled;
 
 	int link_up;
 	unsigned int link_options;
@@ -732,6 +754,10 @@ struct efx_nic {
 	struct work_struct reconfigure_work;
 
 	atomic_t rx_reset;
+	enum efx_loopback_mode loopback_mode;
+	unsigned int loopback_modes;
+
+	void *loopback_selftest;
 };
 
 /**

drivers/net/sfc/rx.c

@@ -19,6 +19,7 @@
 #include "rx.h"
 #include "efx.h"
 #include "falcon.h"
+#include "selftest.h"
 #include "workarounds.h"
 
 /* Number of RX descriptors pushed at once. */
@@ -683,6 +684,15 @@ void __efx_rx_packet(struct efx_channel *channel,
 	struct sk_buff *skb;
 	int lro = efx->net_dev->features & NETIF_F_LRO;
 
+	/* If we're in loopback test, then pass the packet directly to the
+	 * loopback layer, and free the rx_buf here
+	 */
+	if (unlikely(efx->loopback_selftest)) {
+		efx_loopback_rx_packet(efx, rx_buf->data, rx_buf->len);
+		efx_free_rx_buffer(efx, rx_buf);
+		goto done;
+	}
+
 	if (rx_buf->skb) {
 		prefetch(skb_shinfo(rx_buf->skb));
 
@@ -736,7 +746,6 @@ void __efx_rx_packet(struct efx_channel *channel,
 	/* Update allocation strategy method */
 	channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
 
-	/* fall-thru */
 done:
 	efx->net_dev->last_rx = jiffies;
 }

drivers/net/sfc/selftest.h

+/****************************************************************************
+ * 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.
+ */
+
+#ifndef EFX_SELFTEST_H
+#define EFX_SELFTEST_H
+
+#include "net_driver.h"
+
+/*
+ * Self tests
+ */
+
+struct efx_loopback_self_tests {
+	int tx_sent[EFX_MAX_TX_QUEUES];
+	int tx_done[EFX_MAX_TX_QUEUES];
+	int rx_good;
+	int rx_bad;
+};
+
+/* Efx self test results
+ * For fields which are not counters, 1 indicates success and -1
+ * indicates failure.
+ */
+struct efx_self_tests {
+	int interrupt;
+	int eventq_dma[EFX_MAX_CHANNELS];
+	int eventq_int[EFX_MAX_CHANNELS];
+	int eventq_poll[EFX_MAX_CHANNELS];
+	int phy_ok;
+	int loopback_speed;
+	int loopback_full_duplex;
+	struct efx_loopback_self_tests loopback[LOOPBACK_TEST_MAX];
+};
+
+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);
+
+#endif /* EFX_SELFTEST_H */

drivers/net/sfc/sfe4001.c

@@ -130,6 +130,15 @@ void sfe4001_poweroff(struct efx_nic *efx)
 	(void) efx_i2c_read(i2c, MAX6647, RSL, &in, 1);
 }
 
+/* The P0_EN_3V3X line on SFE4001 boards (from A2 onward) is connected
+ * to the FLASH_CFG_1 input on the DSP.  We must keep it high at power-
+ * up to allow writing the flash (done through MDIO from userland).
+ */
+unsigned int sfe4001_phy_flash_cfg;
+module_param_named(phy_flash_cfg, sfe4001_phy_flash_cfg, uint, 0444);
+MODULE_PARM_DESC(phy_flash_cfg,
+		 "Force PHY to enter flash configuration mode");
+
 /* 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
@@ -203,6 +212,8 @@ int sfe4001_poweron(struct efx_nic *efx)
 		out = 0xff & ~((1 << P0_EN_1V2_LBN) | (1 << P0_EN_2V5_LBN) |
 			       (1 << P0_EN_3V3X_LBN) | (1 << P0_EN_5V_LBN) |
 			       (1 << P0_X_TRST_LBN));
+		if (sfe4001_phy_flash_cfg)
+			out |= 1 << P0_EN_3V3X_LBN;
 
 		rc = efx_i2c_write(i2c, PCA9539, P0_OUT, &out, 1);
 		if (rc)
@@ -226,6 +237,9 @@ int sfe4001_poweron(struct efx_nic *efx)
 		if (in & (1 << P1_AFE_PWD_LBN))
 			goto done;
 
+		/* DSP doesn't look powered in flash config mode */
+		if (sfe4001_phy_flash_cfg)
+			goto done;
 	} while (++count < 20);
 
 	EFX_INFO(efx, "timed out waiting for power\n");

drivers/net/sfc/tenxpress.c

@@ -24,6 +24,11 @@
 				 MDIO_MMDREG_DEVS0_PCS    | \
 				 MDIO_MMDREG_DEVS0_PHYXS)
 
+#define TENXPRESS_LOOPBACKS ((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)
  */
@@ -72,6 +77,10 @@
 #define PMA_PMD_BIST_RXD_LBN	(1)
 #define PMA_PMD_BIST_AFE_LBN	(0)
 
+/* Special Software reset register */
+#define PMA_PMD_EXT_CTRL_REG 49152
+#define PMA_PMD_EXT_SSR_LBN 15
+
 #define BIST_MAX_DELAY	(1000)
 #define BIST_POLL_DELAY	(10)
 
@@ -86,6 +95,11 @@
 #define	PCS_TEST_SELECT_REG 0xd807	/* PRM 10.5.8 */
 #define	CLK312_EN_LBN 3
 
+/* PHYXS registers */
+#define PHYXS_TEST1         (49162)
+#define LOOPBACK_NEAR_LBN   (8)
+#define LOOPBACK_NEAR_WIDTH (1)
+
 /* Boot status register */
 #define PCS_BOOT_STATUS_REG	(0xd000)
 #define PCS_BOOT_FATAL_ERR_LBN	(0)
@@ -106,7 +120,9 @@ MODULE_PARM_DESC(crc_error_reset_threshold,
 
 struct tenxpress_phy_data {
 	enum tenxpress_state state;
+	enum efx_loopback_mode loopback_mode;
 	atomic_t bad_crc_count;
+	int tx_disabled;
 	int bad_lp_tries;
 };
 
@@ -199,10 +215,12 @@ static int tenxpress_phy_init(struct efx_nic *efx)
 
 	tenxpress_set_state(efx, TENXPRESS_STATUS_NORMAL);
 
-	rc = mdio_clause45_wait_reset_mmds(efx,
-					   TENXPRESS_REQUIRED_DEVS);
-	if (rc < 0)
-		goto fail;
+	if (!sfe4001_phy_flash_cfg) {
+		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)
@@ -225,6 +243,35 @@ static int tenxpress_phy_init(struct efx_nic *efx)
 	return rc;
 }
 
+static int tenxpress_special_reset(struct efx_nic *efx)
+{
+	int rc, reg;
+
+	EFX_TRACE(efx, "%s\n", __func__);
+
+	/* Initiate reset */
+	reg = mdio_clause45_read(efx, efx->mii.phy_id,
+				 MDIO_MMD_PMAPMD, PMA_PMD_EXT_CTRL_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);
+
+	msleep(200);
+
+	/* Wait for the blocks to come out of reset */
+	rc = mdio_clause45_wait_reset_mmds(efx,
+					   TENXPRESS_REQUIRED_DEVS);
+	if (rc < 0)
+		return rc;
+
+	/* Try and reconfigure the device */
+	rc = tenxpress_init(efx);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
 static void tenxpress_set_bad_lp(struct efx_nic *efx, int bad_lp)
 {
 	struct tenxpress_phy_data *pd = efx->phy_data;
@@ -299,11 +346,46 @@ static int tenxpress_link_ok(struct efx_nic *efx, int check_lp)
 	return ok;
 }
 
+static void tenxpress_phyxs_loopback(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);
+	else
+		ctrl2 &= ~(1 << LOOPBACK_NEAR_LBN);
+	if (ctrl1 != ctrl2)
+		mdio_clause45_write(efx, phy_id, MDIO_MMD_PHYXS,
+				    PHYXS_TEST1, ctrl2);
+}
+
 static void tenxpress_phy_reconfigure(struct efx_nic *efx)
 {
+	struct tenxpress_phy_data *phy_data = efx->phy_data;
+	int loop_change = LOOPBACK_OUT_OF(phy_data, efx,
+					  TENXPRESS_LOOPBACKS);
+
 	if (!tenxpress_state_is(efx, TENXPRESS_STATUS_NORMAL))
 		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 ((phy_data->tx_disabled && !efx->tx_disabled) ||
+	    loop_change) {
+		(void) tenxpress_special_reset(efx);
+		falcon_reset_xaui(efx);
+	}
+
+	mdio_clause45_transmit_disable(efx);
+	mdio_clause45_phy_reconfigure(efx);
+	tenxpress_phyxs_loopback(efx);
+
+	phy_data->tx_disabled = efx->tx_disabled;
+	phy_data->loopback_mode = efx->loopback_mode;
 	efx->link_up = tenxpress_link_ok(efx, 0);
 	efx->link_options = GM_LPA_10000FULL;
 }
@@ -431,4 +513,5 @@ struct efx_phy_operations falcon_tenxpress_phy_ops = {
 	.clear_interrupt  = tenxpress_phy_clear_interrupt,
 	.reset_xaui       = tenxpress_reset_xaui,
 	.mmds             = TENXPRESS_REQUIRED_DEVS,
+	.loopbacks        = TENXPRESS_LOOPBACKS,
 };

drivers/net/sfc/xfp_phy.c

@@ -24,6 +24,10 @@
 			   MDIO_MMDREG_DEVS0_PMAPMD |	\
 			   MDIO_MMDREG_DEVS0_PHYXS)
 
+#define XFP_LOOPBACKS ((1 << LOOPBACK_PCS) |		\
+		       (1 << LOOPBACK_PMAPMD) |		\
+		       (1 << LOOPBACK_NETWORK))
+
 /****************************************************************************/
 /* Quake-specific MDIO registers */
 #define MDIO_QUAKE_LED0_REG	(0xD006)
@@ -35,6 +39,10 @@ void xfp_set_led(struct efx_nic *p, int led, int mode)
 			    mode);
 }
 
+struct xfp_phy_data {
+	int tx_disabled;
+};
+
 #define XFP_MAX_RESET_TIME 500
 #define XFP_RESET_WAIT 10
 
@@ -72,18 +80,31 @@ static int xfp_reset_phy(struct efx_nic *efx)
 
 static int xfp_phy_init(struct efx_nic *efx)
 {
+	struct xfp_phy_data *phy_data;
 	u32 devid = mdio_clause45_read_id(efx, MDIO_MMD_PHYXS);
 	int rc;
 
+	phy_data = kzalloc(sizeof(struct xfp_phy_data), GFP_KERNEL);
+	efx->phy_data = (void *) phy_data;
+
 	EFX_INFO(efx, "XFP: PHY ID reg %x (OUI %x model %x revision"
 		 " %x)\n", devid, MDIO_ID_OUI(devid), MDIO_ID_MODEL(devid),
 		 MDIO_ID_REV(devid));
 
+	phy_data->tx_disabled = efx->tx_disabled;
+
 	rc = xfp_reset_phy(efx);
 
 	EFX_INFO(efx, "XFP: PHY init %s.\n",
 		 rc ? "failed" : "successful");
+	if (rc < 0)
+		goto fail;
 
+	return 0;
+
+ fail:
+	kfree(efx->phy_data);
+	efx->phy_data = NULL;
 	return rc;
 }
 
@@ -110,6 +131,16 @@ static int xfp_phy_check_hw(struct efx_nic *efx)
 
 static void xfp_phy_reconfigure(struct efx_nic *efx)
 {
+	struct xfp_phy_data *phy_data = efx->phy_data;
+
+	/* Reset the PHY when moving from tx off to tx on */
+	if (phy_data->tx_disabled && !efx->tx_disabled)
+		xfp_reset_phy(efx);
+
+	mdio_clause45_transmit_disable(efx);
+	mdio_clause45_phy_reconfigure(efx);
+
+	phy_data->tx_disabled = efx->tx_disabled;
 	efx->link_up = xfp_link_ok(efx);
 	efx->link_options = GM_LPA_10000FULL;
 }
@@ -119,6 +150,10 @@ static void xfp_phy_fini(struct efx_nic *efx)
 {
 	/* Clobber the LED if it was blinking */
 	efx->board_info.blink(efx, 0);
+
+	/* Free the context block */
+	kfree(efx->phy_data);
+	efx->phy_data = NULL;
 }
 
 struct efx_phy_operations falcon_xfp_phy_ops = {
@@ -129,4 +164,5 @@ struct efx_phy_operations falcon_xfp_phy_ops = {
 	.clear_interrupt = xfp_phy_clear_interrupt,
 	.reset_xaui      = efx_port_dummy_op_void,
 	.mmds            = XFP_REQUIRED_DEVS,
+	.loopbacks       = XFP_LOOPBACKS,
 };

drivers/net/sky2.h

@@ -1966,13 +1966,13 @@ struct sky2_status_le {
 struct tx_ring_info {
 	struct sk_buff	*skb;
 	DECLARE_PCI_UNMAP_ADDR(mapaddr);
-	DECLARE_PCI_UNMAP_ADDR(maplen);
+	DECLARE_PCI_UNMAP_LEN(maplen);
 };
 
 struct rx_ring_info {
 	struct sk_buff	*skb;
 	dma_addr_t	data_addr;
-	DECLARE_PCI_UNMAP_ADDR(data_size);
+	DECLARE_PCI_UNMAP_LEN(data_size);
 	dma_addr_t	frag_addr[ETH_JUMBO_MTU >> PAGE_SHIFT];
 };