Merge branch 'master' into for-next

Merge with latest Linus' tree, as I have incoming patches
that fix code that is newer than current HEAD of for-next.

Conflicts:
	drivers/net/ethernet/realtek/r8169.c
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 7f06508..a2d39d2 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -29,7 +29,6 @@
 #include <linux/pci-aspm.h>
 #include <linux/prefetch.h>
 
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
@@ -255,10 +254,6 @@
 	RTL_CFG_2
 };
 
-static void rtl_hw_start_8169(struct net_device *);
-static void rtl_hw_start_8168(struct net_device *);
-static void rtl_hw_start_8101(struct net_device *);
-
 static DEFINE_PCI_DEVICE_TABLE(rtl8169_pci_tbl) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
@@ -667,12 +662,25 @@
 	__le16	tx_underun;
 };
 
+enum rtl_flag {
+	RTL_FLAG_TASK_ENABLED,
+	RTL_FLAG_TASK_SLOW_PENDING,
+	RTL_FLAG_TASK_RESET_PENDING,
+	RTL_FLAG_TASK_PHY_PENDING,
+	RTL_FLAG_MAX
+};
+
+struct rtl8169_stats {
+	u64			packets;
+	u64			bytes;
+	struct u64_stats_sync	syncp;
+};
+
 struct rtl8169_private {
 	void __iomem *mmio_addr;	/* memory map physical address */
 	struct pci_dev *pci_dev;
 	struct net_device *dev;
 	struct napi_struct napi;
-	spinlock_t lock;
 	u32 msg_enable;
 	u16 txd_version;
 	u16 mac_version;
@@ -680,6 +688,8 @@
 	u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */
 	u32 dirty_rx;
 	u32 dirty_tx;
+	struct rtl8169_stats rx_stats;
+	struct rtl8169_stats tx_stats;
 	struct TxDesc *TxDescArray;	/* 256-aligned Tx descriptor ring */
 	struct RxDesc *RxDescArray;	/* 256-aligned Rx descriptor ring */
 	dma_addr_t TxPhyAddr;
@@ -688,9 +698,8 @@
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
 	struct timer_list timer;
 	u16 cp_cmd;
-	u16 intr_event;
-	u16 napi_event;
-	u16 intr_mask;
+
+	u16 event_slow;
 
 	struct mdio_ops {
 		void (*write)(void __iomem *, int, int);
@@ -714,7 +723,13 @@
 	unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
 	unsigned int (*link_ok)(void __iomem *);
 	int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd);
-	struct delayed_work task;
+
+	struct {
+		DECLARE_BITMAP(flags, RTL_FLAG_MAX);
+		struct mutex mutex;
+		struct work_struct work;
+	} wk;
+
 	unsigned features;
 
 	struct mii_if_info mii;
@@ -754,22 +769,15 @@
 MODULE_FIRMWARE(FIRMWARE_8168F_1);
 MODULE_FIRMWARE(FIRMWARE_8168F_2);
 
-static int rtl8169_open(struct net_device *dev);
-static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
-				      struct net_device *dev);
-static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance);
-static int rtl8169_init_ring(struct net_device *dev);
-static void rtl_hw_start(struct net_device *dev);
-static int rtl8169_close(struct net_device *dev);
-static void rtl_set_rx_mode(struct net_device *dev);
-static void rtl8169_tx_timeout(struct net_device *dev);
-static struct net_device_stats *rtl8169_get_stats(struct net_device *dev);
-static int rtl8169_rx_interrupt(struct net_device *, struct rtl8169_private *,
-				void __iomem *, u32 budget);
-static int rtl8169_change_mtu(struct net_device *dev, int new_mtu);
-static void rtl8169_down(struct net_device *dev);
-static void rtl8169_rx_clear(struct rtl8169_private *tp);
-static int rtl8169_poll(struct napi_struct *napi, int budget);
+static void rtl_lock_work(struct rtl8169_private *tp)
+{
+	mutex_lock(&tp->wk.mutex);
+}
+
+static void rtl_unlock_work(struct rtl8169_private *tp)
+{
+	mutex_unlock(&tp->wk.mutex);
+}
 
 static void rtl_tx_performance_tweak(struct pci_dev *pdev, u16 force)
 {
@@ -1180,12 +1188,51 @@
 	return value;
 }
 
+static u16 rtl_get_events(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	return RTL_R16(IntrStatus);
+}
+
+static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	RTL_W16(IntrStatus, bits);
+	mmiowb();
+}
+
+static void rtl_irq_disable(struct rtl8169_private *tp)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	RTL_W16(IntrMask, 0);
+	mmiowb();
+}
+
+static void rtl_irq_enable(struct rtl8169_private *tp, u16 bits)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	RTL_W16(IntrMask, bits);
+}
+
+#define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
+#define RTL_EVENT_NAPI_TX	(TxOK | TxErr)
+#define RTL_EVENT_NAPI		(RTL_EVENT_NAPI_RX | RTL_EVENT_NAPI_TX)
+
+static void rtl_irq_enable_all(struct rtl8169_private *tp)
+{
+	rtl_irq_enable(tp, RTL_EVENT_NAPI | tp->event_slow);
+}
+
 static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	RTL_W16(IntrMask, 0x0000);
-	RTL_W16(IntrStatus, tp->intr_event);
+	rtl_irq_disable(tp);
+	rtl_ack_events(tp, RTL_EVENT_NAPI | tp->event_slow);
 	RTL_R8(ChipCmd);
 }
 
@@ -1276,9 +1323,6 @@
 					struct rtl8169_private *tp,
 					void __iomem *ioaddr, bool pm)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&tp->lock, flags);
 	if (tp->link_ok(ioaddr)) {
 		rtl_link_chg_patch(tp);
 		/* This is to cancel a scheduled suspend if there's one. */
@@ -1293,7 +1337,6 @@
 		if (pm)
 			pm_schedule_suspend(&tp->pci_dev->dev, 5000);
 	}
-	spin_unlock_irqrestore(&tp->lock, flags);
 }
 
 static void rtl8169_check_link_status(struct net_device *dev,
@@ -1336,12 +1379,12 @@
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	spin_lock_irq(&tp->lock);
+	rtl_lock_work(tp);
 
 	wol->supported = WAKE_ANY;
 	wol->wolopts = __rtl8169_get_wol(tp);
 
-	spin_unlock_irq(&tp->lock);
+	rtl_unlock_work(tp);
 }
 
 static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
@@ -1378,14 +1421,15 @@
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	spin_lock_irq(&tp->lock);
+	rtl_lock_work(tp);
 
 	if (wol->wolopts)
 		tp->features |= RTL_FEATURE_WOL;
 	else
 		tp->features &= ~RTL_FEATURE_WOL;
 	__rtl8169_set_wol(tp, wol->wolopts);
-	spin_unlock_irq(&tp->lock);
+
+	rtl_unlock_work(tp);
 
 	device_set_wakeup_enable(&tp->pci_dev->dev, wol->wolopts);
 
@@ -1540,15 +1584,14 @@
 static int rtl8169_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	unsigned long flags;
 	int ret;
 
 	del_timer_sync(&tp->timer);
 
-	spin_lock_irqsave(&tp->lock, flags);
+	rtl_lock_work(tp);
 	ret = rtl8169_set_speed(dev, cmd->autoneg, ethtool_cmd_speed(cmd),
 				cmd->duplex, cmd->advertising);
-	spin_unlock_irqrestore(&tp->lock, flags);
+	rtl_unlock_work(tp);
 
 	return ret;
 }
@@ -1568,33 +1611,51 @@
 	return features;
 }
 
-static int rtl8169_set_features(struct net_device *dev,
-	netdev_features_t features)
+static void __rtl8169_set_features(struct net_device *dev,
+				   netdev_features_t features)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
+	netdev_features_t changed = features ^ dev->features;
 	void __iomem *ioaddr = tp->mmio_addr;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tp->lock, flags);
+	if (!(changed & (NETIF_F_RXALL | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_RX)))
+		return;
 
-	if (features & NETIF_F_RXCSUM)
-		tp->cp_cmd |= RxChkSum;
-	else
-		tp->cp_cmd &= ~RxChkSum;
+	if (changed & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_RX)) {
+		if (features & NETIF_F_RXCSUM)
+			tp->cp_cmd |= RxChkSum;
+		else
+			tp->cp_cmd &= ~RxChkSum;
 
-	if (dev->features & NETIF_F_HW_VLAN_RX)
-		tp->cp_cmd |= RxVlan;
-	else
-		tp->cp_cmd &= ~RxVlan;
+		if (dev->features & NETIF_F_HW_VLAN_RX)
+			tp->cp_cmd |= RxVlan;
+		else
+			tp->cp_cmd &= ~RxVlan;
 
-	RTL_W16(CPlusCmd, tp->cp_cmd);
-	RTL_R16(CPlusCmd);
+		RTL_W16(CPlusCmd, tp->cp_cmd);
+		RTL_R16(CPlusCmd);
+	}
+	if (changed & NETIF_F_RXALL) {
+		int tmp = (RTL_R32(RxConfig) & ~(AcceptErr | AcceptRunt));
+		if (features & NETIF_F_RXALL)
+			tmp |= (AcceptErr | AcceptRunt);
+		RTL_W32(RxConfig, tmp);
+	}
+}
 
-	spin_unlock_irqrestore(&tp->lock, flags);
+static int rtl8169_set_features(struct net_device *dev,
+				netdev_features_t features)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	rtl_lock_work(tp);
+	__rtl8169_set_features(dev, features);
+	rtl_unlock_work(tp);
 
 	return 0;
 }
 
+
 static inline u32 rtl8169_tx_vlan_tag(struct rtl8169_private *tp,
 				      struct sk_buff *skb)
 {
@@ -1643,14 +1704,12 @@
 static int rtl8169_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	unsigned long flags;
 	int rc;
 
-	spin_lock_irqsave(&tp->lock, flags);
-
+	rtl_lock_work(tp);
 	rc = tp->get_settings(dev, cmd);
+	rtl_unlock_work(tp);
 
-	spin_unlock_irqrestore(&tp->lock, flags);
 	return rc;
 }
 
@@ -1658,14 +1717,13 @@
 			     void *p)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	unsigned long flags;
 
 	if (regs->len > R8169_REGS_SIZE)
 		regs->len = R8169_REGS_SIZE;
 
-	spin_lock_irqsave(&tp->lock, flags);
+	rtl_lock_work(tp);
 	memcpy_fromio(p, tp->mmio_addr, regs->len);
-	spin_unlock_irqrestore(&tp->lock, flags);
+	rtl_unlock_work(tp);
 }
 
 static u32 rtl8169_get_msglevel(struct net_device *dev)
@@ -3182,18 +3240,14 @@
 	}
 }
 
-static void rtl8169_phy_timer(unsigned long __opaque)
+static void rtl_phy_work(struct rtl8169_private *tp)
 {
-	struct net_device *dev = (struct net_device *)__opaque;
-	struct rtl8169_private *tp = netdev_priv(dev);
 	struct timer_list *timer = &tp->timer;
 	void __iomem *ioaddr = tp->mmio_addr;
 	unsigned long timeout = RTL8169_PHY_TIMEOUT;
 
 	assert(tp->mac_version > RTL_GIGA_MAC_VER_01);
 
-	spin_lock_irq(&tp->lock);
-
 	if (tp->phy_reset_pending(tp)) {
 		/*
 		 * A busy loop could burn quite a few cycles on nowadays CPU.
@@ -3204,34 +3258,29 @@
 	}
 
 	if (tp->link_ok(ioaddr))
-		goto out_unlock;
+		return;
 
-	netif_warn(tp, link, dev, "PHY reset until link up\n");
+	netif_warn(tp, link, tp->dev, "PHY reset until link up\n");
 
 	tp->phy_reset_enable(tp);
 
 out_mod_timer:
 	mod_timer(timer, jiffies + timeout);
-out_unlock:
-	spin_unlock_irq(&tp->lock);
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/*
- * Polling 'interrupt' - used by things like netconsole to send skbs
- * without having to re-enable interrupts. It's not called while
- * the interrupt routine is executing.
- */
-static void rtl8169_netpoll(struct net_device *dev)
+static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-	struct pci_dev *pdev = tp->pci_dev;
-
-	disable_irq(pdev->irq);
-	rtl8169_interrupt(pdev->irq, dev);
-	enable_irq(pdev->irq);
+	if (!test_and_set_bit(flag, tp->wk.flags))
+		schedule_work(&tp->wk.work);
 }
-#endif
+
+static void rtl8169_phy_timer(unsigned long __opaque)
+{
+	struct net_device *dev = (struct net_device *)__opaque;
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING);
+}
 
 static void rtl8169_release_board(struct pci_dev *pdev, struct net_device *dev,
 				  void __iomem *ioaddr)
@@ -3310,7 +3359,7 @@
 	low  = addr[0] | (addr[1] << 8) | (addr[2] << 16) | (addr[3] << 24);
 	high = addr[4] | (addr[5] << 8);
 
-	spin_lock_irq(&tp->lock);
+	rtl_lock_work(tp);
 
 	RTL_W8(Cfg9346, Cfg9346_Unlock);
 
@@ -3334,7 +3383,7 @@
 
 	RTL_W8(Cfg9346, Cfg9346_Lock);
 
-	spin_unlock_irq(&tp->lock);
+	rtl_unlock_work(tp);
 }
 
 static int rtl_set_mac_address(struct net_device *dev, void *p)
@@ -3384,69 +3433,6 @@
 	return -EOPNOTSUPP;
 }
 
-static const struct rtl_cfg_info {
-	void (*hw_start)(struct net_device *);
-	unsigned int region;
-	unsigned int align;
-	u16 intr_event;
-	u16 napi_event;
-	unsigned features;
-	u8 default_ver;
-} rtl_cfg_infos [] = {
-	[RTL_CFG_0] = {
-		.hw_start	= rtl_hw_start_8169,
-		.region		= 1,
-		.align		= 0,
-		.intr_event	= SYSErr | LinkChg | RxOverflow |
-				  RxFIFOOver | TxErr | TxOK | RxOK | RxErr,
-		.napi_event	= RxFIFOOver | TxErr | TxOK | RxOK | RxOverflow,
-		.features	= RTL_FEATURE_GMII,
-		.default_ver	= RTL_GIGA_MAC_VER_01,
-	},
-	[RTL_CFG_1] = {
-		.hw_start	= rtl_hw_start_8168,
-		.region		= 2,
-		.align		= 8,
-		.intr_event	= SYSErr | LinkChg | RxOverflow |
-				  TxErr | TxOK | RxOK | RxErr,
-		.napi_event	= TxErr | TxOK | RxOK | RxOverflow,
-		.features	= RTL_FEATURE_GMII | RTL_FEATURE_MSI,
-		.default_ver	= RTL_GIGA_MAC_VER_11,
-	},
-	[RTL_CFG_2] = {
-		.hw_start	= rtl_hw_start_8101,
-		.region		= 2,
-		.align		= 8,
-		.intr_event	= SYSErr | LinkChg | RxOverflow | PCSTimeout |
-				  RxFIFOOver | TxErr | TxOK | RxOK | RxErr,
-		.napi_event	= RxFIFOOver | TxErr | TxOK | RxOK | RxOverflow,
-		.features	= RTL_FEATURE_MSI,
-		.default_ver	= RTL_GIGA_MAC_VER_13,
-	}
-};
-
-/* Cfg9346_Unlock assumed. */
-static unsigned rtl_try_msi(struct rtl8169_private *tp,
-			    const struct rtl_cfg_info *cfg)
-{
-	void __iomem *ioaddr = tp->mmio_addr;
-	unsigned msi = 0;
-	u8 cfg2;
-
-	cfg2 = RTL_R8(Config2) & ~MSIEnable;
-	if (cfg->features & RTL_FEATURE_MSI) {
-		if (pci_enable_msi(tp->pci_dev)) {
-			netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n");
-		} else {
-			cfg2 |= MSIEnable;
-			msi = RTL_FEATURE_MSI;
-		}
-	}
-	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
-		RTL_W8(Config2, cfg2);
-	return msi;
-}
-
 static void rtl_disable_msi(struct pci_dev *pdev, struct rtl8169_private *tp)
 {
 	if (tp->features & RTL_FEATURE_MSI) {
@@ -3455,25 +3441,6 @@
 	}
 }
 
-static const struct net_device_ops rtl8169_netdev_ops = {
-	.ndo_open		= rtl8169_open,
-	.ndo_stop		= rtl8169_close,
-	.ndo_get_stats		= rtl8169_get_stats,
-	.ndo_start_xmit		= rtl8169_start_xmit,
-	.ndo_tx_timeout		= rtl8169_tx_timeout,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_mtu		= rtl8169_change_mtu,
-	.ndo_fix_features	= rtl8169_fix_features,
-	.ndo_set_features	= rtl8169_set_features,
-	.ndo_set_mac_address	= rtl_set_mac_address,
-	.ndo_do_ioctl		= rtl8169_ioctl,
-	.ndo_set_rx_mode	= rtl_set_rx_mode,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= rtl8169_netpoll,
-#endif
-
-};
-
 static void __devinit rtl_init_mdio_ops(struct rtl8169_private *tp)
 {
 	struct mdio_ops *ops = &tp->mdio_ops;
@@ -3781,12 +3748,20 @@
 
 static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	RTL_W8(Cfg9346, Cfg9346_Unlock);
 	rtl_generic_op(tp, tp->jumbo_ops.enable);
+	RTL_W8(Cfg9346, Cfg9346_Lock);
 }
 
 static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
 {
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	RTL_W8(Cfg9346, Cfg9346_Unlock);
 	rtl_generic_op(tp, tp->jumbo_ops.disable);
+	RTL_W8(Cfg9346, Cfg9346_Lock);
 }
 
 static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp)
@@ -3824,23 +3799,21 @@
 static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
-	struct pci_dev *pdev = tp->pci_dev;
 
 	RTL_W8(MaxTxPacketSize, 0x3f);
 	RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0);
 	RTL_W8(Config4, RTL_R8(Config4) | 0x01);
-	pci_write_config_byte(pdev, 0x79, 0x20);
+	rtl_tx_performance_tweak(tp->pci_dev, 0x2 << MAX_READ_REQUEST_SHIFT);
 }
 
 static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
-	struct pci_dev *pdev = tp->pci_dev;
 
 	RTL_W8(MaxTxPacketSize, 0x0c);
 	RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0);
 	RTL_W8(Config4, RTL_R8(Config4) & ~0x01);
-	pci_write_config_byte(pdev, 0x79, 0x50);
+	rtl_tx_performance_tweak(tp->pci_dev, 0x5 << MAX_READ_REQUEST_SHIFT);
 }
 
 static void r8168b_0_hw_jumbo_enable(struct rtl8169_private *tp)
@@ -3939,280 +3912,6 @@
 	}
 }
 
-static int __devinit
-rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
-{
-	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
-	const unsigned int region = cfg->region;
-	struct rtl8169_private *tp;
-	struct mii_if_info *mii;
-	struct net_device *dev;
-	void __iomem *ioaddr;
-	int chipset, i;
-	int rc;
-
-	if (netif_msg_drv(&debug)) {
-		printk(KERN_INFO "%s Gigabit Ethernet driver %s loaded\n",
-		       MODULENAME, RTL8169_VERSION);
-	}
-
-	dev = alloc_etherdev(sizeof (*tp));
-	if (!dev) {
-		if (netif_msg_drv(&debug))
-			dev_err(&pdev->dev, "unable to alloc new ethernet\n");
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	SET_NETDEV_DEV(dev, &pdev->dev);
-	dev->netdev_ops = &rtl8169_netdev_ops;
-	tp = netdev_priv(dev);
-	tp->dev = dev;
-	tp->pci_dev = pdev;
-	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
-
-	mii = &tp->mii;
-	mii->dev = dev;
-	mii->mdio_read = rtl_mdio_read;
-	mii->mdio_write = rtl_mdio_write;
-	mii->phy_id_mask = 0x1f;
-	mii->reg_num_mask = 0x1f;
-	mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII);
-
-	/* disable ASPM completely as that cause random device stop working
-	 * problems as well as full system hangs for some PCIe devices users */
-	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
-				     PCIE_LINK_STATE_CLKPM);
-
-	/* enable device (incl. PCI PM wakeup and hotplug setup) */
-	rc = pci_enable_device(pdev);
-	if (rc < 0) {
-		netif_err(tp, probe, dev, "enable failure\n");
-		goto err_out_free_dev_1;
-	}
-
-	if (pci_set_mwi(pdev) < 0)
-		netif_info(tp, probe, dev, "Mem-Wr-Inval unavailable\n");
-
-	/* make sure PCI base addr 1 is MMIO */
-	if (!(pci_resource_flags(pdev, region) & IORESOURCE_MEM)) {
-		netif_err(tp, probe, dev,
-			  "region #%d not an MMIO resource, aborting\n",
-			  region);
-		rc = -ENODEV;
-		goto err_out_mwi_2;
-	}
-
-	/* check for weird/broken PCI region reporting */
-	if (pci_resource_len(pdev, region) < R8169_REGS_SIZE) {
-		netif_err(tp, probe, dev,
-			  "Invalid PCI region size(s), aborting\n");
-		rc = -ENODEV;
-		goto err_out_mwi_2;
-	}
-
-	rc = pci_request_regions(pdev, MODULENAME);
-	if (rc < 0) {
-		netif_err(tp, probe, dev, "could not request regions\n");
-		goto err_out_mwi_2;
-	}
-
-	tp->cp_cmd = RxChkSum;
-
-	if ((sizeof(dma_addr_t) > 4) &&
-	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && use_dac) {
-		tp->cp_cmd |= PCIDAC;
-		dev->features |= NETIF_F_HIGHDMA;
-	} else {
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (rc < 0) {
-			netif_err(tp, probe, dev, "DMA configuration failed\n");
-			goto err_out_free_res_3;
-		}
-	}
-
-	/* ioremap MMIO region */
-	ioaddr = ioremap(pci_resource_start(pdev, region), R8169_REGS_SIZE);
-	if (!ioaddr) {
-		netif_err(tp, probe, dev, "cannot remap MMIO, aborting\n");
-		rc = -EIO;
-		goto err_out_free_res_3;
-	}
-	tp->mmio_addr = ioaddr;
-
-	if (!pci_is_pcie(pdev))
-		netif_info(tp, probe, dev, "not PCI Express\n");
-
-	/* Identify chip attached to board */
-	rtl8169_get_mac_version(tp, dev, cfg->default_ver);
-
-	rtl_init_rxcfg(tp);
-
-	RTL_W16(IntrMask, 0x0000);
-
-	rtl_hw_reset(tp);
-
-	RTL_W16(IntrStatus, 0xffff);
-
-	pci_set_master(pdev);
-
-	/*
-	 * Pretend we are using VLANs; This bypasses a nasty bug where
-	 * Interrupts stop flowing on high load on 8110SCd controllers.
-	 */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
-		tp->cp_cmd |= RxVlan;
-
-	rtl_init_mdio_ops(tp);
-	rtl_init_pll_power_ops(tp);
-	rtl_init_jumbo_ops(tp);
-
-	rtl8169_print_mac_version(tp);
-
-	chipset = tp->mac_version;
-	tp->txd_version = rtl_chip_infos[chipset].txd_version;
-
-	RTL_W8(Cfg9346, Cfg9346_Unlock);
-	RTL_W8(Config1, RTL_R8(Config1) | PMEnable);
-	RTL_W8(Config5, RTL_R8(Config5) & PMEStatus);
-	if ((RTL_R8(Config3) & (LinkUp | MagicPacket)) != 0)
-		tp->features |= RTL_FEATURE_WOL;
-	if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0)
-		tp->features |= RTL_FEATURE_WOL;
-	tp->features |= rtl_try_msi(tp, cfg);
-	RTL_W8(Cfg9346, Cfg9346_Lock);
-
-	if (rtl_tbi_enabled(tp)) {
-		tp->set_speed = rtl8169_set_speed_tbi;
-		tp->get_settings = rtl8169_gset_tbi;
-		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
-		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
-		tp->link_ok = rtl8169_tbi_link_ok;
-		tp->do_ioctl = rtl_tbi_ioctl;
-	} else {
-		tp->set_speed = rtl8169_set_speed_xmii;
-		tp->get_settings = rtl8169_gset_xmii;
-		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
-		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
-		tp->link_ok = rtl8169_xmii_link_ok;
-		tp->do_ioctl = rtl_xmii_ioctl;
-	}
-
-	spin_lock_init(&tp->lock);
-
-	/* Get MAC address */
-	for (i = 0; i < ETH_ALEN; i++)
-		dev->dev_addr[i] = RTL_R8(MAC0 + i);
-	memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
-
-	SET_ETHTOOL_OPS(dev, &rtl8169_ethtool_ops);
-	dev->watchdog_timeo = RTL8169_TX_TIMEOUT;
-	dev->irq = pdev->irq;
-	dev->base_addr = (unsigned long) ioaddr;
-
-	netif_napi_add(dev, &tp->napi, rtl8169_poll, R8169_NAPI_WEIGHT);
-
-	/* don't enable SG, IP_CSUM and TSO by default - it might not work
-	 * properly for all devices */
-	dev->features |= NETIF_F_RXCSUM |
-		NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
-
-	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
-	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_HIGHDMA;
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
-		/* 8110SCd requires hardware Rx VLAN - disallow toggling */
-		dev->hw_features &= ~NETIF_F_HW_VLAN_RX;
-
-	tp->intr_mask = 0xffff;
-	tp->hw_start = cfg->hw_start;
-	tp->intr_event = cfg->intr_event;
-	tp->napi_event = cfg->napi_event;
-
-	tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
-		~(RxBOVF | RxFOVF) : ~0;
-
-	init_timer(&tp->timer);
-	tp->timer.data = (unsigned long) dev;
-	tp->timer.function = rtl8169_phy_timer;
-
-	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
-
-	rc = register_netdev(dev);
-	if (rc < 0)
-		goto err_out_msi_4;
-
-	pci_set_drvdata(pdev, dev);
-
-	netif_info(tp, probe, dev, "%s at 0x%lx, %pM, XID %08x IRQ %d\n",
-		   rtl_chip_infos[chipset].name, dev->base_addr, dev->dev_addr,
-		   (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), dev->irq);
-	if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) {
-		netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, "
-			   "tx checksumming: %s]\n",
-			   rtl_chip_infos[chipset].jumbo_max,
-			   rtl_chip_infos[chipset].jumbo_tx_csum ? "ok" : "ko");
-	}
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_28 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_31) {
-		rtl8168_driver_start(tp);
-	}
-
-	device_set_wakeup_enable(&pdev->dev, tp->features & RTL_FEATURE_WOL);
-
-	if (pci_dev_run_wake(pdev))
-		pm_runtime_put_noidle(&pdev->dev);
-
-	netif_carrier_off(dev);
-
-out:
-	return rc;
-
-err_out_msi_4:
-	rtl_disable_msi(pdev, tp);
-	iounmap(ioaddr);
-err_out_free_res_3:
-	pci_release_regions(pdev);
-err_out_mwi_2:
-	pci_clear_mwi(pdev);
-	pci_disable_device(pdev);
-err_out_free_dev_1:
-	free_netdev(dev);
-	goto out;
-}
-
-static void __devexit rtl8169_remove_one(struct pci_dev *pdev)
-{
-	struct net_device *dev = pci_get_drvdata(pdev);
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_28 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_31) {
-		rtl8168_driver_stop(tp);
-	}
-
-	cancel_delayed_work_sync(&tp->task);
-
-	unregister_netdev(dev);
-
-	rtl_release_firmware(tp);
-
-	if (pci_dev_run_wake(pdev))
-		pm_runtime_get_noresume(&pdev->dev);
-
-	/* restore original MAC address */
-	rtl_rar_set(tp, dev->perm_addr);
-
-	rtl_disable_msi(pdev, tp);
-	rtl8169_release_board(pdev, dev, tp->mmio_addr);
-	pci_set_drvdata(pdev, NULL);
-}
-
 static void rtl_request_uncached_firmware(struct rtl8169_private *tp)
 {
 	struct rtl_fw *rtl_fw;
@@ -4257,78 +3956,6 @@
 		rtl_request_uncached_firmware(tp);
 }
 
-static int rtl8169_open(struct net_device *dev)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	void __iomem *ioaddr = tp->mmio_addr;
-	struct pci_dev *pdev = tp->pci_dev;
-	int retval = -ENOMEM;
-
-	pm_runtime_get_sync(&pdev->dev);
-
-	/*
-	 * Rx and Tx descriptors needs 256 bytes alignment.
-	 * dma_alloc_coherent provides more.
-	 */
-	tp->TxDescArray = dma_alloc_coherent(&pdev->dev, R8169_TX_RING_BYTES,
-					     &tp->TxPhyAddr, GFP_KERNEL);
-	if (!tp->TxDescArray)
-		goto err_pm_runtime_put;
-
-	tp->RxDescArray = dma_alloc_coherent(&pdev->dev, R8169_RX_RING_BYTES,
-					     &tp->RxPhyAddr, GFP_KERNEL);
-	if (!tp->RxDescArray)
-		goto err_free_tx_0;
-
-	retval = rtl8169_init_ring(dev);
-	if (retval < 0)
-		goto err_free_rx_1;
-
-	INIT_DELAYED_WORK(&tp->task, NULL);
-
-	smp_mb();
-
-	rtl_request_firmware(tp);
-
-	retval = request_irq(dev->irq, rtl8169_interrupt,
-			     (tp->features & RTL_FEATURE_MSI) ? 0 : IRQF_SHARED,
-			     dev->name, dev);
-	if (retval < 0)
-		goto err_release_fw_2;
-
-	napi_enable(&tp->napi);
-
-	rtl8169_init_phy(dev, tp);
-
-	rtl8169_set_features(dev, dev->features);
-
-	rtl_pll_power_up(tp);
-
-	rtl_hw_start(dev);
-
-	tp->saved_wolopts = 0;
-	pm_runtime_put_noidle(&pdev->dev);
-
-	rtl8169_check_link_status(dev, tp, ioaddr);
-out:
-	return retval;
-
-err_release_fw_2:
-	rtl_release_firmware(tp);
-	rtl8169_rx_clear(tp);
-err_free_rx_1:
-	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
-			  tp->RxPhyAddr);
-	tp->RxDescArray = NULL;
-err_free_tx_0:
-	dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray,
-			  tp->TxPhyAddr);
-	tp->TxDescArray = NULL;
-err_pm_runtime_put:
-	pm_runtime_put_noidle(&pdev->dev);
-	goto out;
-}
-
 static void rtl_rx_close(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
@@ -4379,7 +4006,7 @@
 
 	tp->hw_start(dev);
 
-	netif_start_queue(dev);
+	rtl_irq_enable_all(tp);
 }
 
 static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp,
@@ -4436,6 +4063,56 @@
 	}
 }
 
+static void rtl_set_rx_mode(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	void __iomem *ioaddr = tp->mmio_addr;
+	u32 mc_filter[2];	/* Multicast hash filter */
+	int rx_mode;
+	u32 tmp = 0;
+
+	if (dev->flags & IFF_PROMISC) {
+		/* Unconditionally log net taps. */
+		netif_notice(tp, link, dev, "Promiscuous mode enabled\n");
+		rx_mode =
+		    AcceptBroadcast | AcceptMulticast | AcceptMyPhys |
+		    AcceptAllPhys;
+		mc_filter[1] = mc_filter[0] = 0xffffffff;
+	} else if ((netdev_mc_count(dev) > multicast_filter_limit) ||
+		   (dev->flags & IFF_ALLMULTI)) {
+		/* Too many to filter perfectly -- accept all multicasts. */
+		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys;
+		mc_filter[1] = mc_filter[0] = 0xffffffff;
+	} else {
+		struct netdev_hw_addr *ha;
+
+		rx_mode = AcceptBroadcast | AcceptMyPhys;
+		mc_filter[1] = mc_filter[0] = 0;
+		netdev_for_each_mc_addr(ha, dev) {
+			int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26;
+			mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+			rx_mode |= AcceptMulticast;
+		}
+	}
+
+	if (dev->features & NETIF_F_RXALL)
+		rx_mode |= (AcceptErr | AcceptRunt);
+
+	tmp = (RTL_R32(RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode;
+
+	if (tp->mac_version > RTL_GIGA_MAC_VER_06) {
+		u32 data = mc_filter[0];
+
+		mc_filter[0] = swab32(mc_filter[1]);
+		mc_filter[1] = swab32(data);
+	}
+
+	RTL_W32(MAR0 + 4, mc_filter[1]);
+	RTL_W32(MAR0 + 0, mc_filter[0]);
+
+	RTL_W32(RxConfig, tmp);
+}
+
 static void rtl_hw_start_8169(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -4506,9 +4183,6 @@
 
 	/* no early-rx interrupts */
 	RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xF000);
-
-	/* Enable all known interrupts by setting the interrupt mask. */
-	RTL_W16(IntrMask, tp->intr_event);
 }
 
 static void rtl_csi_access_enable(void __iomem *ioaddr, u32 bits)
@@ -4888,8 +4562,8 @@
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-		tp->intr_event |= RxFIFOOver | PCSTimeout;
-		tp->intr_event &= ~RxOverflow;
+		tp->event_slow |= RxFIFOOver | PCSTimeout;
+		tp->event_slow &= ~RxOverflow;
 	}
 
 	rtl_set_rx_tx_desc_registers(tp, ioaddr);
@@ -4977,8 +4651,6 @@
 	RTL_W8(Cfg9346, Cfg9346_Lock);
 
 	RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xF000);
-
-	RTL_W16(IntrMask, tp->intr_event);
 }
 
 #define R810X_CPCMD_QUIRK_MASK (\
@@ -5077,10 +4749,8 @@
 	void __iomem *ioaddr = tp->mmio_addr;
 	struct pci_dev *pdev = tp->pci_dev;
 
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_30) {
-		tp->intr_event &= ~RxFIFOOver;
-		tp->napi_event &= ~RxFIFOOver;
-	}
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_30)
+		tp->event_slow &= ~RxFIFOOver;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_16) {
@@ -5136,8 +4806,6 @@
 	rtl_set_rx_mode(dev);
 
 	RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000);
-
-	RTL_W16(IntrMask, tp->intr_event);
 }
 
 static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
@@ -5328,94 +4996,37 @@
 {
 	rtl8169_tx_clear_range(tp, tp->dirty_tx, NUM_TX_DESC);
 	tp->cur_tx = tp->dirty_tx = 0;
+	netdev_reset_queue(tp->dev);
 }
 
-static void rtl8169_schedule_work(struct net_device *dev, work_func_t task)
+static void rtl_reset_work(struct rtl8169_private *tp)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	PREPARE_DELAYED_WORK(&tp->task, task);
-	schedule_delayed_work(&tp->task, 4);
-}
-
-static void rtl8169_wait_for_quiescence(struct net_device *dev)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	void __iomem *ioaddr = tp->mmio_addr;
-
-	synchronize_irq(dev->irq);
-
-	/* Wait for any pending NAPI task to complete */
-	napi_disable(&tp->napi);
-
-	rtl8169_irq_mask_and_ack(tp);
-
-	tp->intr_mask = 0xffff;
-	RTL_W16(IntrMask, tp->intr_event);
-	napi_enable(&tp->napi);
-}
-
-static void rtl8169_reinit_task(struct work_struct *work)
-{
-	struct rtl8169_private *tp =
-		container_of(work, struct rtl8169_private, task.work);
-	struct net_device *dev = tp->dev;
-	int ret;
-
-	rtnl_lock();
-
-	if (!netif_running(dev))
-		goto out_unlock;
-
-	rtl8169_wait_for_quiescence(dev);
-	rtl8169_close(dev);
-
-	ret = rtl8169_open(dev);
-	if (unlikely(ret < 0)) {
-		if (net_ratelimit())
-			netif_err(tp, drv, dev,
-				  "reinit failure (status = %d). Rescheduling\n",
-				  ret);
-		rtl8169_schedule_work(dev, rtl8169_reinit_task);
-	}
-
-out_unlock:
-	rtnl_unlock();
-}
-
-static void rtl8169_reset_task(struct work_struct *work)
-{
-	struct rtl8169_private *tp =
-		container_of(work, struct rtl8169_private, task.work);
 	struct net_device *dev = tp->dev;
 	int i;
 
-	rtnl_lock();
-
-	if (!netif_running(dev))
-		goto out_unlock;
+	napi_disable(&tp->napi);
+	netif_stop_queue(dev);
+	synchronize_sched();
 
 	rtl8169_hw_reset(tp);
 
-	rtl8169_wait_for_quiescence(dev);
-
 	for (i = 0; i < NUM_RX_DESC; i++)
 		rtl8169_mark_to_asic(tp->RxDescArray + i, rx_buf_sz);
 
 	rtl8169_tx_clear(tp);
 	rtl8169_init_ring_indexes(tp);
 
+	napi_enable(&tp->napi);
 	rtl_hw_start(dev);
 	netif_wake_queue(dev);
 	rtl8169_check_link_status(dev, tp, tp->mmio_addr);
-
-out_unlock:
-	rtnl_unlock();
 }
 
 static void rtl8169_tx_timeout(struct net_device *dev)
 {
-	rtl8169_schedule_work(dev, rtl8169_reset_task);
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
 static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
@@ -5540,6 +5151,10 @@
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
+	netdev_sent_queue(dev, skb->len);
+
+	skb_tx_timestamp(skb);
+
 	wmb();
 
 	/* Anti gcc 2.95.3 bugware (sic) */
@@ -5552,9 +5167,22 @@
 
 	RTL_W8(TxPoll, NPQ);
 
+	mmiowb();
+
 	if (TX_BUFFS_AVAIL(tp) < MAX_SKB_FRAGS) {
+		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
+		 * not miss a ring update when it notices a stopped queue.
+		 */
+		smp_wmb();
 		netif_stop_queue(dev);
-		smp_rmb();
+		/* Sync with rtl_tx:
+		 * - publish queue status and cur_tx ring index (write barrier)
+		 * - refresh dirty_tx ring index (read barrier).
+		 * May the current thread have a pessimistic view of the ring
+		 * status and forget to wake up queue, a racing rtl_tx thread
+		 * can't.
+		 */
+		smp_mb();
 		if (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)
 			netif_wake_queue(dev);
 	}
@@ -5618,14 +5246,19 @@
 
 	rtl8169_hw_reset(tp);
 
-	rtl8169_schedule_work(dev, rtl8169_reinit_task);
+	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
-static void rtl8169_tx_interrupt(struct net_device *dev,
-				 struct rtl8169_private *tp,
-				 void __iomem *ioaddr)
+struct rtl_txc {
+	int packets;
+	int bytes;
+};
+
+static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 {
+	struct rtl8169_stats *tx_stats = &tp->tx_stats;
 	unsigned int dirty_tx, tx_left;
+	struct rtl_txc txc = { 0, 0 };
 
 	dirty_tx = tp->dirty_tx;
 	smp_rmb();
@@ -5644,18 +5277,34 @@
 		rtl8169_unmap_tx_skb(&tp->pci_dev->dev, tx_skb,
 				     tp->TxDescArray + entry);
 		if (status & LastFrag) {
-			dev->stats.tx_packets++;
-			dev->stats.tx_bytes += tx_skb->skb->len;
-			dev_kfree_skb(tx_skb->skb);
+			struct sk_buff *skb = tx_skb->skb;
+
+			txc.packets++;
+			txc.bytes += skb->len;
+			dev_kfree_skb(skb);
 			tx_skb->skb = NULL;
 		}
 		dirty_tx++;
 		tx_left--;
 	}
 
+	u64_stats_update_begin(&tx_stats->syncp);
+	tx_stats->packets += txc.packets;
+	tx_stats->bytes += txc.bytes;
+	u64_stats_update_end(&tx_stats->syncp);
+
+	netdev_completed_queue(dev, txc.packets, txc.bytes);
+
 	if (tp->dirty_tx != dirty_tx) {
 		tp->dirty_tx = dirty_tx;
-		smp_wmb();
+		/* Sync with rtl8169_start_xmit:
+		 * - publish dirty_tx ring index (write barrier)
+		 * - refresh cur_tx ring index and queue status (read barrier)
+		 * May the current thread miss the stopped queue condition,
+		 * a racing xmit thread can only have a right view of the
+		 * ring status.
+		 */
+		smp_mb();
 		if (netif_queue_stopped(dev) &&
 		    (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)) {
 			netif_wake_queue(dev);
@@ -5666,9 +5315,11 @@
 		 * of start_xmit activity is detected (if it is not detected,
 		 * it is slow enough). -- FR
 		 */
-		smp_rmb();
-		if (tp->cur_tx != dirty_tx)
+		if (tp->cur_tx != dirty_tx) {
+			void __iomem *ioaddr = tp->mmio_addr;
+
 			RTL_W8(TxPoll, NPQ);
+		}
 	}
 }
 
@@ -5707,9 +5358,7 @@
 	return skb;
 }
 
-static int rtl8169_rx_interrupt(struct net_device *dev,
-				struct rtl8169_private *tp,
-				void __iomem *ioaddr, u32 budget)
+static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget)
 {
 	unsigned int cur_rx, rx_left;
 	unsigned int count;
@@ -5737,14 +5386,26 @@
 			if (status & RxCRC)
 				dev->stats.rx_crc_errors++;
 			if (status & RxFOVF) {
-				rtl8169_schedule_work(dev, rtl8169_reset_task);
+				rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 				dev->stats.rx_fifo_errors++;
 			}
+			if ((status & (RxRUNT | RxCRC)) &&
+			    !(status & (RxRWT | RxFOVF)) &&
+			    (dev->features & NETIF_F_RXALL))
+				goto process_pkt;
+
 			rtl8169_mark_to_asic(desc, rx_buf_sz);
 		} else {
 			struct sk_buff *skb;
-			dma_addr_t addr = le64_to_cpu(desc->addr);
-			int pkt_size = (status & 0x00003fff) - 4;
+			dma_addr_t addr;
+			int pkt_size;
+
+process_pkt:
+			addr = le64_to_cpu(desc->addr);
+			if (likely(!(dev->features & NETIF_F_RXFCS)))
+				pkt_size = (status & 0x00003fff) - 4;
+			else
+				pkt_size = status & 0x00003fff;
 
 			/*
 			 * The driver does not support incoming fragmented
@@ -5774,8 +5435,10 @@
 
 			napi_gro_receive(&tp->napi, skb);
 
-			dev->stats.rx_bytes += pkt_size;
-			dev->stats.rx_packets++;
+			u64_stats_update_begin(&tp->rx_stats.syncp);
+			tp->rx_stats.packets++;
+			tp->rx_stats.bytes += pkt_size;
+			u64_stats_update_end(&tp->rx_stats.syncp);
 		}
 
 		/* Work around for AMD plateform. */
@@ -5798,101 +5461,120 @@
 {
 	struct net_device *dev = dev_instance;
 	struct rtl8169_private *tp = netdev_priv(dev);
-	void __iomem *ioaddr = tp->mmio_addr;
 	int handled = 0;
-	int status;
+	u16 status;
 
-	/* loop handling interrupts until we have no new ones or
-	 * we hit a invalid/hotplug case.
-	 */
-	status = RTL_R16(IntrStatus);
-	while (status && status != 0xffff) {
-		status &= tp->intr_event;
-		if (!status)
-			break;
+	status = rtl_get_events(tp);
+	if (status && status != 0xffff) {
+		status &= RTL_EVENT_NAPI | tp->event_slow;
+		if (status) {
+			handled = 1;
 
-		handled = 1;
-
-		/* Handle all of the error cases first. These will reset
-		 * the chip, so just exit the loop.
-		 */
-		if (unlikely(!netif_running(dev))) {
-			rtl8169_hw_reset(tp);
-			break;
+			rtl_irq_disable(tp);
+			napi_schedule(&tp->napi);
 		}
-
-		if (unlikely(status & RxFIFOOver)) {
-			switch (tp->mac_version) {
-			/* Work around for rx fifo overflow */
-			case RTL_GIGA_MAC_VER_11:
-				netif_stop_queue(dev);
-				rtl8169_tx_timeout(dev);
-				goto done;
-			default:
-				break;
-			}
-		}
-
-		if (unlikely(status & SYSErr)) {
-			rtl8169_pcierr_interrupt(dev);
-			break;
-		}
-
-		if (status & LinkChg)
-			__rtl8169_check_link_status(dev, tp, ioaddr, true);
-
-		/* We need to see the lastest version of tp->intr_mask to
-		 * avoid ignoring an MSI interrupt and having to wait for
-		 * another event which may never come.
-		 */
-		smp_rmb();
-		if (status & tp->intr_mask & tp->napi_event) {
-			RTL_W16(IntrMask, tp->intr_event & ~tp->napi_event);
-			tp->intr_mask = ~tp->napi_event;
-
-			if (likely(napi_schedule_prep(&tp->napi)))
-				__napi_schedule(&tp->napi);
-			else
-				netif_info(tp, intr, dev,
-					   "interrupt %04x in poll\n", status);
-		}
-
-		/* We only get a new MSI interrupt when all active irq
-		 * sources on the chip have been acknowledged. So, ack
-		 * everything we've seen and check if new sources have become
-		 * active to avoid blocking all interrupts from the chip.
-		 */
-		RTL_W16(IntrStatus,
-			(status & RxFIFOOver) ? (status | RxOverflow) : status);
-		status = RTL_R16(IntrStatus);
 	}
-done:
 	return IRQ_RETVAL(handled);
 }
 
+/*
+ * Workqueue context.
+ */
+static void rtl_slow_event_work(struct rtl8169_private *tp)
+{
+	struct net_device *dev = tp->dev;
+	u16 status;
+
+	status = rtl_get_events(tp) & tp->event_slow;
+	rtl_ack_events(tp, status);
+
+	if (unlikely(status & RxFIFOOver)) {
+		switch (tp->mac_version) {
+		/* Work around for rx fifo overflow */
+		case RTL_GIGA_MAC_VER_11:
+			netif_stop_queue(dev);
+			/* XXX - Hack alert. See rtl_task(). */
+			set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
+		default:
+			break;
+		}
+	}
+
+	if (unlikely(status & SYSErr))
+		rtl8169_pcierr_interrupt(dev);
+
+	if (status & LinkChg)
+		__rtl8169_check_link_status(dev, tp, tp->mmio_addr, true);
+
+	napi_disable(&tp->napi);
+	rtl_irq_disable(tp);
+
+	napi_enable(&tp->napi);
+	napi_schedule(&tp->napi);
+}
+
+static void rtl_task(struct work_struct *work)
+{
+	static const struct {
+		int bitnr;
+		void (*action)(struct rtl8169_private *);
+	} rtl_work[] = {
+		/* XXX - keep rtl_slow_event_work() as first element. */
+		{ RTL_FLAG_TASK_SLOW_PENDING,	rtl_slow_event_work },
+		{ RTL_FLAG_TASK_RESET_PENDING,	rtl_reset_work },
+		{ RTL_FLAG_TASK_PHY_PENDING,	rtl_phy_work }
+	};
+	struct rtl8169_private *tp =
+		container_of(work, struct rtl8169_private, wk.work);
+	struct net_device *dev = tp->dev;
+	int i;
+
+	rtl_lock_work(tp);
+
+	if (!netif_running(dev) ||
+	    !test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags))
+		goto out_unlock;
+
+	for (i = 0; i < ARRAY_SIZE(rtl_work); i++) {
+		bool pending;
+
+		pending = test_and_clear_bit(rtl_work[i].bitnr, tp->wk.flags);
+		if (pending)
+			rtl_work[i].action(tp);
+	}
+
+out_unlock:
+	rtl_unlock_work(tp);
+}
+
 static int rtl8169_poll(struct napi_struct *napi, int budget)
 {
 	struct rtl8169_private *tp = container_of(napi, struct rtl8169_private, napi);
 	struct net_device *dev = tp->dev;
-	void __iomem *ioaddr = tp->mmio_addr;
-	int work_done;
+	u16 enable_mask = RTL_EVENT_NAPI | tp->event_slow;
+	int work_done= 0;
+	u16 status;
 
-	work_done = rtl8169_rx_interrupt(dev, tp, ioaddr, (u32) budget);
-	rtl8169_tx_interrupt(dev, tp, ioaddr);
+	status = rtl_get_events(tp);
+	rtl_ack_events(tp, status & ~tp->event_slow);
+
+	if (status & RTL_EVENT_NAPI_RX)
+		work_done = rtl_rx(dev, tp, (u32) budget);
+
+	if (status & RTL_EVENT_NAPI_TX)
+		rtl_tx(dev, tp);
+
+	if (status & tp->event_slow) {
+		enable_mask &= ~tp->event_slow;
+
+		rtl_schedule_task(tp, RTL_FLAG_TASK_SLOW_PENDING);
+	}
 
 	if (work_done < budget) {
 		napi_complete(napi);
 
-		/* We need for force the visibility of tp->intr_mask
-		 * for other CPUs, as we can loose an MSI interrupt
-		 * and potentially wait for a retransmit timeout if we don't.
-		 * The posted write to IntrMask is safe, as it will
-		 * eventually make it to the chip and we won't loose anything
-		 * until it does.
-		 */
-		tp->intr_mask = 0xffff;
-		wmb();
-		RTL_W16(IntrMask, tp->intr_event);
+		rtl_irq_enable(tp, enable_mask);
+		mmiowb();
 	}
 
 	return work_done;
@@ -5916,26 +5598,19 @@
 
 	del_timer_sync(&tp->timer);
 
-	netif_stop_queue(dev);
-
 	napi_disable(&tp->napi);
-
-	spin_lock_irq(&tp->lock);
+	netif_stop_queue(dev);
 
 	rtl8169_hw_reset(tp);
 	/*
 	 * At this point device interrupts can not be enabled in any function,
-	 * as netif_running is not true (rtl8169_interrupt, rtl8169_reset_task,
-	 * rtl8169_reinit_task) and napi is disabled (rtl8169_poll).
+	 * as netif_running is not true (rtl8169_interrupt, rtl8169_reset_task)
+	 * and napi is disabled (rtl8169_poll).
 	 */
 	rtl8169_rx_missed(dev, ioaddr);
 
-	spin_unlock_irq(&tp->lock);
-
-	synchronize_irq(dev->irq);
-
 	/* Give a racing hard_start_xmit a few cycles to complete. */
-	synchronize_sched();  /* FIXME: should this be synchronize_irq()? */
+	synchronize_sched();
 
 	rtl8169_tx_clear(tp);
 
@@ -5954,9 +5629,13 @@
 	/* Update counters before going down */
 	rtl8169_update_counters(dev);
 
-	rtl8169_down(dev);
+	rtl_lock_work(tp);
+	clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
 
-	free_irq(dev->irq, dev);
+	rtl8169_down(dev);
+	rtl_unlock_work(tp);
+
+	free_irq(pdev->irq, dev);
 
 	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
 			  tp->RxPhyAddr);
@@ -5970,77 +5649,127 @@
 	return 0;
 }
 
-static void rtl_set_rx_mode(struct net_device *dev)
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void rtl8169_netpoll(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	rtl8169_interrupt(tp->pci_dev->irq, dev);
+}
+#endif
+
+static int rtl_open(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
-	unsigned long flags;
-	u32 mc_filter[2];	/* Multicast hash filter */
-	int rx_mode;
-	u32 tmp = 0;
+	struct pci_dev *pdev = tp->pci_dev;
+	int retval = -ENOMEM;
 
-	if (dev->flags & IFF_PROMISC) {
-		/* Unconditionally log net taps. */
-		netif_notice(tp, link, dev, "Promiscuous mode enabled\n");
-		rx_mode =
-		    AcceptBroadcast | AcceptMulticast | AcceptMyPhys |
-		    AcceptAllPhys;
-		mc_filter[1] = mc_filter[0] = 0xffffffff;
-	} else if ((netdev_mc_count(dev) > multicast_filter_limit) ||
-		   (dev->flags & IFF_ALLMULTI)) {
-		/* Too many to filter perfectly -- accept all multicasts. */
-		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys;
-		mc_filter[1] = mc_filter[0] = 0xffffffff;
-	} else {
-		struct netdev_hw_addr *ha;
+	pm_runtime_get_sync(&pdev->dev);
 
-		rx_mode = AcceptBroadcast | AcceptMyPhys;
-		mc_filter[1] = mc_filter[0] = 0;
-		netdev_for_each_mc_addr(ha, dev) {
-			int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26;
-			mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
-			rx_mode |= AcceptMulticast;
-		}
-	}
+	/*
+	 * Rx and Tx descriptors needs 256 bytes alignment.
+	 * dma_alloc_coherent provides more.
+	 */
+	tp->TxDescArray = dma_alloc_coherent(&pdev->dev, R8169_TX_RING_BYTES,
+					     &tp->TxPhyAddr, GFP_KERNEL);
+	if (!tp->TxDescArray)
+		goto err_pm_runtime_put;
 
-	spin_lock_irqsave(&tp->lock, flags);
+	tp->RxDescArray = dma_alloc_coherent(&pdev->dev, R8169_RX_RING_BYTES,
+					     &tp->RxPhyAddr, GFP_KERNEL);
+	if (!tp->RxDescArray)
+		goto err_free_tx_0;
 
-	tmp = (RTL_R32(RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode;
+	retval = rtl8169_init_ring(dev);
+	if (retval < 0)
+		goto err_free_rx_1;
 
-	if (tp->mac_version > RTL_GIGA_MAC_VER_06) {
-		u32 data = mc_filter[0];
+	INIT_WORK(&tp->wk.work, rtl_task);
 
-		mc_filter[0] = swab32(mc_filter[1]);
-		mc_filter[1] = swab32(data);
-	}
+	smp_mb();
 
-	RTL_W32(MAR0 + 4, mc_filter[1]);
-	RTL_W32(MAR0 + 0, mc_filter[0]);
+	rtl_request_firmware(tp);
 
-	RTL_W32(RxConfig, tmp);
+	retval = request_irq(pdev->irq, rtl8169_interrupt,
+			     (tp->features & RTL_FEATURE_MSI) ? 0 : IRQF_SHARED,
+			     dev->name, dev);
+	if (retval < 0)
+		goto err_release_fw_2;
 
-	spin_unlock_irqrestore(&tp->lock, flags);
+	rtl_lock_work(tp);
+
+	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+
+	napi_enable(&tp->napi);
+
+	rtl8169_init_phy(dev, tp);
+
+	__rtl8169_set_features(dev, dev->features);
+
+	rtl_pll_power_up(tp);
+
+	rtl_hw_start(dev);
+
+	netif_start_queue(dev);
+
+	rtl_unlock_work(tp);
+
+	tp->saved_wolopts = 0;
+	pm_runtime_put_noidle(&pdev->dev);
+
+	rtl8169_check_link_status(dev, tp, ioaddr);
+out:
+	return retval;
+
+err_release_fw_2:
+	rtl_release_firmware(tp);
+	rtl8169_rx_clear(tp);
+err_free_rx_1:
+	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
+			  tp->RxPhyAddr);
+	tp->RxDescArray = NULL;
+err_free_tx_0:
+	dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray,
+			  tp->TxPhyAddr);
+	tp->TxDescArray = NULL;
+err_pm_runtime_put:
+	pm_runtime_put_noidle(&pdev->dev);
+	goto out;
 }
 
-/**
- *  rtl8169_get_stats - Get rtl8169 read/write statistics
- *  @dev: The Ethernet Device to get statistics for
- *
- *  Get TX/RX statistics for rtl8169
- */
-static struct net_device_stats *rtl8169_get_stats(struct net_device *dev)
+static struct rtnl_link_stats64 *
+rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
-	unsigned long flags;
+	unsigned int start;
 
-	if (netif_running(dev)) {
-		spin_lock_irqsave(&tp->lock, flags);
+	if (netif_running(dev))
 		rtl8169_rx_missed(dev, ioaddr);
-		spin_unlock_irqrestore(&tp->lock, flags);
-	}
 
-	return &dev->stats;
+	do {
+		start = u64_stats_fetch_begin_bh(&tp->rx_stats.syncp);
+		stats->rx_packets = tp->rx_stats.packets;
+		stats->rx_bytes	= tp->rx_stats.bytes;
+	} while (u64_stats_fetch_retry_bh(&tp->rx_stats.syncp, start));
+
+
+	do {
+		start = u64_stats_fetch_begin_bh(&tp->tx_stats.syncp);
+		stats->tx_packets = tp->tx_stats.packets;
+		stats->tx_bytes	= tp->tx_stats.bytes;
+	} while (u64_stats_fetch_retry_bh(&tp->tx_stats.syncp, start));
+
+	stats->rx_dropped	= dev->stats.rx_dropped;
+	stats->tx_dropped	= dev->stats.tx_dropped;
+	stats->rx_length_errors = dev->stats.rx_length_errors;
+	stats->rx_errors	= dev->stats.rx_errors;
+	stats->rx_crc_errors	= dev->stats.rx_crc_errors;
+	stats->rx_fifo_errors	= dev->stats.rx_fifo_errors;
+	stats->rx_missed_errors = dev->stats.rx_missed_errors;
+
+	return stats;
 }
 
 static void rtl8169_net_suspend(struct net_device *dev)
@@ -6050,10 +5779,15 @@
 	if (!netif_running(dev))
 		return;
 
-	rtl_pll_power_down(tp);
-
 	netif_device_detach(dev);
 	netif_stop_queue(dev);
+
+	rtl_lock_work(tp);
+	napi_disable(&tp->napi);
+	clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+	rtl_unlock_work(tp);
+
+	rtl_pll_power_down(tp);
 }
 
 #ifdef CONFIG_PM
@@ -6076,7 +5810,12 @@
 
 	rtl_pll_power_up(tp);
 
-	rtl8169_schedule_work(dev, rtl8169_reset_task);
+	rtl_lock_work(tp);
+	napi_enable(&tp->napi);
+	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+	rtl_unlock_work(tp);
+
+	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
 static int rtl8169_resume(struct device *device)
@@ -6102,10 +5841,10 @@
 	if (!tp->TxDescArray)
 		return 0;
 
-	spin_lock_irq(&tp->lock);
+	rtl_lock_work(tp);
 	tp->saved_wolopts = __rtl8169_get_wol(tp);
 	__rtl8169_set_wol(tp, WAKE_ANY);
-	spin_unlock_irq(&tp->lock);
+	rtl_unlock_work(tp);
 
 	rtl8169_net_suspend(dev);
 
@@ -6121,10 +5860,10 @@
 	if (!tp->TxDescArray)
 		return 0;
 
-	spin_lock_irq(&tp->lock);
+	rtl_lock_work(tp);
 	__rtl8169_set_wol(tp, tp->saved_wolopts);
 	tp->saved_wolopts = 0;
-	spin_unlock_irq(&tp->lock);
+	rtl_unlock_work(tp);
 
 	rtl8169_init_phy(dev, tp);
 
@@ -6186,18 +5925,17 @@
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rtl8169_private *tp = netdev_priv(dev);
+	struct device *d = &pdev->dev;
+
+	pm_runtime_get_sync(d);
 
 	rtl8169_net_suspend(dev);
 
 	/* Restore original MAC address */
 	rtl_rar_set(tp, dev->perm_addr);
 
-	spin_lock_irq(&tp->lock);
-
 	rtl8169_hw_reset(tp);
 
-	spin_unlock_irq(&tp->lock);
-
 	if (system_state == SYSTEM_POWER_OFF) {
 		if (__rtl8169_get_wol(tp) & WAKE_ANY) {
 			rtl_wol_suspend_quirk(tp);
@@ -6207,13 +5945,362 @@
 		pci_wake_from_d3(pdev, true);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
+
+	pm_runtime_put_noidle(d);
+}
+
+static void __devexit rtl_remove_one(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_28 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_31) {
+		rtl8168_driver_stop(tp);
+	}
+
+	cancel_work_sync(&tp->wk.work);
+
+	unregister_netdev(dev);
+
+	rtl_release_firmware(tp);
+
+	if (pci_dev_run_wake(pdev))
+		pm_runtime_get_noresume(&pdev->dev);
+
+	/* restore original MAC address */
+	rtl_rar_set(tp, dev->perm_addr);
+
+	rtl_disable_msi(pdev, tp);
+	rtl8169_release_board(pdev, dev, tp->mmio_addr);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static const struct net_device_ops rtl_netdev_ops = {
+	.ndo_open		= rtl_open,
+	.ndo_stop		= rtl8169_close,
+	.ndo_get_stats64	= rtl8169_get_stats64,
+	.ndo_start_xmit		= rtl8169_start_xmit,
+	.ndo_tx_timeout		= rtl8169_tx_timeout,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= rtl8169_change_mtu,
+	.ndo_fix_features	= rtl8169_fix_features,
+	.ndo_set_features	= rtl8169_set_features,
+	.ndo_set_mac_address	= rtl_set_mac_address,
+	.ndo_do_ioctl		= rtl8169_ioctl,
+	.ndo_set_rx_mode	= rtl_set_rx_mode,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= rtl8169_netpoll,
+#endif
+
+};
+
+static const struct rtl_cfg_info {
+	void (*hw_start)(struct net_device *);
+	unsigned int region;
+	unsigned int align;
+	u16 event_slow;
+	unsigned features;
+	u8 default_ver;
+} rtl_cfg_infos [] = {
+	[RTL_CFG_0] = {
+		.hw_start	= rtl_hw_start_8169,
+		.region		= 1,
+		.align		= 0,
+		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
+		.features	= RTL_FEATURE_GMII,
+		.default_ver	= RTL_GIGA_MAC_VER_01,
+	},
+	[RTL_CFG_1] = {
+		.hw_start	= rtl_hw_start_8168,
+		.region		= 2,
+		.align		= 8,
+		.event_slow	= SYSErr | LinkChg | RxOverflow,
+		.features	= RTL_FEATURE_GMII | RTL_FEATURE_MSI,
+		.default_ver	= RTL_GIGA_MAC_VER_11,
+	},
+	[RTL_CFG_2] = {
+		.hw_start	= rtl_hw_start_8101,
+		.region		= 2,
+		.align		= 8,
+		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver |
+				  PCSTimeout,
+		.features	= RTL_FEATURE_MSI,
+		.default_ver	= RTL_GIGA_MAC_VER_13,
+	}
+};
+
+/* Cfg9346_Unlock assumed. */
+static unsigned rtl_try_msi(struct rtl8169_private *tp,
+			    const struct rtl_cfg_info *cfg)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	unsigned msi = 0;
+	u8 cfg2;
+
+	cfg2 = RTL_R8(Config2) & ~MSIEnable;
+	if (cfg->features & RTL_FEATURE_MSI) {
+		if (pci_enable_msi(tp->pci_dev)) {
+			netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n");
+		} else {
+			cfg2 |= MSIEnable;
+			msi = RTL_FEATURE_MSI;
+		}
+	}
+	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
+		RTL_W8(Config2, cfg2);
+	return msi;
+}
+
+static int __devinit
+rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
+	const unsigned int region = cfg->region;
+	struct rtl8169_private *tp;
+	struct mii_if_info *mii;
+	struct net_device *dev;
+	void __iomem *ioaddr;
+	int chipset, i;
+	int rc;
+
+	if (netif_msg_drv(&debug)) {
+		printk(KERN_INFO "%s Gigabit Ethernet driver %s loaded\n",
+		       MODULENAME, RTL8169_VERSION);
+	}
+
+	dev = alloc_etherdev(sizeof (*tp));
+	if (!dev) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	SET_NETDEV_DEV(dev, &pdev->dev);
+	dev->netdev_ops = &rtl_netdev_ops;
+	tp = netdev_priv(dev);
+	tp->dev = dev;
+	tp->pci_dev = pdev;
+	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
+
+	mii = &tp->mii;
+	mii->dev = dev;
+	mii->mdio_read = rtl_mdio_read;
+	mii->mdio_write = rtl_mdio_write;
+	mii->phy_id_mask = 0x1f;
+	mii->reg_num_mask = 0x1f;
+	mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII);
+
+	/* disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users */
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+				     PCIE_LINK_STATE_CLKPM);
+
+	/* enable device (incl. PCI PM wakeup and hotplug setup) */
+	rc = pci_enable_device(pdev);
+	if (rc < 0) {
+		netif_err(tp, probe, dev, "enable failure\n");
+		goto err_out_free_dev_1;
+	}
+
+	if (pci_set_mwi(pdev) < 0)
+		netif_info(tp, probe, dev, "Mem-Wr-Inval unavailable\n");
+
+	/* make sure PCI base addr 1 is MMIO */
+	if (!(pci_resource_flags(pdev, region) & IORESOURCE_MEM)) {
+		netif_err(tp, probe, dev,
+			  "region #%d not an MMIO resource, aborting\n",
+			  region);
+		rc = -ENODEV;
+		goto err_out_mwi_2;
+	}
+
+	/* check for weird/broken PCI region reporting */
+	if (pci_resource_len(pdev, region) < R8169_REGS_SIZE) {
+		netif_err(tp, probe, dev,
+			  "Invalid PCI region size(s), aborting\n");
+		rc = -ENODEV;
+		goto err_out_mwi_2;
+	}
+
+	rc = pci_request_regions(pdev, MODULENAME);
+	if (rc < 0) {
+		netif_err(tp, probe, dev, "could not request regions\n");
+		goto err_out_mwi_2;
+	}
+
+	tp->cp_cmd = RxChkSum;
+
+	if ((sizeof(dma_addr_t) > 4) &&
+	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && use_dac) {
+		tp->cp_cmd |= PCIDAC;
+		dev->features |= NETIF_F_HIGHDMA;
+	} else {
+		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (rc < 0) {
+			netif_err(tp, probe, dev, "DMA configuration failed\n");
+			goto err_out_free_res_3;
+		}
+	}
+
+	/* ioremap MMIO region */
+	ioaddr = ioremap(pci_resource_start(pdev, region), R8169_REGS_SIZE);
+	if (!ioaddr) {
+		netif_err(tp, probe, dev, "cannot remap MMIO, aborting\n");
+		rc = -EIO;
+		goto err_out_free_res_3;
+	}
+	tp->mmio_addr = ioaddr;
+
+	if (!pci_is_pcie(pdev))
+		netif_info(tp, probe, dev, "not PCI Express\n");
+
+	/* Identify chip attached to board */
+	rtl8169_get_mac_version(tp, dev, cfg->default_ver);
+
+	rtl_init_rxcfg(tp);
+
+	rtl_irq_disable(tp);
+
+	rtl_hw_reset(tp);
+
+	rtl_ack_events(tp, 0xffff);
+
+	pci_set_master(pdev);
+
+	/*
+	 * Pretend we are using VLANs; This bypasses a nasty bug where
+	 * Interrupts stop flowing on high load on 8110SCd controllers.
+	 */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
+		tp->cp_cmd |= RxVlan;
+
+	rtl_init_mdio_ops(tp);
+	rtl_init_pll_power_ops(tp);
+	rtl_init_jumbo_ops(tp);
+
+	rtl8169_print_mac_version(tp);
+
+	chipset = tp->mac_version;
+	tp->txd_version = rtl_chip_infos[chipset].txd_version;
+
+	RTL_W8(Cfg9346, Cfg9346_Unlock);
+	RTL_W8(Config1, RTL_R8(Config1) | PMEnable);
+	RTL_W8(Config5, RTL_R8(Config5) & PMEStatus);
+	if ((RTL_R8(Config3) & (LinkUp | MagicPacket)) != 0)
+		tp->features |= RTL_FEATURE_WOL;
+	if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0)
+		tp->features |= RTL_FEATURE_WOL;
+	tp->features |= rtl_try_msi(tp, cfg);
+	RTL_W8(Cfg9346, Cfg9346_Lock);
+
+	if (rtl_tbi_enabled(tp)) {
+		tp->set_speed = rtl8169_set_speed_tbi;
+		tp->get_settings = rtl8169_gset_tbi;
+		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
+		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
+		tp->link_ok = rtl8169_tbi_link_ok;
+		tp->do_ioctl = rtl_tbi_ioctl;
+	} else {
+		tp->set_speed = rtl8169_set_speed_xmii;
+		tp->get_settings = rtl8169_gset_xmii;
+		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
+		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
+		tp->link_ok = rtl8169_xmii_link_ok;
+		tp->do_ioctl = rtl_xmii_ioctl;
+	}
+
+	mutex_init(&tp->wk.mutex);
+
+	/* Get MAC address */
+	for (i = 0; i < ETH_ALEN; i++)
+		dev->dev_addr[i] = RTL_R8(MAC0 + i);
+	memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
+
+	SET_ETHTOOL_OPS(dev, &rtl8169_ethtool_ops);
+	dev->watchdog_timeo = RTL8169_TX_TIMEOUT;
+
+	netif_napi_add(dev, &tp->napi, rtl8169_poll, R8169_NAPI_WEIGHT);
+
+	/* don't enable SG, IP_CSUM and TSO by default - it might not work
+	 * properly for all devices */
+	dev->features |= NETIF_F_RXCSUM |
+		NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
+
+	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
+		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
+	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
+		NETIF_F_HIGHDMA;
+
+	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
+		/* 8110SCd requires hardware Rx VLAN - disallow toggling */
+		dev->hw_features &= ~NETIF_F_HW_VLAN_RX;
+
+	dev->hw_features |= NETIF_F_RXALL;
+	dev->hw_features |= NETIF_F_RXFCS;
+
+	tp->hw_start = cfg->hw_start;
+	tp->event_slow = cfg->event_slow;
+
+	tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
+		~(RxBOVF | RxFOVF) : ~0;
+
+	init_timer(&tp->timer);
+	tp->timer.data = (unsigned long) dev;
+	tp->timer.function = rtl8169_phy_timer;
+
+	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
+
+	rc = register_netdev(dev);
+	if (rc < 0)
+		goto err_out_msi_4;
+
+	pci_set_drvdata(pdev, dev);
+
+	netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n",
+		   rtl_chip_infos[chipset].name, ioaddr, dev->dev_addr,
+		   (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), pdev->irq);
+	if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) {
+		netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, "
+			   "tx checksumming: %s]\n",
+			   rtl_chip_infos[chipset].jumbo_max,
+			   rtl_chip_infos[chipset].jumbo_tx_csum ? "ok" : "ko");
+	}
+
+	if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_28 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_31) {
+		rtl8168_driver_start(tp);
+	}
+
+	device_set_wakeup_enable(&pdev->dev, tp->features & RTL_FEATURE_WOL);
+
+	if (pci_dev_run_wake(pdev))
+		pm_runtime_put_noidle(&pdev->dev);
+
+	netif_carrier_off(dev);
+
+out:
+	return rc;
+
+err_out_msi_4:
+	rtl_disable_msi(pdev, tp);
+	iounmap(ioaddr);
+err_out_free_res_3:
+	pci_release_regions(pdev);
+err_out_mwi_2:
+	pci_clear_mwi(pdev);
+	pci_disable_device(pdev);
+err_out_free_dev_1:
+	free_netdev(dev);
+	goto out;
 }
 
 static struct pci_driver rtl8169_pci_driver = {
 	.name		= MODULENAME,
 	.id_table	= rtl8169_pci_tbl,
-	.probe		= rtl8169_init_one,
-	.remove		= __devexit_p(rtl8169_remove_one),
+	.probe		= rtl_init_one,
+	.remove		= __devexit_p(rtl_remove_one),
 	.shutdown	= rtl_shutdown,
 	.driver.pm	= RTL8169_PM_OPS,
 };