These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

4 files changed, 221 insertions, 106 deletions

diff --git a/kernel/drivers/net/ethernet/realtek/8139cp.c b/kernel/drivers/net/ethernet/realtek/8139cp.c
index d79e33b3c..deae10d74 100644
--- a/kernel/drivers/net/ethernet/realtek/8139cp.c
+++ b/kernel/drivers/net/ethernet/realtek/8139cp.c
@@ -157,6 +157,7 @@ enum {
 	NWayAdvert	= 0x66, /* MII ADVERTISE */
 	NWayLPAR	= 0x68, /* MII LPA */
 	NWayExpansion	= 0x6A, /* MII Expansion */
+	TxDmaOkLowDesc  = 0x82, /* Low 16 bit address of a Tx descriptor. */
 	Config5		= 0xD8,	/* Config5 */
 	TxPoll		= 0xD9,	/* Tell chip to check Tx descriptors for work */
 	RxMaxSize	= 0xDA, /* Max size of an Rx packet (8169 only) */
@@ -174,7 +175,7 @@ enum {
 	LastFrag	= (1 << 28), /* Final segment of a packet */
 	LargeSend	= (1 << 27), /* TCP Large Send Offload (TSO) */
 	MSSShift	= 16,	     /* MSS value position */
-	MSSMask		= 0xfff,     /* MSS value: 11 bits */
+	MSSMask		= 0x7ff,     /* MSS value: 11 bits */
 	TxError		= (1 << 23), /* Tx error summary */
 	RxError		= (1 << 20), /* Rx error summary */
 	IPCS		= (1 << 18), /* Calculate IP checksum */
@@ -341,6 +342,7 @@ struct cp_private {
 	unsigned		tx_tail;
 	struct cp_desc		*tx_ring;
 	struct sk_buff		*tx_skb[CP_TX_RING_SIZE];
+	u32			tx_opts[CP_TX_RING_SIZE];
 
 	unsigned		rx_buf_sz;
 	unsigned		wol_enabled : 1; /* Is Wake-on-LAN enabled? */
@@ -665,7 +667,7 @@ static void cp_tx (struct cp_private *cp)
 		BUG_ON(!skb);
 
 		dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
-				 le32_to_cpu(txd->opts1) & 0xffff,
+				 cp->tx_opts[tx_tail] & 0xffff,
 				 PCI_DMA_TODEVICE);
 
 		if (status & LastFrag) {
@@ -733,7 +735,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned entry;
-	u32 eor, flags;
+	u32 eor, opts1;
 	unsigned long intr_flags;
 	__le32 opts2;
 	int mss = 0;
@@ -752,7 +754,28 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 	eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 	mss = skb_shinfo(skb)->gso_size;
 
+	if (mss > MSSMask) {
+		WARN_ONCE(1, "Net bug: GSO size %d too large for 8139CP\n",
+			  mss);
+		goto out_dma_error;
+	}
+
 	opts2 = cpu_to_le32(cp_tx_vlan_tag(skb));
+	opts1 = DescOwn;
+	if (mss)
+		opts1 |= LargeSend | (mss << MSSShift);
+	else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		const struct iphdr *ip = ip_hdr(skb);
+		if (ip->protocol == IPPROTO_TCP)
+			opts1 |= IPCS | TCPCS;
+		else if (ip->protocol == IPPROTO_UDP)
+			opts1 |= IPCS | UDPCS;
+		else {
+			WARN_ONCE(1,
+				  "Net bug: asked to checksum invalid Legacy IP packet\n");
+			goto out_dma_error;
+		}
+	}
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		struct cp_desc *txd = &cp->tx_ring[entry];
@@ -768,31 +791,20 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(mapping);
 		wmb();
 
-		flags = eor | len | DescOwn | FirstFrag | LastFrag;
-
-		if (mss)
-			flags |= LargeSend | ((mss & MSSMask) << MSSShift);
-		else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			const struct iphdr *ip = ip_hdr(skb);
-			if (ip->protocol == IPPROTO_TCP)
-				flags |= IPCS | TCPCS;
-			else if (ip->protocol == IPPROTO_UDP)
-				flags |= IPCS | UDPCS;
-			else
-				WARN_ON(1);	/* we need a WARN() */
-		}
+		opts1 |= eor | len | FirstFrag | LastFrag;
 
-		txd->opts1 = cpu_to_le32(flags);
+		txd->opts1 = cpu_to_le32(opts1);
 		wmb();
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
+		cp->tx_opts[entry] = opts1;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
+			  entry, skb->len);
 	} else {
 		struct cp_desc *txd;
-		u32 first_len, first_eor;
+		u32 first_len, first_eor, ctrl;
 		dma_addr_t first_mapping;
 		int frag, first_entry = entry;
-		const struct iphdr *ip = ip_hdr(skb);
 
 		/* We must give this initial chunk to the device last.
 		 * Otherwise we could race with the device.
@@ -805,14 +817,14 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			goto out_dma_error;
 
 		cp->tx_skb[entry] = skb;
-		entry = NEXT_TX(entry);
 
 		for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) {
 			const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[frag];
 			u32 len;
-			u32 ctrl;
 			dma_addr_t mapping;
 
+			entry = NEXT_TX(entry);
+
 			len = skb_frag_size(this_frag);
 			mapping = dma_map_single(&cp->pdev->dev,
 						 skb_frag_address(this_frag),
@@ -824,19 +836,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 
 			eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 
-			ctrl = eor | len | DescOwn;
-
-			if (mss)
-				ctrl |= LargeSend |
-					((mss & MSSMask) << MSSShift);
-			else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				if (ip->protocol == IPPROTO_TCP)
-					ctrl |= IPCS | TCPCS;
-				else if (ip->protocol == IPPROTO_UDP)
-					ctrl |= IPCS | UDPCS;
-				else
-					BUG();
-			}
+			ctrl = opts1 | eor | len;
 
 			if (frag == skb_shinfo(skb)->nr_frags - 1)
 				ctrl |= LastFrag;
@@ -849,8 +849,8 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 			txd->opts1 = cpu_to_le32(ctrl);
 			wmb();
 
+			cp->tx_opts[entry] = ctrl;
 			cp->tx_skb[entry] = skb;
-			entry = NEXT_TX(entry);
 		}
 
 		txd = &cp->tx_ring[first_entry];
@@ -858,27 +858,17 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
 		txd->addr = cpu_to_le64(first_mapping);
 		wmb();
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			if (ip->protocol == IPPROTO_TCP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | TCPCS);
-			else if (ip->protocol == IPPROTO_UDP)
-				txd->opts1 = cpu_to_le32(first_eor | first_len |
-							 FirstFrag | DescOwn |
-							 IPCS | UDPCS);
-			else
-				BUG();
-		} else
-			txd->opts1 = cpu_to_le32(first_eor | first_len |
-						 FirstFrag | DescOwn);
+		ctrl = opts1 | first_eor | first_len | FirstFrag;
+		txd->opts1 = cpu_to_le32(ctrl);
 		wmb();
+
+		cp->tx_opts[first_entry] = ctrl;
+		netif_dbg(cp, tx_queued, cp->dev, "tx queued, slots %d-%d, skblen %d\n",
+			  first_entry, entry, skb->len);
 	}
-	cp->tx_head = entry;
+	cp->tx_head = NEXT_TX(entry);
 
 	netdev_sent_queue(dev, skb->len);
-	netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n",
-		  entry, skb->len);
 	if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1))
 		netif_stop_queue(dev);
 
@@ -1115,6 +1105,7 @@ static int cp_init_rings (struct cp_private *cp)
 {
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
 	cp->tx_ring[CP_TX_RING_SIZE - 1].opts1 = cpu_to_le32(RingEnd);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	cp_init_rings_index(cp);
 
@@ -1151,7 +1142,7 @@ static void cp_clean_rings (struct cp_private *cp)
 			desc = cp->rx_ring + i;
 			dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr),
 					 cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
-			dev_kfree_skb(cp->rx_skb[i]);
+			dev_kfree_skb_any(cp->rx_skb[i]);
 		}
 	}
 
@@ -1164,7 +1155,7 @@ static void cp_clean_rings (struct cp_private *cp)
 					 le32_to_cpu(desc->opts1) & 0xffff,
 					 PCI_DMA_TODEVICE);
 			if (le32_to_cpu(desc->opts1) & LastFrag)
-				dev_kfree_skb(skb);
+				dev_kfree_skb_any(skb);
 			cp->dev->stats.tx_dropped++;
 		}
 	}
@@ -1172,6 +1163,7 @@ static void cp_clean_rings (struct cp_private *cp)
 
 	memset(cp->rx_ring, 0, sizeof(struct cp_desc) * CP_RX_RING_SIZE);
 	memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE);
+	memset(cp->tx_opts, 0, sizeof(cp->tx_opts));
 
 	memset(cp->rx_skb, 0, sizeof(struct sk_buff *) * CP_RX_RING_SIZE);
 	memset(cp->tx_skb, 0, sizeof(struct sk_buff *) * CP_TX_RING_SIZE);
@@ -1249,7 +1241,7 @@ static void cp_tx_timeout(struct net_device *dev)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
-	int rc;
+	int rc, i;
 
 	netdev_warn(dev, "Transmit timeout, status %2x %4x %4x %4x\n",
 		    cpr8(Cmd), cpr16(CpCmd),
@@ -1257,13 +1249,26 @@ static void cp_tx_timeout(struct net_device *dev)
 
 	spin_lock_irqsave(&cp->lock, flags);
 
+	netif_dbg(cp, tx_err, cp->dev, "TX ring head %d tail %d desc %x\n",
+		  cp->tx_head, cp->tx_tail, cpr16(TxDmaOkLowDesc));
+	for (i = 0; i < CP_TX_RING_SIZE; i++) {
+		netif_dbg(cp, tx_err, cp->dev,
+			  "TX slot %d @%p: %08x (%08x) %08x %llx %p\n",
+			  i, &cp->tx_ring[i], le32_to_cpu(cp->tx_ring[i].opts1),
+			  cp->tx_opts[i], le32_to_cpu(cp->tx_ring[i].opts2),
+			  le64_to_cpu(cp->tx_ring[i].addr),
+			  cp->tx_skb[i]);
+	}
+
 	cp_stop_hw(cp);
 	cp_clean_rings(cp);
 	rc = cp_init_rings(cp);
 	cp_start_hw(cp);
-	cp_enable_irq(cp);
+	__cp_set_rx_mode(dev);
+	cpw16_f(IntrMask, cp_norx_intr_mask);
 
 	netif_wake_queue(dev);
+	napi_schedule_irqoff(&cp->napi);
 
 	spin_unlock_irqrestore(&cp->lock, flags);
 }
@@ -1853,6 +1858,15 @@ static void cp_set_d3_state (struct cp_private *cp)
 	pci_set_power_state (cp->pdev, PCI_D3hot);
 }
 
+static netdev_features_t cp_features_check(struct sk_buff *skb,
+					   struct net_device *dev,
+					   netdev_features_t features)
+{
+	if (skb_shinfo(skb)->gso_size > MSSMask)
+		features &= ~NETIF_F_TSO;
+
+	return vlan_features_check(skb, features);
+}
 static const struct net_device_ops cp_netdev_ops = {
 	.ndo_open		= cp_open,
 	.ndo_stop		= cp_close,
@@ -1865,6 +1879,7 @@ static const struct net_device_ops cp_netdev_ops = {
 	.ndo_tx_timeout		= cp_tx_timeout,
 	.ndo_set_features	= cp_set_features,
 	.ndo_change_mtu		= cp_change_mtu,
+	.ndo_features_check	= cp_features_check,
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= cp_poll_controller,
@@ -1984,12 +1999,12 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->ethtool_ops = &cp_ethtool_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
-	dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+	dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
+		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (pci_using_dac)
 		dev->features |= NETIF_F_HIGHDMA;
 
-	/* disabled by default until verified */
 	dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
diff --git a/kernel/drivers/net/ethernet/realtek/8139too.c b/kernel/drivers/net/ethernet/realtek/8139too.c
index b5156963c..d987d571f 100644
--- a/kernel/drivers/net/ethernet/realtek/8139too.c
+++ b/kernel/drivers/net/ethernet/realtek/8139too.c
@@ -2388,7 +2388,6 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *
 	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
-	info->regdump_len = tp->regs_len;
 }
 
 static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/kernel/drivers/net/ethernet/realtek/Kconfig b/kernel/drivers/net/ethernet/realtek/Kconfig
index ae5d02709..7c69f4c81 100644
--- a/kernel/drivers/net/ethernet/realtek/Kconfig
+++ b/kernel/drivers/net/ethernet/realtek/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_REALTEK
 	default y
 	depends on PCI || (PARPORT && X86)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -24,8 +22,7 @@ config ATP
 	select CRC32
 	---help---
 	  This is a network (Ethernet) device which attaches to your parallel
-	  port. Read <file:drivers/net/ethernet/realtek/atp.c> as well as the
-	  Ethernet-HOWTO, available from <http://www.tldp.org/docs.html#howto>,
+	  port. Read the file <file:drivers/net/ethernet/realtek/atp.c>
 	  if you want to use this.  If you intend to use this driver, you
 	  should have said N to the "Parallel printer support", because the two
 	  drivers don't like each other.
@@ -40,9 +37,7 @@ config 8139CP
 	select MII
 	---help---
 	  This is a driver for the Fast Ethernet PCI network cards based on
-	  the RTL8139C+ chips. If you have one of those, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  the RTL8139C+ chips. If you have one of those, say Y here.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called 8139cp.  This is recommended.
@@ -54,8 +49,7 @@ config 8139TOO
 	select MII
 	---help---
 	  This is a driver for the Fast Ethernet PCI network cards based on
-	  the RTL 8129/8130/8139 chips. If you have one of those, say Y and
-	  read the Ethernet-HOWTO <http://www.tldp.org/docs.html#howto>.
+	  the RTL 8129/8130/8139 chips. If you have one of those, say Y here.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called 8139too.  This is recommended.
diff --git a/kernel/drivers/net/ethernet/realtek/r8169.c b/kernel/drivers/net/ethernet/realtek/r8169.c
index 3df51faf1..79ef799f8 100644
--- a/kernel/drivers/net/ethernet/realtek/r8169.c
+++ b/kernel/drivers/net/ethernet/realtek/r8169.c
@@ -637,6 +637,9 @@ enum rtl_register_content {
 	/* _TBICSRBit */
 	TBILinkOK	= 0x02000000,
 
+	/* ResetCounterCommand */
+	CounterReset	= 0x1,
+
 	/* DumpCounterCommand */
 	CounterDump	= 0x8,
 
@@ -747,6 +750,13 @@ struct rtl8169_counters {
 	__le16	tx_underun;
 };
 
+struct rtl8169_tc_offsets {
+	bool	inited;
+	__le64	tx_errors;
+	__le32	tx_multi_collision;
+	__le16	tx_aborted;
+};
+
 enum rtl_flag {
 	RTL_FLAG_TASK_ENABLED,
 	RTL_FLAG_TASK_SLOW_PENDING,
@@ -823,7 +833,9 @@ struct rtl8169_private {
 	unsigned features;
 
 	struct mii_if_info mii;
-	struct rtl8169_counters counters;
+	dma_addr_t counters_phys_addr;
+	struct rtl8169_counters *counters;
+	struct rtl8169_tc_offsets tc_offset;
 	u32 saved_wolopts;
 	u32 opts1_mask;
 
@@ -2183,65 +2195,121 @@ DECLARE_RTL_COND(rtl_counters_cond)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	return RTL_R32(CounterAddrLow) & CounterDump;
+	return RTL_R32(CounterAddrLow) & (CounterReset | CounterDump);
 }
 
-static void rtl8169_update_counters(struct net_device *dev)
+static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
-	struct device *d = &tp->pci_dev->dev;
-	struct rtl8169_counters *counters;
-	dma_addr_t paddr;
+	dma_addr_t paddr = tp->counters_phys_addr;
 	u32 cmd;
+	bool ret;
+
+	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
+	cmd = (u64)paddr & DMA_BIT_MASK(32);
+	RTL_W32(CounterAddrLow, cmd);
+	RTL_W32(CounterAddrLow, cmd | counter_cmd);
+
+	ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
+
+	RTL_W32(CounterAddrLow, 0);
+	RTL_W32(CounterAddrHigh, 0);
+
+	return ret;
+}
+
+static bool rtl8169_reset_counters(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	/*
+	 * Versions prior to RTL_GIGA_MAC_VER_19 don't support resetting the
+	 * tally counters.
+	 */
+	if (tp->mac_version < RTL_GIGA_MAC_VER_19)
+		return true;
+
+	return rtl8169_do_counters(dev, CounterReset);
+}
+
+static bool rtl8169_update_counters(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	void __iomem *ioaddr = tp->mmio_addr;
 
 	/*
 	 * Some chips are unable to dump tally counters when the receiver
 	 * is disabled.
 	 */
 	if ((RTL_R8(ChipCmd) & CmdRxEnb) == 0)
-		return;
+		return true;
 
-	counters = dma_alloc_coherent(d, sizeof(*counters), &paddr, GFP_KERNEL);
-	if (!counters)
-		return;
+	return rtl8169_do_counters(dev, CounterDump);
+}
 
-	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
-	cmd = (u64)paddr & DMA_BIT_MASK(32);
-	RTL_W32(CounterAddrLow, cmd);
-	RTL_W32(CounterAddrLow, cmd | CounterDump);
+static bool rtl8169_init_counter_offsets(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_counters *counters = tp->counters;
+	bool ret = false;
+
+	/*
+	 * rtl8169_init_counter_offsets is called from rtl_open.  On chip
+	 * versions prior to RTL_GIGA_MAC_VER_19 the tally counters are only
+	 * reset by a power cycle, while the counter values collected by the
+	 * driver are reset at every driver unload/load cycle.
+	 *
+	 * To make sure the HW values returned by @get_stats64 match the SW
+	 * values, we collect the initial values at first open(*) and use them
+	 * as offsets to normalize the values returned by @get_stats64.
+	 *
+	 * (*) We can't call rtl8169_init_counter_offsets from rtl_init_one
+	 * for the reason stated in rtl8169_update_counters; CmdRxEnb is only
+	 * set at open time by rtl_hw_start.
+	 */
 
-	if (rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000))
-		memcpy(&tp->counters, counters, sizeof(*counters));
+	if (tp->tc_offset.inited)
+		return true;
 
-	RTL_W32(CounterAddrLow, 0);
-	RTL_W32(CounterAddrHigh, 0);
+	/* If both, reset and update fail, propagate to caller. */
+	if (rtl8169_reset_counters(dev))
+		ret = true;
+
+	if (rtl8169_update_counters(dev))
+		ret = true;
 
-	dma_free_coherent(d, sizeof(*counters), counters, paddr);
+	tp->tc_offset.tx_errors = counters->tx_errors;
+	tp->tc_offset.tx_multi_collision = counters->tx_multi_collision;
+	tp->tc_offset.tx_aborted = counters->tx_aborted;
+	tp->tc_offset.inited = true;
+
+	return ret;
 }
 
 static void rtl8169_get_ethtool_stats(struct net_device *dev,
 				      struct ethtool_stats *stats, u64 *data)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_counters *counters = tp->counters;
 
 	ASSERT_RTNL();
 
 	rtl8169_update_counters(dev);
 
-	data[0] = le64_to_cpu(tp->counters.tx_packets);
-	data[1] = le64_to_cpu(tp->counters.rx_packets);
-	data[2] = le64_to_cpu(tp->counters.tx_errors);
-	data[3] = le32_to_cpu(tp->counters.rx_errors);
-	data[4] = le16_to_cpu(tp->counters.rx_missed);
-	data[5] = le16_to_cpu(tp->counters.align_errors);
-	data[6] = le32_to_cpu(tp->counters.tx_one_collision);
-	data[7] = le32_to_cpu(tp->counters.tx_multi_collision);
-	data[8] = le64_to_cpu(tp->counters.rx_unicast);
-	data[9] = le64_to_cpu(tp->counters.rx_broadcast);
-	data[10] = le32_to_cpu(tp->counters.rx_multicast);
-	data[11] = le16_to_cpu(tp->counters.tx_aborted);
-	data[12] = le16_to_cpu(tp->counters.tx_underun);
+	data[0] = le64_to_cpu(counters->tx_packets);
+	data[1] = le64_to_cpu(counters->rx_packets);
+	data[2] = le64_to_cpu(counters->tx_errors);
+	data[3] = le32_to_cpu(counters->rx_errors);
+	data[4] = le16_to_cpu(counters->rx_missed);
+	data[5] = le16_to_cpu(counters->align_errors);
+	data[6] = le32_to_cpu(counters->tx_one_collision);
+	data[7] = le32_to_cpu(counters->tx_multi_collision);
+	data[8] = le64_to_cpu(counters->rx_unicast);
+	data[9] = le64_to_cpu(counters->rx_broadcast);
+	data[10] = le32_to_cpu(counters->rx_multicast);
+	data[11] = le16_to_cpu(counters->tx_aborted);
+	data[12] = le16_to_cpu(counters->tx_underun);
 }
 
 static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -4875,10 +4943,12 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_46:
 	case RTL_GIGA_MAC_VER_47:
 	case RTL_GIGA_MAC_VER_48:
+		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+		break;
 	case RTL_GIGA_MAC_VER_49:
 	case RTL_GIGA_MAC_VER_50:
 	case RTL_GIGA_MAC_VER_51:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	default:
 		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST);
@@ -6011,7 +6081,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 	struct pci_dev *pdev = tp->pci_dev;
-	u16 rg_saw_cnt;
+	int rg_saw_cnt;
 	u32 data;
 	static const struct ephy_info e_info_8168h_1[] = {
 		{ 0x1e, 0x0800,	0x0001 },
@@ -7359,6 +7429,9 @@ process_pkt:
 
 			rtl8169_rx_vlan_tag(desc, skb);
 
+			if (skb->pkt_type == PACKET_MULTICAST)
+				dev->stats.multicast++;
+
 			napi_gro_receive(&tp->napi, skb);
 
 			u64_stats_update_begin(&tp->rx_stats.syncp);
@@ -7629,6 +7702,9 @@ static int rtl_open(struct net_device *dev)
 
 	rtl_hw_start(dev);
 
+	if (!rtl8169_init_counter_offsets(dev))
+		netif_warn(tp, hw, dev, "counter reset/update failed\n");
+
 	netif_start_queue(dev);
 
 	rtl_unlock_work(tp);
@@ -7661,6 +7737,7 @@ 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;
+	struct rtl8169_counters *counters = tp->counters;
 	unsigned int start;
 
 	if (netif_running(dev))
@@ -7672,7 +7749,6 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->rx_bytes	= tp->rx_stats.bytes;
 	} while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start));
 
-
 	do {
 		start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp);
 		stats->tx_packets = tp->tx_stats.packets;
@@ -7686,6 +7762,24 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	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;
+	stats->multicast	= dev->stats.multicast;
+
+	/*
+	 * Fetch additonal counter values missing in stats collected by driver
+	 * from tally counters.
+	 */
+	rtl8169_update_counters(dev);
+
+	/*
+	 * Subtract values fetched during initalization.
+	 * See rtl8169_init_counter_offsets for a description why we do that.
+	 */
+	stats->tx_errors = le64_to_cpu(counters->tx_errors) -
+		le64_to_cpu(tp->tc_offset.tx_errors);
+	stats->collisions = le32_to_cpu(counters->tx_multi_collision) -
+		le32_to_cpu(tp->tc_offset.tx_multi_collision);
+	stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) -
+		le16_to_cpu(tp->tc_offset.tx_aborted);
 
 	return stats;
 }
@@ -7886,6 +7980,9 @@ static void rtl_remove_one(struct pci_dev *pdev)
 
 	unregister_netdev(dev);
 
+	dma_free_coherent(&tp->pci_dev->dev, sizeof(*tp->counters),
+			  tp->counters, tp->counters_phys_addr);
+
 	rtl_release_firmware(tp);
 
 	if (pci_dev_run_wake(pdev))
@@ -8311,9 +8408,16 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
+	tp->counters = dma_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
+					   &tp->counters_phys_addr, GFP_KERNEL);
+	if (!tp->counters) {
+		rc = -ENOMEM;
+		goto err_out_msi_4;
+	}
+
 	rc = register_netdev(dev);
 	if (rc < 0)
-		goto err_out_msi_4;
+		goto err_out_cnt_5;
 
 	pci_set_drvdata(pdev, dev);
 
@@ -8347,6 +8451,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 out:
 	return rc;
 
+err_out_cnt_5:
+	dma_free_coherent(&pdev->dev, sizeof(*tp->counters), tp->counters,
+			  tp->counters_phys_addr);
 err_out_msi_4:
 	netif_napi_del(&tp->napi);
 	rtl_disable_msi(pdev, tp);