Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 149 insertions, 15 deletions

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f790f61ea78a..24dcbe62412a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/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,
@@ -824,6 +834,7 @@ struct rtl8169_private {
 
 	struct mii_if_info mii;
 	struct rtl8169_counters counters;
+	struct rtl8169_tc_offsets tc_offset;
 	u32 saved_wolopts;
 	u32 opts1_mask;
 
@@ -2179,6 +2190,73 @@ static int rtl8169_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
+static struct rtl8169_counters *rtl8169_map_counters(struct net_device *dev,
+						     dma_addr_t *paddr,
+						     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;
+	u32 cmd;
+
+	counters = dma_alloc_coherent(d, sizeof(*counters), paddr, GFP_KERNEL);
+	if (counters) {
+		RTL_W32(CounterAddrHigh, (u64)*paddr >> 32);
+		cmd = (u64)*paddr & DMA_BIT_MASK(32);
+		RTL_W32(CounterAddrLow, cmd);
+		RTL_W32(CounterAddrLow, cmd | counter_cmd);
+	}
+	return counters;
+}
+
+static void rtl8169_unmap_counters (struct net_device *dev,
+				    dma_addr_t paddr,
+				    struct rtl8169_counters *counters)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	void __iomem *ioaddr = tp->mmio_addr;
+	struct device *d = &tp->pci_dev->dev;
+
+	RTL_W32(CounterAddrLow, 0);
+	RTL_W32(CounterAddrHigh, 0);
+
+	dma_free_coherent(d, sizeof(*counters), counters, paddr);
+}
+
+DECLARE_RTL_COND(rtl_reset_counters_cond)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+
+	return RTL_R32(CounterAddrLow) & CounterReset;
+}
+
+static bool rtl8169_reset_counters(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_counters *counters;
+	dma_addr_t paddr;
+	bool ret = true;
+
+	/*
+	 * 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;
+
+	counters = rtl8169_map_counters(dev, &paddr, CounterReset);
+	if (!counters)
+		return false;
+
+	if (!rtl_udelay_loop_wait_low(tp, &rtl_reset_counters_cond, 10, 1000))
+		ret = false;
+
+	rtl8169_unmap_counters(dev, paddr, counters);
+
+	return ret;
+}
+
 DECLARE_RTL_COND(rtl_counters_cond)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
@@ -2186,38 +2264,71 @@ DECLARE_RTL_COND(rtl_counters_cond)
 	return RTL_R32(CounterAddrLow) & CounterDump;
 }
 
-static void rtl8169_update_counters(struct net_device *dev)
+static bool rtl8169_update_counters(struct net_device *dev)
 {
 	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;
-	u32 cmd;
+	bool ret = true;
 
 	/*
 	 * 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);
+	counters = rtl8169_map_counters(dev, &paddr, CounterDump);
 	if (!counters)
-		return;
-
-	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
-	cmd = (u64)paddr & DMA_BIT_MASK(32);
-	RTL_W32(CounterAddrLow, cmd);
-	RTL_W32(CounterAddrLow, cmd | CounterDump);
+		return false;
 
 	if (rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000))
 		memcpy(&tp->counters, counters, sizeof(*counters));
+	else
+		ret = false;
 
-	RTL_W32(CounterAddrLow, 0);
-	RTL_W32(CounterAddrHigh, 0);
+	rtl8169_unmap_counters(dev, paddr, counters);
 
-	dma_free_coherent(d, sizeof(*counters), counters, paddr);
+	return ret;
+}
+
+static bool rtl8169_init_counter_offsets(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	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 (tp->tc_offset.inited)
+		return true;
+
+	/* If both, reset and update fail, propagate to caller. */
+	if (rtl8169_reset_counters(dev))
+		ret = true;
+
+	if (rtl8169_update_counters(dev))
+		ret = true;
+
+	tp->tc_offset.tx_errors = tp->counters.tx_errors;
+	tp->tc_offset.tx_multi_collision = tp->counters.tx_multi_collision;
+	tp->tc_offset.tx_aborted = tp->counters.tx_aborted;
+	tp->tc_offset.inited = true;
+
+	return ret;
 }
 
 static void rtl8169_get_ethtool_stats(struct net_device *dev,
@@ -7367,6 +7478,9 @@ process_pkt:
 			tp->rx_stats.packets++;
 			tp->rx_stats.bytes += pkt_size;
 			u64_stats_update_end(&tp->rx_stats.syncp);
+
+			if (skb->pkt_type == PACKET_MULTICAST)
+				dev->stats.multicast++;
 		}
 release_descriptor:
 		desc->opts2 = 0;
@@ -7631,6 +7745,9 @@ 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);
@@ -7674,7 +7791,6 @@ 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;
@@ -7688,6 +7804,24 @@ 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(tp->counters.tx_errors) -
+		le64_to_cpu(tp->tc_offset.tx_errors);
+	stats->collisions = le32_to_cpu(tp->counters.tx_multi_collision) -
+		le32_to_cpu(tp->tc_offset.tx_multi_collision);
+	stats->tx_aborted_errors = le16_to_cpu(tp->counters.tx_aborted) -
+		le16_to_cpu(tp->tc_offset.tx_aborted);
 
 	return stats;
 }