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, 56 insertions, 80 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 830466c..e174fbb 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -57,8 +57,8 @@
 #include "igb.h"
 
 #define MAJ 5
-#define MIN 2
-#define BUILD 18
+#define MIN 3
+#define BUILD 0
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
 char igb_driver_name[] = "igb";
@@ -179,6 +179,8 @@ static void igb_check_vf_rate_limit(struct igb_adapter *);
 #ifdef CONFIG_PCI_IOV
 static int igb_vf_configure(struct igb_adapter *adapter, int vf);
 static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs);
+static int igb_disable_sriov(struct pci_dev *dev);
+static int igb_pci_disable_sriov(struct pci_dev *dev);
 #endif
 
 #ifdef CONFIG_PM
@@ -1205,10 +1207,14 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 
 	/* allocate q_vector and rings */
 	q_vector = adapter->q_vector[v_idx];
-	if (!q_vector)
+	if (!q_vector) {
 		q_vector = kzalloc(size, GFP_KERNEL);
-	else
+	} else if (size > ksize(q_vector)) {
+		kfree_rcu(q_vector, rcu);
+		q_vector = kzalloc(size, GFP_KERNEL);
+	} else {
 		memset(q_vector, 0, size);
+	}
 	if (!q_vector)
 		return -ENOMEM;
 
@@ -2645,7 +2651,11 @@ err_eeprom:
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
 err_sw_init:
+	kfree(adapter->shadow_vfta);
 	igb_clear_interrupt_scheme(adapter);
+#ifdef CONFIG_PCI_IOV
+	igb_disable_sriov(pdev);
+#endif
 	pci_iounmap(pdev, hw->hw_addr);
 err_ioremap:
 	free_netdev(netdev);
@@ -2805,14 +2815,14 @@ static void igb_remove(struct pci_dev *pdev)
 	 */
 	igb_release_hw_control(adapter);
 
-	unregister_netdev(netdev);
-
-	igb_clear_interrupt_scheme(adapter);
-
 #ifdef CONFIG_PCI_IOV
 	igb_disable_sriov(pdev);
 #endif
 
+	unregister_netdev(netdev);
+
+	igb_clear_interrupt_scheme(adapter);
+
 	pci_iounmap(pdev, hw->hw_addr);
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
@@ -2847,7 +2857,7 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 		return;
 
 	pci_sriov_set_totalvfs(pdev, 7);
-	igb_pci_enable_sriov(pdev, max_vfs);
+	igb_enable_sriov(pdev, max_vfs);
 
 #endif /* CONFIG_PCI_IOV */
 }
@@ -2888,6 +2898,14 @@ static void igb_init_queue_configuration(struct igb_adapter *adapter)
 
 	adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
 
+	igb_set_flag_queue_pairs(adapter, max_rss_queues);
+}
+
+void igb_set_flag_queue_pairs(struct igb_adapter *adapter,
+			      const u32 max_rss_queues)
+{
+	struct e1000_hw *hw = &adapter->hw;
+
 	/* Determine if we need to pair queues. */
 	switch (hw->mac.type) {
 	case e1000_82575:
@@ -2968,6 +2986,8 @@ static int igb_sw_init(struct igb_adapter *adapter)
 	}
 #endif /* CONFIG_PCI_IOV */
 
+	igb_probe_vfs(adapter);
+
 	igb_init_queue_configuration(adapter);
 
 	/* Setup and initialize a copy of the hw vlan table array */
@@ -2980,8 +3000,6 @@ static int igb_sw_init(struct igb_adapter *adapter)
 		return -ENOMEM;
 	}
 
-	igb_probe_vfs(adapter);
-
 	/* Explicitly disable IRQ since the NIC can be in any state. */
 	igb_irq_disable(adapter);
 
@@ -6621,22 +6639,25 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 			    struct sk_buff *skb)
 {
 	struct page *page = rx_buffer->page;
+	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = IGB_RX_BUFSZ;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
+	unsigned int pull_len;
 
-	if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) {
-		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+	if (unlikely(skb_is_nonlinear(skb)))
+		goto add_tail_frag;
 
-		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
-			igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
-			va += IGB_TS_HDR_LEN;
-			size -= IGB_TS_HDR_LEN;
-		}
+	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
+		va += IGB_TS_HDR_LEN;
+		size -= IGB_TS_HDR_LEN;
+	}
 
+	if (likely(size <= IGB_RX_HDR_LEN)) {
 		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
 
 		/* page is not reserved, we can reuse buffer as-is */
@@ -6648,8 +6669,21 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 		return false;
 	}
 
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	va += pull_len;
+	size -= pull_len;
+
+add_tail_frag:
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			rx_buffer->page_offset, size, truesize);
+			(unsigned long)va & ~PAGE_MASK, size, truesize);
 
 	return igb_can_reuse_rx_page(rx_buffer, page, truesize);
 }
@@ -6791,62 +6825,6 @@ static bool igb_is_non_eop(struct igb_ring *rx_ring,
 }
 
 /**
- *  igb_pull_tail - igb specific version of skb_pull_tail
- *  @rx_ring: rx descriptor ring packet is being transacted on
- *  @rx_desc: pointer to the EOP Rx descriptor
- *  @skb: pointer to current skb being adjusted
- *
- *  This function is an igb specific version of __pskb_pull_tail.  The
- *  main difference between this version and the original function is that
- *  this function can make several assumptions about the state of things
- *  that allow for significant optimizations versus the standard function.
- *  As a result we can do things like drop a frag and maintain an accurate
- *  truesize for the skb.
- */
-static void igb_pull_tail(struct igb_ring *rx_ring,
-			  union e1000_adv_rx_desc *rx_desc,
-			  struct sk_buff *skb)
-{
-	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
-	unsigned char *va;
-	unsigned int pull_len;
-
-	/* it is valid to use page_address instead of kmap since we are
-	 * working with pages allocated out of the lomem pool per
-	 * alloc_page(GFP_ATOMIC)
-	 */
-	va = skb_frag_address(frag);
-
-	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
-		/* retrieve timestamp from buffer */
-		igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
-
-		/* update pointers to remove timestamp header */
-		skb_frag_size_sub(frag, IGB_TS_HDR_LEN);
-		frag->page_offset += IGB_TS_HDR_LEN;
-		skb->data_len -= IGB_TS_HDR_LEN;
-		skb->len -= IGB_TS_HDR_LEN;
-
-		/* move va to start of packet data */
-		va += IGB_TS_HDR_LEN;
-	}
-
-	/* we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
-
-	/* update all of the pointers */
-	skb_frag_size_sub(frag, pull_len);
-	frag->page_offset += pull_len;
-	skb->data_len -= pull_len;
-	skb->tail += pull_len;
-}
-
-/**
  *  igb_cleanup_headers - Correct corrupted or empty headers
  *  @rx_ring: rx descriptor ring packet is being transacted on
  *  @rx_desc: pointer to the EOP Rx descriptor
@@ -6873,10 +6851,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
 		}
 	}
 
-	/* place header in linear portion of buffer */
-	if (skb_is_nonlinear(skb))
-		igb_pull_tail(rx_ring, rx_desc, skb);
-
 	/* if eth_skb_pad returns an error the skb was freed */
 	if (eth_skb_pad(skb))
 		return true;
@@ -7445,6 +7419,7 @@ static int igb_resume(struct device *dev)
 
 	if (igb_init_interrupt_scheme(adapter, true)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		rtnl_unlock();
 		return -ENOMEM;
 	}
 
@@ -7538,6 +7513,7 @@ static int igb_sriov_reinit(struct pci_dev *dev)
 	igb_init_queue_configuration(adapter);
 
 	if (igb_init_interrupt_scheme(adapter, true)) {
+		rtnl_unlock();
 		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}