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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 90 insertions, 19 deletions

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 72ab7b6bf20b..3e0a695537e2 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -46,6 +46,8 @@
 #include <asm/vio.h>
 #include <asm/iommu.h>
 #include <asm/firmware.h>
+#include <net/tcp.h>
+#include <net/ip6_checksum.h>
 
 #include "ibmveth.h"
 
@@ -808,8 +810,7 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data)
 
 	ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr);
 
-	if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
-	    !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
+	if (ret == H_SUCCESS &&
 	    (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
 		ret4 = h_illan_attributes(adapter->vdev->unit_address, clr_attr,
 					 set_attr, &ret_attr);
@@ -1040,6 +1041,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 	dma_addr_t dma_addr;
 	unsigned long mss = 0;
 
+	/* veth doesn't handle frag_list, so linearize the skb.
+	 * When GRO is enabled SKB's can have frag_list.
+	 */
+	if (adapter->is_active_trunk &&
+	    skb_has_frag_list(skb) && __skb_linearize(skb)) {
+		netdev->stats.tx_dropped++;
+		goto out;
+	}
+
 	/*
 	 * veth handles a maximum of 6 segments including the header, so
 	 * we have to linearize the skb if there are more than this.
@@ -1064,9 +1074,6 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 	desc_flags = IBMVETH_BUF_VALID;
 
-	if (skb_is_gso(skb) && adapter->fw_large_send_support)
-		desc_flags |= IBMVETH_BUF_LRG_SND;
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		unsigned char *buf = skb_transport_header(skb) +
 						skb->csum_offset;
@@ -1076,6 +1083,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 		/* Need to zero out the checksum */
 		buf[0] = 0;
 		buf[1] = 0;
+
+		if (skb_is_gso(skb) && adapter->fw_large_send_support)
+			desc_flags |= IBMVETH_BUF_LRG_SND;
 	}
 
 retry_bounce:
@@ -1128,7 +1138,7 @@ retry_bounce:
 		descs[i+1].fields.address = dma_addr;
 	}
 
-	if (skb_is_gso(skb)) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		if (adapter->fw_large_send_support) {
 			mss = (unsigned long)skb_shinfo(skb)->gso_size;
 			adapter->tx_large_packets++;
@@ -1232,6 +1242,71 @@ static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
 	}
 }
 
+static void ibmveth_rx_csum_helper(struct sk_buff *skb,
+				   struct ibmveth_adapter *adapter)
+{
+	struct iphdr *iph = NULL;
+	struct ipv6hdr *iph6 = NULL;
+	__be16 skb_proto = 0;
+	u16 iphlen = 0;
+	u16 iph_proto = 0;
+	u16 tcphdrlen = 0;
+
+	skb_proto = be16_to_cpu(skb->protocol);
+
+	if (skb_proto == ETH_P_IP) {
+		iph = (struct iphdr *)skb->data;
+
+		/* If the IP checksum is not offloaded and if the packet
+		 *  is large send, the checksum must be rebuilt.
+		 */
+		if (iph->check == 0xffff) {
+			iph->check = 0;
+			iph->check = ip_fast_csum((unsigned char *)iph,
+						  iph->ihl);
+		}
+
+		iphlen = iph->ihl * 4;
+		iph_proto = iph->protocol;
+	} else if (skb_proto == ETH_P_IPV6) {
+		iph6 = (struct ipv6hdr *)skb->data;
+		iphlen = sizeof(struct ipv6hdr);
+		iph_proto = iph6->nexthdr;
+	}
+
+	/* In OVS environment, when a flow is not cached, specifically for a
+	 * new TCP connection, the first packet information is passed up
+	 * the user space for finding a flow. During this process, OVS computes
+	 * checksum on the first packet when CHECKSUM_PARTIAL flag is set.
+	 *
+	 * Given that we zeroed out TCP checksum field in transmit path
+	 * (refer ibmveth_start_xmit routine) as we set "no checksum bit",
+	 * OVS computed checksum will be incorrect w/o TCP pseudo checksum
+	 * in the packet. This leads to OVS dropping the packet and hence
+	 * TCP retransmissions are seen.
+	 *
+	 * So, re-compute TCP pseudo header checksum.
+	 */
+	if (iph_proto == IPPROTO_TCP && adapter->is_active_trunk) {
+		struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen);
+
+		tcphdrlen = skb->len - iphlen;
+
+		/* Recompute TCP pseudo header checksum */
+		if (skb_proto == ETH_P_IP)
+			tcph->check = ~csum_tcpudp_magic(iph->saddr,
+					iph->daddr, tcphdrlen, iph_proto, 0);
+		else if (skb_proto == ETH_P_IPV6)
+			tcph->check = ~csum_ipv6_magic(&iph6->saddr,
+					&iph6->daddr, tcphdrlen, iph_proto, 0);
+
+		/* Setup SKB fields for checksum offload */
+		skb_partial_csum_set(skb, iphlen,
+				     offsetof(struct tcphdr, check));
+		skb_reset_network_header(skb);
+	}
+}
+
 static int ibmveth_poll(struct napi_struct *napi, int budget)
 {
 	struct ibmveth_adapter *adapter =
@@ -1239,7 +1314,6 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	struct net_device *netdev = adapter->netdev;
 	int frames_processed = 0;
 	unsigned long lpar_rc;
-	struct iphdr *iph;
 	u16 mss = 0;
 
 restart_poll:
@@ -1297,17 +1371,7 @@ restart_poll:
 
 			if (csum_good) {
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
-				if (be16_to_cpu(skb->protocol) == ETH_P_IP) {
-					iph = (struct iphdr *)skb->data;
-
-					/* If the IP checksum is not offloaded and if the packet
-					 *  is large send, the checksum must be rebuilt.
-					 */
-					if (iph->check == 0xffff) {
-						iph->check = 0;
-						iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
-					}
-				}
+				ibmveth_rx_csum_helper(skb, adapter);
 			}
 
 			if (length > netdev->mtu + ETH_HLEN) {
@@ -1626,6 +1690,13 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		netdev->hw_features |= NETIF_F_TSO;
 	}
 
+	adapter->is_active_trunk = false;
+	if (ret == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK)) {
+		adapter->is_active_trunk = true;
+		netdev->hw_features |= NETIF_F_FRAGLIST;
+		netdev->features |= NETIF_F_FRAGLIST;
+	}
+
 	netdev->min_mtu = IBMVETH_MIN_MTU;
 	netdev->max_mtu = ETH_MAX_MTU;
 
@@ -1843,7 +1914,7 @@ static struct vio_device_id ibmveth_device_table[] = {
 };
 MODULE_DEVICE_TABLE(vio, ibmveth_device_table);
 
-static struct dev_pm_ops ibmveth_pm_ops = {
+static const struct dev_pm_ops ibmveth_pm_ops = {
 	.resume = ibmveth_resume
 };