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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 39 insertions, 23 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 44d431849d39..beaf28456301 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -43,6 +43,7 @@
 #include <linux/ipv6.h>
 #include <linux/icmpv6.h>
 #include <linux/random.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/tcp.h>
 #include <net/ndisc.h>
@@ -90,6 +91,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
 }
 #endif
 
+/* Helper returning the inet6 address from a given tcp socket.
+ * It can be used in TCP stack instead of inet6_sk(sk).
+ * This avoids a dereference and allow compiler optimizations.
+ * It is a specialized version of inet6_sk_generic().
+ */
+static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk)
+{
+	unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo);
+
+	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
+}
+
 static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -99,7 +112,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-		inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
+		tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
 	}
 }
 
@@ -138,7 +151,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock *inet = inet_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
 	struct ipv6_txoptions *opt;
@@ -390,7 +403,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
-	if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
+	if (ipv6_hdr(skb)->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
 		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
 		goto out;
 	}
@@ -405,7 +418,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 	}
 
-	np = inet6_sk(sk);
+	np = tcp_inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
 		if (!sock_owned_by_user(sk)) {
@@ -478,7 +491,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct ipv6_txoptions *opt;
 	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sk_buff *skb;
@@ -737,7 +750,7 @@ static void tcp_v6_init_req(struct request_sock *req,
 {
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 	struct inet_request_sock *ireq = inet_rsk(req);
-	const struct ipv6_pinfo *np = inet6_sk(sk_listener);
+	const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener);
 
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
@@ -1066,9 +1079,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 {
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp;
-	const struct ipv6_pinfo *np = inet6_sk(sk);
+	const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct ipv6_txoptions *opt;
-	struct tcp6_sock *newtcp6sk;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1088,11 +1100,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		if (!newsk)
 			return NULL;
 
-		newtcp6sk = (struct tcp6_sock *)newsk;
-		inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
+		inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
 
 		newinet = inet_sk(newsk);
-		newnp = inet6_sk(newsk);
+		newnp = tcp_inet6_sk(newsk);
 		newtp = tcp_sk(newsk);
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
@@ -1156,12 +1167,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	ip6_dst_store(newsk, dst, NULL, NULL);
 	inet6_sk_rx_dst_set(newsk, skb);
 
-	newtcp6sk = (struct tcp6_sock *)newsk;
-	inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
+	inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
 
 	newtp = tcp_sk(newsk);
 	newinet = inet_sk(newsk);
-	newnp = inet6_sk(newsk);
+	newnp = tcp_inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
@@ -1276,9 +1286,9 @@ out:
  */
 static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 {
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct tcp_sock *tp;
+	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct sk_buff *opt_skb = NULL;
+	struct tcp_sock *tp;
 
 	/* Imagine: socket is IPv6. IPv4 packet arrives,
 	   goes to IPv4 receive handler and backlogged.
@@ -1426,8 +1436,9 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
 }
 
-static int tcp_v6_rcv(struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 {
+	struct sk_buff *skb_to_free;
 	int sdif = inet6_sdif(skb);
 	const struct tcphdr *th;
 	const struct ipv6hdr *hdr;
@@ -1524,7 +1535,7 @@ process:
 			return 0;
 		}
 	}
-	if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
+	if (hdr->hop_limit < tcp_inet6_sk(sk)->min_hopcount) {
 		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
 		goto discard_and_relse;
 	}
@@ -1554,12 +1565,17 @@ process:
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
+		skb_to_free = sk->sk_rx_skb_cache;
+		sk->sk_rx_skb_cache = NULL;
 		ret = tcp_v6_do_rcv(sk, skb);
-	} else if (tcp_add_backlog(sk, skb)) {
-		goto discard_and_relse;
+	} else {
+		if (tcp_add_backlog(sk, skb))
+			goto discard_and_relse;
+		skb_to_free = NULL;
 	}
 	bh_unlock_sock(sk);
-
+	if (skb_to_free)
+		__kfree_skb(skb_to_free);
 put_and_return:
 	if (refcounted)
 		sock_put(sk);
@@ -1639,7 +1655,7 @@ do_time_wait:
 	goto discard_it;
 }
 
-static void tcp_v6_early_demux(struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
 {
 	const struct ipv6hdr *hdr;
 	const struct tcphdr *th;
@@ -1669,7 +1685,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
-				dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+				dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie);
 			if (dst &&
 			    inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
 				skb_dst_set_noref(skb, dst);