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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 93 insertions, 77 deletions

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6ba535b6feb..189dc4ae3eca 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,72 +148,85 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const struct in6_addr *daddr, __be16 dport,
 				int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
 
-	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
-			sk->sk_family == PF_INET6) {
-		struct inet_sock *inet = inet_sk(sk);
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    sk->sk_family != PF_INET6)
+		return -1;
 
-		score = 0;
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
-				return -1;
-			score++;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score++;
-		}
+	score = 0;
+	inet = inet_sk(sk);
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
+			return -1;
+		score++;
+	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+			return -1;
+		score++;
+	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
+			return -1;
+		score++;
 	}
+
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score++;
+	}
+
 	return score;
 }
 
 #define SCORE2_MAX (1 + 1 + 1)
 static inline int compute_score2(struct sock *sk, struct net *net,
-				const struct in6_addr *saddr, __be16 sport,
-				const struct in6_addr *daddr, unsigned short hnum,
-				int dif)
+				 const struct in6_addr *saddr, __be16 sport,
+				 const struct in6_addr *daddr,
+				 unsigned short hnum, int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
 
-	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
-			sk->sk_family == PF_INET6) {
-		struct inet_sock *inet = inet_sk(sk);
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    sk->sk_family != PF_INET6)
+		return -1;
 
-		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+	if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+		return -1;
+
+	score = 0;
+	inet = inet_sk(sk);
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
 			return -1;
-		score = 0;
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
-				return -1;
-			score++;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score++;
-		}
+		score++;
 	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
+			return -1;
+		score++;
+	}
+
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score++;
+	}
+
 	return score;
 }
 
-
 /* called with read_rcu_lock() */
 static struct sock *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
@@ -357,7 +370,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 	struct sock *sk;
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 
-	if (unlikely(sk = skb_steal_sock(skb)))
+	sk = skb_steal_sock(skb);
+	if (unlikely(sk))
 		return sk;
 	return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
@@ -424,10 +438,10 @@ try_again:
 	}
 
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
+					    msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg);
 		if (err == -EINVAL)
 			goto csum_copy_err;
 	}
@@ -577,6 +591,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
@@ -659,15 +674,13 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
-				" %d while full coverage %d requested\n",
-				UDP_SKB_CB(skb)->cscov, skb->len);
+			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
+					    UDP_SKB_CB(skb)->cscov, skb->len);
 			goto drop;
 		}
 		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d "
-						    "too small, need min %d\n",
-				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
+					    UDP_SKB_CB(skb)->cscov, up->pcrlen);
 			goto drop;
 		}
 	}
@@ -760,9 +773,9 @@ static void udp6_csum_zero_error(struct sk_buff *skb)
 	/* RFC 2460 section 8.1 says that we SHOULD log
 	 * this error. Well, it is reasonable.
 	 */
-	LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
-		       &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
-		       &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
+	net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
+			    &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
+			    &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
 }
 
 /*
@@ -771,7 +784,7 @@ static void udp6_csum_zero_error(struct sk_buff *skb)
  */
 static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
-		struct udp_table *udptable)
+		struct udp_table *udptable, int proto)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	const struct udphdr *uh = udp_hdr(skb);
@@ -781,6 +794,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	int dif = inet6_iif(skb);
 	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
+	bool inner_flushed = false;
 
 	if (use_hash2) {
 		hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
@@ -803,6 +817,7 @@ start_lookup:
 		    (uh->check || udp_sk(sk)->no_check6_rx)) {
 			if (unlikely(count == ARRAY_SIZE(stack))) {
 				flush_stack(stack, count, skb, ~0);
+				inner_flushed = true;
 				count = 0;
 			}
 			stack[count++] = sk;
@@ -821,7 +836,10 @@ start_lookup:
 	if (count) {
 		flush_stack(stack, count, skb, count - 1);
 	} else {
-		kfree_skb(skb);
+		if (!inner_flushed)
+			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					 proto == IPPROTO_UDPLITE);
+		consume_skb(skb);
 	}
 	return 0;
 }
@@ -873,7 +891,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 */
 	if (ipv6_addr_is_multicast(daddr))
 		return __udp6_lib_mcast_deliver(net, skb,
-				saddr, daddr, udptable);
+				saddr, daddr, udptable, proto);
 
 	/* Unicast */
 
@@ -925,14 +943,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	return 0;
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
-		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
-		       saddr,
-		       ntohs(uh->source),
-		       ulen,
-		       skb->len,
-		       daddr,
-		       ntohs(uh->dest));
+	net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
+			    proto == IPPROTO_UDPLITE ? "-Lite" : "",
+			    saddr, ntohs(uh->source),
+			    ulen, skb->len,
+			    daddr, ntohs(uh->dest));
 	goto discard;
 csum_error:
 	UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
@@ -1025,7 +1040,8 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	fl6 = &inet->cork.fl.u.ip6;
 
 	/* Grab the skbuff where UDP header space exists. */
-	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
+	skb = skb_peek(&sk->sk_write_queue);
+	if (skb == NULL)
 		goto out;
 
 	/*
@@ -1284,7 +1300,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
+		net_dbg_ratelimited("udp cork app bug 2\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1296,7 +1312,7 @@ do_append_data:
 		dontfrag = np->dontfrag;
 	up->len += ulen;
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
+	err = ip6_append_data(sk, getfrag, msg, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info *)dst,
 		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);