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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 47 insertions, 42 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a7aea2048a0d..c65b93a7b711 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -91,14 +91,19 @@ void ip_send_check(struct iphdr *iph)
 }
 EXPORT_SYMBOL(ip_send_check);
 
-int __ip_local_out(struct sk_buff *skb)
+int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
-	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
-		       skb_dst(skb)->dev, dst_output);
+	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, NULL,
+		       skb_dst(skb)->dev, dst_output_sk);
+}
+
+int __ip_local_out(struct sk_buff *skb)
+{
+	return __ip_local_out_sk(skb->sk, skb);
 }
 
 int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
@@ -148,7 +153,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(skb, sk);
+	ip_select_ident(sock_net(sk), skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -163,7 +168,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
 
-static inline int ip_finish_output2(struct sk_buff *skb)
+static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct rtable *rt = (struct rtable *)dst;
@@ -182,7 +187,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 		struct sk_buff *skb2;
 
 		skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
-		if (skb2 == NULL) {
+		if (!skb2) {
 			kfree_skb(skb);
 			return -ENOMEM;
 		}
@@ -211,7 +216,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
-static int ip_finish_output_gso(struct sk_buff *skb)
+static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
 {
 	netdev_features_t features;
 	struct sk_buff *segs;
@@ -220,7 +225,7 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 	/* common case: locally created skb or seglen is <= mtu */
 	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
 	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
-		return ip_finish_output2(skb);
+		return ip_finish_output2(sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.
 	 *
@@ -243,7 +248,7 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 		int err;
 
 		segs->next = NULL;
-		err = ip_fragment(segs, ip_finish_output2);
+		err = ip_fragment(sk, segs, ip_finish_output2);
 
 		if (err && ret == 0)
 			ret = err;
@@ -253,22 +258,22 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 	return ret;
 }
 
-static int ip_finish_output(struct sk_buff *skb)
+static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
-	if (skb_dst(skb)->xfrm != NULL) {
+	if (skb_dst(skb)->xfrm) {
 		IPCB(skb)->flags |= IPSKB_REROUTED;
-		return dst_output(skb);
+		return dst_output_sk(sk, skb);
 	}
 #endif
 	if (skb_is_gso(skb))
-		return ip_finish_output_gso(skb);
+		return ip_finish_output_gso(sk, skb);
 
 	if (skb->len > ip_skb_dst_mtu(skb))
-		return ip_fragment(skb, ip_finish_output2);
+		return ip_fragment(sk, skb, ip_finish_output2);
 
-	return ip_finish_output2(skb);
+	return ip_finish_output2(sk, skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)
@@ -307,7 +312,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-					newskb, NULL, newskb->dev,
+					sk, newskb, NULL, newskb->dev,
 					dev_loopback_xmit);
 		}
 
@@ -322,11 +327,11 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 	if (rt->rt_flags&RTCF_BROADCAST) {
 		struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 		if (newskb)
-			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb,
+			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, newskb,
 				NULL, newskb->dev, dev_loopback_xmit);
 	}
 
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL,
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL,
 			    skb->dev, ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -340,7 +345,8 @@ int ip_output(struct sock *sk, struct sk_buff *skb)
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);
 
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, dev,
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
+			    NULL, dev,
 			    ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -376,12 +382,12 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 	inet_opt = rcu_dereference(inet->inet_opt);
 	fl4 = &fl->u.ip4;
 	rt = skb_rtable(skb);
-	if (rt != NULL)
+	if (rt)
 		goto packet_routed;
 
 	/* Make sure we can route this packet. */
 	rt = (struct rtable *)__sk_dst_check(sk, 0);
-	if (rt == NULL) {
+	if (!rt) {
 		__be32 daddr;
 
 		/* Use correct destination address if we have options. */
@@ -430,7 +436,8 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
+	ip_select_ident_segs(sock_net(sk), skb, sk,
+			     skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
@@ -448,7 +455,6 @@ no_route:
 }
 EXPORT_SYMBOL(ip_queue_xmit);
 
-
 static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 {
 	to->pkt_type = from->pkt_type;
@@ -479,7 +485,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
  *	single device frame, and queue such a frame for sending.
  */
 
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
+int ip_fragment(struct sock *sk, struct sk_buff *skb,
+		int (*output)(struct sock *, struct sk_buff *))
 {
 	struct iphdr *iph;
 	int ptr;
@@ -586,13 +593,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 					ip_options_fragment(frag);
 				offset += skb->len - hlen;
 				iph->frag_off = htons(offset>>3);
-				if (frag->next != NULL)
+				if (frag->next)
 					iph->frag_off |= htons(IP_MF);
 				/* Ready, complete checksum */
 				ip_send_check(iph);
 			}
 
-			err = output(skb);
+			err = output(sk, skb);
 
 			if (!err)
 				IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
@@ -636,10 +643,7 @@ slow_path:
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */
 
-	/* for bridged IP traffic encapsulated inside f.e. a vlan header,
-	 * we need to make room for the encapsulating header
-	 */
-	ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb));
+	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
 
 	/*
 	 *	Fragment the datagram.
@@ -732,7 +736,7 @@ slow_path:
 
 		ip_send_check(iph);
 
-		err = output(skb2);
+		err = output(sk, skb2);
 		if (err)
 			goto fail;
 
@@ -792,12 +796,13 @@ static inline int ip_ufo_append_data(struct sock *sk,
 	 * device, so create one single skb packet containing complete
 	 * udp datagram
 	 */
-	if ((skb = skb_peek_tail(queue)) == NULL) {
+	skb = skb_peek_tail(queue);
+	if (!skb) {
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
 
-		if (skb == NULL)
+		if (!skb)
 			return err;
 
 		/* reserve space for Hardware header */
@@ -814,7 +819,6 @@ static inline int ip_ufo_append_data(struct sock *sk,
 
 		skb->csum = 0;
 
-
 		__skb_queue_tail(queue, skb);
 	} else if (skb_is_gso(skb)) {
 		goto append;
@@ -963,10 +967,10 @@ alloc_new_skb:
 					skb = sock_wmalloc(sk,
 							   alloclen + hh_len + 15, 1,
 							   sk->sk_allocation);
-				if (unlikely(skb == NULL))
+				if (unlikely(!skb))
 					err = -ENOBUFS;
 			}
-			if (skb == NULL)
+			if (!skb)
 				goto error;
 
 			/*
@@ -1090,10 +1094,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	 */
 	opt = ipc->opt;
 	if (opt) {
-		if (cork->opt == NULL) {
+		if (!cork->opt) {
 			cork->opt = kmalloc(sizeof(struct ip_options) + 40,
 					    sk->sk_allocation);
-			if (unlikely(cork->opt == NULL))
+			if (unlikely(!cork->opt))
 				return -ENOBUFS;
 		}
 		memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
@@ -1200,7 +1204,8 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		return -EMSGSIZE;
 	}
 
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+	skb = skb_peek_tail(&sk->sk_write_queue);
+	if (!skb)
 		return -EINVAL;
 
 	cork->length += size;
@@ -1211,7 +1216,6 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 	}
 
-
 	while (size > 0) {
 		int i;
 
@@ -1331,7 +1335,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	__be16 df = 0;
 	__u8 ttl;
 
-	if ((skb = __skb_dequeue(queue)) == NULL)
+	skb = __skb_dequeue(queue);
+	if (!skb)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
 
@@ -1382,7 +1387,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(skb, sk);
+	ip_select_ident(net, skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;