3.10.69 -> 3.10.70

6 files changed, 47 insertions, 43 deletions

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index bd1c5baf6..31ee5c603 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -175,7 +175,8 @@ int ip_forward(struct sk_buff *skb)
 	 *	We now generate an ICMP HOST REDIRECT giving the route
 	 *	we calculated.
 	 */
-	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
 	skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1bb117130..3ffc57f7a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1454,23 +1454,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
 			   __be32 saddr, const struct ip_reply_arg *arg,
 			   unsigned int len)
 {
@@ -1478,9 +1463,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (ip_options_echo(&replyopts.opt.opt, skb))
@@ -1510,15 +1494,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1534,13 +1514,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 23e6ab0a2..f6603142c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -410,15 +410,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin_family = AF_UNSPEC;
+	memset(sin, 0, sizeof(*sin));
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
-		struct inet_sock *inet = inet_sk(sk);
-
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
-		sin->sin_port = 0;
-		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
-		if (inet->cmsg_flags)
+		if (inet_sk(sk)->cmsg_flags)
 			ip_cmsg_recv(msg, skb);
 	}
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 271732355..577801102 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1523,11 +1523,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+	    skb->protocol == htons(ETH_P_IP) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-		flags |= RTCF_DOREDIRECT;
-		do_cache = false;
-	}
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -2264,6 +2263,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+		r->rtm_flags |= RTCF_DOREDIRECT;
 
 	if (nla_put_be32(skb, RTA_DST, dst))
 		goto nla_put_failure;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 35c01585c..7edf30cdd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -707,7 +707,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, ip_hdr(skb)->saddr,
 			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
@@ -790,7 +791,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, ip_hdr(skb)->saddr,
 			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
@@ -3009,14 +3011,39 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
 	net->ipv4.sysctl_tcp_ecn = 2;
 	return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0a9..4a000f1dd 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
-	for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+	for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &table->hash[slot];
 
+		num = 0;
+
 		if (hlist_nulls_empty(&hslot->head))
 			continue;