Merge branch 'linux-3.10.33' into dev-kernel-3.10

Bug 1456092

Change-Id: I3021247ec68a3c2dddd9e98cde13d70a45191d53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

12 files changed, 145 insertions, 33 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e392355afe22..b151e0ac7f27 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1439,7 +1439,8 @@ static size_t inet_nlmsg_size(void)
 	       + nla_total_size(4) /* IFA_ADDRESS */
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
-	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
+	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+	       + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
 }
 
 static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a209f9d..4556cd25acde 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1049,6 +1049,8 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	}
 
 	in_dev = __in_dev_get_rtnl(dev);
+	if (!in_dev)
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5f648751fce2..45dbdab915e2 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = inet->inet_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
@@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 
 	r->idiag_family	      = tw->tw_family;
 	r->idiag_retrans      = 0;
+
 	r->id.idiag_if	      = tw->tw_bound_dev_if;
 	sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
 	r->id.idiag_sport     = tw->tw_sport;
 	r->id.idiag_dport     = tw->tw_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
 	r->id.idiag_dst[0]    = tw->tw_daddr;
+
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
 	r->idiag_expires      = DIV_ROUND_UP(tmo * 1000, HZ);
@@ -732,8 +743,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = ireq->rmt_port;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = ireq->loc_addr;
 	r->id.idiag_dst[0] = ireq->rmt_addr;
+
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
@@ -945,7 +961,7 @@ next_normal:
 			++num;
 		}
 
-		if (r->idiag_states & TCPF_TIME_WAIT) {
+		if (r->idiag_states & (TCPF_TIME_WAIT | TCPF_FIN_WAIT2)) {
 			struct inet_timewait_sock *tw;
 
 			inet_twsk_for_each(tw, node,
@@ -955,6 +971,8 @@ next_normal:
 
 				if (num < s_num)
 					goto next_dying;
+				if (!(r->idiag_states & (1 << tw->tw_substate)))
+					goto next_dying;
 				if (r->sdiag_family != AF_UNSPEC &&
 						tw->tw_family != r->sdiag_family)
 					goto next_dying;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b7aebf..98d7e53d2afd 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+	       !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu || skb->local_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+	unsigned int mtu;
+
+	if (skb->local_df || !skb_is_gso(skb))
+		return false;
+
+	mtu = dst_mtu(skb_dst(skb));
+
+	/* if seglen > mtu, do software segmentation for IP fragmentation on
+	 * output.  DF bit cannot be set since ip_forward would have sent
+	 * icmp error.
+	 */
+	return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	features = netif_skb_dev_features(skb, dst->dev);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = dst_output(segs);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	if (ip_gso_exceeds_dst_mtu(skb))
+		return ip_forward_finish_gso(skb);
+
 	return dst_output(skb);
 }
 
@@ -88,8 +156,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(dst_mtu(&rt->dst)));
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 64e4e98c8786..828b2e8631e7 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -335,6 +335,7 @@ static int ipgre_rcv(struct sk_buff *skb)
 				  iph->saddr, iph->daddr, tpi.key);
 
 	if (tunnel) {
+		skb_pop_mac_header(skb);
 		ip_tunnel_rcv(tunnel, skb, &tpi, hdr_len, log_ecn_error);
 		return 0;
 	}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 15e3e683adec..0a22bb0ce1a8 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -313,7 +313,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 
-	if (sysctl_ip_early_demux && !skb_dst(skb)) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct net_protocol *ipprot;
 		int protocol = iph->protocol;
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 46dcf32c012e..fa6573264c8a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -636,6 +636,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
+			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2c581da1fcab..7dbad6835843 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
-	struct ipmr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv4.mr_rules_ops,
 			       flowi4_to_flowi(flp4), 0, &arg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6c6ab14da41..1a362f375e67 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1544,6 +1544,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
@@ -1645,8 +1646,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (err != 0)
 		goto no_route;
 
-	RT_CACHE_STAT_INC(in_slow_tot);
-
 	if (res.type == RTN_BROADCAST)
 		goto brd_input;
 
@@ -1715,6 +1714,7 @@ local_input:
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 306dbd9a9441..b500d2ddc476 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+						   struct net *net, unsigned int hash);
+
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 	}
 }
 
+#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+		tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH	5
+#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 					  struct inetpeer_addr *addr,
-					  unsigned int hash,
-					  bool reclaim)
+					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
 	struct net *net;
+	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
 	net = dev_net(dst->dev);
+
+	/* While waiting for the spin-lock the cache might have been populated
+	 * with this entry and so we have to check again.
+	 */
+	tm = __tcp_get_metrics(addr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR) {
+		reclaim = true;
+		tm = NULL;
+	}
+	if (tm) {
+		tcpm_check_stamp(tm, dst);
+		goto out_unlock;
+	}
+
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
@@ -169,17 +197,6 @@ out_unlock:
 	return tm;
 }
 
-#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
-		tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH	5
-#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
-
 static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
 {
 	if (tm)
@@ -280,7 +297,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	struct inetpeer_addr addr;
 	unsigned int hash;
 	struct net *net;
-	bool reclaim;
 
 	addr.family = sk->sk_family;
 	switch (addr.family) {
@@ -300,13 +316,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
 	tm = __tcp_get_metrics(&addr, net, hash);
-	reclaim = false;
-	if (tm == TCP_METRICS_RECLAIM_PTR) {
-		reclaim = true;
+	if (tm == TCP_METRICS_RECLAIM_PTR)
 		tm = NULL;
-	}
 	if (!tm && create)
-		tm = tcpm_new(dst, &addr, hash, reclaim);
+		tm = tcpm_new(dst, &addr, hash);
 	else
 		tcpm_check_stamp(tm, dst);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3b113f84a277..5dc91c31be21 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -685,7 +685,8 @@ static void tcp_tsq_handler(struct sock *sk)
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
  * One tasklest per cpu tries to send more skbs.
@@ -1874,7 +1875,15 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 * We abuse smp_mb__after_clear_bit() because
+			 * there is no smp_mb__after_set_bit() yet
+			 */
+			smp_mb__after_clear_bit();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
 
 		limit = mss_now;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fe1a3404314d..313f1f73bdbe 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1075,9 +1075,6 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
-	if (flags & MSG_SENDPAGE_NOTLAST)
-		flags |= MSG_MORE;
-
 	if (!up->pending) {
 		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };