Merge tag 'v3.0.72' into android-3.0

This is the 3.0.72 stable release

5 files changed, 36 insertions, 21 deletions

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5ff2a51..210b710 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -21,6 +21,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
+#include <net/sock.h>
 #include <net/inet_frag.h>
 
 static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -271,6 +272,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 {
 	struct inet_frag_queue *q;
 	struct hlist_node *n;
+	int depth = 0;
 
 	hlist_for_each_entry(q, n, &f->hash[hash], list) {
 		if (q->net == nf && f->match(q, key)) {
@@ -278,9 +280,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 			read_unlock(&f->lock);
 			return q;
 		}
+		depth++;
 	}
 	read_unlock(&f->lock);
 
-	return inet_frag_create(nf, f, key);
+	if (depth <= INETFRAGS_MAXDEPTH)
+		return inet_frag_create(nf, f, key);
+	else
+		return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);
+
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix)
+{
+	static const char msg[] = "inet_frag_find: Fragment hash bucket"
+		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
+		". Dropping fragment.\n";
+
+	if (PTR_ERR(q) == -ENOBUFS)
+		LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+}
+EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0ad6035..da38472 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -20,6 +20,8 @@
  *		Patrick McHardy :	LRU queue of frag heads for evictor.
  */
 
+#define pr_fmt(fmt) "IPv4: " fmt
+
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -292,14 +294,12 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (q == NULL)
-		goto out_nomem;
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
 
 	return container_of(q, struct ipq, q);
-
-out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n");
-	return NULL;
 }
 
 /* Is the fragment too far ahead to be part of ipq? */
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 42dd1a9..40eb4fc 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -358,7 +358,6 @@ int ip_options_compile(struct net *net,
 				}
 				switch (optptr[3]&0xF) {
 				      case IPOPT_TS_TSONLY:
-					opt->ts = optptr - iph;
 					if (skb)
 						timeptr = &optptr[optptr[2]-1];
 					opt->ts_needtime = 1;
@@ -369,7 +368,6 @@ int ip_options_compile(struct net *net,
 						pp_ptr = optptr + 2;
 						goto error;
 					}
-					opt->ts = optptr - iph;
 					if (rt)  {
 						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
 						timeptr = &optptr[optptr[2]+3];
@@ -383,7 +381,6 @@ int ip_options_compile(struct net *net,
 						pp_ptr = optptr + 2;
 						goto error;
 					}
-					opt->ts = optptr - iph;
 					{
 						__be32 addr;
 						memcpy(&addr, &optptr[optptr[2]-1], 4);
@@ -416,12 +413,12 @@ int ip_options_compile(struct net *net,
 					pp_ptr = optptr + 3;
 					goto error;
 				}
-				opt->ts = optptr - iph;
 				if (skb) {
 					optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
 					opt->is_changed = 1;
 				}
 			}
+			opt->ts = optptr - iph;
 			break;
 		      case IPOPT_RA:
 			if (optlen < 4) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7f4e391..ab44f9d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2244,11 +2244,8 @@ void tcp_enter_loss(struct sock *sk, int how)
 	if (tcp_is_reno(tp))
 		tcp_reset_reno_sack(tp);
 
-	if (!how) {
-		/* Push undo marker, if it was plain RTO and nothing
-		 * was retransmitted. */
-		tp->undo_marker = tp->snd_una;
-	} else {
+	tp->undo_marker = tp->snd_una;
+	if (how) {
 		tp->sacked_out = 0;
 		tp->fackets_out = 0;
 	}
@@ -5419,6 +5416,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 				if (tcp_checksum_complete_user(sk, skb))
 					goto csum_error;
 
+				if ((int)skb->truesize > sk->sk_forward_alloc)
+					goto step5;
+
 				/* Predicted packet is in window by definition.
 				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
 				 * Hence, check seq<=rcv_wup reduces to:
@@ -5430,9 +5430,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 
 				tcp_rcv_rtt_measure_ts(sk, skb);
 
-				if ((int)skb->truesize > sk->sk_forward_alloc)
-					goto step5;
-
 				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
 				/* Bulk data transfer: receiver */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e0b8bd1..0d9b959 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1579,8 +1579,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 			goto send_now;
 	}
 
-	/* Ok, it looks like it is advisable to defer.  */
-	tp->tso_deferred = 1 | (jiffies << 1);
+	/* Ok, it looks like it is advisable to defer.
+	 * Do not rearm the timer if already set to not break TCP ACK clocking.
+	 */
+	if (!tp->tso_deferred)
+		tp->tso_deferred = 1 | (jiffies << 1);
 
 	return 1;