Merge branch 'linux-linaro-lsk-v3.10' into linux-linaro-lsk-v3.10-android

5 files changed, 56 insertions, 24 deletions

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 31ee5c6033df..479e8a63125a 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -126,6 +126,9 @@ int ip_forward(struct sk_buff *skb)
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 834857f3c871..86183c4e4fd5 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -23,7 +23,6 @@
 #define ALPHA_MIN	((3*ALPHA_SCALE)/10)	/* ~0.3 */
 #define ALPHA_MAX	(10*ALPHA_SCALE)	/* 10.0 */
 #define ALPHA_BASE	ALPHA_SCALE		/* 1.0 */
-#define U32_MAX		((u32)~0U)
 #define RTT_MAX		(U32_MAX / ALPHA_MAX)	/* 3.3 secs */
 
 #define BETA_SHIFT	6
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7aa7faa7c3dd..22fc869465e8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3077,10 +3077,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			if (seq_rtt < 0) {
 				seq_rtt = ca_seq_rtt;
 			}
-			if (!(sacked & TCPCB_SACKED_ACKED))
+			if (!(sacked & TCPCB_SACKED_ACKED)) {
 				reord = min(pkts_acked, reord);
-			if (!after(scb->end_seq, tp->high_seq))
-				flag |= FLAG_ORIG_SACK_ACKED;
+				if (!after(scb->end_seq, tp->high_seq))
+					flag |= FLAG_ORIG_SACK_ACKED;
+			}
 		}
 
 		if (sacked & TCPCB_SACKED_ACKED)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8e374e566932..d64453a81028 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1902,7 +1902,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk->sk_state != TCP_TIME_WAIT) {
-			struct dst_entry *dst = sk->sk_rx_dst;
+			struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, 0);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f755a8326e88..5653febcb2ac 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2570,39 +2570,65 @@ begin_fwd:
 	}
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
@@ -2771,6 +2797,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	}
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
@@ -2908,6 +2936,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+	skb_shinfo(syn_data)->gso_segs = 1;
 	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
 					 fo->data->msg_iov, 0, space))) {
 		kfree_skb(syn_data);