1 files changed, 153 insertions, 111 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 53c8ce4046b..e886e2f7fa8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -61,6 +61,8 @@
  *		Pasi Sarolahti:		F-RTO for dealing with spurious RTOs
  */
 
+#define pr_fmt(fmt) "TCP: " fmt
+
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -1403,8 +1405,16 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 
 	BUG_ON(!pcount);
 
-	/* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */
-	if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint))
+	/* Adjust counters and hints for the newly sacked sequence
+	 * range but discard the return value since prev is already
+	 * marked. We must tag the range first because the seq
+	 * advancement below implicitly advances
+	 * tcp_highest_sack_seq() when skb is highest_sack.
+	 */
+	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
+			start_seq, end_seq, dup_sack, pcount);
+
+	if (skb == tp->lost_skb_hint)
 		tp->lost_cnt_hint += pcount;
 
 	TCP_SKB_CB(prev)->end_seq += shifted;
@@ -1430,12 +1440,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 		skb_shinfo(skb)->gso_type = 0;
 	}
 
-	/* Adjust counters and hints for the newly sacked sequence range but
-	 * discard the return value since prev is already marked.
-	 */
-	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
-			start_seq, end_seq, dup_sack, pcount);
-
 	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
 	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
 
@@ -1583,6 +1587,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	/* tcp_sacktag_one() won't SACK-tag ranges below snd_una */
+	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
+		goto fallback;
+
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
 	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
@@ -2567,6 +2575,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 
 		if (cnt > packets) {
 			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+			    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
 			    (oldcnt >= packets))
 				break;
 
@@ -3860,9 +3869,9 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
 					opt_rx->wscale_ok = 1;
 					if (snd_wscale > 14) {
 						if (net_ratelimit())
-							printk(KERN_INFO "tcp_parse_options: Illegal window "
-							       "scaling value %d >14 received.\n",
-							       snd_wscale);
+							pr_info("%s: Illegal window scaling value %d >14 received\n",
+								__func__,
+								snd_wscale);
 						snd_wscale = 14;
 					}
 					opt_rx->snd_wscale = snd_wscale;
@@ -4184,7 +4193,7 @@ static void tcp_fin(struct sock *sk)
 		/* Only TCP_LISTEN and TCP_CLOSE are left, in these
 		 * cases we should never reach this piece of code.
 		 */
-		printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
+		pr_err("%s: Impossible, sk->sk_state=%d\n",
 		       __func__, sk->sk_state);
 		break;
 	}
@@ -4437,6 +4446,137 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
 	return 0;
 }
 
+static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb1;
+	u32 seq, end_seq;
+
+	TCP_ECN_check_ce(tp, skb);
+
+	if (tcp_try_rmem_schedule(sk, skb->truesize)) {
+		/* TODO: should increment a counter */
+		__kfree_skb(skb);
+		return;
+	}
+
+	/* Disable header prediction. */
+	tp->pred_flags = 0;
+	inet_csk_schedule_ack(sk);
+
+	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
+		   tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+
+	skb1 = skb_peek_tail(&tp->out_of_order_queue);
+	if (!skb1) {
+		/* Initial out of order segment, build 1 SACK. */
+		if (tcp_is_sack(tp)) {
+			tp->rx_opt.num_sacks = 1;
+			tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
+			tp->selective_acks[0].end_seq =
+						TCP_SKB_CB(skb)->end_seq;
+		}
+		__skb_queue_head(&tp->out_of_order_queue, skb);
+		goto end;
+	}
+
+	seq = TCP_SKB_CB(skb)->seq;
+	end_seq = TCP_SKB_CB(skb)->end_seq;
+
+	if (seq == TCP_SKB_CB(skb1)->end_seq) {
+		/* Packets in ofo can stay in queue a long time.
+		 * Better try to coalesce them right now
+		 * to avoid future tcp_collapse_ofo_queue(),
+		 * probably the most expensive function in tcp stack.
+		 */
+		if (skb->len <= skb_tailroom(skb1) && !tcp_hdr(skb)->fin) {
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPRCVCOALESCE);
+			BUG_ON(skb_copy_bits(skb, 0,
+					     skb_put(skb1, skb->len),
+					     skb->len));
+			TCP_SKB_CB(skb1)->end_seq = end_seq;
+			TCP_SKB_CB(skb1)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+			__kfree_skb(skb);
+			skb = NULL;
+		} else {
+			__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
+		}
+
+		if (!tp->rx_opt.num_sacks ||
+		    tp->selective_acks[0].end_seq != seq)
+			goto add_sack;
+
+		/* Common case: data arrive in order after hole. */
+		tp->selective_acks[0].end_seq = end_seq;
+		goto end;
+	}
+
+	/* Find place to insert this segment. */
+	while (1) {
+		if (!after(TCP_SKB_CB(skb1)->seq, seq))
+			break;
+		if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) {
+			skb1 = NULL;
+			break;
+		}
+		skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1);
+	}
+
+	/* Do skb overlap to previous one? */
+	if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) {
+		if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
+			/* All the bits are present. Drop. */
+			__kfree_skb(skb);
+			skb = NULL;
+			tcp_dsack_set(sk, seq, end_seq);
+			goto add_sack;
+		}
+		if (after(seq, TCP_SKB_CB(skb1)->seq)) {
+			/* Partial overlap. */
+			tcp_dsack_set(sk, seq,
+				      TCP_SKB_CB(skb1)->end_seq);
+		} else {
+			if (skb_queue_is_first(&tp->out_of_order_queue,
+					       skb1))
+				skb1 = NULL;
+			else
+				skb1 = skb_queue_prev(
+					&tp->out_of_order_queue,
+					skb1);
+		}
+	}
+	if (!skb1)
+		__skb_queue_head(&tp->out_of_order_queue, skb);
+	else
+		__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
+
+	/* And clean segments covered by new one as whole. */
+	while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) {
+		skb1 = skb_queue_next(&tp->out_of_order_queue, skb);
+
+		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
+			break;
+		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
+			tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
+					 end_seq);
+			break;
+		}
+		__skb_unlink(skb1, &tp->out_of_order_queue);
+		tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
+				 TCP_SKB_CB(skb1)->end_seq);
+		__kfree_skb(skb1);
+	}
+
+add_sack:
+	if (tcp_is_sack(tp))
+		tcp_sack_new_ofo_skb(sk, seq, end_seq);
+end:
+	if (skb)
+		skb_set_owner_r(skb, sk);
+}
+
+
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
@@ -4552,105 +4692,7 @@ drop:
 		goto queue_and_out;
 	}
 
-	TCP_ECN_check_ce(tp, skb);
-
-	if (tcp_try_rmem_schedule(sk, skb->truesize))
-		goto drop;
-
-	/* Disable header prediction. */
-	tp->pred_flags = 0;
-	inet_csk_schedule_ack(sk);
-
-	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
-		   tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
-
-	skb_set_owner_r(skb, sk);
-
-	if (!skb_peek(&tp->out_of_order_queue)) {
-		/* Initial out of order segment, build 1 SACK. */
-		if (tcp_is_sack(tp)) {
-			tp->rx_opt.num_sacks = 1;
-			tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
-			tp->selective_acks[0].end_seq =
-						TCP_SKB_CB(skb)->end_seq;
-		}
-		__skb_queue_head(&tp->out_of_order_queue, skb);
-	} else {
-		struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue);
-		u32 seq = TCP_SKB_CB(skb)->seq;
-		u32 end_seq = TCP_SKB_CB(skb)->end_seq;
-
-		if (seq == TCP_SKB_CB(skb1)->end_seq) {
-			__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
-
-			if (!tp->rx_opt.num_sacks ||
-			    tp->selective_acks[0].end_seq != seq)
-				goto add_sack;
-
-			/* Common case: data arrive in order after hole. */
-			tp->selective_acks[0].end_seq = end_seq;
-			return;
-		}
-
-		/* Find place to insert this segment. */
-		while (1) {
-			if (!after(TCP_SKB_CB(skb1)->seq, seq))
-				break;
-			if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) {
-				skb1 = NULL;
-				break;
-			}
-			skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1);
-		}
-
-		/* Do skb overlap to previous one? */
-		if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) {
-			if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
-				/* All the bits are present. Drop. */
-				__kfree_skb(skb);
-				tcp_dsack_set(sk, seq, end_seq);
-				goto add_sack;
-			}
-			if (after(seq, TCP_SKB_CB(skb1)->seq)) {
-				/* Partial overlap. */
-				tcp_dsack_set(sk, seq,
-					      TCP_SKB_CB(skb1)->end_seq);
-			} else {
-				if (skb_queue_is_first(&tp->out_of_order_queue,
-						       skb1))
-					skb1 = NULL;
-				else
-					skb1 = skb_queue_prev(
-						&tp->out_of_order_queue,
-						skb1);
-			}
-		}
-		if (!skb1)
-			__skb_queue_head(&tp->out_of_order_queue, skb);
-		else
-			__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
-
-		/* And clean segments covered by new one as whole. */
-		while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) {
-			skb1 = skb_queue_next(&tp->out_of_order_queue, skb);
-
-			if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
-				break;
-			if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
-				tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
-						 end_seq);
-				break;
-			}
-			__skb_unlink(skb1, &tp->out_of_order_queue);
-			tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
-					 TCP_SKB_CB(skb1)->end_seq);
-			__kfree_skb(skb1);
-		}
-
-add_sack:
-		if (tcp_is_sack(tp))
-			tcp_sack_new_ofo_skb(sk, seq, end_seq);
-	}
+	tcp_data_queue_ofo(sk, skb);
 }
 
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,