1 files changed, 96 insertions, 141 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85b07eba187..557fe16cbfb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -42,7 +42,7 @@
 /* People can turn this off for buggy TCP's found in printers etc. */
 int sysctl_tcp_retrans_collapse __read_mostly = 1;
 
-/* People can turn this on to  work with those rare, broken TCPs that
+/* People can turn this on to work with those rare, broken TCPs that
  * interpret the window field as a signed quantity.
  */
 int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
@@ -484,7 +484,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	}
 	if (likely(sysctl_tcp_window_scaling)) {
 		opts->ws = tp->rx_opt.rcv_wscale;
-		if(likely(opts->ws))
+		if (likely(opts->ws))
 			size += TCPOLEN_WSCALE_ALIGNED;
 	}
 	if (likely(sysctl_tcp_sack)) {
@@ -526,7 +526,7 @@ static unsigned tcp_synack_options(struct sock *sk,
 
 	if (likely(ireq->wscale_ok)) {
 		opts->ws = ireq->rcv_wscale;
-		if(likely(opts->ws))
+		if (likely(opts->ws))
 			size += TCPOLEN_WSCALE_ALIGNED;
 	}
 	if (likely(doing_ts)) {
@@ -663,10 +663,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->urg_ptr		= 0;
 
 	/* The urg_mode check is necessary during a below snd_una win probe */
-	if (unlikely(tcp_urg_mode(tp) &&
-		     between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
-		th->urg_ptr		= htons(tp->snd_up - tcb->seq);
-		th->urg			= 1;
+	if (unlikely(tcp_urg_mode(tp))) {
+		if (between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF)) {
+			th->urg_ptr = htons(tp->snd_up - tcb->seq);
+			th->urg = 1;
+		} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
+			th->urg_ptr = 0xFFFF;
+			th->urg = 1;
+		}
 	}
 
 	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
@@ -722,8 +726,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
-	if (skb->len <= mss_now || !sk_can_gso(sk) ||
-	    tcp_urg_mode(tcp_sk(sk))) {
+	if (skb->len <= mss_now || !sk_can_gso(sk)) {
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
@@ -1029,10 +1032,6 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
 
 /* Compute the current effective MSS, taking SACKs and IP options,
  * and even PMTU discovery events into account.
- *
- * LARGESEND note: !tcp_urg_mode is overkill, only frames up to snd_up
- * cannot be large. However, taking into account rare use of URG, this
- * is not a big flaw.
  */
 unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 {
@@ -1047,7 +1046,7 @@ unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 
 	mss_now = tp->mss_cache;
 
-	if (large_allowed && sk_can_gso(sk) && !tcp_urg_mode(tp))
+	if (large_allowed && sk_can_gso(sk))
 		doing_tso = 1;
 
 	if (dst) {
@@ -1164,9 +1163,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
 {
 	int tso_segs = tcp_skb_pcount(skb);
 
-	if (!tso_segs ||
-	    (tso_segs > 1 && (tcp_skb_mss(skb) != mss_now ||
-			      tcp_urg_mode(tcp_sk(sk))))) {
+	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
 		tcp_set_skb_tso_segs(sk, skb, mss_now);
 		tso_segs = tcp_skb_pcount(skb);
 	}
@@ -1175,7 +1172,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
 
 static inline int tcp_minshall_check(const struct tcp_sock *tp)
 {
-	return after(tp->snd_sml,tp->snd_una) &&
+	return after(tp->snd_sml, tp->snd_una) &&
 		!after(tp->snd_sml, tp->snd_nxt);
 }
 
@@ -1341,7 +1338,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 
 	/* Defer for less than two clock ticks. */
 	if (tp->tso_deferred &&
-	    ((jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
+	    (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
 		goto send_now;
 
 	in_flight = tcp_packets_in_flight(tp);
@@ -1519,10 +1516,15 @@ static int tcp_mtu_probe(struct sock *sk)
  * send_head.  This happens as incoming acks open up the remote
  * window for us.
  *
+ * LARGESEND note: !tcp_urg_mode is overkill, only frames between
+ * snd_up-64k-mss .. snd_up cannot be large. However, taking into
+ * account rare use of URG, this is not a big flaw.
+ *
  * Returns 1, if no segments are in flight and we have queued segments, but
  * cannot send anything now because of SWS or another problem.
  */
-static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
+static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
+			  int push_one, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -1530,20 +1532,16 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 	int cwnd_quota;
 	int result;
 
-	/* If we are closed, the bytes will have to remain here.
-	 * In time closedown will finish, we empty the write queue and all
-	 * will be happy.
-	 */
-	if (unlikely(sk->sk_state == TCP_CLOSE))
-		return 0;
-
 	sent_pkts = 0;
 
-	/* Do MTU probing. */
-	if ((result = tcp_mtu_probe(sk)) == 0) {
-		return 0;
-	} else if (result > 0) {
-		sent_pkts = 1;
+	if (!push_one) {
+		/* Do MTU probing. */
+		result = tcp_mtu_probe(sk);
+		if (!result) {
+			return 0;
+		} else if (result > 0) {
+			sent_pkts = 1;
+		}
 	}
 
 	while ((skb = tcp_send_head(sk))) {
@@ -1565,12 +1563,12 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 						      nonagle : TCP_NAGLE_PUSH))))
 				break;
 		} else {
-			if (tcp_tso_should_defer(sk, skb))
+			if (!push_one && tcp_tso_should_defer(sk, skb))
 				break;
 		}
 
 		limit = mss_now;
-		if (tso_segs > 1)
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    cwnd_quota);
 
@@ -1580,7 +1578,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 
 		TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
-		if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC)))
+		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
 		/* Advance the send_head.  This one is sent out.
@@ -1590,6 +1588,9 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 
 		tcp_minshall_update(tp, mss_now, skb);
 		sent_pkts++;
+
+		if (push_one)
+			break;
 	}
 
 	if (likely(sent_pkts)) {
@@ -1608,10 +1609,18 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 {
 	struct sk_buff *skb = tcp_send_head(sk);
 
-	if (skb) {
-		if (tcp_write_xmit(sk, cur_mss, nonagle))
-			tcp_check_probe_timer(sk);
-	}
+	if (!skb)
+		return;
+
+	/* If we are closed, the bytes will have to remain here.
+	 * In time closedown will finish, we empty the write queue and
+	 * all will be happy.
+	 */
+	if (unlikely(sk->sk_state == TCP_CLOSE))
+		return;
+
+	if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC))
+		tcp_check_probe_timer(sk);
 }
 
 /* Send _single_ skb sitting at the send head. This function requires
@@ -1620,36 +1629,10 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 void tcp_push_one(struct sock *sk, unsigned int mss_now)
 {
 	struct sk_buff *skb = tcp_send_head(sk);
-	unsigned int tso_segs, cwnd_quota;
 
 	BUG_ON(!skb || skb->len < mss_now);
 
-	tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
-	cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);
-
-	if (likely(cwnd_quota)) {
-		unsigned int limit;
-
-		BUG_ON(!tso_segs);
-
-		limit = mss_now;
-		if (tso_segs > 1)
-			limit = tcp_mss_split_point(sk, skb, mss_now,
-						    cwnd_quota);
-
-		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now)))
-			return;
-
-		/* Send it out now. */
-		TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
-		if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
-			tcp_event_new_data_sent(sk, skb);
-			tcp_cwnd_validate(sk);
-			return;
-		}
-	}
+	tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation);
 }
 
 /* This function returns the amount that we can raise the
@@ -1769,46 +1752,22 @@ u32 __tcp_select_window(struct sock *sk)
 	return window;
 }
 
-/* Attempt to collapse two adjacent SKB's during retransmission. */
-static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb,
-				     int mss_now)
+/* Collapses two adjacent SKB's during retransmission. */
+static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
 	int skb_size, next_skb_size;
 	u16 flags;
 
-	/* The first test we must make is that neither of these two
-	 * SKB's are still referenced by someone else.
-	 */
-	if (skb_cloned(skb) || skb_cloned(next_skb))
-		return;
-
 	skb_size = skb->len;
 	next_skb_size = next_skb->len;
 	flags = TCP_SKB_CB(skb)->flags;
 
-	/* Also punt if next skb has been SACK'd. */
-	if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
-		return;
-
-	/* Next skb is out of window. */
-	if (after(TCP_SKB_CB(next_skb)->end_seq, tcp_wnd_end(tp)))
-		return;
-
-	/* Punt if not enough space exists in the first SKB for
-	 * the data in the second, or the total combined payload
-	 * would exceed the MSS.
-	 */
-	if ((next_skb_size > skb_tailroom(skb)) ||
-	    ((skb_size + next_skb_size) > mss_now))
-		return;
-
 	BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
 
 	tcp_highest_sack_combine(sk, next_skb, skb);
 
-	/* Ok.	We will be able to collapse the packet. */
 	tcp_unlink_write_queue(next_skb, sk);
 
 	skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size),
@@ -1850,54 +1809,60 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb,
 	sk_wmem_free_skb(sk, next_skb);
 }
 
-/* Do a simple retransmit without using the backoff mechanisms in
- * tcp_timer. This is used for path mtu discovery.
- * The socket is already locked here.
- */
-void tcp_simple_retransmit(struct sock *sk)
+static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
+{
+	if (tcp_skb_pcount(skb) > 1)
+		return 0;
+	/* TODO: SACK collapsing could be used to remove this condition */
+	if (skb_shinfo(skb)->nr_frags != 0)
+		return 0;
+	if (skb_cloned(skb))
+		return 0;
+	if (skb == tcp_send_head(sk))
+		return 0;
+	/* Some heurestics for collapsing over SACK'd could be invented */
+	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+		return 0;
+
+	return 1;
+}
+
+static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
+				     int space)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
-	unsigned int mss = tcp_current_mss(sk, 0);
-	u32 prior_lost = tp->lost_out;
+	struct sk_buff *skb = to, *tmp;
+	int first = 1;
 
-	tcp_for_write_queue(skb, sk) {
-		if (skb == tcp_send_head(sk))
+	if (!sysctl_tcp_retrans_collapse)
+		return;
+	if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)
+		return;
+
+	tcp_for_write_queue_from_safe(skb, tmp, sk) {
+		if (!tcp_can_collapse(sk, skb))
 			break;
-		if (skb->len > mss &&
-		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
-			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
-				tp->retrans_out -= tcp_skb_pcount(skb);
-			}
-			tcp_skb_mark_lost_uncond_verify(tp, skb);
-		}
-	}
 
-	tcp_clear_retrans_hints_partial(tp);
+		space -= skb->len;
 
-	if (prior_lost == tp->lost_out)
-		return;
+		if (first) {
+			first = 0;
+			continue;
+		}
 
-	if (tcp_is_reno(tp))
-		tcp_limit_reno_sacked(tp);
+		if (space < 0)
+			break;
+		/* Punt if not enough space exists in the first SKB for
+		 * the data in the second
+		 */
+		if (skb->len > skb_tailroom(to))
+			break;
 
-	tcp_verify_left_out(tp);
+		if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))
+			break;
 
-	/* Don't muck with the congestion window here.
-	 * Reason is that we do not increase amount of _data_
-	 * in network, but units changed and effective
-	 * cwnd/ssthresh really reduced now.
-	 */
-	if (icsk->icsk_ca_state != TCP_CA_Loss) {
-		tp->high_seq = tp->snd_nxt;
-		tp->snd_ssthresh = tcp_current_ssthresh(sk);
-		tp->prior_ssthresh = 0;
-		tp->undo_marker = 0;
-		tcp_set_ca_state(sk, TCP_CA_Loss);
+		tcp_collapse_retrans(sk, to);
 	}
-	tcp_xmit_retransmit_queue(sk);
 }
 
 /* This retransmits one SKB.  Policy decisions and retransmit queue
@@ -1949,17 +1914,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 			return -ENOMEM; /* We'll try again later. */
 	}
 
-	/* Collapse two adjacent packets if worthwhile and we can. */
-	if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
-	    (skb->len < (cur_mss >> 1)) &&
-	    (!tcp_skb_is_last(sk, skb)) &&
-	    (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
-	    (skb_shinfo(skb)->nr_frags == 0 &&
-	     skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) &&
-	    (tcp_skb_pcount(skb) == 1 &&
-	     tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) &&
-	    (sysctl_tcp_retrans_collapse != 0))
-		tcp_retrans_try_collapse(sk, skb, cur_mss);
+	tcp_retrans_try_collapse(sk, skb, cur_mss);
 
 	/* Some Solaris stacks overoptimize and ignore the FIN on a
 	 * retransmit when old data is attached.  So strip it off