[PATCH] tcp: don't use timestamp from repaired skb-s to calculate RTT

[Andrey Vagin <avagin@openvz.org>]

We don't know right timestamp for repaired skb-s. Wrong RTT estimations
isn't good, because some congestion modules heavily depends on it.

This patch adds the TCPCB_REPAIRED flag, which is included in
TCPCB_RETRANS.

Thanks to Eric for the advice how to fix this issue.

This patch fixes the warning:
[  879.562947] WARNING: CPU: 0 PID: 2825 at net/ipv4/tcp_input.c:3078 tcp_ack+0x11f5/0x1380()
[  879.567253] CPU: 0 PID: 2825 Comm: socket-tcpbuf-l Not tainted 3.16.0-next-20140811 #1
[  879.567829] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  879.568177]  0000000000000000 00000000c532680c ffff880039643d00 ffffffff817aa2d2
[  879.568776]  0000000000000000 ffff880039643d38 ffffffff8109afbd ffff880039d6ba80
[  879.569386]  ffff88003a449800 000000002983d6bd 0000000000000000 000000002983d6bc
[  879.569982] Call Trace:
[  879.570264]  [<ffffffff817aa2d2>] dump_stack+0x4d/0x66
[  879.570599]  [<ffffffff8109afbd>] warn_slowpath_common+0x7d/0xa0
[  879.570935]  [<ffffffff8109b0ea>] warn_slowpath_null+0x1a/0x20
[  879.571292]  [<ffffffff816d0a05>] tcp_ack+0x11f5/0x1380
[  879.571614]  [<ffffffff816d10bd>] tcp_rcv_established+0x1ed/0x710
[  879.571958]  [<ffffffff816dc9da>] tcp_v4_do_rcv+0x10a/0x370
[  879.572315]  [<ffffffff81657459>] release_sock+0x89/0x1d0
[  879.572642]  [<ffffffff816c81a0>] do_tcp_setsockopt.isra.36+0x120/0x860
[  879.573000]  [<ffffffff8110a52e>] ? rcu_read_lock_held+0x6e/0x80
[  879.573352]  [<ffffffff816c8912>] tcp_setsockopt+0x32/0x40
[  879.573678]  [<ffffffff81654ac4>] sock_common_setsockopt+0x14/0x20
[  879.574031]  [<ffffffff816537b0>] SyS_setsockopt+0x80/0xf0
[  879.574393]  [<ffffffff817b40a9>] system_call_fastpath+0x16/0x1b
[  879.574730] ---[ end trace a17cbc38eb8c5c00 ]---

Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 include/net/tcp.h |  4 +++-
 net/ipv4/tcp.c    | 16 +++++++++-------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index dafa1cb..36f5525 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -705,8 +705,10 @@ struct tcp_skb_cb {
 #define TCPCB_SACKED_RETRANS	0x02	/* SKB retransmitted		*/
 #define TCPCB_LOST		0x04	/* SKB is lost			*/
 #define TCPCB_TAGBITS		0x07	/* All tag bits			*/
+#define TCPCB_REPAIRED		0x10	/* SKB repaired (no skb_mstamp)	*/
 #define TCPCB_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
-#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
+#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
+				TCPCB_REPAIRED)
 
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	/* 1 byte hole */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 181b70e..cb5f548 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1188,13 +1188,6 @@ new_segment:
 					goto wait_for_memory;
 
 				/*
-				 * All packets are restored as if they have
-				 * already been sent.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
-				/*
 				 * Check whether we can use HW checksum.
 				 */
 				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -1203,6 +1196,15 @@ new_segment:
 				skb_entail(sk, skb);
 				copy = size_goal;
 				max = size_goal;
+
+				/* All packets are restored as if they have
+				 * already been sent. skb_mstamp isn't set to
+				 * avoid wrong rtt estimation.
+				 */
+				if (tp->repair) {
+					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
+					TCP_SKB_CB(skb)->when = tcp_time_stamp;
+				}
 			}
 
 			/* Try to append data to the end of skb. */
-- 
1.9.3