summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2018-10-18 09:12:19 -0700
committerDavid S. Miller <davem@davemloft.net>2018-10-18 16:51:02 -0700
commit79861919b8896e14b8e5707242721f2312c57ae4 (patch)
treee4d0a3a96f8109c5a0aaf295a31bdfffc611622f /net/ipv4
parentcc18a7543d2f63a2c93fc61cfa7fd8be5464f75e (diff)
tcp: fix TCP_REPAIR xmit queue setup
Andrey reported the following warning triggered while running CRIU tests: tcp_clean_rtx_queue() ... last_ackt = tcp_skb_timestamp_us(skb); WARN_ON_ONCE(last_ackt == 0); This is caused by 5f6188a8003d ("tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh"), as we end up having skbs in retransmit queue with a zero skb->skb_mstamp_ns field. We could fix this bug in different ways, like making sure tp->tcp_wstamp_ns is not zero at socket creation, but as Neal pointed out, we also do not want that pacing status of a repaired socket could push tp->tcp_wstamp_ns far ahead in the future. So we prefer changing tcp_write_xmit() to not call tcp_update_skb_after_send() and instead do what is requested by TCP_REPAIR logic. Fixes: 5f6188a8003d ("tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Andrey Vagin <avagin@openvz.org> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_output.c13
1 files changed, 7 insertions, 6 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d212e4cbc689..c07990a35ff3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2321,18 +2321,19 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
+ if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
+ /* "skb_mstamp_ns" is used as a start point for the retransmit timer */
+ skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
+ list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+ goto repair; /* Skip network transmission */
+ }
+
if (tcp_pacing_check(sk))
break;
tso_segs = tcp_init_tso_segs(skb, mss_now);
BUG_ON(!tso_segs);
- if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
- /* "skb_mstamp" is used as a start point for the retransmit timer */
- tcp_update_skb_after_send(sk, skb, tp->tcp_wstamp_ns);
- goto repair; /* Skip network transmission */
- }
-
cwnd_quota = tcp_cwnd_test(tp, skb);
if (!cwnd_quota) {
if (push_one == 2)