summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorAli Saidi <saidi@engin.umich.edu>2008-10-07 15:31:19 -0700
committerDavid S. Miller <davem@davemloft.net>2008-10-07 15:31:19 -0700
commit53240c208776d557dba9d7afedbcdbf512774c16 (patch)
treeb47429ecaf4ea004857e5464cf0612cbd06081c7 /net
parentb6c40d68ff6498b7f63ddf97cf0aa818d748dee7 (diff)
tcp: Fix possible double-ack w/ user dma
From: Ali Saidi <saidi@engin.umich.edu> When TCP receive copy offload is enabled it's possible that tcp_rcv_established() will cause two acks to be sent for a single packet. In the case that a tcp_dma_early_copy() is successful, copied_early is set to true which causes tcp_cleanup_rbuf() to be called early which can send an ack. Further along in tcp_rcv_established(), __tcp_ack_snd_check() is called and will schedule a delayed ACK. If no packets are processed before the delayed ack timer expires the packet will be acked twice. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp_input.c3
1 files changed, 2 insertions, 1 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 67ccce2a96bd..7abc6b80d47d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4879,7 +4879,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
goto no_ack;
}
- __tcp_ack_snd_check(sk, 0);
+ if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
+ __tcp_ack_snd_check(sk, 0);
no_ack:
#ifdef CONFIG_NET_DMA
if (copied_early)