diff options
| author | Herbert Xu <herbert@gondor.apana.org.au> | 2005-09-23 10:32:56 +0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2005-09-23 10:32:56 +0400 |
| commit | 83ca28befc43e93849e79c564cda10e39d983e75 (patch) | |
| tree | b86c768738f929246e4a0f858f8f6df88c015da8 /net/ipv4 | |
| parent | e484585ec3ee66cd07a627d3a9e2364640a3807f (diff) | |
| download | linux-83ca28befc43e93849e79c564cda10e39d983e75.tar.xz | |
[TCP]: Adjust Reno SACK estimate in tcp_fragment
Since the introduction of TSO pcount a year ago, it has been possible
for tcp_fragment() to cause packets_out to decrease. Prior to that,
tcp_retrans_try_collapse() was the only way for that to happen on the
retransmission path.
When this happens with Reno, it is possible for sasked_out to become
invalid because it is only an estimate and not tied to any particular
packet on the retransmission queue.
Therefore we need to adjust sacked_out as well as left_out in the Reno
case. The following patch does exactly that.
This bug is pretty difficult to trigger in practice though since you
need a SACKless peer with a retransmission that occurs just as the
cached MTU value expires.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/tcp_output.c | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5dd6dd7d091e..d6e3d269e906 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -509,7 +509,16 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss tp->lost_out -= diff; tp->left_out -= diff; } + if (diff > 0) { + /* Adjust Reno SACK estimate. */ + if (!tp->rx_opt.sack_ok) { + tp->sacked_out -= diff; + if ((int)tp->sacked_out < 0) + tp->sacked_out = 0; + tcp_sync_left_out(tp); + } + tp->fackets_out -= diff; if ((int)tp->fackets_out < 0) tp->fackets_out = 0; |