diff options
author | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-19 18:55:56 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-19 18:55:56 -0700 |
commit | d0b952a9837f81cd89e756b1b34293fa6e1cb59d (patch) | |
tree | fbe488bc5f407afa0e91cefb262d9e9ee69062ac /net/sctp/sm_statefuns.c | |
parent | d90125bfe958ed0451c6b98f831c86aba08b43d5 (diff) | |
parent | 47552c4e555eefe381f3d45140b59a2ea4b16486 (diff) |
Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (109 commits)
[ETHTOOL]: Fix UFO typo
[SCTP]: Fix persistent slowdown in sctp when a gap ack consumes rx buffer.
[SCTP]: Send only 1 window update SACK per message.
[SCTP]: Don't do CRC32C checksum over loopback.
[SCTP] Reset rtt_in_progress for the chunk when processing its sack.
[SCTP]: Reject sctp packets with broadcast addresses.
[SCTP]: Limit association max_retrans setting in setsockopt.
[PFKEYV2]: Fix inconsistent typing in struct sadb_x_kmprivate.
[IPV6]: Sum real space for RTAs.
[IRDA]: Use put_unaligned() in irlmp_do_discovery().
[BRIDGE]: Add support for NETIF_F_HW_CSUM devices
[NET]: Add NETIF_F_GEN_CSUM and NETIF_F_ALL_CSUM
[TG3]: Convert to non-LLTX
[TG3]: Remove unnecessary tx_lock
[TCP]: Add tcp_slow_start_after_idle sysctl.
[BNX2]: Update version and reldate
[BNX2]: Use CPU native page size
[BNX2]: Use compressed firmware
[BNX2]: Add firmware decompression
[BNX2]: Allow WoL settings on new 5708 chips
...
Manual fixup for conflict in drivers/net/tulip/winbond-840.c
Diffstat (limited to 'net/sctp/sm_statefuns.c')
-rw-r--r-- | net/sctp/sm_statefuns.c | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 8bc279219a7..9e58144f485 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -5293,10 +5293,18 @@ static int sctp_eat_data(const struct sctp_association *asoc, * seems a bit troublesome in that frag_point varies based on * PMTU. In cases, such as loopback, this might be a rather * large spill over. + * NOTE: If we have a full receive buffer here, we only renege if + * our receiver can still make progress without the tsn being + * received. We do this because in the event that the associations + * receive queue is empty we are filling a leading gap, and since + * reneging moves the gap to the end of the tsn stream, we are likely + * to stall again very shortly. Avoiding the renege when we fill a + * leading gap is a good heuristic for avoiding such steady state + * stalls. */ if (!asoc->rwnd || asoc->rwnd_over || (datalen > asoc->rwnd + asoc->frag_point) || - rcvbuf_over) { + (rcvbuf_over && (!skb_queue_len(&sk->sk_receive_queue)))) { /* If this is the next TSN, consider reneging to make * room. Note: Playing nice with a confused sender. A |