summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorIlpo Järvinen <ilpo.jarvinen@helsinki.fi>2008-06-04 11:34:22 -0700
committerDavid S. Miller <davem@davemloft.net>2008-06-04 11:34:22 -0700
commit8aca6cb1179ed9bef9351028c8d8af852903eae2 (patch)
tree4a2243d41b625872381e86fbb8e72eddd3d078df /net/ipv4
parentb9c698964614f71b9c8afeca163a945b4c2e2d20 (diff)
tcp: Fix inconsistency source (CA_Open only when !tcp_left_out(tp))
It is possible that this skip path causes TCP to end up into an invalid state where ca_state was left to CA_Open while some segments already came into sacked_out. If next valid ACK doesn't contain new SACK information TCP fails to enter into tcp_fastretrans_alert(). Thus at least high_seq is set incorrectly to a too high seqno because some new data segments could be sent in between (and also, limited transmit is not being correctly invoked there). Reordering in both directions can easily cause this situation to occur. I guess we would want to use tcp_moderate_cwnd(tp) there as well as it may be possible to use this to trigger oversized burst to network by sending an old ACK with huge amount of SACK info, but I'm a bit unsure about its effects (mainly to FlightSize), so to be on the safe side I just currently fixed it minimally to keep TCP's state consistent (obviously, such nasty ACKs have been possible this far). Though it seems that FlightSize is already underestimated by some amount, so probably on the long term we might want to trigger recovery there too, if appropriate, to make FlightSize calculation to resemble reality at the time when the losses where discovered (but such change scares me too much now and requires some more thinking anyway how to do that as it likely involves some code shuffling). This bug was found by Brian Vowell while running my TCP debug patch to find cause of another TCP issue (fackets_out miscount). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_input.c29
1 files changed, 19 insertions, 10 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b54d9d37b636..54a0b7412782 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2483,6 +2483,20 @@ static inline void tcp_complete_cwr(struct sock *sk)
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
+static void tcp_try_keep_open(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int state = TCP_CA_Open;
+
+ if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+ state = TCP_CA_Disorder;
+
+ if (inet_csk(sk)->icsk_ca_state != state) {
+ tcp_set_ca_state(sk, state);
+ tp->high_seq = tp->snd_nxt;
+ }
+}
+
static void tcp_try_to_open(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2496,15 +2510,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
tcp_enter_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
- int state = TCP_CA_Open;
-
- if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
- state = TCP_CA_Disorder;
-
- if (inet_csk(sk)->icsk_ca_state != state) {
- tcp_set_ca_state(sk, state);
- tp->high_seq = tp->snd_nxt;
- }
+ tcp_try_keep_open(sk);
tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_down(sk, flag);
@@ -3310,8 +3316,11 @@ no_queue:
return 1;
old_ack:
- if (TCP_SKB_CB(skb)->sacked)
+ if (TCP_SKB_CB(skb)->sacked) {
tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ if (icsk->icsk_ca_state == TCP_CA_Open)
+ tcp_try_keep_open(sk);
+ }
uninteresting_ack:
SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);