From 882bebaaca4bb1484078d44ef011f918c0e1e14e Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 7 Apr 2008 22:33:07 -0700 Subject: [TCP]: tcp_simple_retransmit can cause S+L This fixes Bugzilla #10384 tcp_simple_retransmit does L increment without any checking whatsoever for overflowing S+L when Reno is in use. The simplest scenario I can currently think of is rather complex in practice (there might be some more straightforward cases though). Ie., if mss is reduced during mtu probing, it may end up marking everything lost and if some duplicate ACKs arrived prior to that sacked_out will be non-zero as well, leading to S+L > packets_out, tcp_clean_rtx_queue on the next cumulative ACK or tcp_fastretrans_alert on the next duplicate ACK will fix the S counter. More straightforward (but questionable) solution would be to just call tcp_reset_reno_sack() in tcp_simple_retransmit but it would negatively impact the probe's retransmission, ie., the retransmissions would not occur if some duplicate ACKs had arrived. So I had to add reno sacked_out reseting to CA_Loss state when the first cumulative ACK arrives (this stale sacked_out might actually be the explanation for the reports of left_out overflows in kernel prior to 2.6.23 and S+L overflow reports of 2.6.24). However, this alone won't be enough to fix kernel before 2.6.24 because it is building on top of the commit 1b6d427bb7e ([TCP]: Reduce sacked_out with reno when purging write_queue) to keep the sacked_out from overflowing. Signed-off-by: Ilpo Järvinen Reported-by: Alessandro Suardi Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 24 ++++++++++++++++++------ net/ipv4/tcp_output.c | 3 +++ 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7d0958785bfb..b4812c3cbbcf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1625,13 +1625,11 @@ out: return flag; } -/* If we receive more dupacks than we expected counting segments - * in assumption of absent reordering, interpret this as reordering. - * The only another reason could be bug in receiver TCP. +/* Limits sacked_out so that sum with lost_out isn't ever larger than + * packets_out. Returns zero if sacked_out adjustement wasn't necessary. */ -static void tcp_check_reno_reordering(struct sock *sk, const int addend) +int tcp_limit_reno_sacked(struct tcp_sock *tp) { - struct tcp_sock *tp = tcp_sk(sk); u32 holes; holes = max(tp->lost_out, 1U); @@ -1639,8 +1637,20 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) if ((tp->sacked_out + holes) > tp->packets_out) { tp->sacked_out = tp->packets_out - holes; - tcp_update_reordering(sk, tp->packets_out + addend, 0); + return 1; } + return 0; +} + +/* If we receive more dupacks than we expected counting segments + * in assumption of absent reordering, interpret this as reordering. + * The only another reason could be bug in receiver TCP. + */ +static void tcp_check_reno_reordering(struct sock *sk, const int addend) +{ + struct tcp_sock *tp = tcp_sk(sk); + if (tcp_limit_reno_sacked(tp)) + tcp_update_reordering(sk, tp->packets_out + addend, 0); } /* Emulate SACKs for SACKless connection: account for a new dupack. */ @@ -2600,6 +2610,8 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) case TCP_CA_Loss: if (flag & FLAG_DATA_ACKED) icsk->icsk_retransmits = 0; + if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED) + tcp_reset_reno_sack(tp); if (!tcp_try_undo_loss(sk)) { tcp_moderate_cwnd(tp); tcp_xmit_retransmit_queue(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 72b9350006fe..d29ef79c00ca 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1808,6 +1808,9 @@ void tcp_simple_retransmit(struct sock *sk) if (!lost) return; + if (tcp_is_reno(tp)) + tcp_limit_reno_sacked(tp); + tcp_verify_left_out(tp); /* Don't muck with the congestion window here. -- cgit v1.2.3