From e56d6cd6057aac1c6ed8e1590acd62b46e06201d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=E4rvinen?= Date: Thu, 1 Nov 2007 00:09:37 -0700 Subject: [TCP]: Process DSACKs that reside within a SACK block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DSACK inside another SACK block were missed if start_seq of DSACK was larger than SACK block's because sorting prioritizes full processing of the SACK block before DSACK. After SACK block sorting situation is like this: SSSSSSSSS D SSSSSS SSSSSSS Because write_queue is walked in-order, when the first SACK block has been processed, TCP is already past the skb for which the DSACK arrived and we haven't taught it to backtrack (nor should we), so TCP just continues processing by going to the next SACK block after the DSACK (if any). Whenever such DSACK is present, do an embedded checking during the previous SACK block. If the DSACK is below snd_una, there won't be overlapping SACK block, and thus no problem in that case. Also if start_seq of the DSACK is equal to the actual block, it will be processed first. Tested this by using netem to duplicate 15% of packets, and by printing SACK block when found_dup_sack is true and the selected skb in the dup_sack = 1 branch (if taken): SACK block 0: 4344-5792 (relative to snd_una 2019137317) SACK block 1: 4344-5792 (relative to snd_una 2019137317) equal start seqnos => next_dup = 0, dup_sack = 1 won't occur... SACK block 0: 5792-7240 (relative to snd_una 2019214061) SACK block 1: 2896-7240 (relative to snd_una 2019214061) DSACK skb match 5792-7240 (relative to snd_una) ...and next_dup = 1 case (after the not shown start_seq sort), went to dup_sack = 1 branch. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 69d8c38ccd39..4d72781a49be 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1330,12 +1330,15 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ cached_fack_count = 0; } - for (i=0; istart_seq); __u32 end_seq = ntohl(sp->end_seq); int fack_count; int dup_sack = (found_dup_sack && (i == first_sack_index)); + int next_dup = (found_dup_sack && (i+1 == first_sack_index)); + + sp++; if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) { if (dup_sack) { @@ -1361,7 +1364,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ flag |= FLAG_DATA_LOST; tcp_for_write_queue_from(skb, sk) { - int in_sack; + int in_sack = 0; u8 sacked; if (skb == tcp_send_head(sk)) @@ -1380,7 +1383,23 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; - in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq); + dup_sack = (found_dup_sack && (i == first_sack_index)); + + /* Due to sorting DSACK may reside within this SACK block! */ + if (next_dup) { + u32 dup_start = ntohl(sp->start_seq); + u32 dup_end = ntohl(sp->end_seq); + + if (before(TCP_SKB_CB(skb)->seq, dup_end)) { + in_sack = tcp_match_skb_to_sack(sk, skb, dup_start, dup_end); + if (in_sack > 0) + dup_sack = 1; + } + } + + /* DSACK info lost if out-of-mem, try SACK still */ + if (in_sack <= 0) + in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq); if (in_sack < 0) break; -- cgit v1.2.3