Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S966195AbbD0Vqf (ORCPT ); Mon, 27 Apr 2015 17:46:35 -0400 Received: from ip4-83-240-67-251.cust.nbox.cz ([83.240.67.251]:49627 "EHLO ip4-83-240-18-248.cust.nbox.cz" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753251AbbD0Vc6 (ORCPT ); Mon, 27 Apr 2015 17:32:58 -0400 From: Jiri Slaby To: stable@vger.kernel.org Cc: linux-kernel@vger.kernel.org, Neal Cardwell , Yuchung Cheng , "David S. Miller" , Jiri Slaby Subject: [PATCH 3.12 54/83] tcp: fix FRTO undo on cumulative ACK of SACKed range Date: Mon, 27 Apr 2015 23:32:25 +0200 Message-Id: X-Mailer: git-send-email 2.3.5 In-Reply-To: <3426bb8de3a655aa6668e92ee92eb35f0db86582.1430159990.git.jslaby@suse.cz> References: <3426bb8de3a655aa6668e92ee92eb35f0db86582.1430159990.git.jslaby@suse.cz> In-Reply-To: References: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1937 Lines: 56 From: Neal Cardwell 3.12-stable review patch. If anyone has any objections, please let me know. =============== [ Upstream commit 666b805150efd62f05810ff0db08f44a2370c937 ] On processing cumulative ACKs, the FRTO code was not checking the SACKed bit, meaning that there could be a spurious FRTO undo on a cumulative ACK of a previously SACKed skb. The FRTO code should only consider a cumulative ACK to indicate that an original/unretransmitted skb is newly ACKed if the skb was not yet SACKed. The effect of the spurious FRTO undo would typically be to make the connection think that all previously-sent packets were in flight when they really weren't, leading to a stall and an RTO. Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Fixes: e33099f96d99c ("tcp: implement RFC5682 F-RTO") Signed-off-by: David S. Miller Signed-off-by: Jiri Slaby --- net/ipv4/tcp_input.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 172cd999290c..49c87a39948f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3014,10 +3014,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (seq_rtt < 0) { seq_rtt = ca_seq_rtt; } - if (!(sacked & TCPCB_SACKED_ACKED)) + if (!(sacked & TCPCB_SACKED_ACKED)) { reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; + } } if (sacked & TCPCB_SACKED_ACKED) -- 2.3.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/