From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933068Ab3EGOIU (ORCPT ); Tue, 7 May 2013 10:08:20 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:42307 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932574Ab3EGNlT (ORCPT ); Tue, 7 May 2013 09:41:19 -0400 From: Luis Henriques To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Thomas Graf , "David S. Miller" , Luis Henriques Subject: [PATCH 052/118] tcp: Reallocate headroom if it would overflow csum_start Date: Tue, 7 May 2013 14:38:18 +0100 Message-Id: <1367933964-1564-53-git-send-email-luis.henriques@canonical.com> X-Mailer: git-send-email 1.8.1.2 In-Reply-To: <1367933964-1564-1-git-send-email-luis.henriques@canonical.com> References: <1367933964-1564-1-git-send-email-luis.henriques@canonical.com> X-Extended-Stable: 3.5 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.5.7.12 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Thomas Graf commit 50bceae9bd3569d56744882f3012734d48a1d413 upstream. If a TCP retransmission gets partially ACKed and collapsed multiple times it is possible for the headroom to grow beyond 64K which will overflow the 16bit skb->csum_start which is based on the start of the headroom. It has been observed rarely in the wild with IPoIB due to the 64K MTU. Verify if the acking and collapsing resulted in a headroom exceeding what csum_start can cover and reallocate the headroom if so. A big thank you to Jim Foraker and the team at LLNL for helping out with the investigation and testing. Reported-by: Jim Foraker Signed-off-by: Thomas Graf Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Luis Henriques --- net/ipv4/tcp_output.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e0cd660..ae12c92 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2175,8 +2175,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -- 1.8.1.2