This is a note to let you know that I've just added the patch titled
tcp: gso: fix truesize tracking
to the 3.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
tcp-gso-fix-truesize-tracking.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <[email protected]> know about it.
>From 934c8b7de7c0632cf0dbaa5d9c9dcdcdc23cb33c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <[email protected]>
Date: Fri, 25 Oct 2013 17:26:17 -0700
Subject: tcp: gso: fix truesize tracking
From: Eric Dumazet <[email protected]>
[ Upstream commit 0d08c42cf9a71530fef5ebcfe368f38f2dd0476f ]
commit 6ff50cd55545 ("tcp: gso: do not generate out of order packets")
had an heuristic that can trigger a warning in skb_try_coalesce(),
because skb->truesize of the gso segments were exactly set to mss.
This breaks the requirement that
skb->truesize >= skb->len + truesizeof(struct sk_buff);
It can trivially be reproduced by :
ifconfig lo mtu 1500
ethtool -K lo tso off
netperf
As the skbs are looped into the TCP networking stack, skb_try_coalesce()
warns us of these skb under-estimating their truesize.
Signed-off-by: Eric Dumazet <[email protected]>
Reported-by: Alexei Starovoitov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
net/ipv4/tcp.c | 13 +++++--------
1 file changed, 5 insertions(+), 8 deletions(-)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2899,6 +2899,7 @@ struct sk_buff *tcp_tso_segment(struct s
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int sum_truesize = 0;
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
@@ -2982,13 +2983,7 @@ struct sk_buff *tcp_tso_segment(struct s
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be
gso_skb->truesize
- * So we account mss bytes of 'true size' for each
segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
+ sum_truesize += skb->truesize;
}
skb = skb->next;
th = tcp_hdr(skb);
@@ -3005,7 +3000,9 @@ struct sk_buff *tcp_tso_segment(struct s
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
+ sum_truesize += skb->truesize;
+ atomic_add(sum_truesize - gso_skb->truesize,
+ &skb->sk->sk_wmem_alloc);
}
delta = htonl(oldlen + (skb->tail - skb->transport_header) +
Patches currently in stable-queue which might be from [email protected] are
queue-3.10/net-8139cp-fix-a-bug_on-triggered-by-wrong-bytes_compl.patch
queue-3.10/net-tcp-fix-panic-in-tcp_fastopen_cache_set.patch
queue-3.10/tcp-tsq-restore-minimal-amount-of-queueing.patch
queue-3.10/ipv6-fix-possible-seqlock-deadlock-in-ip6_finish_output2.patch
queue-3.10/tcp-don-t-update-snd_nxt-when-a-socket-is-switched-from-repair-mode.patch
queue-3.10/inet-fix-possible-seqlock-deadlocks.patch
queue-3.10/net-clamp-msg_namelen-instead-of-returning-an-error.patch
queue-3.10/af_packet-block-bh-in-prb_shutdown_retire_blk_timer.patch
queue-3.10/ipv4-fix-possible-seqlock-deadlock.patch
queue-3.10/tcp-gso-fix-truesize-tracking.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
