From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Slava Shwartsman <slavash@mellanox.com>,
Herbert Xu <herbert@gondor.apana.org.au>,
Eric Dumazet <edumazet@google.com>,
"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 4.4 17/27] gro: Disable frag0 optimization on IPv6 ext headers
Date: Fri, 13 Jan 2017 12:38:34 +0100 [thread overview]
Message-ID: <20170113113723.336668704@linuxfoundation.org> (raw)
In-Reply-To: <20170113113722.669106991@linuxfoundation.org>
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Herbert Xu <herbert@gondor.apana.org.au>
[ Upstream commit 57ea52a865144aedbcd619ee0081155e658b6f7d ]
The GRO fast path caches the frag0 address. This address becomes
invalid if frag0 is modified by pskb_may_pull or its variants.
So whenever that happens we must disable the frag0 optimization.
This is usually done through the combination of gro_header_hard
and gro_header_slow, however, the IPv6 extension header path did
the pulling directly and would continue to use the GRO fast path
incorrectly.
This patch fixes it by disabling the fast path when we enter the
IPv6 extension header path.
Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/linux/netdevice.h | 9 +++++++--
net/ipv6/ip6_offload.c | 1 +
2 files changed, 8 insertions(+), 2 deletions(-)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2325,14 +2325,19 @@ static inline int skb_gro_header_hard(st
return NAPI_GRO_CB(skb)->frag0_len < hlen;
}
+static inline void skb_gro_frag0_invalidate(struct sk_buff *skb)
+{
+ NAPI_GRO_CB(skb)->frag0 = NULL;
+ NAPI_GRO_CB(skb)->frag0_len = 0;
+}
+
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
unsigned int offset)
{
if (!pskb_may_pull(skb, hlen))
return NULL;
- NAPI_GRO_CB(skb)->frag0 = NULL;
- NAPI_GRO_CB(skb)->frag0_len = 0;
+ skb_gro_frag0_invalidate(skb);
return skb->data + offset;
}
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -196,6 +196,7 @@ static struct sk_buff **ipv6_gro_receive
ops = rcu_dereference(inet6_offloads[proto]);
if (!ops || !ops->callbacks.gro_receive) {
__pskb_pull(skb, skb_gro_offset(skb));
+ skb_gro_frag0_invalidate(skb);
proto = ipv6_gso_pull_exthdrs(skb, proto);
skb_gro_pull(skb, -skb_transport_offset(skb));
skb_reset_transport_header(skb);
next prev parent reply other threads:[~2017-01-13 11:39 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20170113113908epcas2p26894f438616da1bf9f7b6b31f735fedc@epcas2p2.samsung.com>
2017-01-13 11:38 ` [PATCH 4.4 00/27] 4.4.43-stable review Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 01/27] netvsc: reduce maximum GSO size Greg Kroah-Hartman
2017-02-09 19:37 ` Ben Hutchings
2017-02-10 21:15 ` Greg Kroah-Hartman
2017-02-10 21:41 ` Patch "[PATCH] netvsc: Set maximum GSO size in the right place" has been added to the 4.4-stable tree gregkh
2017-01-13 11:38 ` [PATCH 4.4 02/27] ser_gigaset: return -ENOMEM on error instead of success Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 03/27] net: vrf: Drop conntrack data after pass through VRF device on Tx Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 04/27] ipv6: handle -EFAULT from skb_copy_bits Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 05/27] net, sched: fix soft lockup in tc_classify Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 06/27] net: stmmac: Fix race between stmmac_drv_probe and stmmac_open Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 07/27] net/mlx5: Check FW limitations on log_max_qp before setting it Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 08/27] net/mlx5: Avoid shadowing numa_node Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 09/27] drop_monitor: add missing call to genlmsg_end Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 10/27] drop_monitor: consider inserted data in genlmsg_end Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 11/27] igmp: Make igmp group member RFC 3376 compliant Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 12/27] ipv4: Do not allow MAIN to be alias for new LOCAL w/ custom rules Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 13/27] r8152: split rtl8152_suspend function Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 14/27] r8152: fix rx issue for runtime suspend Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 15/27] gro: Enter slow-path if there is no tailroom Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 16/27] gro: use min_t() in skb_gro_reset_offset() Greg Kroah-Hartman
2017-01-13 11:38 ` Greg Kroah-Hartman [this message]
2017-01-13 11:38 ` [PATCH 4.4 18/27] net: ipv4: Fix multipath selection with vrf Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 19/27] net: vrf: do not allow table id 0 Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 20/27] HID: hid-cypress: validate length of report Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 21/27] ALSA: firewire-tascam: Fix to handle error from initialization of stream data Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 22/27] powerpc: Fix build warning on 32-bit PPC Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 23/27] ARM: zynq: Reserve correct amount of non-DMA RAM Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 24/27] ARM: OMAP4+: Fix bad fallthrough for cpuidle Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 26/27] ALSA: usb-audio: Add a quirk for Plantronics BT600 Greg Kroah-Hartman
2017-01-13 11:38 ` [PATCH 4.4 27/27] mm/init: fix zone boundary creation Greg Kroah-Hartman
2017-01-13 20:19 ` [PATCH 4.4 00/27] 4.4.43-stable review Guenter Roeck
2017-01-14 7:24 ` Greg Kroah-Hartman
2017-01-13 21:57 ` Shuah Khan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170113113723.336668704@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=herbert@gondor.apana.org.au \
--cc=linux-kernel@vger.kernel.org \
--cc=slavash@mellanox.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).