diff options
| author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-09-01 00:50:51 +0000 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2010-09-26 17:18:11 -0700 |
| commit | 76dcdc683e9ab26c0227d9f40b390edba9fca621 (patch) | |
| tree | 2cbd32efb0b63065633eb5acd4a076132ab409e9 | |
| parent | 5d92da4418de42f1f85920f84d81a66bb559727e (diff) | |
| download | kernel-common-76dcdc683e9ab26c0227d9f40b390edba9fca621.tar.gz kernel-common-76dcdc683e9ab26c0227d9f40b390edba9fca621.tar.bz2 kernel-common-76dcdc683e9ab26c0227d9f40b390edba9fca621.zip | |
gro: fix different skb headrooms
[ Upstream commit 3d3be4333fdf6faa080947b331a6a19bce1a4f57 ]
Packets entering GRO might have different headrooms, even for a given
flow (because of implementation details in drivers, like copybreak).
We cant force drivers to deliver packets with a fixed headroom.
1) fix skb_segment()
skb_segment() makes the false assumption headrooms of fragments are same
than the head. When CHECKSUM_PARTIAL is used, this can give csum_start
errors, and crash later in skb_copy_and_csum_dev()
2) allocate a minimal skb for head of frag_list
skb_gro_receive() uses netdev_alloc_skb(headroom + skb_gro_offset(p)) to
allocate a fresh skb. This adds NET_SKB_PAD to a padding already
provided by netdevice, depending on various things, like copybreak.
Use alloc_skb() to allocate an exact padding, to reduce cache line
needs:
NET_SKB_PAD + NET_IP_ALIGN
bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=16626
Many thanks to Plamen Petrov, testing many debugging patches !
With help of Jarek Poplawski.
Reported-by: Plamen Petrov <pvp-lsts@fs.uni-ruse.bg>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
| -rw-r--r-- | net/core/skbuff.c | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce88293a34e2..5046b9542260 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2574,6 +2574,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; + /* nskb and skb might have different headroom */ + if (nskb->ip_summed == CHECKSUM_PARTIAL) + nskb->csum_start += skb_headroom(nskb) - headroom; + skb_reset_mac_header(nskb); skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + @@ -2703,8 +2707,8 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; - headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); + headroom = NET_SKB_PAD + NET_IP_ALIGN; + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; |