diff options
| author | Eric Dumazet <edumazet@google.com> | 2013-05-13 21:25:52 +0000 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2013-06-27 10:34:31 -0700 |
| commit | 41a187532a9458873a603aee48f017c0288d03fe (patch) | |
| tree | f027c38a92cbae99e4582f831c83f1028e89f5f8 | |
| parent | 1819a873d94cd7abeb94f235175052f72fe6fa2c (diff) | |
tcp: fix tcp_md5_hash_skb_data()
[ Upstream commit 54d27fcb338bd9c42d1dfc5a39e18f6f9d373c2e ]
TCP md5 communications fail [1] for some devices, because sg/crypto code
assume page offsets are below PAGE_SIZE.
This was discovered using mlx4 driver [2], but I suspect loopback
might trigger the same bug now we use order-3 pages in tcp_sendmsg()
[1] Failure is giving following messages.
huh, entered softirq 3 NET_RX ffffffff806ad230 preempt_count 00000100,
exited with 00000101?
[2] mlx4 driver uses order-2 pages to allocate RX frags
Reported-by: Matt Schnall <mischnal@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Bernhard Beck <bbeck@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | net/ipv4/tcp.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2c423b660e5..0be492f644b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3043,7 +3043,11 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const struct skb_frag_struct *f = &shi->frags[i]; - sg_set_page(&sg, f->page, f->size, f->page_offset); + unsigned int offset = f->page_offset; + struct page *page = f->page + (offset >> PAGE_SHIFT); + + sg_set_page(&sg, page, f->size, + offset_in_page(offset)); if (crypto_hash_update(desc, &sg, f->size)) return 1; } |