ipv6: ip6_fragment: fix headroom tests and skb leak

David Woodhouse reports skb_under_panic when we try to push ethernet
header to fragmented ipv6 skbs:

 skbuff: skb_under_panic: text:c1277f1e len:1294 put:14 head:dec98000
 data:dec97ffc tail:0xdec9850a end:0xdec98f40 dev:br-lan
[..]
ip6_finish_output2+0x196/0x4da

David further debugged this:
  [..] offending fragments were arriving here with skb_headroom(skb)==10.
  Which is reasonable, being the Solos ADSL card's header of 8 bytes
  followed by 2 bytes of PPP frame type.

The problem is that if netfilter ipv6 defragmentation is used, skb_cow()
in ip6_forward will only see reassembled skb.

Therefore, headroom is overestimated by 8 bytes (we pulled fragment
header) and we don't check the skbs in the frag_list either.

We can't do these checks in netfilter defrag since outdev isn't known yet.

Furthermore, existing tests in ip6_fragment did not consider the fragment
or ipv6 header size when checking headroom of the fraglist skbs.

While at it, also fix a skb leak on memory allocation -- ip6_fragment
must consume the skb.

I tested this e1000 driver hacked to not allocate additional headroom
(we end up in slowpath, since LL_RESERVED_SPACE is 16).

If 2 bytes of headroom are allocated, fastpath is taken (14 byte
ethernet header was pulled, so 16 byte headroom available in all
fragments).

Reported-by: David Woodhouse <dwmw2@infradead.org>
Diagnosed-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Tested-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Florian Westphal 2015-09-16 17:26:14 +02:00 committed by David S. Miller
parent ce816eb064
commit 1d325d217c

View File

@ -586,20 +586,22 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr); &ipv6_hdr(skb)->saddr);
hroom = LL_RESERVED_SPACE(rt->dst.dev);
if (skb_has_frag_list(skb)) { if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb); int first_len = skb_pagelen(skb);
struct sk_buff *frag2; struct sk_buff *frag2;
if (first_len - hlen > mtu || if (first_len - hlen > mtu ||
((first_len - hlen) & 7) || ((first_len - hlen) & 7) ||
skb_cloned(skb)) skb_cloned(skb) ||
skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto slow_path; goto slow_path;
skb_walk_frags(skb, frag) { skb_walk_frags(skb, frag) {
/* Correct geometry. */ /* Correct geometry. */
if (frag->len > mtu || if (frag->len > mtu ||
((frag->len & 7) && frag->next) || ((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen) skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr)))
goto slow_path_clean; goto slow_path_clean;
/* Partially cloned skb? */ /* Partially cloned skb? */
@ -616,8 +618,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
err = 0; err = 0;
offset = 0; offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
/* BUILD HEADER */ /* BUILD HEADER */
*prevhdr = NEXTHDR_FRAGMENT; *prevhdr = NEXTHDR_FRAGMENT;
@ -625,8 +625,11 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
if (!tmp_hdr) { if (!tmp_hdr) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS); IPSTATS_MIB_FRAGFAILS);
return -ENOMEM; err = -ENOMEM;
goto fail;
} }
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
__skb_pull(skb, hlen); __skb_pull(skb, hlen);
fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr)); fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr));
@ -723,7 +726,6 @@ slow_path:
*/ */
*prevhdr = NEXTHDR_FRAGMENT; *prevhdr = NEXTHDR_FRAGMENT;
hroom = LL_RESERVED_SPACE(rt->dst.dev);
troom = rt->dst.dev->needed_tailroom; troom = rt->dst.dev->needed_tailroom;
/* /*