From 2fdba6b085eb7068e9594cfa55ffe40466184b4d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 18 May 2005 22:52:33 -0700 Subject: [IPV4/IPV6] Ensure all frag_list members have NULL sk Having frag_list members which holds wmem of an sk leads to nightmares with partially cloned frag skb's. The reason is that once you unleash a skb with a frag_list that has individual sk ownerships into the stack you can never undo those ownerships safely as they may have been cloned by things like netfilter. Since we have to undo them in order to make skb_linearize happy this approach leads to a dead-end. So let's go the other way and make this an invariant: For any skb on a frag_list, skb->sk must be NULL. That is, the socket ownership always belongs to the head skb. It turns out that the implementation is actually pretty simple. The above invariant is actually violated in the following patch for a short duration inside ip_fragment. This is OK because the offending frag_list member is either destroyed at the end of the slow path without being sent anywhere, or it is detached from the frag_list before being sent. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 8 ++++++++ net/ipv6/ip6_output.c | 14 ++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index daebd93..760dc82 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -490,6 +490,14 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path; + + BUG_ON(frag->sk); + if (skb->sk) { + sock_hold(skb->sk); + frag->sk = skb->sk; + frag->destructor = sock_wfree; + skb->truesize -= frag->truesize; + } } /* Everything is OK. Generate! */ diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0f07114..b78a535 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -552,13 +552,17 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_headroom(frag) < hlen) goto slow_path; - /* Correct socket ownership. */ - if (frag->sk == NULL) - goto slow_path; - /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path; + + BUG_ON(frag->sk); + if (skb->sk) { + sock_hold(skb->sk); + frag->sk = skb->sk; + frag->destructor = sock_wfree; + skb->truesize -= frag->truesize; + } } err = 0; @@ -1116,12 +1120,10 @@ int ip6_push_pending_frames(struct sock *sk) tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; -#if 0 /* Logically correct, but useless work, ip_fragment() will have to undo */ skb->truesize += tmp_skb->truesize; __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; -#endif } ipv6_addr_copy(final_dst, &fl->fl6_dst); -- cgit v1.1