3.16.48-rc1 review patch. If anyone has any objections, please let me know. ------------------ From: Eric Dumazet <edumazet@xxxxxxxxxx> commit f6ba8d33cfbb46df569972e64dbb5bb7e929bfd9 upstream. I should have known that lowering skb->truesize was dangerous :/ In case packets are not leaving the host via a standard Ethernet device, but looped back to local sockets, bad things can happen, as reported by Michael Madsen ( https://bugzilla.kernel.org/show_bug.cgi?id=195713 ) So instead of tweaking skb->truesize, lets change skb->destructor and keep a reference on the owner socket via its sk_refcnt. Fixes: f2f872f9272a ("netem: Introduce skb_orphan_partial() helper") Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx> Reported-by: Michael Madsen <mkm@xxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> [bwh: Backported to 3.16: drop changes to the preceding comment and the fast path, which we don't have] Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx> --- --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1654,17 +1654,17 @@ EXPORT_SYMBOL(sock_wfree); void skb_orphan_partial(struct sk_buff *skb) { - /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, - * so we do not completely orphan skb, but transfert all - * accounted bytes but one, to avoid unexpected reorders. - */ if (skb->destructor == sock_wfree #ifdef CONFIG_INET || skb->destructor == tcp_wfree #endif ) { - atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); - skb->truesize = 1; + struct sock *sk = skb->sk; + + if (atomic_inc_not_zero(&sk->sk_refcnt)) { + atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + skb->destructor = sock_efree; + } } else { skb_orphan(skb); }