[NET]: Conditionally use bh_lock_sock_nested in sk_receive_skb
Spotted by Ian McDonald, tentatively fixed by Gerrit Renker:
http://www.mail-archive.com/dccp%40vger.kernel.org/msg00599.html
Rewritten not to unroll sk_receive_skb, in the common case, i.e. no lock
debugging, its optimized away.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
diff --git a/net/core/sock.c b/net/core/sock.c
index 32ff1c5..ab8fafa 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -270,7 +270,7 @@
}
EXPORT_SYMBOL(sock_queue_rcv_skb);
-int sk_receive_skb(struct sock *sk, struct sk_buff *skb)
+int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
{
int rc = NET_RX_SUCCESS;
@@ -279,7 +279,10 @@
skb->dev = NULL;
- bh_lock_sock(sk);
+ if (nested)
+ bh_lock_sock_nested(sk);
+ else
+ bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
/*
* trylock + unlock semantics: