Merge bk://kernel.bkbits.net/acme/net-2.6

into nuts.davemloft.net:/disk1/BK/net-2.6

include/net/sock.h

@@ -410,6 +410,20 @@ do {	if (!(__sk)->sk_backlog.tail) {				\
 	(__skb)->next = NULL;					\
 } while(0)
 
+#define sk_wait_event(__sk, __timeo, __condition)		\
+({	int rc;							\
+	release_sock(__sk);					\
+	rc = __condition;					\
+	if (!rc) {						\
+		*(__timeo) = schedule_timeout(*(__timeo));	\
+		rc = __condition;				\
+	}							\
+	lock_sock(__sk);					\
+	rc;							\
+})
+
+extern int sk_wait_data(struct sock *sk, long *timeo);
+
 /* IP protocol blocks we attach to sockets.
  * socket layer -> transport layer interface
  * transport -> network interface is defined by struct inet_proto

net/core/sock.c

@@ -917,6 +917,31 @@ void __release_sock(struct sock *sk)
 	} while((skb = sk->sk_backlog.head) != NULL);
 }
 
+/**
+ * sk_wait_data - wait for data to arrive at sk_receive_queue
+ * sk - sock to wait on
+ * timeo - for how long
+ *
+ * Now socket state including sk->sk_err is changed only under lock,
+ * hence we may omit checks after joining wait queue.
+ * We check receive queue before schedule() only as optimization;
+ * it is very likely that release_sock() added new data.
+ */
+int sk_wait_data(struct sock *sk, long *timeo)
+{
+	int rc;
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
+	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	finish_wait(sk->sk_sleep, &wait);
+	return rc;
+}
+
+EXPORT_SYMBOL(sk_wait_data);
+
 /*
  * Set of default routines for initialising struct proto_ops when
  * the protocol does not support a particular function. In certain

net/ipv4/tcp.c

@@ -1356,31 +1356,6 @@ static void cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-/* Now socket state including sk->sk_err is changed only under lock,
- * hence we may omit checks after joining wait queue.
- * We check receive queue before schedule() only as optimization;
- * it is very likely that release_sock() added new data.
- */
-
-static long tcp_data_wait(struct sock *sk, long timeo)
-{
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
-
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
-	release_sock(sk);
-
-	if (skb_queue_empty(&sk->sk_receive_queue))
-		timeo = schedule_timeout(timeo);
-
-	lock_sock(sk);
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
-
-	finish_wait(sk->sk_sleep, &wait);
-	return timeo;
-}
-
 static void tcp_prequeue_process(struct sock *sk)
 {
 	struct sk_buff *skb;
@@ -1660,9 +1635,8 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
 			lock_sock(sk);
-		} else {
-			timeo = tcp_data_wait(sk, timeo);
-		}
+		} else
+			sk_wait_data(sk, &timeo);
 
 		if (user_recv) {
 			int chunk;