net: adding memory barrier to the poll and receive callbacks

Adding memory barrier after the poll_wait function, paired with
receive callbacks. Adding fuctions sock_poll_wait and sk_has_sleeper
to wrap the memory barrier.

Without the memory barrier, following race can happen.
The race fires, when following code paths meet, and the tp->rcv_nxt
and __add_wait_queue updates stay in CPU caches.

CPU1                         CPU2

sys_select                   receive packet
  ...                        ...
  __add_wait_queue           update tp->rcv_nxt
  ...                        ...
  tp->rcv_nxt check          sock_def_readable
  ...                        {
  schedule                      ...
                                if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
                                        wake_up_interruptible(sk->sk_sleep)
                                ...
                             }

If there was no cache the code would work ok, since the wait_queue and
rcv_nxt are opposit to each other.

Meaning that once tp->rcv_nxt is updated by CPU2, the CPU1 either already
passed the tp->rcv_nxt check and sleeps, or will get the new value for
tp->rcv_nxt and will return with new data mask.
In both cases the process (CPU1) is being added to the wait queue, so the
waitqueue_active (CPU2) call cannot miss and will wake up CPU1.

The bad case is when the __add_wait_queue changes done by CPU1 stay in its
cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1 will then
endup calling schedule and sleep forever if there are no more data on the
socket.

Calls to poll_wait in following modules were ommited:
	net/bluetooth/af_bluetooth.c
	net/irda/af_irda.c
	net/irda/irnet/irnet_ppp.c
	net/mac80211/rc80211_pid_debugfs.c
	net/phonet/socket.c
	net/rds/af_rds.c
	net/rfkill/core.c
	net/sunrpc/cache.c
	net/sunrpc/rpc_pipe.c
	net/tipc/socket.c

Signed-off-by: Jiri Olsa <[email protected]>
Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

include/net/sock.h

@@ -54,6 +54,7 @@
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <linux/poll.h>
 
 #include <asm/atomic.h>
 #include <net/dst.h>
@@ -1241,6 +1242,71 @@ static inline int sk_has_allocations(const struct sock *sk)
 	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
 }
 
+/**
+ * sk_has_sleeper - check if there are any waiting processes
+ * @sk: socket
+ *
+ * Returns true if socket has waiting processes
+ *
+ * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory
+ * barrier call. They were added due to the race found within the tcp code.
+ *
+ * Consider following tcp code paths:
+ *
+ * CPU1                  CPU2
+ *
+ * sys_select            receive packet
+ *   ...                 ...
+ *   __add_wait_queue    update tp->rcv_nxt
+ *   ...                 ...
+ *   tp->rcv_nxt check   sock_def_readable
+ *   ...                 {
+ *   schedule               ...
+ *                          if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ *                              wake_up_interruptible(sk->sk_sleep)
+ *                          ...
+ *                       }
+ *
+ * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
+ * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
+ * could then endup calling schedule and sleep forever if there are no more
+ * data on the socket.
+ */
+static inline int sk_has_sleeper(struct sock *sk)
+{
+	/*
+	 * We need to be sure we are in sync with the
+	 * add_wait_queue modifications to the wait queue.
+	 *
+	 * This memory barrier is paired in the sock_poll_wait.
+	 */
+	smp_mb();
+	return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
+}
+
+/**
+ * sock_poll_wait - place memory barrier behind the poll_wait call.
+ * @filp:           file
+ * @wait_address:   socket wait queue
+ * @p:              poll_table
+ *
+ * See the comments in the sk_has_sleeper function.
+ */
+static inline void sock_poll_wait(struct file *filp,
+		wait_queue_head_t *wait_address, poll_table *p)
+{
+	if (p && wait_address) {
+		poll_wait(filp, wait_address, p);
+		/*
+		 * We need to be sure we are in sync with the
+		 * socket flags modification.
+		 *
+		 * This memory barrier is paired in the sk_has_sleeper.
+		*/
+		smp_mb();
+	}
+}
+
 /*
  * 	Queue a received datagram if it will fit. Stream and sequenced
  *	protocols can't normally use this as they need to fit buffers in

net/atm/common.c

@@ -92,7 +92,7 @@ static void vcc_sock_destruct(struct sock *sk)
 static void vcc_def_wakeup(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up(sk->sk_sleep);
 	read_unlock(&sk->sk_callback_lock);
 }
@@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk)
 	read_lock(&sk->sk_callback_lock);
 
 	if (vcc_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible(sk->sk_sleep);
 
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
@@ -594,7 +594,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct atm_vcc *vcc;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	vcc = ATM_SD(sock);

net/core/datagram.c

@@ -712,7 +712,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */

net/core/sock.c

@@ -1715,15 +1715,15 @@ EXPORT_SYMBOL(sock_no_sendpage);
 static void sock_def_wakeup(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_all(sk->sk_sleep);
 	read_unlock(&sk->sk_callback_lock);
 }
 
 static void sock_def_error_report(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_poll(sk->sk_sleep, POLLERR);
 	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
 	read_unlock(&sk->sk_callback_lock);
@@ -1732,7 +1732,7 @@ static void sock_def_error_report(struct sock *sk)
 static void sock_def_readable(struct sock *sk, int len)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN |
 						POLLRDNORM | POLLRDBAND);
 	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -1747,7 +1747,7 @@ static void sock_def_write_space(struct sock *sk)
 	 * progress.  --DaveM
 	 */
 	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 

net/dccp/output.c

@@ -196,7 +196,7 @@ void dccp_write_space(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
 
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible(sk->sk_sleep);
 	/* Should agree with poll, otherwise some programs break */
 	if (sock_writeable(sk))

net/dccp/proto.c

@@ -311,7 +311,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 

net/ipv4/tcp.c

@@ -339,7 +339,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct sock *sk = sock->sk;
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	if (sk->sk_state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 

net/iucv/af_iucv.c

@@ -306,7 +306,7 @@ static inline int iucv_below_msglim(struct sock *sk)
 static void iucv_sock_wake_msglim(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_all(sk->sk_sleep);
 	sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	read_unlock(&sk->sk_callback_lock);
@@ -1256,7 +1256,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	unsigned int mask = 0;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);

net/rxrpc/af_rxrpc.c

@@ -63,7 +63,7 @@ static void rxrpc_write_space(struct sock *sk)
 	_enter("%p", sk);
 	read_lock(&sk->sk_callback_lock);
 	if (rxrpc_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible(sk->sk_sleep);
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
@@ -588,7 +588,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx

net/unix/af_unix.c

@@ -315,7 +315,7 @@ static void unix_write_space(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
 	if (unix_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible_sync(sk->sk_sleep);
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
@@ -1985,7 +1985,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table
 	struct sock *sk = sock->sk;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2022,7 +2022,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk, *other;
 	unsigned int mask, writable;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2053,7 +2053,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		other = unix_peer_get(sk);
 		if (other) {
 			if (unix_peer(other) != sk) {
-				poll_wait(file, &unix_sk(other)->peer_wait,
+				sock_poll_wait(file, &unix_sk(other)->peer_wait,
 					  wait);
 				if (unix_recvq_full(other))
 					writable = 0;