X-Git-Url: https://git.kernel.dk/?a=blobdiff_plain;f=include%2Fnet%2Fsock.h;h=4eb8409249f6dfbdec81708921fe48d24cea639d;hb=a57de0b4336e48db2811a2030bb68dba8dd09d88;hp=352f06bbd7a9b14b0257b8014d4ecf3027aad44e;hpb=1b614fb9a00e97b1eab54d4e442d405229c059dd;p=linux-2.6-block.git

diff --git a/include/net/sock.h b/include/net/sock.h
index 352f06bbd7a9..4eb8409249f6 100644
--- a/include/net/sock.h
+++ b/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