Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

3 files changed, 74 insertions, 1 deletions

diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index e73e2429a1b..2ce29831feb 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -99,7 +99,6 @@ enum rfkill_user_states {
 #undef RFKILL_STATE_UNBLOCKED
 #undef RFKILL_STATE_HARD_BLOCKED
 
-#include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 252b245cfcf..4be57ab0347 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -132,6 +132,11 @@ do {								\
 #endif /*__raw_spin_is_contended*/
 #endif
 
+/* The lock does not imply full memory barrier. */
+#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
+static inline void smp_mb__after_lock(void) { smp_mb(); }
+#endif
+
 /**
  * spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.
diff --git a/include/net/sock.h b/include/net/sock.h
index 352f06bbd7a..2c0da9239b9 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 +1242,74 @@ 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.
+ *
+ * The sk_has_sleeper is always called right after a call to read_lock, so we
+ * can use smp_mb__after_lock barrier.
+ */
+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__after_lock();
+	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