2 files changed, 151 insertions, 1 deletions

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f5b7127f54ac..7f5809eddee6 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -31,6 +31,7 @@ Contents:
 
      - Locking functions.
      - Interrupt disabling functions.
+     - Sleep and wake-up functions.
      - Miscellaneous functions.
 
  (*) Inter-CPU locking barrier effects.
@@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
 other means.
 
 
+SLEEP AND WAKE-UP FUNCTIONS
+---------------------------
+
+Sleeping and waking on an event flagged in global data can be viewed as an
+interaction between two pieces of data: the task state of the task waiting for
+the event and the global data used to indicate the event.  To make sure that
+these appear to happen in the right order, the primitives to begin the process
+of going to sleep, and the primitives to initiate a wake up imply certain
+barriers.
+
+Firstly, the sleeper normally follows something like this sequence of events:
+
+        for (;;) {
+                set_current_state(TASK_UNINTERRUPTIBLE);
+                if (event_indicated)
+                        break;
+                schedule();
+        }
+
+A general memory barrier is interpolated automatically by set_current_state()
+after it has altered the task state:
+
+        CPU 1
+        ===============================
+        set_current_state();
+          set_mb();
+            STORE current->state
+            <general barrier>
+        LOAD event_indicated
+
+set_current_state() may be wrapped by:
+
+        prepare_to_wait();
+        prepare_to_wait_exclusive();
+
+which therefore also imply a general memory barrier after setting the state.
+The whole sequence above is available in various canned forms, all of which
+interpolate the memory barrier in the right place:
+
+        wait_event();
+        wait_event_interruptible();
+        wait_event_interruptible_exclusive();
+        wait_event_interruptible_timeout();
+        wait_event_killable();
+        wait_event_timeout();
+        wait_on_bit();
+        wait_on_bit_lock();
+
+
+Secondly, code that performs a wake up normally follows something like this:
+
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+or:
+
+        event_indicated = 1;
+        wake_up_process(event_daemon);
+
+A write memory barrier is implied by wake_up() and co. if and only if they wake
+something up.  The barrier occurs before the task state is cleared, and so sits
+between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+
+        CPU 1                           CPU 2
+        =============================== ===============================
+        set_current_state();            STORE event_indicated
+          set_mb();                     wake_up();
+            STORE current->state          <write barrier>
+            <general barrier>             STORE current->state
+        LOAD event_indicated
+
+The available waker functions include:
+
+        complete();
+        wake_up();
+        wake_up_all();
+        wake_up_bit();
+        wake_up_interruptible();
+        wake_up_interruptible_all();
+        wake_up_interruptible_nr();
+        wake_up_interruptible_poll();
+        wake_up_interruptible_sync();
+        wake_up_interruptible_sync_poll();
+        wake_up_locked();
+        wake_up_locked_poll();
+        wake_up_nr();
+        wake_up_poll();
+        wake_up_process();
+
+
+[!] Note that the memory barriers implied by the sleeper and the waker do _not_
+order multiple stores before the wake-up with respect to loads of those stored
+values after the sleeper has called set_current_state().  For instance, if the
+sleeper does:
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (event_indicated)
+                break;
+        __set_current_state(TASK_RUNNING);
+        do_something(my_data);
+
+and the waker does:
+
+        my_data = value;
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+there's no guarantee that the change to event_indicated will be perceived by
+the sleeper as coming after the change to my_data.  In such a circumstance, the
+code on both sides must interpolate its own memory barriers between the
+separate data accesses.  Thus the above sleeper ought to do:
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (event_indicated) {
+                smp_rmb();
+                do_something(my_data);
+        }
+
+and the waker should do:
+
+        my_data = value;
+        smp_wmb();
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+
 MISCELLANEOUS FUNCTIONS
 -----------------------
 
@@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
 
 Under normal operation, memory operation reordering is generally not going to
 be a problem as a single-threaded linear piece of code will still appear to
-work correctly, even if it's in an SMP kernel.  There are, however, three
+work correctly, even if it's in an SMP kernel.  There are, however, four
 circumstances in which reordering definitely _could_ be a problem:
 
  (*) Interprocessor interaction.
diff --git a/kernel/sched.c b/kernel/sched.c
index 228acae8821f..c3c04e256560 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2464,6 +2464,17 @@ out:
         return success;
 }
 
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
 int wake_up_process(struct task_struct *p)
 {
         return try_to_wake_up(p, TASK_ALL, 0);
@@ -5425,6 +5436,9 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up(wait_queue_head_t *q, unsigned int mode,
                         int nr_exclusive, void *key)
@@ -5463,6 +5477,9 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
  * with each other. This can prevent needless bouncing between CPUs.
  *
  * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
                         int nr_exclusive, void *key)
@@ -5499,6 +5516,9 @@ EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
  * awakened in the same order in which they were queued.
  *
  * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete(struct completion *x)
 {
@@ -5516,6 +5536,9 @@ EXPORT_SYMBOL(complete);
  * @x:  holds the state of this particular completion
  *
  * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete_all(struct completion *x)
 {