[PATCH 6/8] optimize rt lock wakeup

[Gregory Haskins <ghaskins@xxxxxxxxxx>]

It is redundant to wake the grantee task if it is already running

Credit goes to Peter Morreale for the general idea.

Signed-off-by: Gregory Haskins <ghaskins@xxxxxxxxxx>
Signed-off-by: Peter Morreale <pmorreale@xxxxxxxxxx>
---

 kernel/rtmutex.c |   44 +++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index f50ec55..f60d03f 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -519,6 +519,40 @@ static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
 	pendowner = waiter->task;
 	waiter->task = NULL;
 
+	/*
+	 * Do the wakeup before the ownership change to give any spinning
+	 * waiter grantees a headstart over the other threads that will
+	 * trigger once owner changes.
+	 *
+	 * We can skip the actual (expensive) wakeup if the
+	 * waiter is already running, but we have to be careful
+	 * of race conditions because they may be about to sleep.
+	 *
+	 * The waiter-side protocol has the following pattern:
+	 * 1: Set state != RUNNING
+	 * 2: Conditionally sleep if waiter->task != NULL;
+	 *
+	 * And the owner-side has the following:
+	 * A: Set waiter->task = NULL
+	 * B: Conditionally wake if the state != RUNNING
+	 *
+	 * As long as we ensure 1->2 order, and A->B order, we
+	 * will never miss a wakeup.
+	 *
+	 * Therefore, this barrier ensures that waiter->task = NULL
+	 * is visible before we test the pendowner->state.  The
+	 * corresponding barrier is in the sleep logic.
+	 */
+	smp_mb();
+
+	if ((pendowner->state != TASK_RUNNING)
+	    && (pendowner->state != TASK_RUNNING_MUTEX)) {
+		if (savestate)
+			wake_up_process_mutex(pendowner);
+		else
+			wake_up_process(pendowner);
+	}
+
 	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
 
 	spin_unlock(&current->pi_lock);
@@ -545,11 +579,6 @@ static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
 		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
 	}
 	spin_unlock(&pendowner->pi_lock);
-
-	if (savestate)
-		wake_up_process_mutex(pendowner);
-	else
-		wake_up_process(pendowner);
 }
 
 /*
@@ -754,6 +783,11 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
 		/* adaptive_wait() returns 1 if we need to sleep */
 		if (adaptive_wait(lock, &waiter, &adaptive)) {
 			update_current(TASK_UNINTERRUPTIBLE, &saved_state);
+			/*
+			 * The xchg() in update_current() is an implicit
+			 * barrier which we rely upon to ensure current->state
+			 * is visible before we test waiter.task.
+			 */
 			if (waiter.task)
 				schedule_rt_mutex(lock);
 		}

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html