On 04/18/2014 03:46 AM, Ingo Molnar wrote:

* Waiman Long[off-list ref]  wrote:

quoted

On 04/17/2014 11:58 AM, Peter Zijlstra wrote:

quoted

On Thu, Apr 17, 2014 at 11:03:57AM -0400, Waiman Long wrote:

quoted

+static __always_inline void
+clear_pending_set_locked(struct qspinlock *lock, u32 val)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	ACCESS_ONCE(l->locked_pending) = 1;
+}

@@ -157,8 +251,13 @@ static inline int trylock_pending(struct qspinlock *lock, u32 *pval)
  	 * we're pending, wait for the owner to go away.
  	 *
  	 * *,1,1 ->   *,1,0
+	 *
+	 * this wait loop must be a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this because not all try_clear_pending_set_locked()
+	 * implementations imply full barriers.

You renamed the function referred in the above comment.

Sorry, will fix the comments.

I suggest not renaming the function instead.
try_clear_pending_set_locked() tells the intent in a clearer fashion.

Thanks,

	Ingo

I usually use the word "try" if there is a possibility of failure. 
However, the function will always succeed, albeit by waiting a bit in 
some cases. That is why I remove "try" from the name.

-Longman