Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - big rtmutex and futex cleanup and robustification from Thomas
     Gleixner
   - mutex optimizations and refinements from Jason Low
   - arch_mutex_cpu_relax() removal and related cleanups
   - smaller lockdep tweaks"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  arch, locking: Ciao arch_mutex_cpu_relax()
  locking/lockdep: Only ask for /proc/lock_stat output when available
  locking/mutexes: Optimize mutex trylock slowpath
  locking/mutexes: Try to acquire mutex only if it is unlocked
  locking/mutexes: Delete the MUTEX_SHOW_NO_WAITER macro
  locking/mutexes: Correct documentation on mutex optimistic spinning
  rtmutex: Make the rtmutex tester depend on BROKEN
  futex: Simplify futex_lock_pi_atomic() and make it more robust
  futex: Split out the first waiter attachment from lookup_pi_state()
  futex: Split out the waiter check from lookup_pi_state()
  futex: Use futex_top_waiter() in lookup_pi_state()
  futex: Make unlock_pi more robust
  rtmutex: Avoid pointless requeueing in the deadlock detection chain walk
  rtmutex: Cleanup deadlock detector debug logic
  rtmutex: Confine deadlock logic to futex
  rtmutex: Simplify remove_waiter()
  rtmutex: Document pi chain walk
  rtmutex: Clarify the boost/deboost part
  rtmutex: No need to keep task ref for lock owner check
  rtmutex: Simplify and document try_to_take_rtmutex()
  ...

1 files changed, 20 insertions, 19 deletions

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index acca2c1a3c5e..ae712b25e492 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -46,12 +46,6 @@
 # include <asm/mutex.h>
 #endif
 
-/*
- * A negative mutex count indicates that waiters are sleeping waiting for the
- * mutex.
- */
-#define	MUTEX_SHOW_NO_WAITER(mutex)	(atomic_read(&(mutex)->count) >= 0)
-
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -152,7 +146,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		if (need_resched())
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
 
@@ -388,12 +382,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	/*
 	 * Optimistic spinning.
 	 *
-	 * We try to spin for acquisition when we find that there are no
-	 * pending waiters and the lock owner is currently running on a
-	 * (different) CPU.
-	 *
-	 * The rationale is that if the lock owner is running, it is likely to
-	 * release the lock soon.
+	 * We try to spin for acquisition when we find that the lock owner
+	 * is currently running on a (different) CPU and while we don't
+	 * need to reschedule. The rationale is that if the lock owner is
+	 * running, it is likely to release the lock soon.
 	 *
 	 * Since this needs the lock owner, and this mutex implementation
 	 * doesn't track the owner atomically in the lock field, we need to
@@ -440,7 +432,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		if (owner && !mutex_spin_on_owner(lock, owner))
 			break;
 
-		if ((atomic_read(&lock->count) == 1) &&
+		/* Try to acquire the mutex if it is unlocked. */
+		if (!mutex_is_locked(lock) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			if (use_ww_ctx) {
@@ -471,7 +464,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	osq_unlock(&lock->osq);
 slowpath:
@@ -485,8 +478,11 @@ slowpath:
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
-	/* once more, can we acquire the lock? */
-	if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, 0) == 1))
+	/*
+	 * Once more, try to acquire the lock. Only try-lock the mutex if
+	 * it is unlocked to reduce unnecessary xchg() operations.
+	 */
+	if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -506,9 +502,10 @@ slowpath:
 		 * it's unlocked. Later on, if we sleep, this is the
 		 * operation that gives us the lock. We xchg it to -1, so
 		 * that when we release the lock, we properly wake up the
-		 * other waiters:
+		 * other waiters. We only attempt the xchg if the count is
+		 * non-negative in order to avoid unnecessary xchg operations:
 		 */
-		if (MUTEX_SHOW_NO_WAITER(lock) &&
+		if (atomic_read(&lock->count) >= 0 &&
 		    (atomic_xchg(&lock->count, -1) == 1))
 			break;
 
@@ -823,6 +820,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
 	unsigned long flags;
 	int prev;
 
+	/* No need to trylock if the mutex is locked. */
+	if (mutex_is_locked(lock))
+		return 0;
+
 	spin_lock_mutex(&lock->wait_lock, flags);
 
 	prev = atomic_xchg(&lock->count, -1);