locking/spinlocks: Remove an instruction from spin and write locks

Both spin locks and write locks currently do:

f0 0f b1 17 lock cmpxchg %edx,(%rdi)
85 c0 test %eax,%eax
75 05 jne [slowpath]

This 'test' insn is superfluous; the cmpxchg insn sets the Z flag
appropriately. Peter pointed out that using atomic_try_cmpxchg_acquire()
will let the compiler know this is true. Comparing before/after
disassemblies show the only effect is to remove this insn.

Take this opportunity to make the spin & write lock code resemble each
other more closely and have similar likely() hints.

Suggested-by: Peter Zijlstra <[e-mail]>
Signed-off-by: Matthew Wilcox <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Acked-by: Will Deacon <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Waiman Long <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

include/asm-generic/qrwlock.h

···
 	if (unlikely(cnts))
 		return 0;
 
-	return likely(atomic_cmpxchg_acquire(&lock->cnts,
-					     cnts, cnts | _QW_LOCKED) == cnts);
+	return likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts,
+				_QW_LOCKED));
 }
 /**
  * queued_read_lock - acquire read lock of a queue rwlock
···
  */
 static inline void queued_write_lock(struct qrwlock *lock)
 {
+	u32 cnts = 0;
 	/* Optimize for the unfair lock case where the fair flag is 0. */
-	if (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0)
+	if (likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)))
 		return;
 
 	queued_write_lock_slowpath(lock);

include/asm-generic/qspinlock.h

···
  */
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
-	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
-		return 1;
-	return 0;
+	u32 val = atomic_read(&lock->val);
+
+	if (unlikely(val))
+		return 0;
+
+	return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL));
 }
 
 extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
···
  */
 static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
-	u32 val;
+	u32 val = 0;
 
-	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
-	if (likely(val == 0))
+	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
 		return;
+
 	queued_spin_lock_slowpath(lock, val);
 }