locking/pvqspinlock: Use try_cmpxchg_acquire() in trylock_clear_pending()

Replace this pattern in trylock_clear_pending():

    cmpxchg_acquire(*ptr, old, new) == old

... with the simpler and faster:

    try_cmpxchg_acquire(*ptr, &old, new)

The x86 CMPXCHG instruction returns success in the ZF flag, so this change
saves a compare after the CMPXCHG.

Also change the return type of the function to bool and streamline
the control flow in the _Q_PENDING_BITS == 8 variant a bit.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20240325140943.815051-1-ubizjak@gmail.com

diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 169950fe1aad996b11e3eb7033d8f5c3fb2d14e6..77ba80bd95f98b1948717407de93c57895c31b04 100644 (file)
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -116,11 +116,12 @@ static __always_inline void set_pending(struct qspinlock *lock)
  * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the
  * lock just to be sure that it will get it.
  */
-static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
 {
+       u16 old = _Q_PENDING_VAL;
+
        return !READ_ONCE(lock->locked) &&
-              (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
-                               _Q_LOCKED_VAL) == _Q_PENDING_VAL);
+              try_cmpxchg_acquire(&lock->locked_pending, &old, _Q_LOCKED_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */
 static __always_inline void set_pending(struct qspinlock *lock)
@@ -128,27 +129,21 @@ static __always_inline void set_pending(struct qspinlock *lock)
        atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
-static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
 {
-       int val = atomic_read(&lock->val);
-
-       for (;;) {
-               int old, new;
-
-               if (val  & _Q_LOCKED_MASK)
-                       break;
+       int old, new;
 
+       old = atomic_read(&lock->val);
+       do {
+               if (old & _Q_LOCKED_MASK)
+                       return false;
                /*
                 * Try to clear pending bit & set locked bit
                 */
-               old = val;
-               new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
-               val = atomic_cmpxchg_acquire(&lock->val, old, new);
+               new = (old & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+       } while (!atomic_try_cmpxchg_acquire (&lock->val, &old, new));
 
-               if (val == old)
-                       return 1;
-       }
-       return 0;
+       return true;
 }
 #endif /* _Q_PENDING_BITS == 8 */