[tip: locking/core] locking/pvqspinlock: Use try_cmpxchg_acquire() in trylock_clear_pending()

[tip-bot2 for Uros Bizjak]

The following commit has been merged into the locking/core branch of tip:

Commit-ID:     6a97734f2222e0352f1900e3eb3167e9069b91bb
Gitweb:        https://git.kernel.org/tip/6a97734f2222e0352f1900e3eb3167e9069b91bb
Author:        Uros Bizjak <ubizjak@xxxxxxxxx>
AuthorDate:    Mon, 25 Mar 2024 15:09:32 +01:00
Committer:     Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Fri, 12 Apr 2024 11:40:51 +02:00

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@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: Waiman Long <longman@xxxxxxxxxx>
Reviewed-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20240325140943.815051-1-ubizjak@xxxxxxxxx
---
 kernel/locking/qspinlock_paravirt.h | 31 +++++++++++-----------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 169950f..77ba80b 100644
--- 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 */