Received-SPF: pass (google.com: domain of linux-kernel+bounces-141529-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Uros Bizjak <ubizjak@gmail.com>
To: x86@kernel.org,
	linux-kernel@vger.kernel.org
Cc: Uros Bizjak <ubizjak@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	Will Deacon <will@kernel.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Waiman Long <longman@redhat.com>
Subject: [PATCH v2 1/2] locking/pvqspinlock: Use try_cmpxchg_acquire() in trylock_clear_pending()
Date: Thu, 11 Apr 2024 21:22:54 +0200
Message-ID: <20240411192317.25432-1-ubizjak@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Use try_cmpxchg_acquire(*ptr, &old, new) instead of
cmpxchg_acquire(*ptr, old, new) == old in trylock_clear_pending().
x86 CMPXCHG instruction returns success in ZF flag, so this change
saves a compare after cmpxchg.

Also change the return type of the function to bool.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Waiman Long <longman@redhat.com>
---
v2: Correct cut-n-pasto in the ChangeLog.
---
 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 169950fe1aad..77ba80bd95f9 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 */
 
-- 
2.42.0