locking/pvqspinlock: Use try_cmpxchg() in qspinlock_paravirt.h

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

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>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20240411192317.25432-2-ubizjak@gmail.com

kernel/locking/qspinlock_paravirt.h

@@ -86,9 +86,10 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 	 */
 	for (;;) {
 		int val = atomic_read(&lock->val);
+		u8 old = 0;
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
-		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
+		    try_cmpxchg_acquire(&lock->locked, &old, _Q_LOCKED_VAL)) {
 			lockevent_inc(pv_lock_stealing);
 			return true;
 		}
@@ -211,8 +212,9 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
 	int hopcnt = 0;
 
 	for_each_hash_entry(he, offset, hash) {
+		struct qspinlock *old = NULL;
 		hopcnt++;
-		if (!cmpxchg(&he->lock, NULL, lock)) {
+		if (try_cmpxchg(&he->lock, &old, lock)) {
 			WRITE_ONCE(he->node, node);
 			lockevent_pv_hop(hopcnt);
 			return &he->lock;
@@ -355,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-
+	enum vcpu_state old = vcpu_halted;
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
 	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will
@@ -372,8 +374,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * subsequent writes.
 	 */
 	smp_mb__before_atomic();
-	if (cmpxchg_relaxed(&pn->state, vcpu_halted, vcpu_hashed)
-	    != vcpu_halted)
+	if (!try_cmpxchg_relaxed(&pn->state, &old, vcpu_hashed))
 		return;
 
 	/*
@@ -541,15 +542,14 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #ifndef __pv_queued_spin_unlock
 __visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	u8 locked;
+	u8 locked = _Q_LOCKED_VAL;
 
 	/*
 	 * We must not unlock if SLOW, because in that case we must first
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
-	if (likely(locked == _Q_LOCKED_VAL))
+	if (try_cmpxchg_release(&lock->locked, &locked, 0))
 		return;
 
 	__pv_queued_spin_unlock_slowpath(lock, locked);