3.19.1-stable review

@@ -46,7 +46,7 @@ static __always_inline bool static_key_f
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
 {
-	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+	set_bit(0, (volatile unsigned long *)&lock->tickets.head);
 }
 
 #else  /* !CONFIG_PARAVIRT_SPINLOCKS */

@@ -60,10 +60,30 @@ static inline void __ticket_unlock_kick(
 }
 
 #endif /* CONFIG_PARAVIRT_SPINLOCKS */
+static inline int  __tickets_equal(__ticket_t one, __ticket_t two)
+{
+	return !((one ^ two) & ~TICKET_SLOWPATH_FLAG);
+}
+
+static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock,
+							__ticket_t head)
+{
+	if (head & TICKET_SLOWPATH_FLAG) {
+		arch_spinlock_t old, new;
+
+		old.tickets.head = head;
+		new.tickets.head = head & ~TICKET_SLOWPATH_FLAG;
+		old.tickets.tail = new.tickets.head + TICKET_LOCK_INC;
+		new.tickets.tail = old.tickets.tail;
+
+		/* try to clear slowpath flag when there are no contenders */
+		cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
+	}
+}
 
 static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
-	return lock.tickets.head == lock.tickets.tail;
+	return __tickets_equal(lock.tickets.head, lock.tickets.tail);
 }
 
 /*

@@ -87,18 +107,21 @@ static __always_inline void arch_spin_lo
 	if (likely(inc.head == inc.tail))
 		goto out;
 
-	inc.tail &= ~TICKET_SLOWPATH_FLAG;
 	for (;;) {
 		unsigned count = SPIN_THRESHOLD;
 
 		do {
-			if (READ_ONCE(lock->tickets.head) == inc.tail)
-				goto out;
+			inc.head = READ_ONCE(lock->tickets.head);
+			if (__tickets_equal(inc.head, inc.tail))
+				goto clear_slowpath;
 			cpu_relax();
 		} while (--count);
 		__ticket_lock_spinning(lock, inc.tail);
 	}
-out:	barrier();	/* make sure nothing creeps before the lock is taken */
+clear_slowpath:
+	__ticket_check_and_clear_slowpath(lock, inc.head);
+out:
+	barrier();	/* make sure nothing creeps before the lock is taken */
 }
 
 static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)

@@ -106,56 +129,30 @@ static __always_inline int arch_spin_try
 	arch_spinlock_t old, new;
 
 	old.tickets = READ_ONCE(lock->tickets);
-	if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
+	if (!__tickets_equal(old.tickets.head, old.tickets.tail))
 		return 0;
 
 	new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
+	new.head_tail &= ~TICKET_SLOWPATH_FLAG;
 
 	/* cmpxchg is a full barrier, so nothing can move before it */
 	return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
 }
 
-static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
-					    arch_spinlock_t old)
-{
-	arch_spinlock_t new;
-
-	BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
-
-	/* Perform the unlock on the "before" copy */
-	old.tickets.head += TICKET_LOCK_INC;
-
-	/* Clear the slowpath flag */
-	new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
-
-	/*
-	 * If the lock is uncontended, clear the flag - use cmpxchg in
-	 * case it changes behind our back though.
-	 */
-	if (new.tickets.head != new.tickets.tail ||
-	    cmpxchg(&lock->head_tail, old.head_tail,
-					new.head_tail) != old.head_tail) {
-		/*
-		 * Lock still has someone queued for it, so wake up an
-		 * appropriate waiter.
-		 */
-		__ticket_unlock_kick(lock, old.tickets.head);
-	}
-}
-
 static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	if (TICKET_SLOWPATH_FLAG &&
-	    static_key_false(&paravirt_ticketlocks_enabled)) {
-		arch_spinlock_t prev;
+		static_key_false(&paravirt_ticketlocks_enabled)) {
+		__ticket_t head;
 
-		prev = *lock;
-		add_smp(&lock->tickets.head, TICKET_LOCK_INC);
+		BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
 
-		/* add_smp() is a full mb() */
+		head = xadd(&lock->tickets.head, TICKET_LOCK_INC);
 
-		if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
-			__ticket_unlock_slowpath(lock, prev);
+		if (unlikely(head & TICKET_SLOWPATH_FLAG)) {
+			head &= ~TICKET_SLOWPATH_FLAG;
+			__ticket_unlock_kick(lock, (head + TICKET_LOCK_INC));
+		}
 	} else
 		__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
 }

@@ -164,14 +161,15 @@ static inline int arch_spin_is_locked(ar
 {
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
-	return tmp.tail != tmp.head;
+	return !__tickets_equal(tmp.tail, tmp.head);
 }
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
-	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
+	tmp.head &= ~TICKET_SLOWPATH_FLAG;
+	return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
 #define arch_spin_is_contended	arch_spin_is_contended
 

@@ -183,16 +181,16 @@ static __always_inline void arch_spin_lo
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-	__ticket_t head = ACCESS_ONCE(lock->tickets.head);
+	__ticket_t head = READ_ONCE(lock->tickets.head);
 
 	for (;;) {
-		struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+		struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 		/*
 		 * We need to check "unlocked" in a loop, tmp.head == head
 		 * can be false positive because of overflow.
 		 */
-		if (tmp.head == (tmp.tail & ~TICKET_SLOWPATH_FLAG) ||
-		    tmp.head != head)
+		if (__tickets_equal(tmp.head, tmp.tail) ||
+				!__tickets_equal(tmp.head, head))
 			break;
 
 		cpu_relax();

@@ -609,7 +609,7 @@ static inline void check_zero(void)
 	u8 ret;
 	u8 old;
 
-	old = ACCESS_ONCE(zero_stats);
+	old = READ_ONCE(zero_stats);
 	if (unlikely(old)) {
 		ret = cmpxchg(&zero_stats, old, 0);
 		/* This ensures only one fellow resets the stat */

@@ -727,6 +727,7 @@ __visible void kvm_lock_spinning(struct
 	int cpu;
 	u64 start;
 	unsigned long flags;
+	__ticket_t head;
 
 	if (in_nmi())
 		return;

@@ -768,11 +769,15 @@ __visible void kvm_lock_spinning(struct
 	 */
 	__ticket_enter_slowpath(lock);
 
+	/* make sure enter_slowpath, which is atomic does not cross the read */
+	smp_mb__after_atomic();
+
 	/*
 	 * check again make sure it didn't become free while
 	 * we weren't looking.
 	 */
-	if (ACCESS_ONCE(lock->tickets.head) == want) {
+	head = READ_ONCE(lock->tickets.head);
+	if (__tickets_equal(head, want)) {
 		add_stats(TAKEN_SLOW_PICKUP, 1);
 		goto out;
 	}

@@ -803,8 +808,8 @@ static void kvm_unlock_kick(struct arch_
 	add_stats(RELEASED_SLOW, 1);
 	for_each_cpu(cpu, &waiting_cpus) {
 		const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
-		if (ACCESS_ONCE(w->lock) == lock &&
-		    ACCESS_ONCE(w->want) == ticket) {
+		if (READ_ONCE(w->lock) == lock &&
+		    READ_ONCE(w->want) == ticket) {
 			add_stats(RELEASED_SLOW_KICKED, 1);
 			kvm_kick_cpu(cpu);
 			break;

@@ -41,7 +41,7 @@ static u8 zero_stats;
 static inline void check_zero(void)
 {
 	u8 ret;
-	u8 old = ACCESS_ONCE(zero_stats);
+	u8 old = READ_ONCE(zero_stats);
 	if (unlikely(old)) {
 		ret = cmpxchg(&zero_stats, old, 0);
 		/* This ensures only one fellow resets the stat */

@@ -112,6 +112,7 @@ __visible void xen_lock_spinning(struct
 	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
 	int cpu = smp_processor_id();
 	u64 start;
+	__ticket_t head;
 	unsigned long flags;
 
 	/* If kicker interrupts not initialized yet, just spin */

@@ -159,11 +160,15 @@ __visible void xen_lock_spinning(struct
 	 */
 	__ticket_enter_slowpath(lock);
 
+	/* make sure enter_slowpath, which is atomic does not cross the read */
+	smp_mb__after_atomic();
+
 	/*
 	 * check again make sure it didn't become free while
 	 * we weren't looking
 	 */
-	if (ACCESS_ONCE(lock->tickets.head) == want) {
+	head = READ_ONCE(lock->tickets.head);
+	if (__tickets_equal(head, want)) {
 		add_stats(TAKEN_SLOW_PICKUP, 1);
 		goto out;
 	}

@@ -204,8 +209,8 @@ static void xen_unlock_kick(struct arch_
 		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
 
 		/* Make sure we read lock before want */
-		if (ACCESS_ONCE(w->lock) == lock &&
-		    ACCESS_ONCE(w->want) == next) {
+		if (READ_ONCE(w->lock) == lock &&
+		    READ_ONCE(w->want) == next) {
 			add_stats(RELEASED_SLOW_KICKED, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 			break;

@@ -554,7 +554,7 @@ static bool alloc_p2m(unsigned long pfn)
 		mid_mfn = NULL;
 	}
 
-	p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep));
+	p2m_pfn = pte_pfn(READ_ONCE(*ptep));
 	if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
 	    p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
 		/* p2m leaf page is missing */