kernel/locking: qspinlock improvements

index 34a028a7bcc5..5b2b0b5ea06d 100644
@@ -244,6 +244,8 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_inc_not_zero(l) \
 	ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
 
+#define atomic_long_cond_read_relaxed(v, c) \
+	ATOMIC_LONG_PFX(_cond_read_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (c))
 #define atomic_long_cond_read_acquire(v, c) \
 	ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c))
 

index 29458bbb2fa0..2cafdbb9ae4c 100644
@@ -221,18 +221,17 @@ do {									\
 #endif
 
 /**
- * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
  * @ptr: pointer to the variable to wait on
  * @cond: boolean expression to wait for
  *
- * Equivalent to using smp_load_acquire() on the condition variable but employs
- * the control dependency of the wait to reduce the barrier on many platforms.
+ * Equivalent to using READ_ONCE() on the condition variable.
  *
  * Due to C lacking lambda expressions we load the value of *ptr into a
  * pre-named variable @VAL to be used in @cond.
  */
-#ifndef smp_cond_load_acquire
-#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+#ifndef smp_cond_load_relaxed
+#define smp_cond_load_relaxed(ptr, cond_expr) ({		\
 	typeof(ptr) __PTR = (ptr);				\
 	typeof(*ptr) VAL;					\
 	for (;;) {						\

@@ -241,10 +240,26 @@ do {									\
 			break;					\
 		cpu_relax();					\
 	}							\
-	smp_acquire__after_ctrl_dep();				\
 	VAL;							\
 })
 #endif
 
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+	typeof(*ptr) _val;					\
+	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
+	smp_acquire__after_ctrl_dep();				\
+	_val;							\
+})
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */

index 8b276fd9a127..01ce3997cb42 100644
@@ -654,6 +654,7 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
+#define atomic_cond_read_relaxed(v, c)	smp_cond_load_relaxed(&(v)->counter, (c))
 #define atomic_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
 
 #ifdef CONFIG_GENERIC_ATOMIC64

@@ -1075,6 +1076,7 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v
 }
 #endif
 
+#define atomic64_cond_read_relaxed(v, c)	smp_cond_load_relaxed(&(v)->counter, (c))
 #define atomic64_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
 
 #include <asm-generic/atomic-long.h>

index 5e16b5d40d32..90b0b0ed8161 100644
@@ -16,7 +16,7 @@
  */
 static inline void native_queued_spin_unlock(struct qspinlock *lock)
 {
-	smp_store_release((u8 *)lock, 0);
+	smp_store_release(&lock->locked, 0);
 }
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS

index 923307ea11c7..9ef5ee03d2d7 100644
@@ -22,8 +22,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
  *
  * void __pv_queued_spin_unlock(struct qspinlock *lock)
  * {
- *	struct __qspinlock *l = (void *)lock;
- *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *	u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
  *
  *	if (likely(lockval == _Q_LOCKED_VAL))
  *		return;

index 034acd0c4956..0763f065b975 100644
@@ -29,13 +29,41 @@
 #endif
 
 typedef struct qspinlock {
-	atomic_t	val;
+	union {
+		atomic_t val;
+
+		/*
+		 * By using the whole 2nd least significant byte for the
+		 * pending bit, we can allow better optimization of the lock
+		 * acquisition for the pending bit holder.
+		 */
+#ifdef __LITTLE_ENDIAN
+		struct {
+			u8	locked;
+			u8	pending;
+		};
+		struct {
+			u16	locked_pending;
+			u16	tail;
+		};
+#else
+		struct {
+			u16	tail;
+			u16	locked_pending;
+		};
+		struct {
+			u8	reserved[2];
+			u8	pending;
+			u8	locked;
+		};
+#endif
+	};
 } arch_spinlock_t;
 
 /*
  * Initializier
  */
-#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ .val = ATOMIC_INIT(0) }
 
 /*
  * Bitfields in the atomic value:

74 lines not on this page · raw message

index 6ee477765e6c..2711940429f5 100644
@@ -87,8 +87,6 @@ struct pv_node {
 #define queued_spin_trylock(l)	pv_hybrid_queued_unfair_trylock(l)
 static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
 	 * Stay in unfair lock mode as long as queued mode waiters are
 	 * present in the MCS wait queue but the pending bit isn't set.

@@ -97,7 +95,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 		int val = atomic_read(&lock->val);
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
-		   (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
 			qstat_inc(qstat_pv_lock_stealing, true);
 			return true;
 		}

@@ -117,16 +115,12 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 #if _Q_PENDING_BITS == 8
 static __always_inline void set_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 1);
+	WRITE_ONCE(lock->pending, 1);
 }
 
 static __always_inline void clear_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 0);
+	WRITE_ONCE(lock->pending, 0);
 }
 
 /*

@@ -136,10 +130,8 @@ static __always_inline void clear_pending(struct qspinlock *lock)
  */
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	return !READ_ONCE(l->locked) &&
-	       (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL,
+	return !READ_ONCE(lock->locked) &&
+	       (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
 				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */

@@ -384,7 +376,6 @@ 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;
-	struct __qspinlock *l = (void *)lock;
 
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of

@@ -413,7 +404,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * the hash table later on at unlock time, no atomic instruction is
 	 * needed.
 	 */
-	WRITE_ONCE(l->locked, _Q_SLOW_VAL);
+	WRITE_ONCE(lock->locked, _Q_SLOW_VAL);
 	(void)pv_hash(lock, pn);
 }
 

@@ -428,7 +419,6 @@ static u32
 pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	struct __qspinlock *l = (void *)lock;
 	struct qspinlock **lp = NULL;
 	int waitcnt = 0;
 	int loop;

@@ -479,13 +469,13 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 			 *
 			 * Matches the smp_rmb() in __pv_queued_spin_unlock().
 			 */
-			if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
+			if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) {
 				/*
 				 * The lock was free and now we own the lock.
 				 * Change the lock value back to _Q_LOCKED_VAL
 				 * and unhash the table.
 				 */
-				WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+				WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 				WRITE_ONCE(*lp, NULL);
 				goto gotlock;
 			}

@@ -493,7 +483,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
-		pv_wait(&l->locked, _Q_SLOW_VAL);
+		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
 		 * Because of lock stealing, the queue head vCPU may not be

@@ -518,7 +508,6 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 __visible void
 __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
-	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {

@@ -547,7 +536,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * Now that we have a reference to the (likely) blocked pv_node,
 	 * release the lock.
 	 */
-	smp_store_release(&l->locked, 0);
+	smp_store_release(&lock->locked, 0);
 
 	/*
 	 * At this point the memory pointed at by lock can be freed/reused,

@@ -573,7 +562,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #ifndef __pv_queued_spin_unlock
 __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
 	u8 locked;
 
 	/*

@@ -581,7 +569,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0);
+	locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
 	if (likely(locked == _Q_LOCKED_VAL))
 		return;
 

index f5b0e59f6d14..a0f7976348f8 100644
@@ -77,6 +77,18 @@
 #endif
 
 /*
+ * The pending bit spinning loop count.
+ * This heuristic is used to limit the number of lockword accesses
+ * made by atomic_cond_read_relaxed when waiting for the lock to
+ * transition out of the "== _Q_PENDING_VAL" state. We don't spin
+ * indefinitely because there's no guarantee that we'll make forward
+ * progress.
+ */
+#ifndef _Q_PENDING_LOOPS
+#define _Q_PENDING_LOOPS	1
+#endif
+
+/*
  * Per-CPU queue node structures; we can never have more than 4 nested
  * contexts: task, softirq, hardirq, nmi.
  *

@@ -266,13 +278,15 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		return;
 
 	/*
-	 * wait for in-progress pending->locked hand-overs
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
 	 *
 	 * 0,1,0 -> 0,0,1
 	 */
 	if (val == _Q_PENDING_VAL) {
-		while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
-			cpu_relax();
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed(&lock->val,
+					       (VAL != _Q_PENDING_VAL) || !cnt--);
 	}
 
 	/*

index 90b0b0ed8161..da1370ad206d 100644
@@ -7,6 +7,8 @@
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
 
+#define _Q_PENDING_LOOPS	(1 << 9)
+
 #define	queued_spin_unlock queued_spin_unlock
 /**
  * queued_spin_unlock - release a queued spinlock

index a0f7976348f8..ad94b7def005 100644
@@ -128,6 +128,17 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 
 #if _Q_PENDING_BITS == 8
 /**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
+
+/**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
  *

@@ -163,6 +174,17 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 #else /* _Q_PENDING_BITS == 8 */
 
 /**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
+/**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
  *

@@ -266,7 +288,7 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	struct mcs_spinlock *prev, *next, *node;
-	u32 new, old, tail;
+	u32 old, tail;
 	int idx;
 
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));

@@ -290,58 +312,50 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	}
 
 	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
 	 * trylock || pending
 	 *
 	 * 0,0,0 -> 0,0,1 ; trylock
 	 * 0,0,1 -> 0,1,1 ; pending
 	 */
-	for (;;) {
+	val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+	if (!(val & ~_Q_LOCKED_MASK)) {
 		/*
-		 * If we observe any contention; queue.
+		 * we're pending, wait for the owner to go away.
+		 *
+		 * *,1,1 -> *,1,0
+		 *
+		 * this wait loop must be a load-acquire such that we match the
+		 * store-release that clears the locked bit and create lock
+		 * sequentiality; this is because not all
+		 * clear_pending_set_locked() implementations imply full
+		 * barriers.
 		 */
-		if (val & ~_Q_LOCKED_MASK)
-			goto queue;
-
-		new = _Q_LOCKED_VAL;
-		if (val == new)
-			new |= _Q_PENDING_VAL;
+		if (val & _Q_LOCKED_MASK) {
+			smp_cond_load_acquire(&lock->val.counter,
+					      !(VAL & _Q_LOCKED_MASK));
+		}
 
 		/*
-		 * Acquire semantic is required here as the function may
-		 * return immediately if the lock was free.
+		 * take ownership and clear the pending bit.
+		 *
+		 * *,1,0 -> *,0,1
 		 */
-		old = atomic_cmpxchg_acquire(&lock->val, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
-
-	/*
-	 * we won the trylock
-	 */
-	if (new == _Q_LOCKED_VAL)
+		clear_pending_set_locked(lock);
 		return;
+	}
 
 	/*
-	 * we're pending, wait for the owner to go away.
-	 *
-	 * *,1,1 -> *,1,0
-	 *
-	 * this wait loop must be a load-acquire such that we match the
-	 * store-release that clears the locked bit and create lock
-	 * sequentiality; this is because not all clear_pending_set_locked()
-	 * implementations imply full barriers.
-	 */
-	smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
-
-	/*
-	 * take ownership and clear the pending bit.
-	 *
-	 * *,1,0 -> *,0,1
+	 * If pending was clear but there are waiters in the queue, then
+	 * we need to undo our setting of pending before we queue ourselves.
 	 */
-	clear_pending_set_locked(lock);
-	return;
+	if (!(val & _Q_PENDING_MASK))
+		clear_pending(lock);
 
 	/*
 	 * End of pending bit optimistic spinning and beginning of MCS

@@ -445,15 +459,15 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * claim the lock:
 	 *
 	 * n,0,0 -> 0,0,1 : lock, uncontended
-	 * *,0,0 -> *,0,1 : lock, contended
+	 * *,*,0 -> *,*,1 : lock, contended
 	 *
-	 * If the queue head is the only one in the queue (lock value == tail),
-	 * clear the tail code and grab the lock. Otherwise, we only need
-	 * to grab the lock.
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
 	 */
 	for (;;) {
 		/* In the PV case we might already have _Q_LOCKED_VAL set */
-		if ((val & _Q_TAIL_MASK) != tail) {
+		if ((val & _Q_TAIL_MASK) != tail || (val & _Q_PENDING_MASK)) {
 			set_locked(lock);
 			break;
 		}

index 2711940429f5..2dbad2f25480 100644
@@ -118,11 +118,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	WRITE_ONCE(lock->pending, 1);
 }
 
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	WRITE_ONCE(lock->pending, 0);
-}
-
 /*
  * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
  * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the

index 25730b2ac022..5a0cf5f9008c 100644
@@ -130,11 +130,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	atomic_andnot(_Q_PENDING_VAL, &lock->val);
-}
-
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
 	int val = atomic_read(&lock->val);

index ad94b7def005..e42f50d69ed6 100644
@@ -465,24 +465,21 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * and nobody is pending, clear the tail code and grab the lock.
 	 * Otherwise, we only need to grab the lock.
 	 */
-	for (;;) {
-		/* In the PV case we might already have _Q_LOCKED_VAL set */
-		if ((val & _Q_TAIL_MASK) != tail || (val & _Q_PENDING_MASK)) {
-			set_locked(lock);
-			break;
-		}
+
+	/* In the PV case we might already have _Q_LOCKED_VAL set */
+	if ((val & _Q_TAIL_MASK) == tail) {
 		/*
 		 * The smp_cond_load_acquire() call above has provided the
-		 * necessary acquire semantics required for locking. At most
-		 * two iterations of this loop may be ran.
+		 * necessary acquire semantics required for locking.
 		 */
 		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
 		if (old == val)
-			goto release;	/* No contention */
-
-		val = old;
+			goto release; /* No contention */
 	}
 
+	/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
+	set_locked(lock);
+
 	/*
 	 * contended path; wait for next if not observed yet, release.
 	 */

index e42f50d69ed6..5e383cfe4cce 100644
@@ -337,8 +337,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		 * barriers.
 		 */
 		if (val & _Q_LOCKED_MASK) {
-			smp_cond_load_acquire(&lock->val.counter,
-					      !(VAL & _Q_LOCKED_MASK));
+			atomic_cond_read_acquire(&lock->val,
+						 !(VAL & _Q_LOCKED_MASK));
 		}
 
 		/*

@@ -441,8 +441,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_cond_load_acquire() call. As the next PV queue head hasn't been
-	 * designated yet, there is no way for the locked value to become
+	 * atomic_cond_read_acquire() call. As the next PV queue head hasn't
+	 * been designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.
 	 *

@@ -452,7 +452,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	if ((val = pv_wait_head_or_lock(lock, node)))
 		goto locked;
 
-	val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK));
+	val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
 
 locked:
 	/*

@@ -469,7 +469,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	/* In the PV case we might already have _Q_LOCKED_VAL set */
 	if ((val & _Q_TAIL_MASK) == tail) {
 		/*
-		 * The smp_cond_load_acquire() call above has provided the
+		 * The atomic_cond_read_acquire() call above has provided the
 		 * necessary acquire semantics required for locking.
 		 */
 		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);

index f046b7ce9dd6..5e10153b4d3c 100644
@@ -23,13 +23,15 @@ struct mcs_spinlock {
 
 #ifndef arch_mcs_spin_lock_contended
 /*
- * Using smp_load_acquire() provides a memory barrier that ensures
- * subsequent operations happen after the lock is acquired.
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
  */
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
-	while (!(smp_load_acquire(l)))					\
-		cpu_relax();						\
+	smp_cond_load_acquire(l, VAL);					\
 } while (0)
 #endif
 

index 5e383cfe4cce..7b8c81ebb15e 100644
@@ -483,10 +483,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	/*
 	 * contended path; wait for next if not observed yet, release.
 	 */
-	if (!next) {
-		while (!(next = READ_ONCE(node->next)))
-			cpu_relax();
-	}
+	if (!next)
+		next = smp_cond_load_relaxed(&node->next, (VAL));
 
 	arch_mcs_spin_unlock_contended(&next->locked);
 	pv_kick_node(lock, next);

index da1370ad206d..3e70bed8a978 100644
@@ -9,6 +9,12 @@
 
 #define _Q_PENDING_LOOPS	(1 << 9)
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
 #define	queued_spin_unlock queued_spin_unlock
 /**
  * queued_spin_unlock - release a queued spinlock

@@ -21,12 +27,6 @@ static inline void native_queued_spin_unlock(struct qspinlock *lock)
 	smp_store_release(&lock->locked, 0);
 }
 
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_init_lock_hash(void);
-extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
-
 static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	pv_queued_spin_lock_slowpath(lock, val);

@@ -42,11 +42,6 @@ static inline bool vcpu_is_preempted(long cpu)
 {
 	return pv_vcpu_is_preempted(cpu);
 }
-#else
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
-	native_queued_spin_unlock(lock);
-}
 #endif
 
 #ifdef CONFIG_PARAVIRT

index b37b4ad7eb94..a8ed0a352d75 100644
@@ -100,7 +100,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 	/*
 	 * unlock() needs release semantics:
 	 */
-	(void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val);
+	smp_store_release(&lock->locked, 0);
 }
 #endif
 

index 7b8c81ebb15e..fa5d2ab369f9 100644
@@ -164,10 +164,10 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
 	/*
-	 * Use release semantics to make sure that the MCS node is properly
-	 * initialized before changing the tail code.
+	 * We can use relaxed semantics since the caller ensures that the
+	 * MCS node is properly initialized before updating the tail.
 	 */
-	return (u32)xchg_release(&lock->tail,
+	return (u32)xchg_relaxed(&lock->tail,
 				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 

@@ -212,10 +212,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
 		/*
-		 * Use release semantics to make sure that the MCS node is
-		 * properly initialized before changing the tail code.
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
 		 */
-		old = atomic_cmpxchg_release(&lock->val, val, new);
+		old = atomic_cmpxchg_relaxed(&lock->val, val, new);
 		if (old == val)
 			break;
 

@@ -388,12 +389,18 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		goto release;
 
 	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
 	 * We have already touched the queueing cacheline; don't bother with
 	 * pending stuff.
 	 *
 	 * p,*,* -> n,*,*
-	 *
-	 * RELEASE, such that the stores to @node must be complete.
 	 */
 	old = xchg_tail(lock, tail);
 	next = NULL;

@@ -405,14 +412,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
 
-		/*
-		 * We must ensure that the stores to @node are observed before
-		 * the write to prev->next. The address dependency from
-		 * xchg_tail is not sufficient to ensure this because the read
-		 * component of xchg_tail is unordered with respect to the
-		 * initialisation of @node.
-		 */
-		smp_store_release(&prev->next, node);
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
 
 		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);

index fa5d2ab369f9..1e3ddc42135e 100644
@@ -467,16 +467,15 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * Otherwise, we only need to grab the lock.
 	 */
 
-	/* In the PV case we might already have _Q_LOCKED_VAL set */
-	if ((val & _Q_TAIL_MASK) == tail) {
-		/*
-		 * The atomic_cond_read_acquire() call above has provided the
-		 * necessary acquire semantics required for locking.
-		 */
-		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
-		if (old == val)
-			goto release; /* No contention */
-	}
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set.
+	 *
+	 * The atomic_cond_read_acquire() call above has provided the
+	 * necessary acquire semantics required for locking.
+	 */
+	if (((val & _Q_TAIL_MASK) == tail) &&
+	    atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+		goto release; /* No contention */
 
 	/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
 	set_locked(lock);

index 1e3ddc42135e..b39f341d831b 100644
@@ -12,11 +12,11 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
- * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2013-2014,2018 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
  * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <[email protected]>
+ * Authors: Waiman Long <[email protected]>
  *          Peter Zijlstra <[email protected]>
  */
 

@@ -33,6 +33,11 @@
 #include <asm/qspinlock.h>
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * The basic principle of a queue-based spinlock can best be understood
  * by studying a classic queue-based spinlock implementation called the
  * MCS lock. The paper below provides a good description for this kind

@@ -295,7 +300,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
 
 	if (pv_enabled())
-		goto queue;
+		goto pv_queue;
 
 	if (virt_spin_lock(lock))
 		return;

@@ -348,6 +353,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		 * *,1,0 -> *,0,1
 		 */
 		clear_pending_set_locked(lock);
+		qstat_inc(qstat_lock_pending, true);
 		return;
 	}
 

@@ -363,6 +369,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * queuing.
 	 */
 queue:
+	qstat_inc(qstat_lock_slowpath, true);
+pv_queue:
 	node = this_cpu_ptr(&mcs_nodes[0]);
 	idx = node->count++;
 	tail = encode_tail(smp_processor_id(), idx);

index 2dbad2f25480..25730b2ac022 100644
@@ -56,11 +56,6 @@ struct pv_node {
 };
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Hybrid PV queued/unfair lock
  *
  * By replacing the regular queued_spin_trylock() with the function below,

@@ -428,7 +423,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_pv_lock_slowpath, true);
+	qstat_inc(qstat_lock_slowpath, true);
 
 	for (;; waitcnt++) {
 		/*

index 4a30ef63c607..6bd78c0740fc 100644
@@ -22,13 +22,14 @@
  *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
  *   pv_latency_kick	- average latency (ns) of vCPU kick operation
  *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_slowpath	- # of locking operations via the slowpath
  *   pv_lock_stealing	- # of lock stealing operations
  *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
  *   pv_wait_again	- # of wait's after a queue head vCPU kick
  *   pv_wait_early	- # of early vCPU wait's
  *   pv_wait_head	- # of vCPU wait's at the queue head
  *   pv_wait_node	- # of vCPU wait's at a non-head queue node
+ *   lock_pending	- # of locking operations via pending code
+ *   lock_slowpath	- # of locking operations via MCS lock queue
  *
  * Writing to the "reset_counters" file will reset all the above counter
  * values.

@@ -46,13 +47,14 @@ enum qlock_stats {
 	qstat_pv_kick_wake,
 	qstat_pv_latency_kick,
 	qstat_pv_latency_wake,
-	qstat_pv_lock_slowpath,
 	qstat_pv_lock_stealing,
 	qstat_pv_spurious_wakeup,
 	qstat_pv_wait_again,
 	qstat_pv_wait_early,
 	qstat_pv_wait_head,
 	qstat_pv_wait_node,
+	qstat_lock_pending,
+	qstat_lock_slowpath,
 	qstat_num,	/* Total number of statistical counters */
 	qstat_reset_cnts = qstat_num,
 };

@@ -73,12 +75,13 @@ static const char * const qstat_names[qstat_num + 1] = {
 	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
 	[qstat_pv_latency_kick]	   = "pv_latency_kick",
 	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_slowpath]   = "pv_lock_slowpath",
 	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
 	[qstat_pv_wait_again]      = "pv_wait_again",
 	[qstat_pv_wait_early]      = "pv_wait_early",
 	[qstat_pv_wait_head]       = "pv_wait_head",
 	[qstat_pv_wait_node]       = "pv_wait_node",
+	[qstat_lock_pending]       = "lock_pending",
+	[qstat_lock_slowpath]      = "lock_slowpath",
 	[qstat_reset_cnts]         = "reset_counters",
 };