Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Lots of tidying up changes all across the map for Linux's formal
   memory/locking-model tooling, by Alan Stern, Akira Yokosawa, Andrea
   Parri, Paul E. McKenney and SeongJae Park.

   Notable changes beyond an overall update in the tooling itself is the
   tidying up of spin_is_locked() semantics, which spills over into the
   kernel proper as well.

 - qspinlock improvements: the locking algorithm now guarantees forward
   progress whereas the previous implementation in mainline could starve
   threads indefinitely in cmpxchg() loops. Also other related cleanups
   to the qspinlock code (Will Deacon)

 - misc smaller improvements, cleanups and fixes all across the locking
   subsystem

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  locking/rwsem: Simplify the is-owner-spinnable checks
  tools/memory-model: Add reference for 'Simplifying ARM concurrency'
  tools/memory-model: Update ASPLOS information
  MAINTAINERS, tools/memory-model: Update e-mail address for Andrea Parri
  tools/memory-model: Fix coding style in 'lock.cat'
  tools/memory-model: Remove out-of-date comments and code from lock.cat
  tools/memory-model: Improve mixed-access checking in lock.cat
  tools/memory-model: Improve comments in lock.cat
  tools/memory-model: Remove duplicated code from lock.cat
  tools/memory-model: Flag "cumulativity" and "propagation" tests
  tools/memory-model: Add model support for spin_is_locked()
  tools/memory-model: Add scripts to test memory model
  tools/memory-model: Fix coding style in 'linux-kernel.def'
  tools/memory-model: Model 'smp_store_mb()'
  tools/memory-order: Update the cheat-sheet to show that smp_mb__after_atomic() orders later RMW operations
  tools/memory-order: Improve key for SELF and SV
  tools/memory-model: Fix cheat sheet typo
  tools/memory-model: Update required version of herdtools7
  tools/memory-model: Redefine rb in terms of rcu-fence
  tools/memory-model: Rename link and rcu-path to rcu-link and rb
  ...

9 files changed, 198 insertions, 256 deletions

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e2764d767f18..ca8ac2824f0b 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,23 +44,24 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 {
 	tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
 	if (tsk->delays)
-		spin_lock_init(&tsk->delays->lock);
+		raw_spin_lock_init(&tsk->delays->lock);
 }
 
 /*
  * Finish delay accounting for a statistic using its timestamps (@start),
  * accumalator (@total) and @count
  */
-static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
+static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total,
+			  u32 *count)
 {
 	s64 ns = ktime_get_ns() - *start;
 	unsigned long flags;
 
 	if (ns > 0) {
-		spin_lock_irqsave(lock, flags);
+		raw_spin_lock_irqsave(lock, flags);
 		*total += ns;
 		(*count)++;
-		spin_unlock_irqrestore(lock, flags);
+		raw_spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -127,7 +128,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
 	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
 
-	spin_lock_irqsave(&tsk->delays->lock, flags);
+	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
 	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
 	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
 	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
@@ -137,7 +138,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
-	spin_unlock_irqrestore(&tsk->delays->lock, flags);
+	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
 }
@@ -147,10 +148,10 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
 	__u64 ret;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tsk->delays->lock, flags);
+	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
 	ret = nsec_to_clock_t(tsk->delays->blkio_delay +
 				tsk->delays->swapin_delay);
-	spin_unlock_irqrestore(&tsk->delays->lock, flags);
+	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 	return ret;
 }
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 023386338269..edcac5de7ebc 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -561,20 +561,24 @@ static void print_lock(struct held_lock *hlock)
 	printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
 }
 
-static void lockdep_print_held_locks(struct task_struct *curr)
+static void lockdep_print_held_locks(struct task_struct *p)
 {
-	int i, depth = curr->lockdep_depth;
+	int i, depth = READ_ONCE(p->lockdep_depth);
 
-	if (!depth) {
-		printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr));
+	if (!depth)
+		printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p));
+	else
+		printk("%d lock%s held by %s/%d:\n", depth,
+		       depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+	/*
+	 * It's not reliable to print a task's held locks if it's not sleeping
+	 * and it's not the current task.
+	 */
+	if (p->state == TASK_RUNNING && p != current)
 		return;
-	}
-	printk("%d lock%s held by %s/%d:\n",
-		depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr));
-
 	for (i = 0; i < depth; i++) {
 		printk(" #%d: ", i);
-		print_lock(curr->held_locks + i);
+		print_lock(p->held_locks + i);
 	}
 }
 
@@ -4451,8 +4455,6 @@ EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
-	int count = 10;
-	int unlock = 1;
 
 	if (unlikely(!debug_locks)) {
 		pr_warn("INFO: lockdep is turned off.\n");
@@ -4460,50 +4462,18 @@ void debug_show_all_locks(void)
 	}
 	pr_warn("\nShowing all locks held in the system:\n");
 
-	/*
-	 * Here we try to get the tasklist_lock as hard as possible,
-	 * if not successful after 2 seconds we ignore it (but keep
-	 * trying). This is to enable a debug printout even if a
-	 * tasklist_lock-holding task deadlocks or crashes.
-	 */
-retry:
-	if (!read_trylock(&tasklist_lock)) {
-		if (count == 10)
-			pr_warn("hm, tasklist_lock locked, retrying... ");
-		if (count) {
-			count--;
-			pr_cont(" #%d", 10-count);
-			mdelay(200);
-			goto retry;
-		}
-		pr_cont(" ignoring it.\n");
-		unlock = 0;
-	} else {
-		if (count != 10)
-			pr_cont(" locked it.\n");
-	}
-
-	do_each_thread(g, p) {
-		/*
-		 * It's not reliable to print a task's held locks
-		 * if it's not sleeping (or if it's not the current
-		 * task):
-		 */
-		if (p->state == TASK_RUNNING && p != current)
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		if (!p->lockdep_depth)
 			continue;
-		if (p->lockdep_depth)
-			lockdep_print_held_locks(p);
-		if (!unlock)
-			if (read_trylock(&tasklist_lock))
-				unlock = 1;
+		lockdep_print_held_locks(p);
 		touch_nmi_watchdog();
-	} while_each_thread(g, p);
+		touch_all_softlockup_watchdogs();
+	}
+	rcu_read_unlock();
 
 	pr_warn("\n");
 	pr_warn("=============================================\n\n");
-
-	if (unlock)
-		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
 #endif
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index f046b7ce9dd6..5e10153b4d3c 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -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
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2048359f33d2..f44f658ae629 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -139,8 +139,9 @@ static inline bool __mutex_trylock(struct mutex *lock)
 static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
 {
 	unsigned long curr = (unsigned long)current;
+	unsigned long zero = 0UL;
 
-	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
 		return true;
 
 	return false;
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index d880296245c5..bfaeb05123ff 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -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 <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
  *          Peter Zijlstra <peterz@infradead.org>
  */
 
@@ -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
@@ -77,6 +82,18 @@
 #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.
  *
@@ -114,41 +131,18 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 
 #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
 
-/*
- * 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.
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
  *
- * This internal structure is also used by the set_locked function which
- * is not restricted to _Q_PENDING_BITS == 8.
+ * *,1,* -> *,0,*
  */
-struct __qspinlock {
-	union {
-		atomic_t val;
-#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
-	};
-};
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
 
-#if _Q_PENDING_BITS == 8
 /**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
@@ -159,9 +153,7 @@ struct __qspinlock {
  */
 static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
 }
 
 /*
@@ -176,19 +168,28 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
  */
 static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
-	 * 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(&l->tail,
+	return (u32)xchg_relaxed(&lock->tail,
 				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #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
  *
@@ -216,10 +217,11 @@ 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;
 
@@ -237,9 +239,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
  */
 static __always_inline void set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 }
 
 
@@ -294,86 +294,83 @@ 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));
 
 	if (pv_enabled())
-		goto queue;
+		goto pv_queue;
 
 	if (virt_spin_lock(lock))
 		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--);
 	}
 
 	/*
+	 * 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) {
+			atomic_cond_read_acquire(&lock->val,
+						 !(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);
+		qstat_inc(qstat_lock_pending, true);
 		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
 	 * 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);
@@ -400,12 +397,18 @@ queue:
 		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;
@@ -417,14 +420,8 @@ queue:
 	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);
@@ -453,8 +450,8 @@ queue:
 	 *
 	 * 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.
 	 *
@@ -464,44 +461,38 @@ queue:
 	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:
 	/*
 	 * 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) {
-			set_locked(lock);
-			break;
-		}
-		/*
-		 * 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.
-		 */
-		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
-		if (old == val)
-			goto release;	/* No contention */
 
-		val = old;
-	}
+	/*
+	 * 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);
 
 	/*
 	 * 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);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6ee477765e6c..5a0cf5f9008c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -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,
@@ -87,8 +82,6 @@ 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 +90,7 @@ 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 +110,7 @@ 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);
-}
-
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 0);
+	WRITE_ONCE(lock->pending, 1);
 }
 
 /*
@@ -136,10 +120,8 @@ 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 */
@@ -148,11 +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);
@@ -384,7 +361,6 @@ 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 +389,7 @@ 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 +404,6 @@ 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;
@@ -443,7 +418,7 @@ 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++) {
 		/*
@@ -479,13 +454,13 @@ 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 +468,7 @@ 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 +493,6 @@ gotlock:
 __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 +521,7 @@ __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 +547,6 @@ __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 +554,7 @@ __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;
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 4a30ef63c607..6bd78c0740fc 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -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",
 };
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a90336779375..3064c50e181e 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -347,6 +347,15 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 	}
 }
 
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner;
@@ -359,17 +368,10 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
-	if (!owner || !is_rwsem_owner_spinnable(owner)) {
-		ret = !owner;	/* !owner is spinnable */
-		goto done;
+	if (owner) {
+		ret = is_rwsem_owner_spinnable(owner) &&
+		      owner_on_cpu(owner);
 	}
-
-	/*
-	 * As lock holder preemption issue, we both skip spinning if task is not
-	 * on cpu or its cpu is preempted
-	 */
-	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-done:
 	rcu_read_unlock();
 	return ret;
 }
@@ -398,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 * abort spinning when need_resched or owner is not running or
 		 * owner's cpu is preempted.
 		 */
-		if (!owner->on_cpu || need_resched() ||
-				vcpu_is_preempted(task_cpu(owner))) {
+		if (need_resched() || !owner_on_cpu(owner)) {
 			rcu_read_unlock();
 			return false;
 		}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 64c0291b579c..f89014a2c238 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -37,7 +37,7 @@ struct cpu_stop_done {
 struct cpu_stopper {
 	struct task_struct	*thread;
 
-	spinlock_t		lock;
+	raw_spinlock_t		lock;
 	bool			enabled;	/* is this stopper enabled? */
 	struct list_head	works;		/* list of pending works */
 
@@ -81,13 +81,13 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	unsigned long flags;
 	bool enabled;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
 		__cpu_stop_queue_work(stopper, work, &wakeq);
 	else if (work->done)
 		cpu_stop_signal_done(work->done);
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
 	wake_up_q(&wakeq);
 
@@ -237,8 +237,8 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	DEFINE_WAKE_Q(wakeq);
 	int err;
 retry:
-	spin_lock_irq(&stopper1->lock);
-	spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+	raw_spin_lock_irq(&stopper1->lock);
+	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
 	err = -ENOENT;
 	if (!stopper1->enabled || !stopper2->enabled)
@@ -261,8 +261,8 @@ retry:
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
 unlock:
-	spin_unlock(&stopper2->lock);
-	spin_unlock_irq(&stopper1->lock);
+	raw_spin_unlock(&stopper2->lock);
+	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
 		while (stop_cpus_in_progress)
@@ -457,9 +457,9 @@ static int cpu_stop_should_run(unsigned int cpu)
 	unsigned long flags;
 	int run;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 	run = !list_empty(&stopper->works);
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 	return run;
 }
 
@@ -470,13 +470,13 @@ static void cpu_stopper_thread(unsigned int cpu)
 
 repeat:
 	work = NULL;
-	spin_lock_irq(&stopper->lock);
+	raw_spin_lock_irq(&stopper->lock);
 	if (!list_empty(&stopper->works)) {
 		work = list_first_entry(&stopper->works,
 					struct cpu_stop_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_irq(&stopper->lock);
+	raw_spin_unlock_irq(&stopper->lock);
 
 	if (work) {
 		cpu_stop_fn_t fn = work->fn;
@@ -550,7 +550,7 @@ static int __init cpu_stop_init(void)
 	for_each_possible_cpu(cpu) {
 		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-		spin_lock_init(&stopper->lock);
+		raw_spin_lock_init(&stopper->lock);
 		INIT_LIST_HEAD(&stopper->works);
 	}