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

Pull locking updates from Ingo Molnar:
 "The tree got pretty big in this development cycle, but the net effect
  is pretty good:

    115 files changed, 673 insertions(+), 1522 deletions(-)

  The main changes were:

   - Rework and generalize the mutex code to remove per arch mutex
     primitives. (Peter Zijlstra)

   - Add vCPU preemption support: add an interface to query the
     preemption status of vCPUs and use it in locking primitives - this
     optimizes paravirt performance. (Pan Xinhui, Juergen Gross,
     Christian Borntraeger)

   - Introduce cpu_relax_yield() and remov cpu_relax_lowlatency() to
     clean up and improve the s390 lock yielding machinery and its core
     kernel impact. (Christian Borntraeger)

   - Micro-optimize mutexes some more. (Waiman Long)

   - Reluctantly add the to-be-deprecated mutex_trylock_recursive()
     interface on a temporary basis, to give the DRM code more time to
     get rid of its locking hacks. Any other users will be NAK-ed on
     sight. (We turned off the deprecation warning for the time being to
     not pollute the build log.) (Peter Zijlstra)

   - Improve the rtmutex code a bit, in light of recent long lived
     bugs/races. (Thomas Gleixner)

   - Misc fixes, cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/paravirt: Fix bool return type for PVOP_CALL()
  x86/paravirt: Fix native_patch()
  locking/ww_mutex: Use relaxed atomics
  locking/rtmutex: Explain locking rules for rt_mutex_proxy_unlock()/init_proxy_locked()
  locking/rtmutex: Get rid of RT_MUTEX_OWNER_MASKALL
  x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()
  locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted
  locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()
  Documentation/virtual/kvm: Support the vCPU preemption check
  x86/xen: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  kvm: Introduce kvm_write_guest_offset_cached()
  locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests
  locking/spinlocks, s390: Implement vcpu_is_preempted(cpu)
  locking/core, powerpc: Implement vcpu_is_preempted(cpu)
  sched/core: Introduce the vcpu_is_preempted(cpu) interface
  sched/wake_q: Rename WAKE_Q to DEFINE_WAKE_Q
  locking/core: Provide common cpu_relax_yield() definition
  locking/mutex: Don't mark mutex_trylock_recursive() as deprecated, temporarily
  ...

15 files changed, 400 insertions, 335 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index ebdb0043203a..84d882f3e299 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -225,7 +225,7 @@ config ARCH_SUPPORTS_ATOMIC_RMW
 
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+	depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y
diff --git a/kernel/futex.c b/kernel/futex.c
index 2c4be467fecd..9246d9f593d1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1298,7 +1298,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	struct task_struct *new_owner;
 	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 	bool deboost;
 	int ret = 0;
 
@@ -1415,7 +1415,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (!bitset)
 		return -EINVAL;
@@ -1469,7 +1469,7 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	int ret, op_ret;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
@@ -1708,7 +1708,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (requeue_pi) {
 		/*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4d7ffc0a0d00..7bd265f6b098 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -840,9 +840,9 @@ static struct lock_list *alloc_list_entry(void)
 /*
  * Add a new dependency to the head of the list:
  */
-static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
-			    struct list_head *head, unsigned long ip,
-			    int distance, struct stack_trace *trace)
+static int add_lock_to_list(struct lock_class *this, struct list_head *head,
+			    unsigned long ip, int distance,
+			    struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -1868,14 +1868,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * Ok, all validations passed, add the new lock
 	 * to the previous lock's dependency list:
 	 */
-	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+	ret = add_lock_to_list(hlock_class(next),
 			       &hlock_class(prev)->locks_after,
 			       next->acquire_ip, distance, &trace);
 
 	if (!ret)
 		return 0;
 
-	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+	ret = add_lock_to_list(hlock_class(prev),
 			       &hlock_class(next)->locks_before,
 			       next->acquire_ip, distance, &trace);
 	if (!ret)
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index c835270f0c2f..6a385aabcce7 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -28,7 +28,7 @@ struct mcs_spinlock {
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
 	while (!(smp_load_acquire(l)))					\
-		cpu_relax_lowlatency();					\
+		cpu_relax();						\
 } while (0)
 #endif
 
@@ -108,7 +108,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 			return;
 		/* Wait until the next pointer is set */
 		while (!(next = READ_ONCE(node->next)))
-			cpu_relax_lowlatency();
+			cpu_relax();
 	}
 
 	/* Pass lock to next waiter. */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9c951fade415..9aa713629387 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -73,21 +73,8 @@ void debug_mutex_unlock(struct mutex *lock)
 {
 	if (likely(debug_locks)) {
 		DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-
-		if (!lock->owner)
-			DEBUG_LOCKS_WARN_ON(!lock->owner);
-		else
-			DEBUG_LOCKS_WARN_ON(lock->owner != current);
-
 		DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	}
-
-	/*
-	 * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
-	 * mutexes so that we can do it here after we've verified state.
-	 */
-	mutex_clear_owner(lock);
-	atomic_set(&lock->count, 1);
 }
 
 void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 57a871ae3c81..a459faa48987 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -27,16 +27,6 @@ extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
 
-static inline void mutex_set_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, current);
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, NULL);
-}
-
 #define spin_lock_mutex(lock, flags)			\
 	do {						\
 		struct mutex *l = container_of(lock, struct mutex, wait_lock); \
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index a70b90db3909..9b349619f431 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -27,41 +27,176 @@
 #include <linux/debug_locks.h>
 #include <linux/osq_lock.h>
 
-/*
- * In the DEBUG case we are using the "NULL fastpath" for mutexes,
- * which forces all calls into the slowpath:
- */
 #ifdef CONFIG_DEBUG_MUTEXES
 # include "mutex-debug.h"
-# include <asm-generic/mutex-null.h>
-/*
- * Must be 0 for the debug case so we do not do the unlock outside of the
- * wait_lock region. debug_mutex_unlock() will do the actual unlock in this
- * case.
- */
-# undef __mutex_slowpath_needs_to_unlock
-# define  __mutex_slowpath_needs_to_unlock()	0
 #else
 # include "mutex.h"
-# include <asm/mutex.h>
 #endif
 
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
-	atomic_set(&lock->count, 1);
+	atomic_long_set(&lock->owner, 0);
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
-	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	osq_lock_init(&lock->osq);
 #endif
 
 	debug_mutex_init(lock, name, key);
 }
-
 EXPORT_SYMBOL(__mutex_init);
 
+/*
+ * @owner: contains: 'struct task_struct *' to the current lock owner,
+ * NULL means not owned. Since task_struct pointers are aligned at
+ * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low
+ * bits to store extra state.
+ *
+ * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
+ * Bit1 indicates unlock needs to hand the lock to the top-waiter
+ */
+#define MUTEX_FLAG_WAITERS	0x01
+#define MUTEX_FLAG_HANDOFF	0x02
+
+#define MUTEX_FLAGS		0x03
+
+static inline struct task_struct *__owner_task(unsigned long owner)
+{
+	return (struct task_struct *)(owner & ~MUTEX_FLAGS);
+}
+
+static inline unsigned long __owner_flags(unsigned long owner)
+{
+	return owner & MUTEX_FLAGS;
+}
+
+/*
+ * Actual trylock that will work on any unlocked state.
+ *
+ * When setting the owner field, we must preserve the low flag bits.
+ *
+ * Be careful with @handoff, only set that in a wait-loop (where you set
+ * HANDOFF) to avoid recursive lock attempts.
+ */
+static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
+{
+	unsigned long owner, curr = (unsigned long)current;
+
+	owner = atomic_long_read(&lock->owner);
+	for (;;) { /* must loop, can race against a flag */
+		unsigned long old, flags = __owner_flags(owner);
+
+		if (__owner_task(owner)) {
+			if (handoff && unlikely(__owner_task(owner) == current)) {
+				/*
+				 * Provide ACQUIRE semantics for the lock-handoff.
+				 *
+				 * We cannot easily use load-acquire here, since
+				 * the actual load is a failed cmpxchg, which
+				 * doesn't imply any barriers.
+				 *
+				 * Also, this is a fairly unlikely scenario, and
+				 * this contains the cost.
+				 */
+				smp_mb(); /* ACQUIRE */
+				return true;
+			}
+
+			return false;
+		}
+
+		/*
+		 * We set the HANDOFF bit, we must make sure it doesn't live
+		 * past the point where we acquire it. This would be possible
+		 * if we (accidentally) set the bit on an unlocked mutex.
+		 */
+		if (handoff)
+			flags &= ~MUTEX_FLAG_HANDOFF;
+
+		old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags);
+		if (old == owner)
+			return true;
+
+		owner = old;
+	}
+}
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+/*
+ * Lockdep annotations are contained to the slow paths for simplicity.
+ * There is nothing that would stop spreading the lockdep annotations outwards
+ * except more code.
+ */
+
+/*
+ * Optimistic trylock that only works in the uncontended case. Make sure to
+ * follow with a __mutex_trylock() before failing.
+ */
+static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
+{
+	unsigned long curr = (unsigned long)current;
+
+	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+		return true;
+
+	return false;
+}
+
+static __always_inline bool __mutex_unlock_fast(struct mutex *lock)
+{
+	unsigned long curr = (unsigned long)current;
+
+	if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr)
+		return true;
+
+	return false;
+}
+#endif
+
+static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag)
+{
+	atomic_long_or(flag, &lock->owner);
+}
+
+static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag)
+{
+	atomic_long_andnot(flag, &lock->owner);
+}
+
+static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter)
+{
+	return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter;
+}
+
+/*
+ * Give up ownership to a specific task, when @task = NULL, this is equivalent
+ * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE
+ * semantics like a regular unlock, the __mutex_trylock() provides matching
+ * ACQUIRE semantics for the handoff.
+ */
+static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
+{
+	unsigned long owner = atomic_long_read(&lock->owner);
+
+	for (;;) {
+		unsigned long old, new;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+#endif
+
+		new = (owner & MUTEX_FLAG_WAITERS);
+		new |= (unsigned long)task;
+
+		old = atomic_long_cmpxchg_release(&lock->owner, owner, new);
+		if (old == owner)
+			break;
+
+		owner = old;
+	}
+}
+
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * We split the mutex lock/unlock logic into separate fastpath and
@@ -69,7 +204,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
+static void __sched __mutex_lock_slowpath(struct mutex *lock);
 
 /**
  * mutex_lock - acquire the mutex
@@ -95,14 +230,10 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
 void __sched mutex_lock(struct mutex *lock)
 {
 	might_sleep();
-	/*
-	 * The locking fastpath is the 1->0 transition from
-	 * 'unlocked' into 'locked' state.
-	 */
-	__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
-	mutex_set_owner(lock);
-}
 
+	if (!__mutex_trylock_fast(lock))
+		__mutex_lock_slowpath(lock);
+}
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
@@ -149,9 +280,6 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
 /*
  * After acquiring lock with fastpath or when we lost out in contested
  * slowpath, set ctx and wake up any waiters so they can recheck.
- *
- * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
- * as the fastpath and opportunistic spinning are disabled in that case.
  */
 static __always_inline void
 ww_mutex_set_context_fastpath(struct ww_mutex *lock,
@@ -176,7 +304,7 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
 	/*
 	 * Check if lock is contended, if not there is nobody to wake up
 	 */
-	if (likely(atomic_read(&lock->base.count) == 0))
+	if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
 		return;
 
 	/*
@@ -227,7 +355,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 	bool ret = true;
 
 	rcu_read_lock();
-	while (lock->owner == owner) {
+	while (__mutex_owner(lock) == owner) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
 		 * checking lock->owner still matches owner. If that fails,
@@ -236,12 +364,16 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		 */
 		barrier();
 
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * Use vcpu_is_preempted to detect lock holder preemption issue.
+		 */
+		if (!owner->on_cpu || need_resched() ||
+				vcpu_is_preempted(task_cpu(owner))) {
 			ret = false;
 			break;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	rcu_read_unlock();
 
@@ -260,27 +392,25 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 		return 0;
 
 	rcu_read_lock();
-	owner = READ_ONCE(lock->owner);
+	owner = __mutex_owner(lock);
+
+	/*
+	 * As lock holder preemption issue, we both skip spinning if task is not
+	 * on cpu or its cpu is preempted
+	 */
 	if (owner)
-		retval = owner->on_cpu;
+		retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
 	rcu_read_unlock();
+
 	/*
-	 * if lock->owner is not set, the mutex owner may have just acquired
-	 * it and not set the owner yet or the mutex has been released.
+	 * If lock->owner is not set, the mutex has been released. Return true
+	 * such that we'll trylock in the spin path, which is a faster option
+	 * than the blocking slow path.
 	 */
 	return retval;
 }
 
 /*
- * Atomically try to take the lock when it is available
- */
-static inline bool mutex_try_to_acquire(struct mutex *lock)
-{
-	return !mutex_is_locked(lock) &&
-		(atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1);
-}
-
-/*
  * Optimistic spinning.
  *
  * We try to spin for acquisition when we find that the lock owner
@@ -288,13 +418,6 @@ static inline bool mutex_try_to_acquire(struct mutex *lock)
  * need to reschedule. The rationale is that if the lock owner is
  * running, it is likely to release the lock soon.
  *
- * Since this needs the lock owner, and this mutex implementation
- * doesn't track the owner atomically in the lock field, we need to
- * track it non-atomically.
- *
- * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
- * to serialize everything.
- *
  * The mutex spinners are queued up using MCS lock so that only one
  * spinner can compete for the mutex. However, if mutex spinning isn't
  * going to happen, there is no point in going through the lock/unlock
@@ -302,24 +425,39 @@ static inline bool mutex_try_to_acquire(struct mutex *lock)
  *
  * Returns true when the lock was taken, otherwise false, indicating
  * that we need to jump to the slowpath and sleep.
+ *
+ * The waiter flag is set to true if the spinner is a waiter in the wait
+ * queue. The waiter-spinner will spin on the lock directly and concurrently
+ * with the spinner at the head of the OSQ, if present, until the owner is
+ * changed to itself.
  */
 static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+				  struct ww_acquire_ctx *ww_ctx,
+				  const bool use_ww_ctx, const bool waiter)
 {
 	struct task_struct *task = current;
 
-	if (!mutex_can_spin_on_owner(lock))
-		goto done;
+	if (!waiter) {
+		/*
+		 * The purpose of the mutex_can_spin_on_owner() function is
+		 * to eliminate the overhead of osq_lock() and osq_unlock()
+		 * in case spinning isn't possible. As a waiter-spinner
+		 * is not going to take OSQ lock anyway, there is no need
+		 * to call mutex_can_spin_on_owner().
+		 */
+		if (!mutex_can_spin_on_owner(lock))
+			goto fail;
 
-	/*
-	 * In order to avoid a stampede of mutex spinners trying to
-	 * acquire the mutex all at once, the spinners need to take a
-	 * MCS (queued) lock first before spinning on the owner field.
-	 */
-	if (!osq_lock(&lock->osq))
-		goto done;
+		/*
+		 * In order to avoid a stampede of mutex spinners trying to
+		 * acquire the mutex all at once, the spinners need to take a
+		 * MCS (queued) lock first before spinning on the owner field.
+		 */
+		if (!osq_lock(&lock->osq))
+			goto fail;
+	}
 
-	while (true) {
+	for (;;) {
 		struct task_struct *owner;
 
 		if (use_ww_ctx && ww_ctx->acquired > 0) {
@@ -335,40 +473,26 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 			 * performed the optimistic spinning cannot be done.
 			 */
 			if (READ_ONCE(ww->ctx))
-				break;
+				goto fail_unlock;
 		}
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		owner = READ_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
-			break;
-
-		/* Try to acquire the mutex if it is unlocked. */
-		if (mutex_try_to_acquire(lock)) {
-			lock_acquired(&lock->dep_map, ip);
-
-			if (use_ww_ctx) {
-				struct ww_mutex *ww;
-				ww = container_of(lock, struct ww_mutex, base);
-
-				ww_mutex_set_context_fastpath(ww, ww_ctx);
+		owner = __mutex_owner(lock);
+		if (owner) {
+			if (waiter && owner == task) {
+				smp_mb(); /* ACQUIRE */
+				break;
 			}
 
-			mutex_set_owner(lock);
-			osq_unlock(&lock->osq);
-			return true;
+			if (!mutex_spin_on_owner(lock, owner))
+				goto fail_unlock;
 		}
 
-		/*
-		 * When there's no owner, we might have preempted between the
-		 * owner acquiring the lock and setting the owner field. If
-		 * we're an RT task that will live-lock because we won't let
-		 * the owner complete.
-		 */
-		if (!owner && (need_resched() || rt_task(task)))
+		/* Try to acquire the mutex if it is unlocked. */
+		if (__mutex_trylock(lock, waiter))
 			break;
 
 		/*
@@ -377,11 +501,20 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
-	osq_unlock(&lock->osq);
-done:
+	if (!waiter)
+		osq_unlock(&lock->osq);
+
+	return true;
+
+
+fail_unlock:
+	if (!waiter)
+		osq_unlock(&lock->osq);
+
+fail:
 	/*
 	 * If we fell out of the spin path because of need_resched(),
 	 * reschedule now, before we try-lock the mutex. This avoids getting
@@ -400,14 +533,14 @@ done:
 }
 #else
 static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+				  struct ww_acquire_ctx *ww_ctx,
+				  const bool use_ww_ctx, const bool waiter)
 {
 	return false;
 }
 #endif
 
-__visible __used noinline
-void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip);
 
 /**
  * mutex_unlock - release the mutex
@@ -422,21 +555,12 @@ void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
  */
 void __sched mutex_unlock(struct mutex *lock)
 {
-	/*
-	 * The unlocking fastpath is the 0->1 transition from 'locked'
-	 * into 'unlocked' state:
-	 */
-#ifndef CONFIG_DEBUG_MUTEXES
-	/*
-	 * When debugging is enabled we must not clear the owner before time,
-	 * the slow path will always be taken, and that clears the owner field
-	 * after verifying that it was indeed current.
-	 */
-	mutex_clear_owner(lock);
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+	if (__mutex_unlock_fast(lock))
+		return;
 #endif
-	__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
+	__mutex_unlock_slowpath(lock, _RET_IP_);
 }
-
 EXPORT_SYMBOL(mutex_unlock);
 
 /**
@@ -465,15 +589,7 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 		lock->ctx = NULL;
 	}
 
-#ifndef CONFIG_DEBUG_MUTEXES
-	/*
-	 * When debugging is enabled we must not clear the owner before time,
-	 * the slow path will always be taken, and that clears the owner field
-	 * after verifying that it was indeed current.
-	 */
-	mutex_clear_owner(&lock->base);
-#endif
-	__mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath);
+	mutex_unlock(&lock->base);
 }
 EXPORT_SYMBOL(ww_mutex_unlock);
 
@@ -509,10 +625,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
 	unsigned long flags;
+	bool first = false;
+	struct ww_mutex *ww;
 	int ret;
 
 	if (use_ww_ctx) {
-		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+		ww = container_of(lock, struct ww_mutex, base);
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
 	}
@@ -520,20 +638,21 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
-	if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
+	if (__mutex_trylock(lock, false) ||
+	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) {
 		/* got the lock, yay! */
+		lock_acquired(&lock->dep_map, ip);
+		if (use_ww_ctx)
+			ww_mutex_set_context_fastpath(ww, ww_ctx);
 		preempt_enable();
 		return 0;
 	}
 
 	spin_lock_mutex(&lock->wait_lock, flags);
-
 	/*
-	 * Once more, try to acquire the lock. Only try-lock the mutex if
-	 * it is unlocked to reduce unnecessary xchg() operations.
+	 * After waiting to acquire the wait_lock, try again.
 	 */
-	if (!mutex_is_locked(lock) &&
-	    (atomic_xchg_acquire(&lock->count, 0) == 1))
+	if (__mutex_trylock(lock, false))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -543,26 +662,26 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
+	if (__mutex_waiter_is_first(lock, &waiter))
+		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+
 	lock_contended(&lock->dep_map, ip);
 
+	set_task_state(task, state);
 	for (;;) {
 		/*
-		 * Lets try to take the lock again - this is needed even if
-		 * we get here for the first time (shortly after failing to
-		 * acquire the lock), to make sure that we get a wakeup once
-		 * it's unlocked. Later on, if we sleep, this is the
-		 * operation that gives us the lock. We xchg it to -1, so
-		 * that when we release the lock, we properly wake up the
-		 * other waiters. We only attempt the xchg if the count is
-		 * non-negative in order to avoid unnecessary xchg operations:
+		 * Once we hold wait_lock, we're serialized against
+		 * mutex_unlock() handing the lock off to us, do a trylock
+		 * before testing the error conditions to make sure we pick up
+		 * the handoff.
 		 */
-		if (atomic_read(&lock->count) >= 0 &&
-		    (atomic_xchg_acquire(&lock->count, -1) == 1))
-			break;
+		if (__mutex_trylock(lock, first))
+			goto acquired;
 
 		/*
-		 * got a signal? (This code gets eliminated in the
-		 * TASK_UNINTERRUPTIBLE case.)
+		 * Check for signals and wound conditions while holding
+		 * wait_lock. This ensures the lock cancellation is ordered
+		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
 		if (unlikely(signal_pending_state(state, task))) {
 			ret = -EINTR;
@@ -575,36 +694,49 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 				goto err;
 		}
 
-		__set_task_state(task, state);
-
-		/* didn't get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
 		schedule_preempt_disabled();
+
+		if (!first && __mutex_waiter_is_first(lock, &waiter)) {
+			first = true;
+			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+		}
+
+		set_task_state(task, state);
+		/*
+		 * Here we order against unlock; we must either see it change
+		 * state back to RUNNING and fall through the next schedule(),
+		 * or we must see its unlock and acquire.
+		 */
+		if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) ||
+		     __mutex_trylock(lock, first))
+			break;
+
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
+	spin_lock_mutex(&lock->wait_lock, flags);
+acquired:
 	__set_task_state(task, TASK_RUNNING);
 
 	mutex_remove_waiter(lock, &waiter, task);
-	/* set it to 0 if there are no waiters left: */
 	if (likely(list_empty(&lock->wait_list)))
-		atomic_set(&lock->count, 0);
+		__mutex_clear_flag(lock, MUTEX_FLAGS);
+
 	debug_mutex_free_waiter(&waiter);
 
 skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
-	mutex_set_owner(lock);
 
-	if (use_ww_ctx) {
-		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+	if (use_ww_ctx)
 		ww_mutex_set_context_slowpath(ww, ww_ctx);
-	}
 
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	preempt_enable();
 	return 0;
 
 err:
+	__set_task_state(task, TASK_RUNNING);
 	mutex_remove_waiter(lock, &waiter, task);
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	debug_mutex_free_waiter(&waiter);
@@ -631,7 +763,6 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
 			    0, nest, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
@@ -650,7 +781,6 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
 				   subclass, NULL, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
 static inline int
@@ -715,54 +845,64 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
 /*
  * Release the lock, slowpath:
  */
-static inline void
-__mutex_unlock_common_slowpath(struct mutex *lock, int nested)
+static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 {
-	unsigned long flags;
-	WAKE_Q(wake_q);
+	struct task_struct *next = NULL;
+	unsigned long owner, flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	mutex_release(&lock->dep_map, 1, ip);
 
 	/*
-	 * As a performance measurement, release the lock before doing other
-	 * wakeup related duties to follow. This allows other tasks to acquire
-	 * the lock sooner, while still handling cleanups in past unlock calls.
-	 * This can be done as we do not enforce strict equivalence between the
-	 * mutex counter and wait_list.
-	 *
+	 * Release the lock before (potentially) taking the spinlock such that
+	 * other contenders can get on with things ASAP.
 	 *
-	 * Some architectures leave the lock unlocked in the fastpath failure
-	 * case, others need to leave it locked. In the later case we have to
-	 * unlock it here - as the lock counter is currently 0 or negative.
+	 * Except when HANDOFF, in that case we must not clear the owner field,
+	 * but instead set it to the top waiter.
 	 */
-	if (__mutex_slowpath_needs_to_unlock())
-		atomic_set(&lock->count, 1);
+	owner = atomic_long_read(&lock->owner);
+	for (;;) {
+		unsigned long old;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+#endif
+
+		if (owner & MUTEX_FLAG_HANDOFF)
+			break;
+
+		old = atomic_long_cmpxchg_release(&lock->owner, owner,
+						  __owner_flags(owner));
+		if (old == owner) {
+			if (owner & MUTEX_FLAG_WAITERS)
+				break;
+
+			return;
+		}
+
+		owner = old;
+	}
 
 	spin_lock_mutex(&lock->wait_lock, flags);
-	mutex_release(&lock->dep_map, nested, _RET_IP_);
 	debug_mutex_unlock(lock);
-
 	if (!list_empty(&lock->wait_list)) {
 		/* get the first entry from the wait-list: */
 		struct mutex_waiter *waiter =
-				list_entry(lock->wait_list.next,
-					   struct mutex_waiter, list);
+			list_first_entry(&lock->wait_list,
+					 struct mutex_waiter, list);
+
+		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
-		wake_q_add(&wake_q, waiter->task);
+		wake_q_add(&wake_q, next);
 	}
 
-	spin_unlock_mutex(&lock->wait_lock, flags);
-	wake_up_q(&wake_q);
-}
+	if (owner & MUTEX_FLAG_HANDOFF)
+		__mutex_handoff(lock, next);
 
-/*
- * Release the lock, slowpath:
- */
-__visible void
-__mutex_unlock_slowpath(atomic_t *lock_count)
-{
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
+	spin_unlock_mutex(&lock->wait_lock, flags);
 
-	__mutex_unlock_common_slowpath(lock, 1);
+	wake_up_q(&wake_q);
 }
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
@@ -789,38 +929,30 @@ __mutex_lock_interruptible_slowpath(struct mutex *lock);
  */
 int __sched mutex_lock_interruptible(struct mutex *lock)
 {
-	int ret;
-
 	might_sleep();
-	ret =  __mutex_fastpath_lock_retval(&lock->count);
-	if (likely(!ret)) {
-		mutex_set_owner(lock);
+
+	if (__mutex_trylock_fast(lock))
 		return 0;
-	} else
-		return __mutex_lock_interruptible_slowpath(lock);
+
+	return __mutex_lock_interruptible_slowpath(lock);
 }
 
 EXPORT_SYMBOL(mutex_lock_interruptible);
 
 int __sched mutex_lock_killable(struct mutex *lock)
 {
-	int ret;
-
 	might_sleep();
-	ret = __mutex_fastpath_lock_retval(&lock->count);
-	if (likely(!ret)) {
-		mutex_set_owner(lock);
+
+	if (__mutex_trylock_fast(lock))
 		return 0;
-	} else
-		return __mutex_lock_killable_slowpath(lock);
+
+	return __mutex_lock_killable_slowpath(lock);
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-__visible void __sched
-__mutex_lock_slowpath(atomic_t *lock_count)
+static noinline void __sched
+__mutex_lock_slowpath(struct mutex *lock)
 {
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
 			    NULL, _RET_IP_, NULL, 0);
 }
@@ -856,37 +988,6 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
 
 #endif
 
-/*
- * Spinlock based trylock, we take the spinlock and check whether we
- * can get the lock:
- */
-static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
-{
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-	unsigned long flags;
-	int prev;
-
-	/* No need to trylock if the mutex is locked. */
-	if (mutex_is_locked(lock))
-		return 0;
-
-	spin_lock_mutex(&lock->wait_lock, flags);
-
-	prev = atomic_xchg_acquire(&lock->count, -1);
-	if (likely(prev == 1)) {
-		mutex_set_owner(lock);
-		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-	}
-
-	/* Set it back to 0 if there are no waiters: */
-	if (likely(list_empty(&lock->wait_list)))
-		atomic_set(&lock->count, 0);
-
-	spin_unlock_mutex(&lock->wait_lock, flags);
-
-	return prev == 1;
-}
-
 /**
  * mutex_trylock - try to acquire the mutex, without waiting
  * @lock: the mutex to be acquired
@@ -903,13 +1004,12 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	int ret;
+	bool locked = __mutex_trylock(lock, false);
 
-	ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
-	if (ret)
-		mutex_set_owner(lock);
+	if (locked)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 
-	return ret;
+	return locked;
 }
 EXPORT_SYMBOL(mutex_trylock);
 
@@ -917,36 +1017,28 @@ EXPORT_SYMBOL(mutex_trylock);
 int __sched
 __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	int ret;
-
 	might_sleep();
 
-	ret = __mutex_fastpath_lock_retval(&lock->base.count);
-
-	if (likely(!ret)) {
+	if (__mutex_trylock_fast(&lock->base)) {
 		ww_mutex_set_context_fastpath(lock, ctx);
-		mutex_set_owner(&lock->base);
-	} else
-		ret = __ww_mutex_lock_slowpath(lock, ctx);
-	return ret;
+		return 0;
+	}
+
+	return __ww_mutex_lock_slowpath(lock, ctx);
 }
 EXPORT_SYMBOL(__ww_mutex_lock);
 
 int __sched
 __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	int ret;
-
 	might_sleep();
 
-	ret = __mutex_fastpath_lock_retval(&lock->base.count);
-
-	if (likely(!ret)) {
+	if (__mutex_trylock_fast(&lock->base)) {
 		ww_mutex_set_context_fastpath(lock, ctx);
-		mutex_set_owner(&lock->base);
-	} else
-		ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx);
-	return ret;
+		return 0;
+	}
+
+	return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
 }
 EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
 
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 6cd6b8e9efd7..4410a4af42a3 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -16,32 +16,6 @@
 #define mutex_remove_waiter(lock, waiter, task) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-/*
- * The mutex owner can get read and written to locklessly.
- * We should use WRITE_ONCE when writing the owner value to
- * avoid store tearing, otherwise, a thread could potentially
- * read a partially written and incomplete owner value.
- */
-static inline void mutex_set_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, current);
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, NULL);
-}
-#else
-static inline void mutex_set_owner(struct mutex *lock)
-{
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-}
-#endif
-
 #define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
 #define debug_mutex_free_waiter(waiter)			do { } while (0)
 #define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 05a37857ab55..a3167941093b 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -21,6 +21,11 @@ static inline int encode_cpu(int cpu_nr)
 	return cpu_nr + 1;
 }
 
+static inline int node_cpu(struct optimistic_spin_node *node)
+{
+	return node->cpu - 1;
+}
+
 static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
 {
 	int cpu_nr = encoded_cpu_val - 1;
@@ -75,7 +80,7 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 				break;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
 	return next;
@@ -118,11 +123,13 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	while (!READ_ONCE(node->locked)) {
 		/*
 		 * If we need to reschedule bail... so we can block.
+		 * Use vcpu_is_preempted() to avoid waiting for a preempted
+		 * lock holder:
 		 */
-		if (need_resched())
+		if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
 			goto unqueue;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	return true;
 
@@ -148,7 +155,7 @@ unqueue:
 		if (smp_load_acquire(&node->locked))
 			return true;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 
 		/*
 		 * Or we race against a concurrent unqueue()'s step-B, in which
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 19248ddf37ce..cc3ed0ccdfa2 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -54,7 +54,7 @@ static __always_inline void
 rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
 {
 	while ((cnts & _QW_WMASK) == _QW_LOCKED) {
-		cpu_relax_lowlatency();
+		cpu_relax();
 		cnts = atomic_read_acquire(&lock->cnts);
 	}
 }
@@ -130,7 +130,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 		   (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
 	/* When no more readers, set the locked flag */
@@ -141,7 +141,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 					    _QW_LOCKED) == _QW_WAITING))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 unlock:
 	arch_spin_unlock(&lock->wait_lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2c49d76f96c3..2f443ed2320a 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1446,7 +1446,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
 				   struct wake_q_head *wqh))
 {
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
 		rt_mutex_deadlock_account_unlock(current);
@@ -1619,11 +1619,15 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init);
  * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
  *				proxy owner
  *
- * @lock: 	the rt_mutex to be locked
+ * @lock:	the rt_mutex to be locked
  * @proxy_owner:the task to set as owner
  *
  * No locking. Caller has to do serializing itself
- * Special API call for PI-futex support
+ *
+ * Special API call for PI-futex support. This initializes the rtmutex and
+ * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
+ * possible at this point because the pi_state which contains the rtmutex
+ * is not yet visible to other tasks.
  */
 void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				struct task_struct *proxy_owner)
@@ -1637,10 +1641,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 /**
  * rt_mutex_proxy_unlock - release a lock on behalf of owner
  *
- * @lock: 	the rt_mutex to be locked
+ * @lock:	the rt_mutex to be locked
  *
  * No locking. Caller has to do serializing itself
- * Special API call for PI-futex support
+ *
+ * Special API call for PI-futex support. This merrily cleans up the rtmutex
+ * (debugging) state. Concurrent operations on this rt_mutex are not
+ * possible because it belongs to the pi_state which is about to be freed
+ * and it is not longer visible to other tasks.
  */
 void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 			   struct task_struct *proxy_owner)
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index e317e1cbb3eb..990134617b4c 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -71,13 +71,12 @@ task_top_pi_waiter(struct task_struct *p)
  * lock->owner state tracking:
  */
 #define RT_MUTEX_HAS_WAITERS	1UL
-#define RT_MUTEX_OWNER_MASKALL	1UL
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
 	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
 
-	return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL);
+	return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2337b4bb2366..631506004f9e 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -225,7 +225,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk = current;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	waiter.task = tsk;
 	waiter.type = RWSEM_WAITING_FOR_READ;
@@ -336,7 +336,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		goto done;
 	}
 
-	ret = owner->on_cpu;
+	/*
+	 * 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;
@@ -362,13 +366,17 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 */
 		barrier();
 
-		/* abort spinning when need_resched or owner is not running */
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * 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))) {
 			rcu_read_unlock();
 			return false;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	rcu_read_unlock();
 out:
@@ -423,7 +431,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	osq_unlock(&sem->osq);
 done:
@@ -461,7 +469,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	bool waiting = true; /* any queued threads before us */
 	struct rwsem_waiter waiter;
 	struct rw_semaphore *ret = sem;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	/* undo write bias from down_write operation, stop active locking */
 	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
@@ -495,7 +503,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 		 * wake any read locks that were queued ahead of us.
 		 */
 		if (count > RWSEM_WAITING_BIAS) {
-			WAKE_Q(wake_q);
+			DEFINE_WAKE_Q(wake_q);
 
 			__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
 			/*
@@ -571,7 +579,7 @@ __visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	/*
 	 * If a spinner is present, it is not necessary to do the wakeup.
@@ -625,7 +633,7 @@ __visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 154fd689fe02..8b08fb257856 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -75,11 +75,11 @@
 #include <linux/compiler.h>
 #include <linux/frame.h>
 #include <linux/prefetch.h>
+#include <linux/mutex.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
-#include <asm/mutex.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index ec9ab2f01489..1eb82661ecdb 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -194,7 +194,7 @@ static int multi_cpu_stop(void *data)
 	/* Simple state machine */
 	do {
 		/* Chill out and ensure we re-read multi_stop_state. */
-		cpu_relax();
+		cpu_relax_yield();
 		if (msdata->state != curstate) {
 			curstate = msdata->state;
 			switch (curstate) {