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

Pull core locking updates from Ingo Molnar:
 "The biggest change is the MCS spinlock generalization changes from Tim
  Chen, Peter Zijlstra, Jason Low et al.  There's also lockdep
  fixes/enhancements from Oleg Nesterov, in particular a false negative
  fix related to lockdep_set_novalidate_class() usage"

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  locking/mutex: Fix debug checks
  locking/mutexes: Add extra reschedule point
  locking/mutexes: Introduce cancelable MCS lock for adaptive spinning
  locking/mutexes: Unlock the mutex without the wait_lock
  locking/mutexes: Modify the way optimistic spinners are queued
  locking/mutexes: Return false if task need_resched() in mutex_can_spin_on_owner()
  locking: Move mcs_spinlock.h into kernel/locking/
  m68k: Skip futex_atomic_cmpxchg_inatomic() test
  futex: Allow architectures to skip futex_atomic_cmpxchg_inatomic() test
  Revert "sched/wait: Suppress Sparse 'variable shadowing' warning"
  lockdep: Change lockdep_set_novalidate_class() to use _and_name
  lockdep: Change mark_held_locks() to check hlock->check instead of lockdep_no_validate
  lockdep: Don't create the wrong dependency on hlock->check == 0
  lockdep: Make held_lock->check and "int check" argument bool
  locking/mcs: Allow architecture specific asm files to be used for contended case
  locking/mcs: Order the header files in Kbuild of each architecture in alphabetical order
  sched/wait: Suppress Sparse 'variable shadowing' warning
  hung_task/Documentation: Fix hung_task_warnings description
  locking/mcs: Allow architectures to hook in to contended paths
  locking/mcs: Micro-optimize the MCS code, add extra comments
  ...

7 files changed, 377 insertions, 86 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 08ec814ad9d2..67dacaf93e56 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -157,7 +157,9 @@
  * enqueue.
  */
 
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 int __read_mostly futex_cmpxchg_enabled;
+#endif
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -2875,9 +2877,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
 {
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 	u32 curval;
+
+	/*
+	 * This will fail and we want it. Some arch implementations do
+	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
+	 * functionality. We want to know that before we call in any
+	 * of the complex code paths. Also we want to prevent
+	 * registration of robust lists in that case. NULL is
+	 * guaranteed to fault and we get -EFAULT on functional
+	 * implementation, the non-functional ones will return
+	 * -ENOSYS.
+	 */
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+		futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
 	unsigned int futex_shift;
 	unsigned long i;
 
@@ -2893,18 +2914,8 @@ static int __init futex_init(void)
 					       &futex_shift, NULL,
 					       futex_hashsize, futex_hashsize);
 	futex_hashsize = 1UL << futex_shift;
-	/*
-	 * This will fail and we want it. Some arch implementations do
-	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
-	 * functionality. We want to know that before we call in any
-	 * of the complex code paths. Also we want to prevent
-	 * registration of robust lists in that case. NULL is
-	 * guaranteed to fault and we get -EFAULT on functional
-	 * implementation, the non-functional ones will return
-	 * -ENOSYS.
-	 */
-	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
-		futex_cmpxchg_enabled = 1;
+
+	futex_detect_cmpxchg();
 
 	for (i = 0; i < futex_hashsize; i++) {
 		atomic_set(&futex_queues[i].waiters, 0);
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index baab8e5e7f66..2a9ee96ecf00 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
 
-obj-y += mutex.o semaphore.o rwsem.o lglock.o
+obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = -pg
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index eb8a54783fa0..bf0c6b0dd9c5 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1936,12 +1936,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 
 	for (;;) {
 		int distance = curr->lockdep_depth - depth + 1;
-		hlock = curr->held_locks + depth-1;
+		hlock = curr->held_locks + depth - 1;
 		/*
 		 * Only non-recursive-read entries get new dependencies
 		 * added:
 		 */
-		if (hlock->read != 2) {
+		if (hlock->read != 2 && hlock->check) {
 			if (!check_prev_add(curr, hlock, next,
 						distance, trylock_loop))
 				return 0;
@@ -2098,7 +2098,7 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
 	 * (If lookup_chain_cache() returns with 1 it acquires
 	 * graph_lock for us)
 	 */
-	if (!hlock->trylock && (hlock->check == 2) &&
+	if (!hlock->trylock && hlock->check &&
 	    lookup_chain_cache(curr, hlock, chain_key)) {
 		/*
 		 * Check whether last held lock:
@@ -2517,7 +2517,7 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark)
 
 		BUG_ON(usage_bit >= LOCK_USAGE_STATES);
 
-		if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys)
+		if (!hlock->check)
 			continue;
 
 		if (!mark_lock(curr, hlock, usage_bit))
@@ -3055,9 +3055,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	int class_idx;
 	u64 chain_key;
 
-	if (!prove_locking)
-		check = 1;
-
 	if (unlikely(!debug_locks))
 		return 0;
 
@@ -3069,8 +3066,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return 0;
 
-	if (lock->key == &__lockdep_no_validate__)
-		check = 1;
+	if (!prove_locking || lock->key == &__lockdep_no_validate__)
+		check = 0;
 
 	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
 		class = lock->class_cache[subclass];
@@ -3138,7 +3135,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->holdtime_stamp = lockstat_clock();
 #endif
 
-	if (check == 2 && !mark_irqflags(curr, hlock))
+	if (check && !mark_irqflags(curr, hlock))
 		return 0;
 
 	/* mark it as used: */
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
new file mode 100644
index 000000000000..838dc9e00669
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.c
@@ -0,0 +1,178 @@
+
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_SMP
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ */
+static inline struct optimistic_spin_queue *
+osq_wait_next(struct optimistic_spin_queue **lock,
+	      struct optimistic_spin_queue *node,
+	      struct optimistic_spin_queue *prev)
+{
+	struct optimistic_spin_queue *next = NULL;
+
+	for (;;) {
+		if (*lock == node && cmpxchg(lock, node, prev) == node) {
+			/*
+			 * We were the last queued, we moved @lock back. @prev
+			 * will now observe @lock and will complete its
+			 * unlock()/unqueue().
+			 */
+			break;
+		}
+
+		/*
+		 * We must xchg() the @node->next value, because if we were to
+		 * leave it in, a concurrent unlock()/unqueue() from
+		 * @node->next might complete Step-A and think its @prev is
+		 * still valid.
+		 *
+		 * If the concurrent unlock()/unqueue() wins the race, we'll
+		 * wait for either @lock to point to us, through its Step-B, or
+		 * wait for a new @node->next from its Step-C.
+		 */
+		if (node->next) {
+			next = xchg(&node->next, NULL);
+			if (next)
+				break;
+		}
+
+		arch_mutex_cpu_relax();
+	}
+
+	return next;
+}
+
+bool osq_lock(struct optimistic_spin_queue **lock)
+{
+	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_queue *prev, *next;
+
+	node->locked = 0;
+	node->next = NULL;
+
+	node->prev = prev = xchg(lock, node);
+	if (likely(prev == NULL))
+		return true;
+
+	ACCESS_ONCE(prev->next) = node;
+
+	/*
+	 * Normally @prev is untouchable after the above store; because at that
+	 * moment unlock can proceed and wipe the node element from stack.
+	 *
+	 * However, since our nodes are static per-cpu storage, we're
+	 * guaranteed their existence -- this allows us to apply
+	 * cmpxchg in an attempt to undo our queueing.
+	 */
+
+	while (!smp_load_acquire(&node->locked)) {
+		/*
+		 * If we need to reschedule bail... so we can block.
+		 */
+		if (need_resched())
+			goto unqueue;
+
+		arch_mutex_cpu_relax();
+	}
+	return true;
+
+unqueue:
+	/*
+	 * Step - A  -- stabilize @prev
+	 *
+	 * Undo our @prev->next assignment; this will make @prev's
+	 * unlock()/unqueue() wait for a next pointer since @lock points to us
+	 * (or later).
+	 */
+
+	for (;;) {
+		if (prev->next == node &&
+		    cmpxchg(&prev->next, node, NULL) == node)
+			break;
+
+		/*
+		 * We can only fail the cmpxchg() racing against an unlock(),
+		 * in which case we should observe @node->locked becomming
+		 * true.
+		 */
+		if (smp_load_acquire(&node->locked))
+			return true;
+
+		arch_mutex_cpu_relax();
+
+		/*
+		 * Or we race against a concurrent unqueue()'s step-B, in which
+		 * case its step-C will write us a new @node->prev pointer.
+		 */
+		prev = ACCESS_ONCE(node->prev);
+	}
+
+	/*
+	 * Step - B -- stabilize @next
+	 *
+	 * Similar to unlock(), wait for @node->next or move @lock from @node
+	 * back to @prev.
+	 */
+
+	next = osq_wait_next(lock, node, prev);
+	if (!next)
+		return false;
+
+	/*
+	 * Step - C -- unlink
+	 *
+	 * @prev is stable because its still waiting for a new @prev->next
+	 * pointer, @next is stable because our @node->next pointer is NULL and
+	 * it will wait in Step-A.
+	 */
+
+	ACCESS_ONCE(next->prev) = prev;
+	ACCESS_ONCE(prev->next) = next;
+
+	return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue **lock)
+{
+	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_queue *next;
+
+	/*
+	 * Fast path for the uncontended case.
+	 */
+	if (likely(cmpxchg(lock, node, NULL) == node))
+		return;
+
+	/*
+	 * Second most likely case.
+	 */
+	next = xchg(&node->next, NULL);
+	if (next) {
+		ACCESS_ONCE(next->locked) = 1;
+		return;
+	}
+
+	next = osq_wait_next(lock, node, NULL);
+	if (next)
+		ACCESS_ONCE(next->locked) = 1;
+}
+
+#endif
+
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
new file mode 100644
index 000000000000..a2dbac4aca6b
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.h
@@ -0,0 +1,129 @@
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+#include <asm/mcs_spinlock.h>
+
+struct mcs_spinlock {
+	struct mcs_spinlock *next;
+	int locked; /* 1 if lock acquired */
+};
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_load_acquire() provides a memory barrier that ensures
+ * subsequent operations happen after the lock is acquired.
+ */
+#define arch_mcs_spin_lock_contended(l)					\
+do {									\
+	while (!(smp_load_acquire(l)))					\
+		arch_mutex_cpu_relax();					\
+} while (0)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l)				\
+	smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ *
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+static inline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/*
+		 * Lock acquired, don't need to set node->locked to 1. Threads
+		 * only spin on its own node->locked value for lock acquisition.
+		 * However, since this thread can immediately acquire the lock
+		 * and does not proceed to spin on its own node->locked, this
+		 * value won't be used. If a debug mode is needed to
+		 * audit lock status, then set node->locked value here.
+		 */
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+
+	/* Wait until the lock holder passes the lock down. */
+	arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (likely(cmpxchg(lock, node, NULL) == node))
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	}
+
+	/* Pass lock to next waiter. */
+	arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+/*
+ * Cancellable version of the MCS lock above.
+ *
+ * Intended for adaptive spinning of sleeping locks:
+ * mutex_lock()/rwsem_down_{read,write}() etc.
+ */
+
+struct optimistic_spin_queue {
+	struct optimistic_spin_queue *next, *prev;
+	int locked; /* 1 if lock acquired */
+};
+
+extern bool osq_lock(struct optimistic_spin_queue **lock);
+extern void osq_unlock(struct optimistic_spin_queue **lock);
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index faf6f5b53e77..e1191c996c59 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -83,6 +83,12 @@ void debug_mutex_unlock(struct mutex *lock)
 
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
+
+	/*
+	 * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
+	 * mutexes so that we can do it here after we've verified state.
+	 */
+	atomic_set(&lock->count, 1);
 }
 
 void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 4dd6e4c219de..14fe72cc8ce7 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/debug_locks.h>
+#include "mcs_spinlock.h"
 
 /*
  * In the DEBUG case we are using the "NULL fastpath" for mutexes,
@@ -33,6 +34,13 @@
 #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>
@@ -52,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	lock->spin_mlock = NULL;
+	lock->osq = NULL;
 #endif
 
 	debug_mutex_init(lock, name, key);
@@ -111,54 +119,7 @@ EXPORT_SYMBOL(mutex_lock);
  * more or less simultaneously, the spinners need to acquire a MCS lock
  * first before spinning on the owner field.
  *
- * We don't inline mspin_lock() so that perf can correctly account for the
- * time spent in this lock function.
  */
-struct mspin_node {
-	struct mspin_node *next ;
-	int		  locked;	/* 1 if lock acquired */
-};
-#define	MLOCK(mutex)	((struct mspin_node **)&((mutex)->spin_mlock))
-
-static noinline
-void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
-{
-	struct mspin_node *prev;
-
-	/* Init node */
-	node->locked = 0;
-	node->next   = NULL;
-
-	prev = xchg(lock, node);
-	if (likely(prev == NULL)) {
-		/* Lock acquired */
-		node->locked = 1;
-		return;
-	}
-	ACCESS_ONCE(prev->next) = node;
-	smp_wmb();
-	/* Wait until the lock holder passes the lock down */
-	while (!ACCESS_ONCE(node->locked))
-		arch_mutex_cpu_relax();
-}
-
-static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
-{
-	struct mspin_node *next = ACCESS_ONCE(node->next);
-
-	if (likely(!next)) {
-		/*
-		 * Release the lock by setting it to NULL
-		 */
-		if (cmpxchg(lock, node, NULL) == node)
-			return;
-		/* Wait until the next pointer is set */
-		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
-	}
-	ACCESS_ONCE(next->locked) = 1;
-	smp_wmb();
-}
 
 /*
  * Mutex spinning code migrated from kernel/sched/core.c
@@ -212,6 +173,9 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 	struct task_struct *owner;
 	int retval = 1;
 
+	if (need_resched())
+		return 0;
+
 	rcu_read_lock();
 	owner = ACCESS_ONCE(lock->owner);
 	if (owner)
@@ -446,9 +410,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	if (!mutex_can_spin_on_owner(lock))
 		goto slowpath;
 
+	if (!osq_lock(&lock->osq))
+		goto slowpath;
+
 	for (;;) {
 		struct task_struct *owner;
-		struct mspin_node  node;
 
 		if (use_ww_ctx && ww_ctx->acquired > 0) {
 			struct ww_mutex *ww;
@@ -463,19 +429,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			 * performed the optimistic spinning cannot be done.
 			 */
 			if (ACCESS_ONCE(ww->ctx))
-				goto slowpath;
+				break;
 		}
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		mspin_lock(MLOCK(lock), &node);
 		owner = ACCESS_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner)) {
-			mspin_unlock(MLOCK(lock), &node);
-			goto slowpath;
-		}
+		if (owner && !mutex_spin_on_owner(lock, owner))
+			break;
 
 		if ((atomic_read(&lock->count) == 1) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
@@ -488,11 +451,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			}
 
 			mutex_set_owner(lock);
-			mspin_unlock(MLOCK(lock), &node);
+			osq_unlock(&lock->osq);
 			preempt_enable();
 			return 0;
 		}
-		mspin_unlock(MLOCK(lock), &node);
 
 		/*
 		 * When there's no owner, we might have preempted between the
@@ -501,7 +463,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * the owner complete.
 		 */
 		if (!owner && (need_resched() || rt_task(task)))
-			goto slowpath;
+			break;
 
 		/*
 		 * The cpu_relax() call is a compiler barrier which forces
@@ -511,7 +473,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 */
 		arch_mutex_cpu_relax();
 	}
+	osq_unlock(&lock->osq);
 slowpath:
+	/*
+	 * If we fell out of the spin path because of need_resched(),
+	 * reschedule now, before we try-lock the mutex. This avoids getting
+	 * scheduled out right after we obtained the mutex.
+	 */
+	if (need_resched())
+		schedule_preempt_disabled();
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
@@ -717,10 +687,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
 	unsigned long flags;
 
-	spin_lock_mutex(&lock->wait_lock, flags);
-	mutex_release(&lock->dep_map, nested, _RET_IP_);
-	debug_mutex_unlock(lock);
-
 	/*
 	 * some architectures leave the lock unlocked in the fastpath failure
 	 * case, others need to leave it locked. In the later case we have to
@@ -729,6 +695,10 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 	if (__mutex_slowpath_needs_to_unlock())
 		atomic_set(&lock->count, 1);
 
+	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 =