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 main changes in this cycle were:

   - Implement wraparound-safe refcount_t and kref_t types based on
     generic atomic primitives (Peter Zijlstra)

   - Improve and fix the ww_mutex code (Nicolai Hähnle)

   - Add self-tests to the ww_mutex code (Chris Wilson)

   - Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr
     Bueso)

   - Micro-optimize the current-task logic all around the core kernel
     (Davidlohr Bueso)

   - Tidy up after recent optimizations: remove stale code and APIs,
     clean up the code (Waiman Long)

   - ... plus misc fixes, updates and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  fork: Fix task_struct alignment
  locking/spinlock/debug: Remove spinlock lockup detection code
  lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS
  lkdtm: Convert to refcount_t testing
  kref: Implement 'struct kref' using refcount_t
  refcount_t: Introduce a special purpose refcount type
  sched/wake_q: Clarify queue reinit comment
  sched/wait, rcuwait: Fix typo in comment
  locking/mutex: Fix lockdep_assert_held() fail
  locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock()
  locking/rwsem: Reinit wake_q after use
  locking/rwsem: Remove unnecessary atomic_long_t casts
  jump_labels: Move header guard #endif down where it belongs
  locking/atomic, kref: Implement kref_put_lock()
  locking/ww_mutex: Turn off __must_check for now
  locking/atomic, kref: Avoid more abuse
  locking/atomic, kref: Use kref_get_unless_zero() more
  locking/atomic, kref: Kill kref_sub()
  locking/atomic, kref: Add kref_read()
  locking/atomic, kref: Add KREF_INIT()
  ...

13 files changed, 417 insertions, 118 deletions

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a0547c571800..b63d6b7b0db0 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -402,6 +402,6 @@ extern bool ____wrong_branch_error(void);
 #define static_branch_enable(x)		static_key_enable(&(x)->key)
 #define static_branch_disable(x)	static_key_disable(&(x)->key)
 
-#endif	/* _LINUX_JUMP_LABEL_H */
-
 #endif /* __ASSEMBLY__ */
+
+#endif	/* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/kref.h b/include/linux/kref.h
index e15828fd71f1..f4156f88f557 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -15,22 +15,27 @@
 #ifndef _KREF_H_
 #define _KREF_H_
 
-#include <linux/bug.h>
-#include <linux/atomic.h>
-#include <linux/kernel.h>
-#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
 
 struct kref {
-	atomic_t refcount;
+	refcount_t refcount;
 };
 
+#define KREF_INIT(n)	{ .refcount = REFCOUNT_INIT(n), }
+
 /**
  * kref_init - initialize object.
  * @kref: object in question.
  */
 static inline void kref_init(struct kref *kref)
 {
-	atomic_set(&kref->refcount, 1);
+	refcount_set(&kref->refcount, 1);
+}
+
+static inline unsigned int kref_read(const struct kref *kref)
+{
+	return refcount_read(&kref->refcount);
 }
 
 /**
@@ -39,17 +44,12 @@ static inline void kref_init(struct kref *kref)
  */
 static inline void kref_get(struct kref *kref)
 {
-	/* If refcount was 0 before incrementing then we have a race
-	 * condition when this kref is freeing by some other thread right now.
-	 * In this case one should use kref_get_unless_zero()
-	 */
-	WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2);
+	refcount_inc(&kref->refcount);
 }
 
 /**
- * kref_sub - subtract a number of refcounts for object.
+ * kref_put - decrement refcount for object.
  * @kref: object.
- * @count: Number of recounts to subtract.
  * @release: pointer to the function that will clean up the object when the
  *	     last reference to the object is released.
  *	     This pointer is required, and it is not acceptable to pass kfree
@@ -58,57 +58,43 @@ static inline void kref_get(struct kref *kref)
  *	     maintainer, and anyone else who happens to notice it.  You have
  *	     been warned.
  *
- * Subtract @count from the refcount, and if 0, call release().
+ * Decrement the refcount, and if 0, call release().
  * Return 1 if the object was removed, otherwise return 0.  Beware, if this
  * function returns 0, you still can not count on the kref from remaining in
  * memory.  Only use the return value if you want to see if the kref is now
  * gone, not present.
  */
-static inline int kref_sub(struct kref *kref, unsigned int count,
-	     void (*release)(struct kref *kref))
+static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
 {
 	WARN_ON(release == NULL);
 
-	if (atomic_sub_and_test((int) count, &kref->refcount)) {
+	if (refcount_dec_and_test(&kref->refcount)) {
 		release(kref);
 		return 1;
 	}
 	return 0;
 }
 
-/**
- * kref_put - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.  If the caller does pass kfree to this
- *	     function, you will be publicly mocked mercilessly by the kref
- *	     maintainer, and anyone else who happens to notice it.  You have
- *	     been warned.
- *
- * Decrement the refcount, and if 0, call release().
- * Return 1 if the object was removed, otherwise return 0.  Beware, if this
- * function returns 0, you still can not count on the kref from remaining in
- * memory.  Only use the return value if you want to see if the kref is now
- * gone, not present.
- */
-static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
-{
-	return kref_sub(kref, 1, release);
-}
-
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
 {
 	WARN_ON(release == NULL);
-	if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) {
-		mutex_lock(lock);
-		if (unlikely(!atomic_dec_and_test(&kref->refcount))) {
-			mutex_unlock(lock);
-			return 0;
-		}
+
+	if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) {
+		release(kref);
+		return 1;
+	}
+	return 0;
+}
+
+static inline int kref_put_lock(struct kref *kref,
+				void (*release)(struct kref *kref),
+				spinlock_t *lock)
+{
+	WARN_ON(release == NULL);
+
+	if (refcount_dec_and_lock(&kref->refcount, lock)) {
 		release(kref);
 		return 1;
 	}
@@ -133,6 +119,6 @@ static inline int kref_put_mutex(struct kref *kref,
  */
 static inline int __must_check kref_get_unless_zero(struct kref *kref)
 {
-	return atomic_add_unless(&kref->refcount, 1, 0);
+	return refcount_inc_not_zero(&kref->refcount);
 }
 #endif /* _KREF_H_ */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 7fffbfcd5430..1127fe31645d 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -20,6 +20,8 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 
+struct ww_acquire_ctx;
+
 /*
  * Simple, straightforward mutexes with strict semantics:
  *
@@ -65,7 +67,7 @@ struct mutex {
 
 static inline struct task_struct *__mutex_owner(struct mutex *lock)
 {
-	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03);
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x07);
 }
 
 /*
@@ -75,6 +77,7 @@ static inline struct task_struct *__mutex_owner(struct mutex *lock)
 struct mutex_waiter {
 	struct list_head	list;
 	struct task_struct	*task;
+	struct ww_acquire_ctx	*ww_ctx;
 #ifdef CONFIG_DEBUG_MUTEXES
 	void			*magic;
 #endif
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 5b2e6159b744..93664f022ecf 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -4,15 +4,15 @@
 #include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
-#include <linux/wait.h>
+#include <linux/rcuwait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
 
 struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
 	unsigned int __percpu	*read_count;
-	struct rw_semaphore	rw_sem;
-	wait_queue_head_t	writer;
+	struct rw_semaphore	rw_sem; /* slowpath */
+	struct rcuwait          writer; /* blocked writer */
 	int			readers_block;
 };
 
@@ -22,7 +22,7 @@ static struct percpu_rw_semaphore name = {				\
 	.rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC),	\
 	.read_count = &__percpu_rwsem_rc_##name,			\
 	.rw_sem = __RWSEM_INITIALIZER(name.rw_sem),			\
-	.writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer),		\
+	.writer = __RCUWAIT_INITIALIZER(name.writer),			\
 }
 
 extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 51334edec506..a39540326417 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -80,6 +80,7 @@
 /********** kernel/mutexes **********/
 #define MUTEX_DEBUG_INIT	0x11
 #define MUTEX_DEBUG_FREE	0x22
+#define MUTEX_POISON_WW_CTX	((void *) 0x500 + POISON_POINTER_DELTA)
 
 /********** lib/flex_array.c **********/
 #define FLEX_ARRAY_FREE	0x6c	/* for use-after-free poisoning */
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
new file mode 100644
index 000000000000..a4ede51b3e7c
--- /dev/null
+++ b/include/linux/rcuwait.h
@@ -0,0 +1,63 @@
+#ifndef _LINUX_RCUWAIT_H_
+#define _LINUX_RCUWAIT_H_
+
+#include <linux/rcupdate.h>
+
+/*
+ * rcuwait provides a way of blocking and waking up a single
+ * task in an rcu-safe manner; where it is forbidden to use
+ * after exit_notify(). task_struct is not properly rcu protected,
+ * unless dealing with rcu-aware lists, ie: find_task_by_*().
+ *
+ * Alternatively we have task_rcu_dereference(), but the return
+ * semantics have different implications which would break the
+ * wakeup side. The only time @task is non-nil is when a user is
+ * blocked (or checking if it needs to) on a condition, and reset
+ * as soon as we know that the condition has succeeded and are
+ * awoken.
+ */
+struct rcuwait {
+	struct task_struct *task;
+};
+
+#define __RCUWAIT_INITIALIZER(name)		\
+	{ .task = NULL, }
+
+static inline void rcuwait_init(struct rcuwait *w)
+{
+	w->task = NULL;
+}
+
+extern void rcuwait_wake_up(struct rcuwait *w);
+
+/*
+ * The caller is responsible for locking around rcuwait_wait_event(),
+ * such that writes to @task are properly serialized.
+ */
+#define rcuwait_wait_event(w, condition)				\
+({									\
+	/*								\
+	 * Complain if we are called after do_exit()/exit_notify(),     \
+	 * as we cannot rely on the rcu critical region for the		\
+	 * wakeup side.							\
+	 */                                                             \
+	WARN_ON(current->exit_state);                                   \
+									\
+	rcu_assign_pointer((w)->task, current);				\
+	for (;;) {							\
+		/*							\
+		 * Implicit barrier (A) pairs with (B) in		\
+		 * rcuwait_wake_up().					\
+		 */							\
+		set_current_state(TASK_UNINTERRUPTIBLE);		\
+		if (condition)						\
+			break;						\
+									\
+		schedule();						\
+	}								\
+									\
+	WRITE_ONCE((w)->task, NULL);					\
+	__set_current_state(TASK_RUNNING);				\
+})
+
+#endif /* _LINUX_RCUWAIT_H_ */
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
new file mode 100644
index 000000000000..600aadf9cca4
--- /dev/null
+++ b/include/linux/refcount.h
@@ -0,0 +1,294 @@
+#ifndef _LINUX_REFCOUNT_H
+#define _LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_DEBUG_REFCOUNT
+#define REFCOUNT_WARN(cond, str) WARN_ON(cond)
+#define __refcount_check	__must_check
+#else
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#endif
+
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+	atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+	return atomic_read(&r->refs);
+}
+
+static inline __refcount_check
+bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (!val)
+			return false;
+
+		if (unlikely(val == UINT_MAX))
+			return true;
+
+		new = val + i;
+		if (new < val)
+			new = UINT_MAX;
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+static inline void refcount_add(unsigned int i, refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		new = val + 1;
+
+		if (!val)
+			return false;
+
+		if (unlikely(!new))
+			return true;
+
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return false;
+
+		new = val - i;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return false;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+	return refcount_sub_and_test(1, r);
+}
+
+/*
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
+static inline
+void refcount_dec(refcount_t *r)
+{
+	REFCOUNT_WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+}
+
+/*
+ * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the
+ * success thereof.
+ *
+ * Like all decrement operations, it provides release memory order and provides
+ * a control dependency.
+ *
+ * It can be used like a try-delete operator; this explicit case is provided
+ * and not cmpxchg in generic, because that would allow implementing unsafe
+ * operations.
+ */
+static inline __refcount_check
+bool refcount_dec_if_one(refcount_t *r)
+{
+	return atomic_cmpxchg_release(&r->refs, 1, 0) == 1;
+}
+
+/*
+ * No atomic_t counterpart, it decrements unless the value is 1, in which case
+ * it will return false.
+ *
+ * Was often done like: atomic_add_unless(&var, -1, 1)
+ */
+static inline __refcount_check
+bool refcount_dec_not_one(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return true;
+
+		if (val == 1)
+			return false;
+
+		new = val - 1;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return true;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return true;
+}
+
+/*
+ * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail
+ * to decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock)
+{
+	if (refcount_dec_not_one(r))
+		return false;
+
+	mutex_lock(lock);
+	if (!refcount_dec_and_test(r)) {
+		mutex_unlock(lock);
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock)
+{
+	if (refcount_dec_not_one(r))
+		return false;
+
+	spin_lock(lock);
+	if (!refcount_dec_and_test(r)) {
+		spin_unlock(lock);
+		return false;
+	}
+
+	return true;
+}
+
+#endif /* _LINUX_REFCOUNT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c89b7fdec41e..c8e519d0b4a3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -226,7 +226,7 @@ extern void proc_sched_set_task(struct task_struct *p);
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
 
-/* Convenience macros for the sake of set_task_state */
+/* Convenience macros for the sake of set_current_state */
 #define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
@@ -253,17 +253,6 @@ extern char ___assert_task_state[1 - 2*!!(
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
-#define __set_task_state(tsk, state_value)			\
-	do {							\
-		(tsk)->task_state_change = _THIS_IP_;		\
-		(tsk)->state = (state_value);			\
-	} while (0)
-#define set_task_state(tsk, state_value)			\
-	do {							\
-		(tsk)->task_state_change = _THIS_IP_;		\
-		smp_store_mb((tsk)->state, (state_value));	\
-	} while (0)
-
 #define __set_current_state(state_value)			\
 	do {							\
 		current->task_state_change = _THIS_IP_;		\
@@ -276,20 +265,6 @@ extern char ___assert_task_state[1 - 2*!!(
 	} while (0)
 
 #else
-
-/*
- * @tsk had better be current, or you get to keep the pieces.
- *
- * The only reason is that computing current can be more expensive than
- * using a pointer that's already available.
- *
- * Therefore, see set_current_state().
- */
-#define __set_task_state(tsk, state_value)		\
-	do { (tsk)->state = (state_value); } while (0)
-#define set_task_state(tsk, state_value)		\
-	smp_store_mb((tsk)->state, (state_value))
-
 /*
  * set_current_state() includes a barrier so that the write of current->state
  * is correctly serialised wrt the caller's subsequent test of whether to
@@ -1018,8 +993,8 @@ enum cpu_idle_type {
  *
  * The DEFINE_WAKE_Q macro declares and initializes the list head.
  * wake_up_q() does NOT reinitialize the list; it's expected to be
- * called near the end of a function, where the fact that the queue is
- * not used again will be easy to see by inspection.
+ * called near the end of a function. Otherwise, the list can be
+ * re-initialized for later re-use by wake_q_init().
  *
  * Note that this can cause spurious wakeups. schedule() callers
  * must ensure the call is done inside a loop, confirming that the
@@ -1039,6 +1014,12 @@ struct wake_q_head {
 #define DEFINE_WAKE_Q(name)				\
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
+static inline void wake_q_init(struct wake_q_head *head)
+{
+	head->first = WAKE_Q_TAIL;
+	head->lastp = &head->first;
+}
+
 extern void wake_q_add(struct wake_q_head *head,
 		       struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 47dd0cebd204..59248dcc6ef3 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -180,8 +180,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define raw_spin_lock_nested(lock, subclass) \
 	_raw_spin_lock_nested(lock, subclass)
-# define raw_spin_lock_bh_nested(lock, subclass) \
-	_raw_spin_lock_bh_nested(lock, subclass)
 
 # define raw_spin_lock_nest_lock(lock, nest_lock)			\
 	 do {								\
@@ -197,7 +195,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # define raw_spin_lock_nested(lock, subclass)		\
 	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
-# define raw_spin_lock_bh_nested(lock, subclass)	_raw_spin_lock_bh(lock)
 #endif
 
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
@@ -317,11 +314,6 @@ do {								\
 	raw_spin_lock_nested(spinlock_check(lock), subclass);	\
 } while (0)
 
-#define spin_lock_bh_nested(lock, subclass)			\
-do {								\
-	raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\
-} while (0)
-
 #define spin_lock_nest_lock(lock, nest_lock)				\
 do {									\
 	raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock);	\
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 5344268e6e62..42dfab89e740 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -22,8 +22,6 @@ int in_lock_functions(unsigned long addr);
 void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)		__acquires(lock);
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 								__acquires(lock);
-void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
-								__acquires(lock);
 void __lockfunc
 _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map)
 								__acquires(lock);
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index d3afef9d8dbe..d0d188861ad6 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -57,7 +57,6 @@
 
 #define _raw_spin_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_nested(lock, subclass)	__LOCK(lock)
-#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock)
 #define _raw_read_lock(lock)			__LOCK(lock)
 #define _raw_write_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_bh(lock)			__LOCK_BH(lock)
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 62a60eeacb0a..8a511c0985aa 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -198,7 +198,7 @@ static inline struct cache_head  *cache_get(struct cache_head *h)
 
 static inline void cache_put(struct cache_head *h, struct cache_detail *cd)
 {
-	if (atomic_read(&h->ref.refcount) <= 2 &&
+	if (kref_read(&h->ref) <= 2 &&
 	    h->expiry_time < cd->nextcheck)
 		cd->nextcheck = h->expiry_time;
 	kref_put(&h->ref, cd->cache_put);
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 7b0066814fa0..5dd9a7682227 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -51,10 +51,10 @@ struct ww_mutex {
 };
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) \
-		, .ww_class = &ww_class
+# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \
+		, .ww_class = class
 #else
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class)
+# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class)
 #endif
 
 #define __WW_CLASS_INITIALIZER(ww_class) \
@@ -63,7 +63,7 @@ struct ww_mutex {
 		, .mutex_name = #ww_class "_mutex" }
 
 #define __WW_MUTEX_INITIALIZER(lockname, class) \
-		{ .base = { \__MUTEX_INITIALIZER(lockname) } \
+		{ .base =  __MUTEX_INITIALIZER(lockname.base) \
 		__WW_CLASS_MUTEX_INITIALIZER(lockname, class) }
 
 #define DEFINE_WW_CLASS(classname) \
@@ -186,11 +186,6 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
 #endif
 }
 
-extern int __must_check __ww_mutex_lock(struct ww_mutex *lock,
-					struct ww_acquire_ctx *ctx);
-extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock,
-						      struct ww_acquire_ctx *ctx);
-
 /**
  * ww_mutex_lock - acquire the w/w mutex
  * @lock: the mutex to be acquired
@@ -220,14 +215,7 @@ extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock,
  *
  * A mutex acquired with this function must be released with ww_mutex_unlock.
  */
-static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
-{
-	if (ctx)
-		return __ww_mutex_lock(lock, ctx);
-
-	mutex_lock(&lock->base);
-	return 0;
-}
+extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx);
 
 /**
  * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible
@@ -259,14 +247,8 @@ static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ct
  *
  * A mutex acquired with this function must be released with ww_mutex_unlock.
  */
-static inline int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock,
-							   struct ww_acquire_ctx *ctx)
-{
-	if (ctx)
-		return __ww_mutex_lock_interruptible(lock, ctx);
-	else
-		return mutex_lock_interruptible(&lock->base);
-}
+extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock,
+						    struct ww_acquire_ctx *ctx);
 
 /**
  * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex