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
  ...

9 files changed, 82 insertions, 279 deletions

diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
deleted file mode 100644
index c54829d3de37..000000000000
--- a/include/asm-generic/mutex-dec.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * include/asm-generic/mutex-dec.h
- *
- * Generic implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- */
-#ifndef _ASM_GENERIC_MUTEX_DEC_H
-#define _ASM_GENERIC_MUTEX_DEC_H
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function MUST leave the value lower than
- * 1 even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return_acquire(count) < 0))
-		fail_fn(count);
-}
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count)
-{
-	if (unlikely(atomic_dec_return_acquire(count) < 0))
-		return -1;
-	return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 0
- *
- * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
- * In the failure case, this function is allowed to either set the value to
- * 1, or to set it to a value lower than 1.
- *
- * If the implementation sets it to a value of lower than 1, then the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_inc_return_release(count) <= 0))
-		fail_fn(count);
-}
-
-#define __mutex_slowpath_needs_to_unlock()		1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1))
-		return 1;
-	return 0;
-}
-
-#endif
diff --git a/include/asm-generic/mutex-null.h b/include/asm-generic/mutex-null.h
deleted file mode 100644
index 61069ed334e2..000000000000
--- a/include/asm-generic/mutex-null.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * include/asm-generic/mutex-null.h
- *
- * Generic implementation of the mutex fastpath, based on NOP :-)
- *
- * This is used by the mutex-debugging infrastructure, but it can also
- * be used by architectures that (for whatever reason) want to use the
- * spinlock based slowpath.
- */
-#ifndef _ASM_GENERIC_MUTEX_NULL_H
-#define _ASM_GENERIC_MUTEX_NULL_H
-
-#define __mutex_fastpath_lock(count, fail_fn)		fail_fn(count)
-#define __mutex_fastpath_lock_retval(count)		(-1)
-#define __mutex_fastpath_unlock(count, fail_fn)		fail_fn(count)
-#define __mutex_fastpath_trylock(count, fail_fn)	fail_fn(count)
-#define __mutex_slowpath_needs_to_unlock()		1
-
-#endif
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
deleted file mode 100644
index 3269ec4e195f..000000000000
--- a/include/asm-generic/mutex-xchg.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * include/asm-generic/mutex-xchg.h
- *
- * Generic implementation of the mutex fastpath, based on xchg().
- *
- * NOTE: An xchg based implementation might be less optimal than an atomic
- *       decrement/increment based implementation. If your architecture
- *       has a reasonable atomic dec/inc then you should probably use
- *	 asm-generic/mutex-dec.h instead, or you could open-code an
- *	 optimized version in asm/mutex.h.
- */
-#ifndef _ASM_GENERIC_MUTEX_XCHG_H
-#define _ASM_GENERIC_MUTEX_XCHG_H
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_xchg(count, 0) != 1))
-		/*
-		 * We failed to acquire the lock, so mark it contended
-		 * to ensure that any waiting tasks are woken up by the
-		 * unlock slow path.
-		 */
-		if (likely(atomic_xchg_acquire(count, -1) != 1))
-			fail_fn(count);
-}
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count)
-{
-	if (unlikely(atomic_xchg_acquire(count, 0) != 1))
-		if (likely(atomic_xchg(count, -1) != 1))
-			return -1;
-	return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 0
- *
- * try to promote the mutex from 0 to 1. if it wasn't 0, call <function>
- * In the failure case, this function is allowed to either set the value to
- * 1, or to set it to a value lower than one.
- * If the implementation sets it to a value of lower than one, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_xchg_release(count, 1) != 0))
-		fail_fn(count);
-}
-
-#define __mutex_slowpath_needs_to_unlock()		0
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: spinlock based trylock implementation
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int prev;
-
-	if (atomic_read(count) != 1)
-		return 0;
-
-	prev = atomic_xchg_acquire(count, 0);
-	if (unlikely(prev < 0)) {
-		/*
-		 * The lock was marked contended so we must restore that
-		 * state. If while doing so we get back a prev value of 1
-		 * then we just own it.
-		 *
-		 * [ In the rare case of the mutex going to 1, to 0, to -1
-		 *   and then back to 0 in this few-instructions window,
-		 *   this has the potential to trigger the slowpath for the
-		 *   owner's unlock path needlessly, but that's not a problem
-		 *   in practice. ]
-		 */
-		prev = atomic_xchg_acquire(count, prev);
-		if (prev < 0)
-			prev = 0;
-	}
-
-	return prev;
-}
-
-#endif
diff --git a/include/asm-generic/mutex.h b/include/asm-generic/mutex.h
deleted file mode 100644
index fe91ab502793..000000000000
--- a/include/asm-generic/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_GENERIC_MUTEX_H
-#define __ASM_GENERIC_MUTEX_H
-/*
- * Pull in the generic implementation for the mutex fastpath,
- * which is a reasonable default on many architectures.
- */
-
-#include <asm-generic/mutex-dec.h>
-#endif /* __ASM_GENERIC_MUTEX_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 01c0b9cc3915..6f0023797b33 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -645,6 +645,8 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 		    unsigned long len);
 int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			   void *data, unsigned long len);
+int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, int offset, unsigned long len);
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
diff --git a/include/linux/mutex-debug.h b/include/linux/mutex-debug.h
deleted file mode 100644
index 4ac8b1977b73..000000000000
--- a/include/linux/mutex-debug.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef __LINUX_MUTEX_DEBUG_H
-#define __LINUX_MUTEX_DEBUG_H
-
-#include <linux/linkage.h>
-#include <linux/lockdep.h>
-#include <linux/debug_locks.h>
-
-/*
- * Mutexes - debugging helpers:
- */
-
-#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
-	, .magic = &lockname
-
-#define mutex_init(mutex)						\
-do {									\
-	static struct lock_class_key __key;				\
-									\
-	__mutex_init((mutex), #mutex, &__key);				\
-} while (0)
-
-extern void mutex_destroy(struct mutex *lock);
-
-#endif
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 2cb7531e7d7a..b97870f2debd 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -18,6 +18,7 @@
 #include <linux/atomic.h>
 #include <asm/processor.h>
 #include <linux/osq_lock.h>
+#include <linux/debug_locks.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -48,16 +49,12 @@
  *   locks and tasks (and only those tasks)
  */
 struct mutex {
-	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
-	atomic_t		count;
+	atomic_long_t		owner;
 	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
-	struct task_struct	*owner;
-#endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
+	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_MUTEXES
 	void			*magic;
 #endif
@@ -66,6 +63,11 @@ struct mutex {
 #endif
 };
 
+static inline struct task_struct *__mutex_owner(struct mutex *lock)
+{
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03);
+}
+
 /*
  * This is the control structure for tasks blocked on mutex,
  * which resides on the blocked task's kernel stack:
@@ -79,9 +81,20 @@ struct mutex_waiter {
 };
 
 #ifdef CONFIG_DEBUG_MUTEXES
-# include <linux/mutex-debug.h>
+
+#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
+	, .magic = &lockname
+
+extern void mutex_destroy(struct mutex *lock);
+
 #else
+
 # define __DEBUG_MUTEX_INITIALIZER(lockname)
+
+static inline void mutex_destroy(struct mutex *lock) {}
+
+#endif
+
 /**
  * mutex_init - initialize the mutex
  * @mutex: the mutex to be initialized
@@ -90,14 +103,12 @@ struct mutex_waiter {
  *
  * It is not allowed to initialize an already locked mutex.
  */
-# define mutex_init(mutex) \
-do {							\
-	static struct lock_class_key __key;		\
-							\
-	__mutex_init((mutex), #mutex, &__key);		\
+#define mutex_init(mutex)						\
+do {									\
+	static struct lock_class_key __key;				\
+									\
+	__mutex_init((mutex), #mutex, &__key);				\
 } while (0)
-static inline void mutex_destroy(struct mutex *lock) {}
-#endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
@@ -107,7 +118,7 @@ static inline void mutex_destroy(struct mutex *lock) {}
 #endif
 
 #define __MUTEX_INITIALIZER(lockname) \
-		{ .count = ATOMIC_INIT(1) \
+		{ .owner = ATOMIC_LONG_INIT(0) \
 		, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
 		, .wait_list = LIST_HEAD_INIT(lockname.wait_list) \
 		__DEBUG_MUTEX_INITIALIZER(lockname) \
@@ -127,7 +138,10 @@ extern void __mutex_init(struct mutex *lock, const char *name,
  */
 static inline int mutex_is_locked(struct mutex *lock)
 {
-	return atomic_read(&lock->count) != 1;
+	/*
+	 * XXX think about spin_is_locked
+	 */
+	return __mutex_owner(lock) != NULL;
 }
 
 /*
@@ -175,4 +189,35 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
+/*
+ * These values are chosen such that FAIL and SUCCESS match the
+ * values of the regular mutex_trylock().
+ */
+enum mutex_trylock_recursive_enum {
+	MUTEX_TRYLOCK_FAILED    = 0,
+	MUTEX_TRYLOCK_SUCCESS   = 1,
+	MUTEX_TRYLOCK_RECURSIVE,
+};
+
+/**
+ * mutex_trylock_recursive - trylock variant that allows recursive locking
+ * @lock: mutex to be locked
+ *
+ * This function should not be used, _ever_. It is purely for hysterical GEM
+ * raisins, and once those are gone this will be removed.
+ *
+ * Returns:
+ *  MUTEX_TRYLOCK_FAILED    - trylock failed,
+ *  MUTEX_TRYLOCK_SUCCESS   - lock acquired,
+ *  MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
+ */
+static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
+mutex_trylock_recursive(struct mutex *lock)
+{
+	if (unlikely(__mutex_owner(lock) == current))
+		return MUTEX_TRYLOCK_RECURSIVE;
+
+	return mutex_trylock(lock);
+}
+
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e9c009dc3a4a..8863bdf582d5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -989,7 +989,7 @@ enum cpu_idle_type {
  * already in a wake queue, the wakeup will happen soon and the second
  * waker can just skip it.
  *
- * The WAKE_Q macro declares and initializes the list head.
+ * 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.
@@ -1009,7 +1009,7 @@ struct wake_q_head {
 
 #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
 
-#define WAKE_Q(name)					\
+#define DEFINE_WAKE_Q(name)				\
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
 extern void wake_q_add(struct wake_q_head *head,
@@ -2444,6 +2444,10 @@ static inline void calc_load_enter_idle(void) { }
 static inline void calc_load_exit_idle(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
+#ifndef cpu_relax_yield
+#define cpu_relax_yield() cpu_relax()
+#endif
+
 /*
  * Do not use outside of architecture code which knows its limitations.
  *
@@ -3508,6 +3512,18 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #endif /* CONFIG_SMP */
 
+/*
+ * In order to reduce various lock holder preemption latencies provide an
+ * interface to see if a vCPU is currently running or not.
+ *
+ * This allows us to terminate optimistic spin loops and block, analogous to
+ * the native optimistic spin heuristic of testing if the lock owner task is
+ * running or not.
+ */
+#ifndef vcpu_is_preempted
+# define vcpu_is_preempted(cpu)	false
+#endif
+
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 2bb5deb0012e..7b0066814fa0 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -120,7 +120,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 				   struct ww_class *ww_class)
 {
 	ctx->task = current;
-	ctx->stamp = atomic_long_inc_return(&ww_class->stamp);
+	ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp);
 	ctx->acquired = 0;
 #ifdef CONFIG_DEBUG_MUTEXES
 	ctx->ww_class = ww_class;