[PATCH -v3 00/10] locking/mutex: Rewrite basic mutex

[PATCH -v3 00/10] locking/mutex: Rewrite basic mutex

[Peter Zijlstra]

Hi,

New version, with improved Changelogs and bits. This version has survived aim7
loads on my 2 socket machine, I've yet to try the 4 socket. But over-all it
seem to behave as expected.

That is, all except the last patch, which I just wrote and hasn't even seen a
compiler up close.


---
 arch/alpha/include/asm/mutex.h           |   9 -
 arch/arc/include/asm/mutex.h             |  18 -
 arch/arm/include/asm/mutex.h             |  21 --
 arch/arm64/include/asm/Kbuild            |   1 -
 arch/avr32/include/asm/mutex.h           |   9 -
 arch/blackfin/include/asm/Kbuild         |   1 -
 arch/c6x/include/asm/mutex.h             |   6 -
 arch/cris/include/asm/mutex.h            |   9 -
 arch/frv/include/asm/mutex.h             |   9 -
 arch/h8300/include/asm/mutex.h           |   9 -
 arch/hexagon/include/asm/mutex.h         |   8 -
 arch/ia64/include/asm/mutex.h            |  90 -----
 arch/m32r/include/asm/mutex.h            |   9 -
 arch/m68k/include/asm/Kbuild             |   1 -
 arch/metag/include/asm/Kbuild            |   1 -
 arch/microblaze/include/asm/mutex.h      |   1 -
 arch/mips/include/asm/Kbuild             |   1 -
 arch/mn10300/include/asm/mutex.h         |  16 -
 arch/nios2/include/asm/mutex.h           |   1 -
 arch/openrisc/include/asm/mutex.h        |  27 --
 arch/parisc/include/asm/Kbuild           |   1 -
 arch/powerpc/include/asm/mutex.h         | 132 -------
 arch/s390/include/asm/mutex.h            |   9 -
 arch/score/include/asm/mutex.h           |   6 -
 arch/sh/include/asm/atomic-llsc.h        |   2 +-
 arch/sh/include/asm/mutex-llsc.h         | 109 ------
 arch/sh/include/asm/mutex.h              |  12 -
 arch/sparc/include/asm/Kbuild            |   1 -
 arch/tile/include/asm/Kbuild             |   1 -
 arch/um/include/asm/Kbuild               |   1 -
 arch/unicore32/include/asm/mutex.h       |  20 --
 arch/x86/include/asm/mutex.h             |   5 -
 arch/x86/include/asm/mutex_32.h          | 110 ------
 arch/x86/include/asm/mutex_64.h          | 127 -------
 arch/xtensa/include/asm/mutex.h          |   9 -
 drivers/gpu/drm/i915/i915_gem_shrinker.c |  26 +-
 drivers/gpu/drm/msm/msm_gem_shrinker.c   |  23 +-
 include/asm-generic/mutex-dec.h          |  88 -----
 include/asm-generic/mutex-null.h         |  19 -
 include/asm-generic/mutex-xchg.h         | 120 -------
 include/asm-generic/mutex.h              |   9 -
 include/linux/mutex-debug.h              |  24 --
 include/linux/mutex.h                    |  46 ++-
 kernel/Kconfig.locks                     |   2 +-
 kernel/locking/mutex-debug.c             |  13 -
 kernel/locking/mutex-debug.h             |  10 -
 kernel/locking/mutex.c                   | 589 ++++++++++++++++++-------------
 kernel/locking/mutex.h                   |  26 --
 kernel/sched/core.c                      |   2 +-
 49 files changed, 382 insertions(+), 1407 deletions(-)

[PATCH -v3 01/10] locking/drm: Kill mutex trickery

[Peter Zijlstra]

[-- Attachment #1: peterz-revert-drm-i915-brainmelt.patch --]
[-- Type: text/plain, Size: 2415 bytes --]

Poking at lock internals is not cool. Since I'm going to change the
implementation this will break, take it out.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Rob Clark <robdclark@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 drivers/gpu/drm/i915/i915_gem_shrinker.c |   26 +++-----------------------
 drivers/gpu/drm/msm/msm_gem_shrinker.c   |   23 +++--------------------
 2 files changed, 6 insertions(+), 43 deletions(-)

--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -35,19 +35,6 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
-{
-	if (!mutex_is_locked(mutex))
-		return false;
-
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
-
 static int num_vma_bound(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
@@ -238,17 +225,10 @@ unsigned long i915_gem_shrink_all(struct
 
 static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
-
-		if (to_i915(dev)->mm.shrinker_no_lock_stealing)
-			return false;
-
-		*unlock = false;
-	} else
-		*unlock = true;
+	if (!mutex_trylock(&dev->struct_mutex))
+		return false;
 
+	*unlock = true;
 	return true;
 }
 
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -18,29 +18,12 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
-{
-	if (!mutex_is_locked(mutex))
-		return false;
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
-
 static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
-		*unlock = false;
-	} else {
-		*unlock = true;
-	}
+	if (!mutex_trylock(&dev->struct_mutex))
+		return false;
 
+	*unlock = true;
 	return true;
 }
 

[PATCH -v3 02/10] sh/atomic: Fix ATOMIC_FETCH_OP()

[Peter Zijlstra]

[-- Attachment #1: peterz-atomic-fix-sh.patch --]
[-- Type: text/plain, Size: 815 bytes --]

We cannot use the "z" constraint twice, since its a single register
(r0). Change the one not used by movli.l/movco.l to "r".

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/sh/include/asm/atomic-llsc.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -60,7 +60,7 @@ static inline int atomic_fetch_##op(int
 "	movco.l	%0, @%3					\n"		\
 "	bf	1b					\n"		\
 "	synco						\n"		\
-	: "=&z" (temp), "=&z" (res)					\
+	: "=&z" (temp), "=&r" (res)					\
 	: "r" (i), "r" (&v->counter)					\
 	: "t");								\
 									\

[PATCH -v3 03/10] locking/mutex: Rework mutex::owner

[Peter Zijlstra]

[-- Attachment #1: peterz-locking-rewrite-mutex-owner.patch --]
[-- Type: text/plain, Size: 25568 bytes --]

The current mutex implementation has an atomic lock word and a
non-atomic owner field.

This disparity leads to a number of issues with the current mutex code
as it means that we can have a locked mutex without an explicit owner
(because the owner field has not been set, or already cleared).

This leads to a number of weird corner cases, esp. between the
optimistic spinning and debug code. Where the optimistic spinning
code needs the owner field updated inside the lock region, the debug
code is more relaxed because the whole lock is serialized by the
wait_lock.

Also, the spinning code itself has a few corner cases where we need to
deal with a held lock without an owner field.

Furthermore, it becomes even more of a problem when trying to fix
starvation cases in the current code. We end up stacking special case
on special case.

To solve this rework the basic mutex implementation to be a single
atomic word that contains the owner and uses the low bits for extra
state.

This matches how PI futexes and rt_mutex already work. By having the
owner an integral part of the lock state a lot of the problems
dissapear and we get a better option to deal with starvation cases,
direct owner handoff.

Changing the basic mutex does however invalidate all the arch specific
mutex code; this patch leaves that unused in-place, a later patch will
remove that.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/mutex-debug.h  |   24 --
 include/linux/mutex.h        |   46 +++--
 kernel/locking/mutex-debug.c |   13 -
 kernel/locking/mutex-debug.h |   10 -
 kernel/locking/mutex.c       |  371 ++++++++++++++++++-------------------------
 kernel/locking/mutex.h       |   26 ---
 kernel/sched/core.c          |    2 
 7 files changed, 187 insertions(+), 305 deletions(-)

--- 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
--- 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
 #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 *l
  */
 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;
 }
 
 /*
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -73,21 +73,8 @@ void debug_mutex_unlock(struct mutex *lo
 {
 	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,
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -27,16 +27,6 @@ extern void debug_mutex_unlock(struct mu
 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); \
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -27,41 +27,113 @@
 #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.
+ */
+#define MUTEX_FLAG_WAITERS	0x01
+
+#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.
+ */
+static inline bool __mutex_trylock(struct mutex *lock)
+{
+	unsigned long owner, curr = (unsigned long)current;
+
+	owner = atomic_long_read(&lock->owner);
+	for (;;) { /* must loop, can race against a flag */
+		unsigned long old;
+
+		if (__owner_task(owner))
+			return false;
+
+		old = atomic_long_cmpxchg_acquire(&lock->owner, owner,
+						  curr | __owner_flags(owner));
+		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);
+}
+
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * We split the mutex lock/unlock logic into separate fastpath and
@@ -69,7 +141,7 @@ 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 +167,10 @@ __visible void __sched __mutex_lock_slow
 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 +217,6 @@ static __always_inline void ww_mutex_loc
 /*
  * 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 +241,7 @@ ww_mutex_set_context_fastpath(struct ww_
 	/*
 	 * 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 +292,7 @@ bool mutex_spin_on_owner(struct mutex *l
 	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,
@@ -260,27 +325,20 @@ static inline int mutex_can_spin_on_owne
 		return 0;
 
 	rcu_read_lock();
-	owner = READ_ONCE(lock->owner);
+	owner = __mutex_owner(lock);
 	if (owner)
 		retval = owner->on_cpu;
 	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 +346,6 @@ static inline bool mutex_try_to_acquire(
  * 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
@@ -342,36 +393,17 @@ static bool mutex_optimistic_spin(struct
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		owner = READ_ONCE(lock->owner);
+		owner = __mutex_owner(lock);
 		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);
-			}
-
-			mutex_set_owner(lock);
+		if (__mutex_trylock(lock)) {
 			osq_unlock(&lock->osq);
 			return true;
 		}
 
 		/*
-		 * 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)))
-			break;
-
-		/*
 		 * The cpu_relax() call is a compiler barrier which forces
 		 * everything in this loop to be re-loaded. We don't need
 		 * memory barriers as we'll eventually observe the right
@@ -406,8 +438,7 @@ static bool mutex_optimistic_spin(struct
 }
 #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 +453,12 @@ void __sched __mutex_unlock_slowpath(ato
  */
 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 +487,7 @@ void __sched ww_mutex_unlock(struct ww_m
 		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);
 
@@ -520,20 +534,24 @@ __mutex_lock_common(struct mutex *lock,
 	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) || mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
 		/* got the lock, yay! */
+		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);
+		}
 		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))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -543,21 +561,13 @@ __mutex_lock_common(struct mutex *lock,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
+	if (list_first_entry(&lock->wait_list, struct mutex_waiter, list) == &waiter)
+		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+
 	lock_contended(&lock->dep_map, ip);
 
 	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:
-		 */
-		if (atomic_read(&lock->count) >= 0 &&
-		    (atomic_xchg_acquire(&lock->count, -1) == 1))
+		if (__mutex_trylock(lock))
 			break;
 
 		/*
@@ -585,15 +595,14 @@ __mutex_lock_common(struct mutex *lock,
 	__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_FLAG_WAITERS);
+
 	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);
@@ -631,7 +640,6 @@ _mutex_lock_nest_lock(struct mutex *lock
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
 			    0, nest, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
@@ -650,7 +658,6 @@ mutex_lock_interruptible_nested(struct m
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
 				   subclass, NULL, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
 static inline int
@@ -715,29 +722,22 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interr
 /*
  * 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;
+	unsigned long owner, flags;
 	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.
-	 *
-	 *
-	 * 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.
+	 * Release the lock before (potentially) taking the spinlock
+	 * such that other contenders can get on with things ASAP.
 	 */
-	if (__mutex_slowpath_needs_to_unlock())
-		atomic_set(&lock->count, 1);
+	owner = atomic_long_fetch_and_release(MUTEX_FLAGS, &lock->owner);
+	if (!owner)
+		return;
 
 	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)) {
@@ -754,17 +754,6 @@ __mutex_unlock_common_slowpath(struct mu
 	wake_up_q(&wake_q);
 }
 
-/*
- * Release the lock, slowpath:
- */
-__visible void
-__mutex_unlock_slowpath(atomic_t *lock_count)
-{
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-
-	__mutex_unlock_common_slowpath(lock, 1);
-}
-
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * Here come the less common (and hence less performance-critical) APIs:
@@ -789,38 +778,30 @@ __mutex_lock_interruptible_slowpath(stru
  */
 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 +837,6 @@ __ww_mutex_lock_interruptible_slowpath(s
 
 #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 +853,12 @@ static inline int __mutex_trylock_slowpa
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	int ret;
+	bool locked = __mutex_trylock(lock);
 
-	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 +866,28 @@ 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);
 
--- 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)
--- 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

[PATCH -v3 04/10] locking/mutex: Kill arch specific code

[Peter Zijlstra]

[-- Attachment #1: peterz-locking-rewrite-mutex-rm.patch --]
[-- Type: text/plain, Size: 37398 bytes --]

Its all generic atomic_long_t stuff now.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/alpha/include/asm/mutex.h      |    9 --
 arch/arc/include/asm/mutex.h        |   18 ----
 arch/arm/include/asm/mutex.h        |   21 -----
 arch/arm64/include/asm/Kbuild       |    1 
 arch/avr32/include/asm/mutex.h      |    9 --
 arch/blackfin/include/asm/Kbuild    |    1 
 arch/c6x/include/asm/mutex.h        |    6 -
 arch/cris/include/asm/mutex.h       |    9 --
 arch/frv/include/asm/mutex.h        |    9 --
 arch/h8300/include/asm/mutex.h      |    9 --
 arch/hexagon/include/asm/mutex.h    |    8 --
 arch/ia64/include/asm/mutex.h       |   90 ------------------------
 arch/m32r/include/asm/mutex.h       |    9 --
 arch/m68k/include/asm/Kbuild        |    1 
 arch/metag/include/asm/Kbuild       |    1 
 arch/microblaze/include/asm/mutex.h |    1 
 arch/mips/include/asm/Kbuild        |    1 
 arch/mn10300/include/asm/mutex.h    |   16 ----
 arch/nios2/include/asm/mutex.h      |    1 
 arch/openrisc/include/asm/mutex.h   |   27 -------
 arch/parisc/include/asm/Kbuild      |    1 
 arch/powerpc/include/asm/mutex.h    |  132 ------------------------------------
 arch/s390/include/asm/mutex.h       |    9 --
 arch/score/include/asm/mutex.h      |    6 -
 arch/sh/include/asm/mutex-llsc.h    |  109 -----------------------------
 arch/sh/include/asm/mutex.h         |   12 ---
 arch/sparc/include/asm/Kbuild       |    1 
 arch/tile/include/asm/Kbuild        |    1 
 arch/um/include/asm/Kbuild          |    1 
 arch/unicore32/include/asm/mutex.h  |   20 -----
 arch/x86/include/asm/mutex.h        |    5 -
 arch/x86/include/asm/mutex_32.h     |  110 ------------------------------
 arch/x86/include/asm/mutex_64.h     |  127 ----------------------------------
 arch/xtensa/include/asm/mutex.h     |    9 --
 include/asm-generic/mutex-dec.h     |   88 ------------------------
 include/asm-generic/mutex-null.h    |   19 -----
 include/asm-generic/mutex-xchg.h    |  120 --------------------------------
 include/asm-generic/mutex.h         |    9 --
 38 files changed, 1026 deletions(-)

--- a/arch/alpha/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/arc/include/asm/mutex.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * xchg() based mutex fast path maintains a state of 0 or 1, as opposed to
- * atomic dec based which can "count" any number of lock contenders.
- * This ideally needs to be fixed in core, but for now switching to dec ver.
- */
-#if defined(CONFIG_SMP) && (CONFIG_NR_CPUS > 2)
-#include <asm-generic/mutex-dec.h>
-#else
-#include <asm-generic/mutex-xchg.h>
-#endif
--- a/arch/arm/include/asm/mutex.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/include/asm/mutex.h
- *
- * ARM optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
-/*
- * On pre-ARMv6 hardware this results in a swp-based implementation,
- * which is the most efficient. For ARMv6+, we have exclusive memory
- * accessors and use atomic_dec to avoid the extra xchg operations
- * on the locking slowpaths.
- */
-#if __LINUX_ARM_ARCH__ < 6
-#include <asm-generic/mutex-xchg.h>
-#else
-#include <asm-generic/mutex-dec.h>
-#endif
-#endif	/* _ASM_MUTEX_H */
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -26,7 +26,6 @@ generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
-generic-y += mutex.h
 generic-y += pci.h
 generic-y += poll.h
 generic-y += preempt.h
--- a/arch/avr32/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -24,7 +24,6 @@ generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += pgalloc.h
--- a/arch/c6x/include/asm/mutex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_C6X_MUTEX_H
-#define _ASM_C6X_MUTEX_H
-
-#include <asm-generic/mutex-null.h>
-
-#endif /* _ASM_C6X_MUTEX_H */
--- a/arch/cris/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/frv/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/h8300/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/hexagon/include/asm/mutex.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#include <asm-generic/mutex-xchg.h>
--- a/arch/ia64/include/asm/mutex.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * ia64 implementation of the mutex fastpath.
- *
- * Copyright (C) 2006 Ken Chen <kenneth.w.chen@intel.com>
- *
- */
-
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_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(ia64_fetchadd4_acq(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(ia64_fetchadd4_acq(count, -1) != 1))
-		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 *))
-{
-	int ret = ia64_fetchadd4_rel(count, 1);
-	if (unlikely(ret < 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 (atomic_read(count) == 1 && cmpxchg_acq(count, 1, 0) == 1)
-		return 1;
-	return 0;
-}
-
-#endif
--- a/arch/m32r/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -20,7 +20,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
-generic-y += mutex.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += resource.h
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -27,7 +27,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
--- a/arch/microblaze/include/asm/mutex.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mutex-dec.h>
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -9,7 +9,6 @@ generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
--- a/arch/mn10300/include/asm/mutex.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* MN10300 Mutex fastpath
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- *
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#include <asm-generic/mutex-null.h>
--- a/arch/nios2/include/asm/mutex.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mutex-dec.h>
--- a/arch/openrisc/include/asm/mutex.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * OpenRISC Linux
- *
- * Linux architectural port borrowing liberally from similar works of
- * others.  All original copyrights apply as per the original source
- * declaration.
- *
- * OpenRISC implementation:
- * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
- * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
- * et al.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += poll.h
--- a/arch/powerpc/include/asm/mutex.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
- */
-#ifndef _ASM_POWERPC_MUTEX_H
-#define _ASM_POWERPC_MUTEX_H
-
-static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
-{
-	int t;
-
-	__asm__ __volatile__ (
-"1:	lwarx	%0,0,%1		# mutex trylock\n\
-	cmpw	0,%0,%2\n\
-	bne-	2f\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%3,0,%1\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	"\n\
-2:"
-	: "=&r" (t)
-	: "r" (&v->counter), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return t;
-}
-
-static inline int __mutex_dec_return_lock(atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-"1:	lwarx	%0,0,%1		# mutex lock\n\
-	addic	%0,%0,-1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	: "=&r" (t)
-	: "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
-}
-
-static inline int __mutex_inc_return_unlock(atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
-"1:	lwarx	%0,0,%1		# mutex unlock\n\
-	addic	%0,%0,1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
-}
-
-/**
- *  __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(__mutex_dec_return_lock(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(__mutex_dec_return_lock(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.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(__mutex_inc_return_unlock(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 0, and return 1 (success), or if the count
- * was not 1, then return 0 (failure).
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1))
-		return 1;
-	return 0;
-}
-
-#endif
--- a/arch/s390/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- a/arch/score/include/asm/mutex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_MUTEX_H
-#define _ASM_SCORE_MUTEX_H
-
-#include <asm-generic/mutex-dec.h>
-
-#endif /* _ASM_SCORE_MUTEX_H */
--- a/arch/sh/include/asm/mutex-llsc.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/*
- * arch/sh/include/asm/mutex-llsc.h
- *
- * SH-4A optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef __ASM_SH_MUTEX_LLSC_H
-#define __ASM_SH_MUTEX_LLSC_H
-
-/*
- * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure.
- * with a bastardized atomic decrement (it is not a reliable atomic decrement
- * but it satisfies the defined semantics for our purpose, while being
- * smaller and faster than a real atomic decrement or atomic swap.
- * The idea is to attempt  decrementing the lock value only once. If once
- * decremented it isn't zero, or if its store-back fails due to a dispute
- * on the exclusive store, we simply bail out immediately through the slow
- * path where the lock will be reattempted until it succeeds.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n"
-		"add		#-1, %0	\n"
-		"movco.l	%0, @%2	\n"
-		"movt		%1	\n"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count)
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n"
-		"add		#-1, %0	\n"
-		"movco.l	%0, @%2	\n"
-		"movt		%1	\n"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res != 0))
-		__res = -1;
-
-	return __res;
-}
-
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n\t"
-		"add		#1, %0	\n\t"
-		"movco.l	%0, @%2 \n\t"
-		"movt		%1	\n\t"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res <= 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we do an atomic decrement and check the
- * result and put it in the __res variable.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __res, __orig;
-
-	__asm__ __volatile__ (
-		"1: movli.l	@%2, %0		\n\t"
-		"dt		%0		\n\t"
-		"movco.l	%0,@%2		\n\t"
-		"bf		1b		\n\t"
-		"cmp/eq		#0,%0		\n\t"
-		"bt		2f		\n\t"
-		"mov		#0, %1		\n\t"
-		"bf		3f		\n\t"
-		"2: mov		#1, %1		\n\t"
-		"3:				"
-		: "=&z" (__orig), "=&r" (__res)
-		: "r" (&count->counter)
-		: "t");
-
-	return __res;
-}
-#endif /* __ASM_SH_MUTEX_LLSC_H */
--- a/arch/sh/include/asm/mutex.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#if defined(CONFIG_CPU_SH4A)
-#include <asm/mutex-llsc.h>
-#else
-#include <asm-generic/mutex-dec.h>
-#endif
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -14,7 +14,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += module.h
-generic-y += mutex.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += serial.h
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -21,7 +21,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += poll.h
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -17,7 +17,6 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
--- a/arch/unicore32/include/asm/mutex.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * linux/arch/unicore32/include/asm/mutex.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * UniCore optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef __UNICORE_MUTEX_H__
-#define __UNICORE_MUTEX_H__
-
-# include <asm-generic/mutex-xchg.h>
-#endif
--- a/arch/x86/include/asm/mutex.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include <asm/mutex_32.h>
-#else
-# include <asm/mutex_64.h>
-#endif
--- a/arch/x86/include/asm/mutex_32.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_32_H
-#define _ASM_X86_MUTEX_32_H
-
-#include <asm/alternative.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
- *  @fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-#define __mutex_fastpath_lock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%eax)\n"		\
-		     "   jns 1f	\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-
-/**
- *  __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(count) < 0))
-		return -1;
-	else
-		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 <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, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-#define __mutex_fastpath_unlock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%eax)\n"		\
-		     "   jg	1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-#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.
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	/* cmpxchg because it never induces a false contention state. */
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-
-	return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_32_H */
--- a/arch/x86/include/asm/mutex_64.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_64_H
-#define _ASM_X86_MUTEX_64_H
-
-/**
- * __mutex_fastpath_lock - decrement and call function if negative
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is negative
- *
- * Atomically decrements @v and calls <fail_fn> if the result is negative.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_lock(atomic_t *v,
-					 void (*fail_fn)(atomic_t *))
-{
-	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
-			  "   jns %l[exit]\n"
-			  : : "m" (v->counter)
-			  : "memory", "cc"
-			  : exit);
-	fail_fn(v);
-exit:
-	return;
-}
-#else
-#define __mutex_fastpath_lock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%rdi)\n"		\
-		     "   jns 1f		\n"			\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-#endif
-
-/**
- *  __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(count) < 0))
-		return -1;
-	else
-		return 0;
-}
-
-/**
- * __mutex_fastpath_unlock - increment and call function if nonpositive
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is nonpositive
- *
- * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_unlock(atomic_t *v,
-					   void (*fail_fn)(atomic_t *))
-{
-	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
-			  "   jg %l[exit]\n"
-			  : : "m" (v->counter)
-			  : "memory", "cc"
-			  : exit);
-	fail_fn(v);
-exit:
-	return;
-}
-#else
-#define __mutex_fastpath_unlock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%rdi)\n"		\
-		     "   jg 1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-#endif
-
-#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 0 and return 1 (success), or return 0 (failure)
- * if it wasn't 1 originally. [the fallback function is never used on
- * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-
-	return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_64_H */
--- a/arch/xtensa/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
--- 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
--- 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
--- 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
--- 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 */

[PATCH -v3 05/10] locking/mutex: Allow MUTEX_SPIN_ON_OWNER when DEBUG_MUTEXES

[Peter Zijlstra]

[-- Attachment #1: peterz-locking-mutex-enable-spin_on_owner-debug.patch --]
[-- Type: text/plain, Size: 557 bytes --]

Now that mutex::count and mutex::owner are the same field, we can
allow SPIN_ON_OWNER while DEBUG_MUTEX.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/Kconfig.locks |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- 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

[PATCH -v3 06/10] locking/mutex: Add lock handoff to avoid starvation

[Peter Zijlstra]

[-- Attachment #1: peterz-locking-mutex-steal.patch --]
[-- Type: text/plain, Size: 9134 bytes --]

Implement lock handoff to avoid lock starvation.

Lock starvation is possible because mutex_lock() allows lock stealing,
where a running (or optimistic spinning) task beats the woken waiter
to the acquire.

Lock stealing is an important performance optimization because waiting
for a waiter to wake up and get runtime can take a significant time,
during which everyboy would stall on the lock.

The down-side is of course that it allows for starvation.

This patch has the waiter requesting a handoff if it fails to acquire
the lock upon waking. This re-introduces some of the wait time,
because once we do a handoff we have to wait for the waiter to wake up
again.

A future patch will add a round of optimistic spinning to attempt to
alleviate this penalty, but if that turns out to not be enough, we can
add a counter and only request handoff after multiple failed wakeups.

There are a few tricky implementation details:

 - accepting a handoff must only be done in the wait-loop. Since the
   handoff condition is owner == current, it can easily cause
   recursive locking trouble.

 - accepting the handoff must be careful to provide the ACQUIRE
   semantics.

 - having the HANDOFF bit set on unlock requires care, we must not
   clear the owner.

 - we must be careful to not leave HANDOFF set after we've acquired
   the lock. An alternative approach is to combine the bit set and a
   trylock in one cmpxchg loop, which ensures we either steal/acquire
   the lock or unlock must observe and clear HANDOFF.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/locking/mutex.c |  139 +++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 117 insertions(+), 22 deletions(-)

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -54,8 +54,10 @@ EXPORT_SYMBOL(__mutex_init);
  * 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
 
@@ -71,8 +73,13 @@ static inline unsigned long __owner_flag
 
 /*
  * 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)
+static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
 {
 	unsigned long owner, curr = (unsigned long)current;
 
@@ -80,8 +87,24 @@ static inline bool __mutex_trylock(struc
 	for (;;) { /* must loop, can race against a flag */
 		unsigned long old;
 
-		if (__owner_task(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;
+		}
 
 		old = atomic_long_cmpxchg_acquire(&lock->owner, owner,
 						  curr | __owner_flags(owner));
@@ -134,6 +157,39 @@ static inline void __mutex_clear_flag(st
 	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
@@ -398,7 +454,7 @@ static bool mutex_optimistic_spin(struct
 			break;
 
 		/* Try to acquire the mutex if it is unlocked. */
-		if (__mutex_trylock(lock)) {
+		if (__mutex_trylock(lock, false)) {
 			osq_unlock(&lock->osq);
 			return true;
 		}
@@ -523,6 +579,7 @@ __mutex_lock_common(struct mutex *lock,
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
 	unsigned long flags;
+	bool first = false;
 	int ret;
 
 	if (use_ww_ctx) {
@@ -534,7 +591,8 @@ __mutex_lock_common(struct mutex *lock,
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
-	if (__mutex_trylock(lock) || mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
+	if (__mutex_trylock(lock, false) ||
+	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
 		if (use_ww_ctx) {
@@ -551,7 +609,7 @@ __mutex_lock_common(struct mutex *lock,
 	/*
 	 * After waiting to acquire the wait_lock, try again.
 	 */
-	if (__mutex_trylock(lock))
+	if (__mutex_trylock(lock, false))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -561,15 +619,15 @@ __mutex_lock_common(struct mutex *lock,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
-	if (list_first_entry(&lock->wait_list, struct mutex_waiter, list) == &waiter)
+	if (__mutex_waiter_is_first(lock, &waiter))
 		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
 
+	if (__mutex_trylock(lock, false))
+		goto remove_waiter;
+
 	lock_contended(&lock->dep_map, ip);
 
 	for (;;) {
-		if (__mutex_trylock(lock))
-			break;
-
 		/*
 		 * got a signal? (This code gets eliminated in the
 		 * TASK_UNINTERRUPTIBLE case.)
@@ -586,17 +644,26 @@ __mutex_lock_common(struct mutex *lock,
 		}
 
 		__set_task_state(task, state);
-
-		/* didn't get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
 		schedule_preempt_disabled();
 		spin_lock_mutex(&lock->wait_lock, flags);
+
+		if (__mutex_waiter_is_first(lock, &waiter)) {
+			first = true;
+			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+		}
+
+		if (__mutex_trylock(lock, true))
+			break;
 	}
 	__set_task_state(task, TASK_RUNNING);
 
+remove_waiter:
 	mutex_remove_waiter(lock, &waiter, task);
 	if (likely(list_empty(&lock->wait_list)))
-		__mutex_clear_flag(lock, MUTEX_FLAG_WAITERS);
+		__mutex_clear_flag(lock, MUTEX_FLAGS);
+	else if (first && (atomic_long_read(&lock->owner) & MUTEX_FLAG_HANDOFF))
+		__mutex_clear_flag(lock, MUTEX_FLAG_HANDOFF);
 
 	debug_mutex_free_waiter(&waiter);
 
@@ -724,33 +791,61 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interr
  */
 static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 {
+	struct task_struct *next = NULL;
 	unsigned long owner, flags;
 	WAKE_Q(wake_q);
 
 	mutex_release(&lock->dep_map, 1, ip);
 
 	/*
-	 * Release the lock before (potentially) taking the spinlock
-	 * such that other contenders can get on with things ASAP.
+	 * Release the lock before (potentially) taking the spinlock such that
+	 * other contenders can get on with things ASAP.
+	 *
+	 * Except when HANDOFF, in that case we must not clear the owner field,
+	 * but instead set it to the top waiter.
 	 */
-	owner = atomic_long_fetch_and_release(MUTEX_FLAGS, &lock->owner);
-	if (!owner)
-		return;
+	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);
 	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);
 	}
 
+	if (owner & MUTEX_FLAG_HANDOFF)
+		__mutex_handoff(lock, next);
+
 	spin_unlock_mutex(&lock->wait_lock, flags);
+
 	wake_up_q(&wake_q);
 }
 
@@ -853,7 +948,7 @@ __ww_mutex_lock_interruptible_slowpath(s
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	bool locked = __mutex_trylock(lock);
+	bool locked = __mutex_trylock(lock, false);
 
 	if (locked)
 		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);

[PATCH -v3 07/10] mutex: Restructure wait loop

[Peter Zijlstra]

[-- Attachment #1: peterz-locking-mutex-wait_lock-opt.patch --]
[-- Type: text/plain, Size: 2257 bytes --]

Doesn't really matter yet, but pull the HANDOFF and trylock out from
under the wait_lock.

The intention is to add an optimistic spin loop here, which requires
we do not hold the wait_lock, so shuffle code around in preparation.

Also clarify the purpose of taking the wait_lock in the wait loop, its
tempting to want to avoid it altogether, but the cancellation cases
need to to avoid loosing wakeups.

Suggested-by: Waiman Long <waiman.long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/locking/mutex.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -627,10 +627,12 @@ __mutex_lock_common(struct mutex *lock,
 
 	lock_contended(&lock->dep_map, ip);
 
+	set_task_state(task, state);
 	for (;;) {
 		/*
-		 * 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;
@@ -643,20 +645,27 @@ __mutex_lock_common(struct mutex *lock,
 				goto err;
 		}
 
-		__set_task_state(task, state);
 		spin_unlock_mutex(&lock->wait_lock, flags);
 		schedule_preempt_disabled();
-		spin_lock_mutex(&lock->wait_lock, flags);
 
 		if (__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 (__mutex_trylock(lock, true))
 			break;
+
+		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 	__set_task_state(task, TASK_RUNNING);
+	spin_lock_mutex(&lock->wait_lock, flags);
 
 remove_waiter:
 	mutex_remove_waiter(lock, &waiter, task);
@@ -681,6 +690,7 @@ __mutex_lock_common(struct mutex *lock,
 	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);

[PATCH -v3 08/10] locking/mutex: Simplify some ww_mutex code in __mutex_lock_common()

[Peter Zijlstra]

[-- Attachment #1: waiman_long-locking_mutex-simplify_some_ww_mutex_code_in___mutex_lock_common.patch --]
[-- Type: text/plain, Size: 1986 bytes --]

This patch removes some of the redundant ww_mutex code in
__mutex_lock_common().

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jason Low <jason.low2@hpe.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Will Deacon <Will.Deacon@arm.com>
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1472254509-27508-1-git-send-email-Waiman.Long@hpe.com
---
 kernel/locking/mutex.c |   13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -580,10 +580,11 @@ __mutex_lock_common(struct mutex *lock,
 	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;
 	}
@@ -595,12 +596,8 @@ __mutex_lock_common(struct mutex *lock,
 	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
-		if (use_ww_ctx) {
-			struct ww_mutex *ww;
-			ww = container_of(lock, struct ww_mutex, base);
-
+		if (use_ww_ctx)
 			ww_mutex_set_context_fastpath(ww, ww_ctx);
-		}
 		preempt_enable();
 		return 0;
 	}
@@ -680,10 +677,8 @@ __mutex_lock_common(struct mutex *lock,
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
 
-	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();

[PATCH -v3 09/10] locking/mutex: Enable optimistic spinning of woken waiter

[Peter Zijlstra]

[-- Attachment #1: waiman_long-locking_mutex-enable_optimistic_spinning_of_woken_waiter.patch --]
[-- Type: text/plain, Size: 5089 bytes --]

This patch makes the waiter that sets the HANDOFF flag start spinning
instead of sleeping until the handoff is complete or the owner
sleeps. Otherwise, the handoff will cause the optimistic spinners to
abort spinning as the handed-off owner may not be running.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jason Low <jason.low2@hpe.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Will Deacon <Will.Deacon@arm.com>
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1472254509-27508-2-git-send-email-Waiman.Long@hpe.com
---
 kernel/locking/mutex.c |   76 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 54 insertions(+), 22 deletions(-)

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -409,24 +409,39 @@ static inline int mutex_can_spin_on_owne
  *
  * 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) {
@@ -442,7 +457,7 @@ static bool mutex_optimistic_spin(struct
 			 * performed the optimistic spinning cannot be done.
 			 */
 			if (READ_ONCE(ww->ctx))
-				break;
+				goto fail_unlock;
 		}
 
 		/*
@@ -450,15 +465,20 @@ static bool mutex_optimistic_spin(struct
 		 * release the lock or go to sleep.
 		 */
 		owner = __mutex_owner(lock);
-		if (owner && !mutex_spin_on_owner(lock, owner))
-			break;
+		if (owner) {
+			if (waiter && owner == task) {
+				smp_mb(); /* ACQUIRE */
+				break;
+			}
 
-		/* Try to acquire the mutex if it is unlocked. */
-		if (__mutex_trylock(lock, false)) {
-			osq_unlock(&lock->osq);
-			return true;
+			if (!mutex_spin_on_owner(lock, owner))
+				goto fail_unlock;
 		}
 
+		/* Try to acquire the mutex if it is unlocked. */
+		if (__mutex_trylock(lock, waiter))
+			break;
+
 		/*
 		 * The cpu_relax() call is a compiler barrier which forces
 		 * everything in this loop to be re-loaded. We don't need
@@ -468,8 +488,17 @@ static bool mutex_optimistic_spin(struct
 		cpu_relax_lowlatency();
 	}
 
-	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
@@ -488,7 +517,8 @@ static bool mutex_optimistic_spin(struct
 }
 #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;
 }
@@ -593,7 +623,7 @@ __mutex_lock_common(struct mutex *lock,
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
 	if (__mutex_trylock(lock, false) ||
-	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
+	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
 		if (use_ww_ctx)
@@ -648,6 +678,8 @@ __mutex_lock_common(struct mutex *lock,
 		if (__mutex_waiter_is_first(lock, &waiter)) {
 			first = true;
 			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+			if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true))
+				break;
 		}
 
 		set_task_state(task, state);

[RFC][PATCH -v3 10/10] locking/mutex: Implement alternative HANDOFF

[Peter Zijlstra]

[-- Attachment #1: peterz-mutex-handoff-opt.patch --]
[-- Type: text/plain, Size: 2069 bytes --]

As mentioned in a previous patch, its possible to implement the
handoff logic differently, avoiding the issue where we 'leak' a HADOFF
flag.

This patch does so, just to show what it looks like; I'm not at all
convinced this is worth it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/locking/mutex.c |   34 +++++++++++++++++++++++++++++-----
 1 file changed, 29 insertions(+), 5 deletions(-)

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -71,6 +71,32 @@ static inline unsigned long __owner_flag
 	return owner & MUTEX_FLAGS;
 }
 
+static inline bool __mutex_req_handoff(struct mutex *lock)
+{
+	unsigned long owner, curr = (unsigned long)current;
+
+	owner = atomic_long_read(&lock->owner);
+	for (;;) {
+		unsigned long old, new;
+
+		if (owner & MUTEX_FLAG_HANDOFF)
+			return false;
+
+		if (__owner_task(owner))
+			new = owner | MUTEX_FLAG_HANDOFF;
+		else
+			new = curr | __owner_flags(owner);
+
+		old = atomic_long_cmpxchg_acquire(&lock->owner, owner, new);
+		if (old == owner)
+			break;
+
+		owner = old;
+	}
+
+	return !__owner_task(owner);
+}
+
 /*
  * Actual trylock that will work on any unlocked state.
  *
@@ -609,7 +635,6 @@ __mutex_lock_common(struct mutex *lock,
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
 	unsigned long flags;
-	bool first = false;
 	struct ww_mutex *ww;
 	int ret;
 
@@ -676,8 +701,9 @@ __mutex_lock_common(struct mutex *lock,
 		schedule_preempt_disabled();
 
 		if (__mutex_waiter_is_first(lock, &waiter)) {
-			first = true;
-			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+			if (__mutex_req_handoff(lock))
+				break;
+
 			if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true))
 				break;
 		}
@@ -700,8 +726,6 @@ __mutex_lock_common(struct mutex *lock,
 	mutex_remove_waiter(lock, &waiter, task);
 	if (likely(list_empty(&lock->wait_list)))
 		__mutex_clear_flag(lock, MUTEX_FLAGS);
-	else if (first && (atomic_long_read(&lock->owner) & MUTEX_FLAG_HANDOFF))
-		__mutex_clear_flag(lock, MUTEX_FLAG_HANDOFF);
 
 	debug_mutex_free_waiter(&waiter);
 

Re: [RFC][PATCH -v3 10/10] locking/mutex: Implement alternative HANDOFF

[Waiman Long]

On 09/05/2016 08:36 AM, Peter Zijlstra wrote:
> As mentioned in a previous patch, its possible to implement the
> handoff logic differently, avoiding the issue where we 'leak' a HADOFF
> flag.
>
> This patch does so, just to show what it looks like; I'm not at all
> convinced this is worth it.
>
> Signed-off-by: Peter Zijlstra (Intel)<peterz@infradead.org>
>

I have another way of catching the uncleared handoff flag. See the 
following code to see if you think that will work.

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 9492494..362ff83 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -85,7 +85,13 @@ static inline bool __mutex_trylock(struct mutex 
*lock, const

         owner = atomic_long_read(&lock->owner);
         for (;;) { /* must loop, can race against a flag */
-               unsigned long old;
+               unsigned long old, flags = __owner_flags(owner);
+
+               /*
+                * We don't need to keep the HANDOFF flag for the waiter.
+                */
+               if (handoff)
+                       flags &= ~MUTEX_FLAG_HANDOFF;

                 if (__owner_task(owner)) {
                         if (handoff && unlikely(__owner_task(owner) == 
current))
@@ -107,7 +113,7 @@ static inline bool __mutex_trylock(struct mutex 
*lock, const
                 }

                 old = atomic_long_cmpxchg_acquire(&lock->owner, owner,
-                                                 curr | 
__owner_flags(owner));
+                                                 curr | flags);
                 if (old == owner)
                         return true;

@@ -688,7 +694,7 @@ __mutex_lock_common(struct mutex *lock, long state, 
unsigned
                  * state back to RUNNING and fall through the next 
schedule(),
                  * or we must see its unlock and acquire.
                  */
-               if (__mutex_trylock(lock, true))
+               if (__mutex_trylock(lock, first))
                         break;

                 spin_lock_mutex(&lock->wait_lock, flags);
@@ -700,8 +706,6 @@ remove_waiter:
         mutex_remove_waiter(lock, &waiter, task);
         if (likely(list_empty(&lock->wait_list)))
                 __mutex_clear_flag(lock, MUTEX_FLAGS);
-       else if (first && (atomic_long_read(&lock->owner) & 
MUTEX_FLAG_HANDOFF))
-               __mutex_clear_flag(lock, MUTEX_FLAG_HANDOFF);

         debug_mutex_free_waiter(&waiter);


Cheers,
Longman

Re: [RFC][PATCH -v3 10/10] locking/mutex: Implement alternative HANDOFF

[Peter Zijlstra]

On Fri, Sep 09, 2016 at 06:32:04PM -0400, Waiman Long wrote:

> I have another way of catching the uncleared handoff flag. See the following
> code to see if you think that will work.
> 
> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> index 9492494..362ff83 100644
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -85,7 +85,13 @@ static inline bool __mutex_trylock(struct mutex *lock,
> const
> 
>         owner = atomic_long_read(&lock->owner);
>         for (;;) { /* must loop, can race against a flag */
> -               unsigned long old;
> +               unsigned long old, flags = __owner_flags(owner);
> +
> +               /*
> +                * We don't need to keep the HANDOFF flag for the waiter.
> +                */
> +               if (handoff)
> +                       flags &= ~MUTEX_FLAG_HANDOFF;
> 
>                 if (__owner_task(owner)) {
>                         if (handoff && unlikely(__owner_task(owner) == current))

I placed this condition below the __owner_task() branch.

> @@ -688,7 +694,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned
>                  * state back to RUNNING and fall through the next schedule(),
>                  * or we must see its unlock and acquire.
>                  */
> -               if (__mutex_trylock(lock, true))
> +               if (__mutex_trylock(lock, first))
>                         break;
> 
>                 spin_lock_mutex(&lock->wait_lock, flags);

Hmm, yes. I think that works.

We (the first waiter) set the flag, we clear it on try-lock, or unlock
clears it when it hands the thing off.

Much simpler. Thanks!

Re: [PATCH -v3 07/10] mutex: Restructure wait loop

[Peter Zijlstra]

On Fri, Sep 09, 2016 at 04:32:39PM -0400, Waiman Long wrote:

> >I think you need to remove the HANDOFF flag here in the error path too.
> >Maybe you should fix that in patch 6.
> >
> >It is also possible that __mutex_handoff() has been called at this point.
> >So this task may now be the owner of the lock. Maybe you should do a final
> >trylock here.
> 
> Alternatively, we can move the trylock in the main loop after the
> spin_lock_mutex(). In this case, we don't need an extra trylock in the error
> path.

I did something like so..

--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -629,12 +629,12 @@ __mutex_lock_common(struct mutex *lock,
 	if (__mutex_waiter_is_first(lock, &waiter))
 		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
 
-	if (__mutex_trylock(lock, false))
-		goto remove_waiter;
-
 	lock_contended(&lock->dep_map, ip);
 
 	for (;;) {
+		if (__mutex_trylock(lock, first))
+			break;
+
 		/*
 		 * got a signal? (This code gets eliminated in the
 		 * TASK_UNINTERRUPTIBLE case.)
@@ -659,13 +659,9 @@ __mutex_lock_common(struct mutex *lock,
 			first = true;
 			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
 		}
-
-		if (__mutex_trylock(lock, first))
-			break;
 	}
 	__set_task_state(task, TASK_RUNNING);
 
-remove_waiter:
 	mutex_remove_waiter(lock, &waiter, task);
 	if (likely(list_empty(&lock->wait_list)))
 		__mutex_clear_flag(lock, MUTEX_FLAGS);