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

Pull more locking changes from Ingo Molnar:
 "This is the second round of locking tree updates for v3.16, offering
  large system scalability improvements:

 - optimistic spinning for rwsems, from Davidlohr Bueso.

 - 'qrwlocks' core code and x86 enablement, from Waiman Long and PeterZ"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, locking/rwlocks: Enable qrwlocks on x86
  locking/rwlocks: Introduce 'qrwlocks' - fair, queued rwlocks
  locking/mutexes: Documentation update/rewrite
  locking/rwsem: Fix checkpatch.pl warnings
  locking/rwsem: Fix warnings for CONFIG_RWSEM_GENERIC_SPINLOCK
  locking/rwsem: Support optimistic spinning

3 files changed, 209 insertions, 3 deletions

diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
new file mode 100644
index 000000000000..6383d54bf983
--- /dev/null
+++ b/include/asm-generic/qrwlock.h
@@ -0,0 +1,166 @@
+/*
+ * Queue read/write lock
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QRWLOCK_H
+#define __ASM_GENERIC_QRWLOCK_H
+
+#include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
+#include <asm-generic/qrwlock_types.h>
+
+/*
+ * Writer states & reader shift and bias
+ */
+#define	_QW_WAITING	1		/* A writer is waiting	   */
+#define	_QW_LOCKED	0xff		/* A writer holds the lock */
+#define	_QW_WMASK	0xff		/* Writer mask		   */
+#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define _QR_BIAS	(1U << _QR_SHIFT)
+
+/*
+ * External function declarations
+ */
+extern void queue_read_lock_slowpath(struct qrwlock *lock);
+extern void queue_write_lock_slowpath(struct qrwlock *lock);
+
+/**
+ * queue_read_can_lock- would read_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_read_can_lock(struct qrwlock *lock)
+{
+	return !(atomic_read(&lock->cnts) & _QW_WMASK);
+}
+
+/**
+ * queue_write_can_lock- would write_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_write_can_lock(struct qrwlock *lock)
+{
+	return !atomic_read(&lock->cnts);
+}
+
+/**
+ * queue_read_trylock - try to acquire read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_read_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (likely(!(cnts & _QW_WMASK))) {
+		cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts);
+		if (likely(!(cnts & _QW_WMASK)))
+			return 1;
+		atomic_sub(_QR_BIAS, &lock->cnts);
+	}
+	return 0;
+}
+
+/**
+ * queue_write_trylock - try to acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_write_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (unlikely(cnts))
+		return 0;
+
+	return likely(atomic_cmpxchg(&lock->cnts,
+				     cnts, cnts | _QW_LOCKED) == cnts);
+}
+/**
+ * queue_read_lock - acquire read lock of a queue rwlock
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline void queue_read_lock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_add_return(_QR_BIAS, &lock->cnts);
+	if (likely(!(cnts & _QW_WMASK)))
+		return;
+
+	/* The slowpath will decrement the reader count, if necessary. */
+	queue_read_lock_slowpath(lock);
+}
+
+/**
+ * queue_write_lock - acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_lock(struct qrwlock *lock)
+{
+	/* Optimize for the unfair lock case where the fair flag is 0. */
+	if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)
+		return;
+
+	queue_write_lock_slowpath(lock);
+}
+
+/**
+ * queue_read_unlock - release read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_read_unlock(struct qrwlock *lock)
+{
+	/*
+	 * Atomically decrement the reader count
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QR_BIAS, &lock->cnts);
+}
+
+#ifndef queue_write_unlock
+/**
+ * queue_write_unlock - release write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_unlock(struct qrwlock *lock)
+{
+	/*
+	 * If the writer field is atomic, it can be cleared directly.
+	 * Otherwise, an atomic subtraction will be used to clear it.
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QW_LOCKED, &lock->cnts);
+}
+#endif
+
+/*
+ * Remapping rwlock architecture specific functions to the corresponding
+ * queue rwlock functions.
+ */
+#define arch_read_can_lock(l)	queue_read_can_lock(l)
+#define arch_write_can_lock(l)	queue_write_can_lock(l)
+#define arch_read_lock(l)	queue_read_lock(l)
+#define arch_write_lock(l)	queue_write_lock(l)
+#define arch_read_trylock(l)	queue_read_trylock(l)
+#define arch_write_trylock(l)	queue_write_trylock(l)
+#define arch_read_unlock(l)	queue_read_unlock(l)
+#define arch_write_unlock(l)	queue_write_unlock(l)
+
+#endif /* __ASM_GENERIC_QRWLOCK_H */
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
new file mode 100644
index 000000000000..4d76f24df518
--- /dev/null
+++ b/include/asm-generic/qrwlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_GENERIC_QRWLOCK_TYPES_H
+#define __ASM_GENERIC_QRWLOCK_TYPES_H
+
+#include <linux/types.h>
+#include <asm/spinlock_types.h>
+
+/*
+ * The queue read/write lock data structure
+ */
+
+typedef struct qrwlock {
+	atomic_t		cnts;
+	arch_spinlock_t		lock;
+} arch_rwlock_t;
+
+#define	__ARCH_RW_LOCK_UNLOCKED {		\
+	.cnts = ATOMIC_INIT(0),			\
+	.lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+}
+
+#endif /* __ASM_GENERIC_QRWLOCK_TYPES_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 03f3b05e8ec1..8d79708146aa 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -16,6 +16,7 @@
 
 #include <linux/atomic.h>
 
+struct optimistic_spin_queue;
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -23,9 +24,17 @@ struct rw_semaphore;
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
+	long count;
+	raw_spinlock_t wait_lock;
+	struct list_head wait_list;
+#ifdef CONFIG_SMP
+	/*
+	 * Write owner. Used as a speculative check to see
+	 * if the owner is running on the cpu.
+	 */
+	struct task_struct *owner;
+	struct optimistic_spin_queue *osq; /* spinner MCS lock */
+#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -55,11 +64,21 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
+#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
+#define __RWSEM_INITIALIZER(name)			\
+	{ RWSEM_UNLOCKED_VALUE,				\
+	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
+	  LIST_HEAD_INIT((name).wait_list),		\
+	  NULL, /* owner */				\
+	  NULL /* mcs lock */                           \
+	  __RWSEM_DEP_MAP_INIT(name) }
+#else
 #define __RWSEM_INITIALIZER(name)			\
 	{ RWSEM_UNLOCKED_VALUE,				\
 	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
 	  LIST_HEAD_INIT((name).wait_list)		\
 	  __RWSEM_DEP_MAP_INIT(name) }
+#endif
 
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)