[PATCH v4 0/4] MCS Lock: MCS lock code cleanup and optimizations

[PATCH v4 0/4] MCS Lock: MCS lock code cleanup and optimizations

[Tim Chen]

In this patch series, we separated out the MCS lock code which was
previously embedded in the mutex.c.  This allows for easier reuse of
MCS lock in other places like rwsem and qrwlock.  We also did some micro
optimizations and barrier cleanup.

This patches were previously part of the rwsem optimization patch series
but now we spearate them out.

Tim Chen

v4:
1. Move patch series to the latest tip after v3.12

v3:
1. modified memory barriers to support non x86 architectures that have
weak memory ordering.

v2:
1. change export mcs_spin_lock as a GPL export symbol
2. corrected mcs_spin_lock to references


Jason Low (2):
  MCS Lock: optimizations and extra comments
  MCS Lock: Barrier corrections

Tim Chen (1):
  MCS Lock: Restructure the MCS lock defines and locking code into its
    own file

Waiman Long (2):
  MCS Lock: Make mcs_spinlock.h includable in other files
  MCS Lock: Allow architecture specific memory barrier in lock/unlock

 arch/x86/include/asm/barrier.h |    6 +++
 include/linux/mcs_spinlock.h   |   25 ++++++++++
 include/linux/mutex.h          |    5 +-
 kernel/locking/Makefile        |    6 +-
 kernel/locking/mcs_spinlock.c  |   96 ++++++++++++++++++++++++++++++++++++++++
 kernel/locking/mutex.c         |   60 +++----------------------
 6 files changed, 140 insertions(+), 58 deletions(-)
 create mode 100644 include/linux/mcs_spinlock.h
 create mode 100644 kernel/locking/mcs_spinlock.c

-- 
1.7.4.4

[PATCH v4 1/5] MCS Lock: Restructure the MCS lock defines and locking code into its own file

[Tim Chen]

We will need the MCS lock code for doing optimistic spinning for rwsem
and queue rwlock.  Extracting the MCS code from mutex.c and put into
its own file allow us to reuse this code easily.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
---
 include/linux/mcs_spinlock.h |   64 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mutex.h        |    5 ++-
 kernel/locking/mutex.c       |   60 ++++----------------------------------
 3 files changed, 74 insertions(+), 55 deletions(-)
 create mode 100644 include/linux/mcs_spinlock.h

diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
new file mode 100644
index 0000000..b5de3b0
--- /dev/null
+++ b/include/linux/mcs_spinlock.h
@@ -0,0 +1,64 @@
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+struct mcs_spinlock {
+	struct mcs_spinlock *next;
+	int locked; /* 1 if lock acquired */
+};
+
+/*
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+static noinline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/* Lock acquired */
+		node->locked = 1;
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+	smp_wmb();
+	/* Wait until the lock holder passes the lock down */
+	while (!ACCESS_ONCE(node->locked))
+		arch_mutex_cpu_relax();
+}
+
+static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (cmpxchg(lock, node, NULL) == node)
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	}
+	ACCESS_ONCE(next->locked) = 1;
+	smp_wmb();
+}
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index bab49da..32a32e6 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -46,6 +46,7 @@
  * - detects multi-task circular deadlocks and prints out all affected
  *   locks and tasks (and only those tasks)
  */
+struct mcs_spinlock;
 struct mutex {
 	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
 	atomic_t		count;
@@ -55,7 +56,7 @@ struct mutex {
 	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	void			*spin_mlock;	/* Spinner MCS lock */
+	struct mcs_spinlock	*mcs_lock;	/* Spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
@@ -179,4 +180,4 @@ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 # define arch_mutex_cpu_relax() cpu_relax()
 #endif
 
-#endif
+#endif /* __LINUX_MUTEX_H */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d24105b..e08b183 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/debug_locks.h>
+#include <linux/mcs_spinlock.h>
 
 /*
  * In the DEBUG case we are using the "NULL fastpath" for mutexes,
@@ -52,7 +53,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	lock->spin_mlock = NULL;
+	lock->mcs_lock = NULL;
 #endif
 
 	debug_mutex_init(lock, name, key);
@@ -111,54 +112,7 @@ EXPORT_SYMBOL(mutex_lock);
  * more or less simultaneously, the spinners need to acquire a MCS lock
  * first before spinning on the owner field.
  *
- * We don't inline mspin_lock() so that perf can correctly account for the
- * time spent in this lock function.
  */
-struct mspin_node {
-	struct mspin_node *next ;
-	int		  locked;	/* 1 if lock acquired */
-};
-#define	MLOCK(mutex)	((struct mspin_node **)&((mutex)->spin_mlock))
-
-static noinline
-void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
-{
-	struct mspin_node *prev;
-
-	/* Init node */
-	node->locked = 0;
-	node->next   = NULL;
-
-	prev = xchg(lock, node);
-	if (likely(prev == NULL)) {
-		/* Lock acquired */
-		node->locked = 1;
-		return;
-	}
-	ACCESS_ONCE(prev->next) = node;
-	smp_wmb();
-	/* Wait until the lock holder passes the lock down */
-	while (!ACCESS_ONCE(node->locked))
-		arch_mutex_cpu_relax();
-}
-
-static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
-{
-	struct mspin_node *next = ACCESS_ONCE(node->next);
-
-	if (likely(!next)) {
-		/*
-		 * Release the lock by setting it to NULL
-		 */
-		if (cmpxchg(lock, node, NULL) == node)
-			return;
-		/* Wait until the next pointer is set */
-		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
-	}
-	ACCESS_ONCE(next->locked) = 1;
-	smp_wmb();
-}
 
 /*
  * Mutex spinning code migrated from kernel/sched/core.c
@@ -448,7 +402,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	for (;;) {
 		struct task_struct *owner;
-		struct mspin_node  node;
+		struct mcs_spinlock  node;
 
 		if (use_ww_ctx && ww_ctx->acquired > 0) {
 			struct ww_mutex *ww;
@@ -470,10 +424,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		mspin_lock(MLOCK(lock), &node);
+		mcs_spin_lock(&lock->mcs_lock, &node);
 		owner = ACCESS_ONCE(lock->owner);
 		if (owner && !mutex_spin_on_owner(lock, owner)) {
-			mspin_unlock(MLOCK(lock), &node);
+			mcs_spin_unlock(&lock->mcs_lock, &node);
 			goto slowpath;
 		}
 
@@ -488,11 +442,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			}
 
 			mutex_set_owner(lock);
-			mspin_unlock(MLOCK(lock), &node);
+			mcs_spin_unlock(&lock->mcs_lock, &node);
 			preempt_enable();
 			return 0;
 		}
-		mspin_unlock(MLOCK(lock), &node);
+		mcs_spin_unlock(&lock->mcs_lock, &node);
 
 		/*
 		 * When there's no owner, we might have preempted between the
-- 
1.7.4.4

[PATCH v4 2/5] MCS Lock: optimizations and extra comments

[Tim Chen]

Remove unnecessary operation and make the cmpxchg(lock, node, NULL) == node
check in mcs_spin_unlock() likely() as it is likely that a race did not occur
most of the time.

Also add in more comments describing how the local node is used in MCS locks.

Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Jason Low <jason.low2@hp.com>
---
 include/linux/mcs_spinlock.h |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
index b5de3b0..96f14299 100644
--- a/include/linux/mcs_spinlock.h
+++ b/include/linux/mcs_spinlock.h
@@ -18,6 +18,12 @@ struct mcs_spinlock {
 };
 
 /*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ *
  * We don't inline mcs_spin_lock() so that perf can correctly account for the
  * time spent in this lock function.
  */
@@ -33,7 +39,6 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	prev = xchg(lock, node);
 	if (likely(prev == NULL)) {
 		/* Lock acquired */
-		node->locked = 1;
 		return;
 	}
 	ACCESS_ONCE(prev->next) = node;
@@ -43,6 +48,10 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 		arch_mutex_cpu_relax();
 }
 
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
 static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 {
 	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
@@ -51,7 +60,7 @@ static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *nod
 		/*
 		 * Release the lock by setting it to NULL
 		 */
-		if (cmpxchg(lock, node, NULL) == node)
+		if (likely(cmpxchg(lock, node, NULL) == node))
 			return;
 		/* Wait until the next pointer is set */
 		while (!(next = ACCESS_ONCE(node->next)))
-- 
1.7.4.4

[PATCH v4 3/5] MCS Lock: Barrier corrections

[Tim Chen]

This patch corrects the way memory barriers are used in the MCS lock
and removes ones that are not needed. Also add comments on all barriers.

Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Jason Low <jason.low2@hp.com>
---
 include/linux/mcs_spinlock.h |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
index 96f14299..93d445d 100644
--- a/include/linux/mcs_spinlock.h
+++ b/include/linux/mcs_spinlock.h
@@ -36,16 +36,19 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	node->locked = 0;
 	node->next   = NULL;
 
+	/* xchg() provides a memory barrier */
 	prev = xchg(lock, node);
 	if (likely(prev == NULL)) {
 		/* Lock acquired */
 		return;
 	}
 	ACCESS_ONCE(prev->next) = node;
-	smp_wmb();
 	/* Wait until the lock holder passes the lock down */
 	while (!ACCESS_ONCE(node->locked))
 		arch_mutex_cpu_relax();
+
+	/* Make sure subsequent operations happen after the lock is acquired */
+	smp_rmb();
 }
 
 /*
@@ -58,6 +61,7 @@ static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *nod
 
 	if (likely(!next)) {
 		/*
+		 * cmpxchg() provides a memory barrier.
 		 * Release the lock by setting it to NULL
 		 */
 		if (likely(cmpxchg(lock, node, NULL) == node))
@@ -65,9 +69,14 @@ static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *nod
 		/* Wait until the next pointer is set */
 		while (!(next = ACCESS_ONCE(node->next)))
 			arch_mutex_cpu_relax();
+	} else {
+		/*
+		 * Make sure all operations within the critical section
+		 * happen before the lock is released.
+		 */
+		smp_wmb();
 	}
 	ACCESS_ONCE(next->locked) = 1;
-	smp_wmb();
 }
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
-- 
1.7.4.4

[PATCH v4 4/5] MCS Lock: Make mcs_spinlock.h includable in other files

[Tim Chen]

The following changes are made to enable mcs_spinlock.h file to be
widely included in other files without causing problem:

1) Include a number of prerequisite header files and define
   arch_mutex_cpu_relax(), if not previously defined.
2) Make mcs_spin_unlock() an inlined function and
   rename mcs_spin_lock() to _raw_mcs_spin_lock() which is also an
   inlined function.
3) Create a new mcs_spinlock.c file to contain the non-inlined
   mcs_spin_lock() function.

Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
 include/linux/mcs_spinlock.h  |   27 ++++++++++++++++++++++-----
 kernel/locking/Makefile       |    6 +++---
 kernel/locking/mcs_spinlock.c |   21 +++++++++++++++++++++
 3 files changed, 46 insertions(+), 8 deletions(-)
 create mode 100644 kernel/locking/mcs_spinlock.c

diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
index 93d445d..f2c71e8 100644
--- a/include/linux/mcs_spinlock.h
+++ b/include/linux/mcs_spinlock.h
@@ -12,11 +12,27 @@
 #ifndef __LINUX_MCS_SPINLOCK_H
 #define __LINUX_MCS_SPINLOCK_H
 
+/*
+ * asm/processor.h may define arch_mutex_cpu_relax().
+ * If it is not defined, cpu_relax() will be used.
+ */
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
+
+#ifndef arch_mutex_cpu_relax
+# define arch_mutex_cpu_relax() cpu_relax()
+#endif
+
 struct mcs_spinlock {
 	struct mcs_spinlock *next;
 	int locked; /* 1 if lock acquired */
 };
 
+extern
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node);
+
 /*
  * In order to acquire the lock, the caller should declare a local node and
  * pass a reference of the node to this function in addition to the lock.
@@ -24,11 +40,11 @@ struct mcs_spinlock {
  * on this node->locked until the previous lock holder sets the node->locked
  * in mcs_spin_unlock().
  *
- * We don't inline mcs_spin_lock() so that perf can correctly account for the
- * time spent in this lock function.
+ * The _raw_mcs_spin_lock() function should not be called directly. Instead,
+ * users should call mcs_spin_lock().
  */
-static noinline
-void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+static inline
+void _raw_mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 {
 	struct mcs_spinlock *prev;
 
@@ -55,7 +71,8 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
  * Releases the lock. The caller should pass in the corresponding node that
  * was used to acquire the lock.
  */
-static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 {
 	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index baab8e5..20d9d5c 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -13,12 +13,12 @@ obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
 endif
-obj-$(CONFIG_SMP) += spinlock.o
-obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_SMP) += spinlock.o mcs_spinlock.o
+obj-$(CONFIG_PROVE_LOCKING) += spinlock.o mcs_spinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
-obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o mcs_spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
new file mode 100644
index 0000000..3c55626
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.c
@@ -0,0 +1,21 @@
+/*
+ * MCS lock
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#include <linux/mcs_spinlock.h>
+#include <linux/export.h>
+
+/*
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	_raw_mcs_spin_lock(lock, node);
+}
+EXPORT_SYMBOL_GPL(mcs_spin_lock);
-- 
1.7.4.4

[PATCH v4 5/5] MCS Lock: Allow architecture specific memory barrier in lock/unlock

[Tim Chen]

This patch moves the decision of what kind of memory barriers to be
used in the MCS lock and unlock functions to the architecture specific
layer. It also moves the actual lock/unlock code to mcs_spinlock.c
file.

A full memory barrier will be used if the following macros are not
defined:
 1) smp_mb__before_critical_section()
 2) smp_mb__after_critical_section()

For the x86 architecture, only compiler barrier will be needed.

Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
---
 arch/x86/include/asm/barrier.h |    6 +++
 include/linux/mcs_spinlock.h   |   78 +-------------------------------------
 kernel/locking/mcs_spinlock.c  |   81 ++++++++++++++++++++++++++++++++++++++-
 3 files changed, 86 insertions(+), 79 deletions(-)

diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index c6cd358..6d0172c 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -92,6 +92,12 @@
 #endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#if !defined(CONFIG_X86_PPRO_FENCE) && !defined(CONFIG_X86_OOSTORE)
+# define smp_mb__before_critical_section()	barrier()
+# define smp_mb__after_critical_section()	barrier()
+#endif
+
 #else
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
index f2c71e8..d54bb23 100644
--- a/include/linux/mcs_spinlock.h
+++ b/include/linux/mcs_spinlock.h
@@ -12,19 +12,6 @@
 #ifndef __LINUX_MCS_SPINLOCK_H
 #define __LINUX_MCS_SPINLOCK_H
 
-/*
- * asm/processor.h may define arch_mutex_cpu_relax().
- * If it is not defined, cpu_relax() will be used.
- */
-#include <asm/barrier.h>
-#include <asm/cmpxchg.h>
-#include <asm/processor.h>
-#include <linux/compiler.h>
-
-#ifndef arch_mutex_cpu_relax
-# define arch_mutex_cpu_relax() cpu_relax()
-#endif
-
 struct mcs_spinlock {
 	struct mcs_spinlock *next;
 	int locked; /* 1 if lock acquired */
@@ -32,68 +19,7 @@ struct mcs_spinlock {
 
 extern
 void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node);
-
-/*
- * In order to acquire the lock, the caller should declare a local node and
- * pass a reference of the node to this function in addition to the lock.
- * If the lock has already been acquired, then this will proceed to spin
- * on this node->locked until the previous lock holder sets the node->locked
- * in mcs_spin_unlock().
- *
- * The _raw_mcs_spin_lock() function should not be called directly. Instead,
- * users should call mcs_spin_lock().
- */
-static inline
-void _raw_mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
-{
-	struct mcs_spinlock *prev;
-
-	/* Init node */
-	node->locked = 0;
-	node->next   = NULL;
-
-	/* xchg() provides a memory barrier */
-	prev = xchg(lock, node);
-	if (likely(prev == NULL)) {
-		/* Lock acquired */
-		return;
-	}
-	ACCESS_ONCE(prev->next) = node;
-	/* Wait until the lock holder passes the lock down */
-	while (!ACCESS_ONCE(node->locked))
-		arch_mutex_cpu_relax();
-
-	/* Make sure subsequent operations happen after the lock is acquired */
-	smp_rmb();
-}
-
-/*
- * Releases the lock. The caller should pass in the corresponding node that
- * was used to acquire the lock.
- */
-static inline
-void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
-{
-	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
-
-	if (likely(!next)) {
-		/*
-		 * cmpxchg() provides a memory barrier.
-		 * Release the lock by setting it to NULL
-		 */
-		if (likely(cmpxchg(lock, node, NULL) == node))
-			return;
-		/* Wait until the next pointer is set */
-		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
-	} else {
-		/*
-		 * Make sure all operations within the critical section
-		 * happen before the lock is released.
-		 */
-		smp_wmb();
-	}
-	ACCESS_ONCE(next->locked) = 1;
-}
+extern
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node);
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index 3c55626..2dfd207 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -7,15 +7,90 @@
  * It avoids expensive cache bouncings that common test-and-set spin-lock
  * implementations incur.
  */
+/*
+ * asm/processor.h may define arch_mutex_cpu_relax().
+ * If it is not defined, cpu_relax() will be used.
+ */
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
 #include <linux/mcs_spinlock.h>
 #include <linux/export.h>
 
+#ifndef arch_mutex_cpu_relax
+# define arch_mutex_cpu_relax() cpu_relax()
+#endif
+
 /*
- * We don't inline mcs_spin_lock() so that perf can correctly account for the
- * time spent in this lock function.
+ * Fall back to use full memory barrier if those macros are not defined
+ * in a architecture specific header file.
+ */
+#ifndef smp_mb__before_critical_section
+#define	smp_mb__before_critical_section()	smp_mb()
+#endif
+
+#ifndef smp_mb__after_critical_section
+#define	smp_mb__after_critical_section()	smp_mb()
+#endif
+
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
  */
 void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 {
-	_raw_mcs_spin_lock(lock, node);
+	struct mcs_spinlock *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	/* xchg() provides a memory barrier */
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/* Lock acquired */
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+	/* Wait until the lock holder passes the lock down */
+	while (!ACCESS_ONCE(node->locked))
+		arch_mutex_cpu_relax();
+
+	/* Make sure subsequent operations happen after the lock is acquired */
+	smp_mb__before_critical_section();
 }
 EXPORT_SYMBOL_GPL(mcs_spin_lock);
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * cmpxchg() provides a memory barrier.
+		 * Release the lock by setting it to NULL
+		 */
+		if (likely(cmpxchg(lock, node, NULL) == node))
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	} else {
+		/*
+		 * Make sure all operations within the critical section
+		 * happen before the lock is released.
+		 */
+		smp_mb__after_critical_section();
+	}
+	ACCESS_ONCE(next->locked) = 1;
+}
+EXPORT_SYMBOL_GPL(mcs_spin_unlock);
-- 
1.7.4.4