2 files changed, 115 insertions, 2 deletions

diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h
new file mode 100644
index 000000000000..e9a4d74c63dc
--- /dev/null
+++ b/include/linux/mcs_spinlock.h
@@ -0,0 +1,112 @@
+/*
+ * 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 */
+};
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_load_acquire() provides a memory barrier that ensures
+ * subsequent operations happen after the lock is acquired.
+ */
+#define arch_mcs_spin_lock_contended(l)                                 \
+do {                                                                    \
+        while (!(smp_load_acquire(l)))                                  \
+                arch_mutex_cpu_relax();                                 \
+} while (0)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l)                               \
+        smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * 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.
+ */
+static inline
+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, don't need to set node->locked to 1. Threads
+                 * only spin on its own node->locked value for lock acquisition.
+                 * However, since this thread can immediately acquire the lock
+                 * and does not proceed to spin on its own node->locked, this
+                 * value won't be used. If a debug mode is needed to
+                 * audit lock status, then set node->locked value here.
+                 */
+                return;
+        }
+        ACCESS_ONCE(prev->next) = node;
+
+        /* Wait until the lock holder passes the lock down. */
+        arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * 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)) {
+                /*
+                 * 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();
+        }
+
+        /* Pass lock to next waiter. */
+        arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index d3181936c138..c482e1d2cc49 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 */