locking/spinlocks/mcs: Convert osq lock to atomic_t to reduce overhead

The cancellable MCS spinlock is currently used to queue threads that are
doing optimistic spinning. It uses per-cpu nodes, where a thread obtaining
the lock would access and queue the local node corresponding to the CPU that
it's running on. Currently, the cancellable MCS lock is implemented by using
pointers to these nodes.

In this patch, instead of operating on pointers to the per-cpu nodes, we
store the CPU numbers in which the per-cpu nodes correspond to in atomic_t.
A similar concept is used with the qspinlock.

By operating on the CPU # of the nodes using atomic_t instead of pointers
to those nodes, this can reduce the overhead of the cancellable MCS spinlock
by 32 bits (on 64 bit systems).

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Waiman Long <waiman.long@hp.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chris Mason <clm@fb.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Link: http://lkml.kernel.org/r/1405358872-3732-3-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 44 insertions, 11 deletions

diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index e9866f70e828..32fc16c0a545 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -17,18 +17,44 @@
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
 
 /*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+        return cpu_nr + 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+        int cpu_nr = encoded_cpu_val - 1;
+
+        return per_cpu_ptr(&osq_node, cpu_nr);
+}
+
+/*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
  */
 static inline struct optimistic_spin_node *
-osq_wait_next(struct optimistic_spin_node **lock,
+osq_wait_next(struct optimistic_spin_queue *lock,
               struct optimistic_spin_node *node,
               struct optimistic_spin_node *prev)
 {
         struct optimistic_spin_node *next = NULL;
+        int curr = encode_cpu(smp_processor_id());
+        int old;
+
+        /*
+         * If there is a prev node in queue, then the 'old' value will be
+         * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
+         * we're currently last in queue, then the queue will then become empty.
+         */
+        old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
         for (;;) {
-                if (*lock == node && cmpxchg(lock, node, prev) == node) {
+                if (atomic_read(&lock->tail) == curr &&
+                    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
                         /*
                          * We were the last queued, we moved @lock back. @prev
                          * will now observe @lock and will complete its
@@ -59,18 +85,23 @@ osq_wait_next(struct optimistic_spin_node **lock,
         return next;
 }
 
-bool osq_lock(struct optimistic_spin_node **lock)
+bool osq_lock(struct optimistic_spin_queue *lock)
 {
         struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
         struct optimistic_spin_node *prev, *next;
+        int curr = encode_cpu(smp_processor_id());
+        int old;
 
         node->locked = 0;
         node->next = NULL;
+        node->cpu = curr;
 
-        node->prev = prev = xchg(lock, node);
-        if (likely(prev == NULL))
+        old = atomic_xchg(&lock->tail, curr);
+        if (old == OSQ_UNLOCKED_VAL)
                 return true;
 
+        prev = decode_cpu(old);
+        node->prev = prev;
         ACCESS_ONCE(prev->next) = node;
 
         /*
@@ -149,15 +180,16 @@ unqueue:
         return false;
 }
 
-void osq_unlock(struct optimistic_spin_node **lock)
+void osq_unlock(struct optimistic_spin_queue *lock)
 {
         struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
         struct optimistic_spin_node *next;
+        int curr = encode_cpu(smp_processor_id());
 
         /*
          * Fast path for the uncontended case.
          */
-        if (likely(cmpxchg(lock, node, NULL) == node))
+        if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
                 return;
 
         /*
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index c99dc0052f49..74356dc0ce29 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -121,9 +121,10 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 struct optimistic_spin_node {
         struct optimistic_spin_node *next, *prev;
         int locked; /* 1 if lock acquired */
+        int cpu; /* encoded CPU # value */
 };
 
-extern bool osq_lock(struct optimistic_spin_node **lock);
-extern void osq_unlock(struct optimistic_spin_node **lock);
+extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern void osq_unlock(struct optimistic_spin_queue *lock);
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index bc73d33c6760..d9b313906caa 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -60,7 +60,7 @@ __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->osq = NULL;
+        atomic_set(&lock->osq.tail, OSQ_UNLOCKED_VAL);
 #endif
 
         debug_mutex_init(lock, name, key);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index c40c7d28661d..b77a6230bbf6 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -84,7 +84,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
         INIT_LIST_HEAD(&sem->wait_list);
 #ifdef CONFIG_SMP
         sem->owner = NULL;
-        sem->osq = NULL;
+        atomic_set(&sem->osq.tail, OSQ_UNLOCKED_VAL);
 #endif
 }