[PATCH-tip v2 07/12] locking/rwsem: Enable readers spinning on writer

[Waiman Long]

This patch enables readers to optimistically spin on a
rwsem when it is owned by a writer instead of going to sleep
directly.  The rwsem_can_spin_on_owner() function is extracted
out of rwsem_optimistic_spin() and is called directly by
__rwsem_down_read_failed_common() and __rwsem_down_write_failed_common().

With a locking microbenchmark running on 5.1 based kernel, the total
locking rates (in kops/s) on a 8-socket IvyBrige-EX system with equal
numbers of readers and writers before and after the patch were as
follows:

   # of Threads  Pre-patch    Post-patch
   ------------  ---------    ----------
        4          1,674        1,684
        8          1,062        1,074
       16            924          900
       32            300          458
       64            195          208
      128            164          168
      240            149          143

The performance change wasn't significant in this case, but this change
is required by a follow-on patch.

Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/locking/lock_events_list.h |  1 +
 kernel/locking/rwsem-xadd.c       | 88 ++++++++++++++++++++++++++-----
 kernel/locking/rwsem.h            |  3 ++
 3 files changed, 80 insertions(+), 12 deletions(-)

diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index 29e5c52197fa..333ed5fda333 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -56,6 +56,7 @@ LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
 LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
 LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
 LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
+LOCK_EVENT(rwsem_opt_rlock)	/* # of read locks opt-spin acquired	*/
 LOCK_EVENT(rwsem_opt_wlock)	/* # of write locks opt-spin acquired	*/
 LOCK_EVENT(rwsem_opt_fail)	/* # of failed opt-spinnings		*/
 LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 51858554ff0e..1d61c6a5717f 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -246,6 +246,30 @@ rwsem_try_write_lock(long count, struct rw_semaphore *sem, bool first)
 }
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+/*
+ * Try to acquire read lock before the reader is put on wait queue.
+ * Lock acquisition isn't allowed if the rwsem is locked or a writer handoff
+ * is ongoing.
+ */
+static inline bool rwsem_try_read_lock_unqueued(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+
+	if (RWSEM_COUNT_WLOCKED_OR_HANDOFF(count))
+		return false;
+
+	count = atomic_long_fetch_add_acquire(RWSEM_READER_BIAS, &sem->count);
+	if (!RWSEM_COUNT_WLOCKED_OR_HANDOFF(count)) {
+		rwsem_set_reader_owned(sem);
+		lockevent_inc(rwsem_opt_rlock);
+		return true;
+	}
+
+	/* Back out the change */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	return false;
+}
+
 /*
  * Try to acquire write lock before the writer has been put on wait queue.
  */
@@ -280,9 +304,12 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 
 	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
 
-	if (need_resched())
+	if (need_resched()) {
+		lockevent_inc(rwsem_opt_fail);
 		return false;
+	}
 
+	preempt_disable();
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
 	if (owner) {
@@ -290,6 +317,9 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		      owner_on_cpu(owner);
 	}
 	rcu_read_unlock();
+	preempt_enable();
+
+	lockevent_cond_inc(rwsem_opt_fail, !ret);
 	return ret;
 }
 
@@ -359,7 +389,7 @@ static noinline enum owner_state rwsem_spin_on_owner(struct rw_semaphore *sem)
 	return !owner ? OWNER_NULL : OWNER_READER;
 }
 
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
 {
 	bool taken = false;
 	bool is_rt_task = rt_task(current);
@@ -368,9 +398,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	preempt_disable();
 
 	/* sem->wait_lock should not be held when doing optimistic spinning */
-	if (!rwsem_can_spin_on_owner(sem))
-		goto done;
-
 	if (!osq_lock(&sem->osq))
 		goto done;
 
@@ -390,10 +417,11 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		/*
 		 * Try to acquire the lock
 		 */
-		if (rwsem_try_write_lock_unqueued(sem)) {
-			taken = true;
+		taken = wlock ? rwsem_try_write_lock_unqueued(sem)
+			      : rwsem_try_read_lock_unqueued(sem);
+
+		if (taken)
 			break;
-		}
 
 		/*
 		 * An RT task cannot do optimistic spinning if it cannot
@@ -434,7 +462,12 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	return taken;
 }
 #else
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
+{
+	return false;
+}
+
+static inline bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
 {
 	return false;
 }
@@ -460,6 +493,33 @@ __rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
 	struct rwsem_waiter waiter;
 	DEFINE_WAKE_Q(wake_q);
 
+	if (!rwsem_can_spin_on_owner(sem))
+		goto queue;
+
+	/*
+	 * Undo read bias from down_read() and do optimistic spinning.
+	 */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	adjustment = 0;
+	if (rwsem_optimistic_spin(sem, false)) {
+		unsigned long flags;
+
+		/*
+		 * Opportunistically wake up other readers in the wait queue.
+		 * It has another chance of wakeup at unlock time.
+		 */
+		if ((atomic_long_read(&sem->count) & RWSEM_FLAG_WAITERS) &&
+		    raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
+			if (!list_empty(&sem->wait_list))
+				__rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED,
+						  &wake_q);
+			raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+			wake_up_q(&wake_q);
+		}
+		return sem;
+	}
+
+queue:
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
@@ -472,7 +532,7 @@ __rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
 		 * exit the slowpath and return immediately as its
 		 * RWSEM_READER_BIAS has already been set in the count.
 		 */
-		if (!(atomic_long_read(&sem->count) &
+		if (adjustment && !(atomic_long_read(&sem->count) &
 		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
 			raw_spin_unlock_irq(&sem->wait_lock);
 			rwsem_set_reader_owned(sem);
@@ -484,7 +544,10 @@ __rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we're now waiting on the lock, but no longer actively locking */
-	count = atomic_long_add_return(adjustment, &sem->count);
+	if (adjustment)
+		count = atomic_long_add_return(adjustment, &sem->count);
+	else
+		count = atomic_long_read(&sem->count);
 
 	/*
 	 * If there are no active locks, wake the front queued process(es).
@@ -556,7 +619,8 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	DEFINE_WAKE_Q(wake_q);
 
 	/* do optimistic spinning and steal lock if possible */
-	if (rwsem_optimistic_spin(sem))
+	if (rwsem_can_spin_on_owner(sem) &&
+	    rwsem_optimistic_spin(sem, true))
 		return sem;
 
 	/*
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 3ba235491dc1..0a8657fe4bc9 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -65,9 +65,12 @@
 				 RWSEM_FLAG_HANDOFF)
 
 #define RWSEM_COUNT_LOCKED(c)	((c) & RWSEM_LOCK_MASK)
+#define RWSEM_COUNT_WLOCKED(c)	((c) & RWSEM_WRITER_MASK)
 #define RWSEM_COUNT_HANDOFF(c)	((c) & RWSEM_FLAG_HANDOFF)
 #define RWSEM_COUNT_LOCKED_OR_HANDOFF(c)	\
 	((c) & (RWSEM_LOCK_MASK|RWSEM_FLAG_HANDOFF))
+#define RWSEM_COUNT_WLOCKED_OR_HANDOFF(c)	\
+	((c) & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
-- 
2.18.1