1 files changed, 45 insertions, 18 deletions

diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2f7cc4076f50..e4ad019e23f5 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -14,8 +14,9 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/sched/rt.h>
+#include <linux/osq_lock.h>
 
-#include "mcs_spinlock.h"
+#include "rwsem.h"
 
 /*
  * Guide to the rw_semaphore's count field for common values.
@@ -186,6 +187,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 		waiter = list_entry(next, struct rwsem_waiter, list);
 		next = waiter->list.next;
 		tsk = waiter->task;
+		/*
+		 * Make sure we do not wakeup the next reader before
+		 * setting the nil condition to grant the next reader;
+		 * otherwise we could miss the wakeup on the other
+		 * side and end up sleeping again. See the pairing
+		 * in rwsem_down_read_failed().
+		 */
 		smp_mb();
 		waiter->task = NULL;
 		wake_up_process(tsk);
@@ -258,6 +266,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 		    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
 		if (!list_is_singular(&sem->wait_list))
 			rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+		rwsem_set_owner(sem);
 		return true;
 	}
 
@@ -277,8 +286,10 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 			return false;
 
 		old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS);
-		if (old == count)
+		if (old == count) {
+			rwsem_set_owner(sem);
 			return true;
+		}
 
 		count = old;
 	}
@@ -287,23 +298,30 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner;
-	bool on_cpu = false;
+	bool ret = true;
 
 	if (need_resched())
 		return false;
 
 	rcu_read_lock();
 	owner = ACCESS_ONCE(sem->owner);
-	if (owner)
-		on_cpu = owner->on_cpu;
-	rcu_read_unlock();
+	if (!owner) {
+		long count = ACCESS_ONCE(sem->count);
+		/*
+		 * If sem->owner is not set, yet we have just recently entered the
+		 * slowpath with the lock being active, then there is a possibility
+		 * reader(s) may have the lock. To be safe, bail spinning in these
+		 * situations.
+		 */
+		if (count & RWSEM_ACTIVE_MASK)
+			ret = false;
+		goto done;
+	}
 
-	/*
-	 * If sem->owner is not set, yet we have just recently entered the
-	 * slowpath, then there is a possibility reader(s) may have the lock.
-	 * To be safe, avoid spinning in these situations.
-	 */
-	return on_cpu;
+	ret = owner->on_cpu;
+done:
+	rcu_read_unlock();
+	return ret;
 }
 
 static inline bool owner_running(struct rw_semaphore *sem,
@@ -326,21 +344,30 @@ static inline bool owner_running(struct rw_semaphore *sem,
 static noinline
 bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
 {
+	long count;
+
 	rcu_read_lock();
 	while (owner_running(sem, owner)) {
-		if (need_resched())
-			break;
+		/* abort spinning when need_resched */
+		if (need_resched()) {
+			rcu_read_unlock();
+			return false;
+		}
 
 		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
 
+	if (READ_ONCE(sem->owner))
+		return true; /* new owner, continue spinning */
+
 	/*
-	 * We break out the loop above on need_resched() or when the
-	 * owner changed, which is a sign for heavy contention. Return
-	 * success only when sem->owner is NULL.
+	 * When the owner is not set, the lock could be free or
+	 * held by readers. Check the counter to verify the
+	 * state.
 	 */
-	return sem->owner == NULL;
+	count = READ_ONCE(sem->count);
+	return (count == 0 || count == RWSEM_WAITING_BIAS);
 }
 
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)