locking/percpu-rwsem: Use this_cpu_{inc,dec}() for read_count

The __this_cpu*() accessors are (in general) IRQ-unsafe which, given
that percpu-rwsem is a blocking primitive, should be just fine.

However, file_end_write() is used from IRQ context and will cause
load-store issues on architectures where the per-cpu accessors are not
natively irq-safe.

Fix it by using the IRQ-safe this_cpu_*() for operations on
read_count. This will generate more expensive code on a number of
platforms, which might cause a performance regression for some of the
other percpu-rwsem users.

If any such is reported, we can consider alternative solutions.

Fixes: 70fe2f48 ("aio: fix freeze protection of aio writes")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20200915140750.137881-1-houtao1@huawei.com

include/linux/percpu-rwsem.h

@@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 	 * anything we did within this RCU-sched read-size critical section.
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		__percpu_down_read(sem, false); /* Unconditional memory barrier */
 	/*
@@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
 	preempt_enable();
@@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss))) {
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 	} else {
 		/*
 		 * slowpath; reader will only ever wake a single blocked
@@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 		 * aggregate zero, as that is the only time it matters) they
 		 * will also see our critical section.
 		 */
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 		rcuwait_wake_up(&sem->writer);
 	}
 	preempt_enable();

kernel/locking/percpu-rwsem.c

@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);