locking/percpu-rwsem: Add down_read_preempt_disable()

Provide a down_read()/up_read() variant that keeps preemption disabled
over the whole thing, when possible.

This avoids a needless preemption point for constructs such as:

	percpu_down_read(&global_rwsem);
	spin_lock(&lock);
	...
	spin_unlock(&lock);
	percpu_up_read(&global_rwsem);

Which perturbs timings. In particular it was found to cure a
performance regression in a follow up patch in fs/locks.c

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index d402d39..5b2e615 100644 (file)
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -28,7 +28,7 @@ static struct percpu_rw_semaphore name = {                            \
 extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
 extern void __percpu_up_read(struct percpu_rw_semaphore *);
 
-static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
+static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem)
 {
        might_sleep();
 
@@ -46,13 +46,19 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
        __this_cpu_inc(*sem->read_count);
        if (unlikely(!rcu_sync_is_idle(&sem->rss)))
                __percpu_down_read(sem, false); /* Unconditional memory barrier */
-       preempt_enable();
+       barrier();
        /*
-        * The barrier() from preempt_enable() prevents the compiler from
+        * The barrier() prevents the compiler from
         * bleeding the critical section out.
         */
 }
 
+static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
+{
+       percpu_down_read_preempt_disable(sem);
+       preempt_enable();
+}
+
 static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
        int ret = 1;
@@ -76,13 +82,13 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
        return ret;
 }
 
-static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
+static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem)
 {
        /*
-        * The barrier() in preempt_disable() prevents the compiler from
+        * The barrier() prevents the compiler from
         * bleeding the critical section out.
         */
-       preempt_disable();
+       barrier();
        /*
         * Same as in percpu_down_read().
         */
@@ -95,6 +101,12 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
        rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);
 }
 
+static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
+{
+       preempt_disable();
+       percpu_up_read_preempt_enable(sem);
+}
+
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);