Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Waiman Long <longman@redhat.com>
To:     Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Will Deacon <will.deacon@arm.com>,
        Thomas Gleixner <tglx@linutronix.de>
Cc:     linux-kernel@vger.kernel.org, x86@kernel.org,
        Davidlohr Bueso <dave@stgolabs.net>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        huang ying <huang.ying.caritas@gmail.com>,
        Waiman Long <longman@redhat.com>
Subject: [PATCH v4 16/16] locking/rwsem: Remove redundant computation of writer lock word
Date:   Sat, 13 Apr 2019 13:22:59 -0400
Message-Id: <20190413172259.2740-17-longman@redhat.com>
In-Reply-To: <20190413172259.2740-1-longman@redhat.com>
References: <20190413172259.2740-1-longman@redhat.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 64-bit architectures, each rwsem writer will have its unique lock
word for acquiring the lock. Right now, the writer code recomputes the
lock word every time it tries to acquire the lock. This is a waste of
time. The lock word is now cached and reused when it is needed.

On 32-bit architectures, the extra constant argument to
rwsem_try_write_lock() and rwsem_try_write_lock_unqueued() should be
optimized out by the compiler.

Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/locking/rwsem.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 27219abb8bb6..2c8187690c7c 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -561,6 +561,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
  * bit is set or the lock is acquired.
  */
 static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem,
+					const long wlock,
 					enum writer_wait_state wstate)
 {
 	long new;
@@ -581,7 +582,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem,
 	if ((wstate == WRITER_NOT_FIRST) && RWSEM_COUNT_HANDOFF(count))
 		return false;
 
-	new = (count & ~RWSEM_FLAG_HANDOFF) + RWSEM_WRITER_LOCKED -
+	new = (count & ~RWSEM_FLAG_HANDOFF) + wlock -
 	      (list_is_singular(&sem->wait_list) ? RWSEM_FLAG_WAITERS : 0);
 
 	if (atomic_long_try_cmpxchg_acquire(&sem->count, &count, new)) {
@@ -623,13 +624,14 @@ static inline bool rwsem_try_read_lock_unqueued(struct rw_semaphore *sem)
 /*
  * Try to acquire write lock before the writer has been put on wait queue.
  */
-static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
+static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem,
+						 const long wlock)
 {
 	long count = atomic_long_read(&sem->count);
 
 	while (!RWSEM_COUNT_LOCKED_OR_HANDOFF(count)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
-					count + RWSEM_WRITER_LOCKED)) {
+						    count + wlock)) {
 			rwsem_set_owner(sem);
 			lockevent_inc(rwsem_opt_wlock);
 			return true;
@@ -779,7 +781,7 @@ static inline u64 rwsem_rspin_threshold(struct rw_semaphore *sem)
 		: 25 * NSEC_PER_USEC);
 }
 
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem, const long wlock)
 {
 	bool taken = false;
 	bool is_rt_task = rt_task(current);
@@ -808,7 +810,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
 		/*
 		 * Try to acquire the lock
 		 */
-		taken = wlock ? rwsem_try_write_lock_unqueued(sem)
+		taken = wlock ? rwsem_try_write_lock_unqueued(sem, wlock)
 			      : rwsem_try_read_lock_unqueued(sem);
 
 		if (taken)
@@ -887,7 +889,8 @@ 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)
+static inline bool rwsem_optimistic_spin(struct rw_semaphore *sem,
+					 const long wlock)
 {
 	return false;
 }
@@ -944,7 +947,7 @@ __rwsem_down_read_failed_common(struct rw_semaphore *sem, int state, long count)
 	 */
 	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
 	adjustment = 0;
-	if (rwsem_optimistic_spin(sem, false)) {
+	if (rwsem_optimistic_spin(sem, 0)) {
 		unsigned long flags;
 
 		/*
@@ -1058,10 +1061,11 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	struct rwsem_waiter waiter;
 	struct rw_semaphore *ret = sem;
 	DEFINE_WAKE_Q(wake_q);
+	const long wlock = RWSEM_WRITER_LOCKED;
 
 	/* do optimistic spinning and steal lock if possible */
 	if (rwsem_can_spin_on_owner(sem) &&
-	    rwsem_optimistic_spin(sem, true))
+	    rwsem_optimistic_spin(sem, wlock))
 		return sem;
 
 	/*
@@ -1120,7 +1124,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
 	while (true) {
-		if (rwsem_try_write_lock(count, sem, wstate))
+		if (rwsem_try_write_lock(count, sem, wlock, wstate))
 			break;
 
 		raw_spin_unlock_irq(&sem->wait_lock);
-- 
2.18.1