1 files changed, 134 insertions, 112 deletions

diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index fbe96341beee..0b1f77957240 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -130,6 +130,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 {
 	struct rwsem_waiter *waiter, *tmp;
 	long oldcount, woken = 0, adjustment = 0;
+	struct list_head wlist;
 
 	/*
 	 * Take a peek at the queue head waiter such that we can determine
@@ -147,6 +148,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			 * will notice the queued writer.
 			 */
 			wake_q_add(wake_q, waiter->task);
+			lockevent_inc(rwsem_wake_writer);
 		}
 
 		return;
@@ -176,9 +178,8 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			goto try_reader_grant;
 		}
 		/*
-		 * It is not really necessary to set it to reader-owned here,
-		 * but it gives the spinners an early indication that the
-		 * readers now have the lock.
+		 * Set it to reader-owned to give spinners an early
+		 * indication that readers now have the lock.
 		 */
 		__rwsem_set_reader_owned(sem, waiter->task);
 	}
@@ -188,33 +189,28 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 	 * of the queue. We know that woken will be at least 1 as we accounted
 	 * for above. Note we increment the 'active part' of the count by the
 	 * number of readers before waking any processes up.
+	 *
+	 * We have to do wakeup in 2 passes to prevent the possibility that
+	 * the reader count may be decremented before it is incremented. It
+	 * is because the to-be-woken waiter may not have slept yet. So it
+	 * may see waiter->task got cleared, finish its critical section and
+	 * do an unlock before the reader count increment.
+	 *
+	 * 1) Collect the read-waiters in a separate list, count them and
+	 *    fully increment the reader count in rwsem.
+	 * 2) For each waiters in the new list, clear waiter->task and
+	 *    put them into wake_q to be woken up later.
 	 */
-	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
-		struct task_struct *tsk;
-
+	list_for_each_entry(waiter, &sem->wait_list, list) {
 		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
 			break;
 
 		woken++;
-		tsk = waiter->task;
-
-		get_task_struct(tsk);
-		list_del(&waiter->list);
-		/*
-		 * Ensure calling get_task_struct() before setting the reader
-		 * waiter to nil such that rwsem_down_read_failed() cannot
-		 * race with do_exit() by always holding a reference count
-		 * to the task to wakeup.
-		 */
-		smp_store_release(&waiter->task, NULL);
-		/*
-		 * Ensure issuing the wakeup (either by us or someone else)
-		 * after setting the reader waiter to nil.
-		 */
-		wake_q_add_safe(wake_q, tsk);
 	}
+	list_cut_before(&wlist, &sem->wait_list, &waiter->list);
 
 	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	lockevent_cond_inc(rwsem_wake_reader, woken);
 	if (list_empty(&sem->wait_list)) {
 		/* hit end of list above */
 		adjustment -= RWSEM_WAITING_BIAS;
@@ -222,94 +218,29 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 
 	if (adjustment)
 		atomic_long_add(adjustment, &sem->count);
-}
 
-/*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
-	struct rwsem_waiter waiter;
-	DEFINE_WAKE_Q(wake_q);
+	/* 2nd pass */
+	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
+		struct task_struct *tsk;
 
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
+		tsk = waiter->task;
+		get_task_struct(tsk);
 
-	raw_spin_lock_irq(&sem->wait_lock);
-	if (list_empty(&sem->wait_list)) {
 		/*
-		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer, this reader can exit the slowpath and return
-		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
-		 * been set in the count.
+		 * Ensure calling get_task_struct() before setting the reader
+		 * waiter to nil such that rwsem_down_read_failed() cannot
+		 * race with do_exit() by always holding a reference count
+		 * to the task to wakeup.
 		 */
-		if (atomic_long_read(&sem->count) >= 0) {
-			raw_spin_unlock_irq(&sem->wait_lock);
-			return sem;
-		}
-		adjustment += RWSEM_WAITING_BIAS;
-	}
-	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 there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (count == RWSEM_WAITING_BIAS ||
-	    (count > RWSEM_WAITING_BIAS &&
-	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	/* wait to be given the lock */
-	while (true) {
-		set_current_state(state);
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current)) {
-			raw_spin_lock_irq(&sem->wait_lock);
-			if (waiter.task)
-				goto out_nolock;
-			raw_spin_unlock_irq(&sem->wait_lock);
-			break;
-		}
-		schedule();
+		smp_store_release(&waiter->task, NULL);
+		/*
+		 * Ensure issuing the wakeup (either by us or someone else)
+		 * after setting the reader waiter to nil.
+		 */
+		wake_q_add_safe(wake_q, tsk);
 	}
-
-	__set_current_state(TASK_RUNNING);
-	return sem;
-out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	__set_current_state(TASK_RUNNING);
-	return ERR_PTR(-EINTR);
 }
 
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
 /*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the
@@ -346,21 +277,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = atomic_long_read(&sem->count);
-
-	while (true) {
-		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
-			return false;
+	long count = atomic_long_read(&sem->count);
 
-		old = atomic_long_cmpxchg_acquire(&sem->count, count,
-				      count + RWSEM_ACTIVE_WRITE_BIAS);
-		if (old == count) {
+	while (!count || count == RWSEM_WAITING_BIAS) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+					count + RWSEM_ACTIVE_WRITE_BIAS)) {
 			rwsem_set_owner(sem);
+			lockevent_inc(rwsem_opt_wlock);
 			return true;
 		}
-
-		count = old;
 	}
+	return false;
 }
 
 static inline bool owner_on_cpu(struct task_struct *owner)
@@ -481,6 +408,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	osq_unlock(&sem->osq);
 done:
 	preempt_enable();
+	lockevent_cond_inc(rwsem_opt_fail, !taken);
 	return taken;
 }
 
@@ -505,6 +433,97 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
 #endif
 
 /*
+ * Wait for the read lock to be granted
+ */
+static inline struct rw_semaphore __sched *
+__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
+{
+	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+	struct rwsem_waiter waiter;
+	DEFINE_WAKE_Q(wake_q);
+
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list)) {
+		/*
+		 * In case the wait queue is empty and the lock isn't owned
+		 * by a writer, this reader can exit the slowpath and return
+		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
+		 * been set in the count.
+		 */
+		if (atomic_long_read(&sem->count) >= 0) {
+			raw_spin_unlock_irq(&sem->wait_lock);
+			rwsem_set_reader_owned(sem);
+			lockevent_inc(rwsem_rlock_fast);
+			return sem;
+		}
+		adjustment += RWSEM_WAITING_BIAS;
+	}
+	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 there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (count == RWSEM_WAITING_BIAS ||
+	    (count > RWSEM_WAITING_BIAS &&
+	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
+		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_current_state(state);
+		if (!waiter.task)
+			break;
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			break;
+		}
+		schedule();
+		lockevent_inc(rwsem_sleep_reader);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock);
+	return sem;
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list))
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock_fail);
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed);
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed_killable(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed_killable);
+
+/*
  * Wait until we successfully acquire the write lock
  */
 static inline struct rw_semaphore *
@@ -580,6 +599,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 				goto out_nolock;
 
 			schedule();
+			lockevent_inc(rwsem_sleep_writer);
 			set_current_state(state);
 		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
@@ -588,6 +608,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	__set_current_state(TASK_RUNNING);
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
+	lockevent_inc(rwsem_wlock);
 
 	return ret;
 
@@ -601,6 +622,7 @@ out_nolock:
 		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	wake_up_q(&wake_q);
+	lockevent_inc(rwsem_wlock_fail);
 
 	return ERR_PTR(-EINTR);
 }