[PATCH] rwsem fix

We should merge this backport - it's needed to prevent deadlocks when
dio_complete() does up_read() from IRQ context.  And perhaps other places.

From: David Howells <dhowells@redhat.com>

[PATCH] rwsem: Make rwsems use interrupt disabling spinlocks

The attached patch makes read/write semaphores use interrupt disabling
spinlocks in the slow path, thus rendering the up functions and trylock
functions available for use in interrupt context.  This matches the
regular semaphore behaviour.

I've assumed that the normal down functions must be called with interrupts
enabled (since they might schedule), and used the irq-disabling spinlock
variants that don't save the flags.

Signed-Off-By: David Howells <dhowells@redhat.com>
Tested-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Chris Wright <chrisw@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

2 files changed, 36 insertions, 22 deletions

diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
index 96255f47b1f8..21f0db2c9711 100644
--- a/lib/rwsem-spinlock.c
+++ b/lib/rwsem-spinlock.c
@@ -140,12 +140,12 @@ void fastcall __sched __down_read(struct rw_semaphore *sem)
 
 	rwsemtrace(sem, "Entering __down_read");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irq(&sem->wait_lock);
 
 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity++;
-		spin_unlock(&sem->wait_lock);
+		spin_unlock_irq(&sem->wait_lock);
 		goto out;
 	}
 
@@ -160,7 +160,7 @@ void fastcall __sched __down_read(struct rw_semaphore *sem)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irq(&sem->wait_lock);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -181,10 +181,12 @@ void fastcall __sched __down_read(struct rw_semaphore *sem)
  */
 int fastcall __down_read_trylock(struct rw_semaphore *sem)
 {
+	unsigned long flags;
 	int ret = 0;
+
 	rwsemtrace(sem, "Entering __down_read_trylock");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
@@ -192,7 +194,7 @@ int fastcall __down_read_trylock(struct rw_semaphore *sem)
 		ret = 1;
 	}
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving __down_read_trylock");
 	return ret;
@@ -209,12 +211,12 @@ void fastcall __sched __down_write(struct rw_semaphore *sem)
 
 	rwsemtrace(sem, "Entering __down_write");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irq(&sem->wait_lock);
 
 	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity = -1;
-		spin_unlock(&sem->wait_lock);
+		spin_unlock_irq(&sem->wait_lock);
 		goto out;
 	}
 
@@ -229,7 +231,7 @@ void fastcall __sched __down_write(struct rw_semaphore *sem)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irq(&sem->wait_lock);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -250,10 +252,12 @@ void fastcall __sched __down_write(struct rw_semaphore *sem)
  */
 int fastcall __down_write_trylock(struct rw_semaphore *sem)
 {
+	unsigned long flags;
 	int ret = 0;
+
 	rwsemtrace(sem, "Entering __down_write_trylock");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
 		/* granted */
@@ -261,7 +265,7 @@ int fastcall __down_write_trylock(struct rw_semaphore *sem)
 		ret = 1;
 	}
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving __down_write_trylock");
 	return ret;
@@ -272,14 +276,16 @@ int fastcall __down_write_trylock(struct rw_semaphore *sem)
  */
 void fastcall __up_read(struct rw_semaphore *sem)
 {
+	unsigned long flags;
+
 	rwsemtrace(sem, "Entering __up_read");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
 		sem = __rwsem_wake_one_writer(sem);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving __up_read");
 }
@@ -289,15 +295,17 @@ void fastcall __up_read(struct rw_semaphore *sem)
  */
 void fastcall __up_write(struct rw_semaphore *sem)
 {
+	unsigned long flags;
+
 	rwsemtrace(sem, "Entering __up_write");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	sem->activity = 0;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 1);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving __up_write");
 }
@@ -308,15 +316,17 @@ void fastcall __up_write(struct rw_semaphore *sem)
  */
 void fastcall __downgrade_write(struct rw_semaphore *sem)
 {
+	unsigned long flags;
+
 	rwsemtrace(sem, "Entering __downgrade_write");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	sem->activity = 1;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 0);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving __downgrade_write");
 }
diff --git a/lib/rwsem.c b/lib/rwsem.c
index 924c14e0bfde..7644089ec8fa 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -150,7 +150,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 
 	/* set up my own style of waitqueue */
-	spin_lock(&sem->wait_lock);
+	spin_lock_irq(&sem->wait_lock);
 	waiter->task = tsk;
 	get_task_struct(tsk);
 
@@ -163,7 +163,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 	if (!(count & RWSEM_ACTIVE_MASK))
 		sem = __rwsem_do_wake(sem, 0);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irq(&sem->wait_lock);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -219,15 +219,17 @@ rwsem_down_write_failed(struct rw_semaphore *sem)
  */
 struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
 {
+	unsigned long flags;
+
 	rwsemtrace(sem, "Entering rwsem_wake");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 0);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving rwsem_wake");
 
@@ -241,15 +243,17 @@ struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
  */
 struct rw_semaphore fastcall *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
+	unsigned long flags;
+
 	rwsemtrace(sem, "Entering rwsem_downgrade_wake");
 
-	spin_lock(&sem->wait_lock);
+	spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 1);
 
-	spin_unlock(&sem->wait_lock);
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	rwsemtrace(sem, "Leaving rwsem_downgrade_wake");
 	return sem;