Merge branch 'locking-rwsem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull support for killable rwsems from Ingo Molnar:
 "This, by Michal Hocko, implements down_write_killable().

  The main usecase will be to update mm_sem usage sites to use this new
  API, to allow the mm-reaper introduced in commit aac453635549 ("mm,
  oom: introduce oom reaper") to tear down oom victim address spaces
  asynchronously with minimum latencies and without deadlock worries"

[ The vfs will want it too as the inode lock is changed from a mutex to
  a rwsem due to the parallel lookup and readdir updates ]

* 'locking-rwsem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/rwsem: Fix comment on register clobbering
  locking/rwsem: Fix down_write_killable()
  locking/rwsem, x86: Add frame annotation for call_rwsem_down_write_failed_killable()
  locking/rwsem: Provide down_write_killable()
  locking/rwsem, x86: Provide __down_write_killable()
  locking/rwsem, s390: Provide __down_write_killable()
  locking/rwsem, ia64: Provide __down_write_killable()
  locking/rwsem, alpha: Provide __down_write_killable()
  locking/rwsem: Introduce basis for down_write_killable()
  locking/rwsem, sparc: Drop superfluous arch specific implementation
  locking/rwsem, sh: Drop superfluous arch specific implementation
  locking/rwsem, xtensa: Drop superfluous arch specific implementation
  locking/rwsem: Drop explicit memory barriers
  locking/rwsem: Get rid of __down_write_nested()

3 files changed, 68 insertions, 8 deletions

diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 3a5048572065..1591f6b3539f 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -191,11 +191,12 @@ int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * get a write lock on the semaphore
  */
-void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+int __sched __down_write_common(struct rw_semaphore *sem, int state)
 {
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk;
 	unsigned long flags;
+	int ret = 0;
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
@@ -215,21 +216,33 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 		 */
 		if (sem->count == 0)
 			break;
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		if (signal_pending_state(state, current)) {
+			ret = -EINTR;
+			goto out;
+		}
+		set_task_state(tsk, state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
 		raw_spin_lock_irqsave(&sem->wait_lock, flags);
 	}
 	/* got the lock */
 	sem->count = -1;
+out:
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
 }
 
 void __sched __down_write(struct rw_semaphore *sem)
 {
-	__down_write_nested(sem, 0);
+	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_write_killable(struct rw_semaphore *sem)
+{
+	return __down_write_common(sem, TASK_KILLABLE);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a4d4de05b2d1..09e30c6225e5 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -433,12 +433,13 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
 /*
  * Wait until we successfully acquire the write lock
  */
-__visible
-struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
+static inline struct rw_semaphore *
+__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 {
 	long count;
 	bool waiting = true; /* any queued threads before us */
 	struct rwsem_waiter waiter;
+	struct rw_semaphore *ret = sem;
 
 	/* undo write bias from down_write operation, stop active locking */
 	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
@@ -478,7 +479,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
 
 	/* wait until we successfully acquire the lock */
-	set_current_state(TASK_UNINTERRUPTIBLE);
+	set_current_state(state);
 	while (true) {
 		if (rwsem_try_write_lock(count, sem))
 			break;
@@ -486,21 +487,48 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 
 		/* Block until there are no active lockers. */
 		do {
+			if (signal_pending_state(state, current))
+				goto out_nolock;
+
 			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
+			set_current_state(state);
 		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
 	__set_current_state(TASK_RUNNING);
+	list_del(&waiter.list);
+	raw_spin_unlock_irq(&sem->wait_lock);
 
+	return ret;
+
+out_nolock:
+	__set_current_state(TASK_RUNNING);
+	raw_spin_lock_irq(&sem->wait_lock);
 	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list))
+		rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+	else
+		__rwsem_do_wake(sem, RWSEM_WAKE_ANY);
 	raw_spin_unlock_irq(&sem->wait_lock);
 
-	return sem;
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(rwsem_down_write_failed);
 
+__visible struct rw_semaphore * __sched
+rwsem_down_write_failed_killable(struct rw_semaphore *sem)
+{
+	return __rwsem_down_write_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_write_failed_killable);
+
 /*
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 205be0ce34de..c817216c1615 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -55,6 +55,25 @@ void __sched down_write(struct rw_semaphore *sem)
 EXPORT_SYMBOL(down_write);
 
 /*
+ * lock for writing
+ */
+int __sched down_write_killable(struct rw_semaphore *sem)
+{
+	might_sleep();
+	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+
+	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+		rwsem_release(&sem->dep_map, 1, _RET_IP_);
+		return -EINTR;
+	}
+
+	rwsem_set_owner(sem);
+	return 0;
+}
+
+EXPORT_SYMBOL(down_write_killable);
+
+/*
  * trylock for writing -- returns 1 if successful, 0 if contention
  */
 int down_write_trylock(struct rw_semaphore *sem)