[03/11] locking, rwsem: introduce basis for down_write_killable

Commit Message

Michal Hocko Feb. 29, 2016, 12:58 p.m. UTC

From: Michal Hocko <[e-mail]>

Introduce a generic implementation necessary for down_write_killable.
This is a trivial extension of the already existing down_write call
which can be interrupted by SIGKILL.  This patch doesn't provide
down_write_killable yet because arches have to provide the necessary
pieces before.

rwsem_down_write_failed which is a generic slow path for the
write lock is extended to allow a task state and renamed to
__rwsem_down_write_failed_state. The return value is either a valid
semaphore pointer or ERR_PTR(-EINTR).

rwsem_down_write_failed_killable is exported as a new way to wait for
the lock and be killable.

For rwsem-spinlock implementation the current __down_write it updated
in a similar way as __rwsem_down_write_failed_state except it doesn't
need new exports just visible __down_write_killable.

Architectures which are not using the generic rwsem implementation are
supposed to provide their __down_write_killable implementation and
use rwsem_down_write_failed_killable for the slow path.

Signed-off-by: Michal Hocko <[e-mail]>
---
 include/asm-generic/rwsem.h     | 12 ++++++++++++
 include/linux/rwsem-spinlock.h  |  1 +
 include/linux/rwsem.h           |  2 ++
 kernel/locking/rwsem-spinlock.c | 23 +++++++++++++++++++++--
 kernel/locking/rwsem-xadd.c     | 31 +++++++++++++++++++++++++------
 5 files changed, 61 insertions(+), 8 deletions(-)

Comments

Peter Zijlstra March 30, 2016, 1:25 p.m. UTC | #1

On Mon, Feb 29, 2016 at 01:58:17PM +0100, Michal Hocko wrote:
> @@ -215,16 +216,34 @@ void __sched __down_write(struct rw_semaphore *sem)
>  		 */
>  		if (sem->count == 0)
>  			break;
> -		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
> +		set_task_state(tsk, state);
>  		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
>  		schedule();
> +		if (signal_pending_state(state, current)) {
> +			ret = -EINTR;
> +			raw_spin_lock_irqsave(&sem->wait_lock, flags);
> +			goto out;
> +		}
>  		raw_spin_lock_irqsave(&sem->wait_lock, flags);
>  	}
>  	/* got the lock */
>  	sem->count = -1;

> @@ -487,20 +488,38 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
>  		/* Block until there are no active lockers. */
>  		do {
>  			schedule();
> -			set_current_state(TASK_UNINTERRUPTIBLE);
> +			if (signal_pending_state(state, current)) {
> +				raw_spin_lock_irq(&sem->wait_lock);
> +				ret = ERR_PTR(-EINTR);
> +				goto out;
> +			}
> +			set_current_state(state);
>  		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
>  
>  		raw_spin_lock_irq(&sem->wait_lock);
>  	}
>  	__set_current_state(TASK_RUNNING);

Why is the signal_pending_state() test _after_ the call to schedule()
and before the 'trylock'.

__mutex_lock_common() has it before the call to schedule and after the
'trylock'.

The difference is that rwsem will now respond to the KILL and return
-EINTR even if the lock is available, whereas mutex will acquire it and
ignore the signal (for a little while longer).

Neither is wrong per se, but I feel all the locking primitives should
behave in a consistent manner in this regard.

--
To unsubscribe from this list: send the line "unsubscribe linux-sh" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index b8d8a6cf4ca8..3fc94a046bf5 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -63,6 +63,18 @@  static inline void __down_write(struct rw_semaphore *sem)
 		rwsem_down_write_failed(sem);
 }
 
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+				     (atomic_long_t *)&sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+	return 0;
+}
+
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index a733a5467e6c..ae0528b834cd 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -34,6 +34,7 @@  struct rw_semaphore {
 extern void __down_read(struct rw_semaphore *sem);
 extern int __down_read_trylock(struct rw_semaphore *sem);
 extern void __down_write(struct rw_semaphore *sem);
+extern int __must_check __down_write_killable(struct rw_semaphore *sem);
 extern int __down_write_trylock(struct rw_semaphore *sem);
 extern void __up_read(struct rw_semaphore *sem);
 extern void __up_write(struct rw_semaphore *sem);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8f498cdde280..7d7ae029dac5 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -14,6 +14,7 @@ 
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
+#include <linux/err.h>
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 #include <linux/osq_lock.h>
 #endif
@@ -43,6 +44,7 @@  struct rw_semaphore {
 
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index bab26104a5d0..d1d04ca10d0e 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(struct rw_semaphore *sem)
+int __sched __down_write_state(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);
 
@@ -215,16 +216,34 @@  void __sched __down_write(struct rw_semaphore *sem)
 		 */
 		if (sem->count == 0)
 			break;
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_task_state(tsk, state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
+		if (signal_pending_state(state, current)) {
+			ret = -EINTR;
+			raw_spin_lock_irqsave(&sem->wait_lock, flags);
+			goto out;
+		}
 		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_state(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_write_killable(struct rw_semaphore *sem)
+{
+	return __down_write_state(sem, TASK_KILLABLE);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a4d4de05b2d1..5cec34f1ad6f 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_state(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;
@@ -487,20 +488,38 @@  struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 		/* Block until there are no active lockers. */
 		do {
 			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
+			if (signal_pending_state(state, current)) {
+				raw_spin_lock_irq(&sem->wait_lock);
+				ret = ERR_PTR(-EINTR);
+				goto out;
+			}
+			set_current_state(state);
 		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
 	__set_current_state(TASK_RUNNING);
-
+out:
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
 
-	return sem;
+	return ret;
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_write_failed_state(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_state(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