sched: add wait_for_completion_io[_timeout]

The only difference between wait_for_completion[_timeout]() and
wait_for_completion_io[_timeout]() is that the latter calls
io_schedule_timeout() instead of schedule_timeout() so that the caller
is accounted as waiting for IO, not just sleeping.

These functions can be used for correct iowait time accounting when the
completion struct is actually used for waiting for IO (e.g. completion
of a bio request in the block layer).

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 52 insertions, 5 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 257002c13bb0..d6fdcdcbb9b1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3267,7 +3267,8 @@ void complete_all(struct completion *x)
 EXPORT_SYMBOL(complete_all);
 
 static inline long __sched
-do_wait_for_common(struct completion *x, long timeout, int state)
+do_wait_for_common(struct completion *x,
+                   long (*action)(long), long timeout, int state)
 {
         if (!x->done) {
                 DECLARE_WAITQUEUE(wait, current);
@@ -3280,7 +3281,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                         }
                         __set_current_state(state);
                         spin_unlock_irq(&x->wait.lock);
-                        timeout = schedule_timeout(timeout);
+                        timeout = action(timeout);
                         spin_lock_irq(&x->wait.lock);
                 } while (!x->done && timeout);
                 __remove_wait_queue(&x->wait, &wait);
@@ -3291,17 +3292,30 @@ do_wait_for_common(struct completion *x, long timeout, int state)
         return timeout ?: 1;
 }
 
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
+static inline long __sched
+__wait_for_common(struct completion *x,
+                  long (*action)(long), long timeout, int state)
 {
         might_sleep();
 
         spin_lock_irq(&x->wait.lock);
-        timeout = do_wait_for_common(x, timeout, state);
+        timeout = do_wait_for_common(x, action, timeout, state);
         spin_unlock_irq(&x->wait.lock);
         return timeout;
 }
 
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+        return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+        return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
 /**
  * wait_for_completion: - waits for completion of a task
  * @x:  holds the state of this particular completion
@@ -3338,6 +3352,39 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 EXPORT_SYMBOL(wait_for_completion_timeout);
 
 /**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+        wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+        return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
  * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
  * @x:  holds the state of this particular completion
  *