delayacct: Account blkio completion on the correct task

Before commit:

  e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler")

delayacct_blkio_end() was called after context-switching into the task which
completed I/O.

This resulted in double counting: the task would account a delay both waiting
for I/O and for time spent in the runqueue.

With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up().
In ttwu, we have not yet context-switched. This is more correct, in that
the delay accounting ends when the I/O is complete.

But delayacct_blkio_end() relies on 'get_current()', and we have not yet
context-switched into the task whose I/O completed. This results in the
wrong task having its delay accounting statistics updated.

Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(),
so that it can update the statistics of the correct task.

Signed-off-by: Josh Snyder <joshs@netflix.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Brendan Gregg <bgregg@netflix.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-block@vger.kernel.org
Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler")
Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 33 insertions, 23 deletions

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 4178d24935477d..5e335b6203f49d 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -71,7 +71,7 @@ extern void delayacct_init(void);
 extern void __delayacct_tsk_init(struct task_struct *);
 extern void __delayacct_tsk_exit(struct task_struct *);
 extern void __delayacct_blkio_start(void);
-extern void __delayacct_blkio_end(void);
+extern void __delayacct_blkio_end(struct task_struct *);
 extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
@@ -122,10 +122,10 @@ static inline void delayacct_blkio_start(void)
 		__delayacct_blkio_start();
 }
 
-static inline void delayacct_blkio_end(void)
+static inline void delayacct_blkio_end(struct task_struct *p)
 {
 	if (current->delays)
-		__delayacct_blkio_end();
+		__delayacct_blkio_end(p);
 	delayacct_clear_flag(DELAYACCT_PF_BLKIO);
 }
 
@@ -169,7 +169,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk)
 {}
 static inline void delayacct_blkio_start(void)
 {}
-static inline void delayacct_blkio_end(void)
+static inline void delayacct_blkio_end(struct task_struct *p)
 {}
 static inline int delayacct_add_tsk(struct taskstats *d,
 					struct task_struct *tsk)
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 4a1c33416b6a2d..e2764d767f186e 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk)
  * Finish delay accounting for a statistic using its timestamps (@start),
  * accumalator (@total) and @count
  */
-static void delayacct_end(u64 *start, u64 *total, u32 *count)
+static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
 {
 	s64 ns = ktime_get_ns() - *start;
 	unsigned long flags;
 
 	if (ns > 0) {
-		spin_lock_irqsave(&current->delays->lock, flags);
+		spin_lock_irqsave(lock, flags);
 		*total += ns;
 		(*count)++;
-		spin_unlock_irqrestore(&current->delays->lock, flags);
+		spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -69,17 +69,25 @@ void __delayacct_blkio_start(void)
 	current->delays->blkio_start = ktime_get_ns();
 }
 
-void __delayacct_blkio_end(void)
+/*
+ * We cannot rely on the `current` macro, as we haven't yet switched back to
+ * the process being woken.
+ */
+void __delayacct_blkio_end(struct task_struct *p)
 {
-	if (current->delays->flags & DELAYACCT_PF_SWAPIN)
-		/* Swapin block I/O */
-		delayacct_end(&current->delays->blkio_start,
-			&current->delays->swapin_delay,
-			&current->delays->swapin_count);
-	else	/* Other block I/O */
-		delayacct_end(&current->delays->blkio_start,
-			&current->delays->blkio_delay,
-			&current->delays->blkio_count);
+	struct task_delay_info *delays = p->delays;
+	u64 *total;
+	u32 *count;
+
+	if (p->delays->flags & DELAYACCT_PF_SWAPIN) {
+		total = &delays->swapin_delay;
+		count = &delays->swapin_count;
+	} else {
+		total = &delays->blkio_delay;
+		count = &delays->blkio_count;
+	}
+
+	delayacct_end(&delays->lock, &delays->blkio_start, total, count);
 }
 
 int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
@@ -153,8 +161,10 @@ void __delayacct_freepages_start(void)
 
 void __delayacct_freepages_end(void)
 {
-	delayacct_end(&current->delays->freepages_start,
-			&current->delays->freepages_delay,
-			&current->delays->freepages_count);
+	delayacct_end(
+		&current->delays->lock,
+		&current->delays->freepages_start,
+		&current->delays->freepages_delay,
+		&current->delays->freepages_count);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 644fa2e3d993b5..a7bf32aabfda73 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2056,7 +2056,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->state = TASK_WAKING;
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2069,7 +2069,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 #else /* CONFIG_SMP */
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2122,7 +2122,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 
 	if (!task_on_rq_queued(p)) {
 		if (p->in_iowait) {
-			delayacct_blkio_end();
+			delayacct_blkio_end(p);
 			atomic_dec(&rq->nr_iowait);
 		}
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);