[tip:sched/urgent] sched/core: Fix update_rq_clock() splat on hotplug (and suspend/resume)

[tip-bot for Peter Zijlstra]

Commit-ID:  8cb68b343a66cf19834472012590490d34d31703
Gitweb:     http://git.kernel.org/tip/8cb68b343a66cf19834472012590490d34d31703
Author:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Thu, 2 Feb 2017 16:55:06 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 24 Feb 2017 08:58:33 +0100

sched/core: Fix update_rq_clock() splat on hotplug (and suspend/resume)

The hotplug code still triggers the warning about using a stale
rq->clock value.

Fix things up to actually run update_rq_clock() in a place where we
record the 'UPDATED' flag, and then modify the annotation to retain
this flag over the rq->lock fiddling that happens as a result of
actually migrating all the tasks elsewhere.

Reported-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Tested-by: Mike Galbraith <efault@xxxxxx>
Tested-by: Sachin Sant <sachinp@xxxxxxxxxxxxxxxxxx>
Tested-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Matt Fleming <matt@xxxxxxxxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ross Zwisler <zwisler@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Fixes: 4d25b35ea372 ("sched/fair: Restore previous rq_flags when migrating tasks in hotplug")
Link: http://lkml.kernel.org/r/20170202155506.GX6515@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/sched/core.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 34e2291..2d6e828 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5557,7 +5557,7 @@ static void migrate_tasks(struct rq *dead_rq)
 {
 	struct rq *rq = dead_rq;
 	struct task_struct *next, *stop = rq->stop;
-	struct rq_flags rf, old_rf;
+	struct rq_flags rf;
 	int dest_cpu;
 
 	/*
@@ -5576,7 +5576,9 @@ static void migrate_tasks(struct rq *dead_rq)
 	 * class method both need to have an up-to-date
 	 * value of rq->clock[_task]
 	 */
+	rq_pin_lock(rq, &rf);
 	update_rq_clock(rq);
+	rq_unpin_lock(rq, &rf);
 
 	for (;;) {
 		/*
@@ -5589,7 +5591,7 @@ static void migrate_tasks(struct rq *dead_rq)
 		/*
 		 * pick_next_task() assumes pinned rq->lock:
 		 */
-		rq_pin_lock(rq, &rf);
+		rq_repin_lock(rq, &rf);
 		next = pick_next_task(rq, &fake_task, &rf);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
@@ -5618,13 +5620,6 @@ static void migrate_tasks(struct rq *dead_rq)
 			continue;
 		}
 
-		/*
-		 * __migrate_task() may return with a different
-		 * rq->lock held and a new cookie in 'rf', but we need
-		 * to preserve rf::clock_update_flags for 'dead_rq'.
-		 */
-		old_rf = rf;
-
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
@@ -5633,7 +5628,6 @@ static void migrate_tasks(struct rq *dead_rq)
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
-			rf = old_rf;
 		}
 		raw_spin_unlock(&next->pi_lock);
 	}