sched/core: Correct off by one bug in load migration calculation

The move of calc_load_migrate() from CPU_DEAD to CPU_DYING did not take into
account that the function is now called from a thread running on the outgoing
CPU. As a result a cpu unplug leakes a load of 1 into the global load
accounting mechanism.

Fix it by adjusting for the currently running thread which calls
calc_load_migrate().

Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: rt@linutronix.de
Cc: shreyas@linux.vnet.ibm.com
Fixes: e9cd8fa4fcfd: ("sched/migration: Move calc_load_migrate() into CPU_DYING")
Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1607121744350.4083@nanos
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 9 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51d7105f529a5..97ee9ac7e97c7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5394,13 +5394,15 @@ void idle_task_exit(void)
 /*
  * Since this CPU is going 'away' for a while, fold any nr_active delta
  * we might have. Assumes we're called after migrate_tasks() so that the
- * nr_active count is stable.
+ * nr_active count is stable. We need to take the teardown thread which
+ * is calling this into account, so we hand in adjust = 1 to the load
+ * calculation.
  *
  * Also see the comment "Global load-average calculations".
  */
 static void calc_load_migrate(struct rq *rq)
 {
-	long delta = calc_load_fold_active(rq);
+	long delta = calc_load_fold_active(rq, 1);
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 }
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index b0b93fd33af9e..a2d6eb71f06b8 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -78,11 +78,11 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 	loads[2] = (avenrun[2] + offset) << shift;
 }
 
-long calc_load_fold_active(struct rq *this_rq)
+long calc_load_fold_active(struct rq *this_rq, long adjust)
 {
 	long nr_active, delta = 0;
 
-	nr_active = this_rq->nr_running;
+	nr_active = this_rq->nr_running - adjust;
 	nr_active += (long)this_rq->nr_uninterruptible;
 
 	if (nr_active != this_rq->calc_load_active) {
@@ -188,7 +188,7 @@ void calc_load_enter_idle(void)
 	 * We're going into NOHZ mode, if there's any pending delta, fold it
 	 * into the pending idle delta.
 	 */
-	delta = calc_load_fold_active(this_rq);
+	delta = calc_load_fold_active(this_rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
@@ -389,7 +389,7 @@ void calc_global_load_tick(struct rq *this_rq)
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;
 
-	delta  = calc_load_fold_active(this_rq);
+	delta  = calc_load_fold_active(this_rq, 0);
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7cbeb92a1cb93..898c0d2f18feb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -28,7 +28,7 @@ extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
 extern void calc_global_load_tick(struct rq *this_rq);
-extern long calc_load_fold_active(struct rq *this_rq);
+extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
 #ifdef CONFIG_SMP
 extern void cpu_load_update_active(struct rq *this_rq);