sched/core: Fix remote wakeups

Commit:

  b5179ac70de8 ("sched/fair: Prepare to fix fairness problems on migration")

... introduced a bug: Mike Galbraith found that it introduced a
performance regression, while Paul E. McKenney reported lost
wakeups and bisected it to this commit.

The reason is that I mis-read ttwu_queue() such that I assumed any
wakeup that got a remote queue must have had the task migrated.

Since this is not so; we need to transfer this information between
queueing the wakeup and actually doing the wakeup. Use a new
task_struct::sched_flag for this, we already write to
sched_contributes_to_load in the wakeup path so this is a hot and
modified cacheline.

Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Tested-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Hunter <ahh@google.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Ben Segall <bsegall@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Turner <pjt@google.com>
Cc: Pavan Kondeti <pkondeti@codeaurora.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: byungchul.park@lge.com
Fixes: b5179ac70de8 ("sched/fair: Prepare to fix fairness problems on migration")
Link: http://lkml.kernel.org/r/20160523091907.GD15728@worktop.ger.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 12 insertions, 7 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6cc0df970f1a..e053517a88b6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1533,6 +1533,7 @@ struct task_struct {
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 	unsigned sched_migrated:1;
+	unsigned sched_remote_wakeup:1;
 	unsigned :0; /* force alignment to the next boundary */
 
 	/* unserialized, strictly 'current' */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 404c0784b1fc..7f2cae4620c7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1768,13 +1768,15 @@ void sched_ttwu_pending(void)
 	cookie = lockdep_pin_lock(&rq->lock);
 
 	while (llist) {
+		int wake_flags = 0;
+
 		p = llist_entry(llist, struct task_struct, wake_entry);
 		llist = llist_next(llist);
-		/*
-		 * See ttwu_queue(); we only call ttwu_queue_remote() when
-		 * its a x-cpu wakeup.
-		 */
-		ttwu_do_activate(rq, p, WF_MIGRATED, cookie);
+
+		if (p->sched_remote_wakeup)
+			wake_flags = WF_MIGRATED;
+
+		ttwu_do_activate(rq, p, wake_flags, cookie);
 	}
 
 	lockdep_unpin_lock(&rq->lock, cookie);
@@ -1819,10 +1821,12 @@ void scheduler_ipi(void)
 	irq_exit();
 }
 
-static void ttwu_queue_remote(struct task_struct *p, int cpu)
+static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
 
+	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
+
 	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
 		if (!set_nr_if_polling(rq->idle))
 			smp_send_reschedule(cpu);
@@ -1869,7 +1873,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
 		sched_clock_cpu(cpu); /* sync clocks x-cpu */
-		ttwu_queue_remote(p, cpu);
+		ttwu_queue_remote(p, cpu, wake_flags);
 		return;
 	}
 #endif