* [PATCH tip 2/2] sched/core: Fix endless loop in pick_next_task()
@ 2014-03-06 9:32 Kirill Tkhai
2014-03-11 12:39 ` [tip:sched/core] " tip-bot for Kirill Tkhai
0 siblings, 1 reply; 2+ messages in thread
From: Kirill Tkhai @ 2014-03-06 9:32 UTC (permalink / raw)
To: linux-kernel; +Cc: Peter Zijlstra, Ingo Molnar
1)Single cpu machine case.
When rq has only RT tasks, but no one of them can be picked
because of throttling, we enter in endless loop.
pick_next_task_{dl,rt} return NULL.
In pick_next_task_fair() we permanently go to retry
if (rq->nr_running != rq->cfs.h_nr_running)
return RETRY_TASK;
(rq->nr_running is not being decremented when rt_rq becomes
throttled).
No chances to unthrottle any rt_rq or to wake fair here,
because of rq is locked permanently and interrupts are
disabled.
2)In case of SMP this can cause a hang too. Although we unlock
rq in idle_balance(), interrupts are still disabled.
The solution is to check for available tasks in DL and RT
classes instead of checking for sum.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Ingo Molnar <mingo@redhat.com>
---
kernel/sched/fair.c | 4 +++-
kernel/sched/rt.c | 10 ----------
kernel/sched/sched.h | 12 ++++++++++++
3 files changed, 15 insertions(+), 11 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b956e70..10db4a8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6728,7 +6728,9 @@ static int idle_balance(struct rq *this_rq)
out:
/* Is there a task of a high priority class? */
- if (this_rq->nr_running != this_rq->cfs.h_nr_running)
+ if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+ (this_rq->dl.dl_nr_running ||
+ (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
pulled_task = -1;
if (pulled_task) {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f3cee0a..d8cdf16 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -470,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
dequeue_rt_entity(rt_se);
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -545,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled;
-}
-
static inline const struct cpumask *sched_rt_period_mask(void)
{
return cpu_online_mask;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 378bff7..f2de7a1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -423,6 +423,18 @@ struct rt_rq {
#endif
};
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled;
+}
+#endif
+
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
^ permalink raw reply [flat|nested] 2+ messages in thread
* [tip:sched/core] sched/core: Fix endless loop in pick_next_task()
2014-03-06 9:32 [PATCH tip 2/2] sched/core: Fix endless loop in pick_next_task() Kirill Tkhai
@ 2014-03-11 12:39 ` tip-bot for Kirill Tkhai
0 siblings, 0 replies; 2+ messages in thread
From: tip-bot for Kirill Tkhai @ 2014-03-11 12:39 UTC (permalink / raw)
To: linux-tip-commits; +Cc: linux-kernel, ktkhai, hpa, mingo, peterz, tglx
Commit-ID: 4c6c4e38c4e9a454889298dcc498174968d14a09
Gitweb: http://git.kernel.org/tip/4c6c4e38c4e9a454889298dcc498174968d14a09
Author: Kirill Tkhai <ktkhai@parallels.com>
AuthorDate: Thu, 6 Mar 2014 13:32:01 +0400
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 11 Mar 2014 12:05:39 +0100
sched/core: Fix endless loop in pick_next_task()
1) Single cpu machine case.
When rq has only RT tasks, but no one of them can be picked
because of throttling, we enter in endless loop.
pick_next_task_{dl,rt} return NULL.
In pick_next_task_fair() we permanently go to retry
if (rq->nr_running != rq->cfs.h_nr_running)
return RETRY_TASK;
(rq->nr_running is not being decremented when rt_rq becomes
throttled).
No chances to unthrottle any rt_rq or to wake fair here,
because of rq is locked permanently and interrupts are
disabled.
2) In case of SMP this can cause a hang too. Although we unlock
rq in idle_balance(), interrupts are still disabled.
The solution is to check for available tasks in DL and RT
classes instead of checking for sum.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1394098321.19290.11.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 4 +++-
kernel/sched/rt.c | 10 ----------
kernel/sched/sched.h | 12 ++++++++++++
3 files changed, 15 insertions(+), 11 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b956e70..10db4a8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6728,7 +6728,9 @@ static int idle_balance(struct rq *this_rq)
out:
/* Is there a task of a high priority class? */
- if (this_rq->nr_running != this_rq->cfs.h_nr_running)
+ if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+ (this_rq->dl.dl_nr_running ||
+ (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
pulled_task = -1;
if (pulled_task) {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f3cee0a..d8cdf16 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -470,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
dequeue_rt_entity(rt_se);
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -545,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled;
-}
-
static inline const struct cpumask *sched_rt_period_mask(void)
{
return cpu_online_mask;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 378bff7..f2de7a1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -423,6 +423,18 @@ struct rt_rq {
#endif
};
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled;
+}
+#endif
+
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2014-03-11 12:40 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-03-06 9:32 [PATCH tip 2/2] sched/core: Fix endless loop in pick_next_task() Kirill Tkhai
2014-03-11 12:39 ` [tip:sched/core] " tip-bot for Kirill Tkhai
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome