| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230628190227.894195-1-pauld@redhat.com>
Date: Wed, 28 Jun 2023 15:02:27 -0400
From: Phil Auld <pauld@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: Juri Lelli <juri.lelli@...hat.com>, Ingo Molnar <mingo@...hat.com>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Valentin Schneider <vschneid@...hat.com>,
Ben Segall <bsegall@...gle.com>,
Steven Rostedt <rostedt@...dmis.org>,
Mel Gorman <mgorman@...e.de>, Phil Auld <pauld@...hat.com>
Subject: [PATCH v3] Sched/fair: Block nohz tick_stop when cfs bandwidth in use
CFS bandwidth limits and NOHZ full don't play well together. Tasks
can easily run well past their quotas before a remote tick does
accounting. This leads to long, multi-period stalls before such
tasks can run again. Currentlyi, when presented with these conflicting
requirements the scheduler is favoring nohz_full and letting the tick
be stopped. However, nohz tick stopping is already best-effort, there
are a number of conditions that can prevent it, whereas cfs runtime
bandwidth is expected to be enforced.
Make the scheduler favor bandwidth over stopping the tick by setting
TICK_DEP_BIT_SCHED when the only running task is a cfs task with
runtime limit enabled.
Add sched_feat HZ_BW (off by default) to control this behavior.
Signed-off-by: Phil Auld <pauld@...hat.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Juri Lelli <juri.lelli@...hat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>
Cc: Valentin Schneider <vschneid@...hat.com>
Cc: Ben Segall <bsegall@...gle.com>
---
v2: Ben pointed out that the bit could get cleared in the dequeue path
if we migrate a newly enqueued task without preempting curr. Added a
check for that edge case to sched_can_stop_tick. Removed the call to
sched_can_stop_tick from sched_fair_update_stop_tick since it was
redundant.
v3: Moved sched_cfs_bandwidth_active() prototype to sched.h outside of
guards to silence -Wmissing-prototypes.
kernel/sched/core.c | 10 +++++++++
kernel/sched/fair.c | 45 +++++++++++++++++++++++++++++++++++++++++
kernel/sched/features.h | 2 ++
kernel/sched/sched.h | 1 +
4 files changed, 58 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a68d1276bab0..0d8bdd36f870 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1229,6 +1229,16 @@ bool sched_can_stop_tick(struct rq *rq)
if (rq->nr_running > 1)
return false;
+ /*
+ * If there is one task and it has CFS runtime bandwidth constraints
+ * and it's on the cpu now we don't want to stop the tick.
+ */
+ if (sched_feat(HZ_BW) && rq->nr_running == 1 && rq->curr
+ && rq->curr->sched_class == &fair_sched_class && task_on_rq_queued(rq->curr)) {
+ if (sched_cfs_bandwidth_active(task_cfs_rq(rq->curr)))
+ return false;
+ }
+
return true;
}
#endif /* CONFIG_NO_HZ_FULL */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 373ff5f55884..a05af33b8da9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6139,6 +6139,42 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
rcu_read_unlock();
}
+#ifdef CONFIG_NO_HZ_FULL
+
+bool sched_cfs_bandwidth_active(struct cfs_rq *cfs_rq)
+{
+ if (cfs_bandwidth_used() && cfs_rq->runtime_enabled)
+ return true;
+
+ return false;
+}
+
+/* called from pick_next_task_fair() */
+static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
+{
+ struct cfs_rq *cfs_rq = task_cfs_rq(p);
+ int cpu = cpu_of(rq);
+
+ if (!sched_feat(HZ_BW) || !cfs_bandwidth_used())
+ return;
+
+ if (!tick_nohz_full_cpu(cpu))
+ return;
+
+ if (rq->nr_running != 1)
+ return;
+
+ /*
+ * We know there is only one task runnable and we've just picked it. The
+ * normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
+ * be otherwise able to stop the tick. Just need to check if we are using
+ * bandwidth control.
+ */
+ if (cfs_rq->runtime_enabled)
+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#endif
+
#else /* CONFIG_CFS_BANDWIDTH */
static inline bool cfs_bandwidth_used(void)
@@ -6181,9 +6217,17 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
static inline void update_runtime_enabled(struct rq *rq) {}
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+bool sched_cfs_bandwidth_active(struct cfs_rq *cfs_rq)
+{
+ return false;
+}
#endif /* CONFIG_CFS_BANDWIDTH */
+#if !defined(CONFIG_CFS_BANDWIDTH) || !defined(CONFIG_NO_HZ_FULL)
+static inline void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) {}
+#endif
+
/**************************************************
* CFS operations on tasks:
*/
@@ -8097,6 +8141,7 @@ done: __maybe_unused;
hrtick_start_fair(rq, p);
update_misfit_status(p, rq);
+ sched_fair_update_stop_tick(rq, p);
return p;
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76bd3..6fdf1fdf6b17 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -101,3 +101,5 @@ SCHED_FEAT(LATENCY_WARN, false)
SCHED_FEAT(ALT_PERIOD, true)
SCHED_FEAT(BASE_SLICE, true)
+
+SCHED_FEAT(HZ_BW, false)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ec7b3e0a2b20..f2bd4568472e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2789,6 +2789,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq);
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
+extern bool sched_cfs_bandwidth_active(struct cfs_rq *cfs_rq);
#ifdef CONFIG_NO_HZ_COMMON
#define NOHZ_BALANCE_KICK_BIT 0
--
2.31.1
Powered by blists - more mailing lists