Message-ID: <20200915152048.GA25835@iZj6chx1xj0e0buvshuecpZ>
Date:   Tue, 15 Sep 2020 23:20:48 +0800
From:   Peng Liu <iwtbavbm@...il.com>
To:     mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, valentin.schneider@....com, raistlin@...ux.it,
        linux-kernel@...r.kernel.org
Cc:     iwtbavbm@...il.com
Subject: [PATCH] sched/deadline: Fix sched_dl_global_validate()

When user changes sched_rt_{runtime, period}_us, then

  sched_rt_handler()
    -->	sched_dl_bandwidth_validate()
	{
		new_bw = global_rt_runtime()/global_rt_period();

		for_each_possible_cpu(cpu) {
			dl_b = dl_bw_of(cpu);
			if (new_bw < dl_b->total_bw)
				ret = -EBUSY;
		}
	}

Under CONFIG_SMP, dl_bw is per root domain , but not per CPU,
dl_b->total_bw is the allocated bandwidth of the whole root domain.
we should compare dl_b->total_bw against cpus*new_bw, where 'cpus'
is the number of CPUs of the root domain.

Also, below annotation(in kernel/sched/sched.h) implied implementation
only appeared in SCHED_DEADLINE v2[1], then deadline scheduler kept
evolving till got merged(v9), but the annotation remains unchanged,
meaningless and misleading, correct it.

* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
*  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
*  - dl_total_bw array contains, in the i-eth element, the currently
*    allocated bandwidth on the i-eth CPU.

[1] https://lkml.org/lkml/2010/2/28/119

Signed-off-by: Peng Liu <iwtbavbm@...il.com>
---
In fact, I'm not 100% sure that's a bug, since it's too 'obvious' and
not newly introduced code.

Also, the introduced #ifdef...#endif pairs look ugly, I have no idea
how to eliminate them. Ideas and comments are welcome. Thanks.

 kernel/sched/deadline.c | 48 ++++++++++++++++++++++++++++-------------
 kernel/sched/sched.h    | 17 +++++----------
 2 files changed, 38 insertions(+), 27 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3862a28cd05d..6524cb31148e 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2511,33 +2511,43 @@ const struct sched_class dl_sched_class
 	.update_curr		= update_curr_dl,
 };
 
+#ifdef CONFIG_SMP
+static struct cpumask dl_local_possible_mask;
+#endif /* CONFIG_SMP */
+
 int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	struct dl_bw *dl_b;
-	int cpu, ret = 0;
+	int cpu, cpus = 1, ret = 0;
 	unsigned long flags;
-
+	cpumask_t *possible_mask = NULL;
+#ifdef CONFIG_SMP
+	cpumask_t *span;
+#endif /* CONFIG_SMP */
 	/*
 	 * Here we want to check the bandwidth not being set to some
 	 * value smaller than the currently allocated bandwidth in
 	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
 	 */
-	for_each_possible_cpu(cpu) {
+#ifdef CONFIG_SMP
+	possible_mask = &dl_local_possible_mask;
+	cpumask_copy(possible_mask, cpu_possible_mask);
+#endif /* CONFIG_SMP */
+	for_each_cpu(cpu, possible_mask) {
 		rcu_read_lock_sched();
 		dl_b = dl_bw_of(cpu);
-
+#ifdef CONFIG_SMP
+		span = cpu_rq(cpu)->rd->span;
+		cpus = cpumask_weight(span);
+		cpumask_andnot(possible_mask, possible_mask, span);
+#endif /* CONFIG_SMP */
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
+		if (new_bw * cpus < dl_b->total_bw)
 			ret = -EBUSY;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
 		rcu_read_unlock_sched();
 
 		if (ret)
@@ -2566,6 +2576,10 @@ void sched_dl_do_global(void)
 	struct dl_bw *dl_b;
 	int cpu;
 	unsigned long flags;
+	cpumask_t *possible_mask = NULL;
+#ifdef CONFIG_SMP
+	cpumask_t *span;
+#endif /* CONFIG_SMP */
 
 	def_dl_bandwidth.dl_period = global_rt_period();
 	def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -2573,17 +2587,21 @@ void sched_dl_do_global(void)
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
-	/*
-	 * FIXME: As above...
-	 */
-	for_each_possible_cpu(cpu) {
+#ifdef CONFIG_SMP
+	possible_mask = &dl_local_possible_mask;
+	cpumask_copy(possible_mask, cpu_possible_mask);
+#endif /* CONFIG_SMP */
+	for_each_cpu(cpu, possible_mask) {
 		rcu_read_lock_sched();
 		dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		dl_b->bw = new_bw;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
+#ifdef CONFIG_SMP
+		span = cpu_rq(cpu)->rd->span;
+		cpumask_andnot(possible_mask, possible_mask, span);
+#endif /* CONFIG_SMP */
 		rcu_read_unlock_sched();
 		init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
 	}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 28709f6b0975..2602544e06ff 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -258,9 +258,9 @@ struct rt_bandwidth {
 void __dl_clear_params(struct task_struct *p);
 
 /*
- * To keep the bandwidth of -deadline tasks and groups under control
+ * To keep the bandwidth of -deadline tasks under control
  * we need some place where:
- *  - store the maximum -deadline bandwidth of the system (the group);
+ *  - store the maximum -deadline bandwidth of each root domain;
  *  - cache the fraction of that bandwidth that is currently allocated.
  *
  * This is all done in the data structure below. It is similar to the
@@ -269,17 +269,10 @@ void __dl_clear_params(struct task_struct *p);
  * do not decrease any runtime while the group "executes", neither we
  * need a timer to replenish it.
  *
- * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * With respect to SMP, the bandwidth is given on a per root domain basis,
  * meaning that:
- *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
- *  - dl_total_bw array contains, in the i-eth element, the currently
- *    allocated bandwidth on the i-eth CPU.
- * Moreover, groups consume bandwidth on each CPU, while tasks only
- * consume bandwidth on the CPU they're running on.
- * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
- * that will be shown the next time the proc or cgroup controls will
- * be red. It on its turn can be changed by writing on its own
- * control.
+ *  - bw (< 100%) is the bandwidth of the system on each CPU;
+ *  - total_bw is the currently allocated bandwidth on each root domain.
  */
 struct dl_bandwidth {
 	raw_spinlock_t		dl_runtime_lock;
-- 
2.20.1

Powered by blists - more mailing lists