sched/deadline: Walk up cpuset hierarchy to decide root domain when hot-unplug

*** Bug description ***
When testing kexec-reboot on a 144 cpus machine with
isolcpus=managed_irq,domain,1-71,73-143 in kernel command line, I
encounter the following bug:

[   97.114759] psci: CPU142 killed (polled 0 ms)
[   97.333236] Failed to offline CPU143 - error=-16
[   97.333246] ------------[ cut here ]------------
[   97.342682] kernel BUG at kernel/cpu.c:1569!
[   97.347049] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
[...]

In essence, the issue originates from the CPU hot-removal process, not
limited to kexec. It can be reproduced by writing a SCHED_DEADLINE
program that waits indefinitely on a semaphore, spawning multiple
instances to ensure some run on CPU 72, and then offlining CPUs 1–143
one by one. When attempting this, CPU 143 failed to go offline.
  bash -c 'taskset -cp 0 $$ && for i in {1..143}; do echo 0 > /sys/devices/system/cpu/cpu$i/online 2>/dev/null; done'

Tracking down this issue, I found that dl_bw_deactivate() returned
-EBUSY, which caused sched_cpu_deactivate() to fail on the last CPU.
But that is not the fact, and contributed by the following factors:
When a CPU is inactive, cpu_rq()->rd is set to def_root_domain. For an
blocked-state deadline task (in this case, "cppc_fie"), it was not
migrated to CPU0, and its task_rq() information is stale. So its rq->rd
points to def_root_domain instead of the one shared with CPU0.  As a
result, its bandwidth is wrongly accounted into a wrong root domain
during domain rebuild.

*** Issue ***
The key point is that root_domain is only tracked through active rq->rd.
To avoid using a global data structure to track all root_domains in the
system, there should be a method to locate an active CPU within the
corresponding root_domain.

*** Solution ***
To locate the active cpu, the following rules for deadline
sub-system is useful
  -1.any cpu belongs to a unique root domain at a given time
  -2.DL bandwidth checker ensures that the root domain has active cpus.

Now, let's examine the blocked-state task P.
If P is attached to a cpuset that is a partition root, it is
straightforward to find an active CPU.
If P is attached to a cpuset that has changed from 'root' to 'member',
the active CPUs are grouped into the parent root domain. Naturally, the
CPUs' capacity and reserved DL bandwidth are taken into account in the
ancestor root domain. (In practice, it may be unsafe to attach P to an
arbitrary root domain, since that domain may lack sufficient DL
bandwidth for P.) Again, it is straightforward to find an active CPU in
the ancestor root domain.

This patch groups CPUs into isolated and housekeeping sets. For the
housekeeping group, it walks up the cpuset hierarchy to find active CPUs
in P's root domain and retrieves the valid rd from cpu_rq(cpu)->rd.

Signed-off-by: Pingfan Liu <[email protected]>
Cc: Waiman Long <[email protected]>
Cc: Chen Ridong <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Pierre Gondois <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Ben Segall <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Valentin Schneider <[email protected]>
To: [email protected]
Signed-off-by: Tejun Heo <[email protected]>

Author: Pingfan Liu

kernel/sched/deadline.c

@@ -2465,6 +2465,7 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu
 	return NULL;
 }
 
+/* Access rule: must be called on local CPU with preemption disabled */
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)
@@ -2907,28 +2908,69 @@ void __init init_sched_dl_class(void)
 					GFP_KERNEL, cpu_to_node(i));
 }
 
+/*
+ * This function always returns a non-empty bitmap in @cpus. This is because
+ * if a root domain has reserved bandwidth for DL tasks, the DL bandwidth
+ * check will prevent CPU hotplug from deactivating all CPUs in that domain.
+ */
+static void dl_get_task_effective_cpus(struct task_struct *p, struct cpumask *cpus)
+{
+	const struct cpumask *hk_msk;
+
+	hk_msk = housekeeping_cpumask(HK_TYPE_DOMAIN);
+	if (housekeeping_enabled(HK_TYPE_DOMAIN)) {
+		if (!cpumask_intersects(p->cpus_ptr, hk_msk)) {
+			/*
+			 * CPUs isolated by isolcpu="domain" always belong to
+			 * def_root_domain.
+			 */
+			cpumask_andnot(cpus, cpu_active_mask, hk_msk);
+			return;
+		}
+	}
+
+	/*
+	 * If a root domain holds a DL task, it must have active CPUs. So
+	 * active CPUs can always be found by walking up the task's cpuset
+	 * hierarchy up to the partition root.
+	 */
+	cpuset_cpus_allowed_locked(p, cpus);
+}
+
+/* The caller should hold cpuset_mutex */
 void dl_add_task_root_domain(struct task_struct *p)
 {
 	struct rq_flags rf;
 	struct rq *rq;
 	struct dl_bw *dl_b;
+	unsigned int cpu;
+	struct cpumask *msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 	if (!dl_task(p) || dl_entity_is_special(&p->dl)) {
 		raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 		return;
 	}
 
-	rq = __task_rq_lock(p, &rf);
-
+	/*
+	 * Get an active rq, whose rq->rd traces the correct root
+	 * domain.
+	 * Ideally this would be under cpuset reader lock until rq->rd is
+	 * fetched.  However, sleepable locks cannot nest inside pi_lock, so we
+	 * rely on the caller of dl_add_task_root_domain() holds 'cpuset_mutex'
+	 * to guarantee the CPU stays in the cpuset.
+	 */
+	dl_get_task_effective_cpus(p, msk);
+	cpu = cpumask_first_and(cpu_active_mask, msk);
+	BUG_ON(cpu >= nr_cpu_ids);
+	rq = cpu_rq(cpu);
 	dl_b = &rq->rd->dl_bw;
-	raw_spin_lock(&dl_b->lock);
+	/* End of fetching rd */
 
+	raw_spin_lock(&dl_b->lock);
 	__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
-
 	raw_spin_unlock(&dl_b->lock);
-
-	task_rq_unlock(rq, p, &rf);
+	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 }
 
 void dl_clear_root_domain(struct root_domain *rd)