[PATCH v5 22/29] sched/deadline: Make a rebuild use the CPU recorded with a task's bandwidth

[Mathieu Desnoyers <mathieu.desnoyers@efficios.com>]

A rebuild of the accounting counts each deadline task on the first
active CPU of its cpuset. Commit 318e18ed22e8 ("sched/deadline: Walk up
cpuset hierarchy to decide root domain when hot-unplug") made this
choice. It relies on the bandwidth check to keep such a CPU active.
This guess would go wrong in three ways:

 - A cpuset, like the root one, can hold CPUs isolated by
   isolcpus="domain" beside housekeeping CPUs. If an isolated CPU comes
   first, the task would be counted in the default root domain. Its own
   root domain would then be short of that bandwidth.
 - A task confined to isolated CPUs can see them all go offline. The
   rebuild would then find no active CPU, and hit its BUG_ON().
 - dl_task_offline_migration() moves a throttled task, with its
   bandwidth, off CPUs that went offline. The rebuild would count it in
   its cpuset, not where it moved.

Use the CPU the task is on, if it is active and in the task's mask. A
mask can hold CPUs of both root domains, for instance after
select_fallback_rq() widened it. Else use dl_bw_cpu, the CPU recorded
with the bandwidth, if it is active and in the mask. A task moved asleep
is not on its new CPUs yet. Else take the first active CPU of the mask,
a housekeeping one if any. A partition change sets the task masks before
its rebuild, and the housekeeping mask after, so the mask comes first.
With no active CPU in the mask, take dl_bw_cpu if active, else ask the
cpuset.

Leave out a task with no active CPU, instead of the BUG_ON(). dl_bw_gen
then keeps its release from removing anything.
dl_task_offline_migration() counts it again when it moves it.

A task that select_fallback_rq() moves to another root domain still runs
where its bandwidth is not counted. The next patch moves the bandwidth
with it.

The Sashiko AI reviews of v1 to v4 found these cases.

Fixes: f9a25f776d78 ("cpusets: Rebuild root domain deadline accounting information")
Cc: stable@vger.kernel.org
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
---
 kernel/sched/deadline.c | 83 +++++++++++++++++++++++++++++++++++------
 1 file changed, 72 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8d9e55bca943..bc31045e4686 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -910,14 +910,20 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 			__dl_sub(dl_b, p->dl.dl_bw,
 				 cpumask_weight(src_rq->rd->span));
 			raw_spin_unlock(&dl_b->lock);
-
-			dl_b = &later_rq->rd->dl_bw;
-			raw_spin_lock(&dl_b->lock);
-			__dl_add(dl_b, p->dl.dl_bw,
-				 cpumask_weight(later_rq->rd->span));
-			raw_spin_unlock(&dl_b->lock);
 		}
+		/*
+		 * Count the bandwidth in the root domain the task moves to.
+		 * Do it also when a rebuild left the task out, for want of an
+		 * active CPU. A rebuild that reaches the task after this finds
+		 * its dl_bw_gen current, and leaves it alone.
+		 */
+		dl_b = &later_rq->rd->dl_bw;
+		raw_spin_lock(&dl_b->lock);
+		__dl_add(dl_b, p->dl.dl_bw,
+			 cpumask_weight(later_rq->rd->span));
+		raw_spin_unlock(&dl_b->lock);
 		p->dl.dl_bw_cpu = later_rq->cpu;
+		p->dl.dl_bw_gen = dl_bw_gen;
 	}
 
 	set_task_cpu(p, later_rq->cpu);
@@ -3720,6 +3726,55 @@ static void dl_get_task_effective_cpus(struct task_struct *p, struct cpumask *cp
 	cpuset_cpus_allowed_locked(p, cpus);
 }
 
+/*
+ * Return a CPU of the root domain where a rebuild of the accounting should
+ * count the bandwidth of @p, or nr_cpu_ids if there is none.
+ *
+ * Prefer the CPU @p is on, if it is active and in the mask of @p. The
+ * task runs, or wakes up, in the root domain of that CPU. A mask can hold
+ * CPUs of two root domains: housekeeping CPUs and CPUs isolated by
+ * isolcpus="domain". When every CPU of a mask goes offline,
+ * select_fallback_rq() can widen it to both. It moves no bandwidth.
+ *
+ * Else prefer the CPU recorded with the bandwidth, if it is active and in
+ * the mask. It is in the root domain that admitted the bandwidth, or that
+ * its last move put it in. A task moved asleep is still on a CPU of the
+ * root domain it left, out of its mask. Else take the first active CPU of
+ * the mask, a housekeeping one if there is one. A task on isolated CPUs
+ * that all went offline can have no active CPU at all.
+ */
+static unsigned int dl_task_rebuild_cpu(struct task_struct *p)
+{
+	struct cpumask *msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
+	int recorded = p->dl.dl_bw_cpu;
+	unsigned int cpu;
+
+	/*
+	 * Look at the mask of the task first. A change of the cpusets sets
+	 * the mask of each task before its rebuild. The housekeeping mask
+	 * that dl_get_task_effective_cpus() reads is updated after it. If no
+	 * CPU of the mask is active, take the CPU recorded if it is active:
+	 * dl_task_offline_migration() moved the task there. Else ask the
+	 * cpuset.
+	 */
+	cpumask_and(msk, &p->cpus_mask, cpu_active_mask);
+	cpu = task_cpu(p);
+	if (cpumask_test_cpu(cpu, msk))
+		return cpu;
+	if (cpumask_empty(msk)) {
+		if (recorded >= 0 && cpu_active(recorded))
+			return recorded;
+		dl_get_task_effective_cpus(p, msk);
+		cpumask_and(msk, msk, cpu_active_mask);
+	}
+	if (recorded >= 0 && cpumask_test_cpu(recorded, msk))
+		return recorded;
+	cpu = cpumask_first_and(msk, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
+	if (cpu < nr_cpu_ids)
+		return cpu;
+	return cpumask_first(msk);
+}
+
 /* From dl_rebuild_rd_accounting(), under the locks it asserts. */
 void dl_add_task_root_domain(struct task_struct *p)
 {
@@ -3727,7 +3782,6 @@ void dl_add_task_root_domain(struct task_struct *p)
 	struct rq *rq;
 	struct dl_bw *dl_b;
 	unsigned int cpu;
-	struct cpumask *msk;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 	/*
@@ -3742,10 +3796,17 @@ void dl_add_task_root_domain(struct task_struct *p)
 		return;
 	}
 
-	msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
-	dl_get_task_effective_cpus(p, msk);
-	cpu = cpumask_first_and(cpu_active_mask, msk);
-	BUG_ON(cpu >= nr_cpu_ids);
+	cpu = dl_task_rebuild_cpu(p);
+	if (cpu >= nr_cpu_ids) {
+		/*
+		 * No active CPU can count the bandwidth of this task. Leave it
+		 * out of this rebuild. dl_bw_gen then keeps its release from
+		 * removing anything. A later rebuild, or
+		 * dl_task_offline_migration(), counts it again.
+		 */
+		raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
+		return;
+	}
 
 	raw_spin_lock(&dl_departed_lock);
 	/*
-- 
2.47.3