cgroup/cpuset: Reserve DL bandwidth only for root-domain moves

cpuset_can_attach() currently adds the bandwidth of all migrating
SCHED_DEADLINE tasks to sum_migrate_dl_bw. If the source and destination
cpuset effective CPU masks do not overlap, the whole sum is then
reserved in the destination root domain.

set_cpus_allowed_dl(), however, subtracts bandwidth from the source
root domain only when the affinity change really moves the task between
root domains. A DL task can move between cpusets that are still in the
same root domain, so including that task in sum_migrate_dl_bw can reserve
destination bandwidth without a matching source-side subtraction.

Share the root-domain move test with set_cpus_allowed_dl(). Keep
nr_migrate_dl_tasks counting all migrating deadline tasks for cpuset DL
task accounting, but add to sum_migrate_dl_bw only for tasks that need a
root-domain bandwidth move. Keep using the destination cpuset effective
CPU mask and leave the broader can_attach()/attach() transaction model
unchanged.

Fixes: 2ef269ef1ac0 ("cgroup/cpuset: Free DL BW in case can_attach() fails")
Cc: stable@vger.kernel.org # v6.10+
Signed-off-by: Guopeng Zhang <zhangguopeng@kylinos.cn>
Reviewed-by: Waiman Long <longman@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 29 insertions, 18 deletions

diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index bb4e692bea30..f7aaf01f7cd5 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -167,6 +167,7 @@ struct cpuset {
 	 */
 	int nr_deadline_tasks;
 	int nr_migrate_dl_tasks;
+	/* DL bandwidth that needs destination reservation for this attach. */
 	u64 sum_migrate_dl_bw;
 	/*
 	 * CPU used for temporary DL bandwidth allocation during attach;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3fbf6e7f68c3..e84e801e22cf 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2993,7 +2993,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
 	bool setsched_check;
-	int ret;
+	int cpu, ret;
 
 	/* used later by cpuset_attach() */
 	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
@@ -3038,28 +3038,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		}
 
 		if (dl_task(task)) {
+			/*
+			 * Count all migrating DL tasks for cpuset task accounting.
+			 * Only tasks that need a root-domain bandwidth move
+			 * contribute to sum_migrate_dl_bw.
+			 */
 			cs->nr_migrate_dl_tasks++;
-			cs->sum_migrate_dl_bw += task->dl.dl_bw;
+			if (dl_task_needs_bw_move(task, cs->effective_cpus))
+				cs->sum_migrate_dl_bw += task->dl.dl_bw;
 		}
 	}
 
-	if (!cs->nr_migrate_dl_tasks)
+	if (!cs->sum_migrate_dl_bw)
 		goto out_success;
 
-	if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
-
-		if (unlikely(cpu >= nr_cpu_ids)) {
-			ret = -EINVAL;
-			goto out_unlock;
-		}
+	cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
+	if (unlikely(cpu >= nr_cpu_ids)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
 
-		ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
-		if (ret)
-			goto out_unlock;
+	ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
+	if (ret)
+		goto out_unlock;
 
-		cs->dl_bw_cpu = cpu;
-	}
+	cs->dl_bw_cpu = cpu;
 
 out_success:
 	/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index edca7849b165..7db4c87df83b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3107,20 +3107,18 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 static void set_cpus_allowed_dl(struct task_struct *p,
 				struct affinity_context *ctx)
 {
-	struct root_domain *src_rd;
 	struct rq *rq;
 
 	WARN_ON_ONCE(!dl_task(p));
 
 	rq = task_rq(p);
-	src_rd = rq->rd;
 	/*
 	 * Migrating a SCHED_DEADLINE task between exclusive
 	 * cpusets (different root_domains) entails a bandwidth
 	 * update. We already made space for us in the destination
 	 * domain (see cpuset_can_attach()).
 	 */
-	if (!cpumask_intersects(src_rd->span, ctx->new_mask)) {
+	if (dl_task_needs_bw_move(p, ctx->new_mask)) {
 		struct dl_bw *src_dl_b;
 
 		src_dl_b = dl_bw_of(cpu_of(rq));
@@ -3137,6 +3135,15 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	set_cpus_allowed_common(p, ctx);
 }
 
+bool dl_task_needs_bw_move(struct task_struct *p,
+			   const struct cpumask *new_mask)
+{
+	if (!dl_task(p))
+		return false;
+
+	return !cpumask_intersects(task_rq(p)->rd->span, new_mask);
+}
+
 /* Assumes rq->lock is held */
 static void rq_online_dl(struct rq *rq)
 {