sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets

Qais reported that iterating over all tasks when rebuilding root domains
for finding out which ones are DEADLINE and need their bandwidth
correctly restored on such root domains can be a costly operation (10+
ms delays on suspend-resume).

To fix the problem keep track of the number of DEADLINE tasks belonging
to each cpuset and then use this information (followup patch) to only
perform the above iteration if DEADLINE tasks are actually present in
the cpuset for which a corresponding root domain is being rebuilt.

Reported-by: Qais Yousef <qyousef@layalina.io>
Link: https://lore.kernel.org/lkml/20230206221428.2125324-1-qyousef@layalina.io/
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 43 insertions, 0 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..9d809191a54f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -57,6 +57,7 @@
 #include <linux/file.h>
 #include <linux/fs_parser.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/deadline.h>
 #include <linux/psi.h>
 #include <net/sock.h>
 
@@ -6683,6 +6684,9 @@ void cgroup_exit(struct task_struct *tsk)
 	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
 
+	if (dl_task(tsk))
+		dec_dl_tasks_cs(tsk);
+
 	WARN_ON_ONCE(cgroup_task_frozen(tsk));
 	if (unlikely(!(tsk->flags & PF_KTHREAD) &&
 		     test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 041c0809adaf..ca195ff8b298 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -193,6 +193,12 @@ struct cpuset {
 	int use_parent_ecpus;
 	int child_ecpus_count;
 
+	/*
+	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
+	 * know when to rebuild associated root domain bandwidth information.
+	 */
+	int nr_deadline_tasks;
+
 	/* Invalid partition error code, not lock protected */
 	enum prs_errcode prs_err;
 
@@ -245,6 +251,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs)
 	return css_cs(cs->css.parent);
 }
 
+void inc_dl_tasks_cs(struct task_struct *p)
+{
+	struct cpuset *cs = task_cs(p);
+
+	cs->nr_deadline_tasks++;
+}
+
+void dec_dl_tasks_cs(struct task_struct *p)
+{
+	struct cpuset *cs = task_cs(p);
+
+	cs->nr_deadline_tasks--;
+}
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_ONLINE,
@@ -2499,6 +2519,11 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		ret = security_task_setscheduler(task);
 		if (ret)
 			goto out_unlock;
+
+		if (dl_task(task)) {
+			cs->nr_deadline_tasks++;
+			cpuset_attach_old_cs->nr_deadline_tasks--;
+		}
 	}
 
 	/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5a9a4b81c972..e11de074a6fd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,8 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 
+#include <linux/cpuset.h>
+
 /*
  * Default limits for DL period; on the top end we guard against small util
  * tasks still getting ridiculously long effective runtimes, on the bottom end we
@@ -2596,6 +2598,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
 		task_non_contending(p);
 
+	/*
+	 * In case a task is setscheduled out from SCHED_DEADLINE we need to
+	 * keep track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	dec_dl_tasks_cs(p);
+
 	if (!task_on_rq_queued(p)) {
 		/*
 		 * Inactive timer is armed. However, p is leaving DEADLINE and
@@ -2636,6 +2644,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
 		put_task_struct(p);
 
+	/*
+	 * In case a task is setscheduled to SCHED_DEADLINE we need to keep
+	 * track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	inc_dl_tasks_cs(p);
+
 	/* If p is not queued we will update its parameters at next wakeup. */
 	if (!task_on_rq_queued(p)) {
 		add_rq_bw(&p->dl, &rq->dl);