sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets

commit 6c24849f5515e4966d94fa5279bdff4acf2e9489 upstream.

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 (Google) <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>
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 355f796c5f0781c506adb3039fbf5a835d035026..0348dba5680efa27ed7ae5491c9fbe8fb66e56ed 100644 (file)
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -71,6 +71,8 @@ extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_wait_for_hotplug(void);
+extern void inc_dl_tasks_cs(struct task_struct *task);
+extern void dec_dl_tasks_cs(struct task_struct *task);
 extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
@@ -196,6 +198,8 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
+static inline void inc_dl_tasks_cs(struct task_struct *task) { }
+static inline void dec_dl_tasks_cs(struct task_struct *task) { }
 static inline void cpuset_lock(void) { }
 static inline void cpuset_unlock(void) { }
 

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 73f11e4db3a4d289e0413a820420259365d6a831..97ecca43386d93f12f1b4791f5d311e27ed4b0a4 100644 (file)
--- 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>
 
@@ -6681,6 +6682,9 @@ 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 a8a060fea074293c4acd2626b13c09606937d8f4..5f57829bb9865cd4c607a06f18777433ac3d8559 100644 (file)
--- 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,
@@ -2494,6 +2514,11 @@ 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 f7d381b6c313369a4ae0c7d1c659462d2bc50c74..98154a93e05d32c992e63f7acf7da01221c0c7e2 100644 (file)
--- 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
@@ -2597,6 +2599,12 @@ 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
@@ -2637,6 +2645,12 @@ 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);