sched/core: uclamp: update CPU's refcount on TG's clamp changes

When a task group refcounts a new clamp group, we need to ensure that
the new clamp values are immediately enforced to all its tasks which are
currently RUNNABLE. This is to ensure that all currently RUNNABLE tasks
are boosted and/or clamped as requested as soon as possible.

Let's ensure that, whenever a new clamp group is refcounted by a task
group, all its RUNNABLE tasks are correctly accounted in their
respective CPUs. We do that by slightly refactoring uclamp_group_get()
to get an additional parameter *cgroup_subsys_state which, when
provided, it's used to walk the list of tasks in the corresponding TGs
and update the RUNNABLE ones.

This is a "brute force" solution which allows to reuse the same refcount
update code already used by the per-task API. That's also the only way
to ensure a prompt enforcement of new clamp constraints on RUNNABLE
tasks, as soon as a task group attribute is tweaked.

Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Paul Turner <pjt@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Todd Kjos <tkjos@google.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Steve Muckle <smuckle@google.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-pm@vger.kernel.org
---
Changes in v3:
 - rebased on tip/sched/core
 - fixed some typos

Changes in v2:
 - rebased on v4.18-rc4
 - this code has been split from a previous patch to simplify the review

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 48458fea2d5e9c23559ee4e83df7d9b7f6ff6223..6db307803047d495af7a63d43a2174433e777408 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1255,9 +1255,30 @@ static inline void uclamp_group_put(int clamp_id, int group_id)
        raw_spin_unlock_irqrestore(&uc_map[group_id].se_lock, flags);
 }
 
+static inline void uclamp_group_get_tg(struct cgroup_subsys_state *css,
+                                      int clamp_id, unsigned int group_id)
+{
+       struct css_task_iter it;
+       struct task_struct *p;
+
+       /*
+        * In lazy update mode, tasks will be accounted into the right clamp
+        * group the next time they will be requeued.
+        */
+       if (unlikely(sched_feat(UCLAMP_LAZY_UPDATE)))
+               return;
+
+       /* Update clamp groups for RUNNABLE tasks in this TG */
+       css_task_iter_start(css, 0, &it);
+       while ((p = css_task_iter_next(&it)))
+               uclamp_task_update_active(p, clamp_id, group_id);
+       css_task_iter_end(&it);
+}
+
 /**
  * uclamp_group_get: increase the reference count for a clamp group
  * @p: the task which clamp value must be tracked
+ * @css: the task group which clamp value must be tracked
  * @clamp_id: the clamp index affected by the task
  * @next_group_id: the clamp group to refcount
  * @uc_se: the utilization clamp data for the task
@@ -1269,6 +1290,7 @@ static inline void uclamp_group_put(int clamp_id, int group_id)
  * the task to reference count the clamp value on CPUs while enqueued.
  */
 static inline void uclamp_group_get(struct task_struct *p,
+                                   struct cgroup_subsys_state *css,
                                    int clamp_id, int next_group_id,
                                    struct uclamp_se *uc_se,
                                    unsigned int clamp_value)
@@ -1288,6 +1310,10 @@ static inline void uclamp_group_get(struct task_struct *p,
        uc_map[next_group_id].se_count += 1;
        raw_spin_unlock_irqrestore(&uc_map[next_group_id].se_lock, flags);
 
+       /* Newly created TG don't have tasks assigned */
+       if (css)
+               uclamp_group_get_tg(css, clamp_id, next_group_id);
+
        /* Update CPU's clamp group refcounts of RUNNABLE task */
        if (p)
                uclamp_task_update_active(p, clamp_id, next_group_id);
@@ -1344,12 +1370,12 @@ int sched_uclamp_handler(struct ctl_table *table, int write,
        /* Update each required clamp group */
        if (old_min != sysctl_sched_uclamp_util_min) {
                uc_se = &uclamp_default[UCLAMP_MIN];
-               uclamp_group_get(NULL, UCLAMP_MIN, group_id[UCLAMP_MIN],
+               uclamp_group_get(NULL, NULL, UCLAMP_MIN, group_id[UCLAMP_MIN],
                                 uc_se, sysctl_sched_uclamp_util_min);
        }
        if (old_max != sysctl_sched_uclamp_util_max) {
                uc_se = &uclamp_default[UCLAMP_MAX];
-               uclamp_group_get(NULL, UCLAMP_MAX, group_id[UCLAMP_MAX],
+               uclamp_group_get(NULL, NULL, UCLAMP_MAX, group_id[UCLAMP_MAX],
                                 uc_se, sysctl_sched_uclamp_util_max);
        }
 
@@ -1441,7 +1467,7 @@ static inline int alloc_uclamp_sched_group(struct task_group *tg,
                        return 0;
                }
 #endif
-               uclamp_group_get(NULL, clamp_id, group_id, uc_se,
+               uclamp_group_get(NULL, NULL, clamp_id, group_id, uc_se,
                                 parent->uclamp[clamp_id].value);
        }
 
@@ -1532,12 +1558,12 @@ static inline int __setscheduler_uclamp(struct task_struct *p,
        /* Update each required clamp group */
        if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
                uc_se = &p->uclamp[UCLAMP_MIN];
-               uclamp_group_get(p, UCLAMP_MIN, group_id[UCLAMP_MIN],
+               uclamp_group_get(p, NULL, UCLAMP_MIN, group_id[UCLAMP_MIN],
                                 uc_se, attr->sched_util_min);
        }
        if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
                uc_se = &p->uclamp[UCLAMP_MAX];
-               uclamp_group_get(p, UCLAMP_MAX, group_id[UCLAMP_MAX],
+               uclamp_group_get(p, NULL, UCLAMP_MAX, group_id[UCLAMP_MAX],
                                 uc_se, attr->sched_util_max);
        }
 
@@ -7468,6 +7494,10 @@ static void cpu_util_update_hier(struct cgroup_subsys_state *css,
 
                uc_se->effective.value = value;
                uc_se->effective.group_id = group_id;
+
+               /* Immediately updated descendants active tasks */
+               if (css != top_css)
+                       uclamp_group_get_tg(css, clamp_id, group_id);
        }
 }
 
@@ -7508,7 +7538,7 @@ static int cpu_util_min_write_u64(struct cgroup_subsys_state *css,
 
        /* Update TG's reference count */
        uc_se = &tg->uclamp[UCLAMP_MIN];
-       uclamp_group_get(NULL, UCLAMP_MIN, group_id, uc_se, min_value);
+       uclamp_group_get(NULL, css, UCLAMP_MIN, group_id, uc_se, min_value);
 
 out:
        rcu_read_unlock();
@@ -7554,7 +7584,7 @@ static int cpu_util_max_write_u64(struct cgroup_subsys_state *css,
 
        /* Update TG's reference count */
        uc_se = &tg->uclamp[UCLAMP_MAX];
-       uclamp_group_get(NULL, UCLAMP_MAX, group_id, uc_se, max_value);
+       uclamp_group_get(NULL, css, UCLAMP_MAX, group_id, uc_se, max_value);
 
 out:
        rcu_read_unlock();

diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index a3ca449e36c14226bf1e64dfe0a1cd1b115c36b9..ced86cfd8fcdb15d93ce169715933ccb6c523e9b 100644 (file)
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -91,6 +91,11 @@ SCHED_FEAT(WA_BIAS, true)
  */
 SCHED_FEAT(UTIL_EST, true)
 
+/*
+ * Utilization clamping lazy update.
+ */
+SCHED_FEAT(UCLAMP_LAZY_UPDATE, false)
+
 /*
  * Per class CPU's utilization clamping.
  */