[PATCH v5 05/15] sched/core: uclamp: update CPU's refcount on clamp changes

From: Patrick Bellasi
Date: Mon Oct 29 2018 - 14:33:51 EST

Utilization clamp values enforced on a CPU by a task can be updated at
run-time, for example via a sched_setattr syscall, while a task is
currently RUNNABLE on that CPU. In these cases, the task is already
refcounting a clamp group for its CPU and thus we need to update this
reference to ensure the new constraints are immediately enforced.

Since a clamp value change always implies a clamp group refcount update,
this patch hooks into uclamp_group_get() to trigger a CPU refcount
syncup, via uclamp_cpu_{put,get}_id(), whenever a task is RUNNABLE.

Signed-off-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Todd Kjos <tkjos@xxxxxxxxxx>
Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Quentin Perret <quentin.perret@xxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Morten Rasmussen <morten.rasmussen@xxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-pm@xxxxxxxxxxxxxxx

Changes in v5:
Message-ID: <20180914134128.GP1413@e110439-lin>
- remove not required uclamp_task_affects() since now all tasks always
have a valid clamp group assigned
- consistently use "unsigned int" for both clamp_id and group_id
- fixup documentation
- reduced usage of inline comments
- rebased on v4.19

Changes in v4:
Message-ID: <20180816132249.GA2960@e110439-lin>
- inline uclamp_task_active() code into uclamp_task_update_active()
- get rid of the now unused uclamp_task_active()
- allow to call uclamp_group_get() without a task pointer, which is
used to refcount the initial clamp group for all the global objects
(init_task, root_task_group and system_defaults)
- rebased on v4.19-rc1
Changes in v3:
Message-ID: <CAJuCfpF6=L=0LrmNnJrTNPazT4dWKqNv+thhN0dwpKCgUzs9sg@xxxxxxxxxxxxxx>
- rabased on tip/sched/core
Changes in v2:
Message-ID: <20180413111900.GF4082@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx>
- get rid of the group_id back annotation
which is not requires at this stage where we have only per-task
clamping support. It will be introduce later when CGroups support is
- rabased on v4.18-rc4
- this code has been split from a previous patch to simplify the review
kernel/sched/core.c | 60 ++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 54 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a98a96a7d9f1..21f6251a1d44 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -936,6 +936,48 @@ static inline void uclamp_cpu_put(struct rq *rq, struct task_struct *p)
uclamp_cpu_put_id(p, rq, clamp_id);

+ * uclamp_task_update_active: update the clamp group of a RUNNABLE task
+ * @p: the task which clamp groups must be updated
+ * @clamp_id: the clamp index to consider
+ *
+ * Each time the clamp value of a task group is changed, the old and new clamp
+ * groups must be updated for each CPU containing a RUNNABLE task belonging to
+ * that task group. Sleeping tasks are not updated since they will be enqueued
+ * with the proper clamp group index at their next activation.
+ */
+static inline void
+uclamp_task_update_active(struct task_struct *p, unsigned int clamp_id)
+ struct rq_flags rf;
+ struct rq *rq;
+ /*
+ * Lock the task and the CPU where the task is (or was) queued.
+ *
+ * We might lock the (previous) rq of a !RUNNABLE task, but that's the
+ * price to pay to safely serialize util_{min,max} updates with
+ * enqueues, dequeues and migration operations.
+ * This is the same locking schema used by __set_cpus_allowed_ptr().
+ */
+ rq = task_rq_lock(p, &rf);
+ /*
+ * The setting of the clamp group is serialized by task_rq_lock().
+ * Thus, if the task is not yet RUNNABLE and its task_struct is not
+ * affecting a valid clamp group, then the next time it's going to be
+ * enqueued it will already see the updated clamp group value.
+ */
+ if (!p->uclamp[clamp_id].active)
+ goto done;
+ uclamp_cpu_put_id(p, rq, clamp_id);
+ uclamp_cpu_get_id(p, rq, clamp_id);
+ task_rq_unlock(rq, p, &rf);
* uclamp_group_put: decrease the reference count for a clamp group
* @clamp_id: the clamp index which was affected by a task group
@@ -970,6 +1012,7 @@ static void uclamp_group_put(unsigned int clamp_id, unsigned int group_id)

* uclamp_group_get: increase the reference count for a clamp group
+ * @p: the task which clamp value must be tracked
* @uc_se: the utilization clamp data for the task
* @clamp_id: the clamp index affected by the task
* @clamp_value: the new clamp value for the task
@@ -980,8 +1023,8 @@ static void uclamp_group_put(unsigned int clamp_id, unsigned int group_id)
* reference count the corresponding clamp value while the task is enqueued on
* a CPU.
-static void uclamp_group_get(struct uclamp_se *uc_se, unsigned int clamp_id,
- unsigned int clamp_value)
+static void uclamp_group_get(struct task_struct *p, struct uclamp_se *uc_se,
+ unsigned int clamp_id, unsigned int clamp_value)
union uclamp_map *uc_maps = &uclamp_maps[clamp_id][0];
unsigned int prev_group_id = uc_se->group_id;
@@ -1046,6 +1089,10 @@ static void uclamp_group_get(struct uclamp_se *uc_se, unsigned int clamp_id,
uc_se->value = clamp_value;
uc_se->group_id = group_id;

+ /* Update CPU's clamp group refcounts of RUNNABLE task */
+ if (p)
+ uclamp_task_update_active(p, clamp_id);
/* Release the previous clamp group */
if (uc_se->mapped)
uclamp_group_put(clamp_id, prev_group_id);
@@ -1073,11 +1120,11 @@ static int __setscheduler_uclamp(struct task_struct *p,

/* Update each required clamp group */
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
- uclamp_group_get(&p->uclamp[UCLAMP_MIN],
+ uclamp_group_get(p, &p->uclamp[UCLAMP_MIN],
UCLAMP_MIN, lower_bound);
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
- uclamp_group_get(&p->uclamp[UCLAMP_MAX],
+ uclamp_group_get(p, &p->uclamp[UCLAMP_MAX],
UCLAMP_MAX, upper_bound);

@@ -1125,7 +1172,8 @@ static void uclamp_fork(struct task_struct *p, bool reset)

p->uclamp[clamp_id].mapped = false;
p->uclamp[clamp_id].active = false;
- uclamp_group_get(&p->uclamp[clamp_id], clamp_id, clamp_value);
+ uclamp_group_get(NULL, &p->uclamp[clamp_id],
+ clamp_id, clamp_value);

@@ -1146,7 +1194,7 @@ static void __init init_uclamp(void)
memset(uclamp_maps, 0, sizeof(uclamp_maps));
for (clamp_id = 0; clamp_id < UCLAMP_CNT; ++clamp_id) {
uc_se = &init_task.uclamp[clamp_id];
- uclamp_group_get(uc_se, clamp_id, uclamp_none(clamp_id));
+ uclamp_group_get(NULL, uc_se, clamp_id, uclamp_none(clamp_id));