[PATCH v4 04/16] sched/core: uclamp: update CPU's refcount on clamp changes

[Patrick Bellasi]

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 can be 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 the clamp group refcount getter to trigger a CPU
refcount syncup. Such a syncup is required only by currently RUNNABLE
tasks which are also referencing at least one valid clamp group.

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 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()
 Other:
 - 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>
 - rename UCLAMP_NONE into UCLAMP_NOT_VALID
 Other:
 - 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
   added.
 Other:
 - rabased on v4.18-rc4
 - this code has been split from a previous patch to simplify the review
---
 kernel/sched/core.c  | 65 ++++++++++++++++++++++++++++++++++++++++----
 kernel/sched/sched.h | 16 +++++++++++
 2 files changed, 76 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8f908035701f..64e5c96bfdaf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1080,6 +1080,54 @@ 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
+ * @group_id: the clamp group to update
+ *
+ * Each time the clamp value of a task group is changed, the old and new clamp
+ * groups have to be updated for each CPU containing a RUNNABLE task belonging
+ * to this tasks 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, int clamp_id, int group_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 (!task_on_rq_queued(p) && !p->on_cpu)
+		goto done;
+	if (!uclamp_task_affects(p, clamp_id))
+		goto done;
+
+	/* Release p's currently referenced clamp group */
+	uclamp_cpu_put_id(p, rq, clamp_id);
+
+	/* Get p's new clamp group */
+	uclamp_cpu_get_id(p, rq, clamp_id);
+
+done:
+	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
@@ -1115,6 +1163,7 @@ static inline void uclamp_group_put(int clamp_id, int group_id)
 
 /**
  * uclamp_group_get: increase the reference count for a clamp group
+ * @p: the task 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
@@ -1125,7 +1174,8 @@ static inline void uclamp_group_put(int clamp_id, int group_id)
  * this new clamp value. The corresponding clamp group index will be used by
  * the task to reference count the clamp value on CPUs while enqueued.
  */
-static inline void uclamp_group_get(int clamp_id, int next_group_id,
+static inline void uclamp_group_get(struct task_struct *p,
+				    int clamp_id, int next_group_id,
 				    struct uclamp_se *uc_se,
 				    unsigned int clamp_value)
 {
@@ -1144,6 +1194,10 @@ static inline void uclamp_group_get(int clamp_id, int next_group_id,
 	uc_map[next_group_id].se_count += 1;
 	raw_spin_unlock_irqrestore(&uc_map[next_group_id].se_lock, flags);
 
+	/* Update CPU's clamp group refcounts of RUNNABLE task */
+	if (p)
+		uclamp_task_update_active(p, clamp_id, next_group_id);
+
 	/* Release the previous clamp group */
 	uclamp_group_put(clamp_id, prev_group_id);
 }
@@ -1202,12 +1256,12 @@ 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(UCLAMP_MIN, group_id[UCLAMP_MIN],
+		uclamp_group_get(p, 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(UCLAMP_MAX, group_id[UCLAMP_MAX],
+		uclamp_group_get(p, UCLAMP_MAX, group_id[UCLAMP_MAX],
 				 uc_se, attr->sched_util_max);
 	}
 
@@ -1255,7 +1309,7 @@ static void uclamp_fork(struct task_struct *p, bool reset)
 		}
 
 		p->uclamp[clamp_id].group_id = UCLAMP_NOT_VALID;
-		uclamp_group_get(clamp_id, next_group_id, uc_se,
+		uclamp_group_get(NULL, clamp_id, next_group_id, uc_se,
 				 p->uclamp[clamp_id].value);
 	}
 }
@@ -1289,7 +1343,8 @@ static void __init init_uclamp(void)
 		/* Init init_task's clamp group */
 		uc_se = &init_task.uclamp[clamp_id];
 		uc_se->group_id = UCLAMP_NOT_VALID;
-		uclamp_group_get(clamp_id, 0, uc_se, uclamp_none(clamp_id));
+		uclamp_group_get(NULL, clamp_id, 0, uc_se,
+				 uclamp_none(clamp_id));
 	}
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 513608ae4908..25d1d218ae10 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2210,6 +2210,22 @@ static inline bool uclamp_group_active(struct uclamp_group *uc_grp,
 {
 	return uc_grp[group_id].tasks > 0;
 }
+
+/**
+ * uclamp_task_affects: check if a task affects a utilization clamp
+ * @p: the task to consider
+ * @clamp_id: the utilization clamp to check
+ *
+ * A task affects a clamp index if:
+ * - it's currently enqueued on a CPU
+ * - it references a valid clamp group index for the specified clamp index
+ *
+ * Return: true if p currently affects the specified clamp_id
+ */
+static inline bool uclamp_task_affects(struct task_struct *p, int clamp_id)
+{
+	return (p->uclamp[clamp_id].group_id != UCLAMP_NOT_VALID);
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef CONFIG_CPU_FREQ
-- 
2.18.0