sched/uclamp: Allow to reset a task uclamp constraint value

In case the user wants to stop controlling a uclamp constraint value
for a task, use the magic value -1 in sched_util_{min,max} with the
appropriate sched_flags (SCHED_FLAG_UTIL_CLAMP_{MIN,MAX}) to indicate
the reset.

The advantage over the 'additional flag' approach (i.e. introducing
SCHED_FLAG_UTIL_CLAMP_RESET) is that no additional flag has to be
exported via uapi. This avoids the need to document how this new flag
has be used in conjunction with the existing uclamp related flags.

The following subtle issue is fixed as well. When a uclamp constraint
value is set on a !user_defined uclamp_se it is currently first reset
and then set.
Fix this by AND'ing !user_defined with !SCHED_FLAG_UTIL_CLAMP which
stands for the 'sched class change' case.
The related condition 'if (uc_se->user_defined)' moved from
__setscheduler_uclamp() into uclamp_reset().

Signed-off-by: Dietmar Eggemann <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Yun Hsiang <[e-mail]>
Link: https://lkml.kernel.org/r/[e-mail]

include/uapi/linux/sched/types.h

···
  * on a CPU with a capacity big enough to fit the specified value.
  * A task with a max utilization value smaller than 1024 is more likely
  * scheduled on a CPU with no more capacity than the specified value.
+ *
+ * A task utilization boundary can be reset by setting the attribute to -1.
  */
 struct sched_attr {
 	__u32 size;

kernel/sched/core.c

···
 static int uclamp_validate(struct task_struct *p,
 			   const struct sched_attr *attr)
 {
-	unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value;
-	unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value;
+	int util_min = p->uclamp_req[UCLAMP_MIN].value;
+	int util_max = p->uclamp_req[UCLAMP_MAX].value;
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN)
-		lower_bound = attr->sched_util_min;
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX)
-		upper_bound = attr->sched_util_max;
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+		util_min = attr->sched_util_min;
 
-	if (lower_bound > upper_bound)
-		return -EINVAL;
-	if (upper_bound > SCHED_CAPACITY_SCALE)
+		if (util_min + 1 > SCHED_CAPACITY_SCALE + 1)
+			return -EINVAL;
+	}
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+		util_max = attr->sched_util_max;
+
+		if (util_max + 1 > SCHED_CAPACITY_SCALE + 1)
+			return -EINVAL;
+	}
+
+	if (util_min != -1 && util_max != -1 && util_min > util_max)
 		return -EINVAL;
 
 	/*
···
 	return 0;
 }
 
+static bool uclamp_reset(const struct sched_attr *attr,
+			 enum uclamp_id clamp_id,
+			 struct uclamp_se *uc_se)
+{
+	/* Reset on sched class change for a non user-defined clamp value. */
+	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) &&
+	    !uc_se->user_defined)
+		return true;
+
+	/* Reset on sched_util_{min,max} == -1. */
+	if (clamp_id == UCLAMP_MIN &&
+	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
+	    attr->sched_util_min == -1) {
+		return true;
+	}
+
+	if (clamp_id == UCLAMP_MAX &&
+	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
+	    attr->sched_util_max == -1) {
+		return true;
+	}
+
+	return false;
+}
+
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr)
 {
 	enum uclamp_id clamp_id;
 
-	/*
-	 * On scheduling class change, reset to default clamps for tasks
-	 * without a task-specific value.
-	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
+		unsigned int value;
 
-		/* Keep using defined clamps across class changes */
-		if (uc_se->user_defined)
+		if (!uclamp_reset(attr, clamp_id, uc_se))
 			continue;
 
 		/*
···
 		 * at runtime.
 		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			__uclamp_update_util_min_rt_default(p);
+			value = sysctl_sched_uclamp_util_min_rt_default;
 		else
-			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
+			value = uclamp_none(clamp_id);
+
+		uclamp_se_set(uc_se, value, false);
 
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
 		return;
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
+	    attr->sched_util_min != -1) {
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
 			      attr->sched_util_min, true);
 	}
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
+	    attr->sched_util_max != -1) {
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
 			      attr->sched_util_max, true);
 	}