sched/uclamp: Propagate parent clamps

In order to properly support hierarchical resources control, the cgroup
delegation model requires that attribute writes from a child group never
fail but still are locally consistent and constrained based on parent's
assigned resources. This requires to properly propagate and aggregate
parent attributes down to its descendants.

Implement this mechanism by adding a new "effective" clamp value for each
task group. The effective clamp value is defined as the smaller value
between the clamp value of a group and the effective clamp value of its
parent. This is the actual clamp value enforced on tasks in a task group.

Since it's possible for a cpu.uclamp.min value to be bigger than the
cpu.uclamp.max value, ensure local consistency by restricting each
"protection" (i.e. min utilization) with the corresponding "limit"
(i.e. max utilization).

Do that at effective clamps propagation to ensure all user-space write
never fails while still always tracking the most restrictive values.

Signed-off-by: Patrick Bellasi <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Michal Koutny <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Cc: Alessio Balsini <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Morten Rasmussen <[email protected]>
Cc: Paul Turner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Quentin Perret <[email protected]>
Cc: Rafael J . Wysocki <[email protected]>
Cc: Steve Muckle <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Todd Kjos <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Viresh Kumar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

2 files changed, 46 insertions, 0 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c186abed5c6d..8855481857b5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1166,6 +1166,7 @@ static void __init init_uclamp(void)
 		uclamp_default[clamp_id] = uc_max;
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 		root_task_group.uclamp_req[clamp_id] = uc_max;
+		root_task_group.uclamp[clamp_id] = uc_max;
 #endif
 	}
 }
@@ -6824,6 +6825,7 @@ static inline void alloc_uclamp_sched_group(struct task_group *tg,
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&tg->uclamp_req[clamp_id],
 			      uclamp_none(clamp_id), false);
+		tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
 	}
 #endif
 }
@@ -7070,6 +7072,45 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 }
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css)
+{
+	struct cgroup_subsys_state *top_css = css;
+	struct uclamp_se *uc_parent = NULL;
+	struct uclamp_se *uc_se = NULL;
+	unsigned int eff[UCLAMP_CNT];
+	unsigned int clamp_id;
+	unsigned int clamps;
+
+	css_for_each_descendant_pre(css, top_css) {
+		uc_parent = css_tg(css)->parent
+			? css_tg(css)->parent->uclamp : NULL;
+
+		for_each_clamp_id(clamp_id) {
+			/* Assume effective clamps matches requested clamps */
+			eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
+			/* Cap effective clamps with parent's effective clamps */
+			if (uc_parent &&
+			    eff[clamp_id] > uc_parent[clamp_id].value) {
+				eff[clamp_id] = uc_parent[clamp_id].value;
+			}
+		}
+		/* Ensure protection is always capped by limit */
+		eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);
+
+		/* Propagate most restrictive effective clamps */
+		clamps = 0x0;
+		uc_se = css_tg(css)->uclamp;
+		for_each_clamp_id(clamp_id) {
+			if (eff[clamp_id] == uc_se[clamp_id].value)
+				continue;
+			uc_se[clamp_id].value = eff[clamp_id];
+			uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
+			clamps |= (0x1 << clamp_id);
+		}
+		if (!clamps)
+			css = css_rightmost_descendant(css);
+	}
+}
 
 /*
  * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
@@ -7138,6 +7179,9 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	 */
 	tg->uclamp_pct[clamp_id] = req.percent;
 
+	/* Update effective clamps to track the most restrictive value */
+	cpu_util_update_eff(of_css(of));
+
 	rcu_read_unlock();
 	mutex_unlock(&uclamp_mutex);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ae1be61fb279..5b343112a47b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -397,6 +397,8 @@ struct task_group {
 	unsigned int		uclamp_pct[UCLAMP_CNT];
 	/* Clamp values requested for a task group */
 	struct uclamp_se	uclamp_req[UCLAMP_CNT];
+	/* Effective clamp values used for a task group */
+	struct uclamp_se	uclamp[UCLAMP_CNT];
 #endif
 
 };