sched/uclamp: Fix uclamp_tg_restrict()

Now cpu.uclamp.min acts as a protection, we need to make sure that the
uclamp request of the task is within the allowed range of the cgroup,
that is it is clamp()'ed correctly by tg->uclamp[UCLAMP_MIN] and
tg->uclamp[UCLAMP_MAX].

As reported by Xuewen [1] we can have some corner cases where there's
inversion between uclamp requested by task (p) and the uclamp values of
the taskgroup it's attached to (tg). Following table demonstrates
2 corner cases:

	           |  p  |  tg  |  effective
	-----------+-----+------+-----------
	CASE 1
	-----------+-----+------+-----------
	uclamp_min | 60% | 0%   |  60%
	-----------+-----+------+-----------
	uclamp_max | 80% | 50%  |  50%
	-----------+-----+------+-----------
	CASE 2
	-----------+-----+------+-----------
	uclamp_min | 0%  | 30%  |  30%
	-----------+-----+------+-----------
	uclamp_max | 20% | 50%  |  20%
	-----------+-----+------+-----------

With this fix we get:

	           |  p  |  tg  |  effective
	-----------+-----+------+-----------
	CASE 1
	-----------+-----+------+-----------
	uclamp_min | 60% | 0%   |  50%
	-----------+-----+------+-----------
	uclamp_max | 80% | 50%  |  50%
	-----------+-----+------+-----------
	CASE 2
	-----------+-----+------+-----------
	uclamp_min | 0%  | 30%  |  30%
	-----------+-----+------+-----------
	uclamp_max | 20% | 50%  |  30%
	-----------+-----+------+-----------

Additionally uclamp_update_active_tasks() must now unconditionally
update both UCLAMP_MIN/MAX because changing the tg's UCLAMP_MAX for
instance could have an impact on the effective UCLAMP_MIN of the tasks.

	           |  p  |  tg  |  effective
	-----------+-----+------+-----------
	old
	-----------+-----+------+-----------
	uclamp_min | 60% | 0%   |  50%
	-----------+-----+------+-----------
	uclamp_max | 80% | 50%  |  50%
	-----------+-----+------+-----------
	*new*
	-----------+-----+------+-----------
	uclamp_min | 60% | 0%   | *60%*
	-----------+-----+------+-----------
	uclamp_max | 80% |*70%* | *70%*
	-----------+-----+------+-----------

[1] https://lore.kernel.org/lkml/CAB8ipk_a6VFNjiEnHRHkUMBKbA+qzPQvhtNjJ_YNzQhqV_o8Zw@mail.gmail.com/

Fixes: 0c18f2ecfc ("sched/uclamp: Fix wrong implementation of cpu.uclamp.min")
Reported-by: Xuewen Yan <xuewen.yan94@gmail.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210617165155.3774110-1-qais.yousef@arm.com

kernel/sched/core.c

@@ -1403,8 +1403,10 @@ static void uclamp_sync_util_min_rt_default(void)
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
+	/* Copy by value as we could modify it */
 	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
 #ifdef CONFIG_UCLAMP_TASK_GROUP
+	unsigned int tg_min, tg_max, value;
 
 	/*
 	 * Tasks in autogroups or root task group will be
@@ -1415,23 +1417,11 @@ uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 	if (task_group(p) == &root_task_group)
 		return uc_req;
 
-	switch (clamp_id) {
+	tg_min = task_group(p)->uclamp[UCLAMP_MIN].value;
-	case UCLAMP_MIN: {
+	tg_max = task_group(p)->uclamp[UCLAMP_MAX].value;
-		struct uclamp_se uc_min = task_group(p)->uclamp[clamp_id];
+	value = uc_req.value;
-		if (uc_req.value < uc_min.value)
+	value = clamp(value, tg_min, tg_max);
-			return uc_min;
+	uclamp_se_set(&uc_req, value, false);
-		break;
-	}
-	case UCLAMP_MAX: {
-		struct uclamp_se uc_max = task_group(p)->uclamp[clamp_id];
-		if (uc_req.value > uc_max.value)
-			return uc_max;
-		break;
-	}
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
 #endif
 
 	return uc_req;
@@ -1630,8 +1620,9 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 }
 
 static inline void
-uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+uclamp_update_active(struct task_struct *p)
 {
+	enum uclamp_id clamp_id;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -1651,30 +1642,26 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
+	for_each_clamp_id(clamp_id) {
 		if (p->uclamp[clamp_id].active) {
 			uclamp_rq_dec_id(rq, p, clamp_id);
 			uclamp_rq_inc_id(rq, p, clamp_id);
 		}
+	}
 
 	task_rq_unlock(rq, p, &rf);
 }
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static inline void
-uclamp_update_active_tasks(struct cgroup_subsys_state *css,
+uclamp_update_active_tasks(struct cgroup_subsys_state *css)
-			   unsigned int clamps)
 {
-	enum uclamp_id clamp_id;
 	struct css_task_iter it;
 	struct task_struct *p;
 
 	css_task_iter_start(css, 0, &it);
-	while ((p = css_task_iter_next(&it))) {
+	while ((p = css_task_iter_next(&it)))
-		for_each_clamp_id(clamp_id) {
+		uclamp_update_active(p);
-			if ((0x1 << clamp_id) & clamps)
-				uclamp_update_active(p, clamp_id);
-		}
-	}
 	css_task_iter_end(&it);
 }
 
@@ -9634,7 +9621,7 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css)
 		}
 
 		/* Immediately update descendants RUNNABLE tasks */
-		uclamp_update_active_tasks(css, clamps);
+		uclamp_update_active_tasks(css);
 	}
 }