[PATCH] sched/uclamp: Fix uclamp_tg_restrict()

[Qais Yousef]

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
inverstion 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@xxxxxxxxxxxxxx/

Reported-by: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Fixes: 0c18f2ecfcc2 ("sched/uclamp: Fix wrong implementation of cpu.uclamp.min")
Signed-off-by: Qais Yousef <qais.yousef@xxxxxxx>
---

Xuewen, Yun, Wei

If you can give this a spin and provide Tested-by that would be much
appreciated.

Thanks!


 kernel/sched/core.c | 43 +++++++++++++++----------------------------
 1 file changed, 15 insertions(+), 28 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9e9a5be35cde..0318b00baa97 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1403,38 +1403,28 @@ 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)
 {
-	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+	/* Copy by value as we could modify it */
+	struct uclamp_se uc_eff = 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
 	 * restricted by system defaults.
 	 */
 	if (task_group_is_autogroup(task_group(p)))
-		return uc_req;
+		return uc_eff;
 	if (task_group(p) == &root_task_group)
-		return uc_req;
+		return uc_eff;
 
-	switch (clamp_id) {
-	case UCLAMP_MIN: {
-		struct uclamp_se uc_min = task_group(p)->uclamp[clamp_id];
-		if (uc_req.value < uc_min.value)
-			return uc_min;
-		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;
-	}
+	tg_min = task_group(p)->uclamp[UCLAMP_MIN].value;
+	tg_max = task_group(p)->uclamp[UCLAMP_MAX].value;
+	value = uc_eff.value;
+	value = clamp(value, tg_min, tg_max);
+	uclamp_se_set(&uc_eff, value, false);
 #endif
 
-	return uc_req;
+	return uc_eff;
 }
 
 /*
@@ -1661,8 +1651,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static inline void
-uclamp_update_active_tasks(struct cgroup_subsys_state *css,
-			   unsigned int clamps)
+uclamp_update_active_tasks(struct cgroup_subsys_state *css)
 {
 	enum uclamp_id clamp_id;
 	struct css_task_iter it;
@@ -1670,10 +1659,8 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css,
 
 	css_task_iter_start(css, 0, &it);
 	while ((p = css_task_iter_next(&it))) {
-		for_each_clamp_id(clamp_id) {
-			if ((0x1 << clamp_id) & clamps)
-				uclamp_update_active(p, clamp_id);
-		}
+		for_each_clamp_id(clamp_id)
+			uclamp_update_active(p, clamp_id);
 	}
 	css_task_iter_end(&it);
 }
@@ -9626,7 +9613,7 @@ 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);
 	}
 }
 
-- 
2.25.1