[PATCH] sched/uclamp: Add new flag to control cgroup behavior

[Qais Yousef]

Signed-off-by: Qais Yousef <qais.yousef@xxxxxxx>
---
 include/linux/sched.h      |  1 +
 include/uapi/linux/sched.h |  6 ++++++
 kernel/sched/core.c        | 25 ++++++++++++++++---------
 3 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index afe01e232935..6eb35dfaa893 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -604,6 +604,7 @@ struct uclamp_se {
 	unsigned int bucket_id		: bits_per(UCLAMP_BUCKETS);
 	unsigned int active		: 1;
 	unsigned int user_defined	: 1;
+	unsigned int follow_cgroup	: 1;
 };
 #endif /* CONFIG_UCLAMP_TASK */
 
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..33ff716a7574 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -132,6 +132,12 @@ struct clone_args {
 #define SCHED_FLAG_KEEP_PARAMS		0x10
 #define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
 #define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+/*
+ * Control whether a task follows/inherits the cgroup uclamp.min/max or not.
+ * By default this flag is set for all tasks. Any explicit modification to a
+ * task's UCLAMP_MIN/MAX must set this flag to retain the bahavior.
+ */
+#define SCHED_FLAG_UTIL_FOLLOW_CGROUP	0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d95dc3f4644..1c77d6b8bd96 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1083,7 +1083,7 @@ uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 		return uc_req;
 
 	uc_max = task_group(p)->uclamp[clamp_id];
-	if (uc_req.value > uc_max.value || !uc_req.user_defined)
+	if (uc_req.value > uc_max.value || uc_req.follow_cgroup)
 		return uc_max;
 #endif
 
@@ -1446,6 +1446,7 @@ static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr)
 {
 	enum uclamp_id clamp_id;
+	bool follow_cgroup;
 
 	/*
 	 * On scheduling class change, reset to default clamps for tasks
@@ -1472,14 +1473,18 @@ static void __setscheduler_uclamp(struct task_struct *p,
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
 		return;
 
+	follow_cgroup = attr->sched_flags & SCHED_FLAG_UTIL_FOLLOW_CGROUP;
+
 	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
-		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
-			      attr->sched_util_min, true);
+		struct uclamp_se *uc_se = &p->uclamp_req[UCLAMP_MIN];
+		uc_se->follow_cgroup = follow_cgroup;
+		uclamp_se_set(uc_se, attr->sched_util_min, true);
 	}
 
 	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
-		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
-			      attr->sched_util_max, true);
+		struct uclamp_se *uc_se = &p->uclamp_req[UCLAMP_MAX];
+		uc_se->follow_cgroup = follow_cgroup;
+		uclamp_se_set(uc_se, attr->sched_util_max, true);
 	}
 }
 
@@ -1498,8 +1503,9 @@ static void uclamp_fork(struct task_struct *p)
 		return;
 
 	for_each_clamp_id(clamp_id) {
-		uclamp_se_set(&p->uclamp_req[clamp_id],
-			      uclamp_none(clamp_id), false);
+		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
+		uc_se->follow_cgroup = true;
+		uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 	}
 }
 
@@ -1532,8 +1538,9 @@ static void __init init_uclamp(void)
 		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
-		uclamp_se_set(&init_task.uclamp_req[clamp_id],
-			      uclamp_none(clamp_id), false);
+		struct uclamp_se *uc_se = &init_task.uclamp_req[clamp_id];
+		uc_se->follow_cgroup = true;
+		uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 	}
 
 	/* System defaults allow max clamp values for both indexes */
-- 
2.25.1