[PATCH v3 1/1] sched/uclamp: add SCHED_FLAG_UTIL_CLAMP_RESET flag to reset uclamp

[Yun Hsiang <hsiang023167@gmail.com>]

If the user wants to stop controlling uclamp and let the task inherit
the value from the group, we need a method to reset.

Add SCHED_FLAG_UTIL_CLAMP_RESET flag to allow the user to reset uclamp via
sched_setattr syscall.

The policy is
_CLAMP_RESET                           => reset both min and max
_CLAMP_RESET | _CLAMP_MIN              => reset min value
_CLAMP_RESET | _CLAMP_MAX              => reset max value
_CLAMP_RESET | _CLAMP_MIN | _CLAMP_MAX => reset both min and max

Signed-off-by: Yun Hsiang <hsiang023167@gmail.com>
---
 include/uapi/linux/sched.h |  7 +++++--
 kernel/sched/core.c        | 41 +++++++++++++++++++++++++++++++-------
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..6c823ddb1a1e 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -132,17 +132,20 @@ struct clone_args {
 #define SCHED_FLAG_KEEP_PARAMS		0x10
 #define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
 #define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+#define SCHED_FLAG_UTIL_CLAMP_RESET	0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
 
 #define SCHED_FLAG_UTIL_CLAMP	(SCHED_FLAG_UTIL_CLAMP_MIN | \
-				 SCHED_FLAG_UTIL_CLAMP_MAX)
+				 SCHED_FLAG_UTIL_CLAMP_MAX | \
+				 SCHED_FLAG_UTIL_CLAMP_RESET)
 
 #define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
 			 SCHED_FLAG_RECLAIM		| \
 			 SCHED_FLAG_DL_OVERRUN		| \
 			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
+			 SCHED_FLAG_UTIL_CLAMP		| \
+			 SCHED_FLAG_UTIL_CLAMP_RESET)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8160ab5263f8..b337f8d3b5ae 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1438,9 +1438,22 @@ static int uclamp_validate(struct task_struct *p,
 	return 0;
 }
 
+static unsigned int __default_uclamp_value(struct task_struct *p,
+					int clamp_id)
+{
+	if (rt_task(p) && clamp_id == UCLAMP_MIN)
+		return sysctl_sched_uclamp_util_min_rt_default;
+	else
+		return uclamp_none(clamp_id);
+}
+
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr)
 {
+	int reset = attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_RESET;
+	bool user_defined;
+	unsigned int clamp_value;
+	unsigned long flags = attr->sched_flags & SCHED_FLAG_UTIL_CLAMP;
 	enum uclamp_id clamp_id;
 
 	/*
@@ -1451,7 +1464,8 @@ static void __setscheduler_uclamp(struct task_struct *p,
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
 
 		/* Keep using defined clamps across class changes */
-		if (uc_se->user_defined)
+		if (flags != SCHED_FLAG_UTIL_CLAMP_RESET &&
+				uc_se->user_defined)
 			continue;
 
 		/*
@@ -1462,20 +1476,33 @@ static void __setscheduler_uclamp(struct task_struct *p,
 			__uclamp_update_util_min_rt_default(p);
 		else
 			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
-
 	}
 
-	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
+	if (likely(!flags || flags == SCHED_FLAG_UTIL_CLAMP_RESET))
 		return;
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+	if (flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+		if (reset) {
+			clamp_value = __default_uclamp_value(p, UCLAMP_MIN);
+			user_defined = false;
+		} else {
+			clamp_value = attr->sched_util_min;
+			user_defined = true;
+		}
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
-			      attr->sched_util_min, true);
+				clamp_value, user_defined);
 	}
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+	if (flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+		if (reset) {
+			clamp_value = __default_uclamp_value(p, UCLAMP_MAX);
+			user_defined = false;
+		} else {
+			clamp_value = attr->sched_util_max;
+			user_defined = true;
+		}
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
-			      attr->sched_util_max, true);
+				clamp_value, user_defined);
 	}
 }
 
-- 
2.25.1