[PATCH 03/10] sched: Allow sched_{get,set}attr to change latency_nice of the task

[Peter Zijlstra]

From: Parth Shah <parth@xxxxxxxxxxxxx>

Introduce the latency_nice attribute to sched_attr and provide a
mechanism to change the value with the use of sched_setattr/sched_getattr
syscall.

Also add new flag "SCHED_FLAG_LATENCY_NICE" to hint the change in
latency_nice of the task on every sched_setattr syscall.

[rebase and add a dedicated __setscheduler_latency ]
Signed-off-by: Parth Shah <parth@xxxxxxxxxxxxx>
Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Tested-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Link: https://lkml.kernel.org/r/20230224093454.956298-5-vincent.guittot@xxxxxxxxxx
---
 include/uapi/linux/sched.h       |  4 +++-
 include/uapi/linux/sched/types.h | 19 +++++++++++++++++++
 kernel/sched/core.c              | 24 ++++++++++++++++++++++++
 tools/include/uapi/linux/sched.h |  4 +++-
 4 files changed, 49 insertions(+), 2 deletions(-)

Index: linux-2.6/include/uapi/linux/sched.h
===================================================================
--- linux-2.6.orig/include/uapi/linux/sched.h
+++ linux-2.6/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ 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_LATENCY_NICE		0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
 			 SCHED_FLAG_RECLAIM		| \
 			 SCHED_FLAG_DL_OVERRUN		| \
 			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
+			 SCHED_FLAG_UTIL_CLAMP		| \
+			 SCHED_FLAG_LATENCY_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */
Index: linux-2.6/include/uapi/linux/sched/types.h
===================================================================
--- linux-2.6.orig/include/uapi/linux/sched/types.h
+++ linux-2.6/include/uapi/linux/sched/types.h
@@ -10,6 +10,7 @@ struct sched_param {
 
 #define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
 #define SCHED_ATTR_SIZE_VER1	56	/* add: util_{min,max} */
+#define SCHED_ATTR_SIZE_VER2	60	/* add: latency_nice */
 
 /*
  * Extended scheduling parameters data structure.
@@ -98,6 +99,22 @@ struct sched_param {
  * scheduled on a CPU with no more capacity than the specified value.
  *
  * A task utilization boundary can be reset by setting the attribute to -1.
+ *
+ * Latency Tolerance Attributes
+ * ===========================
+ *
+ * A subset of sched_attr attributes allows to specify the relative latency
+ * requirements of a task with respect to the other tasks running/queued in the
+ * system.
+ *
+ * @ sched_latency_nice	task's latency_nice value
+ *
+ * The latency_nice of a task can have any value in a range of
+ * [MIN_LATENCY_NICE..MAX_LATENCY_NICE].
+ *
+ * A task with latency_nice with the value of LATENCY_NICE_MIN can be
+ * taken for a task requiring a lower latency as opposed to the task with
+ * higher latency_nice.
  */
 struct sched_attr {
 	__u32 size;
@@ -120,6 +137,8 @@ struct sched_attr {
 	__u32 sched_util_min;
 	__u32 sched_util_max;
 
+	/* latency requirement hints */
+	__s32 sched_latency_nice;
 };
 
 #endif /* _UAPI_LINUX_SCHED_TYPES_H */
Index: linux-2.6/kernel/sched/core.c
===================================================================
--- linux-2.6.orig/kernel/sched/core.c
+++ linux-2.6/kernel/sched/core.c
@@ -7451,6 +7451,13 @@ static void __setscheduler_params(struct
 	p->rt_priority = attr->sched_priority;
 	p->normal_prio = normal_prio(p);
 	set_load_weight(p, true);
+}
+
+static void __setscheduler_latency(struct task_struct *p,
+		const struct sched_attr *attr)
+{
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE)
+		p->latency_nice = attr->sched_latency_nice;
 }
 
 /*
@@ -7593,6 +7601,13 @@ recheck:
 			return retval;
 	}
 
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		if (attr->sched_latency_nice > MAX_LATENCY_NICE)
+			return -EINVAL;
+		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
+			return -EINVAL;
+	}
+
 	if (pi)
 		cpuset_read_lock();
 
@@ -7627,6 +7642,9 @@ recheck:
 			goto change;
 		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
 			goto change;
+		if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE &&
+		    attr->sched_latency_nice != p->latency_nice)
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		retval = 0;
@@ -7715,6 +7733,7 @@ change:
 		__setscheduler_params(p, attr);
 		__setscheduler_prio(p, newprio);
 	}
+	__setscheduler_latency(p, attr);
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
@@ -7925,6 +7944,9 @@ static int sched_copy_attr(struct sched_
 	    size < SCHED_ATTR_SIZE_VER1)
 		return -EINVAL;
 
+	if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
+	    size < SCHED_ATTR_SIZE_VER2)
+		return -EINVAL;
 	/*
 	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
@@ -8162,6 +8184,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pi
 	get_params(p, &kattr);
 	kattr.sched_flags &= SCHED_FLAG_ALL;
 
+	kattr.sched_latency_nice = p->latency_nice;
+
 #ifdef CONFIG_UCLAMP_TASK
 	/*
 	 * This could race with another potential updater, but this is fine
Index: linux-2.6/tools/include/uapi/linux/sched.h
===================================================================
--- linux-2.6.orig/tools/include/uapi/linux/sched.h
+++ linux-2.6/tools/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ 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_LATENCY_NICE		0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
 			 SCHED_FLAG_RECLAIM		| \
 			 SCHED_FLAG_DL_OVERRUN		| \
 			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
+			 SCHED_FLAG_UTIL_CLAMP		| \
+			 SCHED_FLAG_LATENCY_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */