[PATCH 03/17] sched/fair: Add sched group latency support

[Peter Zijlstra <peterz@infradead.org>]

From: Vincent Guittot <vincent.guittot@linaro.org>

Task can set its latency priority with sched_setattr(), which is then used
to set the latency offset of its sched_enity, but sched group entities
still have the default latency offset value.

Add a latency.nice field in cpu cgroup controller to set the latency
priority of the group similarly to sched_setattr(). The latency priority
is then used to set the offset of the sched_entities of the group.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20230224093454.956298-7-vincent.guittot@linaro.org
---
 Documentation/admin-guide/cgroup-v2.rst |   10 ++++++++++
 kernel/sched/core.c                     |   30 ++++++++++++++++++++++++++++++
 kernel/sched/fair.c                     |   32 ++++++++++++++++++++++++++++++++
 kernel/sched/sched.h                    |    4 ++++
 4 files changed, 76 insertions(+)

--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1121,6 +1121,16 @@ All time durations are in microseconds.
         values similar to the sched_setattr(2). This maximum utilization
         value is used to clamp the task specific maximum utilization clamp.
 
+  cpu.latency.nice
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	The nice value is in the range [-20, 19].
+
+	This interface file allows reading and setting latency using the
+	same values used by sched_setattr(2). The latency_nice of a group is
+	used to limit the impact of the latency_nice of a task outside the
+	group.
 
 
 Memory
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11068,6 +11068,25 @@ static int cpu_idle_write_s64(struct cgr
 {
 	return sched_group_set_idle(css_tg(css), idle);
 }
+
+static s64 cpu_latency_nice_read_s64(struct cgroup_subsys_state *css,
+				    struct cftype *cft)
+{
+	return PRIO_TO_NICE(css_tg(css)->latency_prio);
+}
+
+static int cpu_latency_nice_write_s64(struct cgroup_subsys_state *css,
+				     struct cftype *cft, s64 nice)
+{
+	int prio;
+
+	if (nice < MIN_NICE || nice > MAX_NICE)
+		return -ERANGE;
+
+	prio = NICE_TO_PRIO(nice);
+
+	return sched_group_set_latency(css_tg(css), prio);
+}
 #endif
 
 static struct cftype cpu_legacy_files[] = {
@@ -11082,6 +11101,11 @@ static struct cftype cpu_legacy_files[]
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency.nice",
+		.read_s64 = cpu_latency_nice_read_s64,
+		.write_s64 = cpu_latency_nice_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
@@ -11299,6 +11323,12 @@ static struct cftype cpu_files[] = {
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency.nice",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_latency_nice_read_s64,
+		.write_s64 = cpu_latency_nice_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12264,6 +12264,7 @@ int alloc_fair_sched_group(struct task_g
 		goto err;
 
 	tg->shares = NICE_0_LOAD;
+	tg->latency_prio = DEFAULT_PRIO;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
@@ -12362,6 +12363,9 @@ void init_tg_cfs_entry(struct task_group
 	}
 
 	se->my_q = cfs_rq;
+
+	se->latency_offset = calc_latency_offset(tg->latency_prio - MAX_RT_PRIO);
+
 	/* guarantee group entities always have weight */
 	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
@@ -12490,6 +12494,34 @@ int sched_group_set_idle(struct task_gro
 
 	mutex_unlock(&shares_mutex);
 	return 0;
+}
+
+int sched_group_set_latency(struct task_group *tg, int prio)
+{
+	long latency_offset;
+	int i;
+
+	if (tg == &root_task_group)
+		return -EINVAL;
+
+	mutex_lock(&shares_mutex);
+
+	if (tg->latency_prio == prio) {
+		mutex_unlock(&shares_mutex);
+		return 0;
+	}
+
+	tg->latency_prio = prio;
+	latency_offset = calc_latency_offset(prio - MAX_RT_PRIO);
+
+	for_each_possible_cpu(i) {
+		struct sched_entity *se = tg->se[i];
+
+		WRITE_ONCE(se->latency_offset, latency_offset);
+	}
+
+	mutex_unlock(&shares_mutex);
+	return 0;
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -378,6 +378,8 @@ struct task_group {
 
 	/* A positive value indicates that this is a SCHED_IDLE group. */
 	int			idle;
+	/* latency priority of the group. */
+	int			latency_prio;
 
 #ifdef	CONFIG_SMP
 	/*
@@ -488,6 +490,8 @@ extern int sched_group_set_shares(struct
 
 extern int sched_group_set_idle(struct task_group *tg, long idle);
 
+extern int sched_group_set_latency(struct task_group *tg, int prio);
+
 #ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);