[PATCH] sched: RT bandwidth interface for cgroup unified hierarchy

[Chengming Zhou]

We need to run RT threads in cgroup unified hierarchy, but we can't
since the default rt_bandwidth.rt_runtime of non-root task_group is 0
and we haven't interface to update it.

This patch add RT bandwidth interface "cpu.max.rt" and update the
documentation accordingly.

Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
---
 Documentation/admin-guide/cgroup-v2.rst | 13 +++++++++++
 kernel/sched/core.c                     | 31 +++++++++++++++++++++++++
 kernel/sched/rt.c                       |  2 +-
 kernel/sched/sched.h                    |  1 +
 4 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 176298f2f4de..3d2949e16e04 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1055,6 +1055,19 @@ All time durations are in microseconds.
 
 	The burst in the range [0, $MAX].
 
+  cpu.max.rt
+	A read-write two value file which exists on all cgroups when
+	CONFIG_RT_GROUP_SCHED enabled, to control CPU bandwidth for
+	RT threads in the task group.
+
+	The maximum bandwidth limit.  It's in the following format::
+
+	  $MAX $PERIOD
+
+	which indicates that RT threads in the group may consume upto
+	$MAX in each $PERIOD duration.  "max" for $MAX indicates no
+	limit.  If only one number is written, $MAX is updated.
+
   cpu.pressure
 	A read-write nested-keyed file.
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index daadedc78fd9..c16f8cc5de08 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11047,6 +11047,30 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
 }
 #endif
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static int cpu_max_rt_show(struct seq_file *sf, void *v)
+{
+	struct task_group *tg = css_tg(seq_css(sf));
+
+	cpu_period_quota_print(sf, sched_group_rt_period(tg), sched_group_rt_runtime(tg));
+	return 0;
+}
+
+static ssize_t cpu_max_rt_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct task_group *tg = css_tg(of_css(of));
+	u64 period = sched_group_rt_period(tg);
+	u64 runtime;
+	int ret;
+
+	ret = cpu_period_quota_parse(buf, &period, &runtime);
+	if (!ret)
+		ret = tg_set_rt_bandwidth(tg, period, runtime);
+	return ret ?: nbytes;
+}
+#endif
+
 static struct cftype cpu_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
@@ -11082,6 +11106,13 @@ static struct cftype cpu_files[] = {
 		.write_u64 = cpu_cfs_burst_write_u64,
 	},
 #endif
+#ifdef CONFIG_RT_GROUP_SCHED
+	{
+		.name = "max.rt",
+		.seq_show = cpu_max_rt_show,
+		.write = cpu_max_rt_write,
+	},
+#endif
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	{
 		.name = "uclamp.min",
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8c9ed9664840..319ce586446f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2819,7 +2819,7 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 	return ret;
 }
 
-static int tg_set_rt_bandwidth(struct task_group *tg,
+int tg_set_rt_bandwidth(struct task_group *tg,
 		u64 rt_period, u64 rt_runtime)
 {
 	int i, err = 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b19a72408b1..317480d535b0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -486,6 +486,7 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
+extern int tg_set_rt_bandwidth(struct task_group *tg, u64 rt_period, u64 rt_runtime);
 extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
 extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
 extern long sched_group_rt_runtime(struct task_group *tg);
-- 
2.36.1