[PATCH v2 4/7] sched: Move DL's admission control to sysfs

[Sebastian Andrzej Siewior]

SCHED_DL uses the sysctl sched_rt_{period|runtime}_us to configure its
admission control. It is used to verify that it does not allocate more
time gobally to SCHED_DL tasks than it can theoretically handle.

This sysctl used to control RT throttling. With the introduction of the
DL server this knob controls RT throttling within a RT-cgroup if
CONFIG_RT_GROUP_SCHED is enabled. In this case the knob is also stuck
and can not be changed. So it can not be used for SCHED_DL control at
all. Unless to disable it by writing -1.

Split the DL bits into its knob at sysfs' location. Once the DL logic
is out, sched_domains_mutex.*() and rebuild_sched_domains() can be
removed from sched_rt_handler().

Move SCHED_DL usage of this sysctl to /sys/kernel/sched/ as
dl_runtime_us + dl_period_us. Replace global_rt_period()/
global_rt_runtime() with sysfs_dl_period/ sysfs_dl_runtime. Store the
new attribues in ns. Move global_rt_period()/ global_rt_runtime() to
CONFIG_RT_GROUP_SCHED.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
 Documentation/arch/arm64/asymmetric-32bit.rst |   2 +-
 Documentation/scheduler/sched-deadline.rst    |  15 +--
 kernel/sched/deadline.c                       | 163 ++++++++++++++++++++++++--
 kernel/sched/rt.c                             |  25 +---
 kernel/sched/sched.h                          |  28 ++---
 5 files changed, 174 insertions(+), 59 deletions(-)

diff --git a/Documentation/arch/arm64/asymmetric-32bit.rst b/Documentation/arch/arm64/asymmetric-32bit.rst
index fc0c350c5e001..375958f8971e5 100644
--- a/Documentation/arch/arm64/asymmetric-32bit.rst
+++ b/Documentation/arch/arm64/asymmetric-32bit.rst
@@ -105,7 +105,7 @@ affinity for the task is updated and any saved mask from a prior
 Explicit admission of a 32-bit deadline task to the default root domain
 (e.g. by calling ``sched_setattr(2)``) is rejected on an asymmetric
 32-bit system unless admission control is disabled by writing -1 to
-``/proc/sys/kernel/sched_rt_runtime_us``.
+``/sys/kernel/sched/dl_runtime_us``.
 
 ``execve(2)`` of a 32-bit program from a 64-bit deadline task will
 return ``-ENOEXEC`` if the root domain for the task contains any
diff --git a/Documentation/scheduler/sched-deadline.rst b/Documentation/scheduler/sched-deadline.rst
index 9019b66f6a5ba..23ea88b2ed7dc 100644
--- a/Documentation/scheduler/sched-deadline.rst
+++ b/Documentation/scheduler/sched-deadline.rst
@@ -590,24 +590,19 @@ Deadline Task Scheduling
 4.1 System wide settings
 ------------------------
 
- The system wide settings are configured under the /proc virtual file system.
+ The system wide settings are configured under /sys/kernel/sched.
 
- For now the -rt knobs are used for -deadline admission control and with
- CONFIG_RT_GROUP_SCHED the -deadline runtime is accounted against the (root)
- -rt runtime. With !CONFIG_RT_GROUP_SCHED the knob only serves for the -dl
- admission control. We realize that this isn't entirely desirable; however, it
- is better to have a small interface for now, and be able to change it easily
- later. The ideal situation (see 5.) is to run -rt tasks from a -deadline
- server; in which case the -rt bandwidth is a direct subset of dl_bw.
+ The ideal situation (see 5.) is to run -rt tasks from a -deadline server; in
+ which case the -rt bandwidth is a direct subset of dl_bw.
 
  This means that, for a root_domain comprising M CPUs, -deadline tasks
  can be created while the sum of their bandwidths stays below:
 
-   M * (sched_rt_runtime_us / sched_rt_period_us)
+   M * (dl_runtime_us / dl_period_us)
 
  It is also possible to disable this bandwidth management logic, and
  be thus free of oversubscribing the system up to any arbitrary level.
- This is done by writing -1 in /proc/sys/kernel/sched_rt_runtime_us.
+ This is done by writing -1 in /sys/kernel/sched/dl_runtime_us.
 
 
 4.2 Task interface
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 24633af261be6..c5a2499a1450a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -23,6 +23,14 @@
 #include "sched.h"
 #include "pelt.h"
 
+/*
+ * Admission control for DL tasks. For a root_domain comprising M CPUs,
+ * -deadline tasks can be created while the sum of their bandwidths stays
+ *  below:  M * (dl_period / dl_runtime)
+ */
+static u64 sysfs_dl_period  = 1000000 * NSEC_PER_USEC;
+static u64 sysfs_dl_runtime = 1000000 * NSEC_PER_USEC;
+
 /*
  * Default limits for DL period; on the top end we guard against small util
  * tasks still getting ridiculously long effective runtimes, on the bottom end we
@@ -509,10 +517,10 @@ static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
-	if (global_rt_runtime() == RUNTIME_INF)
+	if (sysfs_dl_runtime == RUNTIME_INF)
 		dl_b->bw = -1;
 	else
-		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
+		dl_b->bw = to_ratio(sysfs_dl_period, sysfs_dl_runtime);
 	dl_b->total_bw = 0;
 }
 
@@ -3712,10 +3720,8 @@ DEFINE_SCHED_CLASS(dl) = {
  */
 u64 dl_cookie;
 
-int sched_dl_global_validate(void)
+static int sched_dl_global_validate(u64 runtime, u64 period)
 {
-	u64 runtime = global_rt_runtime();
-	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	u64 cookie = ++dl_cookie;
 	struct dl_bw *dl_b;
@@ -3753,18 +3759,18 @@ int sched_dl_global_validate(void)
 
 static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 {
-	if (global_rt_runtime() == RUNTIME_INF) {
+	if (sysfs_dl_runtime == RUNTIME_INF) {
 		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
 		dl_rq->max_bw = dl_rq->extra_bw = 1 << BW_SHIFT;
 	} else {
-		dl_rq->bw_ratio = to_ratio(global_rt_runtime(),
-			  global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT);
+		dl_rq->bw_ratio = to_ratio(sysfs_dl_runtime,
+			  sysfs_dl_period) >> (BW_SHIFT - RATIO_SHIFT);
 		dl_rq->max_bw = dl_rq->extra_bw =
-			to_ratio(global_rt_period(), global_rt_runtime());
+			to_ratio(sysfs_dl_period, sysfs_dl_runtime);
 	}
 }
 
-void sched_dl_do_global(void)
+static void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
 	u64 cookie = ++dl_cookie;
@@ -3772,8 +3778,8 @@ void sched_dl_do_global(void)
 	int cpu;
 	unsigned long flags;
 
-	if (global_rt_runtime() != RUNTIME_INF)
-		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+	if (sysfs_dl_runtime != RUNTIME_INF)
+		new_bw = to_ratio(sysfs_dl_period, sysfs_dl_runtime);
 
 	for_each_possible_cpu(cpu)
 		init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
@@ -4124,3 +4130,136 @@ void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
 }
+
+#define SCHED_ATTR(_name)					\
+	static struct kobj_attribute sched_attr_## _name =	\
+	__ATTR(_name, 0644, sched_attr_##_name##_show, sched_attr_##_name##_store)
+
+static int sched_dl_try_boundary(int runtime, int period)
+{
+	int ret;
+	u64 runtime_ns;
+	u64 period_ns;
+
+	if (runtime) {
+		if (runtime < 0)
+			runtime_ns = RUNTIME_INF;
+		else
+			runtime_ns = runtime * NSEC_PER_USEC;
+	} else {
+		runtime_ns = sysfs_dl_runtime;
+	}
+
+	if (period)
+		period_ns = period * NSEC_PER_USEC;
+	else
+		period_ns = sysfs_dl_period;
+
+	if (runtime_ns != RUNTIME_INF) {
+		if (runtime_ns > period_ns || runtime_ns > MAX_BW)
+			return -EINVAL;
+	}
+
+	sched_domains_mutex_lock();
+	ret = sched_dl_global_validate(runtime_ns, period_ns);
+	if (ret) {
+		sched_domains_mutex_unlock();
+		return ret;
+	}
+
+	sysfs_dl_period = period_ns;
+	sysfs_dl_runtime = runtime_ns;
+
+	sched_dl_do_global();
+	sched_domains_mutex_unlock();
+	/*
+	 * After changing maximum available bandwidth for DEADLINE, we need to
+	 * recompute per root domain and per cpus variables accordingly.
+	 */
+	rebuild_sched_domains();
+	return 0;
+}
+
+static ssize_t sched_attr_dl_runtime_us_show(struct kobject *kobj,
+					     struct kobj_attribute *attr, char *buf)
+{
+	u64 val = sysfs_dl_runtime;
+
+	if (val == RUNTIME_INF)
+		val = -1;
+	else
+		do_div(val, NSEC_PER_USEC);
+
+	return sysfs_emit(buf, "%lld\n", val);
+}
+
+static ssize_t sched_attr_dl_runtime_us_store(struct kobject *kobj,
+					      struct kobj_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int val;
+	int ret;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (!(val == -1 || val > 0))
+		return -EINVAL;
+
+	ret = sched_dl_try_boundary(val, 0);
+	if (ret)
+		return ret;
+	return count;
+}
+SCHED_ATTR(dl_runtime_us);
+
+static ssize_t sched_attr_dl_period_us_show(struct kobject *kobj,
+					    struct kobj_attribute *attr, char *buf)
+{
+	u64 val = sysfs_dl_period;
+
+	do_div(val, NSEC_PER_USEC);
+	return sysfs_emit(buf, "%lld\n", val);
+}
+
+static ssize_t sched_attr_dl_period_us_store(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     const char *buf, size_t count)
+{
+	int val;
+	int ret;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+	if (val <= 0)
+		return -EINVAL;
+
+	ret = sched_dl_try_boundary(0, val);
+	if (ret)
+		return ret;
+	return count;
+}
+SCHED_ATTR(dl_period_us);
+
+static struct attribute *sched_global_attrs[] = {
+	&sched_attr_dl_runtime_us.attr,
+	&sched_attr_dl_period_us.attr,
+	NULL,
+};
+
+static const struct attribute_group sched_global_attrs_group = {
+	.attrs = sched_global_attrs,
+};
+
+static int __init sched_dl_init(void)
+{
+	struct kobject *sched_kobj;
+
+	sched_kobj = kobject_create_and_add("sched", kernel_kobj);
+	if (!sched_kobj)
+		return -ENOMEM;
+	return sysfs_create_group(sched_kobj, &sched_global_attrs_group);
+}
+late_initcall(sched_dl_init);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index cdeddd3fc9af2..1a6450f91d567 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2871,7 +2871,6 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
 	int ret;
 
 	mutex_lock(&mutex);
-	sched_domains_mutex_lock();
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
@@ -2879,29 +2878,13 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
 
 	if (!ret && write) {
 		ret = sched_rt_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_dl_global_validate();
-		if (ret)
-			goto undo;
-
-		sched_dl_do_global();
+		if (ret) {
+			sysctl_sched_rt_period = old_period;
+			sysctl_sched_rt_runtime = old_runtime;
+		}
 	}
-	if (0) {
-undo:
-		sysctl_sched_rt_period = old_period;
-		sysctl_sched_rt_runtime = old_runtime;
-	}
-	sched_domains_mutex_unlock();
 	mutex_unlock(&mutex);
 
-	/*
-	 * After changing maximum available bandwidth for DEADLINE, we need to
-	 * recompute per root domain and per cpus variables accordingly.
-	 */
-	rebuild_sched_domains();
-
 	return ret;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a7964537bac75..5f99f5ef415e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -354,8 +354,6 @@ struct dl_bw {
 };
 
 extern void init_dl_bw(struct dl_bw *dl_b);
-extern int  sched_dl_global_validate(void);
-extern void sched_dl_do_global(void);
 extern int  sched_dl_overflow(struct task_struct *p, int policy, const struct sched_attr *attr);
 extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
 extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr, unsigned int flags);
@@ -599,6 +597,19 @@ static inline int rt_bandwidth_enabled(void)
 {
 	return sysctl_sched_rt_runtime >= 0;
 }
+
+static inline u64 global_rt_period(void)
+{
+	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
+}
+
+static inline u64 global_rt_runtime(void)
+{
+	if (sysctl_sched_rt_runtime < 0)
+		return RUNTIME_INF;
+
+	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
+}
 #endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);
@@ -2505,19 +2516,6 @@ extern union sched_feat_key sched_feat_keys[__SCHED_FEAT_NR];
 extern struct static_key_false sched_numa_balancing;
 extern struct static_key_false sched_schedstats;
 
-static inline u64 global_rt_period(void)
-{
-	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
-}
-
-static inline u64 global_rt_runtime(void)
-{
-	if (sysctl_sched_rt_runtime < 0)
-		return RUNTIME_INF;
-
-	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
-}
-
 /*
  * Is p the current execution context?
  */

-- 
2.55.0