[PATCH v2 6/7] sched: Add sysfs files for the per-CPU fair_server knobs

[Sebastian Andrzej Siewior]

The fair_server exposes the runtime and period knobs per-CPU in the
debugfs folder. The debugfs interface is not a stable ABI.
Make the /sys/kernel/debug/sched/fair_server/cpu*/{period|runtime} knobs
available as /sys/kernel/sched/cpuX/{fair_server_period|fair_server_runtime}.

It adds a struct kobject to the rq and exposes only those two. The
per-runqueue folder is named `cpu' rather than `rq' since it might be
more intuitive to the user than `rq' or `runqueue'.

The set logic is pulled from the debugfs folder but it is still shared.
That debugfs logic could be removed (after providing the same for
ext-server) or symlinked for a while.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
 kernel/sched/deadline.c | 152 +++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/debug.c    |  56 ++----------------
 kernel/sched/sched.h    |   8 +++
 3 files changed, 163 insertions(+), 53 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index c5a2499a1450a..b574135f45e7e 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -4131,6 +4131,59 @@ void print_dl_stats(struct seq_file *m, int cpu)
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
 }
 
+static unsigned long dl_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long dl_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
+
+int __sched_server_write_common(enum dl_param param, u64 value, struct rq *rq,
+				struct sched_dl_entity *dl_se, const char *sname)
+{
+	u64 old_runtime, runtime, period;
+	int retval = 0;
+
+	scoped_guard (rq_lock_irqsave, rq) {
+		old_runtime = runtime = dl_se->dl_runtime;
+		period = dl_se->dl_period;
+
+		switch (param) {
+		case DL_RUNTIME:
+			if (runtime == value)
+				break;
+			runtime = value;
+			break;
+		case DL_PERIOD:
+			if (value == period)
+				break;
+			period = value;
+			break;
+		}
+
+		if (runtime > period ||
+		    period > dl_server_period_max ||
+		    period < dl_server_period_min) {
+			return  -EINVAL;
+		}
+
+		if (!cpu_online(cpu_of(rq)))
+			return -EBUSY;
+
+		update_rq_clock(rq);
+		dl_server_stop(dl_se);
+		retval = dl_server_apply_params(dl_se, runtime, period, 0);
+		dl_server_start(dl_se);
+
+		if (retval < 0)
+			return retval;
+	}
+	if (!!old_runtime ^ !!runtime) {
+		pr_info("%s server %sabled on CPU %d%s.\n",
+			sname,
+			runtime ? "en" : "dis",
+			cpu_of(rq),
+			runtime ? "" : ", system may malfunction due to starvation");
+	}
+	return 0;
+}
+
 #define SCHED_ATTR(_name)					\
 	static struct kobj_attribute sched_attr_## _name =	\
 	__ATTR(_name, 0644, sched_attr_##_name##_show, sched_attr_##_name##_store)
@@ -4253,13 +4306,110 @@ static const struct attribute_group sched_global_attrs_group = {
 	.attrs = sched_global_attrs,
 };
 
+/* RQ */
+#define RQ_ATTR(_name)						\
+	static struct kobj_attribute rq_## _name =	\
+	__ATTR(_name, 0644, rq_##_name##_show, rq_##_name##_store)
+
+#define kobj_to_rq(__kobj) container_of(__kobj, struct rq, rq_kobj)
+
+static ssize_t rq_fair_server_runtime_show(struct kobject *kobj, struct kobj_attribute *attr,
+					   char *buf)
+{
+	struct rq *rq = kobj_to_rq(kobj);
+	struct sched_dl_entity *dl_se;
+
+	dl_se = &rq->fair_server;
+
+	return sysfs_emit(buf, "%llu\n", dl_se->dl_runtime);
+}
+
+static ssize_t rq_fair_server_runtime_store(struct kobject *kobj, struct kobj_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct rq *rq = kobj_to_rq(kobj);
+	u64 val;
+	int ret;
+
+	ret = kstrtoull(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	ret =  __sched_server_write_common(DL_RUNTIME, val, rq, &rq->fair_server, "Fair");
+	if (ret)
+		return ret;
+	return count;
+}
+RQ_ATTR(fair_server_runtime);
+
+static ssize_t rq_fair_server_period_show(struct kobject *kobj, struct kobj_attribute *attr,
+					  char *buf)
+{
+	struct rq *rq = kobj_to_rq(kobj);
+	struct sched_dl_entity *dl_se;
+
+	dl_se = &rq->fair_server;
+
+	return sysfs_emit(buf, "%llu\n", dl_se->dl_period);
+}
+
+static ssize_t rq_fair_server_period_store(struct kobject *kobj, struct kobj_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct rq *rq = kobj_to_rq(kobj);
+	u64 val;
+	int ret;
+
+	ret = kstrtoull(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	ret =  __sched_server_write_common(DL_PERIOD, val, rq, &rq->fair_server, "Fair");
+	if (ret)
+		return ret;
+	return count;
+}
+RQ_ATTR(fair_server_period);
+
+static struct attribute *rq_attrs[] = {
+	&rq_fair_server_runtime.attr,
+	&rq_fair_server_period.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(rq);
+
+static const struct kobj_type rq_ktype = {
+	.sysfs_ops      = &kobj_sysfs_ops,
+	.default_groups = rq_groups,
+};
+
+static int sched_create_rq_sysfs(struct kobject *sched_kobj)
+{
+	unsigned int cpu;
+	int ret;
+
+	for_each_possible_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+
+		ret = kobject_init_and_add(&rq->rq_kobj, &rq_ktype, sched_kobj,
+					   "cpu%d", cpu);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 static int __init sched_dl_init(void)
 {
 	struct kobject *sched_kobj;
+	int ret;
 
 	sched_kobj = kobject_create_and_add("sched", kernel_kobj);
 	if (!sched_kobj)
 		return -ENOMEM;
-	return sysfs_create_group(sched_kobj, &sched_global_attrs_group);
+	ret = sysfs_create_group(sched_kobj, &sched_global_attrs_group);
+	if (ret)
+		return ret;
+	return sched_create_rq_sysfs(sched_kobj);
 }
 late_initcall(sched_dl_init);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e6a3b516c703b..0e0782603a99a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -363,23 +363,13 @@ static const struct file_operations sched_debug_fops = {
 	.release	= seq_release,
 };
 
-enum dl_param {
-	DL_RUNTIME = 0,
-	DL_PERIOD,
-};
-
-static unsigned long dl_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
-static unsigned long dl_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
-
 static ssize_t sched_server_write_common(struct file *filp, const char __user *ubuf,
 					 size_t cnt, loff_t *ppos, enum dl_param param,
 					 void *server)
 {
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;
-	u64 old_runtime, runtime, period;
 	struct rq *rq = cpu_rq(cpu);
-	int retval = 0;
 	size_t err;
 	u64 value;
 
@@ -387,48 +377,10 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u
 	if (err)
 		return err;
 
-	scoped_guard (rq_lock_irqsave, rq) {
-		old_runtime = runtime = dl_se->dl_runtime;
-		period = dl_se->dl_period;
-
-		switch (param) {
-		case DL_RUNTIME:
-			if (runtime == value)
-				break;
-			runtime = value;
-			break;
-		case DL_PERIOD:
-			if (value == period)
-				break;
-			period = value;
-			break;
-		}
-
-		if (runtime > period ||
-		    period > dl_server_period_max ||
-		    period < dl_server_period_min) {
-			return  -EINVAL;
-		}
-
-		if (!cpu_online(cpu_of(rq)))
-			return -EBUSY;
-
-		update_rq_clock(rq);
-		dl_server_stop(dl_se);
-		retval = dl_server_apply_params(dl_se, runtime, period, 0);
-		dl_server_start(dl_se);
-
-		if (retval < 0)
-			return retval;
-	}
-
-	if (!!old_runtime ^ !!runtime) {
-		pr_info("%s server %sabled on CPU %d%s.\n",
-			server == &rq->fair_server ? "Fair" : "Ext",
-			runtime ? "en" : "dis",
-			cpu_of(rq),
-			runtime ? "" : ", system may malfunction due to starvation");
-	}
+	err = __sched_server_write_common(param, value, rq, dl_se,
+					  server == &rq->fair_server ? "Fair" : "Ext");
+	if (err)
+		return err;
 
 	*ppos += cnt;
 	return cnt;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5f99f5ef415e7..8f813d9df0cc5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1432,6 +1432,7 @@ struct rq {
 #endif
 
 	atomic_t		nr_iowait;
+	struct kobject		rq_kobj;
 } __no_randomize_layout;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -3507,6 +3508,13 @@ extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 
+enum dl_param {
+	DL_RUNTIME = 0,
+	DL_PERIOD,
+};
+extern int __sched_server_write_common(enum dl_param param, u64 value, struct rq *rq,
+				       struct sched_dl_entity *dl_se, const char *sname);
+
 extern void resched_latency_warn(int cpu, u64 latency);
 
 #ifdef CONFIG_NUMA_BALANCING

-- 
2.55.0