[RFC v2 5/8] sched/tune: add initial support for CGroups based boosting

[Patrick Bellasi]

To support task performance boosting, the usage of a single knob has the
advantage to be a simple solution, both from the implementation and the
usability standpoint.  However, on a real system it can be difficult to
identify a single value for the knob which fits the needs of multiple
different tasks. For example, some kernel threads and/or user-space
background services should be better managed the "standard" way while we
still want to be able to boost the performance of specific workloads.

In order to improve the flexibility of the task boosting mechanism this
patch is the first of a small series which extends the previous
implementation to introduce a "per task group" support.

This first patch introduces just the basic CGroups support, a new
"schedtune" CGroups controller is added which allows to configure
different boost value for different groups of tasks.
To keep the implementation simple while still supporting an effective
boosting strategy, the new controller:
  1. allows only a two layer hierarchy
  2. supports only a limited number of boost groups

A two layer hierarchy allows to place each task either:
  a) in the root control group
     thus being subject to a system-wide boosting value
  b) in a child of the root group
     thus being subject to the specific boost value defined by that
     "boost group"

The limited number of "boost groups" supported is mainly motivated by
the observation that in a real system it could be useful to have only
few classes of tasks which deserve different treatment.
For example, background vs foreground or interactive vs low-priority.

As an additional benefit, a limited number of boost groups allows also
to have a simpler implementation, especially for the code required to
compute the boost value for CPUs which have RUNNABLE tasks belonging to
different boost groups.

Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Li Zefan <lizefan@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
---
 include/linux/cgroup_subsys.h |   4 +
 init/Kconfig                  |  42 ++++++++
 kernel/sched/tune.c           | 233 ++++++++++++++++++++++++++++++++++++++++++
 kernel/sysctl.c               |   4 +
 4 files changed, 283 insertions(+)

diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 0df0336a..4fd0f82 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -20,6 +20,10 @@ SUBSYS(cpu)
 SUBSYS(cpuacct)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_SCHED_TUNE)
+SUBSYS(schedtune)
+#endif
+
 #if IS_ENABLED(CONFIG_BLK_CGROUP)
 SUBSYS(io)
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index 461e052..5bce1ef 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1074,6 +1074,48 @@ config RT_GROUP_SCHED
 
 endif #CGROUP_SCHED
 
+config CGROUP_SCHED_TUNE
+	bool "Tasks boosting controller"
+	depends on SCHED_TUNE
+	help
+	  This option allows users to define boost values for groups of
+	  SCHED_OTHER tasks. Once enabled, the utilization of a CPU is boosted
+	  by a factor proportional to the maximum boost value of all the tasks
+	  RUNNABLE on that CPU.
+
+	  This new controller:
+	  1. allows only a two layers hierarchy, where the root defines the
+	     system-wide boost value and its children define a
+	     "boost group" whose tasks will be boosted with the configured
+	     value.
+	  2. supports only a limited number of different boost groups, each
+	     one which could be configured with a different boost value.
+
+	  Say N if unsure.
+
+config SCHED_TUNE_BOOSTGROUPS
+	int "Maximum number of SchedTune's boost groups"
+	range 2 16
+	default 5
+	depends on CGROUP_SCHED_TUNE
+
+	help
+	  When per-task boosting is used we still allow only limited number of
+	  boost groups for two main reasons:
+	  1. on a real system we usually have only few classes of workloads which
+	     make sense to boost with different values,
+	     e.g. background vs foreground tasks, interactive vs low-priority tasks
+	  2. a limited number allows for a simpler and more memory/time efficient
+	     implementation especially for the computation of the per-CPU boost
+	     value
+
+	  NOTE: The first boost group is reserved to defined the global boosting to be
+	  applied to all tasks, thus the minimum number of boost groups is 2.
+	  Indeed, if only global boosting is required than per-task boosting is
+	  not required and this support can be disabled.
+
+	  Use the default value (5) is unsure.
+
 config CGROUP_PIDS
 	bool "PIDs controller"
 	help
diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
index c28a06f..4eaea1d 100644
--- a/kernel/sched/tune.c
+++ b/kernel/sched/tune.c
@@ -4,11 +4,239 @@
  * Copyright (C) 2016 ARM Ltd, Patrick Bellasi <patrick.bellasi@xxxxxxx>
  */
 
+#include <linux/cgroup.h>
+#include <linux/err.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
 #include "sched.h"
 #include "tune.h"
 
 unsigned int sysctl_sched_cfs_boost __read_mostly;
 
+#ifdef CONFIG_CGROUP_SCHED_TUNE
+
+/*
+ * CFS Scheduler Tunables for Task Groups.
+ */
+
+/* SchedTune tunables for a group of tasks */
+struct schedtune {
+	/* SchedTune CGroup subsystem */
+	struct cgroup_subsys_state css;
+
+	/* Boost group allocated ID */
+	int idx;
+
+	/* Boost value for tasks on that SchedTune CGroup */
+	unsigned int boost;
+
+};
+
+static inline struct schedtune *css_st(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct schedtune, css) : NULL;
+}
+
+static inline struct schedtune *task_schedtune(struct task_struct *tsk)
+{
+	return css_st(task_css(tsk, schedtune_cgrp_id));
+}
+
+static inline struct schedtune *parent_st(struct schedtune *st)
+{
+	return css_st(st->css.parent);
+}
+
+/*
+ * SchedTune root control group
+ * The root control group is used to define a system-wide boosting tuning,
+ * which is applied to all tasks in the system.
+ * Task specific boost tuning could be specified by creating and
+ * configuring a child control group under the root one.
+ * By default, system-wide boosting is disabled, i.e. no boosting is applied
+ * to tasks which are not into a child control group.
+ */
+static struct schedtune
+root_schedtune = {
+	.boost	= 0,
+};
+
+/*
+ * Maximum number of boost groups to support
+ * When per-task boosting is used we still allow only limited number of
+ * boost groups for two main reasons:
+ * 1. on a real system we usually have only few classes of workloads which
+ *    make sense to boost with different values (e.g. background vs foreground
+ *    tasks, interactive vs low-priority tasks)
+ * 2. a limited number allows for a simpler and more memory/time efficient
+ *    implementation especially for the computation of the per-CPU boost
+ *    value
+ */
+#define boostgroups_max CONFIG_SCHED_TUNE_BOOSTGROUPS
+
+/* Array of configured boostgroups */
+static struct schedtune *allocated_group[boostgroups_max] = {
+	&root_schedtune,
+	NULL,
+};
+
+/* SchedTune boost groups
+ * Keep track of all the boost groups which impact on CPU, for example when a
+ * CPU has two RUNNABLE tasks belonging to two different boost groups and thus
+ * likely with different boost values. Since the maximum number of boost
+ * groups is limited by CONFIG_SCHED_TUNE_BOOSTGROUPS, which is limited to 16,
+ * we use a simple array to keep track of the metrics required to compute the
+ * maximum per-CPU
+ * boosting value.
+ */
+struct boost_groups {
+	/* Maximum boost value for all RUNNABLE tasks on a CPU */
+	unsigned int boost_max;
+	struct {
+		/* The boost for tasks on that boost group */
+		unsigned int boost;
+		/* Count of RUNNABLE tasks on that boost group */
+		unsigned int tasks;
+	} group[boostgroups_max];
+};
+
+/* Boost groups affecting each CPU in the system */
+DEFINE_PER_CPU(struct boost_groups, cpu_boost_groups);
+
+static u64
+boost_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct schedtune *st = css_st(css);
+
+	return st->boost;
+}
+
+static int
+boost_write(struct cgroup_subsys_state *css, struct cftype *cft,
+	    u64 boost)
+{
+	struct schedtune *st = css_st(css);
+
+	if (boost > 100)
+		return -EINVAL;
+	st->boost = boost;
+	if (css == &root_schedtune.css)
+		sysctl_sched_cfs_boost = boost;
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "boost",
+		.read_u64 = boost_read,
+		.write_u64 = boost_write,
+	},
+	{ }	/* terminate */
+};
+
+static int
+schedtune_boostgroup_init(struct schedtune *st)
+{
+	struct boost_groups *bg;
+	int cpu;
+
+	/* Keep track of allocated boost groups */
+	allocated_group[st->idx] = st;
+
+	/* Initialize the per CPU boost groups */
+	for_each_possible_cpu(cpu) {
+		bg = &per_cpu(cpu_boost_groups, cpu);
+		bg->group[st->idx].boost = 0;
+		bg->group[st->idx].tasks = 0;
+	}
+
+	return 0;
+}
+
+static struct cgroup_subsys_state *
+schedtune_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct schedtune *st;
+	int idx;
+
+	if (!parent_css)
+		return &root_schedtune.css;
+
+	/* Allow only single level hierachies */
+	if (parent_css != &root_schedtune.css) {
+		pr_err("Nested SchedTune boosting groups not allowed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Allow only a limited number of boosting groups */
+	for (idx = 1; idx < boostgroups_max; ++idx)
+		if (!allocated_group[idx])
+			break;
+	if (idx == boostgroups_max) {
+		pr_err("Trying to create more than %d SchedTune boosting groups\n",
+		       boostgroups_max);
+		return ERR_PTR(-ENOSPC);
+	}
+
+	st = kzalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto out;
+
+	/* Initialize per CPUs boost group support */
+	st->idx = idx;
+	if (schedtune_boostgroup_init(st))
+		goto release;
+
+	return &st->css;
+
+release:
+	kfree(st);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+static void
+schedtune_boostgroup_release(struct schedtune *st)
+{
+	/* Keep track of allocated boost groups */
+	allocated_group[st->idx] = NULL;
+}
+
+static void
+schedtune_css_free(struct cgroup_subsys_state *css)
+{
+	struct schedtune *st = css_st(css);
+
+	schedtune_boostgroup_release(st);
+	kfree(st);
+}
+
+struct cgroup_subsys schedtune_cgrp_subsys = {
+	.css_alloc	= schedtune_css_alloc,
+	.css_free	= schedtune_css_free,
+	.legacy_cftypes	= files,
+	.early_init	= 1,
+};
+
+static inline void
+schedtune_init_cgroups(void)
+{
+	struct boost_groups *bg;
+	int cpu;
+
+	/* Initialize the per CPU boost groups */
+	for_each_possible_cpu(cpu) {
+		bg = &per_cpu(cpu_boost_groups, cpu);
+		memset(bg, 0, sizeof(struct boost_groups));
+	}
+
+	pr_info("schedtune: configured to support %d boost groups\n",
+		boostgroups_max);
+}
+
+#endif /* CONFIG_CGROUP_SCHED_TUNE */
+
 int
 sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
 			       void __user *buffer, size_t *lenp,
@@ -26,6 +254,11 @@ static int
 schedtune_init(void)
 {
 	schedtune_spc_rdiv = reciprocal_value(100);
+#ifdef CONFIG_CGROUP_SCHED_TUNE
+	schedtune_init_cgroups();
+#else
+	pr_info("schedtune: configured to support global boosting only\n");
+#endif
 	return 0;
 }
 late_initcall(schedtune_init);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 43b6d14..12c3432 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -447,7 +447,11 @@ static struct ctl_table kern_table[] = {
 		.procname	= "sched_cfs_boost",
 		.data		= &sysctl_sched_cfs_boost,
 		.maxlen		= sizeof(sysctl_sched_cfs_boost),
+#ifdef CONFIG_CGROUP_SCHED_TUNE
+		.mode		= 0444,
+#else
 		.mode		= 0644,
+#endif
 		.proc_handler	= &sysctl_sched_cfs_boost_handler,
 		.extra1		= &zero,
 		.extra2		= &one_hundred,
-- 
2.10.1