[PATCH, v8 3/3] cgroups: introduce timer slack controller

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>

Every task_struct has timer_slack_ns value. This value uses to round up
poll() and select() timeout values. This feature can be useful in
mobile environment where combined wakeups are desired.

cgroup subsys "timer_slack" implement timer slack controller. It
provides a way to set minimal timer slack value for a group of tasks.
If a task belongs to a cgroup with minimal timer slack value higher than
task's value, cgroup's value will be applied.

Idea-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
---
 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/sched.h                 |    4 +
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 6 files changed, 207 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

diff --git a/Documentation/cgroups/timer_slack.txt b/Documentation/cgroups/timer_slack.txt
new file mode 100644
index 0000000..b1494ff
--- /dev/null
+++ b/Documentation/cgroups/timer_slack.txt
@@ -0,0 +1,64 @@
+Timer Slack Controller
+=====================
+
+Overview
+--------
+
+Every task_struct has timer_slack_ns value. This value uses to round up
+poll() and select() timeout values. This feature can be useful in
+mobile environment where combined wakeups are desired.
+
+cgroup subsys "timer_slack" implements timer slack controller. It
+provides a way to set minimal timer slack value for a group of tasks.
+If a task belongs to a cgroup with minimal timer slack value higher than
+task's value, cgroup's value will be applied.
+
+User interface
+--------------
+
+To get timer slack controller functionality you need to enable it in
+kernel configuration:
+
+CONFIG_CGROUP_TIMER_SLACK=y
+
+The controller provides two files:
+
+# mount -t cgroup -o timer_slack none /sys/fs/cgroup
+# ls /sys/fs/cgroup/timer_slack.*
+/sys/fs/cgroup/timer_slack.effective_slack_ns
+/sys/fs/cgroup/timer_slack.min_slack_ns
+
+By default timer_slack.min_slack_ns is 0:
+
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+0
+
+You can set it to some value:
+
+# echo 50000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+50000
+
+Tasks still can set task's value below 50000 using prctl(), but in this
+case cgroup's value will be applied.
+
+Timer slack controller supports hierarchical groups.
+
+# mkdir /sys/fs/cgroup/a
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+50000
+# echo 70000 > /sys/fs/cgroup/a/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+
+You can set any value you want, but effective value will the highest value
+up by hierarchy. You can see effective timer slack value for the cgroup from
+timer_slack.effective_slack_ns file:
+
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+70000
+# echo 100000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+100000
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff0..e399228 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -66,3 +66,9 @@ SUBSYS(blkio)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+SUBSYS(timer_slack)
+#endif
+
+/* */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 44f6f55..c10da5d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2620,11 +2620,15 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+extern unsigned long task_get_effective_timer_slack(struct task_struct *tsk);
+#else
 static inline unsigned long task_get_effective_timer_slack(
 		struct task_struct *tsk)
 {
 	return tsk->timer_slack_ns;
 }
+#endif
 
 #endif /* __KERNEL__ */
 
diff --git a/init/Kconfig b/init/Kconfig
index be788c0..bbc4d9c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -596,6 +596,14 @@ config CGROUP_FREEZER
 	  Provides a way to freeze and unfreeze all tasks in a
 	  cgroup.
 
+config CGROUP_TIMER_SLACK
+	bool "Timer slack cgroup controller"
+	help
+	  Provides a way to set minimal timer slack value for tasks in
+	  a cgroup.
+	  It's useful in mobile devices where certain background apps
+	  are attached to a cgroup and combined wakeups are desired.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	help
diff --git a/kernel/Makefile b/kernel/Makefile
index 353d3fe..0b60239 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
+obj-$(CONFIG_CGROUP_TIMER_SLACK) += cgroup_timer_slack.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
diff --git a/kernel/cgroup_timer_slack.c b/kernel/cgroup_timer_slack.c
new file mode 100644
index 0000000..9824807
--- /dev/null
+++ b/kernel/cgroup_timer_slack.c
@@ -0,0 +1,124 @@
+/*
+ * cgroup_timer_slack.c - control group timer slack subsystem
+ *
+ * Copyright Nokia Corparation, 2011
+ * Author: Kirill A. Shutemov
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+
+struct cgroup_subsys timer_slack_subsys;
+struct tslack_cgroup {
+	struct cgroup_subsys_state css;
+	unsigned long min_slack_ns;
+};
+
+static struct tslack_cgroup *cgroup_to_tslack(struct cgroup *cgroup)
+{
+	struct cgroup_subsys_state *css;
+
+	css = cgroup_subsys_state(cgroup, timer_slack_subsys.subsys_id);
+	return container_of(css, struct tslack_cgroup, css);
+}
+
+static struct cgroup_subsys_state *tslack_create(struct cgroup_subsys *subsys,
+		struct cgroup *cgroup)
+{
+	struct tslack_cgroup *tslack_cgroup;
+
+	tslack_cgroup = kmalloc(sizeof(*tslack_cgroup), GFP_KERNEL);
+	if (!tslack_cgroup)
+		return ERR_PTR(-ENOMEM);
+
+	if (cgroup->parent) {
+		struct tslack_cgroup *parent;
+
+		parent = cgroup_to_tslack(cgroup->parent);
+		tslack_cgroup->min_slack_ns = parent->min_slack_ns;
+	} else
+		tslack_cgroup->min_slack_ns = 0UL;
+
+	return &tslack_cgroup->css;
+}
+
+static void tslack_destroy(struct cgroup_subsys *tslack_cgroup,
+		struct cgroup *cgroup)
+{
+	kfree(cgroup_to_tslack(cgroup));
+}
+
+static u64 tslack_read_min(struct cgroup *cgroup, struct cftype *cft)
+{
+	return cgroup_to_tslack(cgroup)->min_slack_ns;
+}
+
+static int tslack_write_min(struct cgroup *cgroup, struct cftype *cft, u64 val)
+{
+	if (val > ULONG_MAX)
+		return -EINVAL;
+
+	cgroup_to_tslack(cgroup)->min_slack_ns = val;
+
+	return 0;
+}
+
+static u64 tslack_read_effective(struct cgroup *cgroup, struct cftype *cft)
+{
+	unsigned long min;
+
+	min = cgroup_to_tslack(cgroup)->min_slack_ns;
+	while (cgroup->parent) {
+		cgroup = cgroup->parent;
+		min = max(cgroup_to_tslack(cgroup)->min_slack_ns, min);
+	}
+
+	return min;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "min_slack_ns",
+		.read_u64 = tslack_read_min,
+		.write_u64 = tslack_write_min,
+	},
+	{
+		.name = "effective_slack_ns",
+		.read_u64 = tslack_read_effective,
+	},
+};
+
+static int tslack_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, subsys, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys timer_slack_subsys = {
+	.name		= "timer_slack",
+	.subsys_id	= timer_slack_subsys_id,
+	.create		= tslack_create,
+	.destroy	= tslack_destroy,
+	.populate	= tslack_populate,
+};
+
+unsigned long task_get_effective_timer_slack(struct task_struct *tsk)
+{
+	struct cgroup *cgroup;
+	unsigned long slack;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(tsk, timer_slack_subsys.subsys_id);
+	slack = tslack_read_effective(cgroup, NULL);
+	rcu_read_unlock();
+
+	return max(tsk->timer_slack_ns, slack);
+}
-- 
1.7.4.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/