cgroup_timer_slack by Kirill A. Shutemov, v10

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.

Originally, prctl() was the only way to change timer slack value of
a process. So you was not able change timer slack value of another
process.

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.

Timer slack controller allows to implement setting timer slack value of
a process based on a policy. For example, you can create foreground and
background cgroups and move tasks between them based on system state.

Idea-by: Jacob Pan <jacob.jun.pan <at> linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill <at> shutemov.name>

task_get_effective_timer_slack() returns timer slack value to be used
to configure per-task timers. It can be equal or higher than task's
timer slack value.

For now task_get_effective_timer_slack() returns timer_slack_ns of the
task. Timer slack cgroup controller will implement a bit more
sophisticated logic.

Signed-off-by: Kirill A. Shutemov <kirill <at> shutemov.name>

PR_GET_EFFECTIVE_TIMERSLACK allows process to know its effective timer
slack value.

Signed-off-by: Kirill A. Shutemov <kirill <at> shutemov.name>

Documentation/cgroups/timer_slack.txt

@@ -0,0 +1,72 @@
+Timer Slack Controller
+======================
+
+Overview
+--------
+
+Every task_struct has timer_slack_ns value. This value is used to round
+up poll() and select() timeout values. This feature can be useful in
+mobile environment where combined wakeups are desired.
+
+Originally, prctl() was the only way to change timer slack value of
+a process. So you was not able change timer slack value of another
+process.
+
+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.
+
+Timer slack controller allows to implement setting timer slack value of
+a process based on a policy. For example, you can create foreground and
+background cgroups and move tasks between them based on system state.
+
+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

fs/select.c

@@ -69,7 +69,6 @@ static long __estimate_accuracy(struct timespec *tv)
 
 long select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
 	struct timespec now;
 
 	/*
@@ -81,10 +80,8 @@ long select_estimate_accuracy(struct timespec *tv)
 
 	ktime_get_ts(&now);
 	now = timespec_sub(*tv, now);
-	ret = __estimate_accuracy(&now);
-	if (ret < current->timer_slack_ns)
-		return current->timer_slack_ns;
-	return ret;
+	return min_t(long, __estimate_accuracy(&now),
+			task_get_effective_timer_slack(current));
 }
 
 

include/linux/cgroup_subsys.h

@@ -64,3 +64,10 @@ SUBSYS(perf)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+SUBSYS(timer_slack)
+#endif
+
+/* */
+

include/linux/prctl.h

@@ -102,4 +102,10 @@
 
 #define PR_MCE_KILL_GET 34
 
+/*
+ * Get effective timerslack value for the process.
+ * It can be higher than PR_GET_TIMERSLACK.
+ */
+#define PR_GET_EFFECTIVE_TIMERSLACK 35
+
 #endif /* _LINUX_PRCTL_H */

include/linux/sched.h

@@ -2701,6 +2701,16 @@ 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__ */
 
 #endif

init/Kconfig

@@ -603,6 +603,14 @@ 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

kernel/Makefile

@@ -61,6 +61,7 @@ obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CGROUP_TIMER_SLACK) += cgroup_timer_slack.o
 obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o

kernel/cgroup_timer_slack.c

@@ -0,0 +1,125 @@
+/*
+ * 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/init_task.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);
+}

kernel/fork.c

@@ -1167,6 +1167,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
 
+	/*
+	 * Save current task's (not effective) timer slack value as default
+	 * timer slack value for new task.
+	 */
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
 	task_io_accounting_init(&p->ioac);

kernel/futex.c

@@ -1875,7 +1875,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 retry:
@@ -2269,7 +2269,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 	/*

kernel/hrtimer.c

@@ -1564,7 +1564,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	int ret = 0;
 	unsigned long slack;
 
-	slack = current->timer_slack_ns;
+	slack = task_get_effective_timer_slack(current);
 	if (rt_task(current))
 		slack = 0;
 

kernel/sys.c

@@ -1761,6 +1761,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
 			break;
+		case PR_GET_EFFECTIVE_TIMERSLACK:
+			error = task_get_effective_timer_slack(current);
+			break;
 		case PR_SET_TIMERSLACK:
 			if (arg2 <= 0)
 				current->timer_slack_ns =