2013-03-29 14:36:31 +08:00
|
|
|
#include <linux/cgroup.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
#include <linux/rcupdate.h>
|
|
|
|
#include <linux/kernel_stat.h>
|
2013-04-10 21:10:50 +08:00
|
|
|
#include <linux/err.h>
|
2013-03-29 14:36:31 +08:00
|
|
|
|
|
|
|
#include "sched.h"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* CPU accounting code for task groups.
|
|
|
|
*
|
|
|
|
* Based on the work by Paul Menage (menage@google.com) and Balbir Singh
|
|
|
|
* (balbir@in.ibm.com).
|
|
|
|
*/
|
|
|
|
|
2013-03-29 14:38:13 +08:00
|
|
|
/* Time spent by the tasks of the cpu accounting group executing in ... */
|
|
|
|
enum cpuacct_stat_index {
|
|
|
|
CPUACCT_STAT_USER, /* ... user mode */
|
|
|
|
CPUACCT_STAT_SYSTEM, /* ... kernel mode */
|
|
|
|
|
|
|
|
CPUACCT_STAT_NSTATS,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* track cpu usage of a group of tasks and its child groups */
|
|
|
|
struct cpuacct {
|
|
|
|
struct cgroup_subsys_state css;
|
|
|
|
/* cpuusage holds pointer to a u64-type object on every cpu */
|
|
|
|
u64 __percpu *cpuusage;
|
|
|
|
struct kernel_cpustat __percpu *cpustat;
|
|
|
|
};
|
|
|
|
|
2013-08-09 08:11:23 +08:00
|
|
|
static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
|
|
|
|
{
|
|
|
|
return css ? container_of(css, struct cpuacct, css) : NULL;
|
|
|
|
}
|
|
|
|
|
2013-03-29 14:38:13 +08:00
|
|
|
/* return cpu accounting group corresponding to this container */
|
|
|
|
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
|
|
|
|
{
|
2013-08-09 08:11:23 +08:00
|
|
|
return css_ca(cgroup_css(cgrp, cpuacct_subsys_id));
|
2013-03-29 14:38:13 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* return cpu accounting group to which this task belongs */
|
|
|
|
static inline struct cpuacct *task_ca(struct task_struct *tsk)
|
|
|
|
{
|
2013-08-09 08:11:23 +08:00
|
|
|
return css_ca(task_css(tsk, cpuacct_subsys_id));
|
2013-03-29 14:38:13 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct cpuacct *parent_ca(struct cpuacct *ca)
|
|
|
|
{
|
cgroup: add css_parent()
Currently, controllers have to explicitly follow the cgroup hierarchy
to find the parent of a given css. cgroup is moving towards using
cgroup_subsys_state as the main controller interface construct, so
let's provide a way to climb the hierarchy using just csses.
This patch implements css_parent() which, given a css, returns its
parent. The function is guarnateed to valid non-NULL parent css as
long as the target css is not at the top of the hierarchy.
freezer, cpuset, cpu, cpuacct, hugetlb, memory, net_cls and devices
are converted to use css_parent() instead of accessing cgroup->parent
directly.
* __parent_ca() is dropped from cpuacct and its usage is replaced with
parent_ca(). The only difference between the two was NULL test on
cgroup->parent which is now embedded in css_parent() making the
distinction moot. Note that eventually a css->parent field will be
added to css and the NULL check in css_parent() will go away.
This patch shouldn't cause any behavior differences.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
2013-08-09 08:11:23 +08:00
|
|
|
return css_ca(css_parent(&ca->css));
|
2013-03-29 14:38:13 +08:00
|
|
|
}
|
|
|
|
|
2013-03-29 14:43:46 +08:00
|
|
|
static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
|
2013-03-29 14:44:04 +08:00
|
|
|
static struct cpuacct root_cpuacct = {
|
|
|
|
.cpustat = &kernel_cpustat,
|
|
|
|
.cpuusage = &root_cpuacct_cpuusage,
|
|
|
|
};
|
2013-03-29 14:36:31 +08:00
|
|
|
|
|
|
|
/* create a new cpu accounting group */
|
2013-08-09 08:11:23 +08:00
|
|
|
static struct cgroup_subsys_state *
|
|
|
|
cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
|
2013-03-29 14:36:31 +08:00
|
|
|
{
|
|
|
|
struct cpuacct *ca;
|
|
|
|
|
2013-08-09 08:11:23 +08:00
|
|
|
if (!parent_css)
|
2013-03-29 14:36:31 +08:00
|
|
|
return &root_cpuacct.css;
|
|
|
|
|
|
|
|
ca = kzalloc(sizeof(*ca), GFP_KERNEL);
|
|
|
|
if (!ca)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ca->cpuusage = alloc_percpu(u64);
|
|
|
|
if (!ca->cpuusage)
|
|
|
|
goto out_free_ca;
|
|
|
|
|
|
|
|
ca->cpustat = alloc_percpu(struct kernel_cpustat);
|
|
|
|
if (!ca->cpustat)
|
|
|
|
goto out_free_cpuusage;
|
|
|
|
|
|
|
|
return &ca->css;
|
|
|
|
|
|
|
|
out_free_cpuusage:
|
|
|
|
free_percpu(ca->cpuusage);
|
|
|
|
out_free_ca:
|
|
|
|
kfree(ca);
|
|
|
|
out:
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* destroy an existing cpu accounting group */
|
2013-08-09 08:11:23 +08:00
|
|
|
static void cpuacct_css_free(struct cgroup_subsys_state *css)
|
2013-03-29 14:36:31 +08:00
|
|
|
{
|
2013-08-09 08:11:23 +08:00
|
|
|
struct cpuacct *ca = css_ca(css);
|
2013-03-29 14:36:31 +08:00
|
|
|
|
|
|
|
free_percpu(ca->cpustat);
|
|
|
|
free_percpu(ca->cpuusage);
|
|
|
|
kfree(ca);
|
|
|
|
}
|
|
|
|
|
|
|
|
static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
|
|
|
|
{
|
|
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
|
|
u64 data;
|
|
|
|
|
|
|
|
#ifndef CONFIG_64BIT
|
|
|
|
/*
|
|
|
|
* Take rq->lock to make 64-bit read safe on 32-bit platforms.
|
|
|
|
*/
|
|
|
|
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
|
|
|
|
data = *cpuusage;
|
|
|
|
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
|
|
|
|
#else
|
|
|
|
data = *cpuusage;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return data;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
|
|
|
|
{
|
|
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
|
|
|
|
|
|
#ifndef CONFIG_64BIT
|
|
|
|
/*
|
|
|
|
* Take rq->lock to make 64-bit write safe on 32-bit platforms.
|
|
|
|
*/
|
|
|
|
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
|
|
|
|
*cpuusage = val;
|
|
|
|
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
|
|
|
|
#else
|
|
|
|
*cpuusage = val;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
/* return total cpu usage (in nanoseconds) of a group */
|
|
|
|
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
|
|
|
|
{
|
|
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
|
|
u64 totalcpuusage = 0;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_present_cpu(i)
|
|
|
|
totalcpuusage += cpuacct_cpuusage_read(ca, i);
|
|
|
|
|
|
|
|
return totalcpuusage;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
|
|
|
|
u64 reset)
|
|
|
|
{
|
|
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
|
|
int err = 0;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (reset) {
|
|
|
|
err = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
for_each_present_cpu(i)
|
|
|
|
cpuacct_cpuusage_write(ca, i, 0);
|
|
|
|
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
|
|
|
|
struct seq_file *m)
|
|
|
|
{
|
|
|
|
struct cpuacct *ca = cgroup_ca(cgroup);
|
|
|
|
u64 percpu;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_present_cpu(i) {
|
|
|
|
percpu = cpuacct_cpuusage_read(ca, i);
|
|
|
|
seq_printf(m, "%llu ", (unsigned long long) percpu);
|
|
|
|
}
|
|
|
|
seq_printf(m, "\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const char * const cpuacct_stat_desc[] = {
|
|
|
|
[CPUACCT_STAT_USER] = "user",
|
|
|
|
[CPUACCT_STAT_SYSTEM] = "system",
|
|
|
|
};
|
|
|
|
|
|
|
|
static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
|
|
|
|
struct cgroup_map_cb *cb)
|
|
|
|
{
|
|
|
|
struct cpuacct *ca = cgroup_ca(cgrp);
|
|
|
|
int cpu;
|
|
|
|
s64 val = 0;
|
|
|
|
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
|
|
|
|
val += kcpustat->cpustat[CPUTIME_USER];
|
|
|
|
val += kcpustat->cpustat[CPUTIME_NICE];
|
|
|
|
}
|
|
|
|
val = cputime64_to_clock_t(val);
|
|
|
|
cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
|
|
|
|
|
|
|
|
val = 0;
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
|
|
|
|
val += kcpustat->cpustat[CPUTIME_SYSTEM];
|
|
|
|
val += kcpustat->cpustat[CPUTIME_IRQ];
|
|
|
|
val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
|
|
|
|
}
|
|
|
|
|
|
|
|
val = cputime64_to_clock_t(val);
|
|
|
|
cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct cftype files[] = {
|
|
|
|
{
|
|
|
|
.name = "usage",
|
|
|
|
.read_u64 = cpuusage_read,
|
|
|
|
.write_u64 = cpuusage_write,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = "usage_percpu",
|
|
|
|
.read_seq_string = cpuacct_percpu_seq_read,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = "stat",
|
|
|
|
.read_map = cpuacct_stats_show,
|
|
|
|
},
|
|
|
|
{ } /* terminate */
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* charge this task's execution time to its accounting group.
|
|
|
|
*
|
|
|
|
* called with rq->lock held.
|
|
|
|
*/
|
|
|
|
void cpuacct_charge(struct task_struct *tsk, u64 cputime)
|
|
|
|
{
|
|
|
|
struct cpuacct *ca;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
cpu = task_cpu(tsk);
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
|
|
|
|
ca = task_ca(tsk);
|
|
|
|
|
2013-03-29 14:37:29 +08:00
|
|
|
while (true) {
|
2013-03-29 14:36:31 +08:00
|
|
|
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
|
|
|
|
*cpuusage += cputime;
|
2013-03-29 14:37:29 +08:00
|
|
|
|
|
|
|
ca = parent_ca(ca);
|
|
|
|
if (!ca)
|
|
|
|
break;
|
2013-03-29 14:36:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
2013-03-29 14:37:06 +08:00
|
|
|
/*
|
|
|
|
* Add user/system time to cpuacct.
|
|
|
|
*
|
|
|
|
* Note: it's the caller that updates the account of the root cgroup.
|
|
|
|
*/
|
|
|
|
void cpuacct_account_field(struct task_struct *p, int index, u64 val)
|
|
|
|
{
|
|
|
|
struct kernel_cpustat *kcpustat;
|
|
|
|
struct cpuacct *ca;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
ca = task_ca(p);
|
2013-03-29 14:37:43 +08:00
|
|
|
while (ca != &root_cpuacct) {
|
2013-03-29 14:37:06 +08:00
|
|
|
kcpustat = this_cpu_ptr(ca->cpustat);
|
|
|
|
kcpustat->cpustat[index] += val;
|
cgroup: add css_parent()
Currently, controllers have to explicitly follow the cgroup hierarchy
to find the parent of a given css. cgroup is moving towards using
cgroup_subsys_state as the main controller interface construct, so
let's provide a way to climb the hierarchy using just csses.
This patch implements css_parent() which, given a css, returns its
parent. The function is guarnateed to valid non-NULL parent css as
long as the target css is not at the top of the hierarchy.
freezer, cpuset, cpu, cpuacct, hugetlb, memory, net_cls and devices
are converted to use css_parent() instead of accessing cgroup->parent
directly.
* __parent_ca() is dropped from cpuacct and its usage is replaced with
parent_ca(). The only difference between the two was NULL test on
cgroup->parent which is now embedded in css_parent() making the
distinction moot. Note that eventually a css->parent field will be
added to css and the NULL check in css_parent() will go away.
This patch shouldn't cause any behavior differences.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
2013-08-09 08:11:23 +08:00
|
|
|
ca = parent_ca(ca);
|
2013-03-29 14:37:06 +08:00
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
2013-03-29 14:36:31 +08:00
|
|
|
struct cgroup_subsys cpuacct_subsys = {
|
2013-03-29 14:44:15 +08:00
|
|
|
.name = "cpuacct",
|
|
|
|
.css_alloc = cpuacct_css_alloc,
|
|
|
|
.css_free = cpuacct_css_free,
|
|
|
|
.subsys_id = cpuacct_subsys_id,
|
|
|
|
.base_cftypes = files,
|
|
|
|
.early_init = 1,
|
2013-03-29 14:36:31 +08:00
|
|
|
};
|