cpuacct.c

#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>
#include <linux/err.h>

#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).
 */

/* 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,
};

static const char * const cpuacct_stat_desc[] = {
	[CPUACCT_STAT_USER] = "user",
	[CPUACCT_STAT_SYSTEM] = "system",
};

struct cpuacct_usage {
	u64	usages[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 */
	struct cpuacct_usage __percpu *cpuusage;
	struct kernel_cpustat __percpu *cpustat;
};

static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
{
	return css ? container_of(css, struct cpuacct, css) : NULL;
}

/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
	return css_ca(task_css(tsk, cpuacct_cgrp_id));
}

static inline struct cpuacct *parent_ca(struct cpuacct *ca)
{
	return css_ca(ca->css.parent);
}

static DEFINE_PER_CPU(struct cpuacct_usage, root_cpuacct_cpuusage);
static struct cpuacct root_cpuacct = {
	.cpustat	= &kernel_cpustat,
	.cpuusage	= &root_cpuacct_cpuusage,
};

/* create a new cpu accounting group */
static struct cgroup_subsys_state *
cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct cpuacct *ca;

	if (!parent_css)
		return &root_cpuacct.css;

	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
	if (!ca)
		goto out;

	ca->cpuusage = alloc_percpu(struct cpuacct_usage);
	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 */
static void cpuacct_css_free(struct cgroup_subsys_state *css)
{
	struct cpuacct *ca = css_ca(css);

	free_percpu(ca->cpustat);
	free_percpu(ca->cpuusage);
	kfree(ca);
}

static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
				 enum cpuacct_stat_index index)
{
	struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
	u64 data;

	/*
	 * We allow index == CPUACCT_STAT_NSTATS here to read
	 * the sum of suages.
	 */
	BUG_ON(index > CPUACCT_STAT_NSTATS);

#ifndef CONFIG_64BIT
	/*
	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
	 */
	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
#endif

	if (index == CPUACCT_STAT_NSTATS) {
		int i = 0;

		data = 0;
		for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
			data += cpuusage->usages[i];
	} else {
		data = cpuusage->usages[index];
	}

#ifndef CONFIG_64BIT
	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#endif

	return data;
}

static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
{
	struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
	int i;

#ifndef CONFIG_64BIT
	/*
	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
	 */
	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
#endif

	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
		cpuusage->usages[i] = val;

#ifndef CONFIG_64BIT
	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#endif
}

/* return total cpu usage (in nanoseconds) of a group */
static u64 __cpuusage_read(struct cgroup_subsys_state *css,
			   enum cpuacct_stat_index index)
{
	struct cpuacct *ca = css_ca(css);
	u64 totalcpuusage = 0;
	int i;

	for_each_possible_cpu(i)
		totalcpuusage += cpuacct_cpuusage_read(ca, i, index);

	return totalcpuusage;
}

static u64 cpuusage_user_read(struct cgroup_subsys_state *css,
			      struct cftype *cft)
{
	return __cpuusage_read(css, CPUACCT_STAT_USER);
}

static u64 cpuusage_sys_read(struct cgroup_subsys_state *css,
			     struct cftype *cft)
{
	return __cpuusage_read(css, CPUACCT_STAT_SYSTEM);
}

static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
	return __cpuusage_read(css, CPUACCT_STAT_NSTATS);
}

static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
			  u64 val)
{
	struct cpuacct *ca = css_ca(css);
	int cpu;

	/*
	 * Only allow '0' here to do a reset.
	 */
	if (val)
		return -EINVAL;

	for_each_possible_cpu(cpu)
		cpuacct_cpuusage_write(ca, cpu, 0);

	return 0;
}

static int __cpuacct_percpu_seq_show(struct seq_file *m,
				     enum cpuacct_stat_index index)
{
	struct cpuacct *ca = css_ca(seq_css(m));
	u64 percpu;
	int i;

	for_each_possible_cpu(i) {
		percpu = cpuacct_cpuusage_read(ca, i, index);
		seq_printf(m, "%llu ", (unsigned long long) percpu);
	}
	seq_printf(m, "\n");
	return 0;
}

static int cpuacct_percpu_user_seq_show(struct seq_file *m, void *V)
{
	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_USER);
}

static int cpuacct_percpu_sys_seq_show(struct seq_file *m, void *V)
{
	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_SYSTEM);
}

static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
{
	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_NSTATS);
}

static int cpuacct_stats_show(struct seq_file *sf, void *v)
{
	struct cpuacct *ca = css_ca(seq_css(sf));
	int cpu;
	s64 val = 0;

	for_each_possible_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);
	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);

	val = 0;
	for_each_possible_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);
	seq_printf(sf, "%s %lld\n", 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_user",
		.read_u64 = cpuusage_user_read,
	},
	{
		.name = "usage_sys",
		.read_u64 = cpuusage_sys_read,
	},
	{
		.name = "usage_percpu",
		.seq_show = cpuacct_percpu_seq_show,
	},
	{
		.name = "usage_percpu_user",
		.seq_show = cpuacct_percpu_user_seq_show,
	},
	{
		.name = "usage_percpu_sys",
		.seq_show = cpuacct_percpu_sys_seq_show,
	},
	{
		.name = "stat",
		.seq_show = 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 index = CPUACCT_STAT_SYSTEM;
	struct pt_regs *regs = task_pt_regs(tsk);

	if (regs && user_mode(regs))
		index = CPUACCT_STAT_USER;

	rcu_read_lock();

	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
		this_cpu_ptr(ca->cpuusage)->usages[index] += cputime;

	rcu_read_unlock();
}

/*
 * 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 *tsk, int index, u64 val)
{
	struct cpuacct *ca;

	rcu_read_lock();
	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
		this_cpu_ptr(ca->cpustat)->cpustat[index] += val;
	rcu_read_unlock();
}

struct cgroup_subsys cpuacct_cgrp_subsys = {
	.css_alloc	= cpuacct_css_alloc,
	.css_free	= cpuacct_css_free,
	.legacy_cftypes	= files,
	.early_init	= true,
};