cpuacct.c 6.2 KB
Newer Older
1 2 3 4 5 6 7 8
#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>
9
#include <linux/err.h>
10 11 12 13 14 15 16 17 18 19

#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).
 */

L
Li Zefan 已提交
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
/* 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;
};

36 37 38 39 40
static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
{
	return css ? container_of(css, struct cpuacct, css) : NULL;
}

L
Li Zefan 已提交
41 42 43
/* return cpu accounting group corresponding to this container */
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
{
44
	return css_ca(cgroup_css(cgrp, cpuacct_subsys_id));
L
Li Zefan 已提交
45 46 47 48 49
}

/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
50
	return css_ca(task_css(tsk, cpuacct_subsys_id));
L
Li Zefan 已提交
51 52 53 54
}

static inline struct cpuacct *parent_ca(struct cpuacct *ca)
{
T
Tejun Heo 已提交
55
	return css_ca(css_parent(&ca->css));
L
Li Zefan 已提交
56 57
}

58
static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
59 60 61 62
static struct cpuacct root_cpuacct = {
	.cpustat	= &kernel_cpustat,
	.cpuusage	= &root_cpuacct_cpuusage,
};
63 64

/* create a new cpu accounting group */
65 66
static struct cgroup_subsys_state *
cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
67 68 69
{
	struct cpuacct *ca;

70
	if (!parent_css)
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
		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 */
96
static void cpuacct_css_free(struct cgroup_subsys_state *css)
97
{
98
	struct cpuacct *ca = css_ca(css);
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253

	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);

254
	while (true) {
255 256
		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
		*cpuusage += cputime;
257 258 259 260

		ca = parent_ca(ca);
		if (!ca)
			break;
261 262 263 264 265
	}

	rcu_read_unlock();
}

266 267 268 269 270 271 272 273 274 275 276 277
/*
 * 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);
278
	while (ca != &root_cpuacct) {
279 280
		kcpustat = this_cpu_ptr(ca->cpustat);
		kcpustat->cpustat[index] += val;
T
Tejun Heo 已提交
281
		ca = parent_ca(ca);
282 283 284 285
	}
	rcu_read_unlock();
}

286
struct cgroup_subsys cpuacct_subsys = {
287 288 289 290 291 292
	.name		= "cpuacct",
	.css_alloc	= cpuacct_css_alloc,
	.css_free	= cpuacct_css_free,
	.subsys_id	= cpuacct_subsys_id,
	.base_cftypes	= files,
	.early_init	= 1,
293
};