diff options
| -rw-r--r-- | Documentation/cgroups/cpuacct.txt | 4 | ||||
| -rw-r--r-- | include/linux/cpuacct.h | 41 | ||||
| -rw-r--r-- | kernel/sched.c | 49 |
3 files changed, 94 insertions, 0 deletions
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt index 9ad85df4b98..2601cdd217c 100644 --- a/Documentation/cgroups/cpuacct.txt +++ b/Documentation/cgroups/cpuacct.txt @@ -39,6 +39,10 @@ system: Time spent by tasks of the cgroup in kernel mode. user and system are in USER_HZ unit. +cpuacct.cpufreq file gives CPU time (in nanoseconds) spent at each CPU +frequency. Platform hooks must be implemented inorder to properly track +time at each CPU frequency. + cpuacct controller uses percpu_counter interface to collect user and system times. This has two side effects: diff --git a/include/linux/cpuacct.h b/include/linux/cpuacct.h new file mode 100644 index 00000000000..560df02f098 --- /dev/null +++ b/include/linux/cpuacct.h @@ -0,0 +1,41 @@ +/* include/linux/cpuacct.h + * + * Copyright (C) 2010 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#ifndef _CPUACCT_H_ +#define _CPUACCT_H_ + +#include <linux/cgroup.h> + +#ifdef CONFIG_CGROUP_CPUACCT + +/* + * Platform specific CPU frequency hooks for cpuacct. These functions are + * called from the scheduler. + */ +struct cpuacct_charge_calls { + /* + * Platforms can take advantage of this data and use + * per-cpu allocations if necessary. + */ + void (*init) (void **cpuacct_data); + void (*charge) (void *cpuacct_data, u64 cputime, unsigned int cpu); + void (*show) (void *cpuacct_data, struct cgroup_map_cb *cb); +}; + +int cpuacct_charge_register(struct cpuacct_charge_calls *fn); + +#endif /* CONFIG_CGROUP_CPUACCT */ + +#endif // _CPUACCT_H_ diff --git a/kernel/sched.c b/kernel/sched.c index 321870ba224..5cf42e8e74a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -71,6 +71,7 @@ #include <linux/ctype.h> #include <linux/ftrace.h> #include <linux/slab.h> +#include <linux/cpuacct.h> #include <asm/tlb.h> #include <asm/irq_regs.h> @@ -9080,8 +9081,30 @@ struct cpuacct { u64 __percpu *cpuusage; struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; + struct cpuacct_charge_calls *cpufreq_fn; + void *cpuacct_data; }; +static struct cpuacct *cpuacct_root; + +/* Default calls for cpufreq accounting */ +static struct cpuacct_charge_calls *cpuacct_cpufreq; +int cpuacct_register_cpufreq(struct cpuacct_charge_calls *fn) +{ + cpuacct_cpufreq = fn; + + /* + * Root node is created before platform can register callbacks, + * initalize here. + */ + if (cpuacct_root && fn) { + cpuacct_root->cpufreq_fn = fn; + if (fn->init) + fn->init(&cpuacct_root->cpuacct_data); + } + return 0; +} + struct cgroup_subsys cpuacct_subsys; /* return cpu accounting group corresponding to this container */ @@ -9116,8 +9139,16 @@ static struct cgroup_subsys_state *cpuacct_create( if (percpu_counter_init(&ca->cpustat[i], 0)) goto out_free_counters; + ca->cpufreq_fn = cpuacct_cpufreq; + + /* If available, have platform code initalize cpu frequency table */ + if (ca->cpufreq_fn && ca->cpufreq_fn->init) + ca->cpufreq_fn->init(&ca->cpuacct_data); + if (cgrp->parent) ca->parent = cgroup_ca(cgrp->parent); + else + cpuacct_root = ca; return &ca->css; @@ -9245,6 +9276,16 @@ static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, return 0; } +static int cpuacct_cpufreq_show(struct cgroup *cgrp, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + if (ca->cpufreq_fn && ca->cpufreq_fn->show) + ca->cpufreq_fn->show(ca->cpuacct_data, cb); + + return 0; +} + static struct cftype files[] = { { .name = "usage", @@ -9259,6 +9300,10 @@ static struct cftype files[] = { .name = "stat", .read_map = cpuacct_stats_show, }, + { + .name = "cpufreq", + .read_map = cpuacct_cpufreq_show, + }, }; static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) @@ -9288,6 +9333,10 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) for (; ca; ca = ca->parent) { u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; + + /* Call back into platform code to account for CPU speeds */ + if (ca->cpufreq_fn && ca->cpufreq_fn->charge) + ca->cpufreq_fn->charge(ca->cpuacct_data, cputime, cpu); } rcu_read_unlock(); |