sched: Split cpuacct code out of core.c

Signed-off-by: Li Zefan <lizefan@huawei.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/5155366F.5060404@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 227 insertions, 0 deletions

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
new file mode 100644
index 000000000000..50ec24b6193d
--- /dev/null
+++ b/kernel/sched/cpuacct.c
@@ -0,0 +1,227 @@
+#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 "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).
+ */
+
+struct cpuacct root_cpuacct;
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
+{
+        struct cpuacct *ca;
+
+        if (!cgrp->parent)
+                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 */
+static void cpuacct_css_free(struct cgroup *cgrp)
+{
+        struct cpuacct *ca = cgroup_ca(cgrp);
+
+        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;
+
+        if (unlikely(!cpuacct_subsys.active))
+                return;
+
+        cpu = task_cpu(tsk);
+
+        rcu_read_lock();
+
+        ca = task_ca(tsk);
+
+        for (; ca; ca = parent_ca(ca)) {
+                u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+                *cpuusage += cputime;
+        }
+
+        rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+        .name = "cpuacct",
+        .css_alloc = cpuacct_css_alloc,
+        .css_free = cpuacct_css_free,
+        .subsys_id = cpuacct_subsys_id,
+        .base_cftypes = files,
+};