3 files changed, 198 insertions, 3 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index ea8c8a12e19a..48a7fae00271 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CGROUP_CPUACCT) += cpu_acct.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/cpu_acct.c b/kernel/cpu_acct.c
new file mode 100644
index 000000000000..731e47e7f164
--- /dev/null
+++ b/kernel/cpu_acct.c
@@ -0,0 +1,186 @@
+/*
+ * kernel/cpu_acct.c - CPU accounting cgroup subsystem
+ *
+ * Copyright (C) Google Inc, 2006
+ *
+ * Developed by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com)
+ *
+ */
+
+/*
+ * Example cgroup subsystem for reporting total CPU usage of tasks in a
+ * cgroup, along with percentage load over a time interval
+ */
+
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/rcupdate.h>
+
+#include <asm/div64.h>
+
+struct cpuacct {
+        struct cgroup_subsys_state css;
+        spinlock_t lock;
+        /* total time used by this class */
+        cputime64_t time;
+
+        /* time when next load calculation occurs */
+        u64 next_interval_check;
+
+        /* time used in current period */
+        cputime64_t current_interval_time;
+
+        /* time used in last period */
+        cputime64_t last_interval_time;
+};
+
+struct cgroup_subsys cpuacct_subsys;
+
+static inline struct cpuacct *cgroup_ca(struct cgroup *cont)
+{
+        return container_of(cgroup_subsys_state(cont, cpuacct_subsys_id),
+                            struct cpuacct, css);
+}
+
+static inline struct cpuacct *task_ca(struct task_struct *task)
+{
+        return container_of(task_subsys_state(task, cpuacct_subsys_id),
+                            struct cpuacct, css);
+}
+
+#define INTERVAL (HZ * 10)
+
+static inline u64 next_interval_boundary(u64 now)
+{
+        /* calculate the next interval boundary beyond the
+         * current time */
+        do_div(now, INTERVAL);
+        return (now + 1) * INTERVAL;
+}
+
+static struct cgroup_subsys_state *cpuacct_create(
+        struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
+        if (!ca)
+                return ERR_PTR(-ENOMEM);
+        spin_lock_init(&ca->lock);
+        ca->next_interval_check = next_interval_boundary(get_jiffies_64());
+        return &ca->css;
+}
+
+static void cpuacct_destroy(struct cgroup_subsys *ss,
+                            struct cgroup *cont)
+{
+        kfree(cgroup_ca(cont));
+}
+
+/* Lazily update the load calculation if necessary. Called with ca locked */
+static void cpuusage_update(struct cpuacct *ca)
+{
+        u64 now = get_jiffies_64();
+
+        /* If we're not due for an update, return */
+        if (ca->next_interval_check > now)
+                return;
+
+        if (ca->next_interval_check <= (now - INTERVAL)) {
+                /* If it's been more than an interval since the last
+                 * check, then catch up - the last interval must have
+                 * been zero load */
+                ca->last_interval_time = 0;
+                ca->next_interval_check = next_interval_boundary(now);
+        } else {
+                /* If a steal takes the last interval time negative,
+                 * then we just ignore it */
+                if ((s64)ca->current_interval_time > 0)
+                        ca->last_interval_time = ca->current_interval_time;
+                else
+                        ca->last_interval_time = 0;
+                ca->next_interval_check += INTERVAL;
+        }
+        ca->current_interval_time = 0;
+}
+
+static u64 cpuusage_read(struct cgroup *cont, struct cftype *cft)
+{
+        struct cpuacct *ca = cgroup_ca(cont);
+        u64 time;
+
+        spin_lock_irq(&ca->lock);
+        cpuusage_update(ca);
+        time = cputime64_to_jiffies64(ca->time);
+        spin_unlock_irq(&ca->lock);
+
+        /* Convert 64-bit jiffies to seconds */
+        time *= 1000;
+        do_div(time, HZ);
+        return time;
+}
+
+static u64 load_read(struct cgroup *cont, struct cftype *cft)
+{
+        struct cpuacct *ca = cgroup_ca(cont);
+        u64 time;
+
+        /* Find the time used in the previous interval */
+        spin_lock_irq(&ca->lock);
+        cpuusage_update(ca);
+        time = cputime64_to_jiffies64(ca->last_interval_time);
+        spin_unlock_irq(&ca->lock);
+
+        /* Convert time to a percentage, to give the load in the
+         * previous period */
+        time *= 100;
+        do_div(time, INTERVAL);
+
+        return time;
+}
+
+static struct cftype files[] = {
+        {
+                .name = "usage",
+                .read_uint = cpuusage_read,
+        },
+        {
+                .name = "load",
+                .read_uint = load_read,
+        }
+};
+
+static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
+}
+
+void cpuacct_charge(struct task_struct *task, cputime_t cputime)
+{
+
+        struct cpuacct *ca;
+        unsigned long flags;
+
+        if (!cpuacct_subsys.active)
+                return;
+        rcu_read_lock();
+        ca = task_ca(task);
+        if (ca) {
+                spin_lock_irqsave(&ca->lock, flags);
+                cpuusage_update(ca);
+                ca->time = cputime64_add(ca->time, cputime);
+                ca->current_interval_time =
+                        cputime64_add(ca->current_interval_time, cputime);
+                spin_unlock_irqrestore(&ca->lock, flags);
+        }
+        rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+        .name = "cpuacct",
+        .create = cpuacct_create,
+        .destroy = cpuacct_destroy,
+        .populate = cpuacct_populate,
+        .subsys_id = cpuacct_subsys_id,
+};
diff --git a/kernel/sched.c b/kernel/sched.c
index ed90be46fb31..72a2a16e2214 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -51,6 +51,7 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
+#include <linux/cpu_acct.h>
 #include <linux/kthread.h>
 #include <linux/seq_file.h>
 #include <linux/sysctl.h>
@@ -3307,9 +3308,13 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
 {
         struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
         cputime64_t tmp;
+        struct rq *rq = this_rq();
 
         p->utime = cputime_add(p->utime, cputime);
 
+        if (p != rq->idle)
+                cpuacct_charge(p, cputime);
+
         /* Add user time to cpustat. */
         tmp = cputime_to_cputime64(cputime);
         if (TASK_NICE(p) > 0)
@@ -3374,9 +3379,10 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
                 cpustat->irq = cputime64_add(cpustat->irq, tmp);
         else if (softirq_count())
                 cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
-        else if (p != rq->idle)
+        else if (p != rq->idle) {
                 cpustat->system = cputime64_add(cpustat->system, tmp);
-        else if (atomic_read(&rq->nr_iowait) > 0)
+                cpuacct_charge(p, cputime);
+        } else if (atomic_read(&rq->nr_iowait) > 0)
                 cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
         else
                 cpustat->idle = cputime64_add(cpustat->idle, tmp);
@@ -3412,8 +3418,10 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
                         cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
                 else
                         cpustat->idle = cputime64_add(cpustat->idle, tmp);
-        } else
+        } else {
                 cpustat->steal = cputime64_add(cpustat->steal, tmp);
+                cpuacct_charge(p, -tmp);
+        }
 }
 
 /*