schedstat: consolidate per-task cpu runtime stats

[pandora-kernel.git] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 74498c8..fd835fc 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -596,6 +596,8 @@ struct rq {
 #ifdef CONFIG_SCHEDSTATS
        /* latency stats */
        struct sched_info rq_sched_info;
+       unsigned long long rq_cpu_time;
+       /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
        /* sys_sched_yield() stats */
        unsigned int yld_exp_empty;
@@ -2266,6 +2268,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 
        smp_wmb();
        rq = task_rq_lock(p, &flags);
+       update_rq_clock(rq);
        old_state = p->state;
        if (!(old_state & state))
                goto out;
@@ -2323,7 +2326,6 @@ out_activate:
                schedstat_inc(p, se.nr_wakeups_local);
        else
                schedstat_inc(p, se.nr_wakeups_remote);
-       update_rq_clock(rq);
        activate_task(rq, p, 1);
        success = 1;
 
@@ -3685,7 +3687,7 @@ out_balanced:
 static void idle_balance(int this_cpu, struct rq *this_rq)
 {
        struct sched_domain *sd;
-       int pulled_task = -1;
+       int pulled_task = 0;
        unsigned long next_balance = jiffies + HZ;
        cpumask_t tmpmask;
 
@@ -6564,7 +6566,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                        req = list_entry(rq->migration_queue.next,
                                         struct migration_req, list);
                        list_del_init(&req->list);
+                       spin_unlock_irq(&rq->lock);
                        complete(&req->done);
+                       spin_lock_irq(&rq->lock);
                }
                spin_unlock_irq(&rq->lock);
                break;
@@ -7673,8 +7677,14 @@ static struct sched_domain_attr *dattr_cur;
  */
 static cpumask_t fallback_doms;
 
-void __attribute__((weak)) arch_update_cpu_topology(void)
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
 {
+       return 0;
 }
 
 /*
@@ -7766,17 +7776,21 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
                             struct sched_domain_attr *dattr_new)
 {
        int i, j, n;
+       int new_topology;
 
        mutex_lock(&sched_domains_mutex);
 
        /* always unregister in case we don't destroy any domains */
        unregister_sched_domain_sysctl();
 
+       /* Let architecture update cpu core mappings. */
+       new_topology = arch_update_cpu_topology();
+
        n = doms_new ? ndoms_new : 0;
 
        /* Destroy deleted domains */
        for (i = 0; i < ndoms_cur; i++) {
-               for (j = 0; j < n; j++) {
+               for (j = 0; j < n && !new_topology; j++) {
                        if (cpus_equal(doms_cur[i], doms_new[j])
                            && dattrs_equal(dattr_cur, i, dattr_new, j))
                                goto match1;
@@ -7796,7 +7810,7 @@ match1:
 
        /* Build new domains */
        for (i = 0; i < ndoms_new; i++) {
-               for (j = 0; j < ndoms_cur; j++) {
+               for (j = 0; j < ndoms_cur && !new_topology; j++) {
                        if (cpus_equal(doms_new[i], doms_cur[j])
                            && dattrs_equal(dattr_new, i, dattr_cur, j))
                                goto match2;
@@ -9263,6 +9277,41 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
        kfree(ca);
 }
 
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+       u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+       u64 data;
+
+#ifndef CONFIG_64BIT
+       /*
+        * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+        */
+       spin_lock_irq(&cpu_rq(cpu)->lock);
+       data = *cpuusage;
+       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 = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+       /*
+        * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+        */
+       spin_lock_irq(&cpu_rq(cpu)->lock);
+       *cpuusage = val;
+       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)
 {
@@ -9270,17 +9319,8 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
        u64 totalcpuusage = 0;
        int i;
 
-       for_each_possible_cpu(i) {
-               u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
-               /*
-                * Take rq->lock to make 64-bit addition safe on 32-bit
-                * platforms.
-                */
-               spin_lock_irq(&cpu_rq(i)->lock);
-               totalcpuusage += *cpuusage;
-               spin_unlock_irq(&cpu_rq(i)->lock);
-       }
+       for_each_present_cpu(i)
+               totalcpuusage += cpuacct_cpuusage_read(ca, i);
 
        return totalcpuusage;
 }
@@ -9297,23 +9337,39 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
                goto out;
        }
 
-       for_each_possible_cpu(i) {
-               u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+       for_each_present_cpu(i)
+               cpuacct_cpuusage_write(ca, i, 0);
 
-               spin_lock_irq(&cpu_rq(i)->lock);
-               *cpuusage = 0;
-               spin_unlock_irq(&cpu_rq(i)->lock);
-       }
 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 struct cftype files[] = {
        {
                .name = "usage",
                .read_u64 = cpuusage_read,
                .write_u64 = cpuusage_write,
        },
+       {
+               .name = "usage_percpu",
+               .read_seq_string = cpuacct_percpu_seq_read,
+       },
+
 };
 
 static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)