perf: Cure task_oncpu_function_call() races

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

diff --git a/kernel/sched.c b/kernel/sched.c
index ea3e5ef..31cb5d5 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -553,9 +553,6 @@ struct rq {
        /* try_to_wake_up() stats */
        unsigned int ttwu_count;
        unsigned int ttwu_local;
-
-       /* BKL stats */
-       unsigned int bkl_count;
 #endif
 };
 
@@ -609,6 +606,9 @@ static inline struct task_group *task_group(struct task_struct *p)
        struct task_group *tg;
        struct cgroup_subsys_state *css;
 
+       if (p->flags & PF_EXITING)
+               return &root_task_group;
+
        css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
                        lockdep_is_held(&task_rq(p)->lock));
        tg = container_of(css, struct task_group, css);
@@ -2265,27 +2265,6 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 #endif /* CONFIG_SMP */
 
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p:         the task to evaluate
- * @func:      the function to be called
- * @info:      the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
-                             void (*func) (void *info), void *info)
-{
-       int cpu;
-
-       preempt_disable();
-       cpu = task_cpu(p);
-       if (task_curr(p))
-               smp_call_function_single(cpu, func, info, 1);
-       preempt_enable();
-}
-
 #ifdef CONFIG_SMP
 /*
  * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
@@ -2776,9 +2755,12 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
                    struct task_struct *next)
 {
+       sched_info_switch(prev, next);
+       perf_event_task_sched_out(prev, next);
        fire_sched_out_preempt_notifiers(prev, next);
        prepare_lock_switch(rq, next);
        prepare_arch_switch(next);
+       trace_sched_switch(prev, next);
 }
 
 /**
@@ -2911,7 +2893,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
        struct mm_struct *mm, *oldmm;
 
        prepare_task_switch(rq, prev, next);
-       trace_sched_switch(prev, next);
+
        mm = next->mm;
        oldmm = prev->active_mm;
        /*
@@ -3887,7 +3869,7 @@ static inline void schedule_debug(struct task_struct *prev)
        schedstat_inc(this_rq(), sched_count);
 #ifdef CONFIG_SCHEDSTATS
        if (unlikely(prev->lock_depth >= 0)) {
-               schedstat_inc(this_rq(), bkl_count);
+               schedstat_inc(this_rq(), rq_sched_info.bkl_count);
                schedstat_inc(prev, sched_info.bkl_count);
        }
 #endif
@@ -3989,9 +3971,6 @@ need_resched_nonpreemptible:
        rq->skip_clock_update = 0;
 
        if (likely(prev != next)) {
-               sched_info_switch(prev, next);
-               perf_event_task_sched_out(prev, next);
-
                rq->nr_switches++;
                rq->curr = next;
                ++*switch_count;
@@ -4871,7 +4850,8 @@ recheck:
                 * assigned.
                 */
                if (rt_bandwidth_enabled() && rt_policy(policy) &&
-                               task_group(p)->rt_bandwidth.rt_runtime == 0) {
+                               task_group(p)->rt_bandwidth.rt_runtime == 0 &&
+                               !task_group_is_autogroup(task_group(p))) {
                        __task_rq_unlock(rq);
                        raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                        return -EPERM;
@@ -8882,6 +8862,20 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
        }
 }
 
+static void
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+{
+       /*
+        * cgroup_exit() is called in the copy_process() failure path.
+        * Ignore this case since the task hasn't ran yet, this avoids
+        * trying to poke a half freed task state from generic code.
+        */
+       if (!(task->flags & PF_EXITING))
+               return;
+
+       sched_move_task(task);
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
                                u64 shareval)
@@ -8954,6 +8948,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
        .destroy        = cpu_cgroup_destroy,
        .can_attach     = cpu_cgroup_can_attach,
        .attach         = cpu_cgroup_attach,
+       .exit           = cpu_cgroup_exit,
        .populate       = cpu_cgroup_populate,
        .subsys_id      = cpu_cgroup_subsys_id,
        .early_init     = 1,