sched/cputime: Fix cpu_timer_sample_group() double accounting

While looking over the cpu-timer code I found that we appear to add
the delta for the calling task twice, through:

  cpu_timer_sample_group()
    thread_group_cputimer()
      thread_group_cputime()
        times->sum_exec_runtime += task_sched_runtime();

    *sample = cputime.sum_exec_runtime + task_delta_exec();

Which would make the sample run ahead, making the sleep short.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20141112113737.GI10476@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 8422b4ed6882be8e8ece65f9a1bcd2ceb5af2bfb..b9376cd5a187e818c28c09935eb022a1920848a8 100644 (file)
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -77,11 +77,6 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
        return kstat_cpu(cpu).irqs_sum;
 }
 
-/*
- * Lock/unlock the current runqueue - to extract task statistics:
- */
-extern unsigned long long task_delta_exec(struct task_struct *);
-
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(cputime_t);

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5f12ca65c9a76ef0a2a2dcac519de1cc1a15a483..797a6c84c48d15517876ce7d56dc085aeb41e62a 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2499,19 +2499,6 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
        return ns;
 }
 
-unsigned long long task_delta_exec(struct task_struct *p)
-{
-       unsigned long flags;
-       struct rq *rq;
-       u64 ns = 0;
-
-       rq = task_rq_lock(p, &flags);
-       ns = do_task_delta_exec(p, rq);
-       task_rq_unlock(rq, p, &flags);
-
-       return ns;
-}
-
 /*
  * Return accounted runtime for the task.
  * In case the task is currently running, return the runtime plus current's

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 492b986195d53350abe899b0ecd059f91edb77a4..a16b67859e2a79929331c5008f96fd7f29ebbfc1 100644 (file)
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -553,7 +553,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
                *sample = cputime_to_expires(cputime.utime);
                break;
        case CPUCLOCK_SCHED:
-               *sample = cputime.sum_exec_runtime + task_delta_exec(p);
+               *sample = cputime.sum_exec_runtime;
                break;
        }
        return 0;