perf_counter: Implement more accurate per task statistics

With the introduction of PERF_EVENT_READ we have the
possibility to provide accurate counter values for
individual tasks in a task hierarchy.

However, due to the lazy context switching used for similar
counter contexts our current per task counts are way off.

In order to maintain some of the lazy switch benefits we
don't disable it out-right, but simply iterate the active
counters and flip the values between the contexts.

This only reads the counters but does not need to reprogram
the full PMU.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 3 insertions, 1 deletions

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 6a384f04755a..de70a10b5ec8 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -178,8 +178,9 @@ struct perf_counter_attr {
                                 mmap           :  1, /* include mmap data     */
                                 comm           :  1, /* include comm data     */
                                 freq           :  1, /* use freq, not period  */
+                                inherit_stat   :  1, /* per task counts       */
 
-                                __reserved_1   : 53;
+                                __reserved_1   : 52;
 
         __u32                   wakeup_events;  /* wakeup every n events */
         __u32                   __reserved_2;
@@ -602,6 +603,7 @@ struct perf_counter_context {
         int                             nr_counters;
         int                             nr_active;
         int                             is_active;
+        int                             nr_stat;
         atomic_t                        refcount;
         struct task_struct              *task;