perf: Optimize the perf_output() path by removing IRQ-disables

Since we can now assume there is only a single writer
to each buffer, we can remove per-cpu lock thingy and
use a simply nest-count to the same effect.

This removes the need to disable IRQs.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 2 insertions, 3 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0b521fc8f5b0..f1f853a9d5eb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -597,12 +597,12 @@ struct perf_mmap_data {
         atomic_t                        events;         /* event_id limit       */
 
         atomic_long_t                   head;           /* write position    */
-        atomic_long_t                   done_head;      /* completed head    */
 
-        atomic_t                        lock;           /* concurrent writes */
         atomic_t                        wakeup;         /* needs a wakeup    */
         atomic_t                        lost;           /* nr records lost   */
 
+        atomic_t                        nest;           /* nested writers    */
+
         long                            watermark;      /* wakeup watermark  */
 
         struct perf_event_mmap_page     *user_page;
@@ -807,7 +807,6 @@ struct perf_output_handle {
         unsigned long                   offset;
         int                             nmi;
         int                             sample;
-        int                             locked;
 };
 
 #ifdef CONFIG_PERF_EVENTS