perf_counter: update mmap() counter read, take 2

Update the userspace read method.

Paul noted that:
 - userspace cannot observe ->lock & 1 on the same cpu.
 - we need a barrier() between reading ->lock and ->index
   to ensure we read them in that prticular order.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090406094517.368446033@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index f2b914d..e22ab47 100644 (file)
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -170,22 +170,18 @@ struct perf_counter_mmap_page {
         *   u32 seq;
         *   s64 count;
         *
-        * again:
-        *   seq = pc->lock;
-        *   if (unlikely(seq & 1)) {
-        *     cpu_relax();
-        *     goto again;
-        *   }
+        *   do {
+        *     seq = pc->lock;
         *
-        *   if (pc->index) {
-        *     count = pmc_read(pc->index - 1);
-        *     count += pc->offset;
-        *   } else
-        *     goto regular_read;
+        *     barrier()
+        *     if (pc->index) {
+        *       count = pmc_read(pc->index - 1);
+        *       count += pc->offset;
+        *     } else
+        *       goto regular_read;
         *
-        *   barrier();
-        *   if (pc->lock != seq)
-        *     goto again;
+        *     barrier();
+        *   } while (pc->lock != seq);
         *
         * NOTE: for obvious reason this only works on self-monitoring
         *       processes.