diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 90cce0c74a034664092cf510ec7a4cc57a6e7443..f2b914de3f0c784fa2f3a1363f5c8f5b85e30935 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -167,30 +167,28 @@ struct perf_counter_mmap_page {
 	/*
 	 * Bits needed to read the hw counters in user-space.
 	 *
-	 * The index and offset should be read atomically using the seqlock:
-	 *
-	 *   __u32 seq, index;
-	 *   __s64 offset;
+	 *   u32 seq;
+	 *   s64 count;
 	 *
 	 * again:
-	 *   rmb();
 	 *   seq = pc->lock;
-	 *
 	 *   if (unlikely(seq & 1)) {
 	 *     cpu_relax();
 	 *     goto again;
 	 *   }
 	 *
-	 *   index = pc->index;
-	 *   offset = pc->offset;
+	 *   if (pc->index) {
+	 *     count = pmc_read(pc->index - 1);
+	 *     count += pc->offset;
+	 *   } else
+	 *     goto regular_read;
 	 *
-	 *   rmb();
+	 *   barrier();
 	 *   if (pc->lock != seq)
 	 *     goto again;
 	 *
-	 * After this, index contains architecture specific counter index + 1,
-	 * so that 0 means unavailable, offset contains the value to be added
-	 * to the result of the raw timer read to obtain this counter's value.
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
 	 */
 	__u32	lock;			/* seqlock for synchronization */
 	__u32	index;			/* hardware counter identifier */
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index f105a6e696c20c178de06fa332c9407e6bb4ce0f..2a5d4f525567800eb52a8d280e02fe504e7b970d 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1340,13 +1340,13 @@ void perf_counter_update_userpage(struct perf_counter *counter)
 	 */
 	preempt_disable();
 	++userpg->lock;
-	smp_wmb();
+	barrier();
 	userpg->index = counter->hw.idx;
 	userpg->offset = atomic64_read(&counter->count);
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
 		userpg->offset -= atomic64_read(&counter->hw.prev_count);
 
-	smp_wmb();
+	barrier();
 	++userpg->lock;
 	preempt_enable();
 unlock: