@@ -191,9 +191,10 @@ __perf_output_begin(struct perf_output_handle *handle,
perf_output_get_handle(handle);
+ offset = local_read(&rb->head);
do {
+ head = offset;
tail = READ_ONCE(rb->user_page->data_tail);
- offset = head = local_read(&rb->head);
if (!rb->overwrite) {
if (unlikely(!ring_buffer_has_space(head, tail,
perf_data_size(rb),
@@ -217,7 +218,7 @@ __perf_output_begin(struct perf_output_handle *handle,
head += size;
else
head -= size;
- } while (local_cmpxchg(&rb->head, offset, head) != offset);
+ } while (!local_try_cmpxchg(&rb->head, &offset, head));
if (backward) {
offset = head;
Use local_try_cmpxchg instead of local_cmpxchg (*ptr, old, new) == old in __perf_output_begin. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg. Also, local_try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails. There is no need to re-read the value in the loop. No functional change intended. Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ian Rogers <irogers@google.com> Signed-off-by: Uros Bizjak <ubizjak@gmail.com> --- kernel/events/ring_buffer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)