[PATCH] perf/x86: Use local64_try_cmpxchg

[Uros Bizjak]

Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old.
x86 CMPXCHG instruction returns success in ZF flag, so this change saves a
compare after cmpxchg (and related move instruction in front of cmpxchg).

Also, 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@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Ian Rogers <irogers@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc. "H. Peter Anvin" <hpa@xxxxxxxxx>
Signed-off-by: Uros Bizjak <ubizjak@xxxxxxxxx>
---
 arch/x86/events/amd/ibs.c      |  4 ++--
 arch/x86/events/core.c         | 10 ++++------
 arch/x86/events/intel/cstate.c | 10 ++++------
 arch/x86/events/msr.c          |  8 +++-----
 4 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 371014802191..b54db2138c16 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -156,8 +156,8 @@ perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width)
 	 * count to the generic event atomically:
 	 */
 	prev_raw_count = local64_read(&hwc->prev_count);
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					new_raw_count) != prev_raw_count)
+	if (!local64_try_cmpxchg(&hwc->prev_count,
+				 &prev_raw_count, new_raw_count))
 		return 0;
 
 	/*
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9d248703cbdd..23c96420dea1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -129,13 +129,11 @@ u64 x86_perf_event_update(struct perf_event *event)
 	 * exchange a new raw count - then add that new-prev delta
 	 * count to the generic event atomically:
 	 */
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	rdpmcl(hwc->event_base_rdpmc, new_raw_count);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					new_raw_count) != prev_raw_count)
-		goto again;
+	do {
+		rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	/*
 	 * Now we have the new raw value and have updated the prev
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 835862c548cc..97035db68df2 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -365,13 +365,11 @@ static void cstate_pmu_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	u64 prev_raw_count, new_raw_count;
 
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	new_raw_count = cstate_pmu_read_counter(event);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-			    new_raw_count) != prev_raw_count)
-		goto again;
+	do {
+		new_raw_count = cstate_pmu_read_counter(event);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	local64_add(new_raw_count - prev_raw_count, &event->count);
 }
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 0feaaa571303..61c59e0627d4 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -244,12 +244,10 @@ static void msr_event_update(struct perf_event *event)
 	s64 delta;
 
 	/* Careful, an NMI might modify the previous event value: */
-again:
 	prev = local64_read(&event->hw.prev_count);
-	now = msr_read_counter(event);
-
-	if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev)
-		goto again;
+	do {
+		now = msr_read_counter(event);
+	} while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, now));
 
 	delta = now - prev;
 	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
-- 
2.41.0