[tip:,perf/core] perf/core: Use local64_try_cmpxchg in perf_swevent_set_period
Commit Message
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 28fd85a10a2a73658c6e26056d9e093de06b5a22
Gitweb: https://git.kernel.org/tip/28fd85a10a2a73658c6e26056d9e093de06b5a22
Author: Uros Bizjak <ubizjak@gmail.com>
AuthorDate: Sat, 08 Jul 2023 10:10:57 +02:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Mon, 10 Jul 2023 09:52:35 +02:00
perf/core: Use local64_try_cmpxchg in perf_swevent_set_period
Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
in perf_swevent_set_period. 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.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230708081129.45915-1-ubizjak@gmail.com
---
kernel/events/core.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
@@ -9595,16 +9595,16 @@ u64 perf_swevent_set_period(struct perf_event *event)
hwc->last_period = hwc->sample_period;
-again:
- old = val = local64_read(&hwc->period_left);
- if (val < 0)
- return 0;
+ old = local64_read(&hwc->period_left);
+ do {
+ val = old;
+ if (val < 0)
+ return 0;
- nr = div64_u64(period + val, period);
- offset = nr * period;
- val -= offset;
- if (local64_cmpxchg(&hwc->period_left, old, val) != old)
- goto again;
+ nr = div64_u64(period + val, period);
+ offset = nr * period;
+ val -= offset;
+ } while (!local64_try_cmpxchg(&hwc->period_left, &old, val));
return nr;
}