2023-11-18 15:52:46

by Yury Norov

Subject: [PATCH 08/34] drivers/perf: optimize ali_drw_get_counter_idx() by using find_bit()

The function searches used_mask for a set bit in a for-loop bit by bit.
We can do it faster by using atomic find_and_set_bit().

Signed-off-by: Yury Norov <[email protected]>
---
drivers/perf/alibaba_uncore_drw_pmu.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index 19d459a36be5..2a3b7701d568 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -274,15 +274,9 @@ static const struct attribute_group *ali_drw_pmu_attr_groups[] = {
static int ali_drw_get_counter_idx(struct perf_event *event)
{
struct ali_drw_pmu *drw_pmu = to_ali_drw_pmu(event->pmu);
- int idx;
+ int idx = find_and_set_bit(drw_pmu->used_mask, ALI_DRW_PMU_COMMON_MAX_COUNTERS);

- for (idx = 0; idx < ALI_DRW_PMU_COMMON_MAX_COUNTERS; ++idx) {
- if (!test_and_set_bit(idx, drw_pmu->used_mask))
- return idx;
- }
-
- /* The counters are all in use. */
- return -EBUSY;
+ return idx < ALI_DRW_PMU_COMMON_MAX_COUNTERS ? idx : -EBUSY;
}

static u64 ali_drw_pmu_read_counter(struct perf_event *event)
--
2.39.2

2023-11-21 15:55:09

by Will Deacon

Subject: Re: [PATCH 08/34] drivers/perf: optimize ali_drw_get_counter_idx() by using find_bit()

On Sat, Nov 18, 2023 at 07:50:39AM -0800, Yury Norov wrote:
> The function searches used_mask for a set bit in a for-loop bit by bit.
> We can do it faster by using atomic find_and_set_bit().
>
> Signed-off-by: Yury Norov <[email protected]>
> ---
> drivers/perf/alibaba_uncore_drw_pmu.c | 10 ++--------
> 1 file changed, 2 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
> index 19d459a36be5..2a3b7701d568 100644
> --- a/drivers/perf/alibaba_uncore_drw_pmu.c
> +++ b/drivers/perf/alibaba_uncore_drw_pmu.c
> @@ -274,15 +274,9 @@ static const struct attribute_group *ali_drw_pmu_attr_groups[] = {
> static int ali_drw_get_counter_idx(struct perf_event *event)
> {
> struct ali_drw_pmu *drw_pmu = to_ali_drw_pmu(event->pmu);
> - int idx;
> + int idx = find_and_set_bit(drw_pmu->used_mask, ALI_DRW_PMU_COMMON_MAX_COUNTERS);
>
> - for (idx = 0; idx < ALI_DRW_PMU_COMMON_MAX_COUNTERS; ++idx) {
> - if (!test_and_set_bit(idx, drw_pmu->used_mask))
> - return idx;
> - }
> -
> - /* The counters are all in use. */
> - return -EBUSY;
> + return idx < ALI_DRW_PMU_COMMON_MAX_COUNTERS ? idx : -EBUSY;
> }
>
> static u64 ali_drw_pmu_read_counter(struct perf_event *event)
> --
> 2.39.2

Acked-by: Will Deacon <[email protected]>

Will