2023-07-03 15:22:53

by Uros Bizjak

Subject: [PATCH] dmaengine:idxd: Use local64_try_cmpxchg in perfmon_pmu_event_update

Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
in perfmon_pmu_event_update. 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: Fenghua Yu <[email protected]>
Cc: Dave Jiang <[email protected]>
Cc: Vinod Koul <[email protected]>
Signed-off-by: Uros Bizjak <[email protected]>
---
drivers/dma/idxd/perfmon.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
index d73004f47cf4..fdda6d604262 100644
--- a/drivers/dma/idxd/perfmon.c
+++ b/drivers/dma/idxd/perfmon.c
@@ -245,12 +245,11 @@ static void perfmon_pmu_event_update(struct perf_event *event)
int shift = 64 - idxd->idxd_pmu->counter_width;
struct hw_perf_event *hwc = &event->hw;

+ prev_raw_count = local64_read(&hwc->prev_count);
do {
- prev_raw_count = local64_read(&hwc->prev_count);
new_raw_count = perfmon_pmu_read_counter(event);
- } while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count);
-
+ } while (!local64_try_cmpxchg(&hwc->prev_count,
+ &prev_raw_count, new_raw_count));
n = (new_raw_count << shift);
p = (prev_raw_count << shift);

--
2.41.0

2023-07-05 15:16:16

by Dave Jiang

Subject: Re: [PATCH] dmaengine:idxd: Use local64_try_cmpxchg in perfmon_pmu_event_update

On 7/3/23 07:52, Uros Bizjak wrote:
> Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
> in perfmon_pmu_event_update. 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: Fenghua Yu <[email protected]>
> Cc: Dave Jiang <[email protected]>
> Cc: Vinod Koul <[email protected]>
> Signed-off-by: Uros Bizjak <[email protected]>


Cc: Tom Zanussi

Tom do you mind review this patch? Thanks!

> ---
> drivers/dma/idxd/perfmon.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
> index d73004f47cf4..fdda6d604262 100644
> --- a/drivers/dma/idxd/perfmon.c
> +++ b/drivers/dma/idxd/perfmon.c
> @@ -245,12 +245,11 @@ static void perfmon_pmu_event_update(struct perf_event *event)
> int shift = 64 - idxd->idxd_pmu->counter_width;
> struct hw_perf_event *hwc = &event->hw;
>
> + prev_raw_count = local64_read(&hwc->prev_count);
> do {
> - prev_raw_count = local64_read(&hwc->prev_count);
> new_raw_count = perfmon_pmu_read_counter(event);
> - } while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
> - new_raw_count) != prev_raw_count);
> -
> + } while (!local64_try_cmpxchg(&hwc->prev_count,
> + &prev_raw_count, new_raw_count));
> n = (new_raw_count << shift);
> p = (prev_raw_count << shift);
>

2023-07-10 21:53:03

by Tom Zanussi

Subject: Re: [PATCH] dmaengine:idxd: Use local64_try_cmpxchg in perfmon_pmu_event_update

On Wed, 2023-07-05 at 07:53 -0700, Dave Jiang wrote:
>
>
> On 7/3/23 07:52, Uros Bizjak wrote:
> > Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
> > in perfmon_pmu_event_update.  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: Fenghua Yu <[email protected]>
> > Cc: Dave Jiang <[email protected]>
> > Cc: Vinod Koul <[email protected]>
> > Signed-off-by: Uros Bizjak <[email protected]>
>
>
> Cc: Tom Zanussi
>
> Tom do you mind review this patch? Thanks!

Looks fine to me.

Thanks,

Reviewed-by: Tom Zanussi <[email protected]>

>
> > ---
> >   drivers/dma/idxd/perfmon.c | 7 +++----
> >   1 file changed, 3 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
> > index d73004f47cf4..fdda6d604262 100644
> > --- a/drivers/dma/idxd/perfmon.c
> > +++ b/drivers/dma/idxd/perfmon.c
> > @@ -245,12 +245,11 @@ static void perfmon_pmu_event_update(struct perf_event *event)
> >         int shift = 64 - idxd->idxd_pmu->counter_width;
> >         struct hw_perf_event *hwc = &event->hw;
> >  
> > +       prev_raw_count = local64_read(&hwc->prev_count);
> >         do {
> > -               prev_raw_count = local64_read(&hwc->prev_count);
> >                 new_raw_count = perfmon_pmu_read_counter(event);
> > -       } while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
> > -                       new_raw_count) != prev_raw_count);
> > -
> > +       } while (!local64_try_cmpxchg(&hwc->prev_count,
> > +                                     &prev_raw_count, new_raw_count));
> >         n = (new_raw_count << shift);
> >         p = (prev_raw_count << shift);
> >  

2023-08-01 19:14:26

by Vinod Koul

Subject: Re: [PATCH] dmaengine:idxd: Use local64_try_cmpxchg in perfmon_pmu_event_update

On Mon, 03 Jul 2023 16:52:37 +0200, Uros Bizjak wrote:
> Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
> in perfmon_pmu_event_update. 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.
>
> [...]

Applied, thanks!

[1/1] dmaengine:idxd: Use local64_try_cmpxchg in perfmon_pmu_event_update
commit: cae701b9ccf128edea26982f73178087fc3ad180

Best regards,
--
~Vinod