Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230703150135.5784-1-ubizjak@gmail.com>
In-Reply-To: <20230703150135.5784-1-ubizjak@gmail.com>
From:   Alex Deucher <alexdeucher@gmail.com>
Date:   Wed, 9 Aug 2023 18:09:36 -0400
Message-ID: <CADnq5_MCquO_Sh0RUVYATbLwS1+h2UrLHoUkCXYeF7=R4kZmDg@mail.gmail.com>
Subject: Re: [PATCH] drm/amdgpu: Use local64_try_cmpxchg in amdgpu_perf_read
To:     Uros Bizjak <ubizjak@gmail.com>
Cc:     amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
        linux-kernel@vger.kernel.org, "Pan, Xinhui" <Xinhui.Pan@amd.com>,
        Alex Deucher <alexander.deucher@amd.com>,
        =?UTF-8?Q?Christian_K=C3=B6nig?= <christian.koenig@amd.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

Applied.  Thanks!

Alex

On Mon, Jul 3, 2023 at 7:16=E2=80=AFPM Uros Bizjak <ubizjak@gmail.com> wrot=
e:
>
> Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) =3D=
=3D old
> in amdgpu_perf_read.  x86 CMPXCHG instruction returns success in ZF flag,
> so this change saves a compare after cmpxchg (and related move instructio=
n
> 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: Alex Deucher <alexander.deucher@amd.com>
> Cc: "Christian K=C3=B6nig" <christian.koenig@amd.com>
> Cc: "Pan, Xinhui" <Xinhui.Pan@amd.com>
> Cc: David Airlie <airlied@gmail.com>
> Cc: Daniel Vetter <daniel@ffwll.ch>
> Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c | 5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/am=
d/amdgpu/amdgpu_pmu.c
> index 71ee361d0972..6e91ea1de5aa 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
> @@ -276,9 +276,8 @@ static void amdgpu_perf_read(struct perf_event *event=
)
>             (!pe->adev->df.funcs->pmc_get_count))
>                 return;
>
> +       prev =3D local64_read(&hwc->prev_count);
>         do {
> -               prev =3D local64_read(&hwc->prev_count);
> -
>                 switch (hwc->config_base) {
>                 case AMDGPU_PMU_EVENT_CONFIG_TYPE_DF:
>                 case AMDGPU_PMU_EVENT_CONFIG_TYPE_XGMI:
> @@ -289,7 +288,7 @@ static void amdgpu_perf_read(struct perf_event *event=
)
>                         count =3D 0;
>                         break;
>                 }
> -       } while (local64_cmpxchg(&hwc->prev_count, prev, count) !=3D prev=
);
> +       } while (!local64_try_cmpxchg(&hwc->prev_count, &prev, count));
>
>         local64_add(count - prev, &event->count);
>  }
> --
> 2.41.0
>