Received-SPF: pass (google.com: domain of linux-kernel+bounces-182313-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Precedence: bulk
MIME-Version: 1.0
References: <20240516115721.1.I8d413e641239c059d018d46cc569048b813a5d9b@changeid>
 <9dd1cfd1-fe13-4434-a7cc-e14113dcaf53@amd.com>
In-Reply-To: <9dd1cfd1-fe13-4434-a7cc-e14113dcaf53@amd.com>
From: Alex Deucher <alexdeucher@gmail.com>
Date: Fri, 17 May 2024 11:46:16 -0400
Message-ID: <CADnq5_NGLrrFmFHFX2bC7naByJGofEiYQyWvRP6CO4BDFo52TQ@mail.gmail.com>
Subject: Re: [PATCH] drm/amdgpu: Remove GC HW IP 9.3.0 from noretry=1
To: =?UTF-8?Q?Christian_K=C3=B6nig?= <christian.koenig@amd.com>
Cc: Tim Van Patten <timvp@chromium.org>, LKML <linux-kernel@vger.kernel.org>, 
	alexander.deucher@amd.com, prathyushi.nangia@amd.com, 
	Tim Van Patten <timvp@google.com>, Daniel Vetter <daniel@ffwll.ch>, David Airlie <airlied@gmail.com>, 
	Felix Kuehling <Felix.Kuehling@amd.com>, Ikshwaku Chauhan <ikshwaku.chauhan@amd.com>, Le Ma <le.ma@amd.com>, 
	Lijo Lazar <lijo.lazar@amd.com>, Mario Limonciello <mario.limonciello@amd.com>, 
	"Pan, Xinhui" <Xinhui.Pan@amd.com>, "Shaoyun.liu" <Shaoyun.liu@amd.com>, 
	Shiwu Zhang <shiwu.zhang@amd.com>, Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>, 
	amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, May 17, 2024 at 2:35=E2=80=AFAM Christian K=C3=B6nig
<christian.koenig@amd.com> wrote:
>
> Am 16.05.24 um 19:57 schrieb Tim Van Patten:
> > From: Tim Van Patten <timvp@google.com>
> >
> > The following commit updated gmc->noretry from 0 to 1 for GC HW IP
> > 9.3.0:
> >
> >      commit 5f3854f1f4e2 ("drm/amdgpu: add more cases to noretry=3D1")
> >
> > This causes the device to hang when a page fault occurs, until the
> > device is rebooted. Instead, revert back to gmc->noretry=3D0 so the dev=
ice
> > is still responsive.
>
> Wait a second. Why does the device hang on a page fault? That shouldn't
> happen independent of noretry.
>
> So that strongly sounds like this is just hiding a bug elsewhere.

Fair enough, but this is also the only gfx9 APU which defaults to
noretry=3D1, all of the rest are dGPUs.  I'd argue it should align with
the other GFX9 APUs or they should all enable noretry=3D1.

Alex

>
> Regards,
> Christian.
>
> >
> > Fixes: 5f3854f1f4e2 ("drm/amdgpu: add more cases to noretry=3D1")
> > Signed-off-by: Tim Van Patten <timvp@google.com>
> > ---
> >
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 1 -
> >   1 file changed, 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/=
amd/amdgpu/amdgpu_gmc.c
> > index be4629cdac049..bff54a20835f1 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> > @@ -876,7 +876,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *a=
dev)
> >       struct amdgpu_gmc *gmc =3D &adev->gmc;
> >       uint32_t gc_ver =3D amdgpu_ip_version(adev, GC_HWIP, 0);
> >       bool noretry_default =3D (gc_ver =3D=3D IP_VERSION(9, 0, 1) ||
> > -                             gc_ver =3D=3D IP_VERSION(9, 3, 0) ||
> >                               gc_ver =3D=3D IP_VERSION(9, 4, 0) ||
> >                               gc_ver =3D=3D IP_VERSION(9, 4, 1) ||
> >                               gc_ver =3D=3D IP_VERSION(9, 4, 2) ||
>