[V2 11/11] drm/amdgpu: do not reset gpu for virtualization

Deucher, Alexander Alexander.Deucher at amd.com
Tue Jan 10 15:28:29 UTC 2017


> -----Original Message-----
> From: amd-gfx [mailto:amd-gfx-bounces at lists.freedesktop.org] On Behalf
> Of Yu, Xiangliang
> Sent: Tuesday, January 10, 2017 8:36 AM
> To: Christian König; amd-gfx at lists.freedesktop.org
> Cc: Liu, Monk
> Subject: RE: [V2 11/11] drm/amdgpu: do not reset gpu for virtualization
> 
> > -----Original Message-----
> > From: Christian König [mailto:deathsimple at vodafone.de]
> > Sent: Tuesday, January 10, 2017 9:19 PM
> > To: Yu, Xiangliang <Xiangliang.Yu at amd.com>; amd-
> > gfx at lists.freedesktop.org
> > Cc: Liu, Monk <Monk.Liu at amd.com>
> > Subject: Re: [V2 11/11] drm/amdgpu: do not reset gpu for virtualization
> >
> > Am 10.01.2017 um 11:00 schrieb Xiangliang Yu:
> > > Current job timeout setting is not fit for virtualization, so it will
> > > cause job timeout sometimes. Add workaround for this when timeout
> > > happen.
> > >
> > > Signed-off-by: Monk Liu <Monk.Liu at amd.com>
> > > Signed-off-by: Xiangliang Yu <Xiangliang.Yu at amd.com>
> > > ---
> > >   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
> > >   1 file changed, 3 insertions(+)
> > >
> > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > > b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > > index a6d828c..5705fbd 100644
> > > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> > > @@ -2324,6 +2324,9 @@ int amdgpu_gpu_reset(struct amdgpu_device
> > *adev)
> > >   	int resched;
> > >   	bool need_full_reset;
> > >
> > > +	if (amdgpu_sriov_vf(adev))
> >
> > At bare minimum we should print a warning here and increase or
> completely
> > disable the job timeout when virtualization is enabled.
> 
> The timeout function has the warning message, I think don't need more.
> The patch is just a workaround, later need to enhance the whole gpu reset
> process.

Please add a comment that explains that this is a temporary workaround, with that:
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>


More information about the amd-gfx mailing list