[PATCH] drm/amdgpu/sriov: give 8s for recover vram under RUNTIME

[Deng, Emily]

Hi Alex,
     Thanks for your review. 
     The host gim driver gives every VF fullaccess_timeout is 3000, so for 4 vf, the worst case is 3*3000(9000), if the vf number is more than 4,
then the time will be longer, so 8000 is not the worst time.
     But with using 8000, it will pass all the TDR test, so it is Ok.  Will send a patch to modify the commit message as your suggestion.
     
Best wishes
Emily Deng 

-----Original Message-----
From: Alex Deucher <alexdeucher at gmail.com> 
Sent: Wednesday, August 8, 2018 12:42 AM
To: Deng, Emily <Emily.Deng at amd.com>
Cc: amd-gfx list <amd-gfx at lists.freedesktop.org>; Liu, Monk <Monk.Liu at amd.com>
Subject: Re: [PATCH] drm/amdgpu/sriov: give 8s for recover vram under RUNTIME

On Tue, Aug 7, 2018 at 6:22 AM, Emily Deng <Emily.Deng at amd.com> wrote:
> Under runtime, the wait fence time could be quite long when other VFs 
> are in exclusive mode.
>
> SWDEV-161490
>
> Change-Id: Ifc32d56ca7fde01b1f4fe2b0db6959b51909008a
> Signed-off-by: Monk Liu <Monk.Liu at amd.com>
> Signed-off-by: Emily Deng <Emily.Deng at amd.com>

Seems pretty long.  Is this value based on any evidence (e.g., worse case length of time slices, etc.) or just a long value that happens to work?  Might be nice to provide a bit more context in the commit message.  E.g., extend the timeout for recovering vram bos from shadows on sr-iov to cover the worst case scenario for timeslices and VFs.

Alex


> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 1d933db..ef82ad1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3124,7 +3124,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
>         long tmo;
>
>         if (amdgpu_sriov_runtime(adev))
> -               tmo = msecs_to_jiffies(amdgpu_lockup_timeout);
> +               tmo = msecs_to_jiffies(8000);
>         else
>                 tmo = msecs_to_jiffies(100);
>
> --
> 2.7.4
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx