[PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[Jiansong Chen]

Enable gpu recovery for navy_flounder by default to trigger
reset once needed.

Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
Change-Id: If213b4c7a5444872ec51869da53a374bf40db7fe
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 087afab67e22..dd67b589b4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4206,6 +4206,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_NAVI14:
 		case CHIP_NAVI12:
 		case CHIP_SIENNA_CICHLID:
+		case CHIP_NAVY_FLOUNDER:
 			break;
 		default:
 			goto disabled;
-- 
2.25.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

RE: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[Zhou1, Tao]

[AMD Public Use]

Reviewed-by: Tao Zhou <tao.zhou1@amd.com>

> -----Original Message-----
> From: Jiansong Chen <Jiansong.Chen@amd.com>
> Sent: Monday, January 11, 2021 5:50 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Zhou1, Tao <Tao.Zhou1@amd.com>; Zhang, Hawking
> <Hawking.Zhang@amd.com>; Chen, Jiansong (Simon)
> <Jiansong.Chen@amd.com>
> Subject: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder
> 
> Enable gpu recovery for navy_flounder by default to trigger reset once needed.
> 
> Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
> Change-Id: If213b4c7a5444872ec51869da53a374bf40db7fe
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 087afab67e22..dd67b589b4ab 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -4206,6 +4206,7 @@ bool amdgpu_device_should_recover_gpu(struct
> amdgpu_device *adev)
>  		case CHIP_NAVI14:
>  		case CHIP_NAVI12:
>  		case CHIP_SIENNA_CICHLID:
> +		case CHIP_NAVY_FLOUNDER:
>  			break;
>  		default:
>  			goto disabled;
> --
> 2.25.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[Paul Menzel]

Dear Jiansong,


Am 11.01.21 um 10:49 schrieb Jiansong Chen:
> Enable gpu recovery for navy_flounder by default to trigger
> reset once needed.

[…]

Why was it disabled before? Were some bugs fixed, that it works now?

How did you test this? Is there a command to “crash“ the GPU, so it can 
be recovered?

Please extend the commit message accordingly.


Kind regards,

Paul
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

RE: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[Chen, Jiansong (Simon)]

[AMD Official Use Only - Internal Distribution Only]

Hi Paul,
We just enable gpu recovery when the feature is stable enough for navy_flounder.  And you can use debugfs interface to perform
a manual GPU reset. Here is more detail https://github.com/RadeonOpenCompute/ROCm/issues/616. Thanks!

Regards,
Jiansong
-----Original Message-----
From: Paul Menzel <pmenzel@molgen.mpg.de>
Sent: Monday, January 11, 2021 7:58 PM
To: Chen, Jiansong (Simon) <Jiansong.Chen@amd.com>
Cc: Zhou1, Tao <Tao.Zhou1@amd.com>; Zhang, Hawking <Hawking.Zhang@amd.com>; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

Dear Jiansong,


Am 11.01.21 um 10:49 schrieb Jiansong Chen:
> Enable gpu recovery for navy_flounder by default to trigger reset once
> needed.

[…]

Why was it disabled before? Were some bugs fixed, that it works now?

How did you test this? Is there a command to “crash“ the GPU, so it can be recovered?

Please extend the commit message accordingly.


Kind regards,

Paul
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] drm/amdgpu: enable gpu recovery for navy_flounder

[Paul Menzel]

Dear Jiansong,


Am 11.01.21 um 13:26 schrieb Chen, Jiansong (Simon):
> [AMD Official Use Only - Internal Distribution Only]

(What does this notice mean exactly? Should be removed for public
mailing lists.)

> We just enable gpu recovery when the feature is stable enough for
> navy_flounder.

Then please mention that in the commit message. Something like:

 > Now that GPU recovery is stable enough, …

> And you can use debugfs interface to perform a manual
> GPU reset. Here is more detail
> https://github.com/RadeonOpenCompute/ROCm/issues/616. Thanks!
Thank you. It would still be nice, to have this information in the 
commit message.


Kind regards,

Paul
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx