[PATCH] drm/amdgpu: ignoring unsupported ras blocks when MCA bank dispatches

Li, Candice Candice.Li at amd.com
Tue May 7 02:17:42 UTC 2024


[AMD Official Use Only - General]

Reviewed-by: Candice Li <candice.li at amd.com>



Thanks,
Candice

-----Original Message-----
From: Wang, Yang(Kevin) <KevinYang.Wang at amd.com>
Sent: Tuesday, May 7, 2024 9:36 AM
To: Wang, Yang(Kevin) <KevinYang.Wang at amd.com>; amd-gfx at lists.freedesktop.org
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Zhou1, Tao <Tao.Zhou1 at amd.com>; Li, Candice <Candice.Li at amd.com>; Zhou, Hao (Claire) <Hao.Zhou at amd.com>
Subject: RE: [PATCH] drm/amdgpu: ignoring unsupported ras blocks when MCA bank dispatches

Ping...

Best Regards,
Kevin

-----Original Message-----
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Yang Wang
Sent: 2024年5月6日 14:47
To: amd-gfx at lists.freedesktop.org
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Zhou1, Tao <Tao.Zhou1 at amd.com>; Li, Candice <Candice.Li at amd.com>
Subject: [PATCH] drm/amdgpu: ignoring unsupported ras blocks when MCA bank dispatches

This patch is used to solve the problem of incorrect parsing of error counts.
When the UE trigger gpu is reset, the driver will attempt to parse all possible ras blocks.
For ras blocks that are not supported by the current ASIC, the driver should ignore this error.

Signed-off-by: Yang Wang <kevinyang.wang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index a7736aa58ba9..0c9a271c5028 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -415,7 +415,7 @@ static int amdgpu_mca_dispatch_mca_set(struct amdgpu_device *adev, enum amdgpu_r

                count = 0;
                ret = amdgpu_mca_smu_parse_mca_error_count(adev, blk, type, entry, &count);
-               if (ret)
+               if (ret && ret != -EOPNOTSUPP)
                        return ret;

                if (!count)
--
2.34.1



More information about the amd-gfx mailing list