[PATCH] drm/amdgpu: Skip err_count sysfs creation on VF unsupported RAS blocks

[Zhang, Hawking]

[AMD Official Use Only - AMD Internal Distribution Only]

+               DRM_DEV_DEBUG(adev->dev, "Unsupported SRIOV RAS telemetry block
+0x%x\n", block);

You may still want to keep dev_err, other that that, the patch is

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

Regards,
Hawking

-----Original Message-----
From: Skvortsov, Victor <Victor.Skvortsov at amd.com>
Sent: Thursday, January 23, 2025 06:00
To: amd-gfx at lists.freedesktop.org
Cc: Luo, Zhigang <Zhigang.Luo at amd.com>; Zhang, Hawking <Hawking.Zhang at amd.com>; Skvortsov, Victor <Victor.Skvortsov at amd.com>
Subject: [PATCH] drm/amdgpu: Skip err_count sysfs creation on VF unsupported RAS blocks

VFs are not able to query error counts for all RAS blocks. Rather than returning error for queries on these blocks, skip sysfs the creation all together.

Signed-off-by: Victor Skvortsov <victor.skvortsov at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c  |  3 +++  drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 +++++++++++++++-  drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  2 ++
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f0924aa3f4e4..0c338dcdde48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1864,6 +1864,9 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev,
        if (!obj || obj->attr_inuse)
                return -EINVAL;

+       if (amdgpu_sriov_vf(adev) && !amdgpu_virt_ras_telemetry_block_en(adev, head->block))
+               return 0;
+
        get_obj(obj);

        snprintf(obj->fs_data.sysfs_name, sizeof(obj->fs_data.sysfs_name), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 0af469ec6fcc..51ec98501aea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -1246,7 +1246,7 @@ amdgpu_ras_block_to_sriov(struct amdgpu_device *adev, enum amdgpu_ras_block bloc
        case AMDGPU_RAS_BLOCK__MPIO:
                return RAS_TELEMETRY_GPU_BLOCK_MPIO;
        default:
-               dev_err(adev->dev, "Unsupported SRIOV RAS telemetry block 0x%x\n", block);
+               DRM_DEV_DEBUG(adev->dev, "Unsupported SRIOV RAS telemetry block
+0x%x\n", block);
                return RAS_TELEMETRY_GPU_BLOCK_COUNT;
        }
 }
@@ -1331,3 +1331,17 @@ int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev)

        return 0;
 }
+
+bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev,
+                                       enum amdgpu_ras_block block)
+{
+       enum amd_sriov_ras_telemetry_gpu_block sriov_block;
+
+       sriov_block = amdgpu_ras_block_to_sriov(adev, block);
+
+       if (sriov_block >= RAS_TELEMETRY_GPU_BLOCK_COUNT ||
+           !amdgpu_sriov_ras_telemetry_block_en(adev, sriov_block))
+               return false;
+
+       return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 5381b8d596e6..270a032e2d70 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -406,4 +406,6 @@ bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev);  int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block,
                                  struct ras_err_data *err_data);
 int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev);
+bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev,
+                                       enum amdgpu_ras_block block);
 #endif
--
2.34.1