drm/amdgpu: support gfx ras error injection and err_cnt query

check gfx error count in both ras querry function and
ras interrupt handler.

gfx ras is still disabled by default due to known stability
issue found in gpu reset.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 0c31bd06a7e8b23432175aea57a45a5f63f9dd7b..e15fedb0ce7340df68c220833c5f727cc19ecfa1 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -602,6 +602,10 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
                if (adev->umc.funcs->query_ras_error_count)
                        adev->umc.funcs->query_ras_error_count(adev, &err_data);
                break;
+       case AMDGPU_RAS_BLOCK__GFX:
+               if (adev->gfx.funcs->query_ras_error_count)
+                       adev->gfx.funcs->query_ras_error_count(adev, &err_data);
+               break;
        default:
                break;
        }
@@ -639,13 +643,22 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
        if (!obj)
                return -EINVAL;
 
-       if (block_info.block_id != TA_RAS_BLOCK__UMC) {
+       switch (info->head.block) {
+       case AMDGPU_RAS_BLOCK__GFX:
+               if (adev->gfx.funcs->ras_error_inject)
+                       ret = adev->gfx.funcs->ras_error_inject(adev, info);
+               else
+                       ret = -EINVAL;
+               break;
+       case AMDGPU_RAS_BLOCK__UMC:
+               ret = psp_ras_trigger_error(&adev->psp, &block_info);
+               break;
+       default:
                DRM_INFO("%s error injection is not supported yet\n",
                         ras_block_str(info->head.block));
-               return -EINVAL;
+               ret = -EINVAL;
        }
 
-       ret = psp_ras_trigger_error(&adev->psp, &block_info);
        if (ret)
                DRM_ERROR("RAS ERROR: inject %s error failed ret %d\n",
                                ras_block_str(info->head.block),

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index c6ad662602bef51d2b7766efb54c39026c962502..bd82f6303bd6ac3a8b64cd2092867d4b98a981f0 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -5611,6 +5611,8 @@ static int gfx_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
 {
        /* TODO ue will trigger an interrupt. */
        kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+       if (adev->gfx.funcs->query_ras_error_count)
+               adev->gfx.funcs->query_ras_error_count(adev, err_data);
        amdgpu_ras_reset_gpu(adev, 0);
        return AMDGPU_RAS_UE;
 }