drm/amdgpu: add support for recording ras error address

more than one error address may be recorded in one query

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Dennis Li <dennis.li@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 5f428a3929bdb3e520642381bcb4f9173d09e0bd..143153a3c5b096226d4530addbe581baea74ba95 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -588,7 +588,7 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
                struct ras_query_if *info)
 {
        struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
-       struct ras_err_data err_data = {0, 0};
+       struct ras_err_data err_data = {0, 0, 0, NULL};
 
        if (!obj)
                return -EINVAL;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 80e94d604a2e7e0789ac154d1b2ecf6ebb5bcdd0..0920db7aff3449cebbaf1a2ec21b8c36b55da46c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -131,6 +131,8 @@ struct ras_fs_data {
 struct ras_err_data {
        unsigned long ue_count;
        unsigned long ce_count;
+       unsigned long err_addr_cnt;
+       uint64_t *err_addr;
 };
 
 struct ras_err_handler_data {