drm/amdgpu: add RAS error count reset for gfx_v9_4_3

Add GFX RAS error count reset function.

v2: remove xcp operation.
    only select_se_sh when instance number is more than 1.
v3: add check for se_num before select_se_sh.
    change instance from 0 to xcc_id for register access.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2023-02-08 14:54:01 +08:00 committed by Alex Deucher
parent bfa84da618
commit 30feef0676
1 changed files with 38 additions and 0 deletions

View File

@ -3773,6 +3773,39 @@ static void gfx_v9_4_3_inst_query_ras_err_count(struct amdgpu_device *adev,
err_data->ue_count += ue_count;
}
static void gfx_v9_4_3_inst_reset_ras_err_count(struct amdgpu_device *adev,
void *ras_error_status, int xcc_id)
{
uint32_t i, j, k;
mutex_lock(&adev->grbm_idx_mutex);
for (i = 0; i < ARRAY_SIZE(gfx_v9_4_3_ce_reg_list); i++) {
for (j = 0; j < gfx_v9_4_3_ce_reg_list[i].se_num; j++) {
for (k = 0; k < gfx_v9_4_3_ce_reg_list[i].reg_entry.reg_inst; k++) {
/* no need to select if instance number is 1 */
if (gfx_v9_4_3_ce_reg_list[i].se_num > 1 ||
gfx_v9_4_3_ce_reg_list[i].reg_entry.reg_inst > 1)
gfx_v9_4_3_xcc_select_se_sh(adev, j, 0, k, xcc_id);
amdgpu_ras_inst_reset_ras_error_count(adev,
&(gfx_v9_4_3_ce_reg_list[i].reg_entry),
1,
GET_INST(GC, xcc_id));
amdgpu_ras_inst_reset_ras_error_count(adev,
&(gfx_v9_4_3_ue_reg_list[i].reg_entry),
1,
GET_INST(GC, xcc_id));
}
}
}
gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
xcc_id);
mutex_unlock(&adev->grbm_idx_mutex);
}
static void gfx_v9_4_3_inst_query_ea_err_status(struct amdgpu_device *adev,
int xcc_id)
{
@ -3882,6 +3915,11 @@ static void gfx_v9_4_3_query_ras_error_count(struct amdgpu_device *adev,
gfx_v9_4_3_inst_query_ras_err_count);
}
static void gfx_v9_4_3_reset_ras_error_count(struct amdgpu_device *adev)
{
amdgpu_gfx_ras_error_func(adev, NULL, gfx_v9_4_3_inst_reset_ras_err_count);
}
static void gfx_v9_4_3_query_ras_error_status(struct amdgpu_device *adev)
{
amdgpu_gfx_ras_error_func(adev, NULL, gfx_v9_4_3_inst_query_ras_err_status);