drm/amdgpu: Add common helper to reset ras error

Add common helper to reset ras error status. It
applies to IP blocks that follow the new ras error
logging register design, and need to write 0 to
reset the error status. For IP blocks that don't
support the new design, please still implement ip
specific helper.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@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 57e86af..8a16a06 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3222,3 +3222,23 @@ void amdgpu_ras_inst_query_ras_error_count(struct amdgpu_device *adev,
                }
        }
 }
+
+void amdgpu_ras_inst_reset_ras_error_count(struct amdgpu_device *adev,
+                                          const struct amdgpu_ras_err_status_reg_entry *reg_list,
+                                          uint32_t reg_list_size,
+                                          uint32_t instance)
+{
+       uint32_t err_status_lo_offset, err_status_hi_offset;
+       uint32_t i;
+
+       for (i = 0; i < reg_list_size; i++) {
+               err_status_lo_offset =
+                       AMDGPU_RAS_REG_ENTRY_OFFSET(reg_list[i].hwip, instance,
+                                                   reg_list[i].seg_lo, reg_list[i].reg_lo);
+               err_status_hi_offset =
+                       AMDGPU_RAS_REG_ENTRY_OFFSET(reg_list[i].hwip, instance,
+                                                   reg_list[i].seg_hi, reg_list[i].reg_hi);
+               WREG32(err_status_lo_offset, 0);
+               WREG32(err_status_hi_offset, 0);
+       }
+}

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index c820af7..e96333d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -750,4 +750,8 @@ void amdgpu_ras_inst_query_ras_error_count(struct amdgpu_device *adev,
                                           uint32_t instance,
                                           uint32_t err_type,
                                           unsigned long *err_count);
+void amdgpu_ras_inst_reset_ras_error_count(struct amdgpu_device *adev,
+                                          const struct amdgpu_ras_err_status_reg_entry *reg_list,
+                                          uint32_t reg_list_size,
+                                          uint32_t instance);
 #endif