drm/amdgpu: record non-zero error counter info in NBIO before resetting GPU

When NBIO's RAS error happens, before trigging GPU reset, it's needed
to record error counter information, which can correct the error counter
value missed issue when reading from debugfs.

Signed-off-by: Guchun Chen <guchun.chen@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/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 65eb378fa035391936c9762e57746e071d9c13ce..149d386590df2beb6b7f034ec46061e5b6c58be8 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -318,6 +318,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 {
        uint32_t bif_doorbell_intr_cntl;
        struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if);
+       struct ras_err_data err_data = {0, 0, 0, NULL};
 
        bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
        if (REG_GET_FIELD(bif_doorbell_intr_cntl,
@@ -332,7 +333,19 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
                 * clear error status after ras_controller_intr according to
                 * hw team and count ue number for query
                 */
-               nbio_v7_4_query_ras_error_count(adev, &obj->err_data);
+               nbio_v7_4_query_ras_error_count(adev, &err_data);
+
+               /* logging on error counter and printing for awareness */
+               obj->err_data.ue_count += err_data.ue_count;
+               obj->err_data.ce_count += err_data.ce_count;
+
+               if (err_data.ce_count)
+                       DRM_INFO("%ld correctable errors detected in %s block\n",
+                               obj->err_data.ce_count, adev->nbio.ras_if->name);
+
+               if (err_data.ue_count)
+                       DRM_INFO("%ld uncorrectable errors detected in %s block\n",
+                               obj->err_data.ue_count, adev->nbio.ras_if->name);
 
                DRM_WARN("RAS controller interrupt triggered by NBIF error\n");