From 56a7af21c3e79db917def98b98b898d88a0760b5 Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Thu, 13 Feb 2020 15:37:09 +0800
Subject: drm/amdgpu: record non-zero error counter info in NBIO before
Git-commit: 3cd4f61859b1b916215e2cfc623cd7076dc76a22
Patch-mainline: v5.7-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322
 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>
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 65eb378fa035..149d386590df 100644
--- 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");
 
-- 
2.28.0