From 7caf33d430a5e7cc03bfc4070e74d3be19466f1d Mon Sep 17 00:00:00 2001
From: Zhigang Luo <zhigang.luo@amd.com>
Date: Fri, 26 Nov 2021 12:16:45 -0500
Subject: drm/amdgpu: skip reset other device in the same hive if it's SRIOV VF
Git-commit: 175ac6ec6bd8db6b7e08fed8fd189bd492015b28
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

On SRIOV, host driver can support FLR(function level reset) on individual VF
within the hive which might bring the individual device back to normal without
the necessary to execute the hive reset. If the FLR failed , host driver will
trigger the hive reset, each guest VF will get reset notification before the
real hive reset been executed. The VF device can handle the reset request
individually in it's reset work handler.

This change updated gpu recover sequence to skip reset other device in
the same hive for SRIOV VF.

Signed-off-by: Zhigang Luo <zhigang.luo@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 20f07732a9d4..16001a310d99 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4746,7 +4746,7 @@ static int amdgpu_device_lock_hive_adev(struct amdgpu_device *adev, struct amdgp
 {
 	struct amdgpu_device *tmp_adev = NULL;
 
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		if (!hive) {
 			dev_err(adev->dev, "Hive is NULL while device has multiple xgmi nodes");
 			return -ENODEV;
@@ -4958,7 +4958,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 * We always reset all schedulers for device and all devices for XGMI
 	 * hive so that should take care of them too.
 	 */
-	hive = amdgpu_get_xgmi_hive(adev);
+	if (!amdgpu_sriov_vf(adev))
+		hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
 		if (atomic_cmpxchg(&hive->in_reset, 0, 1) != 0) {
 			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
@@ -4999,7 +5000,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 * to put adev in the 1st position.
 	 */
 	INIT_LIST_HEAD(&device_list);
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			list_add_tail(&tmp_adev->reset_list, &device_list);
 		if (!list_is_first(&adev->reset_list, &device_list))
-- 
2.38.1