drm/amdgpu: skip reset other device in the same hive if it's SRIOV VF

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>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a1c14466f23d49e63a07280a93d6df103c6b49f8..25a9e529d62ed48766a6cf55e7491fbe1c7febd9 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4747,7 +4747,7 @@ 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;
@@ -4959,7 +4959,8 @@ 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",
@@ -5000,7 +5001,7 @@ 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))