drm/amdgpu: Use per device reset_domain for XGMI on sriov configuration

For SRIOV configuration, host driver control the reset method(either FLR or
heavier chain reset). The host will notify the guest individually with FLR
message if individual GPU within the hive need to be reset. So for guest
side, no need to use hive->reset_domain to replace the original per
device reset_domain

Signed-off-by: shaoyunl <shaoyun.liu@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/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 62b26f0e37b071a1d12ecfd09b476990e73eade4..e2180436299534d67842bdf23067eb9623ec03af 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2453,17 +2453,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
                if (amdgpu_xgmi_add_device(adev) == 0) {
                        struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 
-                       if (!hive->reset_domain ||
-                           !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
-                               r = -ENOENT;
+                       if (!amdgpu_sriov_vf(adev)) {
+                               if (!hive->reset_domain ||
+                                   !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
+                                       r = -ENOENT;
+                                       amdgpu_put_xgmi_hive(hive);
+                                       goto init_failed;
+                               }
+
+                               /* Drop the early temporary reset domain we created for device */
+                               amdgpu_reset_put_reset_domain(adev->reset_domain);
+                               adev->reset_domain = hive->reset_domain;
                                amdgpu_put_xgmi_hive(hive);
-                               goto init_failed;
                        }
-
-                       /* Drop the early temporary reset domain we created for device */
-                       amdgpu_reset_put_reset_domain(adev->reset_domain);
-                       adev->reset_domain = hive->reset_domain;
-                       amdgpu_put_xgmi_hive(hive);
                }
        }
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index d3b483aa81f834fc337ff6746b32c023222cce34..10477ca52a41a33aec6b3256cd5da6f21fe3193d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -391,24 +391,33 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
                goto pro_end;
        }
 
+       /**
+        * Only init hive->reset_domain for none SRIOV configuration. For SRIOV,
+        * Host driver decide how to reset the GPU either through FLR or chain reset.
+        * Guest side will get individual notifications from the host for the FLR
+        * if necessary.
+        */
+       if (!amdgpu_sriov_vf(adev)) {
        /**
         * Avoid recreating reset domain when hive is reconstructed for the case
-        * of reset the devices in the XGMI hive during probe for SRIOV
+        * of reset the devices in the XGMI hive during probe for passthrough GPU
         * See https://www.spinics.net/lists/amd-gfx/msg58836.html
         */
-       if (adev->reset_domain->type != XGMI_HIVE) {
-               hive->reset_domain = amdgpu_reset_create_reset_domain(XGMI_HIVE, "amdgpu-reset-hive");
-                       if (!hive->reset_domain) {
-                               dev_err(adev->dev, "XGMI: failed initializing reset domain for xgmi hive\n");
-                               ret = -ENOMEM;
-                               kobject_put(&hive->kobj);
-                               kfree(hive);
-                               hive = NULL;
-                               goto pro_end;
-                       }
-       } else {
-               amdgpu_reset_get_reset_domain(adev->reset_domain);
-               hive->reset_domain = adev->reset_domain;
+               if (adev->reset_domain->type != XGMI_HIVE) {
+                       hive->reset_domain =
+                               amdgpu_reset_create_reset_domain(XGMI_HIVE, "amdgpu-reset-hive");
+                               if (!hive->reset_domain) {
+                                       dev_err(adev->dev, "XGMI: failed initializing reset domain for xgmi hive\n");
+                                       ret = -ENOMEM;
+                                       kobject_put(&hive->kobj);
+                                       kfree(hive);
+                                       hive = NULL;
+                                       goto pro_end;
+                               }
+               } else {
+                       amdgpu_reset_get_reset_domain(adev->reset_domain);
+                       hive->reset_domain = adev->reset_domain;
+               }
        }
 
        hive->hive_id = adev->gmc.xgmi.hive_id;