drm/amdgpu: Handle xgmi device removal.

XGMI hive has some resources allocted on device init which
needs to be deallocated when the device is unregistered.

v2: Remove creation of dedicated wq for XGMI hive reset.
v3: Use the gmc.xgmi.supported flag

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 24 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c75badfa5c4c..bfd286c40631 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1864,6 +1864,9 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 {
         int i, r;
 
+        if (adev->gmc.xgmi.num_physical_nodes > 1)
+                amdgpu_xgmi_remove_device(adev);
+
         amdgpu_amdkfd_device_fini(adev);
 
         amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index f8c86d0593dd..1b15ff3266b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -135,3 +135,23 @@ exit:
         mutex_unlock(&xgmi_mutex);
         return ret;
 }
+
+void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
+{
+        struct amdgpu_hive_info *hive;
+
+        if (!adev->gmc.xgmi.supported)
+                return;
+
+        mutex_lock(&xgmi_mutex);
+
+        hive = amdgpu_get_xgmi_hive(adev);
+        if (!hive)
+                goto exit;
+
+        if (!(hive->number_devices--))
+                mutex_destroy(&hive->hive_lock);
+
+exit:
+        mutex_unlock(&xgmi_mutex);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 6335bfdcc51d..6151eb9c8ad3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -35,5 +35,6 @@ struct amdgpu_hive_info {
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev);
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
 int amdgpu_xgmi_add_device(struct amdgpu_device *adev);
+void amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
 
 #endif