drm/amdkfd: Add device to topology after it is completely inited

We can't have devices that are not completely initialized in kfd topology.
Otherwise it is a race condition when user access not completely
initialized device. This also addresses a kfd_topology_add_device accessing
NULL dqm pointer issue.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9d1b026e29e945706180acd20f66754c9ca4bd34..ebac7d7f9956e610e6cab41ee01f1d5bf03345b4 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -603,11 +603,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
        if (kfd->kfd2kgd->get_hive_id)
                kfd->hive_id = kfd->kfd2kgd->get_hive_id(kfd->kgd);
 
-       if (kfd_topology_add_device(kfd)) {
-               dev_err(kfd_device, "Error adding device to topology\n");
-               goto kfd_topology_add_device_error;
-       }
-
        if (kfd_interrupt_init(kfd)) {
                dev_err(kfd_device, "Error initializing interrupts\n");
                goto kfd_interrupt_error;
@@ -631,6 +626,11 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
        kfd->dbgmgr = NULL;
 
+       if (kfd_topology_add_device(kfd)) {
+               dev_err(kfd_device, "Error adding device to topology\n");
+               goto kfd_topology_add_device_error;
+       }
+
        kfd->init_complete = true;
        dev_info(kfd_device, "added device %x:%x\n", kfd->pdev->vendor,
                 kfd->pdev->device);
@@ -640,14 +640,13 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
        goto out;
 
+kfd_topology_add_device_error:
 kfd_resume_error:
 device_iommu_error:
        device_queue_manager_uninit(kfd->dqm);
 device_queue_manager_error:
        kfd_interrupt_exit(kfd);
 kfd_interrupt_error:
-       kfd_topology_remove_device(kfd);
-kfd_topology_add_device_error:
        kfd_doorbell_fini(kfd);
 kfd_doorbell_error:
        kfd_gtt_sa_fini(kfd);