drm/amdgpu: Fix handling of KFD initialization failures

Remember KFD module initializaton status in a global variable. Skip KFD
device probing when the module was not initialized. Other amdgpu_amdkfd
calls are then protected by the adev->kfd.dev check.

Also print a clear error message when KFD disables itself. Amdgpu
continues its initialization even when KFD failed.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -36,6 +36,8 @@
  */
 uint64_t amdgpu_amdkfd_total_mem_size;
 
+bool kfd_initialized;
+
 int amdgpu_amdkfd_init(void)
 {
 	struct sysinfo si;
@@ -51,19 +53,26 @@ int amdgpu_amdkfd_init(void)
 #else
 	ret = -ENOENT;
 #endif
+	kfd_initialized = !ret;
 
 	return ret;
 }
 
 void amdgpu_amdkfd_fini(void)
 {
-	kgd2kfd_exit();
+	if (kfd_initialized) {
+		kgd2kfd_exit();
+		kfd_initialized = false;
+	}
 }
 
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	bool vf = amdgpu_sriov_vf(adev);
 
+	if (!kfd_initialized)
+		return;
+
 	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
 				      adev->pdev, adev->asic_type, vf);
 

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

@@ -97,6 +97,7 @@ void kfd_chardev_exit(void)
 	device_destroy(kfd_class, MKDEV(kfd_char_dev_major, 0));
 	class_destroy(kfd_class);
 	unregister_chrdev(kfd_char_dev_major, kfd_dev_name);
+	kfd_device = NULL;
 }
 
 struct device *kfd_chardev(void)

drivers/gpu/drm/amd/amdkfd/kfd_module.c

@@ -70,6 +70,7 @@ err_create_wq:
 err_topology:
 	kfd_chardev_exit();
 err_ioctl:
+	pr_err("KFD is disabled due to module initialization failure\n");
 	return err;
 }