Commit 81665e35 authored by Xiaogang Chen's avatar Xiaogang Chen Committed by Alex Deucher
Browse files

drm/amdkfd: Check if there are kfd porcesses using adev by kfd_processes_count 



During gpu hot-unplug need check if there are kfd porcesses still using the
being removed gpu before clean resources of the device. Current driver checks
if kfd_processes_table is empty. kfd processes are not terminated after
removed from kfd_processes_table immediately. They are still alive and may
access the device until kfd_process_wq work queue got ran.

Check kfd->kfd_processes_count value that is updated after kfd process got
uninitialized when its ref becomes zero.

Fixes: 6cca686d ("drm/amdkfd: kfd driver supports hot unplug/replug amdgpu devices")
Signed-off-by: default avatarXiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: default avatarFelix Kuehling <felix.kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d12d05c4bc4c15585130af43e897923ff292df7b)
parent e6c2e6c2

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

+1 −32
Original line number Diff line number Diff line
@@ -1737,37 +1737,6 @@ bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entr 
	return false;

}



/* check if there is kfd process still uses adev */

static bool kgd2kfd_check_device_idle(struct amdgpu_device *adev)

{

	struct kfd_process *p;

	struct hlist_node *p_temp;

	unsigned int temp;

	struct kfd_node *dev;



	mutex_lock(&kfd_processes_mutex);



	if (hash_empty(kfd_processes_table)) {

		mutex_unlock(&kfd_processes_mutex);

		return true;

	}



	/* check if there is device still use adev */

	hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) {

		for (int i = 0; i < p->n_pdds; i++) {

			dev = p->pdds[i]->dev;

			if (dev->adev == adev) {

				mutex_unlock(&kfd_processes_mutex);

				return false;

			}

		}

	}



	mutex_unlock(&kfd_processes_mutex);



	return true;

}



/** kgd2kfd_teardown_processes - gracefully tear down existing

 *  kfd processes that use adev

 *
@@ -1800,7 +1769,7 @@ void kgd2kfd_teardown_processes(struct amdgpu_device *adev) 
	mutex_unlock(&kfd_processes_mutex);



	/* wait all kfd processes use adev terminate */

	while (!kgd2kfd_check_device_idle(adev))

	while (!!atomic_read(&adev->kfd.dev->kfd_processes_count))

		cond_resched();

}