[v5 5/5] drm/amdgpu: fix invalid memory access in amdgpu_fence_driver_sw_fini()

[Gerry Liu]

> 2025年1月20日 17:04，Christian König <christian.koenig at amd.com> 写道：
> 
> Am 17.01.25 um 08:55 schrieb Jiang Liu:
>> Introduce amdgpu_device_fini_schedulers() to clean scheduler related
>> resources, and avoid possible invalid memory access.
>> 
>> Signed-off-by: Jiang Liu <gerry at linux.alibaba.com>
>> ---
>>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 35 +++++++++++++++++++---
>>  drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  |  9 ------
>>  2 files changed, 31 insertions(+), 13 deletions(-)
>> 
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index ee695e70fb4f..dd94f87c1f7c 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -2821,6 +2821,26 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
>>  	return r;
>>  }
>>  +static void __amdgpu_device_fini_schedulers(struct amdgpu_device *adev,
>> +					    int num_rings)
>> +{
>> +	int i;
>> +
>> +	for (i = 0; i < num_rings; ++i) {
>> +		struct amdgpu_ring *ring = adev->rings[i];
>> +
>> +		if (!ring || ring->no_scheduler)
>> +			continue;
>> +
>> +		drm_sched_fini(&ring->sched);
>> +	}
>> +}
>> +
>> +static void amdgpu_device_fini_schedulers(struct amdgpu_device *adev)
>> +{
>> +	__amdgpu_device_fini_schedulers(adev, AMDGPU_MAX_RINGS);
>> +}
>> +
>>  static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
>>  {
>>  	long timeout;
>> @@ -2857,27 +2877,32 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
>>  		if (r) {
>>  			DRM_ERROR("Failed to create scheduler on ring %s.\n",
>>  				  ring->name);
>> -			return r;
>> +			goto out_err;
>>  		}
>>  		r = amdgpu_uvd_entity_init(adev, ring);
>>  		if (r) {
>>  			DRM_ERROR("Failed to create UVD scheduling entity on ring %s.\n",
>>  				  ring->name);
>> -			return r;
>> +			goto out_sched_fini;
>>  		}
>>  		r = amdgpu_vce_entity_init(adev, ring);
>>  		if (r) {
>>  			DRM_ERROR("Failed to create VCE scheduling entity on ring %s.\n",
>>  				  ring->name);
>> -			return r;
>> +			goto out_sched_fini;
>>  		}
>>  	}
>>    	amdgpu_xcp_update_partition_sched_list(adev);
>>    	return 0;
>> -}
>>  +out_sched_fini:
>> +	drm_sched_fini(&adev->rings[i]->sched);
>> +out_err:
>> +	__amdgpu_device_fini_schedulers(adev, i);
> 
> I would just open code that as:
> 
> while (i--)
>     if (adev->rings[i] && !adev->rings[i]->no_scheduler)
>         drm_sched_fini(adev->rings[i]);
> 
> instead of delegating that to the __amdgpu_device_fini_schedulers() function.
> 
> That makes code maintenance easier should anything more need to be added to the amdgpu_device_fini_schedulers() function in the future.
OK, will fix it in next version.

> 
> Regards,
> Christian.
> 
>> +	return r;
>> +}
>>    /**
>>   * amdgpu_device_ip_init - run init for hardware IPs
>> @@ -3424,6 +3449,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
>>    	amdgpu_amdkfd_device_fini_sw(adev);
>>  +	amdgpu_device_fini_schedulers(adev);
>> +
>>  	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
>>  		if (!adev->ip_blocks[i].status.sw)
>>  			continue;
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> index 2f24a6aa13bf..c95895a7b888 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> @@ -650,15 +650,6 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
>>  		if (!ring || !ring->fence_drv.initialized)
>>  			continue;
>>  -		/*
>> -		 * Notice we check for sched.ops since there's some
>> -		 * override on the meaning of sched.ready by amdgpu.
>> -		 * The natural check would be sched.ready, which is
>> -		 * set as drm_sched_init() finishes...
>> -		 */
>> -		if (ring->sched.ops)
>> -			drm_sched_fini(&ring->sched);
>> -
>>  		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
>>  			dma_fence_put(ring->fence_drv.fences[j]);
>>  		kfree(ring->fence_drv.fences);