[PATCH v2 1/1] drm/amdgpu: clean up bo in vce and vcn test

[Christian König]

Am 08.12.20 um 19:59 schrieb Nirmoy Das:
> BO created with amdgpu_bo_create_reserved() wasn't clean
> properly before, which causes:
>
> [   21.056218] WARNING: CPU: 0 PID: 7 at drivers/gpu/drm/ttm/ttm_bo.c:518 ttm_bo_release+0x2bf/0x310 [ttm]
> <snip>
> [   21.056430] Call Trace:
> [   21.056525]  amdgpu_bo_unref+0x1a/0x30 [amdgpu]
> [   21.056635]  amdgpu_vcn_dec_send_msg+0x1b2/0x270 [amdgpu]
> [   21.056740]  amdgpu_vcn_dec_get_create_msg.constprop.0+0xd8/0x100 [amdgpu]
> [   21.056843]  amdgpu_vcn_dec_ring_test_ib+0x27/0x180 [amdgpu]
> [   21.056936]  amdgpu_ib_ring_tests+0xf1/0x150 [amdgpu]
> [   21.057024]  amdgpu_device_delayed_init_work_handler+0x11/0x30 [amdgpu]
> [   21.057030]  process_one_work+0x1df/0x370
> [   21.057033]  worker_thread+0x46/0x340
> [   21.057034]  ? process_one_work+0x370/0x370
> [   21.057037]  kthread+0x11b/0x140
> [   21.057039]  ? __kthread_bind_mask+0x60/0x60
> [   21.057043]  ret_from_fork+0x22/0x30
>
> Signed-off-by: Nirmoy Das <nirmoy.das at amd.com>

At some point we should probably switch to using an SA BO and stop this 
mess here.

But for now the patch is Reviewed-by: Christian König 
<christian.koenig at amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 9 ++++++---
>   2 files changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
> index ecaa2d7483b2..78a4dd9bf11f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
> @@ -1151,6 +1151,6 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
>   error:
>   	dma_fence_put(fence);
>   	amdgpu_bo_unreserve(bo);
> -	amdgpu_bo_unref(&bo);
> +	amdgpu_bo_free_kernel(&bo, NULL, NULL);
>   	return r;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> index 7e19a6656715..921b81054c1b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> @@ -465,6 +465,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
>   	struct amdgpu_job *job;
>   	struct amdgpu_ib *ib;
>   	uint64_t addr;
> +	void *msg = NULL;
>   	int i, r;
>   
>   	r = amdgpu_job_alloc_with_ib(adev, 64,
> @@ -474,6 +475,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
>   
>   	ib = &job->ibs[0];
>   	addr = amdgpu_bo_gpu_offset(bo);
> +	msg = amdgpu_bo_kptr(bo);
>   	ib->ptr[0] = PACKET0(adev->vcn.internal.data0, 0);
>   	ib->ptr[1] = addr;
>   	ib->ptr[2] = PACKET0(adev->vcn.internal.data1, 0);
> @@ -492,7 +494,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
>   
>   	amdgpu_bo_fence(bo, f, false);
>   	amdgpu_bo_unreserve(bo);
> -	amdgpu_bo_unref(&bo);
> +	amdgpu_bo_free_kernel(&bo, NULL, (void **)&msg);
>   
>   	if (fence)
>   		*fence = dma_fence_get(f);
> @@ -505,7 +507,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
>   
>   err:
>   	amdgpu_bo_unreserve(bo);
> -	amdgpu_bo_unref(&bo);
> +	amdgpu_bo_free_kernel(&bo, NULL, (void **)&msg);
>   	return r;
>   }
>   
> @@ -761,6 +763,7 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
>   error:
>   	dma_fence_put(fence);
>   	amdgpu_bo_unreserve(bo);
> -	amdgpu_bo_unref(&bo);
> +	amdgpu_bo_free_kernel(&bo, NULL, NULL);
> +
>   	return r;
>   }