[PATCH v2 7/8] drm/amdgpu: Fix sdma code crash post device unplug

[Christian König]

Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
> entity->rq becomes null aftre device unplugged so just return early
> in that case.

Mhm, do you have a backtrace for this?

This should only be called by an IOCTL and IOCTLs should already call 
drm_dev_enter()/exit() on their own...

Christian.

>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 21 ++++++++++++++++-----
>   1 file changed, 16 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> index 8d9c6fe..d252427 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> @@ -24,6 +24,7 @@
>   #include "amdgpu_job.h"
>   #include "amdgpu_object.h"
>   #include "amdgpu_trace.h"
> +#include <drm/drm_drv.h>
>   
>   #define AMDGPU_VM_SDMA_MIN_NUM_DW	256u
>   #define AMDGPU_VM_SDMA_MAX_NUM_DW	(16u * 1024u)
> @@ -94,7 +95,12 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
>   	struct drm_sched_entity *entity;
>   	struct amdgpu_ring *ring;
>   	struct dma_fence *f;
> -	int r;
> +	int r, idx;
> +
> +	if (!drm_dev_enter(p->adev->ddev, &idx)) {
> +		r = -ENODEV;
> +		goto nodev;
> +	}
>   
>   	entity = p->immediate ? &p->vm->immediate : &p->vm->delayed;
>   	ring = container_of(entity->rq->sched, struct amdgpu_ring, sched);
> @@ -104,7 +110,7 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
>   	WARN_ON(ib->length_dw > p->num_dw_left);
>   	r = amdgpu_job_submit(p->job, entity, AMDGPU_FENCE_OWNER_VM, &f);
>   	if (r)
> -		goto error;
> +		goto job_fail;
>   
>   	if (p->unlocked) {
>   		struct dma_fence *tmp = dma_fence_get(f);
> @@ -118,10 +124,15 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
>   	if (fence && !p->immediate)
>   		swap(*fence, f);
>   	dma_fence_put(f);
> -	return 0;
>   
> -error:
> -	amdgpu_job_free(p->job);
> +	r = 0;
> +
> +job_fail:
> +	drm_dev_exit(idx);
> +nodev:
> +	if (r)
> +		amdgpu_job_free(p->job);
> +
>   	return r;
>   }
>