[PATCH v14 3/4] drm/amdgpu: Add mapping info option for GEM_OP ioctl

[Christian König]

On 13.08.25 20:49, David Francis wrote:
> Add new GEM_OP_IOCTL option GET_MAPPING_INFO, which
> returns a list of mappings associated with a given bo, along with
> their positions and offsets.
> 
> Signed-off-by: David Francis <David.Francis at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 87 +++++++++++++++++++++++++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h  |  5 ++
>  include/uapi/drm/amdgpu_drm.h           | 21 +++++-
>  3 files changed, 112 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index d17cc7ba66d4..f66f6e1f1c52 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -948,6 +948,89 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
>  	return r;
>  }
>  
> +/**
> + * amdgpu_gem_list_mappings - get information about a buffer's mappings
> + *
> + * @gobj: gem object
> + * @args: gem_op arguments
> + * @fpriv: drm file pointer
> + *
> + * num_entries is set as an input to the size of the user-allocated array of
> + * drm_amdgpu_gem_vm_entry stored at args->value.
> + * num_entries is sent back as output as the number of mappings the bo has.
> + * If that number is larger than the size of the array, the ioctl must
> + * be retried.
> + *
> + * Returns:
> + * 0 for success, -errno for errors.
> + */
> +static int amdgpu_gem_list_mappings(struct drm_gem_object *gobj, struct amdgpu_fpriv *fpriv,
> +					  struct drm_amdgpu_gem_op *args)
> +{
> +	struct amdgpu_vm *avm = &fpriv->vm;
> +	struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
> +	struct amdgpu_bo_va *bo_va = amdgpu_vm_bo_find(avm, bo);
> +	struct drm_amdgpu_gem_vm_entry *vm_entries;
> +	struct amdgpu_bo_va_mapping *mapping;
> +	struct drm_exec exec;
> +	int num_mappings = 0;
> +	int ret;
> +
> +	if (args->padding)
> +		return -EINVAL;
> +
> +	vm_entries = kvcalloc(args->num_entries, sizeof(*vm_entries), GFP_KERNEL);
> +	if (!vm_entries)
> +		return -ENOMEM;
> +
> +	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
> +			  DRM_EXEC_IGNORE_DUPLICATES, 0);
> +	drm_exec_until_all_locked(&exec) {
> +		if (gobj) {
> +			ret = drm_exec_lock_obj(&exec, gobj);
> +			drm_exec_retry_on_contention(&exec);
> +			if (ret)
> +				goto unlock_exec;
> +		}
> +
> +		ret = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 0);
> +		drm_exec_retry_on_contention(&exec);
> +		if (ret)
> +			goto unlock_exec;
> +	}
> +
> +	amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) {
> +		if (num_mappings < args->num_entries) {

> +			vm_entries[num_mappings].start = mapping->start;
> +			vm_entries[num_mappings].last = mapping->last;

Those two needs to be multiplied by AMDGPU_GPU_PAGE_SIZE.

> +			vm_entries[num_mappings].offset = mapping->offset;
> +			vm_entries[num_mappings].flags = mapping->flags;
> +		}
> +		num_mappings += 1;
> +	}
> +
> +	amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) {
> +		if (num_mappings < args->num_entries) {

> +			vm_entries[num_mappings].start = mapping->start;
> +			vm_entries[num_mappings].last = mapping->last;

Here as well.

> +			vm_entries[num_mappings].offset = mapping->offset;
> +			vm_entries[num_mappings].flags = mapping->flags;
> +		}
> +		num_mappings += 1;
> +	}
> +
> +	if (num_mappings > 0 && num_mappings <= args->num_entries)
> +		ret = copy_to_user(u64_to_user_ptr(args->value), vm_entries, num_mappings * sizeof(*vm_entries));
> +
> +	args->num_entries = num_mappings;
> +
> +unlock_exec:
> +	drm_exec_fini(&exec);
> +	kvfree(vm_entries);
> +
> +	return ret;
> +}
> +
>  int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
>  			struct drm_file *filp)
>  {
> @@ -1014,6 +1097,10 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
>  
>  		amdgpu_bo_unreserve(robj);
>  		break;
> +	case AMDGPU_GEM_OP_GET_MAPPING_INFO:
> +		amdgpu_bo_unreserve(robj);

Yeah that is not really 100% clean.

It would be better if we use drm_exec() in the amdgpu_gem_op_ioctl().

> +		r = amdgpu_gem_list_mappings(gobj, filp->driver_priv, args);
> +		break;
>  	default:
>  		amdgpu_bo_unreserve(robj);
>  		r = -EINVAL;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> index f9549f6b3d1f..5a63ae490b0e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> @@ -668,4 +668,9 @@ void amdgpu_vm_tlb_fence_create(struct amdgpu_device *adev,
>  				 struct amdgpu_vm *vm,
>  				 struct dma_fence **fence);
>  
> +#define amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) \
> +		list_for_each_entry(mapping, &bo_va->valids, list)
> +#define amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) \
> +		list_for_each_entry(mapping, &bo_va->invalids, list)
> +
>  #endif
> diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
> index 59b423883e91..bc1e18c06ce4 100644
> --- a/include/uapi/drm/amdgpu_drm.h
> +++ b/include/uapi/drm/amdgpu_drm.h
> @@ -802,6 +802,21 @@ union drm_amdgpu_wait_fences {
>  
>  #define AMDGPU_GEM_OP_GET_GEM_CREATE_INFO	0
>  #define AMDGPU_GEM_OP_SET_PLACEMENT		1
> +#define AMDGPU_GEM_OP_GET_MAPPING_INFO		2
> +
> +struct drm_amdgpu_gem_vm_entry {
> +	/* Start of mapping (in number of pages) */
> +	__u64 start;
> +
> +	/* End of mapping (in number of pages) */
> +	__u64 last;

Size please, not the end. To match the UAPI to create mappings.



> +
> +	/* Mapping offset */
> +	__u64 offset;
> +
> +	/* flags needed to recreate mapping */
> +	__u64 flags;
> +};
>  
>  /* Sets or returns a value associated with a buffer. */
>  struct drm_amdgpu_gem_op {
> @@ -809,8 +824,12 @@ struct drm_amdgpu_gem_op {
>  	__u32	handle;
>  	/** AMDGPU_GEM_OP_* */
>  	__u32	op;
> -	/** Input or return value */
> +	/** Input or return value. For MAPPING_INFO op: pointer to array of struct drm_amdgpu_gem_vm_entry */
>  	__u64	value;
> +	/** For MAPPING_INFO op: number of mappings (in/out) */
> +	__u32	num_entries;
> +
> +	__u32	padding;
>  };
>  
>  #define AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT	(1 << 0)