On Fri, Mar 18, 2022 at 02:27:33PM -0300, Jason Gunthorpe wrote:
> Connect the IOAS to its IOCTL interface. This exposes most of the
> functionality in the io_pagetable to userspace.
> 
> This is intended to be the core of the generic interface that IOMMUFD will
> provide. Every IOMMU driver should be able to implement an iommu_domain
> that is compatible with this generic mechanism.
> 
> It is also designed to be easy to use for simple non virtual machine
> monitor users, like DPDK:
>  - Universal simple support for all IOMMUs (no PPC special path)
>  - An IOVA allocator that considerds the aperture and the reserved ranges
>  - io_pagetable allows any number of iommu_domains to be connected to the
>    IOAS
> 
> Along with room in the design to add non-generic features to cater to
> specific HW functionality.


[snip]
> +/**
> + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC)
> + * @size: sizeof(struct iommu_ioas_alloc)
> + * @flags: Must be 0
> + * @out_ioas_id: Output IOAS ID for the allocated object
> + *
> + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA)
> + * to memory mapping.
> + */
> +struct iommu_ioas_alloc {
> +	__u32 size;
> +	__u32 flags;
> +	__u32 out_ioas_id;
> +};
> +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC)
> +
> +/**
> + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES)
> + * @size: sizeof(struct iommu_ioas_iova_ranges)
> + * @ioas_id: IOAS ID to read ranges from
> + * @out_num_iovas: Output total number of ranges in the IOAS
> + * @__reserved: Must be 0
> + * @out_valid_iovas: Array of valid IOVA ranges. The array length is the smaller
> + *                   of out_num_iovas or the length implied by size.
> + * @out_valid_iovas.start: First IOVA in the allowed range
> + * @out_valid_iovas.last: Inclusive last IOVA in the allowed range
> + *
> + * Query an IOAS for ranges of allowed IOVAs. Operation outside these ranges is
> + * not allowed. out_num_iovas will be set to the total number of iovas
> + * and the out_valid_iovas[] will be filled in as space permits.
> + * size should include the allocated flex array.
> + */
> +struct iommu_ioas_iova_ranges {
> +	__u32 size;
> +	__u32 ioas_id;
> +	__u32 out_num_iovas;
> +	__u32 __reserved;
> +	struct iommu_valid_iovas {
> +		__aligned_u64 start;
> +		__aligned_u64 last;
> +	} out_valid_iovas[];
> +};
> +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES)

Is the information returned by this valid for the lifeime of the IOAS,
or can it change?  If it can change, what events can change it?

If it *can't* change, then how do we have enough information to
determine this at ALLOC time, since we don't necessarily know which
(if any) hardware IOMMU will be attached to it.

> +/**
> + * enum iommufd_ioas_map_flags - Flags for map and copy
> + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate
> + *                             IOVA to place the mapping at
> + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping
> + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping
> + */
> +enum iommufd_ioas_map_flags {
> +	IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0,
> +	IOMMU_IOAS_MAP_WRITEABLE = 1 << 1,
> +	IOMMU_IOAS_MAP_READABLE = 1 << 2,
> +};
> +
> +/**
> + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP)
> + * @size: sizeof(struct iommu_ioas_map)
> + * @flags: Combination of enum iommufd_ioas_map_flags
> + * @ioas_id: IOAS ID to change the mapping of
> + * @__reserved: Must be 0
> + * @user_va: Userspace pointer to start mapping from
> + * @length: Number of bytes to map
> + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set
> + *        then this must be provided as input.
> + *
> + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the
> + * mapping will be established at iova, otherwise a suitable location will be
> + * automatically selected and returned in iova.
> + */
> +struct iommu_ioas_map {
> +	__u32 size;
> +	__u32 flags;
> +	__u32 ioas_id;
> +	__u32 __reserved;
> +	__aligned_u64 user_va;
> +	__aligned_u64 length;
> +	__aligned_u64 iova;
> +};
> +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP)
> +
> +/**
> + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY)
> + * @size: sizeof(struct iommu_ioas_copy)
> + * @flags: Combination of enum iommufd_ioas_map_flags
> + * @dst_ioas_id: IOAS ID to change the mapping of
> + * @src_ioas_id: IOAS ID to copy from
> + * @length: Number of bytes to copy and map
> + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is
> + *            set then this must be provided as input.
> + * @src_iova: IOVA to start the copy
> + *
> + * Copy an already existing mapping from src_ioas_id and establish it in
> + * dst_ioas_id. The src iova/length must exactly match a range used with
> + * IOMMU_IOAS_MAP.
> + */
> +struct iommu_ioas_copy {
> +	__u32 size;
> +	__u32 flags;
> +	__u32 dst_ioas_id;
> +	__u32 src_ioas_id;
> +	__aligned_u64 length;
> +	__aligned_u64 dst_iova;
> +	__aligned_u64 src_iova;
> +};
> +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY)

Since it can only copy a single mapping, what's the benefit of this
over just repeating an IOAS_MAP in the new IOAS?

> +/**
> + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP)
> + * @size: sizeof(struct iommu_ioas_copy)
> + * @ioas_id: IOAS ID to change the mapping of
> + * @iova: IOVA to start the unmapping at
> + * @length: Number of bytes to unmap
> + *
> + * Unmap an IOVA range. The iova/length must exactly match a range
> + * used with IOMMU_IOAS_PAGETABLE_MAP, or be the values 0 & U64_MAX.
> + * In the latter case all IOVAs will be unmaped.
> + */
> +struct iommu_ioas_unmap {
> +	__u32 size;
> +	__u32 ioas_id;
> +	__aligned_u64 iova;
> +	__aligned_u64 length;
> +};
> +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP)
>  #endif

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson