Re: [RFC PATCH] iommu/xen: Add Xen PV-IOMMU driver

[Jan Beulich <jbeulich@xxxxxxxx>]

On 13.06.2024 15:50, Teddy Astie wrote:
> @@ -214,6 +215,38 @@ struct xen_add_to_physmap_range {
>  };
>  DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap_range);
>  
> +/*
> + * With some legacy devices, certain guest-physical addresses cannot safely
> + * be used for other purposes, e.g. to map guest RAM.  This hypercall
> + * enumerates those regions so the toolstack can avoid using them.
> + */
> +#define XENMEM_reserved_device_memory_map   27
> +struct xen_reserved_device_memory {
> +    xen_pfn_t start_pfn;
> +    xen_ulong_t nr_pages;
> +};
> +DEFINE_GUEST_HANDLE_STRUCT(xen_reserved_device_memory);
> +
> +struct xen_reserved_device_memory_map {
> +#define XENMEM_RDM_ALL 1 /* Request all regions (ignore dev union). */
> +    /* IN */
> +    uint32_t flags;
> +    /*
> +     * IN/OUT
> +     *
> +     * Gets set to the required number of entries when too low,
> +     * signaled by error code -ERANGE.
> +     */
> +    unsigned int nr_entries;
> +    /* OUT */
> +    GUEST_HANDLE(xen_reserved_device_memory) buffer;
> +    /* IN */
> +    union {
> +        struct physdev_pci_device pci;
> +    } dev;
> +};
> +DEFINE_GUEST_HANDLE_STRUCT(xen_reserved_device_memory_map);

This is a tools-only (i.e. unstable) sub-function in Xen; even the comment
at the top says "toolstack". It is therefore not suitable for use in a
kernel.

> --- /dev/null
> +++ b/include/xen/interface/pv-iommu.h
> @@ -0,0 +1,114 @@
> +/* SPDX-License-Identifier: MIT */
> +/******************************************************************************
> + * pv-iommu.h
> + *
> + * Paravirtualized IOMMU driver interface.
> + *
> + * Copyright (c) 2024 Teddy Astie <teddy.astie@xxxxxxxxxx>
> + */
> +
> +#ifndef __XEN_PUBLIC_PV_IOMMU_H__
> +#define __XEN_PUBLIC_PV_IOMMU_H__
> +
> +#include "xen.h"
> +#include "physdev.h"
> +
> +#define IOMMU_DEFAULT_CONTEXT (0)
> +
> +/**
> + * Query PV-IOMMU capabilities for this domain.
> + */
> +#define IOMMUOP_query_capabilities    1
> +
> +/**
> + * Allocate an IOMMU context, the new context handle will be written to 
> ctx_no.
> + */
> +#define IOMMUOP_alloc_context         2
> +
> +/**
> + * Destroy a IOMMU context.
> + * All devices attached to this context are reattached to default context.
> + *
> + * The default context can't be destroyed (0).
> + */
> +#define IOMMUOP_free_context          3
> +
> +/**
> + * Reattach the device to IOMMU context.
> + */
> +#define IOMMUOP_reattach_device       4
> +
> +#define IOMMUOP_map_pages             5
> +#define IOMMUOP_unmap_pages           6
> +
> +/**
> + * Get the GFN associated to a specific DFN.
> + */
> +#define IOMMUOP_lookup_page           7
> +
> +struct pv_iommu_op {
> +    uint16_t subop_id;
> +    uint16_t ctx_no;
> +
> +/**
> + * Create a context that is cloned from default.
> + * The new context will be populated with 1:1 mappings covering the entire 
> guest memory.
> + */
> +#define IOMMU_CREATE_clone (1 << 0)
> +
> +#define IOMMU_OP_readable (1 << 0)
> +#define IOMMU_OP_writeable (1 << 1)
> +    uint32_t flags;
> +
> +    union {
> +        struct {
> +            uint64_t gfn;
> +            uint64_t dfn;
> +            /* Number of pages to map */
> +            uint32_t nr_pages;
> +            /* Number of pages actually mapped after sub-op */
> +            uint32_t mapped;
> +        } map_pages;
> +
> +        struct {
> +            uint64_t dfn;
> +            /* Number of pages to unmap */
> +            uint32_t nr_pages;
> +            /* Number of pages actually unmapped after sub-op */
> +            uint32_t unmapped;
> +        } unmap_pages;
> +
> +        struct {
> +            struct physdev_pci_device dev;
> +        } reattach_device;
> +
> +        struct {
> +            uint64_t gfn;
> +            uint64_t dfn;
> +        } lookup_page;
> +
> +        struct {
> +            /* Maximum number of IOMMU context this domain can use. */
> +            uint16_t max_ctx_no;
> +            /* Maximum number of pages that can be modified in a single 
> map/unmap operation. */
> +            uint32_t max_nr_pages;
> +            /* Maximum device address (iova) that the guest can use for 
> mappings. */
> +            uint64_t max_iova_addr;
> +        } cap;
> +    };
> +};
> +
> +typedef struct pv_iommu_op pv_iommu_op_t;
> +DEFINE_GUEST_HANDLE_STRUCT(pv_iommu_op_t);
> +
> +#endif
> +
> +/*
> + * Local variables:
> + * mode: C
> + * c-file-style: "BSD"
> + * c-basic-offset: 4
> + * tab-width: 4
> + * indent-tabs-mode: nil
> + * End:
> + */
> \ No newline at end of file

Nit: I'm pretty sure you want to avoid this.

Jan