Re: [PATCH v2 05/31] x86/virt/tdx: Extend tdx_page_array to support IOMMU_MT

["Edgecombe, Rick P" <rick.p.edgecombe@intel.com>]

On Sat, 2026-03-28 at 00:01 +0800, Xu Yilun wrote:
> IOMMU_MT is another TDX Module defined structure similar to HPA_ARRAY_T
> and HPA_LIST_INFO. The difference is it requires multi-order contiguous
> pages for some entries. It adds an additional NUM_PAGES field for every
> multi-order page entry.
> 
> Add a dedicated allocation helper for IOMMU_MT. Fortunately put_page()
> works well for both single pages and multi-order folios, simplifying the
> cleanup logic for all allocation methods.
> 
> Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
> ---
>  arch/x86/include/asm/tdx.h  |  2 +
>  arch/x86/virt/vmx/tdx/tdx.c | 90 +++++++++++++++++++++++++++++++++++--
>  2 files changed, 89 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
> index 9173a432b312..d5f1d7b7d1e7 100644
> --- a/arch/x86/include/asm/tdx.h
> +++ b/arch/x86/include/asm/tdx.h
> @@ -175,6 +175,8 @@ void tdx_page_array_ctrl_leak(struct tdx_page_array *array);
>  int tdx_page_array_ctrl_release(struct tdx_page_array *array,
>  				unsigned int nr_released,
>  				u64 released_hpa);
> +struct tdx_page_array *
> +tdx_page_array_create_iommu_mt(unsigned int iq_order, unsigned int nr_mt_pages);
>  
>  struct tdx_td {
>  	/* TD root structure: */
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index 6c4ed80e8e5a..2b17e0f73dac 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -275,8 +275,15 @@ static int tdx_page_array_populate(struct tdx_page_array *array,
>  			    TDX_PAGE_ARRAY_MAX_NENTS);
>  
>  	entries = array->root;
> -	for (i = 0; i < array->nents; i++)
> -		entries[i] = page_to_phys(array->pages[offset + i]);
> +	for (i = 0; i < array->nents; i++) {
> +		struct page *page = array->pages[offset + i];
> +
> +		entries[i] = page_to_phys(page);
> +
> +		/* Now only for iommu_mt */
> +		if (compound_nr(page) > 1)
> +			entries[i] |= compound_nr(page);
> +	}
>  
>  	return array->nents;
>  }
> @@ -286,7 +293,7 @@ static void tdx_free_pages_bulk(unsigned int nr_pages, struct page **pages)
>  	int i;
>  
>  	for (i = 0; i < nr_pages; i++)
> -		__free_page(pages[i]);
> +		put_page(pages[i]);
>  }
>  
>  static int tdx_alloc_pages_bulk(unsigned int nr_pages, struct page **pages,
> @@ -463,6 +470,10 @@ static bool tdx_page_array_validate_release(struct tdx_page_array *array,
>  			struct page *page = array->pages[offset + i];
>  			u64 val = page_to_phys(page);
>  
> +			/* Now only for iommu_mt */
> +			if (compound_nr(page) > 1)
> +				val |= compound_nr(page);
> +
>  			if (val != entries[i]) {
>  				pr_err("%s entry[%d] [0x%llx] doesn't match page hpa [0x%llx]\n",
>  				       __func__, i, entries[i], val);
> @@ -555,6 +566,79 @@ tdx_page_array_alloc_contig(unsigned int nr_pages)
>  	return tdx_page_array_alloc(nr_pages, tdx_alloc_pages_contig, NULL);
>  }
>  
> +static int tdx_alloc_pages_iommu_mt(unsigned int nr_pages, struct page **pages,
> +				    void *data)
> +{
> +	unsigned int iq_order = (unsigned int)(long)data;
> +	struct folio *t_iq, *t_ctxiq;
> +	int ret;
> +
> +	/* TODO: folio_alloc_node() is preferred, but need numa info */
> +	t_iq = folio_alloc(GFP_KERNEL | __GFP_ZERO, iq_order);
> +	if (!t_iq)
> +		return -ENOMEM;
> +
> +	t_ctxiq = folio_alloc(GFP_KERNEL | __GFP_ZERO, iq_order);
> +	if (!t_ctxiq) {
> +		ret = -ENOMEM;
> +		goto out_t_iq;
> +	}
> +
> +	ret = tdx_alloc_pages_bulk(nr_pages - 2, pages + 2, NULL);
> +	if (ret)
> +		goto out_t_ctxiq;
> +
> +	pages[0] = folio_page(t_iq, 0);
> +	pages[1] = folio_page(t_ctxiq, 0);

To me it seems like this can't really be called a page array any more. The first
two u64's are too special. Instead it's a special one-off ABI format passed via
a page.

BTW, I can't find TDH.IOMMU.SETUP in the docs. Any pointers?

> +
> +	return 0;
> +
> +out_t_ctxiq:
> +	folio_put(t_ctxiq);
> +out_t_iq:
> +	folio_put(t_iq);
> +
> +	return ret;
> +}
> +
> +/**
> + * tdx_page_array_create_iommu_mt() - Create a page array for IOMMU Memory Tables
> + * @iq_order: The allocation order for the IOMMU Invalidation Queue.
> + * @nr_mt_pages: Number of additional order-0 pages for the MT.
> + *
> + * Allocate and populate a specialized tdx_page_array for IOMMU_MT structures.
> + * The resulting array consists of two multi-order folios (at index 0 and 1)
> + * followed by the requested number of order-0 pages.
> + *
> + * Return: Fully populated tdx_page_array or NULL on failure.
> + */
> +struct tdx_page_array *
> +tdx_page_array_create_iommu_mt(unsigned int iq_order, unsigned int nr_mt_pages)
> +{
> +	unsigned int nr_pages = nr_mt_pages + 2;

Consider the amount of tricks that are needed to coax the tdx_page_array to
populate the handoff page as needed. It adds 2 pages here, then subtracts them
later in the callback. Then tweaks the pa in tdx_page_array_populate() to add
the length...

> +	struct tdx_page_array *array;
> +	int populated;
> +
> +	if (nr_pages > TDX_PAGE_ARRAY_MAX_NENTS)
> +		return NULL;
> +
> +	array = tdx_page_array_alloc(nr_pages, tdx_alloc_pages_iommu_mt,
> +				     (void *)(long)iq_order);
> +	if (!array)
> +		return NULL;
> +
> +	populated = tdx_page_array_populate(array, 0);
> +	if (populated != nr_pages)
> +		goto out_free;
> +
> +	return array;
> +
> +out_free:
> +	tdx_page_array_free(array);
> +	return NULL;
> +}
> +EXPORT_SYMBOL_GPL(tdx_page_array_create_iommu_mt);
> +
>  #define HPA_LIST_INFO_FIRST_ENTRY	GENMASK_U64(11, 3)
>  #define HPA_LIST_INFO_PFN		GENMASK_U64(51, 12)
>  #define HPA_LIST_INFO_LAST_ENTRY	GENMASK_U64(63, 55)