Re: [PATCH 2/9] vfio/pci: Add a helper to look up PFNs for DMABUFs

[Jason Gunthorpe <jgg@nvidia.com>]

On Thu, Apr 16, 2026 at 06:17:45AM -0700, Matt Evans wrote:
> Add vfio_pci_dma_buf_find_pfn(), which a VMA fault handler can use to
> find a PFN.
> 
> This supports multi-range DMABUFs, which typically would be used to
> represent scattered spans but might even represent overlapping or
> aliasing spans of PFNs.
> 
> Because this is intended to be used in vfio_pci_core.c, we also need
> to expose the struct vfio_pci_dma_buf in the vfio_pci_priv.h header.
> 
> Signed-off-by: Matt Evans <mattev@meta.com>
> ---
>  drivers/vfio/pci/vfio_pci_dmabuf.c | 124 ++++++++++++++++++++++++++---
>  drivers/vfio/pci/vfio_pci_priv.h   |  19 +++++
>  2 files changed, 130 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
> index 04478b7415a0..8b6bae56bbf2 100644
> --- a/drivers/vfio/pci/vfio_pci_dmabuf.c
> +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
> @@ -9,19 +9,6 @@
>  
>  MODULE_IMPORT_NS("DMA_BUF");
>  
> -struct vfio_pci_dma_buf {
> -	struct dma_buf *dmabuf;
> -	struct vfio_pci_core_device *vdev;
> -	struct list_head dmabufs_elm;
> -	size_t size;
> -	struct phys_vec *phys_vec;
> -	struct p2pdma_provider *provider;
> -	u32 nr_ranges;
> -	struct kref kref;
> -	struct completion comp;
> -	u8 revoked : 1;
> -};
> -
>  static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
>  				   struct dma_buf_attachment *attachment)
>  {
> @@ -106,6 +93,117 @@ static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
>  	.release = vfio_pci_dma_buf_release,
>  };
>  
> +int vfio_pci_dma_buf_find_pfn(struct vfio_pci_dma_buf *vpdmabuf,
> +			      struct vm_area_struct *vma,
> +			      unsigned long address,
> +			      unsigned int order,
> +			      unsigned long *out_pfn)
> +{
> +	/*
> +	 * Given a VMA (start, end, pgoffs) and a fault address,
> +	 * search the corresponding DMABUF's phys_vec[] to find the
> +	 * range representing the address's offset into the VMA, and
> +	 * its PFN.
> +	 *
> +	 * The phys_vec[] ranges represent contiguous spans of VAs
> +	 * upwards from the buffer offset 0; the actual PFNs might be
> +	 * in any order, overlap/alias, etc.  Calculate an offset of
> +	 * the desired page given VMA start/pgoff and address, then
> +	 * search upwards from 0 to find which span contains it.
> +	 *
> +	 * On success, a valid PFN for a page sized by 'order' is
> +	 * returned into out_pfn.
> +	 *
> +	 * Failure occurs if:
> +	 * - The page would cross the edge of the VMA
> +	 * - The page isn't entirely contained within a range
> +	 * - We find a range, but the final PFN isn't aligned to the
> +	 *   requested order.
> +	 *
> +	 * (Upon failure, the caller is expected to try again with a
> +	 * smaller order; the tests above will always succeed for
> +	 * order=0 as the limit case.)
> +	 *
> +	 * It's suboptimal if DMABUFs are created with neigbouring
> +	 * ranges that are physically contiguous, since hugepages
> +	 * can't straddle range boundaries.  (The construction of the
> +	 * ranges vector should merge such ranges.)
> +	 */
> +
> +	const unsigned long pagesize = PAGE_SIZE << order;
> +	unsigned long rounded_page_addr = address & ~(pagesize - 1);

ALIGN_DOWN(address, pagesize);

> +	unsigned long rounded_page_end = rounded_page_addr + pagesize;
> +	unsigned long buf_page_offset;
> +	unsigned long buf_offset = 0;
> +	unsigned int i;
> +
> +	if (rounded_page_addr < vma->vm_start || rounded_page_end > vma->vm_end) {
> +		if (order > 0)
> +			return -EAGAIN;
> +
> +		/* A fault address outside of the VMA is absurd. */
> +		WARN(1, "Fault addr 0x%lx outside VMA 0x%lx-0x%lx\n",
> +		     address, vma->vm_start, vma->vm_end);
> +		return -EFAULT;
> +	}
> +
> +	if (unlikely(check_add_overflow(rounded_page_addr - vma->vm_start,
> +					vma->vm_pgoff << PAGE_SHIFT, &buf_page_offset)))
> +		return -EFAULT;

> +
> +	for (i = 0; i < vpdmabuf->nr_ranges; i++) {
> +		size_t range_len = vpdmabuf->phys_vec[i].len;
> +		phys_addr_t range_start = vpdmabuf->phys_vec[i].paddr;
> +
> +		/*
> +		 * If the current range starts after the page's span,
> +		 * this and any future range won't match.  Bail early.
> +		 */
> +		if (buf_page_offset + pagesize <= buf_offset)
> +			break;

No overflow check on this +? If we are worried order is so large that
the first needs a check then this would too..

> +
> +		if (buf_page_offset >= buf_offset &&
> +		    buf_page_offset + pagesize <= buf_offset + range_len) {

> +			/*
> +			 * The faulting page is wholly contained
> +			 * within the span represented by the range.
> +			 * Validate PFN alignment for the order:
> +			 */
> +			unsigned long pfn = (range_start >> PAGE_SHIFT) +
> +				((buf_page_offset - buf_offset) >> PAGE_SHIFT);

(range_start + (buf_page_offset - buf_offset)) / PAGE_SIZE;

?

Jason