On Wed, 27 May 2026 03:23:05 -0700
Matt Evans <[email protected]> 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 <[email protected]>
> ---
>  drivers/vfio/pci/vfio_pci_dmabuf.c | 142 ++++++++++++++++++++++++++---
>  drivers/vfio/pci/vfio_pci_priv.h   |  20 ++++
>  2 files changed, 149 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c 
> b/drivers/vfio/pci/vfio_pci_dmabuf.c
> index c16f460c01d6..0d132c4ca95f 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 +93,135 @@ 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,

This private dmabuf object pointer is named priv pretty consistently
throughout the rest of the file.

> +                           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.)
> +      *
> +      * Finally, vma_pgoff_adjust is used for a DMABUF representing
> +      * a VFIO BAR mmap, which is created from the start of the
> +      * offset region.  It should be zero, or equal vm_pgoff.
> +      */
> +
> +     const unsigned long pagesize = PAGE_SIZE << order;
> +     unsigned long vma_off = ((vma->vm_pgoff - vpdmabuf->vma_pgoff_adjust) <<
> +                              PAGE_SHIFT) & VFIO_PCI_OFFSET_MASK;
> +     unsigned long rounded_page_addr = ALIGN_DOWN(address, pagesize);
> +     unsigned long rounded_page_end = rounded_page_addr + pagesize;
> +     unsigned long page_buf_offset;
> +     unsigned long range_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 (vpdmabuf->vma_pgoff_adjust != 0 &&
> +         vpdmabuf->vma_pgoff_adjust != (vma->vm_pgoff &
> +                                        (VFIO_PCI_OFFSET_MASK >> 
> PAGE_SHIFT))) {
> +             WARN(1, "Unexpected vma_pgoff_adjust 0x%lx (vm_pgoff 0x%lx)\n",
> +                  vpdmabuf->vma_pgoff_adjust, vma->vm_pgoff);
> +             return -EFAULT;
> +     }

This appears to be user trigger'able, by causing a vma to be split, and
also unnecessary as it seems the math works out correctly for the split
case.

> +
> +     if (unlikely(check_add_overflow(rounded_page_addr - vma->vm_start,
> +                                     vma_off, &page_buf_offset)))
> +             return -EFAULT;
> +
> +     for (i = 0; i < vpdmabuf->nr_ranges; i++) {
> +             unsigned long page_buf_offset_end;
> +             size_t range_len = vpdmabuf->phys_vec[i].len;
> +             phys_addr_t range_start = vpdmabuf->phys_vec[i].paddr;
> +
> +             if (unlikely(check_add_overflow(page_buf_offset, pagesize,
> +                                             &page_buf_offset_end)))
> +                     return -EFAULT;

Why is this inside the loop, the args are invariant of anything
modified in the loop.  Thanks,

Alex

> +             /*
> +              * If the current range starts after the page's span,
> +              * this and any future range won't match.  Bail early.
> +              */
> +             if (page_buf_offset_end <= range_buf_offset)
> +                     break;
> +
> +             if (page_buf_offset >= range_buf_offset &&
> +                 page_buf_offset_end <= range_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_buf_offset -
> +                                          range_buf_offset) / PAGE_SIZE;
> +
> +                     if (IS_ALIGNED(pfn, 1 << order)) {
> +                             *out_pfn = pfn;
> +                             return 0;
> +                     }
> +                     /* Retry with smaller order */
> +                     return -EAGAIN;
> +             }
> +             range_buf_offset += range_len;
> +     }
> +
> +     /*
> +      * A hugepage straddling a range boundary will fail to match a
> +      * range, but the address will (eventually) match when retried
> +      * with a smaller page.
> +      */
> +     if (order > 0)
> +             return -EAGAIN;
> +
> +     /*
> +      * If we get here, the address fell outside of the span
> +      * represented by the (concatenated) ranges.  Setup of a
> +      * mapping must ensure that the VMA is <= the total size of
> +      * the ranges, so this should never happen.  But, if it does,
> +      * force SIGBUS for the access and warn.
> +      */
> +     WARN_ONCE(1, "No range for addr 0x%lx, order %d: VMA 0x%lx-0x%lx pgoff 
> 0x%lx, %u ranges, size 0x%zx\n",
> +               address, order, vma->vm_start, vma->vm_end, vma->vm_pgoff,
> +               vpdmabuf->nr_ranges, vpdmabuf->size);
> +
> +     return -EFAULT;
> +}
> +
>  /*
>   * This is a temporary "private interconnect" between VFIO DMABUF and 
> iommufd.
>   * It allows the two co-operating drivers to exchange the physical address of
> diff --git a/drivers/vfio/pci/vfio_pci_priv.h 
> b/drivers/vfio/pci/vfio_pci_priv.h
> index fca9d0dfac90..c8f6f959056a 100644
> --- a/drivers/vfio/pci/vfio_pci_priv.h
> +++ b/drivers/vfio/pci/vfio_pci_priv.h
> @@ -23,6 +23,20 @@ struct vfio_pci_ioeventfd {
>       bool                    test_mem;
>  };
>  
> +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;
> +     unsigned long vma_pgoff_adjust;
> +     u8 revoked : 1;
> +};
> +
>  bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
>  void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev);
>  
> @@ -114,6 +128,12 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
>       return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
>  }
>  
> +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);
> +
>  #ifdef CONFIG_VFIO_PCI_DMABUF
>  int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 
> flags,
>                                 struct vfio_device_feature_dma_buf __user 
> *arg,

Reply via email to