On Thu, Oct 29, 2015 at 01:59:45PM +0000, Eric Auger wrote:
> Current vfio_pgsize_bitmap code hides the supported IOMMU page
> sizes smaller than PAGE_SIZE. As a result, in case the IOMMU
> does not support PAGE_SIZE page, the alignment check on map/unmap
> is done with larger page sizes, if any. This can fail although
> mapping could be done with pages smaller than PAGE_SIZE.
>
> This patch modifies vfio_pgsize_bitmap implementation so that,
> in case the IOMMU supports page sizes smaller than PAGE_HOST
> we pretend PAGE_HOST is supported and hide sub-PAGE_HOST sizes.
> That way the user will be able to map/unmap buffers whose size/
> start address is aligned with PAGE_HOST. Pinning code uses that
> granularity while iommu driver can use the sub-PAGE_HOST size
> to map the buffer.
>
> Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
> Signed-off-by: Alex Williamson <alex.williamson@xxxxxxxxxx>
>
> ---
>
> This was tested on AMD Seattle with 64kB page host. ARM MMU 401
> currently expose 4kB, 2MB and 1GB page support. With a 64kB page host,
> the map/unmap check is done against 2MB. Some alignment check fail
> so VFIO_IOMMU_MAP_DMA fail while we could map using 4kB IOMMU page
> size.
>
> RFC -> PATCH v1:
> - move all modifications in vfio_pgsize_bitmap following Alex'
> suggestion to expose a fake PAGE_HOST support
> - restore WARN_ON's
> ---
> drivers/vfio/vfio_iommu_type1.c | 15 ++++++++++++++-
> 1 file changed, 14 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 57d8c37..cee504a 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -403,13 +403,26 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
> static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
> {
> struct vfio_domain *domain;
> - unsigned long bitmap = PAGE_MASK;
> + unsigned long bitmap = ULONG_MAX;
>
> mutex_lock(&iommu->lock);
> list_for_each_entry(domain, &iommu->domain_list, next)
> bitmap &= domain->domain->ops->pgsize_bitmap;
> mutex_unlock(&iommu->lock);
>
> + /*
> + * In case the IOMMU supports page sizes smaller than PAGE_HOST
> + * we pretend PAGE_HOST is supported and hide sub-PAGE_HOST sizes.
> + * That way the user will be able to map/unmap buffers whose size/
> + * start address is aligned with PAGE_HOST. Pinning code uses that
> + * granularity while iommu driver can use the sub-PAGE_HOST size
> + * to map the buffer.
> + */
> + if (bitmap & ~PAGE_MASK) {
> + bitmap &= PAGE_MASK;
> + bitmap |= PAGE_SIZE;
> + }
> +
s/PAGE_HOST/PAGE_SIZE/g (in the cover-letter too) and then I think this
looks good:
Acked-by: Will Deacon <will.deacon@xxxxxxx>
Will
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
