Re: [PATCH v2] KVM: IOMMU: hva align mapping page size

[Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]

On Mon, Nov 04, 2013 at 09:08:12AM -0700, Greg Edwards wrote:
> When determining the page size we could use to map with the IOMMU, the
> page size should also be aligned with the hva, not just the gfn.  The
> gfn may not reflect the real alignment within the hugetlbfs file.
> 
> Signed-off-by: Greg Edwards <gedwards-LfVdkaOWEx8@public.gmane.org>
> Cc: stable-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> ---
>  virt/kvm/iommu.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
> index 72a130b..c329c8f 100644
> --- a/virt/kvm/iommu.c
> +++ b/virt/kvm/iommu.c
> @@ -103,6 +103,10 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
>  		while ((gfn << PAGE_SHIFT) & (page_size - 1))
>  			page_size >>= 1;
>  
> +		/* Make sure hva is aligned to the page size we want to map */
> +		while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
> +			page_size >>= 1;
> +
>  		/*
>  		 * Pin all pages we are about to map in memory. This is
>  		 * important because we unmap and unpin in 4kb steps later.
> -- 
> 1.8.3.2

Reviewed-by: Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>