Re: [Qemu-devel] [RFC PATCH 03/10] vfio: Check guest IOVA ranges against host IOMMU capabilities

[David Gibson <david@gibson.dropbear.id.au>]

[-- Attachment #1: Type: text/plain, Size: 5924 bytes --]

On Wed, Sep 23, 2015 at 09:07:06PM +1000, David Gibson wrote:
> On Wed, Sep 23, 2015 at 12:10:46PM +0200, Thomas Huth wrote:
> > On 17/09/15 15:09, David Gibson wrote:
> > > The current vfio core code assumes that the host IOMMU is capable of
> > > mapping any IOVA the guest wants to use to where we need.  However, real
> > > IOMMUs generally only support translating a certain range of IOVAs (the
> > > "DMA window") not a full 64-bit address space.
> > > 
> > > The common x86 IOMMUs support a wide enough range that guests are very
> > > unlikely to go beyond it in practice, however the IOMMU used on IBM Power
> > > machines - in the default configuration - supports only a much more limited
> > > IOVA range, usually 0..2GiB.
> > > 
> > > If the guest attempts to set up an IOVA range that the host IOMMU can't
> > > map, qemu won't report an error until it actually attempts to map a bad
> > > IOVA.  If guest RAM is being mapped directly into the IOMMU (i.e. no guest
> > > visible IOMMU) then this will show up very quickly.  If there is a guest
> > > visible IOMMU, however, the problem might not show up until much later when
> > > the guest actually attempt to DMA with an IOVA the host can't handle.
> > > 
> > > This patch adds a test so that we will detect earlier if the guest is
> > > attempting to use IOVA ranges that the host IOMMU won't be able to deal
> > > with.
> > > 
> > > For now, we assume that "Type1" (x86) IOMMUs can support any IOVA, this is
> > > incorrect, but no worse than what we have already.  We can't do better for
> > > now because the Type1 kernel interface doesn't tell us what IOVA range the
> > > IOMMU actually supports.
> > > 
> > > For the Power "sPAPR TCE" IOMMU, however, we can retrieve the supported
> > > IOVA range and validate guest IOVA ranges against it, and this patch does
> > > so.
> > > 
> > > Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
> > > ---
> > >  hw/vfio/common.c              | 42 +++++++++++++++++++++++++++++++++++++++---
> > >  include/hw/vfio/vfio-common.h |  6 ++++++
> > >  2 files changed, 45 insertions(+), 3 deletions(-)
> > > 
> > > diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> > > index 9953b9c..c37f1a1 100644
> > > --- a/hw/vfio/common.c
> > > +++ b/hw/vfio/common.c
> > > @@ -344,14 +344,23 @@ static void vfio_listener_region_add(MemoryListener *listener,
> > >      if (int128_ge(int128_make64(iova), llend)) {
> > >          return;
> > >      }
> > > +    end = int128_get64(llend);
> > > +
> > > +    if ((iova < container->iommu_data.min_iova)
> > > +        || ((end - 1) > container->iommu_data.max_iova)) {
> > 
> > (Too much paranthesis for my taste ;-))
> 
> Yes, well, we've already established our tastes differ on that point.
> 
> > > +        error_report("vfio: IOMMU container %p can't map guest IOVA region"
> > > +                     " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx,
> > > +                     container, iova, end - 1);
> > > +        ret = -EFAULT; /* FIXME: better choice here? */
> > 
> > Maybe -EINVAL? ... but -EFAULT also sounds ok for me.
> 
> I try to avoid EINVAL unless it's clearly the only right choice.  So
> many things use it that it tends to be very unhelpful when you get one.
> 
> > > +        goto fail;
> > > +    }
> > ...
> > > @@ -712,6 +732,22 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
> > >              ret = -errno;
> > >              goto free_container_exit;
> > >          }
> > > +
> > > +        /*
> > > +         * FIXME: This only considers the host IOMMU' 32-bit window.
> > > +         * At some point we need to add support for the optional
> > > +         * 64-bit window and dynamic windows
> > > +         */
> > > +        info.argsz = sizeof(info);
> > > +        ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
> > > +        if (ret) {
> > > +            error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m");
> > 
> > Isn't that %m a glibc extension only? ... Well, this code likely only
> > runs on Linux with a glibc, so it likely doesn't matter, I guess...
> 
> Yes, it is, but it's already used extensively within qemu.
> 
> > > +            ret = -errno;
> > > +            goto free_container_exit;
> > > +        }
> > > +        container->iommu_data.min_iova = info.dma32_window_start;
> > > +        container->iommu_data.max_iova = container->iommu_data.min_iova
> > > +            + info.dma32_window_size - 1;
> > >      } else {
> > >          error_report("vfio: No available IOMMU models");
> > >          ret = -EINVAL;
> > > diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> > > index aff18cd..88ec213 100644
> > > --- a/include/hw/vfio/vfio-common.h
> > > +++ b/include/hw/vfio/vfio-common.h
> > > @@ -71,6 +71,12 @@ typedef struct VFIOContainer {
> > >          MemoryListener listener;
> > >          int error;
> > >          bool initialized;
> > > +        /*
> > > +         * FIXME: This assumes the host IOMMU can support only a
> > > +         * single contiguous IOVA window.  We may need to generalize
> > > +         * that in future
> > > +         */
> > > +        hwaddr min_iova, max_iova;
> > 
> > Should that maybe be dma_addr_t instead of hwaddr ?
> 
> Ah, yes it probably should.

Actually, on further consideration, no it shouldn't.  hwaddr is what's
used throughout the VFIO code, in address_space_translate() and in
IOMMUTLBEntry, for both sides of the translation.  In fact, I'm not
entirely convinced there's any reason to have dma_addr_t distinct from
hwaddr at all, but that's a cleanup for some other day.

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: Type: application/pgp-signature, Size: 819 bytes --]