Re: i915 dma faults on Xen

["Roger Pau Monné" <roger.pau@citrix.com>]

On Wed, Oct 14, 2020 at 08:37:06PM +0100, Andrew Cooper wrote:
> On 14/10/2020 20:28, Jason Andryuk wrote:
> > Hi,
> >
> > Bug opened at https://gitlab.freedesktop.org/drm/intel/-/issues/2576
> >
> > I'm seeing DMA faults for the i915 graphics hardware on a Dell
> > Latitude 5500. These were captured when I plugged into a Dell
> > Thunderbolt dock with two DisplayPort monitors attached.  Xen 4.12.4
> > staging and Linux 5.4.70 (and some earlier versions).
> >
> > Oct 14 18:41:49.056490 kernel:[   85.570347] [drm:gen8_de_irq_handler
> > [i915]] *ERROR* Fault errors on pipe A: 0x00000080
> > Oct 14 18:41:49.056494 kernel:[   85.570395] [drm:gen8_de_irq_handler
> > [i915]] *ERROR* Fault errors on pipe A: 0x00000080
> > Oct 14 18:41:49.056589 VM hypervisor: (XEN) [VT-D]DMAR:[DMA Read]
> > Request device [0000:00:02.0] fault addr 39b5845000, iommu reg =
> > ffff82c00021d000
> > Oct 14 18:41:49.056594 VM hypervisor: (XEN) [VT-D]DMAR: reason 06 -
> > PTE Read access is not set
> > Oct 14 18:41:49.056784 kernel:[   85.570668] [drm:gen8_de_irq_handler
> > [i915]] *ERROR* Fault errors on pipe A: 0x00000080
> > Oct 14 18:41:49.056789 kernel:[   85.570687] [drm:gen8_de_irq_handler
> > [i915]] *ERROR* Fault errors on pipe A: 0x00000080
> > Oct 14 18:41:49.056885 VM hypervisor: (XEN) [VT-D]DMAR:[DMA Read]
> > Request device [0000:00:02.0] fault addr 4238d0a000, iommu reg =
> > ffff82c00021d000
> > Oct 14 18:41:49.056890 VM hypervisor: (XEN) [VT-D]DMAR: reason 06 -
> > PTE Read access is not set
> >
> > They repeat. In the log attached to
> > https://gitlab.freedesktop.org/drm/intel/-/issues/2576, they start at
> > "Oct 14 18:41:49.056589" and continue until I unplug the dock around
> > "Oct 14 18:41:54.801802".
> >
> > I've also seen similar messages when attaching the laptop's HDMI port
> > to a 4k monitor. The eDP display by itself seems okay.
> >
> > I tried Fedora 31 & 32 live images with intel_iommu=on, so no Xen, and
> > didn't see any errors
> >
> > This is a kernel & xen log with drm.debug=0x1e. It also includes some
> > application (glass) logging when it changes resolutions which seems to
> > set off the DMA faults. 5500-igfx-messages-kern-xen-glass
> >
> > Running xen with iommu=no-igfx disables the iommu for the i915
> > graphics and no faults are reported. However, that breaks some other
> > devices (Dell Latitude 7200 and 5580) giving a black screen with:
> >
> > Oct 10 13:24:37.022117 kernel:[   14.884759] i915 0000:00:02.0: Failed
> > to idle engines, declaring wedged!
> > Oct 10 13:24:37.022118 kernel:[   14.964794] i915 0000:00:02.0: Failed
> > to initialize GPU, declaring it wedged!
> >
> > Any suggestions welcome.
> 
> Presumably this is with a PV dom0.  What are 39b5845000 and 4238d0a000
> in the machine memory map?
> 
> This smells like a missing RMRR in the ACPI tables.

I agree.

Can you paste the memory map as printed by Xen when booting, and what
command line are you using to boot Xen.

Have you tried adding dom0-iommu=map-inclusive to the Xen command
line?

Roger.