From: Ville Syrjälä <[email protected]>
Broxton has known issues with VT-d superpage. Namely frame buffer
compression (FBC) can't be safely used when superpage is enabled.
Currently we're disabling FBC entirely when VT-d is active, but
I think just disabling superpage would be better since FBC can
save some power.
TODO: would be nice to use the macros from include/drm/i915_pciids.h,
but can't do that with DECLARE_PCI_FIXUP_HEADER()
Cc: David Woodhouse <[email protected]>
Cc: Lu Baolu <[email protected]>
Cc: [email protected]
Signed-off-by: Ville Syrjälä <[email protected]>
---
drivers/iommu/intel/iommu.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 08ba412053e3..ef717908647d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -5681,6 +5681,13 @@ static void quirk_skip_igfx_superpage(struct pci_dev
*dev)
iommu_skip_igfx_superpage = 1;
}
+/* Broxton igfx has issues with superpage */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0A84,
quirk_skip_igfx_superpage);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1A84,
quirk_skip_igfx_superpage);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1A85,
quirk_skip_igfx_superpage);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5A84,
quirk_skip_igfx_superpage);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5A85,
quirk_skip_igfx_superpage);
+
/* Geminilake igfx appears to have issues with superpage */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3184,
quirk_skip_igfx_superpage);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3185,
quirk_skip_igfx_superpage);
--
2.31.1
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx