On Tue, Feb 15, 2022 at 05:08:18PM +0530, Tejas Upadhyay wrote: > The VT-d spec requires (10.4.4 Global Command Register, TE > field) that: > > Hardware implementations supporting DMA draining must drain > any in-flight DMA read/write requests queued within the > Root-Complex before completing the translation enable > command and reflecting the status of the command through > the TES field in the Global Status register. > > Unfortunately, some integrated graphic devices fail to do > so after some kind of power state transition. As the > result, the system might stuck in iommu_disable_translati > on(), waiting for the completion of TE transition. > > This adds RPLS to a quirk list for those devices and skips > TE disabling if the qurik hits. > > Fixes: https://gitlab.freedesktop.org/drm/intel/-/issues/4898 > Fixes: LCK-10789 > Tested-by: Raviteja Goud Talla <ravitejax.goud.ta...@intel.com> > Cc: Ashok Raj <ashok....@intel.com> > Cc: sta...@vger.kernel.org > Signed-off-by: Tejas Upadhyay <tejaskumarx.surendrakumar.upadh...@intel.com> > --- > drivers/iommu/intel/iommu.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c > index 639e4438827e..bd6dac90a948 100644 > --- a/drivers/iommu/intel/iommu.c > +++ b/drivers/iommu/intel/iommu.c > @@ -5741,7 +5741,7 @@ static void quirk_igfx_skip_te_disable(struct pci_dev > *dev) > ver = (dev->device >> 8) & 0xff; > if (ver != 0x45 && ver != 0x46 && ver != 0x4c && > ver != 0x4e && ver != 0x8a && ver != 0x98 && > - ver != 0x9a) > + ver != 0x9a && ver != 0xa7)
It is the first time that I look to this code here. I believe that instead of this if we should be listing the devices individually, probably using the DECLARE_PCI_FIXUP_HEADER or some other way to make it clear and explicit the opt-in on the quirk. Anyway, the addition of this one here is needed and the rest can be in a follow-up: Reviewed-by: Rodrigo Vivi <rodrigo.v...@intel.com> Cc: Baolu Lu <baolu...@linux.intel.com> Cc: David Woodhouse <dw...@infradead.org> Baolu, David, could we push this through drm-intel? > return; > > if (risky_device(dev)) > -- > 2.34.1 >
