Hello, > > When running the rk3588 in endpoint mode, with an Intel host with IOMMU > > enabled, the host side prints: > > DMAR: VT-d detected Invalidation Time-out Error: SID 0 > > > > When running the rk3588 in endpoint mode, with an AMD host with IOMMU > > enabled, the host side prints: > > iommu ivhd0: AMD-Vi: Event logged [IOTLB_INV_TIMEOUT device=63:00.0 address=0x42b5b01a0] > > Maybe add a blank line and indent the message since it's quoted > material? E.g., > > When running the rk3588 in endpoint mode, with an Intel IOMMU, the > host side prints: > > DMAR: VT-d detected Invalidation Time-out Error: SID 0 > > When running the rk3588 in endpoint mode, with an AMD ... > > iommu ivhd0: AMD-Vi: Event logged [IOTLB_INV_TIMEOUT device=63:00.0 address=0x42b5b01a0] > > Too bad DMAR isn't smart enough to include a device ID in its message ;) > > Can you include something here about what the issue is? Based on the > subject line and the patch, I assume something is wrong with the ATS > Capability? I guess this is some kind of rk3588 defect, right? > > > Usually, to handle these issues, we add a quirk for the PCI vendor and > > device ID in drivers/pci/quirks.c with quirk_no_ats(). That is because > > we cannot usually modify the capabilities on the EP side. > > > > In this case, we can modify the capabilties on the EP side. Thus, hide the > > broken ATS capability on rk3588 when running in EP mode. That way, > > we don't need any quirk on the host side, and we see no errors on the host > > side, and we can run pci_endpoint_test successfully, with the IOMMU > > enabled on the host side. > > s/capabilties/capabilities/ If there are no code changes here, then I can update the commit log directly on the branch itself once applied. Thank you! Krzysztof
