On Tue, Jun 9, 2020 at 6:02 AM Zhangfei Gao <zhangfei.gao@xxxxxxxxxx> wrote:
> On 2020/6/9 上午12:41, Bjorn Helgaas wrote:
> > On Mon, Jun 08, 2020 at 10:54:15AM +0800, Zhangfei Gao wrote:
> >> On 2020/6/6 上午7:19, Bjorn Helgaas wrote:
> >>>> +++ b/drivers/iommu/iommu.c
> >>>> @@ -2418,6 +2418,10 @@ int iommu_fwspec_init(struct device *dev, struct
> >>>> fwnode_handle *iommu_fwnode,
> >>>> fwspec->iommu_fwnode = iommu_fwnode;
> >>>> fwspec->ops = ops;
> >>>> dev_iommu_fwspec_set(dev, fwspec);
> >>>> +
> >>>> + if (dev_is_pci(dev))
> >>>> + pci_fixup_device(pci_fixup_final, to_pci_dev(dev));
> >>>> +
> >>>>
> >>>> Then pci_fixup_final will be called twice, the first in pci_bus_add_device.
> >>>> Here in iommu_fwspec_init is the second time, specifically for iommu_fwspec.
> >>>> Will send this when 5.8-rc1 is open.
> >>> Wait, this whole fixup approach seems wrong to me. No matter how you
> >>> do the fixup, it's still a fixup, which means it requires ongoing
> >>> maintenance. Surely we don't want to have to add the Vendor/Device ID
> >>> for every new AMBA device that comes along, do we?
> >>>
> >> Here the fake pci device has standard PCI cfg space, but physical
> >> implementation is base on AMBA
> >> They can provide pasid feature.
> >> However,
> >> 1, does not support tlp since they are not real pci devices.
> >> 2. does not support pri, instead support stall (provided by smmu)
> >> And stall is not a pci feature, so it is not described in struct pci_dev,
> >> but in struct iommu_fwspec.
> >> So we use this fixup to tell pci system that the devices can support stall,
> >> and hereby support pasid.
> > This did not answer my question. Are you proposing that we update a
> > quirk every time a new AMBA device is released? I don't think that
> > would be a good model.
>
> Yes, you are right, but we do not have any better idea yet.
> Currently we have three fake pci devices, which support stall and pasid.
> We have to let pci system know the device can support pasid, because of
> stall feature, though not support pri.
> Do you have any other ideas?
It sounds like the best way would be to allocate a PCI capability for it, so
detection can be done through config space, at least in future devices,
or possibly after a firmware update if the config space in your system
is controlled by firmware somewhere. Once there is a proper mechanism
to do this, using fixups to detect the early devices that don't use that
should be uncontroversial. I have no idea what the process or timeline
is to add new capabilities into the PCIe specification, or if this one
would be acceptable to the PCI SIG at all.
If detection cannot be done through PCI config space, the next best
alternative is to pass auxiliary data through firmware. On DT based
machines, you can list non-hotpluggable PCIe devices and add custom
properties that could be read during device enumeration. I assume
ACPI has something similar, but I have not done that.
Arnd
