On Wed, 2024-09-18 at 11:04 +0200, Niklas Schnelle wrote: > On s390 PCI busses are virtualized and the downstream ports are > invisible to the OS and struct pci_bus::self is NULL. This associated > struct pci_dev is however relied upon in pci_ari_enabled() to check > whether ARI is enabled for the bus. ARI is therefor always detected as > disabled. > > At the same time firmware on s390 always enables and relies upon ARI > thus causing a mismatch. Moreover with per-PCI function pass-through > there may exist busses with no function with devfn 0. For example > a SR-IOV capable device with two PFs may have separate function > dependency link chains for each of the PFs and their child VFs. In this > case the OS may only see the second PF and its child VFs on a bus > without a devfn 0 function. A situation which is also not supported by > the common pci_configure_ari() code. > > Dispite simply being a mismatch this causes problems as some PCI devices > present a different SR-IOV topology depending on PCI_SRIOV_CTRL_ARI. > > A similar mismatch may occur with SR-IOV when virtfn_add_bus() creates new > busses with no associated struct pci_dev. Here too pci_ari_enabled() > on these busses would return false even if ARI is actually used. > > Prevent both mismatches by moving the ari_enabled flag from struct > pci_dev to struct pci_bus making it independent from struct pci_bus:: > self. Let the bus inherit the ari_enabled state from its parent bus when > there is no bridge device such that busses added by virtfn_add_bus() > match their parent. For s390 set ari_enabled when the device supports > ARI in the awareness that all PCIe ports on s390 systems are ARI > capable. > > Signed-off-by: Niklas Schnelle <schnelle@xxxxxxxxxxxxx> > --- > Note: In a comment of the v1 thread I discussed an alternative idea for > a generic solution that would include the Jailhouse hypervisor via > hypervisor_isolated_pci_functions(). As Bjorn correctly pointed out this > more generic solution however lacks a way to indicate that ARI is really > enabled in the hardware. So instead for now I propose to stick with this > patch which only enables this unconditionally on s390x and SR-IOV > virtual busses where the ARI is inherited. > --- > Changes in v2: > - Rebased on v6.11 > - Link to v1: https://lore.kernel.org/r/20240730-ari_no_bus_dev-v1-1-7de17676f9fe@xxxxxxxxxxxxx > > @Bjorn, this seems to have dropped off your radar or would you like me to see if I can find a different approach? Thanks, Niklas
