On Tue, Mar 14, 2017 at 06:56:26PM +0100, Thomas Gleixner wrote: > On Tue, 14 Mar 2017, Andi Kleen wrote: > > The other option is to simply make it unconditional. That would > > be even simpler, but it is a bit more risky. Hmm, I suppose may > > be worth trying to find out what Windows uses. If they get away > > with MMCONFIG everywhere we should be too. > > From the PCIe spec: > > The PCI 3.0 compatible Configuration Space can be accessed using either > the mechanism defined in the PCI Local Bus Specification or the PCI > Express Enhanced Configuration Access Mechanism (ECAM) described later in > this section. Accesses made using either access mechanism are > equivalent. The PCI Express Extended Configuration Space can only be > accessed by using the ECAM. > > The 1.0 spec has a similar wording (s/3.0/2.3). > > Definitely the best way to go.
I agree that it should be fairly safe to do ECAM/MMCONFIG without locking. Can we handle the decision part by adding a "lockless" bit to struct pci_ops? Old ops don't mention that bit, so it will be initialized to zero and we'll do locking as today. ECAM/MMCONFIG ops can set it and we can skip the locking. Bjorn
