On Tue, Sep 18, 2018 at 12:05:40PM -0700, Rob Herring wrote: > On Thu, Sep 13, 2018 at 7:51 AM Lorenzo Pieralisi > <lorenzo.pieralisi@xxxxxxx> wrote: > > > > On Wed, Aug 29, 2018 at 01:34:40PM -0500, Rob Herring wrote: > > > PCI host drivers have already matched on compatible strings, so checking > > > device_type is redundant. Also, device_type is considered deprecated for > > > FDT though we've still been requiring it for PCI hosts as it is useful > > > for finding PCI buses. > > > > Hi Rob, > > > > I have no problem with the patch per-se, I can't parse though the second > > paragraph, in particular what you mean by "useful for finding PCI > > buses". > > Device_type is the only generic way we can identify PCI buses which is > useful for dtc for example to do PCI binding checks. Maybe we can use > the node name which is what I'm doing for cpu nodes, but we've been > less consistent about that for PCI. > > > > > What about the corresponding dts files ? I suspect we had better leave > > them alone lest we can trigger regressions with new dts and older > > kernels. > > Yes. it will take some time before we can remove from dts files. Or > maybe only new ones change. OK, thanks. What about PCI host controllers bindings ? I assume we leave the bindings (that enforce device_type) unchanged too. If Will and Michal have no objections I will queue this patch as-is for v4.20. Thanks, Lorenzo
