[PATCH] PCI: remove unnecessary check of device_type == pci

Will Deacon will.deacon at arm.com
Thu Sep 20 02:02:22 PDT 2018


On Wed, Sep 19, 2018 at 05:33:01PM +0100, Lorenzo Pieralisi wrote:
> 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 at arm.com> 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.

Fine by me!

Will



More information about the linux-arm-kernel mailing list