lkml.org 
[lkml]   [2018]   [Sep]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] PCI: remove unnecessary check of device_type == pci
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@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

\
 
 \ /
  Last update: 2018-09-20 11:02    [W:0.059 / U:0.392 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site