Re: [PATCH] PCI: Allow drivers to claim exclusive access to config regions

[Greg Kroah-Hartman]

On Thu, Mar 25, 2021 at 10:55:01AM -0700, Dan Williams wrote:
> On Thu, Mar 25, 2021 at 1:29 AM Christoph Hellwig <hch@xxxxxxxxxxxxx> wrote:
> >
> > On Thu, Mar 25, 2021 at 07:54:59AM +0100, Greg Kroah-Hartman wrote:
> > > On Wed, Mar 24, 2021 at 06:23:54PM -0700, Dan Williams wrote:
> > > > The PCIE Data Object Exchange (DOE) mailbox is a protocol run over
> > > > configuration cycles. It assumes one initiator at a time is
> > > > reading/writing the data registers.
> > >
> > > That sounds like a horrible protocol for a multi-processor system.
> > > Where is it described and who can we go complain to for creating such a
> > > mess?
> >
> > Indeed.  Dan, is there a way to stilk kill this protocol off before it
> > leaks into the wild?
> 
> Unfortunately I think that opportunity was more than a year ago, and
> there's been a proliferation of derivative protocols building on it
> since.

Doesn't mean it can't be changed, right?

Are there any actual devices that require this?

thanks,

greg k-h