Re: [PATCH] pci-host: Allow extended config space access for PowerNV PHB4 model

[Cédric Le Goater]

On 11/17/21 08:59, Philippe Mathieu-Daudé wrote:
> On 11/9/21 17:04, Cédric Le Goater wrote:
> > On 11/9/21 16:51, Frederic Barrat wrote:
> > > On 09/11/2021 15:50, Christophe Lombard wrote:
> > > > The PCIe extended configuration space on the device is not currently
> > > > accessible to the host. if by default,  it is still inaccessible for
> > > > conventional for PCIe buses, add the current flag
> > > > PCI_BUS_EXTENDED_CONFIG_SPACE on the root bus permits PCI-E extended
> > > > config space access.
> >
> > For the record, this is coming from an experiment of plugging a
> > CXL device on a QEMU PowerNV POWER10 machine (baremetal). Only
> > minor changes (64 bits ops) were required to get it working.
>
> Since this note could be helpful when having future retrospective,
> do you mind amending this note to the commit description?

Yes. I agree. Please do.
 
> > I wonder where we are with the CXL models ?
>
> IIRC Ben worked actively, asked help to the community but received
> very few, basically because there is not enough man power IMHO.
>
> Last thing I remember is Igor suggested a different design approach:
> https://lore.kernel.org/qemu-devel/20210319180705.6ede9091@redhat.com/

Well, the CXL Linux driver seemed to work fine on QEMU machines, Intel
and POWER.

Thanks for the info,

C.