On Fri, Oct 14, 2016 at 09:25:58AM +0200, Laurent Vivier wrote:
> On 14/10/2016 01:29, David Gibson wrote:
> > From 98f07c09c6d72218800d6cfbf44b973a88ece2aa Mon Sep 17 00:00:00 2001
> > From: David Gibson
> > Date: Fri, 14 Oct 2016 10:21:00 +1100
> > Subject: [PATCH]
On 14/10/2016 01:29, David Gibson wrote:
> From 98f07c09c6d72218800d6cfbf44b973a88ece2aa Mon Sep 17 00:00:00 2001
> From: David Gibson
> Date: Fri, 14 Oct 2016 10:21:00 +1100
> Subject: [PATCH] spapr: Improved placement of PCI host bridges in guest memory
> map
>
>
On Thu, Oct 13, 2016 at 10:40:32AM +0200, Laurent Vivier wrote:
>
>
> On 13/10/2016 01:57, David Gibson wrote:
> > Currently, the MMIO space for accessing PCI on pseries guests begins at
> > 1 TiB in guest address space. Each PCI host bridge (PHB) has a 64 GiB
> > chunk of address space in
On 13/10/2016 01:57, David Gibson wrote:
> Currently, the MMIO space for accessing PCI on pseries guests begins at
> 1 TiB in guest address space. Each PCI host bridge (PHB) has a 64 GiB
> chunk of address space in which it places its outbound PIO and 32-bit and
> 64-bit MMIO windows.
>
> This
Currently, the MMIO space for accessing PCI on pseries guests begins at
1 TiB in guest address space. Each PCI host bridge (PHB) has a 64 GiB
chunk of address space in which it places its outbound PIO and 32-bit and
64-bit MMIO windows.
This scheme as several problems:
- It limits guest RAM to