Re: [PATCH RFC 0/2] Linux: possible ixes for mapping high MMIO regions

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Fri, Jan 03, 2014 at 04:45:20PM +0000, David Vrabel wrote:
> This a possible fix for the problems with mapping high MMIO regions in
> certain cases (e.g., the RDMA drivers) as not all mappers were
> specifing the _PAGE_IOMAP which meant no valid MFN could be found and
> the resulting PTE would be marked as not present, causing subsequent
> faults.
> 
> It assumes that anything that isn't RAM (whether ballooned out or not)
> is an I/O region and thus should be 1:1 in the p2m.  Ballooned frames
> are still marked as missing in the p2m as before.
> 
> As a follow on, mfn_to_pfn() is (hopefully) extended to do the right
> thing with such an MFN.  This means the Xen-specific _PAGE_IOMAP PTE
> flag can be removed,

Woot!
> 
> This series is posted as an early RFC in the hope that is an
> acceptable approach.  It has only seen the bare minimum of smoke
> testing (my test dom0 didn't explode). In particular, I've not
> actually tested it with a device with a high MMIO.

I can do in a couple of weeks.
> 
> David
>