Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-19 Thread Konrad Rzeszutek Wilk
On Thu, Aug 18, 2016 at 04:35:44PM +0100, One Thousand Gnomes wrote: > On Thu, 18 Aug 2016 05:12:54 -0600 > "Jan Beulich" wrote: > > > >>> On 18.08.16 at 12:16, wrote: > > > On 18/08/16 11:06, Jan Beulich wrote: > > > On 17.08.16 at 22:32,

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-19 Thread Jan Beulich
>>> On 19.08.16 at 16:52, wrote: > On Thu, Aug 18, 2016 at 04:06:33AM -0600, Jan Beulich wrote: >> >>> On 17.08.16 at 22:32, wrote: >> >Looking at the kernel it assumes that WB is ok for 640KB->1MB. >> >The comment says: >> >" /* Low

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-19 Thread Konrad Rzeszutek Wilk
On Thu, Aug 18, 2016 at 04:06:33AM -0600, Jan Beulich wrote: > >>> On 17.08.16 at 22:32, wrote: > > One of the interesting things about XSA 154 fix ("x86: enforce consistent > > cachability of MMIO mappings") is that when certain applications (mcelog) > > are trying to map

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-18 Thread One Thousand Gnomes
On Thu, 18 Aug 2016 05:12:54 -0600 "Jan Beulich" wrote: > >>> On 18.08.16 at 12:16, wrote: > > On 18/08/16 11:06, Jan Beulich wrote: > > On 17.08.16 at 22:32, wrote: > >>>Looking at the kernel it assumes that

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-18 Thread Jan Beulich
>>> On 18.08.16 at 12:16, wrote: > On 18/08/16 11:06, Jan Beulich wrote: > On 17.08.16 at 22:32, wrote: >>>Looking at the kernel it assumes that WB is ok for 640KB->1MB. >>>The comment says: >>>" /* Low ISA region is always

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-18 Thread Andrew Cooper
On 18/08/16 11:06, Jan Beulich wrote: On 17.08.16 at 22:32, wrote: >> One of the interesting things about XSA 154 fix ("x86: enforce consistent >> cachability of MMIO mappings") is that when certain applications (mcelog) >> are trying to map /dev/mmap and lurk in ISA

Re: [Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-18 Thread Jan Beulich
>>> On 17.08.16 at 22:32, wrote: > One of the interesting things about XSA 154 fix ("x86: enforce consistent > cachability of MMIO mappings") is that when certain applications (mcelog) > are trying to map /dev/mmap and lurk in ISA regions - we get: DYM /dev/mem ? Most

[Xen-devel] XSA 154 and ISA region (640K -> 1MB) WB cache instead of UC

2016-08-17 Thread Konrad Rzeszutek Wilk
Hey Jan, et. al., One of the interesting things about XSA 154 fix ("x86: enforce consistent cachability of MMIO mappings") is that when certain applications (mcelog) are trying to map /dev/mmap and lurk in ISA regions - we get: [ 49.399053] WARNING: CPU: 0 PID: 2471 at arch/x86/mm/pat.c:913