Re: [Xen-devel] VPMU interrupt unreliability

2017-10-22 Thread Meng Xu
On Fri, Oct 20, 2017 at 3:07 AM, Jan Beulich wrote: > > >>> On 19.10.17 at 20:20, wrote: > > Is there any document about the possible attack via the vPMU? The > > document I found (such as [1] and XSA-163) just briefly say that the > > vPMU should be

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-20 Thread Jan Beulich
>>> On 19.10.17 at 20:20, wrote: > Is there any document about the possible attack via the vPMU? The > document I found (such as [1] and XSA-163) just briefly say that the > vPMU should be disabled due to security concern. Besides the other responses you've already got, I

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-19 Thread Andrew Cooper
On 19/10/17 19:24, Kyle Huey wrote: > On Thu, Oct 19, 2017 at 11:20 AM, Meng Xu wrote: >> On Thu, Oct 19, 2017 at 11:40 AM, Andrew Cooper >> wrote: >>> On 19/10/17 16:09, Kyle Huey wrote: On Wed, Oct 11, 2017 at 7:09 AM, Boris Ostrovsky

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-19 Thread Kyle Huey
On Thu, Oct 19, 2017 at 11:20 AM, Meng Xu wrote: > On Thu, Oct 19, 2017 at 11:40 AM, Andrew Cooper > wrote: >> >> On 19/10/17 16:09, Kyle Huey wrote: >> > On Wed, Oct 11, 2017 at 7:09 AM, Boris Ostrovsky >> > wrote:

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-19 Thread Meng Xu
On Thu, Oct 19, 2017 at 11:40 AM, Andrew Cooper wrote: > > On 19/10/17 16:09, Kyle Huey wrote: > > On Wed, Oct 11, 2017 at 7:09 AM, Boris Ostrovsky > > wrote: > >> On 10/10/2017 12:54 PM, Kyle Huey wrote: > >>> On Mon, Jul 24, 2017 at 9:54

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-19 Thread Andrew Cooper
On 19/10/17 16:09, Kyle Huey wrote: > On Wed, Oct 11, 2017 at 7:09 AM, Boris Ostrovsky > wrote: >> On 10/10/2017 12:54 PM, Kyle Huey wrote: >>> On Mon, Jul 24, 2017 at 9:54 AM, Kyle Huey wrote: On Mon, Jul 24, 2017 at 8:07 AM, Boris Ostrovsky

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-19 Thread Kyle Huey
On Wed, Oct 11, 2017 at 7:09 AM, Boris Ostrovsky wrote: > On 10/10/2017 12:54 PM, Kyle Huey wrote: >> On Mon, Jul 24, 2017 at 9:54 AM, Kyle Huey wrote: >>> On Mon, Jul 24, 2017 at 8:07 AM, Boris Ostrovsky >>> wrote:

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-11 Thread Boris Ostrovsky
On 10/10/2017 12:54 PM, Kyle Huey wrote: > On Mon, Jul 24, 2017 at 9:54 AM, Kyle Huey wrote: >> On Mon, Jul 24, 2017 at 8:07 AM, Boris Ostrovsky >> wrote: > One thing I noticed is that the workaround doesn't appear to be > complete: it is

Re: [Xen-devel] VPMU interrupt unreliability

2017-10-10 Thread Kyle Huey
On Mon, Jul 24, 2017 at 9:54 AM, Kyle Huey wrote: > On Mon, Jul 24, 2017 at 8:07 AM, Boris Ostrovsky > wrote: >> One thing I noticed is that the workaround doesn't appear to be complete: it is only checking PMC0 status and not other

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Kyle Huey
On Mon, Jul 24, 2017 at 8:07 AM, Boris Ostrovsky wrote: > >>> One thing I noticed is that the workaround doesn't appear to be >>> complete: it is only checking PMC0 status and not other counters (fixed >>> or architectural). Of course, without knowing what the actual

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Boris Ostrovsky
>> One thing I noticed is that the workaround doesn't appear to be >> complete: it is only checking PMC0 status and not other counters (fixed >> or architectural). Of course, without knowing what the actual problem >> was it's hard to say whether this was intentional. > handle_pmc_quirk appears

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Kyle Huey
On Mon, Jul 24, 2017 at 7:13 AM, Andrew Cooper wrote: > On 22/07/17 21:16, Kyle Huey wrote: >> Last year I reported[0] seeing occasional instability in performance >> counter values when running rr[1], which depends on completely >> deterministic counts of retired

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Kyle Huey
On Mon, Jul 24, 2017 at 7:08 AM, Boris Ostrovsky wrote: > On 07/22/2017 04:16 PM, Kyle Huey wrote: >> Last year I reported[0] seeing occasional instability in performance >> counter values when running rr[1], which depends on completely >> deterministic counts of

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Andrew Cooper
On 22/07/17 21:16, Kyle Huey wrote: > Last year I reported[0] seeing occasional instability in performance > counter values when running rr[1], which depends on completely > deterministic counts of retired conditional branches of userspace > programs. > > I recently identified the cause of this

Re: [Xen-devel] VPMU interrupt unreliability

2017-07-24 Thread Boris Ostrovsky
On 07/22/2017 04:16 PM, Kyle Huey wrote: > Last year I reported[0] seeing occasional instability in performance > counter values when running rr[1], which depends on completely > deterministic counts of retired conditional branches of userspace > programs. > > I recently identified the cause of

[Xen-devel] VPMU interrupt unreliability

2017-07-22 Thread Kyle Huey
Last year I reported[0] seeing occasional instability in performance counter values when running rr[1], which depends on completely deterministic counts of retired conditional branches of userspace programs. I recently identified the cause of this problem. Xen's VPMU code contains a workaround