Jan Beulich wrote on 2015-10-15:
On 15.10.15 at 10:52, wrote:
>> Jan Beulich wrote on 2015-10-15:
>> On 15.10.15 at 09:28, wrote:
The premise for a misbehaving guest to impact the system is that
the IOMMU is buggy which takes long time to complete the invalidation.
In othe
>>> On 15.10.15 at 10:52, wrote:
> Jan Beulich wrote on 2015-10-15:
> On 15.10.15 at 09:28, wrote:
>>> The premise for a misbehaving guest to impact the system is that the
>>> IOMMU is buggy which takes long time to complete the invalidation.
>>> In other words, if all invalidations are able
Jan Beulich wrote on 2015-10-15:
On 15.10.15 at 09:28, wrote:
>> Jan Beulich wrote on 2015-10-15:
>> On 15.10.15 at 03:03, wrote:
Jan Beulich wrote on 2015-10-14:
> As long as the multi-millisecond spins aren't going to go away by
> other means, I think conversion to async m
>>> On 15.10.15 at 09:28, wrote:
> Jan Beulich wrote on 2015-10-15:
> On 15.10.15 at 03:03, wrote:
>>> Jan Beulich wrote on 2015-10-14:
As long as the multi-millisecond spins aren't going to go away by
other means, I think conversion to async mode is ultimately unavoidable.
>>>
>>>
Jan Beulich wrote on 2015-10-15:
On 15.10.15 at 03:03, wrote:
>> Jan Beulich wrote on 2015-10-14:
>>> As long as the multi-millisecond spins aren't going to go away by
>>> other means, I think conversion to async mode is ultimately unavoidable.
>>
>> I am not fully agreed. I think the time t
>>> On 15.10.15 at 03:03, wrote:
> Jan Beulich wrote on 2015-10-14:
>> As long as the multi-millisecond spins aren't going to go away by
>> other means, I think conversion to async mode is ultimately unavoidable.
>
> I am not fully agreed. I think the time to spin is important. To me, less
> tha
Jan Beulich wrote on 2015-10-14:
On 14.10.15 at 07:12, wrote:
>> Jan Beulich wrote on 2015-10-13:
>> On 13.10.15 at 07:27, wrote:
Jan Beulich wrote on 2015-10-12:
On 12.10.15 at 03:42, wrote:
>> So, my suggestion is that we can rely on user to not assign the
>> ATS
>> >>> On 13.10.2015 at 22:50 wrote:
> >>> On 13.10.15 at 16:29, wrote:
> >> > >>>On 29.09.2015 at 15:22 wrote:
> >> >>> On 29.09.15 at 04:53, wrote:
> >> Monday, September 28, 2015 2:47 PM, wrote:
> >> >> >>> On 28.09.15 at 05:08, wrote:
> >> >> Thursday, September 24, 2015 12:27 AM
>> >>>On 13.10.2015 at 17:35, wrote:
> At 11:09 + on 11 Oct (1444561760), Xu, Quan wrote:
> What in particular is worrying you abo
>>> On 14.10.15 at 07:12, wrote:
> Jan Beulich wrote on 2015-10-13:
> On 13.10.15 at 07:27, wrote:
>>> Jan Beulich wrote on 2015-10-12:
>>> On 12.10.15 at 03:42, wrote:
> So, my suggestion is that we can rely on user to not assign the
> ATS device if hypervisor says it cannot sup
Jan Beulich wrote on 2015-10-13:
On 13.10.15 at 07:27, wrote:
>> Jan Beulich wrote on 2015-10-12:
>> On 12.10.15 at 03:42, wrote:
So, my suggestion is that we can rely on user to not assign the
ATS device if hypervisor says it cannot support such device. For
example, if hy
>>> On 13.10.15 at 16:29, wrote:
>> > >>>On 29.09.2015 at 15:22 wrote:
>> >>> On 29.09.15 at 04:53, wrote:
>> Monday, September 28, 2015 2:47 PM, wrote:
>> >> >>> On 28.09.15 at 05:08, wrote:
>> >> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
>>The extra ref taken will pre
>> >>>On 29.09.2015 at 15:22 wrote:
> >>> On 29.09.15 at 04:53, wrote:
> Monday, September 28, 2015 2:47 PM, wrote:
> >> >>> On 28.09.15 at 05:08, wrote:
> >> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
>The extra ref taken will prevent the page from getting freed.
Jan
Hi,
At 11:09 + on 11 Oct (1444561760), Xu, Quan wrote:
> One question: do two lists refer to page_list and arch.relmem_list?
No, I was wondering if a page ever needed to be queued waiting for two
different flushes -- e.g. if there are multiple IOMMUs.
> I know you prefer __scheme_A__(I think
>>> On 13.10.15 at 07:27, wrote:
> Jan Beulich wrote on 2015-10-12:
> On 12.10.15 at 03:42, wrote:
>>> So, my suggestion is that we can rely on user to not assign the ATS
>>> device if hypervisor says it cannot support such device. For
>>> example, if hypervisor find the invalidation isn't co
Jan Beulich wrote on 2015-10-12:
On 12.10.15 at 03:42, wrote:
>> According the discussion and suggestion you made in past several
>> weeks, obviously, it is not an easy task. So I am wondering whether
>> it is worth to do it since:
>> 1. ATS device is not popular. I only know one NIC from Myr
>>> On 12.10.15 at 03:42, wrote:
> According the discussion and suggestion you made in past several weeks,
> obviously, it is not an easy task. So I am wondering whether it is worth to
> do it since:
> 1. ATS device is not popular. I only know one NIC from Myricom has ATS
> capabilities.
> 2.
>>> On 11.10.15 at 13:09, wrote:
> On 11.10.2015 at 2:25, wrote:
>> At 17:02 + on 07 Oct (1444237344), Xu, Quan wrote:
>> > Q2: how do you know when to drop them?
>> >- log (or something) when the IOMMU entry is removed/overwritten; and
>> >- drop the entry when the flush completes.
>
Xu, Quan wrote on 2015-09-16:
> Introduction
>
>
>VT-d code currently has a number of cases where completion of
> certain operations is being waited for by way of spinning. The
> majority of instances use that variable indirectly through
> IOMMU_WAIT_OP() macro , allowing for loop
On 11.10.2015 at 2:25, wrote:
> At 17:02 + on 07 Oct (1444237344), Xu, Quan wrote:
> > Q2: how do you know when to drop them?
> >- log (or something) when the IOMMU entry is removed/overwritten; and
> >- drop the entry when the flush completes.
> >
> >-- We can add a new page_list_
Hi,
At 17:02 + on 07 Oct (1444237344), Xu, Quan wrote:
> __scheme A__
> Q1: - when to take the references?
> take the reference when the IOMMU entry is _created_;
> in detail:
> --iommu_map_page(), or
> --ept_set_entry() [Once IOMMU shares EPT page table.]
>
> That leaves on
>> >>> On 09.10.2015 at 15:18 wrote:
> >>> On 09.10.15 at 09:06, wrote:
> >> > >>>On 08.10.2015 at 16:52 wrote:
> >> >>> On 07.10.15 at 19:02, wrote:
> >> > __scheme B__
> >> > Q1: - when to take the references?
> >> >
> >> > take the reference when the IOMMU entry is _
> removed/overwrit
>>> On 09.10.15 at 09:06, wrote:
>> > >>>On 08.10.2015 at 16:52 wrote:
>> >>> On 07.10.15 at 19:02, wrote:
>> > Q3: what to do about mappings of other domains' memory (i.e. grant and
>> > foreign mappings).
>> >Between two domains, now I have only one idea to fix this tricky
>> > issue -- wa
>> >>>On 08.10.2015 at 16:52 wrote:
> >>> On 07.10.15 at 19:02, wrote:
> > __scheme A__
> > Q1: - when to take the references?
> > take the reference when the IOMMU entry is _created_;
> > in detail:
> > --iommu_map_page(), or
> > --ept_set_entry() [Once IOMMU shares EPT page ta
>>> On 07.10.15 at 19:02, wrote:
> __scheme A__
> Q1: - when to take the references?
> take the reference when the IOMMU entry is _created_;
> in detail:
> --iommu_map_page(), or
> --ept_set_entry() [Once IOMMU shares EPT page table.]
>
> That leaves one question:
> -- how t
>>> >> On October 01, 2015, at 5:09 PM wrote:
> At 15:05 + on 30 Sep (1443625549), Xu, Quan wrote:
> > >> >>> On September 29, 2015, at 5:12 PM, wrote:
> > Could I introduce a new typed reference which can only been deref in
> > QI interrupt handler(or associated tasklet)?? --(stop me, I al
Hi,
At 15:05 + on 30 Sep (1443625549), Xu, Quan wrote:
> >> >>> On September 29, 2015, at 5:12 PM, wrote:
> > So you'll need to do something else to make the unmap safe.
> >The usual
> > method in Xen is to hold a reference to the page (for read-only
> > mappings)
>
>
> Read-only mapping re
>> >>> On September 29, 2015, at 5:12 PM, wrote:
> At 03:08 + on 28 Sep (1443409723), Xu, Quan wrote:
> > >>> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
> > > 7/13: I'm not convinced that making the vcpu spin calling
> > > sched_yield() is a very good plan. Better to explicitly
>>> On 30.09.15 at 15:55, wrote:
>> >> >> >>> On September 29, 2015 at 3:22 PM, wrote:
>> >>> On 29.09.15 at 04:53, wrote:
>> Monday, September 28, 2015 2:47 PM, wrote:
>> >> >>> On 28.09.15 at 05:08, wrote:
>> >> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
>> >
>> > For
> >> >> >>> On September 29, 2015 at 3:22 PM, wrote:
> >>> On 29.09.15 at 04:53, wrote:
> Monday, September 28, 2015 2:47 PM, wrote:
> >> >>> On 28.09.15 at 05:08, wrote:
> >> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
> >
> > For Tim's suggestion --"to make the IOMMU tab
>>> On 29.09.15 at 11:11, wrote:
> With the flush taking longer than Xen can wait for, you'll need to
> do something more complex, e.g.:
> - keep a log of all relevant pending derefs, to be processed when the
>flush completes; or
> - have some other method of preventing changes of ownership/
Hi,
At 03:08 + on 28 Sep (1443409723), Xu, Quan wrote:
> >>> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
> > 7/13: I'm not convinced that making the vcpu spin calling
> > sched_yield() is a very good plan. Better to explicitly pause the domain
> > if you
> > need its vcpus not t
>>> On 29.09.15 at 04:53, wrote:
Monday, September 28, 2015 2:47 PM, wrote:
>> >>> On 28.09.15 at 05:08, wrote:
>> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
>
>> It would be a guest kernel bug, but all _we_ care about is that such a guest
> kernel
>> bug won't affect th
>>> Monday, September 28, 2015 2:47 PM, wrote:
> >>> On 28.09.15 at 05:08, wrote:
> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
> It would be a guest kernel bug, but all _we_ care about is that such a guest
> kernel
> bug won't affect the hypervisor or other guests.
It won't a
>>> On 28.09.15 at 05:08, wrote:
Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
>> 7/13: I'm not convinced that making the vcpu spin calling
>> sched_yield() is a very good plan. Better to explicitly pause the domain if
>> you
>> need its vcpus not to run. But first -- why does I
Tim, thanks for your review.
>>> Thursday, September 24, 2015 12:27 AM, Tim Deegan wrote:
> Hi,
>
> At 14:09 + on 21 Sep (1442844587), Xu, Quan wrote:
> > George / Tim,
> > Could you help me review these memory patches? Thanks!
>
> The interrupt-mapping and chipset control parts of this are
Hi,
At 14:09 + on 21 Sep (1442844587), Xu, Quan wrote:
> George / Tim,
> Could you help me review these memory patches? Thanks!
The interrupt-mapping and chipset control parts of this are outside my
understanding. :) And I'm not an x86/mm maintainer any more, but I'll
have a look:
7/13: I'm
>>> On 21.09.15 at 16:03, wrote:
On 21.09.15 at 20:04, < jbeul...@suse.com > wrote:
>> >>> On 21.09.15 at 11:46, wrote:
>> >>> >>> On 21.09.15 at 16:51, < jbeul...@suse.com > wrote:
>> >>- Anything else?
>> >
>> >
>> > Just test the extreme case. The ATS specification mandates a timeout
>>
George / Tim,
Could you help me review these memory patches? Thanks!
-Quan
> -Original Message-
> From: Xu, Quan
> Sent: Wednesday, September 16, 2015 9:24 PM
> To: andrew.coop...@citrix.com; Dong, Eddie; ian.campb...@citrix.com;
> ian.jack...@eu.citrix.com; jbeul...@suse.com; Nakajima,
>>> On 21.09.15 at 20:04, < jbeul...@suse.com > wrote:
> >>> On 21.09.15 at 11:46, wrote:
> >>> >>> On 21.09.15 at 16:51, < jbeul...@suse.com > wrote:
> >>- Anything else?
> >
> >
> > Just test the extreme case. The ATS specification mandates a timeout
> > of 1 _minute_ for cache flush, even thou
>>> On 21.09.15 at 11:46, wrote:
>>> >>> On 21.09.15 at 16:51, < jbeul...@suse.com > wrote:
>>- Anything else?
>
>
> Just test the extreme case. The ATS specification mandates a timeout of 1
> _minute_ for cache flush, even though it doesn't take so much time for cache
> flush.
> In my design,
Thanks Jan.
>> >>> On 21.09.15 at 16:51, < jbeul...@suse.com > wrote:
>>> On 17.09.15 at 05:26, wrote:
> Much more information:
>If I run a service in this domain and tested this waitqueue case.
> The domain is still working after 60s, but It prints out Call Trace with
> $dmesg:
>
> [ 161
>>> On 17.09.15 at 05:26, wrote:
> Much more information:
>If I run a service in this domain and tested this waitqueue case. The
> domain is still working after 60s, but It prints out Call Trace with $dmesg:
>
> [ 161.978599] BUG: soft lockup - CPU#0 stuck for 57s! [kworker/0:1:272]
Not su
Julien Grall writes ("Re: [Xen-devel] [Patch RFC 00/13] VT-d Asynchronous
Device-TLB Flush for ATS Device"):
> On 16/09/2015 14:47, Ian Jackson wrote:
> > I don't consider myself qualified to review that. I think the
> > MAINTAINERS file should have an entry f
On 16/09/2015 14:47, Ian Jackson wrote:
Julien Grall writes ("Re: [Xen-devel] [Patch RFC 00/13] VT-d Asynchronous Device-TLB
Flush for ATS Device"):
On 16/09/15 11:46, Ian Jackson wrote:
JOOI why did you CC me ? I did a quick scan of these patches and they
don't seem to
> -Original Message-
> From: Xu, Quan
> Sent: Wednesday, September 16, 2015 9:24 PM
> To: andrew.coop...@citrix.com; Dong, Eddie; ian.campb...@citrix.com;
> ian.jack...@eu.citrix.com; jbeul...@suse.com; Nakajima, Jun; k...@xen.org;
> Tian, Kevin; t...@xen.org; Zhang, Yang Z; george.dun...
Julien Grall writes ("Re: [Xen-devel] [Patch RFC 00/13] VT-d Asynchronous
Device-TLB Flush for ATS Device"):
> On 16/09/15 11:46, Ian Jackson wrote:
> > JOOI why did you CC me ? I did a quick scan of these patches and they
> > don't seem to have any tools impact.
> -Original Message-
> From: Ian Jackson [mailto:ian.jack...@eu.citrix.com]
> Sent: Wednesday, September 16, 2015 6:47 PM
> To: Xu, Quan
> Cc: andrew.coop...@citrix.com; Dong, Eddie; ian.campb...@citrix.com;
> ian.jack...@eu.citrix.com; jbeul...@suse.com; Nakajima, Jun; k...@xen.org;
> Ti
On 16/09/15 11:46, Ian Jackson wrote:
> Quan Xu writes ("[Patch RFC 00/13] VT-d Asynchronous Device-TLB Flush for ATS
> Device"):
>> Introduction
>>
>
> Thanks for your submission.
>
> JOOI why did you CC me ? I did a quick scan of these patches and they
> don't seem to have any to
Quan Xu writes ("[Patch RFC 00/13] VT-d Asynchronous Device-TLB Flush for ATS
Device"):
> Introduction
>
Thanks for your submission.
JOOI why did you CC me ? I did a quick scan of these patches and they
don't seem to have any tools impact. I would prefer not to be CC'd
unless ther
Introduction
VT-d code currently has a number of cases where completion of certain
operations
is being waited for by way of spinning. The majority of instances use that
variable
indirectly through IOMMU_WAIT_OP() macro , allowing for loops of up to 1 second
(DMAR_OPERATION_TIMEOU
51 matches
Mail list logo