From: Julien Grall <julien.grall@arm.com>
To: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vijay Kilari <vijay.kilari@gmail.com>,
Andre Przywara <andre.przywara@arm.com>,
george.dunlap@citrix.com, jbeulich@suse.com,
andrew.cooper3@citrix.com, xen-devel@lists.xenproject.org,
nd@arm.com, Shanker Donthineni <shankerd@codeaurora.org>
Subject: Re: [PATCH v2 09/27] ARM: GICv3: introduce separate pending_irq structs for LPIs
Date: Mon, 27 Mar 2017 22:24:36 +0100 [thread overview]
Message-ID: <a76048c8-e8e5-ac0e-8387-a34c2a57c45b@arm.com> (raw)
In-Reply-To: <alpine.DEB.2.10.1703271102240.8001@sstabellini-ThinkPad-X260>
Hi Stefano,
On 27/03/2017 19:39, Stefano Stabellini wrote:
> On Mon, 27 Mar 2017, Julien Grall wrote:
>> For both guest could potentially flood us. It would take us a lot of time to
>> allocate/free memory for each vLPIs modified. Hence, why I didn't suggest it
>> and said: "One could argue that we could allocate on MAPTI to limit the
>> allocation...".
>
> Given that Xen wouldn't allocate the same pending_irq twice, at most Xen
> would allocate the same amount of memory and the same number of
> pending_irq that it would otherwise allocate if we did it at assignment
> time, right?
>
> Therefore, we are not concerned about memory utilization. We are
> concerned about the CPU time to do the allocation itself, right?
>
> However, the CPU time to run xmalloc/xfree should be small and in any
> case the scheduler has always the chance to deschedule the vcpu if it
> wants to. This is no different than issuing any of the hypercalls that
> require some work on the hypervisor side.
>
> I don't think we have reasons to be concerned. Any opinions?
Well, I have already said on the IRQ version but forgot to mention here.
How do you report error if xmalloc has failed? This could happen if
memory resource has been exhausted even for a well-behaved guest.
If you do the allocation on enable, this means on a memory trap, you
would have to inject a data abort to the guest. If you do on the MAPTI
command, it would be a SError with a IMPLEMENTATION DEFINED error code.
In both case the guest will likely not able interpret it and crash. This
could be a vector attack by exhausting the resource.
Furthermore, in the case of enable/disable vLPI solution, you can
disable an LPI that are still inflight. So you would not be able to free
here. Furthermore enable/disable can happen often if you want to mask
the interrupt temporarily (all MSI are edge-interrupt).
Lastly, in the case of MAPTI it is not possible to preempt the command
queue that can contain ~32K of commands. So we may have to do 32K of
xmalloc/xfree. Even one MAPTI is fast, likely 32K will be slow and
monopolize a pCPU for more than expected.
But can we focus on getting a sensible design which can be easily
extended and without any flaw? This already is quite a difficult tasks
with the ITS. Asking also for performance from the first draft is making
much worse.
If you recall, a lot of ARM subsystems (P2M, vGIC...) has been built in
multiple stage. Each stage improved the performance. It sounds quite
unfair to me to require the same level of performance as the current
vGIC just because the code was merged later one.
This is raising the bar to contribute on Xen on ARM very high and may
discourage someone to push something upstream.
To be clear, I do care about performance. But I think this has to come
in a second step when it is too complicate to address as a first step.
The first step is to be able to use Xen on the hardware without any flaw
and allowing us to extend the code easily.
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-03-27 21:24 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-16 11:20 [PATCH v2 00/27] arm64: Dom0 ITS emulation Andre Przywara
2017-03-16 11:20 ` [PATCH v2 01/27] ARM: GICv3 ITS: parse and store ITS subnodes from hardware DT Andre Przywara
2017-03-21 20:17 ` Julien Grall
2017-03-23 10:57 ` Andre Przywara
2017-03-23 17:32 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 02/27] ARM: GICv3: allocate LPI pending and property table Andre Przywara
2017-03-21 21:23 ` Julien Grall
2017-03-23 14:40 ` Andre Przywara
2017-03-23 17:42 ` Julien Grall
2017-03-23 17:45 ` Stefano Stabellini
2017-03-23 17:49 ` Julien Grall
2017-03-23 18:01 ` Stefano Stabellini
2017-03-23 18:21 ` Andre Przywara
2017-03-24 11:45 ` Julien Grall
2017-03-24 17:22 ` Stefano Stabellini
2017-03-21 22:57 ` Stefano Stabellini
2017-03-21 23:08 ` André Przywara
2017-03-21 23:27 ` Stefano Stabellini
2017-03-23 10:50 ` Andre Przywara
2017-03-23 17:47 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 03/27] ARM: GICv3 ITS: allocate device and collection table Andre Przywara
2017-03-21 23:29 ` Stefano Stabellini
2017-03-22 13:52 ` Julien Grall
2017-03-22 16:08 ` André Przywara
2017-03-22 16:33 ` Julien Grall
2017-03-29 13:58 ` Andre Przywara
2017-03-16 11:20 ` [PATCH v2 04/27] ARM: GICv3 ITS: map ITS command buffer Andre Przywara
2017-03-21 23:48 ` Stefano Stabellini
2017-03-22 15:23 ` Julien Grall
2017-03-22 16:31 ` André Przywara
2017-03-22 16:41 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 05/27] ARM: GICv3 ITS: introduce ITS command handling Andre Przywara
2017-03-16 15:05 ` Shanker Donthineni
2017-03-16 15:18 ` Andre Przywara
2017-03-22 0:02 ` Stefano Stabellini
2017-03-22 15:59 ` Julien Grall
2017-04-03 10:58 ` Andre Przywara
2017-04-03 11:23 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 06/27] ARM: GICv3 ITS: introduce device mapping Andre Przywara
2017-03-22 17:29 ` Julien Grall
2017-04-03 20:08 ` Andre Przywara
2017-04-03 20:41 ` Julien Grall
2017-04-04 9:57 ` Andre Przywara
2017-03-22 22:45 ` Stefano Stabellini
2017-04-03 19:45 ` Andre Przywara
2017-03-30 11:17 ` Vijay Kilari
2017-03-16 11:20 ` [PATCH v2 07/27] ARM: arm64: activate atomic 64-bit accessors Andre Przywara
2017-03-22 17:30 ` Julien Grall
2017-03-22 22:49 ` Stefano Stabellini
2017-03-16 11:20 ` [PATCH v2 08/27] ARM: GICv3 ITS: introduce host LPI array Andre Przywara
2017-03-22 23:38 ` Stefano Stabellini
2017-03-23 8:48 ` Julien Grall
2017-03-23 10:21 ` Andre Przywara
2017-03-23 17:52 ` Stefano Stabellini
2017-03-24 11:54 ` Julien Grall
2017-03-23 19:08 ` Julien Grall
2017-04-03 19:30 ` Andre Przywara
2017-04-03 20:13 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 09/27] ARM: GICv3: introduce separate pending_irq structs for LPIs Andre Przywara
2017-03-22 23:44 ` Stefano Stabellini
2017-03-23 20:08 ` André Przywara
2017-03-24 10:59 ` Julien Grall
2017-03-24 11:40 ` Julien Grall
2017-03-24 15:50 ` Andre Przywara
2017-03-24 16:19 ` Julien Grall
2017-03-24 17:26 ` Stefano Stabellini
2017-03-27 9:02 ` Andre Przywara
2017-03-27 14:01 ` Julien Grall
2017-03-27 17:44 ` Stefano Stabellini
2017-03-27 17:49 ` Julien Grall
2017-03-27 18:39 ` Stefano Stabellini
2017-03-27 21:24 ` Julien Grall [this message]
2017-03-28 7:58 ` Jan Beulich
2017-03-28 13:12 ` Julien Grall
2017-03-28 13:34 ` Jan Beulich
2017-03-16 11:20 ` [PATCH v2 10/27] ARM: GICv3: forward pending LPIs to guests Andre Przywara
2017-03-24 12:03 ` Julien Grall
2017-04-03 14:18 ` Andre Przywara
2017-04-04 11:49 ` Julien Grall
2017-04-04 12:51 ` Andre Przywara
2017-04-04 12:50 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 11/27] ARM: GICv3: enable ITS and LPIs on the host Andre Przywara
2017-03-16 11:20 ` [PATCH v2 12/27] ARM: vGICv3: handle virtual LPI pending and property tables Andre Przywara
2017-03-24 12:09 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 13/27] ARM: vGICv3: Handle disabled LPIs Andre Przywara
2017-03-24 12:20 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 14/27] ARM: vGICv3: introduce basic ITS emulation bits Andre Przywara
2017-03-16 16:25 ` Shanker Donthineni
2017-03-20 12:17 ` Vijay Kilari
2017-03-24 12:41 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 15/27] ARM: vITS: introduce translation table walks Andre Przywara
2017-03-24 13:00 ` Julien Grall
2017-04-03 18:25 ` Andre Przywara
2017-04-04 15:59 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 16/27] ARM: vITS: handle CLEAR command Andre Przywara
2017-03-24 14:27 ` Julien Grall
2017-03-24 15:53 ` Andre Przywara
2017-03-24 17:17 ` Stefano Stabellini
2017-03-27 8:44 ` Andre Przywara
2017-03-27 14:12 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 17/27] ARM: vITS: handle INT command Andre Przywara
2017-03-24 14:38 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 18/27] ARM: vITS: handle MAPC command Andre Przywara
2017-03-16 11:20 ` [PATCH v2 19/27] ARM: vITS: handle MAPD command Andre Przywara
2017-03-24 14:41 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 20/27] ARM: vITS: handle MAPTI command Andre Przywara
2017-03-24 14:54 ` Julien Grall
2017-04-03 18:47 ` Andre Przywara
2017-03-16 11:20 ` [PATCH v2 21/27] ARM: vITS: handle MOVI command Andre Przywara
2017-03-24 15:00 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 22/27] ARM: vITS: handle DISCARD command Andre Przywara
2017-03-16 11:20 ` [PATCH v2 23/27] ARM: vITS: handle INV command Andre Przywara
2017-03-16 11:20 ` [PATCH v2 24/27] ARM: vITS: handle INVALL command Andre Przywara
2017-03-24 15:12 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 25/27] ARM: vITS: create and initialize virtual ITSes for Dom0 Andre Przywara
2017-03-24 15:18 ` Julien Grall
2017-03-16 11:20 ` [PATCH v2 26/27] ARM: vITS: create ITS subnodes for Dom0 DT Andre Przywara
2017-03-16 11:20 ` [PATCH v2 27/27] ARM: vGIC: advertise LPI support Andre Przywara
2017-03-24 15:25 ` Julien Grall
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=a76048c8-e8e5-ac0e-8387-a34c2a57c45b@arm.com \
--to=julien.grall@arm.com \
--cc=andre.przywara@arm.com \
--cc=andrew.cooper3@citrix.com \
--cc=george.dunlap@citrix.com \
--cc=jbeulich@suse.com \
--cc=nd@arm.com \
--cc=shankerd@codeaurora.org \
--cc=sstabellini@kernel.org \
--cc=vijay.kilari@gmail.com \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.