xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Marc Zyngier <marc.zyngier@arm.com>
To: Ian Campbell <ian.campbell@citrix.com>,
	Julien Grall <julien.grall@citrix.com>
Cc: Michal Marek <mmarek@suse.cz>,
	"vijay.kilari@gmail.com" <vijay.kilari@gmail.com>,
	Stefano Stabellini <Stefano.Stabellini@eu.citrix.com>,
	"manish.jaggi@caviumnetworks.com"
	<manish.jaggi@caviumnetworks.com>, "tim@xen.org" <tim@xen.org>,
	"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>,
	"stefano.stabellini@citrix.com" <stefano.stabellini@citrix.com>,
	Vijaya Kumar K <Vijaya.Kumar@caviumnetworks.com>
Subject: Re: [PATCH v5 20/22] xen/arm: ITS: Map ITS translation space
Date: Wed, 02 Sep 2015 16:59:16 +0100	[thread overview]
Message-ID: <55E71CD4.3090306@arm.com> (raw)
In-Reply-To: <1441208717.26292.258.camel@citrix.com>

On 02/09/15 16:45, Ian Campbell wrote:
> On Tue, 2015-08-18 at 23:37 +0100, Marc Zyngier wrote:
>> On Tue, 18 Aug 2015 20:14:43 +0100 Julien Grall <julien.grall@citrix.com> wrote:
>>
>>> Marc pointed me today that if the processor is writing into 
>>> GITS_TRANSLATER it may be able to deadlock the system.
>>>
>>> Reading more closely the spec (8.1.3 IHI0069A), there is undefined 
>>> behavior when writing to this register with wrong access size.
>>>
>>> Currently the page table are shared between the processor and the SMMU, 
>>>
>>> so that means that a domain will be able to deadlock the processor and 
>>> therefore the whole platform.
>>
>> Indeed. A CPU should *never* be able to write to the GITS_TRANSLATER
>> register. What would be the meaning anyway? How would a DeviceID be
>> sampled? This is definitely UNPREDICTIBLE territory, and you want to
>> make sure a guest cannot directly write to the HW.
>>
>>> So we should never expose GITS_TRANSLATER into the processor page 
>>> table. 
>>> Which means unsharing some parts if not all of the page tables between 
>>> the processor and the SMMU.
>>
>> Agreed. It looks to me like the CPU should only see the the virtual
>> ITS, and nothing else.
> 
> It's rather unfortunate that using an ITS therefore precludes sharing stage
> -2 page tables between MMU and SMMU, which it seems otherwise the
> architecture designers have tried hard to allow.
> 
> Do you know if this will be fixed in some future revision (although given
> we now need to have the functionality anyway I'm not sure it help more than
>  saving a few pages of memory :-()

I don't have any idea if something is being worked on to address this,
but I think you may be able to share at least the page tables describing
the memory, which should really be the bulk of the page tables.

	M.
-- 
Jazz is not dead. It just smells funny...

  reply	other threads:[~2015-09-02 15:59 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-27 11:11 [PATCH v5 00/22] Add ITS support vijay.kilari
2015-07-27 11:11 ` [PATCH v5 01/22] xen/arm: Return success if dt node does not have irq mapping vijay.kilari
2015-07-28 13:13   ` Julien Grall
2015-07-28 13:23     ` Ian Campbell
2015-07-28 13:27       ` Julien Grall
2015-09-02 15:25   ` Ian Campbell
2015-07-27 11:11 ` [PATCH v5 02/22] xen/arm: Add bitmap_find_next_zero_area helper function vijay.kilari
2015-08-11 13:53   ` Jan Beulich
2015-07-27 11:11 ` [PATCH v5 03/22] xen: Add log2 functionality vijay.kilari
2015-07-27 11:11 ` [PATCH v5 04/22] xen/arm: Set nr_cpu_ids to available number of cpus vijay.kilari
2015-07-28 13:21   ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 05/22] xen/arm: ITS: Port ITS driver to Xen vijay.kilari
2015-07-28 16:46   ` Julien Grall
2015-07-29 15:22     ` Vijay Kilari
2015-07-29 16:06       ` Ian Campbell
2015-07-29 16:18         ` Vijay Kilari
2015-07-31 10:28     ` Vijay Kilari
2015-07-31 11:10       ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 06/22] xen/arm: ITS: Add helper functions to manage its_devices vijay.kilari
2015-07-27 11:11 ` [PATCH v5 07/22] xen/arm: ITS: Add virtual ITS driver vijay.kilari
2015-07-28 17:13   ` Julien Grall
2015-07-31  6:49     ` Vijay Kilari
2015-07-31 10:14       ` Julien Grall
2015-07-31 10:32         ` Ian Campbell
2015-07-27 11:11 ` [PATCH v5 08/22] xen/arm: ITS: Add virtual ITS commands support vijay.kilari
2015-07-28 18:04   ` Julien Grall
2015-07-31  6:57     ` Vijay Kilari
2015-07-31 10:16       ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 09/22] xen/arm: ITS: Export ITS info to Virtual ITS vijay.kilari
2015-07-28 18:14   ` Julien Grall
2015-07-31  7:01     ` Vijay Kilari
2015-08-03 15:58       ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 10/22] xen/arm: ITS: Add GITS registers emulation vijay.kilari
2015-07-28 19:01   ` Julien Grall
2015-07-31  7:25     ` Vijay Kilari
2015-07-31 10:28       ` Julien Grall
2015-08-01  8:50     ` Vijay Kilari
2015-08-03 11:19       ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 11/22] xen/arm: ITS: Enable physical and virtual ITS driver compilation vijay.kilari
2015-07-27 11:11 ` [PATCH v5 12/22] xen/arm: ITS: Add GICR register emulation vijay.kilari
2015-07-30 17:04   ` Julien Grall
2015-07-31  9:08     ` Vijay Kilari
2015-07-31 11:05       ` Julien Grall
2015-08-01 10:25         ` Vijay Kilari
2015-08-01 15:51           ` Julien Grall
2015-08-03  9:36             ` Vijay Kilari
2015-08-03 13:01               ` Julien Grall
2015-08-03 13:51                 ` Vijay Kilari
2015-08-03 13:58                   ` Julien Grall
2015-08-04  6:55                     ` Vijay Kilari
2015-08-04  8:44                       ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 13/22] xen/arm: ITS: Implement gic_is_lpi helper function vijay.kilari
2015-07-30 17:14   ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 14/22] xen/arm: ITS: Allocate irq descriptors for LPIs vijay.kilari
2015-08-04 13:21   ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 15/22] xen/arm: ITS: implement hw_irq_controller " vijay.kilari
2015-08-04 13:45   ` Julien Grall
2015-08-06  8:15     ` Vijay Kilari
2015-08-06 10:05       ` Julien Grall
2015-08-06 10:11         ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 16/22] xen/arm: ITS: Route LPIs vijay.kilari
2015-08-04 14:54   ` Julien Grall
2015-07-27 11:11 ` [PATCH v5 17/22] xen/arm: ITS: Initialize physical ITS vijay.kilari
2015-08-17 19:00   ` Julien Grall
2015-07-27 11:12 ` [PATCH v5 18/22] xen/arm: ITS: Add domain specific ITS initialization vijay.kilari
2015-08-17 18:57   ` Julien Grall
2015-07-27 11:12 ` [PATCH v5 19/22] xen/arm: ITS: Add APIs to add and assign device vijay.kilari
2015-08-17 19:17   ` Julien Grall
2015-07-27 11:12 ` [PATCH v5 20/22] xen/arm: ITS: Map ITS translation space vijay.kilari
2015-08-17 19:20   ` Julien Grall
2015-08-18 19:14   ` Julien Grall
2015-08-18 22:37     ` Marc Zyngier
2015-09-02 15:45       ` Ian Campbell
2015-09-02 15:59         ` Marc Zyngier [this message]
2015-07-27 11:12 ` [PATCH v5 21/22] xen/arm: ITS: Generate ITS node for Dom0 vijay.kilari
2015-08-17 19:41   ` Julien Grall
2015-08-21 23:02     ` Vijay Kilari
2015-08-21 23:48       ` Julien Grall
2015-08-26 12:40     ` Vijay Kilari
2015-08-27  0:02       ` Julien Grall
2015-07-27 11:12 ` [PATCH v5 22/22] xen/arm: ITS: Add pci devices in ThunderX vijay.kilari

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=55E71CD4.3090306@arm.com \
    --to=marc.zyngier@arm.com \
    --cc=Stefano.Stabellini@eu.citrix.com \
    --cc=Vijaya.Kumar@caviumnetworks.com \
    --cc=ian.campbell@citrix.com \
    --cc=julien.grall@citrix.com \
    --cc=manish.jaggi@caviumnetworks.com \
    --cc=mmarek@suse.cz \
    --cc=stefano.stabellini@citrix.com \
    --cc=tim@xen.org \
    --cc=vijay.kilari@gmail.com \
    --cc=xen-devel@lists.xen.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).