From: "Jan Beulich" <JBeulich@suse.com>
To: Paul Durrant <paul.durrant@citrix.com>
Cc: Kevin Tian <kevin.tian@intel.com>,
Stefano Stabellini <sstabellini@kernel.org>,
Wei Liu <wei.liu2@citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Julien Grall <julien.grall@arm.com>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
xen-devel <xen-devel@lists.xenproject.org>,
Brian Woods <brian.woods@amd.com>,
Roger Pau Monne <roger.pau@citrix.com>
Subject: Re: [PATCH 3/5] iommu: move iommu_get_ops() into common code
Date: Wed, 15 May 2019 00:32:51 -0600 [thread overview]
Message-ID: <5CDBB293020000780022F118@prv1-mh.provo.novell.com> (raw)
In-Reply-To: <246a87e654194e5082852b63853415d6@AMSPEX02CL03.citrite.net>
>>> On 14.05.19 at 18:19, <Paul.Durrant@citrix.com> wrote:
>> -----Original Message-----
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 13 May 2019 09:11
>> To: Paul Durrant <Paul.Durrant@citrix.com>
>> Cc: Brian Woods <brian.woods@amd.com>; Suravee Suthikulpanit
> <suravee.suthikulpanit@amd.com>; Julien
>> Grall <julien.grall@arm.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>; Roger
> Pau Monne
>> <roger.pau@citrix.com>; Wei Liu <wei.liu2@citrix.com>; Kevin Tian
> <kevin.tian@intel.com>; Stefano
>> Stabellini <sstabellini@kernel.org>; xen-devel <xen-devel@lists.xenproject.org>
>> Subject: Re: [PATCH 3/5] iommu: move iommu_get_ops() into common code
>>
>> >>> On 08.05.19 at 15:24, <paul.durrant@citrix.com> wrote:
>> > Currently x86 and ARM differ in their implementation for no good reason.
>> > This patch moves the ARM variant of iommu_get/set_ops() helpers into
>> > common code and modifies them so they deal with the __initconstrel
>> > ops structures used by the x86 IOMMU vendor implementations (adding
>> > __initconstrel to the SMMU code to bring it in line). Consequently, a lack
>> > of init() method is now taken to mean uninitialized iommu_ops. Also, the
>> > printk warning in iommu_set_ops() now becomes an ASSERT.
>>
>> When having submitted the indirect call overhead reduction series
>> including IOMMU changes for the first time, I was told that the Arm
>> folks would like to retain the ability to eventually support
>> heterogeneous IOMMUs (and hence I shouldn't provide patching
>> infrastructure there). A single global iommu_[gs]et_ops() is sort of
>> getting in the way of this as well, I think, and hence I'm not sure it
>> is a desirable step to make this so far Arm-specific arrangement
>> the general model. At least it would further complicate Arm side
>> changes towards that (mid / long term?) goal.
>>
>
> Ok. Do you have any more information on what such an architecture would look
> like? I guess it is also conceivable that an x86 architecture might have
> slightly different IOMMU implementations (or at least quirks) for different
> PCI segments. So perhaps a global ops structure is not a good idea in the
> long run.
Different quirks could likely be handled with a global ops instance.
The indirect call overhead elimination alone will imo make it
undesirable to switch to a non-global-ops model on x86, unless
there's a strong reason (like truly different IOMMUs in a single
system).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
WARNING: multiple messages have this Message-ID (diff)
From: "Jan Beulich" <JBeulich@suse.com>
To: "Paul Durrant" <paul.durrant@citrix.com>
Cc: Kevin Tian <kevin.tian@intel.com>,
Stefano Stabellini <sstabellini@kernel.org>,
Wei Liu <wei.liu2@citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Julien Grall <julien.grall@arm.com>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
xen-devel <xen-devel@lists.xenproject.org>,
Brian Woods <brian.woods@amd.com>,
Roger Pau Monne <roger.pau@citrix.com>
Subject: Re: [Xen-devel] [PATCH 3/5] iommu: move iommu_get_ops() into common code
Date: Wed, 15 May 2019 00:32:51 -0600 [thread overview]
Message-ID: <5CDBB293020000780022F118@prv1-mh.provo.novell.com> (raw)
Message-ID: <20190515063251.ijn2_wIg5nG2BPrixAoQWuZ83TqTHpr83tIuXVa-P8A@z> (raw)
In-Reply-To: <246a87e654194e5082852b63853415d6@AMSPEX02CL03.citrite.net>
>>> On 14.05.19 at 18:19, <Paul.Durrant@citrix.com> wrote:
>> -----Original Message-----
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 13 May 2019 09:11
>> To: Paul Durrant <Paul.Durrant@citrix.com>
>> Cc: Brian Woods <brian.woods@amd.com>; Suravee Suthikulpanit
> <suravee.suthikulpanit@amd.com>; Julien
>> Grall <julien.grall@arm.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>; Roger
> Pau Monne
>> <roger.pau@citrix.com>; Wei Liu <wei.liu2@citrix.com>; Kevin Tian
> <kevin.tian@intel.com>; Stefano
>> Stabellini <sstabellini@kernel.org>; xen-devel <xen-devel@lists.xenproject.org>
>> Subject: Re: [PATCH 3/5] iommu: move iommu_get_ops() into common code
>>
>> >>> On 08.05.19 at 15:24, <paul.durrant@citrix.com> wrote:
>> > Currently x86 and ARM differ in their implementation for no good reason.
>> > This patch moves the ARM variant of iommu_get/set_ops() helpers into
>> > common code and modifies them so they deal with the __initconstrel
>> > ops structures used by the x86 IOMMU vendor implementations (adding
>> > __initconstrel to the SMMU code to bring it in line). Consequently, a lack
>> > of init() method is now taken to mean uninitialized iommu_ops. Also, the
>> > printk warning in iommu_set_ops() now becomes an ASSERT.
>>
>> When having submitted the indirect call overhead reduction series
>> including IOMMU changes for the first time, I was told that the Arm
>> folks would like to retain the ability to eventually support
>> heterogeneous IOMMUs (and hence I shouldn't provide patching
>> infrastructure there). A single global iommu_[gs]et_ops() is sort of
>> getting in the way of this as well, I think, and hence I'm not sure it
>> is a desirable step to make this so far Arm-specific arrangement
>> the general model. At least it would further complicate Arm side
>> changes towards that (mid / long term?) goal.
>>
>
> Ok. Do you have any more information on what such an architecture would look
> like? I guess it is also conceivable that an x86 architecture might have
> slightly different IOMMU implementations (or at least quirks) for different
> PCI segments. So perhaps a global ops structure is not a good idea in the
> long run.
Different quirks could likely be handled with a global ops instance.
The indirect call overhead elimination alone will imo make it
undesirable to switch to a non-global-ops model on x86, unless
there's a strong reason (like truly different IOMMUs in a single
system).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2019-05-15 6:32 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-08 13:23 [PATCH 0/5] iommu groups + cleanup Paul Durrant
2019-05-08 13:23 ` [Xen-devel] " Paul Durrant
2019-05-08 13:23 ` [PATCH 1/5] iommu: trivial re-organisation to avoid unnecessary test Paul Durrant
2019-05-08 13:23 ` [Xen-devel] " Paul Durrant
2019-05-13 15:22 ` Jan Beulich
2019-05-13 15:22 ` [Xen-devel] " Jan Beulich
2019-05-08 13:24 ` [PATCH 2/5] iommu / x86: move call to scan_pci_devices() out of vendor code Paul Durrant
2019-05-08 13:24 ` [Xen-devel] " Paul Durrant
2019-05-13 15:35 ` Jan Beulich
2019-05-13 15:35 ` [Xen-devel] " Jan Beulich
2019-05-14 16:13 ` Paul Durrant
2019-05-14 16:13 ` [Xen-devel] " Paul Durrant
2019-05-15 6:29 ` Jan Beulich
2019-05-15 6:29 ` [Xen-devel] " Jan Beulich
2019-05-08 13:24 ` [PATCH 3/5] iommu: move iommu_get_ops() into common code Paul Durrant
2019-05-08 13:24 ` [Xen-devel] " Paul Durrant
2019-05-13 16:11 ` Jan Beulich
2019-05-13 16:11 ` [Xen-devel] " Jan Beulich
2019-05-14 16:19 ` Paul Durrant
2019-05-14 16:19 ` [Xen-devel] " Paul Durrant
2019-05-14 21:36 ` Julien Grall
2019-05-14 21:36 ` [Xen-devel] " Julien Grall
2019-05-15 6:32 ` Jan Beulich [this message]
2019-05-15 6:32 ` Jan Beulich
2019-05-08 13:24 ` [PATCH 4/5] iommu: introduce iommu_groups Paul Durrant
2019-05-08 13:24 ` [Xen-devel] " Paul Durrant
2019-05-15 8:44 ` Roger Pau Monné
2019-05-15 8:44 ` [Xen-devel] " Roger Pau Monné
2019-05-31 13:48 ` Paul Durrant
2019-05-31 13:48 ` [Xen-devel] " Paul Durrant
2019-05-15 14:17 ` Jan Beulich
2019-05-15 14:17 ` [Xen-devel] " Jan Beulich
2019-05-31 13:55 ` Paul Durrant
2019-05-31 13:55 ` [Xen-devel] " Paul Durrant
2019-05-31 14:13 ` Jan Beulich
2019-05-31 14:13 ` [Xen-devel] " Jan Beulich
2019-05-31 14:21 ` Paul Durrant
2019-05-31 14:21 ` [Xen-devel] " Paul Durrant
2019-05-15 14:24 ` Jan Beulich
2019-05-15 14:24 ` [Xen-devel] " Jan Beulich
2019-05-08 13:24 ` [PATCH 5/5] iommu / pci: re-implement XEN_DOMCTL_get_device_group Paul Durrant
2019-05-08 13:24 ` [Xen-devel] " Paul Durrant
2019-05-15 9:06 ` Roger Pau Monné
2019-05-15 9:06 ` [Xen-devel] " Roger Pau Monné
2019-06-03 9:58 ` Paul Durrant
2019-06-03 9:58 ` [Xen-devel] " Paul Durrant
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=5CDBB293020000780022F118@prv1-mh.provo.novell.com \
--to=jbeulich@suse.com \
--cc=andrew.cooper3@citrix.com \
--cc=brian.woods@amd.com \
--cc=julien.grall@arm.com \
--cc=kevin.tian@intel.com \
--cc=paul.durrant@citrix.com \
--cc=roger.pau@citrix.com \
--cc=sstabellini@kernel.org \
--cc=suravee.suthikulpanit@amd.com \
--cc=wei.liu2@citrix.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 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).