From: Tina Zhang <tina.zhang@intel.com>
To: "Tian, Kevin" <kevin.tian@intel.com>,
Jason Gunthorpe <jgg@ziepe.ca>,
"Lu Baolu" <baolu.lu@linux.intel.com>,
Michael Shavit <mshavit@google.com>
Cc: "iommu@lists.linux.dev" <iommu@lists.linux.dev>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/5] Share sva domains with all devices bound to a mm
Date: Thu, 10 Aug 2023 09:31:41 +0800 [thread overview]
Message-ID: <bfc2eb22-54af-dab8-72e3-a142470590c3@intel.com> (raw)
In-Reply-To: <BN9PR11MB527638E7361714F8AA5FD4448C12A@BN9PR11MB5276.namprd11.prod.outlook.com>
Hi,
On 8/9/23 17:41, Tian, Kevin wrote:
>> From: Zhang, Tina <tina.zhang@intel.com>
>> Sent: Tuesday, August 8, 2023 3:50 PM
>>
>> A sva domain's lifetime begins with binding a device to a mm and ends
>> by releasing all the bound devices from that sva domain. Technically,
>> there could be more than one sva domain identified by the mm PASID for
>> the use of bound devices issuing DMA transactions.
>
> Could you elaborate it with some concrete examples which motivate
> this change?
The motivation is to remove the superfluous IOTLB invalidation in
current VT-d driver.
Currently, in VT-d driver, due to lacking shared sva domain info, in
intel_flush_svm_range(), both iotlb and dev-tlb invalidation operations
are performed per-device. However, difference devices could be behind
one IOMMU (e.g., four devices are behind one IOMMU) and invoking iotlb
per-device gives us more iotlb invalidation than necessary (4 iotlb
invalidation instead of 1). This issue may give more performance impact
when in a virtual machine guest, as currently we have one virtual VT-d
for in front of those virtual devices.
This patch fixes this issue by attaching shared sva domain information
to mm, so that it can be utilized in the mm_notifier_ops callbacks.
Regards,
-Tina
>
>>
>> To support mm PASID 1:n with sva domains, each mm needs to keep both a
>> reference list of allocated sva domains and the corresponding PASID.
>> However, currently, mm struct only has one pasid field for sva usage,
>> which is used to keep the info of an assigned PASID. That pasid field
>> cannot provide sufficient info to build up the 1:n mapping between PASID
>> and sva domains.
>>
>> This patch-set fills the gap by adding an mm_iommu field[1], whose type is
>> mm_iommu_data struct, to replace the old pasid field. The introduced
>> mm_iommu_data struct keeps info of both a reference list of sva domains
>> and an assigned PASID.
>>
>>
>> [1]: https://lore.kernel.org/linux-iommu/ZIBxPd1%2FJCAle6yP@nvidia.com/
>>
>>
>> The RFC version of this patch-set is here:
>> https://lore.kernel.org/linux-iommu/20230707013441.365583-1-
>> tina.zhang@intel.com/
>>
>> Tina Zhang (5):
>> iommu: Add mm_get_pasid() helper function
>> iommu: Call helper function to get assigned pasid value
>> mm: Add structure to keep sva information
>> iommu: Support mm PASID 1:n with sva domains
>> mm: Deprecate pasid field
>>
>> arch/x86/kernel/traps.c | 2 +-
>> .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 12 ++---
>> drivers/iommu/intel/svm.c | 8 +--
>> drivers/iommu/iommu-sva.c | 50 ++++++++++++-------
>> include/linux/iommu.h | 19 +++++--
>> include/linux/mm_types.h | 3 +-
>> kernel/fork.c | 1 -
>> mm/init-mm.c | 3 --
>> 8 files changed, 58 insertions(+), 40 deletions(-)
>>
>> --
>> 2.17.1
>
next prev parent reply other threads:[~2023-08-10 1:32 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-08 7:49 Tina Zhang
2023-08-08 7:49 ` [PATCH 1/5] iommu: Add mm_get_pasid() helper function Tina Zhang
2023-08-08 15:02 ` Jason Gunthorpe
2023-08-09 0:31 ` Baolu Lu
2023-08-09 9:47 ` Tian, Kevin
2023-08-09 12:31 ` Jason Gunthorpe
2023-08-08 7:49 ` [PATCH 2/5] iommu: Call helper function to get assigned pasid value Tina Zhang
2023-08-09 0:21 ` Baolu Lu
2023-08-09 9:49 ` Tian, Kevin
2023-08-09 10:58 ` Baolu Lu
2023-08-09 14:48 ` Jason Gunthorpe
2023-08-10 1:37 ` Baolu Lu
2023-08-10 16:30 ` Jason Gunthorpe
2023-08-09 12:35 ` Jason Gunthorpe
2023-08-10 7:52 ` Tian, Kevin
2023-08-10 16:36 ` Jason Gunthorpe
2023-08-11 3:18 ` Tian, Kevin
2023-08-08 7:49 ` [PATCH 3/5] mm: Add structure to keep sva information Tina Zhang
2023-08-08 7:49 ` [PATCH 4/5] iommu: Support mm PASID 1:n with sva domains Tina Zhang
2023-08-08 15:12 ` Jason Gunthorpe
2023-08-08 15:19 ` Jason Gunthorpe
2023-08-10 2:14 ` Tina Zhang
2023-08-08 7:49 ` [PATCH 5/5] mm: Deprecate pasid field Tina Zhang
2023-08-09 0:18 ` [PATCH 0/5] Share sva domains with all devices bound to a mm Baolu Lu
2023-08-09 9:44 ` Tian, Kevin
2023-08-09 10:51 ` Baolu Lu
2023-08-11 1:06 ` Tina Zhang
2023-08-09 14:46 ` Jason Gunthorpe
2023-08-10 1:23 ` Baolu Lu
2023-08-10 7:44 ` Tian, Kevin
2023-08-09 9:41 ` Tian, Kevin
2023-08-10 1:31 ` Tina Zhang [this message]
2023-08-10 7:49 ` Tian, Kevin
2023-08-10 16:27 ` Jason Gunthorpe
2023-08-11 1:12 ` Tina Zhang
2023-08-11 1:07 ` Tina Zhang
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=bfc2eb22-54af-dab8-72e3-a142470590c3@intel.com \
--to=tina.zhang@intel.com \
--cc=baolu.lu@linux.intel.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@ziepe.ca \
--cc=kevin.tian@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mshavit@google.com \
/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
all inboxes | Powered by JetHome®