All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: "Tian, Kevin" <kevin.tian@intel.com>,
	Joerg Roedel <joro@8bytes.org>, Jason Gunthorpe <jgg@nvidia.com>,
	Christoph Hellwig <hch@infradead.org>,
	"Raj, Ashok" <ashok.raj@intel.com>, Will Deacon <will@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	"Pan, Jacob jun" <jacob.jun.pan@intel.com>
Subject: Re: [PATCH RFC v3 08/12] iommu/sva: Use attach/detach_pasid_dev in SVA interfaces
Date: Wed, 13 Apr 2022 19:57:33 +0800	[thread overview]
Message-ID: <c92d014a-9332-27d2-688b-48fc07efdebb@linux.intel.com> (raw)
In-Reply-To: <BN9PR11MB5276BE861CF22DDC11D9D8038CED9@BN9PR11MB5276.namprd11.prod.outlook.com>

On 2022/4/13 7:36, Tian, Kevin wrote:
>> From: Lu Baolu <baolu.lu@linux.intel.com>
>> Sent: Tuesday, April 12, 2022 8:53 PM
>>
>>>
>>>> +	if (!handle) {
>>>> +		ret = -ENOMEM;
>>>> +		goto out_put_ioas;
>>>> +	}
>>>> +
>>>> +	/* The reference to ioas will be kept until domain free. */
>>>> +	domain = iommu_sva_alloc_domain(dev, ioas);
>>>
>>> Shouldn't we first try whether existing domains are compatible to this
>>> device?
>>
>> If we think that here domain represents a hardware pagetable actually
>> used by IOMMU for a {device, pasid}, we are able to use per-{device,
>> pasid} domain without checking compatibility. Sharing a domain among
>> devices under the same IOMMU may be an optimization. That could be done
>> in the IOMMU driver just like what vt-d driver is doing for pass-through
>> DMA domains.
>>
> 
> there is only one hardware page table per mm in this case. Multiple domains
> are required only due to compatibility reason as Jason/Robin pointed out
> in SMMU case. Given all other places create multiple domains per ioas only
> upon incompatibility, probably it's more consistent to doing so in this path
> too...

Sharing domain for compatible devices is valuable when the domain
supports map/unmap operations. That can reduce the number of map/unmap
calls and the resulting synchronization of IOTLB. But for SVA case, it's
a dumb domain which only provides attach/detach operations.

A similar case could be found on pass-through DMA domains. The iommu
core allocates a default domain for each group although all the domains
represent a same page table for the compatible devices. The VT-d driver
optimizes this by exporting a static identity domain.

Anyway, I am open for this. I can add a compatible domain list if most
of you like that way. :-)

Best regards,
baolu
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Lu Baolu <baolu.lu@linux.intel.com>
To: "Tian, Kevin" <kevin.tian@intel.com>,
	Joerg Roedel <joro@8bytes.org>, Jason Gunthorpe <jgg@nvidia.com>,
	Christoph Hellwig <hch@infradead.org>,
	"Raj, Ashok" <ashok.raj@intel.com>, Will Deacon <will@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.com>
Cc: baolu.lu@linux.intel.com, Eric Auger <eric.auger@redhat.com>,
	"Liu, Yi L" <yi.l.liu@intel.com>,
	"Pan, Jacob jun" <jacob.jun.pan@intel.com>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH RFC v3 08/12] iommu/sva: Use attach/detach_pasid_dev in SVA interfaces
Date: Wed, 13 Apr 2022 19:57:33 +0800	[thread overview]
Message-ID: <c92d014a-9332-27d2-688b-48fc07efdebb@linux.intel.com> (raw)
In-Reply-To: <BN9PR11MB5276BE861CF22DDC11D9D8038CED9@BN9PR11MB5276.namprd11.prod.outlook.com>

On 2022/4/13 7:36, Tian, Kevin wrote:
>> From: Lu Baolu <baolu.lu@linux.intel.com>
>> Sent: Tuesday, April 12, 2022 8:53 PM
>>
>>>
>>>> +	if (!handle) {
>>>> +		ret = -ENOMEM;
>>>> +		goto out_put_ioas;
>>>> +	}
>>>> +
>>>> +	/* The reference to ioas will be kept until domain free. */
>>>> +	domain = iommu_sva_alloc_domain(dev, ioas);
>>>
>>> Shouldn't we first try whether existing domains are compatible to this
>>> device?
>>
>> If we think that here domain represents a hardware pagetable actually
>> used by IOMMU for a {device, pasid}, we are able to use per-{device,
>> pasid} domain without checking compatibility. Sharing a domain among
>> devices under the same IOMMU may be an optimization. That could be done
>> in the IOMMU driver just like what vt-d driver is doing for pass-through
>> DMA domains.
>>
> 
> there is only one hardware page table per mm in this case. Multiple domains
> are required only due to compatibility reason as Jason/Robin pointed out
> in SMMU case. Given all other places create multiple domains per ioas only
> upon incompatibility, probably it's more consistent to doing so in this path
> too...

Sharing domain for compatible devices is valuable when the domain
supports map/unmap operations. That can reduce the number of map/unmap
calls and the resulting synchronization of IOTLB. But for SVA case, it's
a dumb domain which only provides attach/detach operations.

A similar case could be found on pass-through DMA domains. The iommu
core allocates a default domain for each group although all the domains
represent a same page table for the compatible devices. The VT-d driver
optimizes this by exporting a static identity domain.

Anyway, I am open for this. I can add a compatible domain list if most
of you like that way. :-)

Best regards,
baolu

  reply	other threads:[~2022-04-13 11:57 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-10 10:24 [PATCH RFC v3 00/12] iommu: SVA and IOPF refactoring Lu Baolu
2022-04-10 10:24 ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 01/12] iommu: Add pasid_bits field in struct dev_iommu Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 02/12] iommu: Add a flag to indicate immutable singleton group Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-12  3:15   ` Tian, Kevin
2022-04-12  3:15     ` Tian, Kevin
2022-04-12  5:08     ` Lu Baolu
2022-04-12  5:08       ` Lu Baolu
2022-04-12  6:34       ` Yi Liu
2022-04-12  6:34         ` Yi Liu
2022-04-12 11:56         ` Lu Baolu
2022-04-12 11:56           ` Lu Baolu
2022-04-12  7:37       ` Tian, Kevin
2022-04-12  7:37         ` Tian, Kevin
2022-04-12 13:02         ` Lu Baolu
2022-04-12 13:02           ` Lu Baolu
2022-04-12 23:32           ` Tian, Kevin
2022-04-12 23:32             ` Tian, Kevin
2022-04-13 12:02             ` Lu Baolu
2022-04-13 12:02               ` Lu Baolu
2022-04-12  7:39   ` Tian, Kevin
2022-04-12  7:39     ` Tian, Kevin
2022-04-12 13:10     ` Lu Baolu
2022-04-12 13:10       ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 03/12] iommu: Add attach/detach_dev_pasid domain ops Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 04/12] iommu/sva: Basic data structures for SVA Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-12  6:49   ` Tian, Kevin
2022-04-12  6:49     ` Tian, Kevin
2022-04-12 11:58     ` Lu Baolu
2022-04-12 11:58       ` Lu Baolu
2022-04-12  6:56   ` Tian, Kevin
2022-04-12  6:56     ` Tian, Kevin
2022-04-12 12:08     ` Lu Baolu
2022-04-12 12:08       ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 05/12] iommu/vt-d: Remove SVM_FLAG_SUPERVISOR_MODE support Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 06/12] iommu/vt-d: Add SVA domain support Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 07/12] arm-smmu-v3/sva: " Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 08/12] iommu/sva: Use attach/detach_pasid_dev in SVA interfaces Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-12  7:19   ` Tian, Kevin
2022-04-12  7:19     ` Tian, Kevin
2022-04-12 12:53     ` Lu Baolu
2022-04-12 12:53       ` Lu Baolu
2022-04-12 23:36       ` Tian, Kevin
2022-04-12 23:36         ` Tian, Kevin
2022-04-13 11:57         ` Lu Baolu [this message]
2022-04-13 11:57           ` Lu Baolu
2022-04-14  3:44           ` Tian, Kevin
2022-04-14  3:44             ` Tian, Kevin
2022-04-10 10:24 ` [PATCH RFC v3 09/12] iommu: Remove SVA related callbacks from iommu ops Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 10/12] iommu: Prepare IOMMU domain for IOPF Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 11/12] iommu: Per-domain I/O page fault handling Lu Baolu
2022-04-10 10:24   ` Lu Baolu
2022-04-10 10:24 ` [PATCH RFC v3 12/12] iommu: Rename iommu-sva-lib.{c,h} Lu Baolu
2022-04-10 10:24   ` Lu Baolu

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=c92d014a-9332-27d2-688b-48fc07efdebb@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=ashok.raj@intel.com \
    --cc=hch@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@intel.com \
    --cc=jean-philippe@linaro.com \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=will@kernel.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.