From: Jason Gunthorpe <jgg@nvidia.com>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Robin Murphy <robin.murphy@arm.com>,
iommu@lists.linux-foundation.org,
LKML <linux-kernel@vger.kernel.org>,
Joerg Roedel <joro@8bytes.org>,
Christoph Hellwig <hch@infradead.org>,
Lu Baolu <baolu.lu@linux.intel.com>,
Jean-Philippe Brucker <jean-philippe@linaro.com>,
"Tian, Kevin" <kevin.tian@intel.com>,
Tony Luck <tony.luck@intel.com>,
Dave Jiang <dave.jiang@intel.com>,
Raj Ashok <ashok.raj@intel.com>,
"Zanussi, Tom" <tom.zanussi@intel.com>,
"Kumar, Sanjay K" <sanjay.k.kumar@intel.com>,
Jacob Pan <jacob.jun.pan@intel.com>,
Dan Williams <dan.j.williams@intel.com>
Subject: Re: [PATCH v2 5/8] iommu: Add PASID support for DMA mapping API users
Date: Tue, 15 Mar 2022 14:05:07 -0300 [thread overview]
Message-ID: <20220315170507.GH11336@nvidia.com> (raw)
In-Reply-To: <20220315093135.5c11066d@jacob-builder>
On Tue, Mar 15, 2022 at 09:31:35AM -0700, Jacob Pan wrote:
> > IMHO it is a device mis-design of IDXD to require all DMA be PASID
> > tagged. Devices should be able to do DMA on their RID when the PCI
> IDXD can do DMA w/ RID, the PASID requirement is only for shared WQ where
> ENQCMDS is used. ENQCMDS has the benefit of avoiding locking where work
> submission is done from multiple CPUs.
> Tony, Dave?
This is what I mean, it has an operating mode you want to use from the
kernel driver that cannot do RID DMA. It is a HW mis-design, IMHO.
Something like PASID0 in the ENQCMDS should have triggered RID DMA.
> > In any case I think we are better to wait for an actual user for multi
> > DMA API iommu_domains to come forward before we try to build an API
> > for it.
>
> What would you recommend in the interim?
Oh, I mean this approach at a high level is fine - I was saying we
shouldn't try to broaden it like Robin was suggesting without a driver
that needs multiple iommu_domains for the DMA API.
Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe via iommu <iommu@lists.linux-foundation.org>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: "Tian, Kevin" <kevin.tian@intel.com>,
Tony Luck <tony.luck@intel.com>,
Dave Jiang <dave.jiang@intel.com>,
Raj Ashok <ashok.raj@intel.com>,
Jean-Philippe Brucker <jean-philippe@linaro.com>,
"Kumar, Sanjay K" <sanjay.k.kumar@intel.com>,
LKML <linux-kernel@vger.kernel.org>,
Christoph Hellwig <hch@infradead.org>,
iommu@lists.linux-foundation.org,
Jacob Pan <jacob.jun.pan@intel.com>,
"Zanussi, Tom" <tom.zanussi@intel.com>,
Dan Williams <dan.j.williams@intel.com>,
Robin Murphy <robin.murphy@arm.com>
Subject: Re: [PATCH v2 5/8] iommu: Add PASID support for DMA mapping API users
Date: Tue, 15 Mar 2022 14:05:07 -0300 [thread overview]
Message-ID: <20220315170507.GH11336@nvidia.com> (raw)
In-Reply-To: <20220315093135.5c11066d@jacob-builder>
On Tue, Mar 15, 2022 at 09:31:35AM -0700, Jacob Pan wrote:
> > IMHO it is a device mis-design of IDXD to require all DMA be PASID
> > tagged. Devices should be able to do DMA on their RID when the PCI
> IDXD can do DMA w/ RID, the PASID requirement is only for shared WQ where
> ENQCMDS is used. ENQCMDS has the benefit of avoiding locking where work
> submission is done from multiple CPUs.
> Tony, Dave?
This is what I mean, it has an operating mode you want to use from the
kernel driver that cannot do RID DMA. It is a HW mis-design, IMHO.
Something like PASID0 in the ENQCMDS should have triggered RID DMA.
> > In any case I think we are better to wait for an actual user for multi
> > DMA API iommu_domains to come forward before we try to build an API
> > for it.
>
> What would you recommend in the interim?
Oh, I mean this approach at a high level is fine - I was saying we
shouldn't try to broaden it like Robin was suggesting without a driver
that needs multiple iommu_domains for the DMA API.
Jason
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2022-03-15 17:05 UTC|newest]
Thread overview: 122+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-15 5:07 [PATCH v2 0/8] Enable PASID for DMA API users Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 1/8] iommu: Assign per device max PASID Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 2/8] iommu: Add attach/detach_dev_pasid domain ops Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 10:24 ` Tian, Kevin
2022-03-15 10:24 ` Tian, Kevin
2022-03-15 11:26 ` Jean-Philippe Brucker
2022-03-15 11:26 ` Jean-Philippe Brucker
2022-03-15 11:49 ` Tian, Kevin
2022-03-15 11:49 ` Tian, Kevin
2022-03-15 16:11 ` Jacob Pan
2022-03-15 16:11 ` Jacob Pan
2022-03-18 12:01 ` Lu Baolu
2022-03-18 12:01 ` Lu Baolu
2022-03-18 13:50 ` Jason Gunthorpe
2022-03-18 13:50 ` Jason Gunthorpe via iommu
2022-03-18 11:52 ` Lu Baolu
2022-03-18 11:52 ` Lu Baolu
2022-03-18 13:48 ` Jason Gunthorpe
2022-03-18 13:48 ` Jason Gunthorpe via iommu
2022-03-15 5:07 ` [PATCH v2 3/8] iommu/vt-d: Implement device_pasid domain attach ops Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 10:33 ` Tian, Kevin
2022-03-15 10:33 ` Tian, Kevin
2022-03-15 22:23 ` Jacob Pan
2022-03-15 22:23 ` Jacob Pan
2022-03-15 14:33 ` Jason Gunthorpe
2022-03-15 14:33 ` Jason Gunthorpe via iommu
2022-03-15 22:36 ` Jacob Pan
2022-03-15 22:36 ` Jacob Pan
2022-03-15 23:04 ` Jason Gunthorpe
2022-03-15 23:04 ` Jason Gunthorpe via iommu
2022-03-16 20:50 ` Jacob Pan
2022-03-16 20:50 ` Jacob Pan
2022-03-16 22:15 ` Jason Gunthorpe
2022-03-16 22:15 ` Jason Gunthorpe via iommu
2022-03-16 22:23 ` Luck, Tony
2022-03-16 22:23 ` Luck, Tony
2022-03-17 0:04 ` Jason Gunthorpe
2022-03-17 0:04 ` Jason Gunthorpe via iommu
2022-03-18 5:47 ` Tian, Kevin
2022-03-18 5:47 ` Tian, Kevin
2022-03-18 13:47 ` Jason Gunthorpe
2022-03-18 13:47 ` Jason Gunthorpe via iommu
2022-03-17 0:49 ` Jacob Pan
2022-03-17 0:49 ` Jacob Pan
2022-03-17 13:23 ` Jason Gunthorpe
2022-03-17 13:23 ` Jason Gunthorpe via iommu
2022-03-17 18:23 ` Jacob Pan
2022-03-17 18:23 ` Jacob Pan
2022-03-16 7:41 ` Tian, Kevin
2022-03-16 7:41 ` Tian, Kevin
2022-03-16 21:01 ` Jacob Pan
2022-03-16 21:01 ` Jacob Pan
2022-03-18 5:33 ` Tian, Kevin
2022-03-18 5:33 ` Tian, Kevin
2022-03-28 21:41 ` Jacob Pan
2022-03-28 21:41 ` Jacob Pan
2022-03-16 7:39 ` Tian, Kevin
2022-03-16 7:39 ` Tian, Kevin
2022-03-16 20:51 ` Jacob Pan
2022-03-16 20:51 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 4/8] iommu/vt-d: Use device_pasid attach op for RID2PASID Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-16 7:54 ` Tian, Kevin
2022-03-16 7:54 ` Tian, Kevin
2022-03-17 20:45 ` Jacob Pan
2022-03-17 20:45 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 5/8] iommu: Add PASID support for DMA mapping API users Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 11:16 ` Robin Murphy
2022-03-15 11:16 ` Robin Murphy
2022-03-15 14:22 ` Jason Gunthorpe
2022-03-15 14:22 ` Jason Gunthorpe via iommu
2022-03-15 16:31 ` Jacob Pan
2022-03-15 16:31 ` Jacob Pan
2022-03-15 17:05 ` Jason Gunthorpe [this message]
2022-03-15 17:05 ` Jason Gunthorpe via iommu
2022-03-15 21:24 ` Jacob Pan
2022-03-15 21:24 ` Jacob Pan
2022-03-16 10:32 ` Tian, Kevin
2022-03-16 10:32 ` Tian, Kevin
2022-03-16 8:41 ` Tian, Kevin
2022-03-16 8:41 ` Tian, Kevin
2022-03-16 14:07 ` Jason Gunthorpe
2022-03-16 14:07 ` Jason Gunthorpe via iommu
2022-03-15 14:35 ` Jason Gunthorpe
2022-03-15 14:35 ` Jason Gunthorpe via iommu
2022-03-15 16:38 ` Jacob Pan
2022-03-15 16:38 ` Jacob Pan
2022-03-15 23:05 ` Jason Gunthorpe
2022-03-15 23:05 ` Jason Gunthorpe via iommu
2022-03-18 12:43 ` Lu Baolu
2022-03-18 12:43 ` Lu Baolu
2022-03-28 21:44 ` Jacob Pan
2022-03-28 21:44 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 6/8] dmaengine: idxd: Use DMA API for in-kernel DMA with PASID Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-18 6:10 ` Tian, Kevin
2022-03-18 6:10 ` Tian, Kevin
2022-03-29 17:39 ` Jacob Pan
2022-03-29 17:39 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 7/8] iommu/vt-d: Delete supervisor/kernel SVA Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-18 6:16 ` Tian, Kevin
2022-03-18 6:16 ` Tian, Kevin
2022-03-29 17:42 ` Jacob Pan
2022-03-29 17:42 ` Jacob Pan
2022-03-15 5:07 ` [PATCH v2 8/8] iommu: Remove unused driver data in sva_bind_device Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-15 11:37 ` Jean-Philippe Brucker
2022-03-15 11:37 ` Jean-Philippe Brucker
2022-03-15 5:07 ` [PATCH v2 9/9] dmaengine: idxd: separate user and kernel pasid enabling Jacob Pan
2022-03-15 5:07 ` Jacob Pan
2022-03-18 6:28 ` Tian, Kevin
2022-03-18 6:28 ` Tian, Kevin
2022-03-15 8:16 ` [PATCH v2 0/8] Enable PASID for DMA API users Tian, Kevin
2022-03-15 8:16 ` Tian, Kevin
2022-03-15 15:49 ` Jacob Pan
2022-03-15 15:49 ` Jacob Pan
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=20220315170507.GH11336@nvidia.com \
--to=jgg@nvidia.com \
--cc=ashok.raj@intel.com \
--cc=baolu.lu@linux.intel.com \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=hch@infradead.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@intel.com \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe@linaro.com \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=sanjay.k.kumar@intel.com \
--cc=tom.zanussi@intel.com \
--cc=tony.luck@intel.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 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.