From: Jason Gunthorpe <jgg@nvidia.com> To: Jacob Pan <jacob.jun.pan@linux.intel.com> Cc: "Luck, Tony" <tony.luck@intel.com>, Christoph Hellwig <hch@infradead.org>, LKML <linux-kernel@vger.kernel.org>, "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>, Joerg Roedel <joro@8bytes.org>, Lu Baolu <baolu.lu@linux.intel.com>, Jean-Philippe Brucker <jean-philippe@linaro.com>, "Liu, Yi L" <yi.l.liu@intel.com>, "Raj, Ashok" <ashok.raj@intel.com>, "Tian, Kevin" <kevin.tian@intel.com>, "Jiang, Dave" <dave.jiang@intel.com>, "wangzhou1@hisilicon.com" <wangzhou1@hisilicon.com>, "zhangfei.gao@linaro.org" <zhangfei.gao@linaro.org>, "vkoul@kernel.org" <vkoul@kernel.org>, David Woodhouse <dwmw2@infradead.org> Subject: Re: [PATCH v4 1/2] iommu/sva: Tighten SVA bind API with explicit flags Date: Thu, 13 May 2021 19:31:22 -0300 [thread overview] Message-ID: <20210513223122.GV1002214@nvidia.com> (raw) In-Reply-To: <20210513132251.0ff89b90@jacob-builder> On Thu, May 13, 2021 at 01:22:51PM -0700, Jacob Pan wrote: > Hi Tony, > > On Thu, 13 May 2021 12:57:49 -0700, "Luck, Tony" <tony.luck@intel.com> > wrote: > > > On Thu, May 13, 2021 at 12:46:21PM -0700, Jacob Pan wrote: > > > It seems there are two options: > > > 1. Add a new IOMMU API to set up a system PASID with a *separate* IOMMU > > > page table/domain, mark the device is PASID only with a flag. Use DMA > > > APIs to explicit map/unmap. Based on this PASID-only flag, Vendor IOMMU > > > driver will decide whether to use system PASID domain during map/unmap. > > > Not clear if we also need to make IOVA==kernel VA. > > > > > > 2. Add a new IOMMU API to setup a system PASID which points to > > > init_mm.pgd. This API only allows trusted device to bind with the > > > system PASID at its own risk. There is no need for DMA API. This is the > > > same as the current code except with an explicit API. > > > > > > Which option? > > > > Option #1 looks cleaner to me. Option #2 gives access to bits > > of memory that the users of system PASID shouldn't ever need > > to touch ... just map regions of memory that the kernel has > > a "struct page" for. > > > > What does "use DMA APIs to explicitly map/unmap" mean? Is that > > for the whole region? > > > If we map the entire kernel direct map during system PASID setup, then we > don't need to use DMA API to map/unmap certain range. > > I was thinking this system PASID page table could be on-demand. The mapping > is built by explicit use of DMA map/unmap APIs. Option 1 should be the PASID works exactly like a normal RID and uses all the normal DMA APIs and IOMMU mechanisms, whatever the platform implements. This might mean an iommu update on every operation or not. > > I'm expecting that once this system PASID has been initialized, > > then any accelerator device with a kernel use case would use the > > same PASID. I.e. DSA for page clearing, IAX for ZSwap compression > > & decompression, etc. > > > OK, sounds like we have to map the entire kernel VA with struct page as you > said. So we still by-pass DMA APIs, can we all agree on that? Option 2 should be the faster option, but not available in all cases. Option 1 isn't optional. DMA and IOMMU code has to be portable and this is the portable API. If you want to do option 1 and option 2 then give it a go, but in most common cases with the IOMMU in a direct map you shouldn't get a notable performance win. Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@nvidia.com> To: Jacob Pan <jacob.jun.pan@linux.intel.com> Cc: "vkoul@kernel.org" <vkoul@kernel.org>, "Tian, Kevin" <kevin.tian@intel.com>, "Luck, Tony" <tony.luck@intel.com>, "Jiang, Dave" <dave.jiang@intel.com>, "Raj, Ashok" <ashok.raj@intel.com>, David Woodhouse <dwmw2@infradead.org>, LKML <linux-kernel@vger.kernel.org>, Christoph Hellwig <hch@infradead.org>, "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>, "zhangfei.gao@linaro.org" <zhangfei.gao@linaro.org>, Jean-Philippe Brucker <jean-philippe@linaro.com> Subject: Re: [PATCH v4 1/2] iommu/sva: Tighten SVA bind API with explicit flags Date: Thu, 13 May 2021 19:31:22 -0300 [thread overview] Message-ID: <20210513223122.GV1002214@nvidia.com> (raw) In-Reply-To: <20210513132251.0ff89b90@jacob-builder> On Thu, May 13, 2021 at 01:22:51PM -0700, Jacob Pan wrote: > Hi Tony, > > On Thu, 13 May 2021 12:57:49 -0700, "Luck, Tony" <tony.luck@intel.com> > wrote: > > > On Thu, May 13, 2021 at 12:46:21PM -0700, Jacob Pan wrote: > > > It seems there are two options: > > > 1. Add a new IOMMU API to set up a system PASID with a *separate* IOMMU > > > page table/domain, mark the device is PASID only with a flag. Use DMA > > > APIs to explicit map/unmap. Based on this PASID-only flag, Vendor IOMMU > > > driver will decide whether to use system PASID domain during map/unmap. > > > Not clear if we also need to make IOVA==kernel VA. > > > > > > 2. Add a new IOMMU API to setup a system PASID which points to > > > init_mm.pgd. This API only allows trusted device to bind with the > > > system PASID at its own risk. There is no need for DMA API. This is the > > > same as the current code except with an explicit API. > > > > > > Which option? > > > > Option #1 looks cleaner to me. Option #2 gives access to bits > > of memory that the users of system PASID shouldn't ever need > > to touch ... just map regions of memory that the kernel has > > a "struct page" for. > > > > What does "use DMA APIs to explicitly map/unmap" mean? Is that > > for the whole region? > > > If we map the entire kernel direct map during system PASID setup, then we > don't need to use DMA API to map/unmap certain range. > > I was thinking this system PASID page table could be on-demand. The mapping > is built by explicit use of DMA map/unmap APIs. Option 1 should be the PASID works exactly like a normal RID and uses all the normal DMA APIs and IOMMU mechanisms, whatever the platform implements. This might mean an iommu update on every operation or not. > > I'm expecting that once this system PASID has been initialized, > > then any accelerator device with a kernel use case would use the > > same PASID. I.e. DSA for page clearing, IAX for ZSwap compression > > & decompression, etc. > > > OK, sounds like we have to map the entire kernel VA with struct page as you > said. So we still by-pass DMA APIs, can we all agree on that? Option 2 should be the faster option, but not available in all cases. Option 1 isn't optional. DMA and IOMMU code has to be portable and this is the portable API. If you want to do option 1 and option 2 then give it a go, but in most common cases with the IOMMU in a direct map you shouldn't get a notable performance win. Jason _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2021-05-13 22:31 UTC|newest] Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-05-10 13:25 [PATCH v4 0/2] Simplify and restrict IOMMU SVA APIs Jacob Pan 2021-05-10 13:25 ` Jacob Pan 2021-05-10 13:25 ` [PATCH v4 1/2] iommu/sva: Tighten SVA bind API with explicit flags Jacob Pan 2021-05-10 13:25 ` Jacob Pan 2021-05-10 23:37 ` Jason Gunthorpe 2021-05-10 23:37 ` Jason Gunthorpe 2021-05-11 3:31 ` Jacob Pan 2021-05-11 3:31 ` Jacob Pan 2021-05-11 11:48 ` Jason Gunthorpe 2021-05-11 11:48 ` Jason Gunthorpe 2021-05-11 16:14 ` Jacob Pan 2021-05-11 16:14 ` Jacob Pan 2021-05-11 16:35 ` Jason Gunthorpe 2021-05-11 16:35 ` Jason Gunthorpe 2021-05-11 18:05 ` Jacob Pan 2021-05-11 18:05 ` Jacob Pan 2021-05-11 19:47 ` Jason Gunthorpe 2021-05-11 19:47 ` Jason Gunthorpe 2021-05-12 6:37 ` Christoph Hellwig 2021-05-12 6:37 ` Christoph Hellwig 2021-05-13 13:00 ` Jacob Pan 2021-05-13 13:00 ` Jacob Pan 2021-05-13 13:38 ` Jason Gunthorpe 2021-05-13 13:38 ` Jason Gunthorpe 2021-05-13 15:10 ` Jacob Pan 2021-05-13 15:10 ` Jacob Pan 2021-05-13 16:44 ` Luck, Tony 2021-05-13 16:44 ` Luck, Tony 2021-05-13 17:33 ` Jason Gunthorpe 2021-05-13 17:33 ` Jason Gunthorpe 2021-05-13 18:53 ` Luck, Tony 2021-05-13 18:53 ` Luck, Tony 2021-05-13 19:00 ` Jason Gunthorpe 2021-05-13 19:00 ` Jason Gunthorpe 2021-05-13 19:14 ` Luck, Tony 2021-05-13 19:14 ` Luck, Tony 2021-05-13 19:20 ` Jason Gunthorpe 2021-05-13 19:20 ` Jason Gunthorpe 2021-05-13 19:46 ` Jacob Pan 2021-05-13 19:46 ` Jacob Pan 2021-05-13 19:57 ` Luck, Tony 2021-05-13 19:57 ` Luck, Tony 2021-05-13 20:22 ` Jacob Pan 2021-05-13 20:22 ` Jacob Pan 2021-05-13 22:31 ` Jason Gunthorpe [this message] 2021-05-13 22:31 ` Jason Gunthorpe 2021-05-13 23:40 ` Jacob Pan 2021-05-13 23:40 ` Jacob Pan 2021-05-17 14:37 ` Jason Gunthorpe 2021-05-17 14:37 ` Jason Gunthorpe 2021-05-19 15:46 ` Jacob Pan 2021-05-19 15:46 ` Jacob Pan 2021-05-12 10:18 ` Jean-Philippe Brucker 2021-05-12 10:18 ` Jean-Philippe Brucker 2021-05-10 13:25 ` [PATCH v4 2/2] iommu/sva: Remove mm parameter from SVA bind API Jacob Pan 2021-05-10 13:25 ` Jacob Pan 2021-05-12 10:24 ` Jean-Philippe Brucker 2021-05-12 10:24 ` Jean-Philippe Brucker
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=20210513223122.GV1002214@nvidia.com \ --to=jgg@nvidia.com \ --cc=ashok.raj@intel.com \ --cc=baolu.lu@linux.intel.com \ --cc=dave.jiang@intel.com \ --cc=dwmw2@infradead.org \ --cc=hch@infradead.org \ --cc=iommu@lists.linux-foundation.org \ --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=tony.luck@intel.com \ --cc=vkoul@kernel.org \ --cc=wangzhou1@hisilicon.com \ --cc=yi.l.liu@intel.com \ --cc=zhangfei.gao@linaro.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: linkBe 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.