From: Lu Baolu <firstname.lastname@example.org> To: Christoph Hellwig <email@example.com> Cc: firstname.lastname@example.org, David Woodhouse <email@example.com>, Joerg Roedel <firstname.lastname@example.org>, email@example.com, firstname.lastname@example.org, email@example.com, Robin Murphy <firstname.lastname@example.org>, email@example.com, firstname.lastname@example.org, Jacob Pan <email@example.com> Subject: Re: [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops Date: Tue, 13 Aug 2019 15:38:48 +0800 [thread overview] Message-ID: <firstname.lastname@example.org> (raw) In-Reply-To: <email@example.com> Hi again, On 8/7/19 11:06 AM, Lu Baolu wrote: > Hi Christoph, > > On 8/6/19 2:43 PM, Christoph Hellwig wrote: >> Hi Lu, >> >> I really do like the switch to the per-device dma_map_ops, but: >> >> On Thu, Aug 01, 2019 at 02:01:55PM +0800, Lu Baolu wrote: >>> Current Intel IOMMU driver sets the system level dma_ops. This >>> implementation has at least the following drawbacks: 1) each >>> dma API will go through the IOMMU driver even the devices are >>> using identity mapped domains; 2) if user requests to use an >>> identity mapped domain (a.k.a. bypass iommu translation), the >>> driver might fall back to dma domain blindly if the device is >>> not able to address all system memory. >> >> This is very clearly a behavioral regression. The intel-iommu driver >> has always used the iommu mapping to provide decent support for >> devices that do not have the full 64-bit addressing capability, and >> changing this will make a lot of existing setups go slower. >> > > I agree with you that we should keep the capability and avoid possible > performance regression on some setups. But, instead of hard-coding this > in the iommu driver, I prefer a more scalable way. > > For example, the concept of per group default domain type  seems to > be a good choice. The kernel could be statically compiled as by-default > "pass through" or "translate everything". The per group default domain > type API could then be used by the privileged user to tweak some of the > groups for better performance, either by 1) bypassing iommu translation > for the trusted super-speed devices, or 2) applying iommu translation to > access the system memory which is beyond the device's address capability > (without the necessary of using bounce buffer). > >  https://www.spinics.net/lists/iommu/msg37113.html > The code that this patch is trying to remove also looks buggy. The check and replace of domain happens in each DMA API, but there isn't any lock to serialize them. Best regards, Lu Baolu
next prev parent reply other threads:[~2019-08-13 7:39 UTC|newest] Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-08-01 6:01 [PATCH 0/3] iommu/vtd: Per device dma ops Lu Baolu 2019-08-01 6:01 ` [PATCH 1/3] iommu/vt-d: Refactor find_domain() helper Lu Baolu 2019-08-01 6:10 ` Christoph Hellwig 2019-08-01 6:20 ` Lu Baolu 2019-08-01 14:09 ` Christoph Hellwig 2019-08-02 2:06 ` Lu Baolu 2019-08-01 6:01 ` [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops Lu Baolu 2019-08-06 6:43 ` Christoph Hellwig 2019-08-07 3:06 ` Lu Baolu 2019-08-13 7:38 ` Lu Baolu [this message] 2019-08-01 6:01 ` [PATCH 3/3] iommu/vt-d: Cleanup after using per-device dma ops 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 \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --subject='Re: [PATCH 2/3] iommu/vt-d: Apply per-device dma_ops' \ /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
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).