[RFC] Use SMMU HTTU for DMA dirty page tracking

Zengtao (B) prime.zeng at hisilicon.com
Wed May 27 06:46:24 UTC 2020


> -----Original Message-----
> From: zhengxiang (A)
> Sent: Monday, May 25, 2020 7:34 PM
> To: Jean-Philippe Brucker
> Cc: linux-arm-kernel at lists.infradead.org; kvmarm at lists.cs.columbia.edu;
> Will Deacon; Wanghaibin (D); Zengtao (B); maz at kernel.org; James Morse;
> julien.thierry.kdev at gmail.com; Suzuki K Poulose; Wangzhou (B);
> iommu at lists.linux-foundation.org; Kirti Wankhede; Yan Zhao;
> alex.williamson at redhat.com
> Subject: Re: [RFC] Use SMMU HTTU for DMA dirty page tracking
> 
> [+cc Kirti, Yan, Alex]
> 
> On 2020/5/23 1:14, Jean-Philippe Brucker wrote:
> > Hi,
> >
> > On Tue, May 19, 2020 at 05:42:55PM +0800, Xiang Zheng wrote:
> >> Hi all,
> >>
> >> Is there any plan for enabling SMMU HTTU?
> >
> > Not outside of SVA, as far as I know.
> >
> 
> >> I have seen the patch locates in the SVA series patch, which adds
> >> support for HTTU:
> >>     https://www.spinics.net/lists/arm-kernel/msg798694.html
> >>
> >> HTTU reduces the number of access faults on SMMU fault queue
> >> (permission faults also benifit from it).
> >>
> >> Besides reducing the faults, HTTU also helps to track dirty pages for
> >> device DMA. Is it feasible to utilize HTTU to get dirty pages on device
> >> DMA during VFIO live migration?
> >
> > As you know there is a VFIO interface for this under discussion:
> >
> https://lore.kernel.org/kvm/1589781397-28368-1-git-send-email-kwankhe
> de at nvidia.com/
> > It doesn't implement an internal API to communicate with the IOMMU
> driver
> > about dirty pages.
> 
> >
> >> If SMMU can track dirty pages, devices are not required to implement
> >> additional dirty pages tracking to support VFIO live migration.
> >
> > It seems feasible, though tracking it in the device might be more
> > efficient. I might have misunderstood but I think for live migration of
> > the Intel NIC they trap guest accesses to the device and introspect its
> > state to figure out which pages it is accessing.
> >
> > With HTTU I suppose (without much knowledge about live migration)
> that
> > you'd need several new interfaces to the IOMMU drivers:
> >
> > * A way for VFIO to query HTTU support in the SMMU. There are some
> >   discussions about communicating more IOMMU capabilities through
> VFIO but
> >   no implementation yet. When HTTU isn't supported the DIRTY_PAGES
> bitmap
> >   would report all pages as they do now.
> >
> > * VFIO_IOMMU_DIRTY_PAGES_FLAG_START/STOP would clear the dirty
> bit
> >   for all VFIO mappings (which is going to take some time). There is a
> >   walker in io-pgtable for iova_to_phys() which could be extended. I
> >   suppose it's also possible to atomically switch the HA and HD bits in
> >   context descriptors.
> 
> Maybe we need not switch HA and HD bits, just turn on them all the time?

I think we need START/STOP, start is called when migration is started and STOP
called when migration finished.

I think you mean that during the migration(between START and STOP), HA and HD
functionality is always turned on.

> 
> >
> > * VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP would query the
> dirty bit for all
> >   VFIO mappings.
> >
We need a clear during the query which mean we have to reset the dirty status 
after a query.

> 
> I think we need to consider the case of IOMMU dirty pages logging. We
> want
> to test Kirti's VFIO migration patches combined with SMMU HTTU, any
> suggestions?

@kirti @yan @alex
As we know, you have worked on this feature for a long time, and it seems that
 everything is going very well now, thanks very much for your VFIO migration 
framework, it really helps a lot, and we want to start with SMMU HTTU enabled
 based on your jobs, it's kind of hardware dirty page tracking, and expected to bring us
 better performance, any suggestions? 

Thank you.
Zengtao 


More information about the iommu mailing list