From: tgh <wwwwww4187@sina.com.cn>
To: Ian Pratt <Ian.Pratt@eu.citrix.com>
Cc: muli@il.ibm.com, xen-devel@lists.xensource.com,
iommu@lists.linux-foundation.org,
Thomas Woller <thomas.woller@amd.com>,
Wei Wang2 <wei.wang2@amd.com>,
"Dannowski, Uwe" <Uwe.Dannowski@amd.com>,
elsie.wahlig@amd.com, "Hohmuth,
Michael" <Michael.Hohmuth@amd.com>,
amit.shah@qumranet.com
Subject: Re: Re: [XEN-IOMMU] Proposal of DMA protection/isolationsupport
Date: Fri, 18 Jan 2008 16:10:46 +0800 [thread overview]
Message-ID: <47905F06.8070406@sina.com.cn> (raw)
In-Reply-To: <DD74FBB8EE28D441903D56487861CD9D26D3E383@lonpexch01.citrite.net>
hi
IOMMU, could it be used in KVM ,or not? if it could , what about the
difference between the usage in xen and the usage in KVM?
Thanks
Ian Pratt 写道:
>> After looking into the grant mapping code (use block device as an
>> example), I got some ideas to share with you and the list. Please
>> correct me if I missed something. There might be 2 places to trigger
>> iommu mapping:
>>
>> 1) Before submitting io request to generic block layer, block backend
>> driver will invoke GNTTABOPs to map granted remote pages . However
>> creating iommu mapping only in GNTTABOP not very enough because local
>> pages will also be submitted to block layer and they should also be
>> translated by iommu.
>>
>> 2) When dma layer is invoked to prepare a bus address for native block
>> device driver. It would be better to have a "hypervisor-aware" dma
>> layer
>> which always maps virtual address to bus address via hypercall.
>> __gnttab_dma_map_page() might be a good place to trigger this new
>> hypercall. Both remote and local pages can be mapped by this way.
>>
>
>
> It's much better to create most mappings in #1 when the operations are
> easily batchable into a single hypercall, and then fill in the missing
> mappings when required at #2.
>
> Since in many situations dom0 does very little IO for itself, this
> should be a significant win, especially for networking.
>
> Ian
>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
>
>
>
next prev parent reply other threads:[~2008-01-18 8:10 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-10 15:48 [XEN-IOMMU] Proposal of DMA protection/isolation support Wei Wang2
2008-01-10 15:54 ` Keir Fraser
2008-01-10 16:52 ` Wei Wang2
2008-01-10 16:58 ` Keir Fraser
2008-01-10 17:31 ` Wei Wang2
2008-01-16 16:34 ` Wei Wang2
2008-01-16 16:45 ` Keir Fraser
2008-01-16 17:15 ` Wei Wang2
2008-01-16 18:25 ` Keir Fraser
2008-01-17 0:11 ` Re: [XEN-IOMMU] Proposal of DMA protection/isolationsupport Ian Pratt
2008-01-18 8:10 ` tgh [this message]
2008-01-12 11:45 ` [XEN-IOMMU] Proposal of DMA protection/isolation support Amit Shah
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=47905F06.8070406@sina.com.cn \
--to=wwwwww4187@sina.com.cn \
--cc=Ian.Pratt@eu.citrix.com \
--cc=Michael.Hohmuth@amd.com \
--cc=Uwe.Dannowski@amd.com \
--cc=amit.shah@qumranet.com \
--cc=elsie.wahlig@amd.com \
--cc=iommu@lists.linux-foundation.org \
--cc=muli@il.ibm.com \
--cc=thomas.woller@amd.com \
--cc=wei.wang2@amd.com \
--cc=xen-devel@lists.xensource.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.