From: Peter Xu <peterx@redhat.com>
To: Jason Wang <jasowang@redhat.com>
Cc: "Tian, Kevin" <kevin.tian@intel.com>,
"Lan, Tianyu" <tianyu.lan@intel.com>,
"Raj, Ashok" <ashok.raj@intel.com>,
"mst@redhat.com" <mst@redhat.com>,
"jan.kiszka@siemens.com" <jan.kiszka@siemens.com>,
"bd.aviv@gmail.com" <bd.aviv@gmail.com>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
"alex.williamson@redhat.com" <alex.williamson@redhat.com>
Subject: Re: [Qemu-devel] [PATCH RFC v3 14/14] intel_iommu: enable vfio devices
Date: Thu, 19 Jan 2017 11:32:56 +0800 [thread overview]
Message-ID: <20170119033256.GC4914@pxdev.xzpeter.org> (raw)
In-Reply-To: <9553e8fa-e8ad-8b28-5f5e-142f10acc030@redhat.com>
On Wed, Jan 18, 2017 at 06:06:57PM +0800, Jason Wang wrote:
[...]
> So I think we should implement DSI and GLOBAL for vfio in this case. We can
> first try to implement it through current VFIO API which can accepts a range
> of iova. If not possible, let's discuss for other possible solutions.
Do you mean VFIO_IOMMU_UNMAP_DMA here?
[...]
> >If my understanding above is correct, there is nothing wrong with
> >above IOMMU driver code - actually it makes sense on bare metal
> >when CM is disabled.
> >
> >But yes, DSI/GLOBAL is far less efficient than PSI when CM is enabled.
> >We rely on cache invalidations to indirectly capture remapping structure
> >change. PSI provides accurate info, while DSI/GLOBAL doesn't. To
> >emulate correct behavior of DSI/GLOBAL, we have to pretend that
> >the whole address space (iova=0, size=agaw) needs to be unmapped
> >(for GLOBAL it further means multiple address spaces)
>
> Maybe a trick to have accurate info is virtual Device IOTLB.
Could you elaborate a bit on this?
Thanks,
-- peterx
next prev parent reply other threads:[~2017-01-19 3:33 UTC|newest]
Thread overview: 93+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-13 3:06 [Qemu-devel] [PATCH RFC v3 00/14] VT-d: vfio enablement and misc enhances Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 01/14] IOMMU: add option to enable VTD_CAP_CM to vIOMMU capility exposoed to guest Peter Xu
2017-01-20 8:32 ` Tian, Kevin
2017-01-20 8:54 ` Peter Xu
2017-01-20 8:59 ` Tian, Kevin
2017-01-20 9:11 ` Peter Xu
2017-01-20 9:20 ` Tian, Kevin
2017-01-20 9:30 ` Peter Xu
2017-01-20 15:42 ` Eric Blake
2017-01-22 2:32 ` Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 02/14] intel_iommu: simplify irq region translation Peter Xu
2017-01-20 8:22 ` Tian, Kevin
2017-01-20 9:05 ` Peter Xu
2017-01-20 9:15 ` Tian, Kevin
2017-01-20 9:27 ` Peter Xu
2017-01-20 9:52 ` Tian, Kevin
2017-01-20 10:04 ` Peter Xu
2017-01-22 4:42 ` Tian, Kevin
2017-01-22 4:50 ` Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 03/14] intel_iommu: renaming gpa to iova where proper Peter Xu
2017-01-20 8:27 ` Tian, Kevin
2017-01-20 9:23 ` Peter Xu
2017-01-20 9:41 ` Tian, Kevin
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 04/14] intel_iommu: fix trace for inv desc handling Peter Xu
2017-01-13 7:46 ` Jason Wang
2017-01-13 9:13 ` Peter Xu
2017-01-13 9:33 ` Jason Wang
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 05/14] intel_iommu: fix trace for addr translation Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 06/14] intel_iommu: vtd_slpt_level_shift check level Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 07/14] memory: add section range info for IOMMU notifier Peter Xu
2017-01-13 7:55 ` Jason Wang
2017-01-13 9:23 ` Peter Xu
2017-01-13 9:37 ` Jason Wang
2017-01-13 10:22 ` Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 08/14] memory: provide iommu_replay_all() Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 09/14] memory: introduce memory_region_notify_one() Peter Xu
2017-01-13 7:58 ` Jason Wang
2017-01-16 7:08 ` Peter Xu
2017-01-16 7:38 ` Jason Wang
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 10/14] memory: add MemoryRegionIOMMUOps.replay() callback Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 11/14] intel_iommu: provide its own replay() callback Peter Xu
2017-01-13 9:26 ` Jason Wang
2017-01-16 7:31 ` Peter Xu
2017-01-16 7:47 ` Jason Wang
2017-01-16 7:59 ` Peter Xu
2017-01-16 8:03 ` Jason Wang
2017-01-16 8:06 ` Peter Xu
2017-01-16 8:23 ` Jason Wang
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 12/14] intel_iommu: do replay when context invalidate Peter Xu
2017-01-16 5:53 ` Jason Wang
2017-01-16 7:43 ` Peter Xu
2017-01-16 7:52 ` Jason Wang
2017-01-16 8:02 ` Peter Xu
2017-01-16 8:18 ` Peter Xu
2017-01-16 8:28 ` Jason Wang
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 13/14] intel_iommu: allow dynamic switch of IOMMU region Peter Xu
2017-01-16 6:20 ` Jason Wang
2017-01-16 7:50 ` Peter Xu
2017-01-16 8:01 ` Jason Wang
2017-01-16 8:12 ` Peter Xu
2017-01-16 8:25 ` Jason Wang
2017-01-16 8:32 ` Peter Xu
2017-01-16 16:25 ` Michael S. Tsirkin
2017-01-17 14:53 ` Peter Xu
2017-01-16 19:53 ` Alex Williamson
2017-01-17 14:00 ` Peter Xu
2017-01-17 15:46 ` Alex Williamson
2017-01-18 7:49 ` Peter Xu
2017-01-19 8:20 ` Peter Xu
2017-01-13 3:06 ` [Qemu-devel] [PATCH RFC v3 14/14] intel_iommu: enable vfio devices Peter Xu
2017-01-16 6:30 ` Jason Wang
2017-01-16 9:18 ` Peter Xu
2017-01-16 9:54 ` Jason Wang
2017-01-17 14:45 ` Peter Xu
2017-01-18 3:10 ` Jason Wang
2017-01-18 8:11 ` Peter Xu
2017-01-18 8:36 ` Jason Wang
2017-01-18 8:46 ` Peter Xu
2017-01-18 9:38 ` Tian, Kevin
2017-01-18 10:06 ` Jason Wang
2017-01-19 3:32 ` Peter Xu [this message]
2017-01-19 3:36 ` Jason Wang
2017-01-19 3:16 ` Peter Xu
2017-01-19 6:22 ` Tian, Kevin
2017-01-19 9:38 ` Peter Xu
2017-01-19 6:44 ` Liu, Yi L
2017-01-19 7:02 ` Jason Wang
2017-01-19 7:02 ` Peter Xu
2017-01-16 9:20 ` Peter Xu
2017-01-13 15:58 ` [Qemu-devel] [PATCH RFC v3 00/14] VT-d: vfio enablement and misc enhances Michael S. Tsirkin
2017-01-14 2:59 ` Peter Xu
2017-01-17 15:07 ` Michael S. Tsirkin
2017-01-18 7:34 ` Peter Xu
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=20170119033256.GC4914@pxdev.xzpeter.org \
--to=peterx@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=bd.aviv@gmail.com \
--cc=jan.kiszka@siemens.com \
--cc=jasowang@redhat.com \
--cc=kevin.tian@intel.com \
--cc=mst@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=tianyu.lan@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 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).