From: David Gibson <david@gibson.dropbear.id.au>
To: Peter Xu <peterx@redhat.com>
Cc: qemu-devel@nongnu.org, tianyu.lan@intel.com,
kevin.tian@intel.com, mst@redhat.com, jan.kiszka@siemens.com,
jasowang@redhat.com, alex.williamson@redhat.com,
bd.aviv@gmail.com
Subject: Re: [Qemu-devel] [PATCH v7 03/17] vfio: allow to notify unmap for very large region
Date: Fri, 10 Feb 2017 12:13:07 +1100 [thread overview]
Message-ID: <20170210011307.GR27610@umbus.fritz.box> (raw)
In-Reply-To: <1486456099-7345-4-git-send-email-peterx@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 2105 bytes --]
On Tue, Feb 07, 2017 at 04:28:05PM +0800, Peter Xu wrote:
> Linux vfio driver supports to do VFIO_IOMMU_UNMAP_DMA for a very big
> region. This can be leveraged by QEMU IOMMU implementation to cleanup
> existing page mappings for an entire iova address space (by notifying
> with an IOTLB with extremely huge addr_mask). However current
> vfio_iommu_map_notify() does not allow that. It make sure that all the
> translated address in IOTLB is falling into RAM range.
>
> The check makes sense, but it should only be a sensible checker for
> mapping operations, and mean little for unmap operations.
>
> This patch moves this check into map logic only, so that we'll get
> faster unmap handling (no need to translate again), and also we can then
> better support unmapping a very big region when it covers non-ram ranges
> or even not-existing ranges.
>
> Acked-by: Alex Williamson <alex.williamson@redhat.com>
> Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Seems sensible of itself, except that I don't understand how we were
ever working before this.
> ---
> hw/vfio/common.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 42c4790..f3ba9b9 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -352,11 +352,10 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
>
> rcu_read_lock();
>
> - if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
> - goto out;
> - }
> -
> if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
> + if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
> + goto out;
> + }
> /*
> * vaddr is only valid until rcu_read_unlock(). But after
> * vfio_dma_map has set up the mapping the pages will be
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
next prev parent reply other threads:[~2017-02-10 2:23 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-07 8:28 [Qemu-devel] [PATCH v7 00/17] VT-d: vfio enablement and misc enhances Peter Xu
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 01/17] vfio: trace map/unmap for notify as well Peter Xu
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 02/17] vfio: introduce vfio_get_vaddr() Peter Xu
2017-02-10 1:12 ` David Gibson
2017-02-10 5:50 ` Peter Xu
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 03/17] vfio: allow to notify unmap for very large region Peter Xu
2017-02-10 1:13 ` David Gibson [this message]
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 04/17] intel_iommu: add "caching-mode" option Peter Xu
2017-02-10 1:14 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 05/17] intel_iommu: simplify irq region translation Peter Xu
2017-02-10 1:15 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 06/17] intel_iommu: renaming gpa to iova where proper Peter Xu
2017-02-10 1:17 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 07/17] intel_iommu: convert dbg macros to traces for inv Peter Xu
2017-02-08 2:47 ` Jason Wang
2017-02-10 1:19 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 08/17] intel_iommu: convert dbg macros to trace for trans Peter Xu
2017-02-08 2:49 ` Jason Wang
2017-02-10 1:20 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 09/17] intel_iommu: vtd_slpt_level_shift check level Peter Xu
2017-02-10 1:20 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 10/17] memory: add section range info for IOMMU notifier Peter Xu
2017-02-10 2:29 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 11/17] memory: provide IOMMU_NOTIFIER_FOREACH macro Peter Xu
2017-02-10 2:30 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 12/17] memory: provide iommu_replay_all() Peter Xu
2017-02-10 2:31 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 13/17] memory: introduce memory_region_notify_one() Peter Xu
2017-02-10 2:33 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 14/17] memory: add MemoryRegionIOMMUOps.replay() callback Peter Xu
2017-02-10 2:34 ` David Gibson
2017-03-27 8:35 ` Liu, Yi L
2017-03-27 9:12 ` Peter Xu
2017-03-27 9:21 ` Liu, Yi L
2017-03-30 11:06 ` Liu, Yi L
2017-03-30 11:57 ` Jason Wang
2017-03-31 2:56 ` Peter Xu
2017-03-31 4:21 ` Jason Wang
2017-03-31 5:01 ` Peter Xu
2017-03-31 5:12 ` Jason Wang
2017-03-31 5:28 ` Peter Xu
2017-03-31 5:34 ` Liu, Yi L
2017-03-31 7:16 ` Jason Wang
2017-03-31 7:30 ` Liu, Yi L
2017-04-01 5:00 ` Jason Wang
2017-04-01 6:39 ` Liu, Yi L
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 15/17] intel_iommu: provide its own replay() callback Peter Xu
2017-02-10 2:36 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 16/17] intel_iommu: allow dynamic switch of IOMMU region Peter Xu
2017-02-10 2:38 ` David Gibson
2017-02-07 8:28 ` [Qemu-devel] [PATCH v7 17/17] intel_iommu: enable vfio devices Peter Xu
2017-02-10 6:24 ` Jason Wang
2017-03-16 4:05 ` Peter Xu
2017-03-19 15:34 ` Aviv B.D.
2017-03-20 1:56 ` Peter Xu
2017-03-20 2:12 ` Liu, Yi L
2017-03-20 2:41 ` Peter Xu
2017-02-17 17:18 ` [Qemu-devel] [PATCH v7 00/17] VT-d: vfio enablement and misc enhances Alex Williamson
2017-02-20 7:47 ` Peter Xu
2017-02-20 8:17 ` Liu, Yi L
2017-02-20 8:32 ` Peter Xu
2017-02-20 19:15 ` Alex Williamson
2017-02-28 7:52 ` 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=20170210011307.GR27610@umbus.fritz.box \
--to=david@gibson.dropbear.id.au \
--cc=alex.williamson@redhat.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=peterx@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).