From: David Woodhouse <dwmw2@infradead.org>
To: Claire Chang <tientzu@chromium.org>,
Rob Herring <robh+dt@kernel.org>,
mpe@ellerman.id.au, Joerg Roedel <joro@8bytes.org>,
Will Deacon <will@kernel.org>,
Frank Rowand <frowand.list@gmail.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
boris.ostrovsky@oracle.com, jgross@suse.com,
Christoph Hellwig <hch@lst.de>,
Marek Szyprowski <m.szyprowski@samsung.com>
Cc: heikki.krogerus@linux.intel.com, peterz@infradead.org,
benh@kernel.crashing.org, grant.likely@arm.com, paulus@samba.org,
mingo@kernel.org, sstabellini@kernel.org,
"Saravana Kannan" <saravanak@google.com>,
xypron.glpk@gmx.de,
"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
"Bartosz Golaszewski" <bgolaszewski@baylibre.com>,
xen-devel@lists.xenproject.org,
"Thierry Reding" <treding@nvidia.com>,
linux-devicetree <devicetree@vger.kernel.org>,
linuxppc-dev@lists.ozlabs.org,
"Nicolas Boichat" <drinkcat@chromium.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Andy Shevchenko" <andriy.shevchenko@linux.intel.com>,
"Greg KH" <gregkh@linuxfoundation.org>,
"Randy Dunlap" <rdunlap@infradead.org>,
lkml <linux-kernel@vger.kernel.org>,
"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
"Jim Quinlan" <james.quinlan@broadcom.com>,
"Robin Murphy" <robin.murphy@arm.com>,
hch@infradead.org, "Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
"Xuan Zhuo" <xuanzhuo@linux.alibaba.com>,
"Eugenio Pérez" <eperezma@redhat.com>,
virtualization@lists.linux.dev, graf@amazon.de
Subject: Using Restricted DMA for virtio-pci
Date: Fri, 21 Mar 2025 15:38:10 +0000 [thread overview]
Message-ID: <979b6a34ca5724ced1d4871b58bf227065d7da57.camel@infradead.org> (raw)
In-Reply-To: <20210209062131.2300005-1-tientzu@chromium.org>
[-- Attachment #1: Type: text/plain, Size: 1994 bytes --]
On Tue, 2021-02-09 at 14:21 +0800, Claire Chang wrote:
> This series implements mitigations for lack of DMA access control on
> systems without an IOMMU, which could result in the DMA accessing the
> system memory at unexpected times and/or unexpected addresses, possibly
> leading to data leakage or corruption.
Replying to an ancient (2021) thread which has already been merged...
I'd like to be able to use this facility for virtio devices.
Virtio already has a complicated relationship with the DMA API, because
there were a bunch of early VMM bugs where the virtio devices where
magically exempted from IOMMU protection, but the VMM lied to the guest
and claimed they weren't.
With the advent of confidential computing, and the VMM (or whatever's
emulating the virtio device) not being *allowed* to arbitrarily access
all of the guest's memory, the DMA API becomes necessary again.
Either a virtual IOMMU needs to determine which guest memory the VMM
may access, or the DMA API is wrappers around operations which
share/unshare (or unencrypt/encrypt) the memory in question.
All of which is complicated and slow, if we're looking at a minimal
privileged hypervisor stub like pKVM which enforces the lack of guest
memory access from VMM.
I'm thinking of defining a new type of virtio-pci device which cannot
do DMA to arbitrary system memory. Instead it has an additional memory
BAR which is used as a SWIOTLB for bounce buffering.
The driver for it would look much like the existing virtio-pci device
except that it would register the restricted-dma region first (and thus
the swiotlb dma_ops), and then just go through the rest of the setup
like any other virtio device.
That seems like it ought to be fairly simple, and seems like a
reasonable way to allow an untrusted VMM to provide virtio devices with
restricted DMA access.
While I start actually doing the typing... does anyone want to start
yelling at me now? Christoph? mst? :)
[-- Attachment #2: smime.p7s --]
[-- Type: application/pkcs7-signature, Size: 5069 bytes --]
next prev parent reply other threads:[~2025-03-21 15:38 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-09 6:21 [PATCH v4 00/14] Restricted DMA Claire Chang
2021-02-09 6:21 ` [PATCH v4 01/14] swiotlb: Remove external access to io_tlb_start Claire Chang
2021-02-09 8:40 ` Christoph Hellwig
2021-02-09 6:21 ` [PATCH v4 02/14] swiotlb: Move is_swiotlb_buffer() to swiotlb.c Claire Chang
2021-02-09 6:21 ` [PATCH v4 03/14] swiotlb: Add struct swiotlb Claire Chang
2021-02-09 6:21 ` [PATCH v4 04/14] swiotlb: Refactor swiotlb_late_init_with_tbl Claire Chang
2021-02-09 6:21 ` [PATCH v4 05/14] swiotlb: Add DMA_RESTRICTED_POOL Claire Chang
2021-02-09 6:21 ` [PATCH v4 06/14] swiotlb: Add restricted DMA pool Claire Chang
2021-02-09 6:21 ` [PATCH v4 07/14] swiotlb: Update swiotlb API to gain a struct device argument Claire Chang
2021-02-09 6:21 ` [PATCH v4 08/14] swiotlb: Use restricted DMA pool if available Claire Chang
2021-02-09 6:21 ` [PATCH v4 09/14] swiotlb: Refactor swiotlb_tbl_{map,unmap}_single Claire Chang
2021-02-09 6:21 ` [PATCH v4 10/14] dma-direct: Add a new wrapper __dma_direct_free_pages() Claire Chang
2021-02-09 6:21 ` [PATCH v4 11/14] swiotlb: Add is_dev_swiotlb_force() Claire Chang
2021-02-09 6:21 ` [PATCH v4 12/14] swiotlb: Add restricted DMA alloc/free support Claire Chang
2021-02-26 4:17 ` Claire Chang
2021-02-26 5:17 ` Christoph Hellwig
2021-02-26 9:35 ` Claire Chang
2021-02-09 6:21 ` [PATCH v4 13/14] dt-bindings: of: Add restricted DMA pool Claire Chang
2021-03-10 16:07 ` Will Deacon
2021-03-10 21:40 ` Rob Herring
2021-03-11 5:04 ` Florian Fainelli
2021-02-09 6:21 ` [PATCH v4 14/14] of: Add plumbing for " Claire Chang
2021-04-22 8:20 ` [PATCH v4 00/14] Restricted DMA Claire Chang
2025-03-21 15:38 ` David Woodhouse [this message]
2025-03-21 18:32 ` Using Restricted DMA for virtio-pci Michael S. Tsirkin
2025-03-21 18:42 ` David Woodhouse
2025-03-28 17:40 ` David Woodhouse
2025-03-30 13:42 ` Michael S. Tsirkin
2025-03-30 15:07 ` David Woodhouse
2025-03-30 16:59 ` Michael S. Tsirkin
2025-03-30 20:07 ` David Woodhouse
2025-03-30 17:06 ` Michael S. Tsirkin
2025-03-30 21:27 ` David Woodhouse
2025-03-30 21:48 ` Michael S. Tsirkin
2025-03-31 9:42 ` David Woodhouse
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=979b6a34ca5724ced1d4871b58bf227065d7da57.camel@infradead.org \
--to=dwmw2@infradead.org \
--cc=andriy.shevchenko@linux.intel.com \
--cc=benh@kernel.crashing.org \
--cc=bgolaszewski@baylibre.com \
--cc=boris.ostrovsky@oracle.com \
--cc=dan.j.williams@intel.com \
--cc=devicetree@vger.kernel.org \
--cc=drinkcat@chromium.org \
--cc=eperezma@redhat.com \
--cc=frowand.list@gmail.com \
--cc=graf@amazon.de \
--cc=grant.likely@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=heikki.krogerus@linux.intel.com \
--cc=iommu@lists.linux-foundation.org \
--cc=james.quinlan@broadcom.com \
--cc=jasowang@redhat.com \
--cc=jgross@suse.com \
--cc=joro@8bytes.org \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=m.szyprowski@samsung.com \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=mst@redhat.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=rdunlap@infradead.org \
--cc=robh+dt@kernel.org \
--cc=robin.murphy@arm.com \
--cc=saravanak@google.com \
--cc=sstabellini@kernel.org \
--cc=tientzu@chromium.org \
--cc=treding@nvidia.com \
--cc=virtualization@lists.linux.dev \
--cc=will@kernel.org \
--cc=xen-devel@lists.xenproject.org \
--cc=xuanzhuo@linux.alibaba.com \
--cc=xypron.glpk@gmx.de \
/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).