From: Jason Gunthorpe <jgg@ziepe.ca>
To: Peter Gonda <pgonda@google.com>
Cc: Jiri Pirko <jiri@resnulli.us>,
dri-devel@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org,
iommu@lists.linux.dev, linux-media@vger.kernel.org,
sumit.semwal@linaro.org, benjamin.gaignard@collabora.com,
Brian.Starkey@arm.com, jstultz@google.com, tjmercier@google.com,
christian.koenig@amd.com, m.szyprowski@samsung.com,
robin.murphy@arm.com, leon@kernel.org, sean.anderson@linux.dev,
ptesarik@suse.com, catalin.marinas@arm.com,
aneesh.kumar@kernel.org, suzuki.poulose@arm.com,
steven.price@arm.com, thomas.lendacky@amd.com,
john.allen@amd.com, ashish.kalra@amd.com,
suravee.suthikulpanit@amd.com, linux-coco@lists.linux.dev
Subject: Re: [PATCH net-next v3 2/2] dma-buf: heaps: system: add system_cc_decrypted heap for explicitly decrypted memory
Date: Mon, 9 Mar 2026 12:50:15 -0300 [thread overview]
Message-ID: <20260309155015.GP1687929@ziepe.ca> (raw)
In-Reply-To: <CAMkAt6o_yZ5T-3TRwymjYQZEq-Q_z=DAA3vc61h81X9sQr_CXA@mail.gmail.com>
On Mon, Mar 09, 2026 at 09:39:44AM -0600, Peter Gonda wrote:
> Great feature to have thanks Jiri! A couple naive questions.
>
> On Thu, Mar 5, 2026 at 5:38 AM Jiri Pirko <jiri@resnulli.us> wrote:
> >
> > From: Jiri Pirko <jiri@nvidia.com>
> >
> > Add a new "system_cc_decrypted" dma-buf heap to allow userspace to
> > allocate decrypted (shared) memory for confidential computing (CoCo)
> > VMs.
> >
> > On CoCo VMs, guest memory is encrypted by default. The hardware uses an
> > encryption bit in page table entries (C-bit on AMD SEV, "shared" bit on
> > Intel TDX) to control whether a given memory access is encrypted or
> > decrypted. The kernel's direct map is set up with encryption enabled,
> > so pages returned by alloc_pages() are encrypted in the direct map
> > by default. To make this memory usable for devices that do not support
> > DMA to encrypted memory (no TDISP support), it has to be explicitly
> > decrypted. A couple of things are needed to properly handle
> > decrypted memory for the dma-buf use case:
> >
> > - set_memory_decrypted() on the direct map after allocation:
> > Besides clearing the encryption bit in the direct map PTEs, this
> > also notifies the hypervisor about the page state change. On free,
> > the inverse set_memory_encrypted() must be called before returning
> > pages to the allocator. If re-encryption fails, pages
> > are intentionally leaked to prevent decrypted memory from being
> > reused as private.
> >
> > - pgprot_decrypted() for userspace and kernel virtual mappings:
> > Any new mapping of the decrypted pages, be it to userspace via
> > mmap or to kernel vmalloc space via vmap, creates PTEs independent
> > of the direct map. These must also have the encryption bit cleared,
> > otherwise accesses through them would see encrypted (garbage) data.
>
> So this only works on new mappings? What if there are existing
> mappings to the memory that will be converted to shared?
The set_memory_decrypted() is called during system_heap_allocate(), it
is not possible to change dynamically between encrypted/decrypted.
Once the heap is created every PTE is always created with the correct
pgprot.
Jason
next prev parent reply other threads:[~2026-03-09 15:50 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-05 12:36 [PATCH net-next v3 0/2] dma-buf: heaps: system: add an option to allocate explicitly decrypted memory Jiri Pirko
2026-03-05 12:36 ` [PATCH net-next v3 1/2] dma-mapping: introduce DMA_ATTR_CC_DECRYPTED for pre-decrypted memory Jiri Pirko
2026-03-08 10:19 ` Leon Romanovsky
2026-03-09 8:57 ` Jiri Pirko
2026-03-09 13:15 ` Jason Gunthorpe
2026-03-09 14:02 ` Leon Romanovsky
2026-03-09 15:18 ` Jason Gunthorpe
2026-03-09 17:51 ` Jiri Pirko
2026-03-12 0:34 ` Jason Gunthorpe
2026-03-12 9:03 ` Jiri Pirko
2026-03-12 12:06 ` Jason Gunthorpe
2026-03-12 13:27 ` Jiri Pirko
2026-03-09 12:56 ` Petr Tesarik
2026-03-09 13:01 ` Jiri Pirko
2026-03-09 13:17 ` Jason Gunthorpe
2026-03-11 14:19 ` Jiri Pirko
2026-03-05 12:36 ` [PATCH net-next v3 2/2] dma-buf: heaps: system: add system_cc_decrypted heap for explicitly decrypted memory Jiri Pirko
2026-03-09 15:39 ` Peter Gonda
2026-03-09 15:50 ` Jason Gunthorpe [this message]
2026-03-05 12:40 ` [PATCH net-next v3 0/2] dma-buf: heaps: system: add an option to allocate " Jiri Pirko
2026-03-17 13:24 ` Mostafa Saleh
2026-03-17 13:37 ` Jiri Pirko
2026-03-17 15:40 ` Mostafa Saleh
2026-03-24 12:00 ` Jason Gunthorpe
2026-03-24 12:14 ` Mostafa Saleh
2026-03-24 12:24 ` Jason Gunthorpe
2026-03-24 17:36 ` Mostafa Saleh
2026-03-24 17:57 ` Jason Gunthorpe
2026-03-24 18:32 ` Mostafa Saleh
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=20260309155015.GP1687929@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=Brian.Starkey@arm.com \
--cc=aneesh.kumar@kernel.org \
--cc=ashish.kalra@amd.com \
--cc=benjamin.gaignard@collabora.com \
--cc=catalin.marinas@arm.com \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=iommu@lists.linux.dev \
--cc=jiri@resnulli.us \
--cc=john.allen@amd.com \
--cc=jstultz@google.com \
--cc=leon@kernel.org \
--cc=linaro-mm-sig@lists.linaro.org \
--cc=linux-coco@lists.linux.dev \
--cc=linux-media@vger.kernel.org \
--cc=m.szyprowski@samsung.com \
--cc=pgonda@google.com \
--cc=ptesarik@suse.com \
--cc=robin.murphy@arm.com \
--cc=sean.anderson@linux.dev \
--cc=steven.price@arm.com \
--cc=sumit.semwal@linaro.org \
--cc=suravee.suthikulpanit@amd.com \
--cc=suzuki.poulose@arm.com \
--cc=thomas.lendacky@amd.com \
--cc=tjmercier@google.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