On 06/11/2026 15:30, Aneesh Kumar K.V wrote:
Suzuki K Poulose <[email protected]> writes:
On 04/11/2026 16:45, Aneesh Kumar K.V (Arm) wrote:
Confidential-computing guests may require memory shared with the host to
be aligned and transitioned in units larger than PAGE_SIZE. Several DMA
users need struct page-backed allocations satisfying these requirements.
Provide a common allocator instead of requiring each user to open-code
this sequence.
Add alloc_cc_shared_pages() and its node-aware variant. The allocator
rounds the requested size to the architecture's shared granule,
allocates suitably aligned contiguous pages and transitions the
complete range to shared state. It also preserves the caller's GFP
policy.
A private-to-shared transition may alter memory contents. Mask
__GFP_ZERO from the underlying allocation and when requested, clear the
complete transitioned range after cc_make_shared() succeeds.
This is not true for pKVM though. It is the other way around. i.e,
pages must be cleared before transition (e.g., from private to shared)
to make sure the contents don't leak into the host.
Do we need to handle such cases with a pre_conversion and
post_conversion hook ?
Patch 2 does something similar.
Ah, yes! Thanks
Cheers
Suzuki
-aneesh
