PT-2026-106690 · Linux · Linux
CVE-2026-98361
·
Published
2026-10-06
·
Updated
2026-10-06
None
No severity ratings or metrics are available. When they are, we'll update the corresponding info on the page.
In the Linux kernel, the following vulnerability has been resolved:
RDMA/rxe: Restore HMM PFN WRITE check in ODP write paths
Commit 0b261d7c1cd3 ("RDMA/rxe: Break endless pagefault loop for RO
pages") dropped the access permission test from rxe check pagefault()
and left only HMM PFN VALID. A page faulted in read-only, for example
a page-cache folio behind a PROT READ file mapping, then satisfies the
check and ODP write operations (RDMA WRITE, RDMA READ response, SEND
payload, atomics) modify it through kmap without ever breaking CoW.
An unprivileged user can register an ODP MR over such a mapping and
have incoming RDMA traffic overwrite the page cache of a file it only
holds O RDONLY, including /etc/passwd or setuid binaries. This is the
same primitive class as Dirty COW and CVE-2022-2590.
mlx5 has the missing invariant: its ODP path sets the device write bit
only for pfns that carry HMM PFN WRITE. Restore it in rxe by requiring
HMM PFN WRITE in rxe check pagefault() for every operation except
RXE PAGEFAULT RDONLY. A write to a non-writable VMA now fails the one
fault attempt with -EPERM from hmm vma fault() instead of re-faulting
forever. For a writable VMA the fault breaks CoW and the write lands
in the private page.
Keep pmem flushes on the read-only check. arch wb cache pmem() never
modifies memory, and the FLUSH access bits do not make the umem
writable, so classifying flushes as writes would make every flush
against a flush-only MR fail.
Found an issue in the description? Have something to add? Feel free to write us 👾
Related Identifiers
Affected Products
Linux