RDMA/bnxt_re: zero shared page before exposing to userspace
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ 1ac5a404797523cedaf424a3aaa3cf8f9548dff8 · < e2b143df29003d2704b51f62e9297006953dbacb| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
RDMA/bnxt_re: zero shared page before exposing to userspace
bnxt_re_alloc_ucontext() allocates uctx->shpg via __get_free_page(GFP_KERNEL). The buddy allocator does not zero pages without __GFP_ZERO, so the page contains stale kernel data from whatever object most recently freed it.
The page is then mapped into userspace via vm_insert_page() under BNXT_RE_MMAP_SH_PAGE in bnxt_re_mmap(). The driver only ever writes 4 bytes (a u32 AVID) at offset BNXT_RE_AVID_OFFT (0x10) inside bnxt_re_create_ah(); the remaining 4092 bytes of the page are exposed to userspace unsanitised, leaking kernel memory contents.
Any user with access to /dev/infiniband/uverbsX on a host with a bnxt_re device (typically rdma group membership) can read this data via a single mmap() at pgoff 0 after IB_USER_VERBS_CMD_GET_CONTEXT.
Other shared pages in the same file already use get_zeroed_page() correctly:
drivers/infiniband/hw/bnxt_re/ib_verbs.c srq->uctx_srq_page = (void *)get_zeroed_page(GFP_KERNEL); cq->uctx_cq_page = (void *)get_zeroed_page(GFP_KERNEL);
uctx->shpg is the only outlier. Bring it in line with the existing convention by switching to get_zeroed_page().
From the CVE record · Linux
The Linux kernel's bnxt_re driver maps a shared page into userspace without clearing stale kernel data. A local user with access to /dev/infiniband/uverbsX on a host with a bnxt_re device can read that data; no other user interaction is needed.
Administrators running Linux kernels on hosts with a bnxt_re device should check their systems; affected versions were not specified.