bpf, x86: Fix per-CPU address resolution into an extended register
Summary
| CVE | CVE-2026-89581 |
| State | PUBLISHED |
| Assigner | Linux |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-09-11 20:19:42 UTC |
| Updated | 2026-09-11 20:19:42 UTC |
| Description | In the Linux kernel, the following vulnerability has been resolved:
bpf, x86: Fix per-CPU address resolution into an extended register
The destination of the per-CPU address MOV is encoded in ModRM.reg,
which is extended by REX.R, but the REX prefix is built with
add_1mod(), which sets REX.B. REX.B extends ModRM.rm and SIB.base, and
this instruction addresses memory as disp32 with no base, so the bit
has no effect at all and the high register bit is simply lost.
Every is_ereg() destination therefore resolves to the wrong register,
picking whichever one shares the low three bits:
R5 -> RAX R7 -> RBP R8 -> RSI R9 -> RDI
With BPF_REG_5, whose reg2hex is 0, the emitted
65 49 03 04 25 <off> add %gs:<off>,%rax
adds the per-CPU offset to RAX rather than R8. The destination keeps
the unadjusted address and RAX is clobbered, so the program goes on to
dereference a pointer that was never made per-CPU:
BUG: unable to handle page fault for address: 0000607e386a8894
RIP: bpf_prog_707837aafd2aa9ae_update_percpu_data+0x93/0xc9
Call Trace:
__bpf_prog_test_run_raw_tp+0x2dc/0x7d0
__flush_smp_call_function_queue+0x1e9/0xc80
Kernel panic - not syncing: Fatal exception in interrupt
R5 is the mildest of the four, aliasing a scratch register and faulting
at the store. R7 aliases RBP and would corrupt the frame pointer, R8
and R9 alias the argument registers.
Use add_2mod() so the register goes through REX.R, matching how
add_2reg() places it in ModRM.reg and how emit_priv_frame_ptr()
hardcodes 0x4c for the same instruction with R9. Encodings for the
non-extended registers are unchanged.
Problem showed up when trying to resurrect BPF_GCC CI (selftests built
with BPF_GCC).
This has gone unnoticed because clang reloads the address into R1
before each per-CPU access, so the destination is never an extended
register. GCC keeps several per-CPU addresses live at once, and
test_progs-bpf_gcc panics the kernel in global_percpu_data/init, where
the address of a .percpu variable ends up in R5. |
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|
| CNA |
Linux |
Linux |
affected 7bdbf7446305cb65c510c16d57cde82bc76b234a 638bc3aada8ecdece184d5c15b100d489c9cccd7 git |
Not specified |
| CNA |
Linux |
Linux |
affected 7bdbf7446305cb65c510c16d57cde82bc76b234a 6886642414f59f928728802dc2c972a9859e6310 git |
Not specified |
| CNA |
Linux |
Linux |
affected 7bdbf7446305cb65c510c16d57cde82bc76b234a 6a19b18d458881bf3269a357cc6dc6db5eef4369 git |
Not specified |
| CNA |
Linux |
Linux |
affected 7bdbf7446305cb65c510c16d57cde82bc76b234a 5bbbce02e500d47d8e259a45be5a7be9741d0533 git |
Not specified |
| CNA |
Linux |
Linux |
affected 6.10 |
Not specified |
| CNA |
Linux |
Linux |
unaffected 6.10 semver |
Not specified |
| CNA |
Linux |
Linux |
unaffected 6.12.109 6.12.* semver |
Not specified |
| CNA |
Linux |
Linux |
unaffected 6.18.50 6.18.* semver |
Not specified |
| CNA |
Linux |
Linux |
unaffected 7.2.4 7.2.* semver |
Not specified |
| CNA |
Linux |
Linux |
unaffected 7.3-rc1 * original_commit_for_fix |
Not specified |
References
| Reference | Source | Link | Tags |
|---|
| git.kernel.org/stable/c/6a19b18d458881bf3269a357cc6dc6db5eef4369 |
416baaa9-dc9f-4396-8d5f-8c081fb06d67 |
git.kernel.org |
|
| git.kernel.org/stable/c/6886642414f59f928728802dc2c972a9859e6310 |
416baaa9-dc9f-4396-8d5f-8c081fb06d67 |
git.kernel.org |
|
| git.kernel.org/stable/c/5bbbce02e500d47d8e259a45be5a7be9741d0533 |
416baaa9-dc9f-4396-8d5f-8c081fb06d67 |
git.kernel.org |
|
| git.kernel.org/stable/c/638bc3aada8ecdece184d5c15b100d489c9cccd7 |
416baaa9-dc9f-4396-8d5f-8c081fb06d67 |
git.kernel.org |
|
| CVE Program record |
CVE.ORG |
www.cve.org |
canonical |
| NVD vulnerability detail |
NVD |
nvd.nist.gov |
canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.