GPU VulnDB

Database/Kernel, userspace & hypervisor

Linux kernel BPF verifier: LD_ABS/LD_IND implicit exit breaks backtracking, causing crash or unsound pruning

CVSS 5.5CVE-2026-98085Kernel, userspace & hypervisorcurated

Impact

BPF_LD ABS and IND instructions have an implicit exit from the current subprogram, and precision backtracking did not handle that edge. Backtracking then edited precision marks in the caller's frame while reading the callee's instructions. According to the fix, this causes segmentation faults during verification (a kernel crash) or unsound state pruning, which could let an unsafe program through. This is a different mechanism from the bpf_loop precision bug published alongside it.

Who can reach it

A local user who can load BPF programs: root, a holder of CAP_BPF, or any user if unprivileged BPF is enabled (disabled by default on most distributions). On GPU nodes, the exposure is privileged pods or agents granted BPF capabilities.

What to do

Update to a stable kernel that carries the referenced fix commits, then drain and reboot each node. Until then, keep unprivileged BPF disabled and withhold CAP_BPF and CAP_SYS_ADMIN from tenant workloads. The record does not name fixed versions.

References

Related entries

All Kernel, userspace & hypervisor entries

This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.