bpf: Fix NMI/tracepoint re-entry deadlock on lru locks
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
|
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
|
|
6.18.407.1.57.2In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix NMI/tracepoint re-entry deadlock on lru locks
NMI and tracepoint BPF programs can re-enter the per-CPU or global LRU lock that bpf_lru_pop_free()/push_free() already hold on the same CPU, AA-deadlocking. Lockdep reports "inconsistent {INITIAL USE} -> {IN-NMI}" on &l->lock (syzbot c69a0a2c816716f1e0d5) and "possible recursive locking detected" on &loc_l->lock (syzbot 18b26edb69b2e19f3b33).
Prior trylock and rqspinlock based fixes (see links) were nacked because compromised on reliability.
This patch converts every LRU lock site to rqspinlock_t and adds a recovery path for some failure windows to avoid node leaks.
Failure recovery:
- *_pop_free top-level: return NULL; prealloc_lru_pop() already treats that as no-free-element (-ENOMEM).
- Cross-CPU steal: skip the victim's locked loc_l, try next CPU.
From the CVE record · Linux
The Linux kernel’s BPF LRU locks can deadlock when an NMI or tracepoint BPF program re-enters a lock already held on the same CPU. This can occur during BPF LRU free-node operations; the input does not specify authentication requirements or user interaction.
Engineers running the Linux kernel should check whether their kernel includes the BPF LRU lock fix; affected versions are not specified.