SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAnalyzed

CVE-2026-31406

In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes…

HIGH 7.8EPSS 0.16%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.16%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

Description

In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_list, &defer_free_list); cleanup_net() [Round 2] rcu_barrier(); net_complete_free() kmem_cache_free(net_cachep, net); nat_keepalive_work() // on freed net To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().

CVSS 3.1
7.8 HIGHCVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS
0.16% probability · 5th percentile
CISA KEV
Not listed
Affected
linux/linux kernel
Source
416baaa9-dc9f-4396-8d5f-8c081fb06d67

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.