Last Modified: Jan 26, 2026
Affected Product(s):
BIG-IP TMOS
Known Affected Versions:
17.1.1.1, 17.1.1.2, 17.1.1.3, 17.1.1.4, 17.1.2, 17.1.2.1, 17.1.2.2, 17.1.3
Opened: Oct 24, 2025 Severity: 2-Critical
A vCMP guest may become unresponsive for approximately 600 seconds, during which time: - Odd-numbered CPUs assigned to the guest (for example, CPUs 1, 3, 5, 7, 9, 11) show 100% utilization. - No logs, statistics, or management-plane responses are generated. - Kernel logs report NMI watchdog soft lockup messages indicating a kernel deadlock. - The issue triggers a failover event and a restart of all services on the affected guest. Kernel logs indicate the lockup occurs on control-plane CPUs and is associated with memory management and TLB flush operations.
-- Temporary loss of management and control-plane responsiveness for the vCMP guest. -- Automatic failover to a standby unit may occur. -- Restart of BIG-IP services on the affected guest. -- Potential disruption to traffic handling during failover, depending on deployment architecture.
This issue may occur under the following conditions: -- vCMP guest running on a BIG-IP system. -- Guest operating under a Linux 3.10-based kernel. -- High control-plane activity involving memory operations (for example, process creation, termination, or memory unmapping). -- Issue observed in virtualized environments (for example, KVM-based platforms). -- Exact steps to reproduce are currently unknown.
None.
None