CVE-2026-99105

In the Linux kernel, the following vulnerability has been resolved:

sched ext: Fix stall when a task enqueued with SCX ENQ LAST lands back on its CPU's local DSQ

With SCX OPS ENQ LAST, the last runnable task on a CPU is passed to ops.enqueue() instead of being kept running. Exiting tasks without SCX OPS ENQ EXITING, migration disabled tasks without SCX OPS ENQ MIGRATION DISABLED and tasks on an offline rq skip ops.enqueue() and go straight to the local DSQ. This happens in put prev task scx() after the pick has settled on idle, so nothing reschedules the CPU, which idles with the task queued until an unrelated wakeup lands on it or the watchdog fires.

scx mitosis, which sets SCX OPS ENQ LAST without SCX OPS ENQ EXITING, hit this during mass cgroup teardown: exiting tasks stuck in exit mmap() for over 40 seconds.

A task put on the local DSQ runs, as anywhere else. If the SCX ENQ LAST enqueue left the task on this CPU's local DSQ, set need resched on the task being switched in, as proxy resched idle() does. resched curr() would flag the task being put instead, and schedule() clears that right after the pick.