A TODO has been sitting in task_tick_numa() regarding init'ing the task_numa_work() task_work in sched_fork() rather than in task_tick_numa(), so I figured I'd have a go at it.
Patches 1 & 2 do that, and patch 3 is a freebie cleanup. Briefly tested on a 2 * (Xeon E5-2690) system, didn't see any obvious breakage. Valentin Schneider (3): sched/fair: Move init_numa_balancing() below task_numa_work() sched/fair: Move task_numa_work() init to init_numa_balancing() sched/fair: Change task_numa_work() storage to static kernel/sched/fair.c | 93 +++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 46 deletions(-) -- 2.22.0
