From db6cc3f4ac2e6cdc898fc9cbc8b32ae1bf56bdad Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 4 Jul 2025 21:56:20 +0800 Subject: Revert "sched/numa: add statistics of numa balance task" This reverts commit ad6b26b6a0a79166b53209df2ca1cf8636296382. This commit introduces per-memcg/task NUMA balance statistics, but unfortunately it introduced a NULL pointer exception due to the following race condition: After a swap task candidate was chosen, its mm_struct pointer was set to NULL due to task exit. Later, when performing the actual task swapping, the p->mm caused the problem. CPU0 CPU1 : ... task_numa_migrate task_numa_find_cpu task_numa_compare # a normal task p is chosen env->best_task = p # p exit: exit_signals(p); p->flags |= PF_EXITING exit_mm p->mm = NULL; migrate_swap_stop __migrate_swap_task((arg->src_task, arg->dst_cpu) count_memcg_event_mm(p->mm, NUMA_TASK_SWAP)# p->mm is NULL task_lock() should be held and the PF_EXITING flag needs to be checked to prevent this from happening. After discussion, the conclusion was that adding a lock is not worthwhile for some statistics calculations. Revert the change and rely on the tracepoint for this purpose. Link: https://lkml.kernel.org/r/20250704135620.685752-1-yu.c.chen@intel.com Link: https://lkml.kernel.org/r/20250708064917.BBD13C4CEED@smtp.kernel.org Fixes: ad6b26b6a0a7 ("sched/numa: add statistics of numa balance task") Signed-off-by: Chen Yu Reported-by: Jirka Hladky Closes: https://lore.kernel.org/all/CAE4VaGBLJxpd=NeRJXpSCuw=REhC5LWJpC29kDy-Zh2ZDyzQZA@mail.gmail.com/ Reported-by: Srikanth Aithal Reported-by: Suneeth D Acked-by: Michal Hocko Cc: Borislav Petkov Cc: Ingo Molnar Cc: Jiri Hladky Cc: Libo Chen Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- kernel/sched/core.c | 9 ++------- kernel/sched/debug.c | 4 ---- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ec68fc686bd7..81c6df746df1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) #ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { - __schedstat_inc(p->stats.numa_task_swapped); - count_vm_numa_event(NUMA_TASK_SWAP); - count_memcg_event_mm(p->mm, NUMA_TASK_SWAP); - if (task_on_rq_queued(p)) { struct rq *src_rq, *dst_rq; struct rq_flags srf, drf; @@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; - __schedstat_inc(p->stats.numa_task_migrated); - count_vm_numa_event(NUMA_TASK_MIGRATE); - count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE); + /* TODO: This is not properly updating schedstats */ + trace_sched_move_numa(p, curr_cpu, target_cpu); return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 9d71baf08075..557246880a7e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P_SCHEDSTAT(nr_failed_migrations_running); P_SCHEDSTAT(nr_failed_migrations_hot); P_SCHEDSTAT(nr_forced_migrations); -#ifdef CONFIG_NUMA_BALANCING - P_SCHEDSTAT(numa_task_migrated); - P_SCHEDSTAT(numa_task_swapped); -#endif P_SCHEDSTAT(nr_wakeups); P_SCHEDSTAT(nr_wakeups_sync); P_SCHEDSTAT(nr_wakeups_migrate); -- cgit v1.2.3