torvalds/linux
3
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-04-04 13:39:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "sched/numa: add statistics of numa balance task"

Browse Source 
This reverts commit ad6b26b6a0.

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: ad6b26b6a0 ("sched/numa: add statistics of numa balance task")
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Closes: https://lore.kernel.org/all/CAE4VaGBLJxpd=NeRJXpSCuw=REhC5LWJpC29kDy-Zh2ZDyzQZA@mail.gmail.com/
Reported-by: Srikanth Aithal <Srikanth.Aithal@amd.com>
Reported-by: Suneeth D <Suneeth.D@amd.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Hladky <jhladky@redhat.com>
Cc: Libo Chen <libo.chen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Chen Yu
2025-07-04 21:56:20 +08:00
committed by Andrew Morton
parent 82241a83cd
commit db6cc3f4ac
7 changed files with 2 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
kernel/sched/core.c
View File

@@ -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);
}

4
kernel/sched/debug.c
View File

@@ -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);