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/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Fixes: ad6b26b6a0a7 ("sched/numa: add statistics of numa balance task")
Signed-off-by: Chen Yu <[e-mail]>
Reported-by: Jirka Hladky <[e-mail]>
Closes: https://lore.kernel.org/all/CAE4VaGBLJxpd=NeRJXpSCuw=[e-mail]/
Reported-by: Srikanth Aithal <[e-mail]>
Reported-by: Suneeth D <[e-mail]>
Acked-by: Michal Hocko <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Hladky <[e-mail]>
Cc: Libo Chen <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

Documentation/admin-guide/cgroup-v2.rst

···
 	  numa_hint_faults (npn)
 		Number of NUMA hinting faults.
 
-	  numa_task_migrated (npn)
-		Number of task migration by NUMA balancing.
-
-	  numa_task_swapped (npn)
-		Number of task swap by NUMA balancing.
-
 	  pgdemote_kswapd
 		Number of pages demoted by kswapd.
 

include/linux/sched.h

···
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
-#ifdef CONFIG_NUMA_BALANCING
-	u64				numa_task_migrated;
-	u64				numa_task_swapped;
-#endif
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;

include/linux/vm_event_item.h

···
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
-		NUMA_TASK_MIGRATE,
-		NUMA_TASK_SWAP,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,

kernel/sched/core.c

···
 #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;
···
 	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);
 }

kernel/sched/debug.c

···
 		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);

mm/memcontrol.c

···
 	NUMA_PAGE_MIGRATE,
 	NUMA_PTE_UPDATES,
 	NUMA_HINT_FAULTS,
-	NUMA_TASK_MIGRATE,
-	NUMA_TASK_SWAP,
 #endif
 };
 

mm/vmstat.c

···
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
-	"numa_task_migrated",
-	"numa_task_swapped",
 #endif
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",