memcg: make memcg_rstat_updated nmi safe

Currently kernel maintains memory related stats updates per-cgroup to
optimize stats flushing.  The stats_updates is defined as atomic64_t which
is not nmi-safe on some archs.  Actually we don't really need 64bit atomic
as the max value stats_updates can get should be less than nr_cpus *
MEMCG_CHARGE_BATCH.  A normal atomic_t should suffice.

Also the function cgroup_rstat_updated() is still not nmi-safe but there
is parallel effort to make it nmi-safe, so until then let's ignore it in
the nmi context.

Link: https://lkml.kernel.org/r/20250519063142.111219-6-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: shakeelb

mm/memcontrol.c

@@ -531,7 +531,7 @@ struct memcg_vmstats {
 	unsigned long		events_pending[NR_MEMCG_EVENTS];
 
 	/* Stats updates since the last flush */
-	atomic64_t		stats_updates;
+	atomic_t		stats_updates;
 };
 
 /*
@@ -557,7 +557,7 @@ static u64 flush_last_time;
 
 static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&vmstats->stats_updates) >
+	return atomic_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
@@ -571,7 +571,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val,
 	if (!val)
 		return;
 
-	cgroup_rstat_updated(memcg->css.cgroup, cpu);
+	/* TODO: add to cgroup update tree once it is nmi-safe. */
+	if (!in_nmi())
+		cgroup_rstat_updated(memcg->css.cgroup, cpu);
 	statc_pcpu = memcg->vmstats_percpu;
 	for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) {
 		statc = this_cpu_ptr(statc_pcpu);
@@ -589,15 +591,15 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val,
 			continue;
 
 		stats_updates = this_cpu_xchg(statc_pcpu->stats_updates, 0);
-		atomic64_add(stats_updates, &statc->vmstats->stats_updates);
+		atomic_add(stats_updates, &statc->vmstats->stats_updates);
 	}
 }
 
 static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force)
 {
 	bool needs_flush = memcg_vmstats_needs_flush(memcg->vmstats);
 
-	trace_memcg_flush_stats(memcg, atomic64_read(&memcg->vmstats->stats_updates),
+	trace_memcg_flush_stats(memcg, atomic_read(&memcg->vmstats->stats_updates),
 		force, needs_flush);
 
 	if (!force && !needs_flush)
@@ -4119,8 +4121,8 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 	}
 	WRITE_ONCE(statc->stats_updates, 0);
 	/* We are in a per-cpu loop here, only do the atomic write once */
-	if (atomic64_read(&memcg->vmstats->stats_updates))
-		atomic64_set(&memcg->vmstats->stats_updates, 0);
+	if (atomic_read(&memcg->vmstats->stats_updates))
+		atomic_set(&memcg->vmstats->stats_updates, 0);
 }
 
 static void mem_cgroup_fork(struct task_struct *task)