memcg: make mod_memcg_state re-entrant safe against irqs

Let's make mod_memcg_state re-entrant safe against irqs.  The only thing
needed is to convert the usage of __this_cpu_add() to this_cpu_add().  In
addition, with re-entrant safety, there is no need to disable irqs.

mod_memcg_state() is not safe against nmi, so let's add warning if someone
tries to call it in nmi context.

Link: https://lkml.kernel.org/r/20250514184158.3471331-4-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: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9ed75f82b858867476dc422765fe2b390aac5a47..92861ff3c43fcaf863ded13a1230dcef6f848bff 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -903,19 +903,9 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
                                            struct mem_cgroup *oom_domain);
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
-void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
-                      int val);
-
 /* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-                                  enum memcg_stat_item idx, int val)
-{
-       unsigned long flags;
-
-       local_irq_save(flags);
-       __mod_memcg_state(memcg, idx, val);
-       local_irq_restore(flags);
-}
+void mod_memcg_state(struct mem_cgroup *memcg,
+                    enum memcg_stat_item idx, int val);
 
 static inline void mod_memcg_page_state(struct page *page,
                                        enum memcg_stat_item idx, int val)
@@ -1375,12 +1365,6 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 {
 }
 
-static inline void __mod_memcg_state(struct mem_cgroup *memcg,
-                                    enum memcg_stat_item idx,
-                                    int nr)
-{
-}
-
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
                                   enum memcg_stat_item idx,
                                   int nr)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 82b51e1b36f06e80632ab9ec1cc42b29e99068f7..25d5b198c8af2f1c87b2fe430db8b8e1a6071250 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -679,12 +679,12 @@ static int memcg_state_val_in_pages(int idx, int val)
 }
 
 /**
- * __mod_memcg_state - update cgroup memory statistics
+ * mod_memcg_state - update cgroup memory statistics
  * @memcg: the memory cgroup
  * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
  * @val: delta to add to the counter, can be negative
  */
-void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
+void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
                       int val)
 {
        int i = memcg_stats_index(idx);
@@ -698,7 +698,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
 
        cpu = get_cpu();
 
-       __this_cpu_add(memcg->vmstats_percpu->state[i], val);
+       this_cpu_add(memcg->vmstats_percpu->state[i], val);
        val = memcg_state_val_in_pages(idx, val);
        memcg_rstat_updated(memcg, val, cpu);
        trace_mod_memcg_state(memcg, idx, val);
@@ -2918,7 +2918,7 @@ static void drain_obj_stock(struct obj_stock_pcp *stock)
 
                        memcg = get_mem_cgroup_from_objcg(old);
 
-                       __mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
+                       mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
                        memcg1_account_kmem(memcg, -nr_pages);
                        if (!mem_cgroup_is_root(memcg))
                                memcg_uncharge(memcg, nr_pages);