memcg: dynamically allocate lruvec_stats

To decouple the dependency of lruvec_stats on NR_VM_NODE_STAT_ITEMS, we
need to dynamically allocate lruvec_stats in the mem_cgroup_per_node
structure.  Also move the definition of lruvec_stats_percpu and
lruvec_stats and related functions to the memcontrol.c to facilitate later
patches.  No functional changes in the patch.

Link: https://lkml.kernel.org/r/20240501172617.678560-3-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: T.J. Mercier <tjmercier@google.com>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 6 insertions, 56 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9aba0d0462ca..ab8a6e884375 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -83,6 +83,8 @@ enum mem_cgroup_events_target {
 
 struct memcg_vmstats_percpu;
 struct memcg_vmstats;
+struct lruvec_stats_percpu;
+struct lruvec_stats;
 
 struct mem_cgroup_reclaim_iter {
 	struct mem_cgroup *position;
@@ -90,25 +92,6 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
-struct lruvec_stats_percpu {
-	/* Local (CPU and cgroup) state */
-	long state[NR_VM_NODE_STAT_ITEMS];
-
-	/* Delta calculation for lockless upward propagation */
-	long state_prev[NR_VM_NODE_STAT_ITEMS];
-};
-
-struct lruvec_stats {
-	/* Aggregated (CPU and subtree) state */
-	long state[NR_VM_NODE_STAT_ITEMS];
-
-	/* Non-hierarchical (CPU aggregated) state */
-	long state_local[NR_VM_NODE_STAT_ITEMS];
-
-	/* Pending child counts during tree propagation */
-	long state_pending[NR_VM_NODE_STAT_ITEMS];
-};
-
 /*
  * per-node information in memory controller.
  */
@@ -116,7 +99,7 @@ struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
 	struct lruvec_stats_percpu __percpu	*lruvec_stats_percpu;
-	struct lruvec_stats			lruvec_stats;
+	struct lruvec_stats			*lruvec_stats;
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
@@ -1037,42 +1020,9 @@ static inline void mod_memcg_page_state(struct page *page,
 }
 
 unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
-
-static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
-					      enum node_stat_item idx)
-{
-	struct mem_cgroup_per_node *pn;
-	long x;
-
-	if (mem_cgroup_disabled())
-		return node_page_state(lruvec_pgdat(lruvec), idx);
-
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = READ_ONCE(pn->lruvec_stats.state[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
-						    enum node_stat_item idx)
-{
-	struct mem_cgroup_per_node *pn;
-	long x = 0;
-
-	if (mem_cgroup_disabled())
-		return node_page_state(lruvec_pgdat(lruvec), idx);
-
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
+unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
+unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+				      enum node_stat_item idx);
 
 void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
 void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);