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, 75 insertions, 12 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 96b72a6e04ba..cf6819a3310d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -575,6 +575,60 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 	return mz;
 }
 
+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];
+};
+
+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;
+}
+
+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;
+}
+
 /* Subset of vm_event_item to report for memcg event stats */
 static const unsigned int memcg_vm_event_stat[] = {
 	PGPGIN,
@@ -5486,18 +5540,25 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
+	pn->lruvec_stats = kzalloc_node(sizeof(struct lruvec_stats), GFP_KERNEL,
+					node);
+	if (!pn->lruvec_stats)
+		goto fail;
+
 	pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
 						   GFP_KERNEL_ACCOUNT);
-	if (!pn->lruvec_stats_percpu) {
-		kfree(pn);
-		return 1;
-	}
+	if (!pn->lruvec_stats_percpu)
+		goto fail;
 
 	lruvec_init(&pn->lruvec);
 	pn->memcg = memcg;
 
 	memcg->nodeinfo[node] = pn;
 	return 0;
+fail:
+	kfree(pn->lruvec_stats);
+	kfree(pn);
+	return 1;
 }
 
 static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
@@ -5508,6 +5569,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 		return;
 
 	free_percpu(pn->lruvec_stats_percpu);
+	kfree(pn->lruvec_stats);
 	kfree(pn);
 }
 
@@ -5860,18 +5922,19 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 
 	for_each_node_state(nid, N_MEMORY) {
 		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
-		struct mem_cgroup_per_node *ppn = NULL;
+		struct lruvec_stats *lstats = pn->lruvec_stats;
+		struct lruvec_stats *plstats = NULL;
 		struct lruvec_stats_percpu *lstatc;
 
 		if (parent)
-			ppn = parent->nodeinfo[nid];
+			plstats = parent->nodeinfo[nid]->lruvec_stats;
 
 		lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
 
 		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
-			delta = pn->lruvec_stats.state_pending[i];
+			delta = lstats->state_pending[i];
 			if (delta)
-				pn->lruvec_stats.state_pending[i] = 0;
+				lstats->state_pending[i] = 0;
 
 			delta_cpu = 0;
 			v = READ_ONCE(lstatc->state[i]);
@@ -5882,12 +5945,12 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 			}
 
 			if (delta_cpu)
-				pn->lruvec_stats.state_local[i] += delta_cpu;
+				lstats->state_local[i] += delta_cpu;
 
 			if (delta) {
-				pn->lruvec_stats.state[i] += delta;
-				if (ppn)
-					ppn->lruvec_stats.state_pending[i] += delta;
+				lstats->state[i] += delta;
+				if (plstats)
+					plstats->state_pending[i] += delta;
 			}
 		}
 	}