mm: clean up and clarify lruvec lookup procedure

There is a per-memcg lruvec and a NUMA node lruvec.  Which one is being
used is somewhat confusing right now, and it's easy to make mistakes -
especially when it comes to global reclaim.

How it works: when memory cgroups are enabled, we always use the
root_mem_cgroup's per-node lruvecs.  When memory cgroups are not compiled
in or disabled at runtime, we use pgdat->lruvec.

Document that in a comment.

Due to the way the reclaim code is generalized, all lookups use the
mem_cgroup_lruvec() helper function, and nobody should have to find the
right lruvec manually right now.  But to avoid future mistakes, rename the
pgdat->lruvec member to pgdat->__lruvec and delete the convenience wrapper
that suggests it's a commonly accessed member.

While in this area, swap the mem_cgroup_lruvec() argument order.  The name
suggests a memcg operation, yet it takes a pgdat first and a memcg second.
I have to double take every time I call this.  Fix that.

Link: http://lkml.kernel.org/r/20191022144803.302233-3-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memcontrol.h

@@ -385,21 +385,21 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
 }
 
 /**
- * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
+ * mem_cgroup_lruvec - get the lru list vector for a memcg & node
- * @node: node of the wanted lruvec
  * @memcg: memcg of the wanted lruvec
  *
- * Returns the lru list vector holding pages for a given @node or a given
+ * Returns the lru list vector holding pages for a given @memcg &
- * @memcg. This can be the node lruvec, if the memory controller is disabled.
+ * @node combination. This can be the node lruvec, if the memory
+ * controller is disabled.
  */
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
-				struct mem_cgroup *memcg)
+					       struct pglist_data *pgdat)
 {
 	struct mem_cgroup_per_node *mz;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
-		lruvec = node_lruvec(pgdat);
+		lruvec = &pgdat->__lruvec;
 		goto out;
 	}
 
@@ -718,7 +718,7 @@ static inline void __mod_lruvec_page_state(struct page *page,
 		return;
 	}
 
-	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+	lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
 
@@ -889,16 +889,16 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
-				struct mem_cgroup *memcg)
+					       struct pglist_data *pgdat)
 {
-	return node_lruvec(pgdat);
+	return &pgdat->__lruvec;
 }
 
 static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 						    struct pglist_data *pgdat)
 {
-	return &pgdat->lruvec;
+	return &pgdat->__lruvec;
 }
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,

include/linux/mmzone.h

@@ -777,7 +777,13 @@ typedef struct pglist_data {
 #endif
 
 	/* Fields commonly accessed by the page reclaim scanner */
-	struct lruvec		lruvec;
+
+	/*
+	 * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED.
+	 *
+	 * Use mem_cgroup_lruvec() to look up lruvecs.
+	 */
+	struct lruvec		__lruvec;
 
 	unsigned long		flags;
 
@@ -800,11 +806,6 @@ typedef struct pglist_data {
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
 
-static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
-{
-	return &pgdat->lruvec;
-}
-
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {
 	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
@@ -842,7 +843,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 #ifdef CONFIG_MEMCG
 	return lruvec->pgdat;
 #else
-	return container_of(lruvec, struct pglist_data, lruvec);
+	return container_of(lruvec, struct pglist_data, __lruvec);
 #endif
 }
 

mm/memcontrol.c

@@ -777,7 +777,7 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	if (!memcg || memcg == root_mem_cgroup) {
 		__mod_node_page_state(pgdat, idx, val);
 	} else {
-		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		lruvec = mem_cgroup_lruvec(memcg, pgdat);
 		__mod_lruvec_state(lruvec, idx, val);
 	}
 	rcu_read_unlock();
@@ -1221,7 +1221,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
-		lruvec = &pgdat->lruvec;
+		lruvec = &pgdat->__lruvec;
 		goto out;
 	}
 
@@ -3634,7 +3634,7 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
 static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 					   int nid, unsigned int lru_mask)
 {
-	struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
+	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
 	unsigned long nr = 0;
 	enum lru_list lru;
 
@@ -5338,8 +5338,8 @@ static int mem_cgroup_move_account(struct page *page,
 	anon = PageAnon(page);
 
 	pgdat = page_pgdat(page);
-	from_vec = mem_cgroup_lruvec(pgdat, from);
+	from_vec = mem_cgroup_lruvec(from, pgdat);
-	to_vec = mem_cgroup_lruvec(pgdat, to);
+	to_vec = mem_cgroup_lruvec(to, pgdat);
 
 	spin_lock_irqsave(&from->move_lock, flags);
 

mm/page_alloc.c

@@ -6713,7 +6713,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 
 	pgdat_page_ext_init(pgdat);
 	spin_lock_init(&pgdat->lru_lock);
-	lruvec_init(node_lruvec(pgdat));
+	lruvec_init(&pgdat->__lruvec);
 }
 
 static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,

mm/slab.h

@@ -369,7 +369,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 	if (ret)
 		goto out;
 
-	lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
 	mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order);
 
 	/* transer try_charge() page references to kmem_cache */
@@ -393,7 +393,7 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 	rcu_read_lock();
 	memcg = READ_ONCE(s->memcg_params.memcg);
 	if (likely(!mem_cgroup_is_root(memcg))) {
-		lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
 		mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order));
 		memcg_kmem_uncharge_memcg(page, order, memcg);
 	} else {

mm/vmscan.c

@@ -2545,7 +2545,7 @@ out:
 static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
 			      struct scan_control *sc)
 {
-	struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
+	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long targets[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
@@ -3023,7 +3023,7 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
 		unsigned long refaults;
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		lruvec = mem_cgroup_lruvec(memcg, pgdat);
 		refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE);
 		lruvec->refaults = refaults;
 	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
@@ -3379,7 +3379,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
-		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
 		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,

mm/workingset.c

@@ -233,7 +233,7 @@ void *workingset_eviction(struct page *page)
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	lruvec = mem_cgroup_lruvec(pgdat, memcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	eviction = atomic_long_inc_return(&lruvec->inactive_age);
 	return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
 }
@@ -280,7 +280,7 @@ void workingset_refault(struct page *page, void *shadow)
 	memcg = mem_cgroup_from_id(memcgid);
 	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
-	lruvec = mem_cgroup_lruvec(pgdat, memcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	refault = atomic_long_read(&lruvec->inactive_age);
 	active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
 
@@ -345,7 +345,7 @@ void workingset_activation(struct page *page)
 	memcg = page_memcg_rcu(page);
 	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
-	lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
 	atomic_long_inc(&lruvec->inactive_age);
 out:
 	rcu_read_unlock();
@@ -426,7 +426,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 		struct lruvec *lruvec;
 		int i;
 
-		lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg);
+		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
 							 NR_LRU_BASE + i);