[PATCH RFC v3 02/17] mm/mglru: make generation page counters atomic

[Kairui Song via B4 Relay <devnull+kasong.tencent.com@kernel.org>]

From: Kairui Song <kasong@tencent.com>

No feature change, convert them to atomic so we can update them without
holding the LRU lock. There is no risk of overflow. The reader always
compares and uses zero instead if the counter values are negative. It
follows final consistency.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 include/linux/mm_inline.h |  6 ++----
 include/linux/mmzone.h    |  2 +-
 mm/vmscan.c               | 27 ++++++++++++---------------
 3 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 597f013c8e04..f52f02e8e5be 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -265,11 +265,9 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli
 	VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1);
 
 	if (old_gen >= 0)
-		WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone],
-			   lrugen->nr_pages[old_gen][type][zone] - delta);
+		atomic_long_sub(delta, &lrugen->nr_pages[old_gen][type][zone]);
 	if (new_gen >= 0)
-		WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone],
-			   lrugen->nr_pages[new_gen][type][zone] + delta);
+		atomic_long_add(delta, &lrugen->nr_pages[new_gen][type][zone]);
 
 	/* addition */
 	if (old_gen < 0) {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3b96d6c7123b..09ce82fa841a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -554,7 +554,7 @@ struct lru_gen_folio {
 	/* the multi-gen LRU lists, lazily sorted on eviction */
 	struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
 	/* the multi-gen LRU sizes, eventually consistent */
-	long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+	atomic_long_t nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
 	/* the exponential moving average of refaulted */
 	unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
 	/* the exponential moving average of evicted+protected */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 91295070ca33..0a29dbf9fa3f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3495,8 +3495,7 @@ static void reset_batch_size(struct lru_gen_mm_walk *walk)
 			continue;
 
 		walk->nr_pages[gen][type][zone] = 0;
-		WRITE_ONCE(lrugen->nr_pages[gen][type][zone],
-			   lrugen->nr_pages[gen][type][zone] + delta);
+		atomic_long_add(delta, &lrugen->nr_pages[gen][type][zone]);
 
 		if (lru_gen_is_active(lruvec, gen))
 			lru += LRU_ACTIVE;
@@ -4117,11 +4116,8 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
 				break;
 		}
 		flush_lru_batch(head, &batch_end, target_list);
-
-		WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone],
-			   lrugen->nr_pages[old_gen][type][zone] - delta);
-		WRITE_ONCE(lrugen->nr_pages[target_gen][type][zone],
-			   lrugen->nr_pages[target_gen][type][zone] + delta);
+		atomic_long_sub(delta, &lrugen->nr_pages[old_gen][type][zone]);
+		atomic_long_add(delta, &lrugen->nr_pages[target_gen][type][zone]);
 		if (!remaining)
 			return false;
 	}
@@ -4226,8 +4222,8 @@ static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness
 	for (type = 0; type < ANON_AND_FILE; type++) {
 		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 			enum lru_list lru = type * LRU_INACTIVE_FILE;
-			long delta = lrugen->nr_pages[prev][type][zone] -
-				     lrugen->nr_pages[next][type][zone];
+			long delta = atomic_long_read(&lrugen->nr_pages[prev][type][zone]) -
+				     atomic_long_read(&lrugen->nr_pages[next][type][zone]);
 
 			if (!delta)
 				continue;
@@ -4345,7 +4341,8 @@ static unsigned long lruvec_evictable_size(struct lruvec *lruvec, int swappiness
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
 			gen = lru_gen_from_seq(seq);
 			for (zone = 0; zone < MAX_NR_ZONES; zone++)
-				total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+				total += max(atomic_long_read(&lrugen->nr_pages[gen][type][zone]),
+					     0L);
 		}
 	}
 
@@ -4765,7 +4762,7 @@ static void __lru_gen_reparent_memcg(struct lruvec *child_lruvec, struct lruvec
 
 	for (i = 0; i < get_nr_gens(child_lruvec, type); i++) {
 		int gen = lru_gen_from_seq(child_lrugen->max_seq - i);
-		long nr_pages = child_lrugen->nr_pages[gen][type][zone];
+		long nr_pages = atomic_long_read(&child_lrugen->nr_pages[gen][type][zone]);
 		int child_lru_active = lru_gen_is_active(child_lruvec, gen) ? LRU_ACTIVE : 0;
 		int parent_lru_active = lru_gen_is_active(parent_lruvec, gen) ? LRU_ACTIVE : 0;
 
@@ -4773,9 +4770,8 @@ static void __lru_gen_reparent_memcg(struct lruvec *child_lruvec, struct lruvec
 		list_splice_tail_init(&child_lrugen->folios[gen][type][zone],
 				      &parent_lrugen->folios[gen][type][zone]);
 
-		WRITE_ONCE(child_lrugen->nr_pages[gen][type][zone], 0);
-		WRITE_ONCE(parent_lrugen->nr_pages[gen][type][zone],
-			   parent_lrugen->nr_pages[gen][type][zone] + nr_pages);
+		atomic_long_set(&child_lrugen->nr_pages[gen][type][zone], 0);
+		atomic_long_add(nr_pages, &parent_lrugen->nr_pages[gen][type][zone]);
 
 		if (lru_gen_is_active(child_lruvec, gen) != lru_gen_is_active(parent_lruvec, gen)) {
 			__update_lru_size(child_lruvec, lru + child_lru_active, zone, -nr_pages);
@@ -5855,7 +5851,8 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
 			char mark = full && seq < min_seq[type] ? 'x' : ' ';
 
 			for (zone = 0; zone < MAX_NR_ZONES; zone++)
-				size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+				size += max(atomic_long_read(&lrugen->nr_pages[gen][type][zone]),
+					    0L);
 
 			seq_printf(m, " %10lu%c", size, mark);
 		}

-- 
2.55.0