[PATCH -V8 2/6] memory tiering: add page promotion counter

[Huang Ying <ying.huang@xxxxxxxxx>]

To distinguish the number of the memory tiering promoted pages from
that of the originally inter-socket NUMA balancing migrated pages.
The counter is per-node (count in the target node).  So this can be
used to identify promotion imbalance among the NUMA nodes.

Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
Cc: Wei Xu <weixugc@xxxxxxxxxx>
Cc: osalvador <osalvador@xxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
---
 include/linux/mmzone.h |  3 +++
 include/linux/node.h   |  5 +++++
 mm/migrate.c           | 11 +++++++++--
 mm/vmstat.c            |  3 +++
 4 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6a1d79d84675..37ccd6158765 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -209,6 +209,9 @@ enum node_stat_item {
 	NR_PAGETABLE,		/* used for pagetables */
 #ifdef CONFIG_SWAP
 	NR_SWAPCACHE,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	PGPROMOTE_SUCCESS,	/* promote successfully */
 #endif
 	NR_VM_NODE_STAT_ITEMS
 };
diff --git a/include/linux/node.h b/include/linux/node.h
index 8e5a29897936..26e96fcc66af 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -181,4 +181,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
 
 #define to_node(device) container_of(device, struct node, dev)
 
+static inline bool node_is_toptier(int node)
+{
+	return node_state(node, N_CPU);
+}
+
 #endif /* _LINUX_NODE_H_ */
diff --git a/mm/migrate.c b/mm/migrate.c
index a159a36dd412..6f7a6e2ef41f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2163,6 +2163,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated;
 	int nr_remaining;
+	int nr_succeeded;
 	LIST_HEAD(migratepages);
 	new_page_t *new;
 	bool compound;
@@ -2201,7 +2202,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 
 	list_add(&page->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
-				     MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL);
+				     MIGRATE_ASYNC, MR_NUMA_MISPLACED,
+				     &nr_succeeded);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
@@ -2210,8 +2212,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 			putback_lru_page(page);
 		}
 		isolated = 0;
-	} else
+	} else {
 		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
+		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
+		    !node_is_toptier(page_to_nid(page)) && node_is_toptier(node))
+			mod_node_page_state(NODE_DATA(node), PGPROMOTE_SUCCESS,
+					    nr_succeeded);
+	}
 	BUG_ON(!list_empty(&migratepages));
 	return isolated;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8ce2620344b2..fff0ec94d795 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1236,6 +1236,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SWAP
 	"nr_swapcached",
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	"pgpromote_success",
+#endif
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
2.30.2