[PATCH 5/9] mm/damon/{p,v}addr: skip folios already on the migration target node

[SJ Park <sj@kernel.org>]

From: Aveline Noir <jm5905938@gmail.com>

While measuring DAMOS migration overhead, I found that the target_nid
path isolates folios already on the target node, then puts them back on
the LRU without migrating them.

Skip them before isolation in vaddr and paddr, as the vaddr explicit
destinations path already does.

In a synthetic same-node fvaddr test on a two-node x86-64 KVM guest (8
interleaved runs per kernel), guest-kernel cycles fell by about 29% with
4 KiB regions and 90% with 16 MiB regions. Median kdamond CPU time fell
by about 76% with 16 MiB regions, with no clear change with 4 KiB
regions.

Cc: Bijan Tabatabai <bijan311@gmail.com>
Signed-off-by: Aveline Noir <jm5905938@gmail.com>
Signed-off-by: SJ Park <sj@kernel.org>
---
Changes from v1
- v1: https://lore.kernel.org/179320218513.2.7432933245840036676.damon-same-node-skip@gmail.com
- Put performance results in commit message.
- Use two tabs indentation for second parameter lines.
- Collect R-b: from SJ.
- Rebase to latest mm-new.

 mm/damon/paddr.c |  2 ++
 mm/damon/vaddr.c | 18 ++++++++++--------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 2cfdc356b4157..5b773012a8764 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -368,6 +368,8 @@ static unsigned long damon_pa_migrate(struct damon_region *r,
 		else
 			*sz_filter_passed += folio_size(folio) / addr_unit;
 
+		if (folio_nid(folio) == s->target_nid)
+			goto put_folio;
 		if (!folio_isolate_lru(folio))
 			goto put_folio;
 		node_stat_add_folio(folio, NR_ISOLATED_ANON +
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index b549496ea8e2c..1e65e7651cd98 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -786,14 +786,15 @@ struct damos_va_migrate_private {
  */
 static void damos_va_migrate_dests_add(struct folio *folio,
 		struct vm_area_struct *vma, unsigned long addr,
-		struct damos_migrate_dests *dests,
+		struct damos *s,
 		struct list_head *migration_lists)
 {
+	struct damos_migrate_dests *dests = &s->migrate_dests;
 	pgoff_t ilx;
 	int order;
 	unsigned int target;
 	unsigned int weight_total = 0;
-	int i;
+	int i, nid;
 
 	/*
 	 * If dests is empty, there is only one migration list corresponding
@@ -801,7 +802,8 @@ static void damos_va_migrate_dests_add(struct folio *folio,
 	 */
 	if (!dests->nr_dests) {
 		i = 0;
-		goto isolate;
+		nid = s->target_nid;
+		goto check_nid;
 	}
 
 	order = folio_order(folio);
@@ -821,12 +823,13 @@ static void damos_va_migrate_dests_add(struct folio *folio,
 			break;
 		target -= dests->weight_arr[i];
 	}
+	nid = dests->node_id_arr[i];
 
+check_nid:
 	/* If the folio is already in the right node, don't do anything */
-	if (folio_nid(folio) == dests->node_id_arr[i])
+	if (folio_nid(folio) == nid)
 		return;
 
-isolate:
 	if (!folio_isolate_lru(folio))
 		return;
 	node_stat_add_folio(folio, NR_ISOLATED_ANON +
@@ -840,7 +843,6 @@ static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct damos_va_migrate_private *priv = walk->private;
 	struct list_head *migration_lists = priv->migration_lists;
 	struct damos *s = priv->scheme;
-	struct damos_migrate_dests *dests = &s->migrate_dests;
 	struct folio *folio;
 	spinlock_t *ptl;
 	pte_t *start_pte, *pte, ptent;
@@ -858,7 +860,7 @@ static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 			goto huge_out;
 		if (damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd))
 			goto huge_out;
-		damos_va_migrate_dests_add(folio, walk->vma, addr, dests,
+		damos_va_migrate_dests_add(folio, walk->vma, addr, s,
 				migration_lists);
 huge_out:
 		spin_unlock(ptl);
@@ -883,7 +885,7 @@ static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 			continue;
 		if (damos_va_filter_out(s, folio, walk->vma, addr, pte, NULL))
 			continue;
-		damos_va_migrate_dests_add(folio, walk->vma, addr, dests,
+		damos_va_migrate_dests_add(folio, walk->vma, addr, s,
 				migration_lists);
 		page_idx = folio_page_idx(folio, pte_page(ptent));
 		nr = folio_nr_pages(folio) - page_idx;
-- 
2.47.3