[PATCHv3] mm: skip CMA pages when they are not available

[zhaoyang.huang]

From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>

This patch fixes unproductive reclaiming of CMA pages by skipping them when they
are not available for current context. It is arise from bellowing OOM issue, which
caused by large proportion of MIGRATE_CMA pages among free pages.

[   36.172486] [03-19 10:05:52.172] ActivityManager: page allocation failure: order:0, mode:0xc00(GFP_NOIO), nodemask=(null),cpuset=foreground,mems_allowed=0
[   36.189447] [03-19 10:05:52.189] DMA32: 0*4kB 447*8kB (C) 217*16kB (C) 124*32kB (C) 136*64kB (C) 70*128kB (C) 22*256kB (C) 3*512kB (C) 0*1024kB 0*2048kB 0*4096kB = 35848kB
[   36.193125] [03-19 10:05:52.193] Normal: 231*4kB (UMEH) 49*8kB (MEH) 14*16kB (H) 13*32kB (H) 8*64kB (H) 2*128kB (H) 0*256kB 1*512kB (H) 0*1024kB 0*2048kB 0*4096kB = 3236kB
...
[   36.234447] [03-19 10:05:52.234] SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
[   36.234455] [03-19 10:05:52.234] cache: ext4_io_end, object size: 64, buffer size: 64, default order: 0, min order: 0
[   36.234459] [03-19 10:05:52.234] node 0: slabs: 53,objs: 3392, free: 0

Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
---
v2: update commit message and fix build error when CONFIG_CMA is not set
V3: update code and comments
---
---
 mm/vmscan.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd6637f..17cd246 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2192,7 +2192,24 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
 	}
 
 }
-
+#ifdef CONFIG_CMA
+/*
+ * It is waste of effort to scan and reclaim CMA pages if it is not available
+ * for current allocation context
+ */
+static bool skip_cma(struct page *page, struct scan_control *sc)
+{
+	if (!current_is_kswapd() && gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE
+		&& get_pageblock_migratetype(page) == MIGRATE_CMA)
+		return true;
+	return false;
+}
+#else
+static bool skip_cma(struct page *page, struct scan_control *sc)
+{
+	return false;
+}
+#endif
 /*
  * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
  *
@@ -2225,10 +2242,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
 	unsigned long scan, total_scan, nr_pages;
+	struct page *page;
 	LIST_HEAD(folios_skipped);
 
 	total_scan = 0;
 	scan = 0;
+
 	while (scan < nr_to_scan && !list_empty(src)) {
 		struct list_head *move_to = src;
 		struct folio *folio;
@@ -2239,12 +2258,14 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 		nr_pages = folio_nr_pages(folio);
 		total_scan += nr_pages;
 
-		if (folio_zonenum(folio) > sc->reclaim_idx) {
+		page = &folio->page;
+
+		if (folio_zonenum(folio) > sc->reclaim_idx
+			|| skip_cma(page, sc)) {
 			nr_skipped[folio_zonenum(folio)] += nr_pages;
 			move_to = &folios_skipped;
 			goto move;
 		}
-
 		/*
 		 * Do not count skipped folios because that makes the function
 		 * return with no isolated folios if the LRU mostly contains
-- 
1.9.1