Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "zhaoyang.huang" <zhaoyang.huang@unisoc.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Matthew Wilcox <willy@infradead.org>,
        Minchan Kim <minchan@kernel.org>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>, <linux-mm@kvack.org>,
        <linux-kernel@vger.kernel.org>,
        Zhaoyang Huang <huangzhaoyang@gmail.com>, <ke.wang@unisoc.com>
Subject: [PATCHv4] mm: skip CMA pages when they are not available
Date:   Mon, 22 May 2023 14:36:03 +0800
Message-ID: <1684737363-31554-1-git-send-email-zhaoyang.huang@unisoc.com>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>

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@unisoc.com>
---
v2: update commit message and fix build error when CONFIG_CMA is not set
v3,v4: update code and comments
---
---
 mm/vmscan.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd6637f..20facec 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2193,6 +2193,26 @@ 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 folio *folio, struct scan_control *sc)
+{
+	if (!current_is_kswapd() &&
+			gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE &&
+			get_pageblock_migratetype(&folio->page) == MIGRATE_CMA)
+		return true;
+	return false;
+}
+#else
+static bool skip_cma(struct folio *folio, struct scan_control *sc)
+{
+	return false;
+}
+#endif
+
 /*
  * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
  *
@@ -2239,7 +2259,8 @@ 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) {
+		if (folio_zonenum(folio) > sc->reclaim_idx ||
+				skip_cma(folio, sc)) {
 			nr_skipped[folio_zonenum(folio)] += nr_pages;
 			move_to = &folios_skipped;
 			goto move;
-- 
1.9.1