From 7ae1e02abbfb50f70a4eb3f8b094e8b77dbbe4d0 Mon Sep 17 00:00:00 2001 From: Zhaoyang Huang Date: Wed, 31 May 2023 10:51:01 +0800 Subject: [PATCH] UPSTREAM: mm: skip CMA pages when they are not available This patch fixes unproductive reclaiming of CMA pages by skipping them when they are not available for current context. It arises from the below OOM issue, which was caused by a 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 This change further decreases the chance for wrong OOMs in the presence of a lot of CMA memory. [david@redhat.com: changelog addition] Link: https://lkml.kernel.org/r/1685501461-19290-1-git-send-email-zhaoyang.huang@unisoc.com Change-Id: I84f1145c38b5ff7b825f2122b33bc55997931bd7 Signed-off-by: Zhaoyang Huang Acked-by: David Hildenbrand Cc: ke.wang Cc: Matthew Wilcox Cc: Minchan Kim Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton (cherry picked from commit 5da226dbfce3a2f44978c2c7cf88166e69a6788b) Bug: 288383787 Bug: 291719697 Signed-off-by: Kalesh Singh --- mm/vmscan.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 73e96cd78b21..5d2260bbd04f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2181,6 +2181,25 @@ 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. Kswapd can not be enrolled as it can not + * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL + */ +static bool skip_cma(struct folio *folio, struct scan_control *sc) +{ + return !current_is_kswapd() && + gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && + get_pageblock_migratetype(&folio->page) == MIGRATE_CMA; +} +#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. * @@ -2227,7 +2246,8 @@ 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;