The quilt patch titled
Subject: mm: vmscan: try to reclaim swapcache pages if no swap space
has been removed from the -mm tree. Its filename was
mm-vmscan-try-to-reclaim-swapcache-pages-if-no-swap-space.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Liu Shixin <liushixin2@xxxxxxxxxx>
Subject: mm: vmscan: try to reclaim swapcache pages if no swap space
Date: Wed, 30 Aug 2023 11:56:00 +0800
When spaces of swap devices are exhausted, only file pages can be
reclaimed. But there are still some swapcache pages in anon lru list.
This can lead to a premature out-of-memory.
The problem is found with such step:
Firstly, set a 9MB disk swap space, then create a cgroup with 10MB
memory limit, then runs an program to allocates about 15MB memory.
The problem occurs occasionally, which may need about 100 times [1].
Fix it by checking number of swapcache pages in can_reclaim_anon_pages().
If the number is not zero, return true and set swapcache_only to 1. When
scan anon lru list in swapcache_only mode, non-swapcache pages will be
skipped to isolate in order to accelerate reclaim efficiency.
However, in swapcache_only mode, the scan count still increased when scan
non-swapcache pages because there are large number of non-swapcache pages
and rare swapcache pages in swapcache_only mode, and if the non-swapcache
is skipped and do not count, the scan of pages in isolate_lru_folios() can
eventually lead to hung task, just as Sachin reported [2].
By the way, since there are enough times of memory reclaim before OOM, it
is not need to isolate too much swapcache pages in one times.
[1]. https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@xxxxxxxxxxxxxx/
[2]. https://lore.kernel.org/linux-mm/CAJD7tkafz_2XAuqE8tGLPEcpLngewhUo=5US14PAtSM9tLBUQg@xxxxxxxxxxxxxx/
[liushixin2@xxxxxxxxxx: fix NULL pointing derefence and hung task problem reported by Sachin]
Link: https://lkml.kernel.org/r/20230915083417.3190512-1-liushixin2@xxxxxxxxxx
Link: https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@xxxxxxxxxxxxxx/
Link: https://lkml.kernel.org/r/20230830035600.1656792-1-liushixin2@xxxxxxxxxx
Signed-off-by: Liu Shixin <liushixin2@xxxxxxxxxx>
Tested-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Reviewed-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Muchun Song <muchun.song@xxxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Sachin Sant <sachinp@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swap.h | 6 ++++++
mm/memcontrol.c | 8 ++++++++
mm/vmscan.c | 24 ++++++++++++++++++++++++
3 files changed, 38 insertions(+)
--- a/include/linux/swap.h~mm-vmscan-try-to-reclaim-swapcache-pages-if-no-swap-space
+++ a/include/linux/swap.h
@@ -655,6 +655,7 @@ static inline void mem_cgroup_uncharge_s
}
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
+extern long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg);
extern bool mem_cgroup_swap_full(struct folio *folio);
#else
static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
@@ -677,6 +678,11 @@ static inline long mem_cgroup_get_nr_swa
return get_nr_swap_pages();
}
+static inline long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
+{
+ return total_swapcache_pages();
+}
+
static inline bool mem_cgroup_swap_full(struct folio *folio)
{
return vm_swap_full();
--- a/mm/memcontrol.c~mm-vmscan-try-to-reclaim-swapcache-pages-if-no-swap-space
+++ a/mm/memcontrol.c
@@ -7898,6 +7898,14 @@ long mem_cgroup_get_nr_swap_pages(struct
return nr_swap_pages;
}
+long mem_cgroup_get_nr_swapcache_pages(struct mem_cgroup *memcg)
+{
+ if (mem_cgroup_disabled())
+ return total_swapcache_pages();
+
+ return memcg_page_state(memcg, NR_SWAPCACHE);
+}
+
bool mem_cgroup_swap_full(struct folio *folio)
{
struct mem_cgroup *memcg;
--- a/mm/vmscan.c~mm-vmscan-try-to-reclaim-swapcache-pages-if-no-swap-space
+++ a/mm/vmscan.c
@@ -136,6 +136,9 @@ struct scan_control {
/* Always discard instead of demoting to lower tier memory */
unsigned int no_demotion:1;
+ /* Swap space is exhausted, only reclaim swapcache for anon LRU */
+ unsigned int swapcache_only:1;
+
/* Allocation order */
s8 order;
@@ -319,10 +322,22 @@ static inline bool can_reclaim_anon_page
*/
if (get_nr_swap_pages() > 0)
return true;
+ /* Is there any swapcache pages to reclaim? */
+ if (total_swapcache_pages() > 0) {
+ if (sc)
+ sc->swapcache_only = 1;
+ return true;
+ }
} else {
/* Is the memcg below its swap limit? */
if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
return true;
+ /* Is there any swapcache pages in memcg to reclaim? */
+ if (mem_cgroup_get_nr_swapcache_pages(memcg) > 0) {
+ if (sc)
+ sc->swapcache_only = 1;
+ return true;
+ }
}
/*
@@ -1646,6 +1661,15 @@ static unsigned long isolate_lru_folios(
*/
scan += nr_pages;
+ /*
+ * Count non-swapcache too because the swapcache pages may
+ * be rare and it takes too much times here if not count
+ * the non-swapcache pages.
+ */
+ if (unlikely(sc->swapcache_only && !is_file_lru(lru) &&
+ !folio_test_swapcache(folio)))
+ goto move;
+
if (!folio_test_lru(folio))
goto move;
if (!sc->may_unmap && folio_mapped(folio))
_
Patches currently in -mm which might be from liushixin2@xxxxxxxxxx are
