mm: vmscan: try to reclaim swapcache pages if no swap space

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@mail.gmail.com/
[2]. https://lore.kernel.org/linux-mm/CAJD7tkafz_2XAuqE8tGLPEcpLngewhUo=5US14PAtSM9tLBUQg@mail.gmail.com/

Link: https://lore.kernel.org/lkml/CAJD7tkZAfgncV+KbKr36=eDzMnT=9dZOT0dpMWcurHLr6Do+GA@mail.gmail.com/
Link: https://lkml.kernel.org/r/20230830035600.1656792-1-liushixin2@huawei.com
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Tested-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index f6dd6575b90545c3c927efbb033c1134e091b69a..3ba146ae7cf5db7766b2cd3a3d7cdf6ae1ce31ae 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -659,6 +659,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p
 }
 
 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)
@@ -681,6 +682,11 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
        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();

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b226090fd9061c6261ace5a09850ebcc0c183060..564aa8f25b7187985680f8204629b33af07ebe29 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7866,6 +7866,14 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
        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;

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5dc581cac225144b3bdb748341cad5026e1e24a9..e78235927deede9d42c044ecca861ee3bf5f1971 100644 (file)
--- a/mm/vmscan.c
+++ b/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 +322,20 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
                 */
                if (get_nr_swap_pages() > 0)
                        return true;
+               /* Is there any swapcache pages to reclaim? */
+               if (total_swapcache_pages() > 0) {
+                       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) {
+                       sc->swapcache_only = 1;
+                       return true;
+               }
        }
 
        /*
@@ -1584,6 +1597,19 @@ static bool skip_cma(struct folio *folio, struct scan_control *sc)
 }
 #endif
 
+static bool skip_isolate(struct folio *folio, struct scan_control *sc,
+                        enum lru_list lru)
+{
+       if (folio_zonenum(folio) > sc->reclaim_idx)
+               return true;
+       if (skip_cma(folio, sc))
+               return true;
+       if (unlikely(sc->swapcache_only && !is_file_lru(lru) &&
+           !folio_test_swapcache(folio)))
+               return true;
+       return false;
+}
+
 /*
  * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
  *
@@ -1630,8 +1656,7 @@ 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 ||
-                               skip_cma(folio, sc)) {
+               if (skip_isolate(folio, sc, lru)) {
                        nr_skipped[folio_zonenum(folio)] += nr_pages;
                        move_to = &folios_skipped;
                        goto move;