On Tue, Nov 14, 2023 at 9:24 PM Liu Shixin <[email protected]> wrote:
>
> 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/
>
> Signed-off-by: Liu Shixin <[email protected]>
> Tested-by: Yosry Ahmed <[email protected]>
> Reviewed-by: "Huang, Ying" <[email protected]>
> Reviewed-by: Yosry Ahmed <[email protected]>
> ---
> v8->v9: Move the swapcache check after can_demote() and refector
> can_reclaim_anon_pages() a bit.
> v7->v8: Reset swapcache_only at the beginning of can_reclaim_anon_pages().
> v6->v7: Reset swapcache_only to zero after there are swap spaces.
> v5->v6: Fix NULL pointing derefence and hung task problem reported by Sachin.
>
> include/linux/swap.h | 6 ++++++
> mm/memcontrol.c | 8 ++++++++
> mm/vmscan.c | 47 ++++++++++++++++++++++++++++++++------------
> 3 files changed, 48 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index f6dd6575b905..3ba146ae7cf5 100644
> --- 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 774bd6e21e27..a76ec540d4a3 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -7865,6 +7865,14 @@ 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 506f8220c5fe..62a1c75f74ad 100644
> --- 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;
>
> @@ -312,25 +315,34 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
> int nid,
> struct scan_control *sc)
> {
> - if (memcg == NULL) {
> - /*
> - * For non-memcg reclaim, is there
> - * space in any swap device?
> - */
> - if (get_nr_swap_pages() > 0)
> - return true;
> - } else {
> - /* Is the memcg below its swap limit? */
> - if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
> - return true;
> - }
> + if (sc)
> + sc->swapcache_only = 0;
> +
> + /*
> + * For non-memcg reclaim, is there space in any swap device?
> + * Or is the memcg below its swap limit?
> + */
> + if ((!memcg && get_nr_swap_pages() > 0) ||
> + (memcg && mem_cgroup_get_nr_swap_pages(memcg) > 0))
> + return true;
>
> /*
> * The page can not be swapped.
> *
> * Can it be reclaimed from this node via demotion?
> */
> - return can_demote(nid, sc);
> + if (can_demote(nid, sc))
> + return true;
> +
> + /* Is there any swapcache pages to reclaim? */
> + if ((!memcg && total_swapcache_pages() > 0) ||
> + (memcg && mem_cgroup_get_nr_swapcache_pages(memcg) > 0)) {
The above can return false positives if there are multiple nodes, so
it needs to be per node or lruvec, i.e., node_page_state() or
lruvec_page_state_local().