On Wed, May 24, 2023 at 2:13 AM zhaoyang.huang
<zhaoyang.huang@xxxxxxxxxx> wrote:
>
> From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
>
> The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> forcefully, which lead to the coming up refault pages possess a large refault
> distance than it should be. These could affect the accuracy of thrashing when
> madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.
Doesn't workingset_eviction() in the following call chain already
handle nonresident page aging?:
reclaim_pages
reclaim_folio_list
shrink_folio_list
__remove_mapping
workingset_eviction
workingset_age_nonresident
>
> Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
> ---
> include/linux/swap.h | 2 +-
> mm/madvise.c | 4 ++--
> mm/vmscan.c | 8 +++++++-
> 3 files changed, 10 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 2787b84..0312142 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
> extern int vm_swappiness;
> long remove_mapping(struct address_space *mapping, struct folio *folio);
>
> -extern unsigned long reclaim_pages(struct list_head *page_list);
> +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
> #ifdef CONFIG_NUMA
> extern int node_reclaim_mode;
> extern int sysctl_min_unmapped_ratio;
> diff --git a/mm/madvise.c b/mm/madvise.c
> index b6ea204..61c8d7b 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> huge_unlock:
> spin_unlock(ptl);
> if (pageout)
> - reclaim_pages(&page_list);
> + reclaim_pages(mm, &page_list);
> return 0;
> }
>
> @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> arch_leave_lazy_mmu_mode();
> pte_unmap_unlock(orig_pte, ptl);
> if (pageout)
> - reclaim_pages(&page_list);
> + reclaim_pages(mm, &page_list);
> cond_resched();
>
> return 0;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 20facec..048c10b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
> return nr_reclaimed;
> }
>
> -unsigned long reclaim_pages(struct list_head *folio_list)
> +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)
You would also need to change Damon usage of reclaim_pages() here:
https://elixir.bootlin.com/linux/v6.4-rc1/source/mm/damon/paddr.c#L253
> {
> int nid;
> unsigned int nr_reclaimed = 0;
> LIST_HEAD(node_folio_list);
> unsigned int noreclaim_flag;
> + struct lruvec *lruvec;
> + struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
>
> if (list_empty(folio_list))
> return nr_reclaimed;
> @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
> }
>
> nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> + lruvec = &memcg->nodeinfo[nid]->lruvec;
> + workingset_age_nonresident(lruvec, -nr_reclaimed);
> nid = folio_nid(lru_to_folio(folio_list));
> } while (!list_empty(folio_list));
>
> nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> + lruvec = &memcg->nodeinfo[nid]->lruvec;
> + workingset_age_nonresident(lruvec, -nr_reclaimed);
>
> memalloc_noreclaim_restore(noreclaim_flag);
>
> --
> 1.9.1
>
