From: Huang Ying <ying.huang@xxxxxxxxx> Subject: mm: free idle swap cache page after COW With commit 09854ba94c6a ("mm: do_wp_page() simplification"), after COW, the idle swap cache page (neither the page nor the corresponding swap entry is mapped by any process) will be left in the LRU list, even if it's in the active list or the head of the inactive list. So, the page reclaimer may take quite some overhead to reclaim these actually unused pages. To help the page reclaiming, in this patch, after COW, the idle swap cache page will be tried to be freed. To avoid to introduce much overhead to the hot COW code path, a) there's almost zero overhead for non-swap case via checking PageSwapCache() firstly. b) the page lock is acquired via trylock only. To test the patch, we used pmbench memory accessing benchmark with working-set larger than available memory on a 2-socket Intel server with a NVMe SSD as swap device. Test results shows that the pmbench score increases up to 23.8% with the decreased size of swap cache and swapin throughput. Link: https://lkml.kernel.org/r/20210601053143.1380078-1-ying.huang@xxxxxxxxx Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx> Suggested-by: Johannes Weiner <hannes@xxxxxxxxxxx> [use free_swap_cache()] Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Peter Xu <peterx@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxx> Cc: Tim Chen <tim.c.chen@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/swap.h | 5 +++++ mm/memory.c | 2 ++ mm/swap_state.c | 2 +- 3 files changed, 8 insertions(+), 1 deletion(-) --- a/include/linux/swap.h~mm-free-idle-swap-cache-page-after-cow +++ a/include/linux/swap.h @@ -446,6 +446,7 @@ extern void __delete_from_swap_cache(str extern void delete_from_swap_cache(struct page *); extern void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, @@ -551,6 +552,10 @@ static inline void put_swap_device(struc #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); +static inline void free_swap_cache(struct page *page) +{ +} + static inline void show_swap_cache_info(void) { } --- a/mm/memory.c~mm-free-idle-swap-cache-page-after-cow +++ a/mm/memory.c @@ -3023,6 +3023,8 @@ static vm_fault_t wp_page_copy(struct vm munlock_vma_page(old_page); unlock_page(old_page); } + if (page_copied) + free_swap_cache(old_page); put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; --- a/mm/swap_state.c~mm-free-idle-swap-cache-page-after-cow +++ a/mm/swap_state.c @@ -286,7 +286,7 @@ void clear_shadow_from_swap_cache(int ty * try_to_free_swap() _with_ the lock. * - Marcelo */ -static inline void free_swap_cache(struct page *page) +void free_swap_cache(struct page *page) { if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) { try_to_free_swap(page); _