From c3f32f75ac28d063d185a641e2f4aacb6db36dd5 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 25 Jun 2020 20:30:37 -0700 Subject: [PATCH 2376/2944] mm/memory: fix IO cost for anonymous page task #31256938 commit 0076f029cb2906d32baf3bf4401ef09663071d16 upstream With synchronous IO swap device, swap-in is directly handled in fault code. Since IO cost notation isn't added there, with synchronous IO swap device, LRU balancing could be wrongly biased. Fix it to count it in fault code. Link: http://lkml.kernel.org/r/1592288204-27734-4-git-send-email-iamjoonsoo.kim@lge.com Fixes: 314b57fb0460001 ("mm: balance LRU lists based on relative thrashing cache sizing") Signed-off-by: Joonsoo Kim Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: zhongjiang-ali Reviewed-by: Xunlei Pang --- mm/memory.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/memory.c b/mm/memory.c index dde0e79..7e6107b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2980,6 +2980,14 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } + /* + * XXX: Move to lru_cache_add() when it + * supports new vs putback + */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost_page(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); + lru_cache_add(page); swap_readpage(page, true); } -- 1.8.3.1