From ca707239e8a7958ffb1c31737d41cae1a674c938 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 19 May 2016 17:12:35 -0700 Subject: mm: update_lru_size warn and reset bad lru_size Though debug kernels have a VM_BUG_ON to help protect from misaccounting lru_size, non-debug kernels are liable to wrap it around: and then the vast unsigned long size draws page reclaim into a loop of repeatedly doing nothing on an empty list, without even a cond_resched(). That soft lockup looks confusingly like an over-busy reclaim scenario, with lots of contention on the lru_lock in shrink_inactive_list(): yet has a totally different origin. Help differentiate with a custom warning in mem_cgroup_update_lru_size(), even in non-debug kernels; and reset the size to avoid the lockup. But the particular bug which suggested this change was mine alone, and since fixed. Make it a WARN_ONCE: the first occurrence is the most informative, a flurry may follow, yet even when rate-limited little more is learnt. Signed-off-by: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Andres Lagar-Cavilla Cc: Yang Shi Cc: Ning Qu Cc: Mel Gorman Cc: Andres Lagar-Cavilla Cc: Konstantin Khlebnikov Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm_inline.h') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 712e8c37a200..d8cea81ab1ac 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -35,8 +35,8 @@ static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { int nr_pages = hpage_nr_pages(page); - mem_cgroup_update_lru_size(lruvec, lru, -nr_pages); list_del(&page->lru); + mem_cgroup_update_lru_size(lruvec, lru, -nr_pages); __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, -nr_pages); } -- cgit v1.2.3 From 9d5e6a9f22311b00a20ff9b072760ad3e73f0d99 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 19 May 2016 17:12:38 -0700 Subject: mm: update_lru_size do the __mod_zone_page_state Konstantin Khlebnikov pointed out (nearly four years ago, when lumpy reclaim was removed) that lru_size can be updated by -nr_taken once per call to isolate_lru_pages(), instead of page by page. Update it inside isolate_lru_pages(), or at its two callsites? I chose to update it at the callsites, rearranging and grouping the updates by nr_taken and nr_scanned together in both. With one exception, mem_cgroup_update_lru_size(,lru,) is then used where __mod_zone_page_state(,NR_LRU_BASE+lru,) is used; and we shall be adding some more calls in a future commit. Make the code a little smaller and simpler by incorporating stat update in lru_size update. The exception was move_active_pages_to_lru(), which aggregated the pgmoved stat update separately from the individual lru_size updates; but I still think this a simplification worth making. However, the __mod_zone_page_state is not peculiar to mem_cgroups: so better use the name update_lru_size, calls mem_cgroup_update_lru_size when CONFIG_MEMCG. Signed-off-by: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Andres Lagar-Cavilla Cc: Yang Shi Cc: Ning Qu Cc: Mel Gorman Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) (limited to 'include/linux/mm_inline.h') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index d8cea81ab1ac..5bd29ba4f174 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -22,22 +22,34 @@ static inline int page_is_file_cache(struct page *page) return !PageSwapBacked(page); } +static __always_inline void __update_lru_size(struct lruvec *lruvec, + enum lru_list lru, int nr_pages) +{ + __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages); +} + +static __always_inline void update_lru_size(struct lruvec *lruvec, + enum lru_list lru, int nr_pages) +{ +#ifdef CONFIG_MEMCG + mem_cgroup_update_lru_size(lruvec, lru, nr_pages); +#else + __update_lru_size(lruvec, lru, nr_pages); +#endif +} + static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - int nr_pages = hpage_nr_pages(page); - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + update_lru_size(lruvec, lru, hpage_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); - __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages); } static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - int nr_pages = hpage_nr_pages(page); list_del(&page->lru); - mem_cgroup_update_lru_size(lruvec, lru, -nr_pages); - __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, -nr_pages); + update_lru_size(lruvec, lru, -hpage_nr_pages(page)); } /** -- cgit v1.2.3