From 88dcb9a3fb48c67ec345f1cdbc2a26119d3cb57d Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 15 Dec 2020 12:33:20 -0800 Subject: [PATCH] mm/thp: move lru_add_page_tail() to huge_memory.c MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Patch series "per memcg lru lock", v21. This patchset includes 3 parts: 1) some code cleanup and minimum optimization as preparation 2) use TestCleanPageLRU as page isolation's precondition 3) replace per node lru_lock with per memcg per node lru_lock Current lru_lock is one for each of node, pgdat->lru_lock, that guard for lru lists, but now we had moved the lru lists into memcg for long time. Still using per node lru_lock is clearly unscalable, pages on each of memcgs have to compete each others for a whole lru_lock. This patchset try to use per lruvec/memcg lru_lock to repleace per node lru lock to guard lru lists, make it scalable for memcgs and get performance gain. Currently lru_lock still guards both lru list and page's lru bit, that's ok. but if we want to use specific lruvec lock on the page, we need to pin down the page's lruvec/memcg during locking. Just taking lruvec lock first may be undermined by the page's memcg charge/migration. To fix this problem, we could take out the page's lru bit clear and use it as pin down action to block the memcg changes. That's the reason for new atomic func TestClearPageLRU. So now isolating a page need both actions: TestClearPageLRU and hold the lru_lock. The typical usage of this is isolate_migratepages_block() in compaction.c we have to take lru bit before lru lock, that serialized the page isolation in memcg page charge/migration which will change page's lruvec and new lru_lock in it. The above solution suggested by Johannes Weiner, and based on his new memcg charge path, then have this patchset. (Hugh Dickins tested and contributed much code from compaction fix to general code polish, thanks a lot!). Daniel Jordan's testing show 62% improvement on modified readtwice case on his 2P * 10 core * 2 HT broadwell box on v18, which has no much different with this v20. https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/ Thanks to Hugh Dickins and Konstantin Khlebnikov, they both brought this idea 8 years ago, and others who gave comments as well: Daniel Jordan, Mel Gorman, Shakeel Butt, Matthew Wilcox, Alexander Duyck etc. Thanks for Testing support from Intel 0day and Rong Chen, Fengguang Wu, and Yun Wang. Hugh Dickins also shared his kbuild-swap case. This patch (of 19): lru_add_page_tail() is only used in huge_memory.c, defining it in other file with a CONFIG_TRANSPARENT_HUGEPAGE macro restrict just looks weird. Let's move it THP. And make it static as Hugh Dickins suggested. Link: https://lkml.kernel.org/r/1604566549-62481-1-git-send-email-alex.shi@linux.alibaba.com Link: https://lkml.kernel.org/r/1604566549-62481-2-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Alex Shi Reviewed-by: Kirill A. Shutemov Acked-by: Hugh Dickins Acked-by: Johannes Weiner Cc: Matthew Wilcox Cc: Mel Gorman Cc: Tejun Heo Cc: Konstantin Khlebnikov Cc: Daniel Jordan Cc: Shakeel Butt Cc: Joonsoo Kim Cc: Wei Yang Cc: Alexander Duyck Cc: "Chen, Rong A" Cc: Michal Hocko Cc: Vladimir Davydov Cc: Andrea Arcangeli Cc: Andrey Ryabinin Cc: "Huang, Ying" Cc: Jann Horn Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Mika Penttilä Cc: Minchan Kim Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 -- mm/huge_memory.c | 30 ++++++++++++++++++++++++++++++ mm/swap.c | 33 --------------------------------- 3 files changed, 30 insertions(+), 35 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 667935c..5e1e967 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -338,8 +338,6 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); -extern void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec, struct list_head *head); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 57d0815..85b50ba 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2359,6 +2359,36 @@ static void remap_page(struct page *page, unsigned int nr) } } +static void lru_add_page_tail(struct page *page, struct page *page_tail, + struct lruvec *lruvec, struct list_head *list) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + VM_BUG_ON_PAGE(PageCompound(page_tail), page); + VM_BUG_ON_PAGE(PageLRU(page_tail), page); + lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); + + if (!list) + SetPageLRU(page_tail); + + if (likely(PageLRU(page))) + list_add_tail(&page_tail->lru, &page->lru); + else if (list) { + /* page reclaim is reclaiming a huge page */ + get_page(page_tail); + list_add_tail(&page_tail->lru, list); + } else { + /* + * Head page has not yet been counted, as an hpage, + * so we must account for each subpage individually. + * + * Put page_tail on the list at the correct position + * so they all end up in order. + */ + add_page_to_lru_list_tail(page_tail, lruvec, + page_lru(page_tail)); + } +} + static void __split_huge_page_tail(struct page *head, int tail, struct lruvec *lruvec, struct list_head *list) { diff --git a/mm/swap.c b/mm/swap.c index 16a5252..6e3121d 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -977,39 +977,6 @@ void __pagevec_release(struct pagevec *pvec) } EXPORT_SYMBOL(__pagevec_release); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* used by __split_huge_page_refcount() */ -void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec, struct list_head *list) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - VM_BUG_ON_PAGE(PageCompound(page_tail), page); - VM_BUG_ON_PAGE(PageLRU(page_tail), page); - lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); - - if (!list) - SetPageLRU(page_tail); - - if (likely(PageLRU(page))) - list_add_tail(&page_tail->lru, &page->lru); - else if (list) { - /* page reclaim is reclaiming a huge page */ - get_page(page_tail); - list_add_tail(&page_tail->lru, list); - } else { - /* - * Head page has not yet been counted, as an hpage, - * so we must account for each subpage individually. - * - * Put page_tail on the list at the correct position - * so they all end up in order. - */ - add_page_to_lru_list_tail(page_tail, lruvec, - page_lru(page_tail)); - } -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { -- 2.7.4