From 2a5e4e340b0fe0f8d402196a466887db6a270b9b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 15 Dec 2020 12:34:33 -0800 Subject: [PATCH] mm/lru: introduce relock_page_lruvec() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Add relock_page_lruvec() to replace repeated same code, no functional change. When testing for relock we can avoid the need for RCU locking if we simply compare the page pgdat and memcg pointers versus those that the lruvec is holding. By doing this we can avoid the extra pointer walks and accesses of the memory cgroup. In addition we can avoid the checks entirely if lruvec is currently NULL. [alex.shi@linux.alibaba.com: use page_memcg()] Link: https://lkml.kernel.org/r/66d8e79d-7ec6-bfbc-1c82-bf32db3ae5b7@linux.alibaba.com Link: https://lkml.kernel.org/r/1604566549-62481-19-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Alexander Duyck Signed-off-by: Alex Shi Acked-by: Hugh Dickins Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Thomas Gleixner Cc: Andrey Ryabinin Cc: Matthew Wilcox Cc: Mel Gorman Cc: Konstantin Khlebnikov Cc: Tejun Heo Cc: Andrea Arcangeli Cc: "Chen, Rong A" Cc: Daniel Jordan Cc: "Huang, Ying" Cc: Jann Horn Cc: Joonsoo Kim Cc: Kirill A. Shutemov Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Michal Hocko Cc: Mika Penttilä Cc: Minchan Kim Cc: Shakeel Butt Cc: Vladimir Davydov Cc: Wei Yang Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++ mm/mlock.c | 11 +--------- mm/swap.c | 33 +++++++---------------------- mm/vmscan.c | 12 ++--------- 4 files changed, 62 insertions(+), 46 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index aa5d559..ff02f83 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -485,6 +485,22 @@ out: struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); +static inline bool lruvec_holds_page_lru_lock(struct page *page, + struct lruvec *lruvec) +{ + pg_data_t *pgdat = page_pgdat(page); + const struct mem_cgroup *memcg; + struct mem_cgroup_per_node *mz; + + if (mem_cgroup_disabled()) + return lruvec == &pgdat->__lruvec; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + memcg = page_memcg(page) ? : root_mem_cgroup; + + return lruvec->pgdat == pgdat && mz->memcg == memcg; +} + struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); @@ -984,6 +1000,14 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, return &pgdat->__lruvec; } +static inline bool lruvec_holds_page_lru_lock(struct page *page, + struct lruvec *lruvec) +{ + pg_data_t *pgdat = page_pgdat(page); + + return lruvec == &pgdat->__lruvec; +} + static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; @@ -1354,6 +1378,34 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } +/* Don't lock again iff page's lruvec locked */ +static inline struct lruvec *relock_page_lruvec_irq(struct page *page, + struct lruvec *locked_lruvec) +{ + if (locked_lruvec) { + if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + return locked_lruvec; + + unlock_page_lruvec_irq(locked_lruvec); + } + + return lock_page_lruvec_irq(page); +} + +/* Don't lock again iff page's lruvec locked */ +static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, + struct lruvec *locked_lruvec, unsigned long *flags) +{ + if (locked_lruvec) { + if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + return locked_lruvec; + + unlock_page_lruvec_irqrestore(locked_lruvec, *flags); + } + + return lock_page_lruvec_irqsave(page, flags); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); diff --git a/mm/mlock.c b/mm/mlock.c index ab164a6..55b3b36 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -277,16 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) * so we can spare the get_page() here. */ if (TestClearPageLRU(page)) { - struct lruvec *new_lruvec; - - new_lruvec = mem_cgroup_page_lruvec(page, - page_pgdat(page)); - if (new_lruvec != lruvec) { - if (lruvec) - unlock_page_lruvec_irq(lruvec); - lruvec = lock_page_lruvec_irq(page); - } - + lruvec = relock_page_lruvec_irq(page, lruvec); del_page_from_lru_list(page, lruvec, page_lru(page)); continue; diff --git a/mm/swap.c b/mm/swap.c index ba9fc21b..2cca714 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -210,19 +210,12 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - struct lruvec *new_lruvec; /* block memcg migration during page moving between lru */ if (!TestClearPageLRU(page)) continue; - new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - if (lruvec != new_lruvec) { - if (lruvec) - unlock_page_lruvec_irqrestore(lruvec, flags); - lruvec = lock_page_lruvec_irqsave(page, &flags); - } - + lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); (*move_fn)(page, lruvec); SetPageLRU(page); @@ -918,17 +911,12 @@ void release_pages(struct page **pages, int nr) } if (PageLRU(page)) { - struct lruvec *new_lruvec; - - new_lruvec = mem_cgroup_page_lruvec(page, - page_pgdat(page)); - if (new_lruvec != lruvec) { - if (lruvec) - unlock_page_lruvec_irqrestore(lruvec, - flags); + struct lruvec *prev_lruvec = lruvec; + + lruvec = relock_page_lruvec_irqsave(page, lruvec, + &flags); + if (prev_lruvec != lruvec) lock_batch = 0; - lruvec = lock_page_lruvec_irqsave(page, &flags); - } VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); @@ -1033,15 +1021,8 @@ void __pagevec_lru_add(struct pagevec *pvec) for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - struct lruvec *new_lruvec; - - new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - if (lruvec != new_lruvec) { - if (lruvec) - unlock_page_lruvec_irqrestore(lruvec, flags); - lruvec = lock_page_lruvec_irqsave(page, &flags); - } + lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); __pagevec_lru_add_fn(page, lruvec); } if (lruvec) diff --git a/mm/vmscan.c b/mm/vmscan.c index b27b5db..60705ea 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1883,8 +1883,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(mem_cgroup_page_lruvec(page, page_pgdat(page)) - != lruvec, page); + VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page); lru = page_lru(page); nr_pages = thp_nr_pages(page); @@ -4273,7 +4272,6 @@ void check_move_unevictable_pages(struct pagevec *pvec) for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; int nr_pages; - struct lruvec *new_lruvec; if (PageTransTail(page)) continue; @@ -4285,13 +4283,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) if (!TestClearPageLRU(page)) continue; - new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - if (lruvec != new_lruvec) { - if (lruvec) - unlock_page_lruvec_irq(lruvec); - lruvec = lock_page_lruvec_irq(page); - } - + lruvec = relock_page_lruvec_irq(page, lruvec); if (page_evictable(page) && PageUnevictable(page)) { enum lru_list lru = page_lru_base_type(page); -- 2.7.4