From: Johannes Weiner <hannes@xxxxxxxxxxx> Subject: mm: page-writeback: simplify memcg handling in test_clear_page_writeback() Page writeback doesn't hold a page reference, which allows truncate to free a page the second PageWriteback is cleared. This used to require special attention in test_clear_page_writeback(), where we had to be careful not to rely on the unstable page->memcg binding and look up all the necessary information before clearing the writeback flag. Since commit 073861ed77b6 ("mm: fix VM_BUG_ON(PageTail) and BUG_ON(PageWriteback)") test_clear_page_writeback() is called with an explicit reference on the page, and this dance is no longer needed. Use unlock_page_memcg() and dec_lruvec_page_state() directly. This removes the last user of the lock_page_memcg() return value, change it to void. Touch up the comments in there as well. This also removes the last extern user of __unlock_page_memcg(), make it static. Further, it removes the last user of dec_lruvec_state(), delete it, along with a few other unused helpers. Link: https://lkml.kernel.org/r/YCQbYAWg4nvBFL6h@xxxxxxxxxxx Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> Acked-by: Hugh Dickins <hughd@xxxxxxxxxx> Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Cc: Roman Gushchin <guro@xxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 10 +-------- include/linux/vmstat.h | 24 ++--------------------- mm/memcontrol.c | 36 ++++++++++------------------------- mm/page-writeback.c | 9 ++------ 4 files changed, 19 insertions(+), 60 deletions(-) --- a/include/linux/memcontrol.h~mm-page-writeback-simplify-memcg-handling-in-test_clear_page_writeback +++ a/include/linux/memcontrol.h @@ -867,8 +867,7 @@ void mem_cgroup_print_oom_group(struct m extern bool cgroup_memory_noswap; #endif -struct mem_cgroup *lock_page_memcg(struct page *page); -void __unlock_page_memcg(struct mem_cgroup *memcg); +void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); /* @@ -1289,12 +1288,7 @@ mem_cgroup_print_oom_meminfo(struct mem_ { } -static inline struct mem_cgroup *lock_page_memcg(struct page *page) -{ - return NULL; -} - -static inline void __unlock_page_memcg(struct mem_cgroup *memcg) +static inline void lock_page_memcg(struct page *page) { } --- a/include/linux/vmstat.h~mm-page-writeback-simplify-memcg-handling-in-test_clear_page_writeback +++ a/include/linux/vmstat.h @@ -512,16 +512,10 @@ static inline void mod_lruvec_page_state #endif /* CONFIG_MEMCG */ -static inline void __inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - __mod_lruvec_state(lruvec, idx, 1); -} - -static inline void __dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) +static inline void inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) { - __mod_lruvec_state(lruvec, idx, -1); + mod_lruvec_state(lruvec, idx, 1); } static inline void __inc_lruvec_page_state(struct page *page, @@ -536,18 +530,6 @@ static inline void __dec_lruvec_page_sta __mod_lruvec_page_state(page, idx, -1); } -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); -} - -static inline void dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, -1); -} - static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { --- a/mm/memcontrol.c~mm-page-writeback-simplify-memcg-handling-in-test_clear_page_writeback +++ a/mm/memcontrol.c @@ -2118,11 +2118,10 @@ void mem_cgroup_print_oom_group(struct m * This function protects unlocked LRU pages from being moved to * another cgroup. * - * It ensures lifetime of the returned memcg. Caller is responsible - * for the lifetime of the page; __unlock_page_memcg() is available - * when @page might get freed inside the locked section. + * It ensures lifetime of the locked memcg. Caller is responsible + * for the lifetime of the page. */ -struct mem_cgroup *lock_page_memcg(struct page *page) +void lock_page_memcg(struct page *page) { struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; @@ -2132,21 +2131,15 @@ struct mem_cgroup *lock_page_memcg(struc * The RCU lock is held throughout the transaction. The fast * path can get away without acquiring the memcg->move_lock * because page moving starts with an RCU grace period. - * - * The RCU lock also protects the memcg from being freed when - * the page state that is going to change is the only thing - * preventing the page itself from being freed. E.g. writeback - * doesn't hold a page reference and relies on PG_writeback to - * keep off truncation, migration and so forth. */ rcu_read_lock(); if (mem_cgroup_disabled()) - return NULL; + return; again: memcg = page_memcg(head); if (unlikely(!memcg)) - return NULL; + return; #ifdef CONFIG_PROVE_LOCKING local_irq_save(flags); @@ -2155,7 +2148,7 @@ again: #endif if (atomic_read(&memcg->moving_account) <= 0) - return memcg; + return; spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page_memcg(head)) { @@ -2164,24 +2157,17 @@ again: } /* - * When charge migration first begins, we can have locked and - * unlocked page stat updates happening concurrently. Track - * the task who has the lock for unlock_page_memcg(). + * When charge migration first begins, we can have multiple + * critical sections holding the fast-path RCU lock and one + * holding the slowpath move_lock. Track the task who has the + * move_lock for unlock_page_memcg(). */ memcg->move_lock_task = current; memcg->move_lock_flags = flags; - - return memcg; } EXPORT_SYMBOL(lock_page_memcg); -/** - * __unlock_page_memcg - unlock and unpin a memcg - * @memcg: the memcg - * - * Unlock and unpin a memcg returned by lock_page_memcg(). - */ -void __unlock_page_memcg(struct mem_cgroup *memcg) +static void __unlock_page_memcg(struct mem_cgroup *memcg) { if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; --- a/mm/page-writeback.c~mm-page-writeback-simplify-memcg-handling-in-test_clear_page_writeback +++ a/mm/page-writeback.c @@ -2722,12 +2722,9 @@ EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); - struct mem_cgroup *memcg; - struct lruvec *lruvec; int ret; - memcg = lock_page_memcg(page); - lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -2755,11 +2752,11 @@ int test_clear_page_writeback(struct pag ret = TestClearPageWriteback(page); } if (ret) { - dec_lruvec_state(lruvec, NR_WRITEBACK); + dec_lruvec_page_state(page, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); } - __unlock_page_memcg(memcg); + unlock_page_memcg(page); return ret; } _