From 00501b531c4723972aa11d6d4ebcf8d6552007c8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 8 Aug 2014 14:19:20 -0700 Subject: mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Vladimir Davydov Signed-off-by: Hugh Dickins Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 53 ++++++++++++---------------------------------- 1 file changed, 14 insertions(+), 39 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index eb65d29516ca..1a9a096858e0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -54,28 +54,11 @@ struct mem_cgroup_reclaim_cookie { }; #ifdef CONFIG_MEMCG -/* - * All "charge" functions with gfp_mask should use GFP_KERNEL or - * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't - * alloc memory but reclaims memory from all available zones. So, "where I want - * memory from" bits of gfp_mask has no meaning. So any bits of that field is - * available but adding a rule is better. charge functions' gfp_mask should - * be set to GFP_KERNEL or gfp_mask & GFP_RECLAIM_MASK for avoiding ambiguous - * codes. - * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.) - */ - -extern int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); -/* for swap handling */ -extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, gfp_t mask, struct mem_cgroup **memcgp); -extern void mem_cgroup_commit_charge_swapin(struct page *page, - struct mem_cgroup *memcg); -extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg); - -extern int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); +int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, struct mem_cgroup **memcgp); +void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); @@ -233,30 +216,22 @@ void mem_cgroup_print_bad_page(struct page *page); #else /* CONFIG_MEMCG */ struct mem_cgroup; -static inline int mem_cgroup_charge_anon(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - return 0; -} - -static inline int mem_cgroup_charge_file(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - return 0; -} - -static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, gfp_t gfp_mask, struct mem_cgroup **memcgp) +static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, + struct mem_cgroup **memcgp) { + *memcgp = NULL; return 0; } -static inline void mem_cgroup_commit_charge_swapin(struct page *page, - struct mem_cgroup *memcg) +static inline void mem_cgroup_commit_charge(struct page *page, + struct mem_cgroup *memcg, + bool lrucare) { } -static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +static inline void mem_cgroup_cancel_charge(struct page *page, + struct mem_cgroup *memcg) { } -- cgit v1.2.2 From 0a31bc97c80c3fa87b32c091d9a930ac19cd0c40 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 8 Aug 2014 14:19:22 -0700 Subject: mm: memcontrol: rewrite uncharge API The memcg uncharging code that is involved towards the end of a page's lifetime - truncation, reclaim, swapout, migration - is impressively complicated and fragile. Because anonymous and file pages were always charged before they had their page->mapping established, uncharges had to happen when the page type could still be known from the context; as in unmap for anonymous, page cache removal for file and shmem pages, and swap cache truncation for swap pages. However, these operations happen well before the page is actually freed, and so a lot of synchronization is necessary: - Charging, uncharging, page migration, and charge migration all need to take a per-page bit spinlock as they could race with uncharging. - Swap cache truncation happens during both swap-in and swap-out, and possibly repeatedly before the page is actually freed. This means that the memcg swapout code is called from many contexts that make no sense and it has to figure out the direction from page state to make sure memory and memory+swap are always correctly charged. - On page migration, the old page might be unmapped but then reused, so memcg code has to prevent untimely uncharging in that case. Because this code - which should be a simple charge transfer - is so special-cased, it is not reusable for replace_page_cache(). But now that charged pages always have a page->mapping, introduce mem_cgroup_uncharge(), which is called after the final put_page(), when we know for sure that nobody is looking at the page anymore. For page migration, introduce mem_cgroup_migrate(), which is called after the migration is successful and the new page is fully rmapped. Because the old page is no longer uncharged after migration, prevent double charges by decoupling the page's memcg association (PCG_USED and pc->mem_cgroup) from the page holding an actual charge. The new bits PCG_MEM and PCG_MEMSW represent the respective charges and are transferred to the new page during migration. mem_cgroup_migrate() is suitable for replace_page_cache() as well, which gets rid of mem_cgroup_replace_page_cache(). However, care needs to be taken because both the source and the target page can already be charged and on the LRU when fuse is splicing: grab the page lock on the charge moving side to prevent changing pc->mem_cgroup of a page under migration. Also, the lruvecs of both pages change as we uncharge the old and charge the new during migration, and putback may race with us, so grab the lru lock and isolate the pages iff on LRU to prevent races and ensure the pages are on the right lruvec afterward. Swap accounting is massively simplified: because the page is no longer uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry before the final put_page() in page reclaim. Finally, page_cgroup changes are now protected by whatever protection the page itself offers: anonymous pages are charged under the page table lock, whereas page cache insertions, swapin, and migration hold the page lock. Uncharging happens under full exclusion with no outstanding references. Charging and uncharging also ensure that the page is off-LRU, which serializes against charge migration. Remove the very costly page_cgroup lock and set pc->flags non-atomically. [mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable] [vdavydov@parallels.com: fix flags definition] Signed-off-by: Johannes Weiner Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Tested-by: Jet Chen Acked-by: Michal Hocko Tested-by: Felipe Balbi Signed-off-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 49 ++++++++++++++-------------------------------- 1 file changed, 15 insertions(+), 34 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1a9a096858e0..806b8fa15c5f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -60,15 +60,17 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); -struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); +void mem_cgroup_uncharge(struct page *page); + +/* Batched uncharging */ +void mem_cgroup_uncharge_start(void); +void mem_cgroup_uncharge_end(void); -/* For coalescing uncharge for reducing memcg' overhead*/ -extern void mem_cgroup_uncharge_start(void); -extern void mem_cgroup_uncharge_end(void); +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, + bool lrucare); -extern void mem_cgroup_uncharge_page(struct page *page); -extern void mem_cgroup_uncharge_cache_page(struct page *page); +struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); +struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, struct mem_cgroup *memcg); @@ -96,12 +98,6 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); -extern void -mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp); -extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok); - struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); @@ -116,8 +112,6 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); -extern void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage); static inline void mem_cgroup_oom_enable(void) { @@ -235,19 +229,21 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } -static inline void mem_cgroup_uncharge_start(void) +static inline void mem_cgroup_uncharge(struct page *page) { } -static inline void mem_cgroup_uncharge_end(void) +static inline void mem_cgroup_uncharge_start(void) { } -static inline void mem_cgroup_uncharge_page(struct page *page) +static inline void mem_cgroup_uncharge_end(void) { } -static inline void mem_cgroup_uncharge_cache_page(struct page *page) +static inline void mem_cgroup_migrate(struct page *oldpage, + struct page *newpage, + bool lrucare) { } @@ -286,17 +282,6 @@ static inline struct cgroup_subsys_state return NULL; } -static inline void -mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp) -{ -} - -static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok) -{ -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -392,10 +377,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage) -{ -} #endif /* CONFIG_MEMCG */ #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM) -- cgit v1.2.2 From 747db954cab64c6b7a95b121b517165f34751898 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 8 Aug 2014 14:19:24 -0700 Subject: mm: memcontrol: use page lists for uncharge batching Pages are now uncharged at release time, and all sources of batched uncharges operate on lists of pages. Directly use those lists, and get rid of the per-task batching state. This also batches statistics accounting, in addition to the res counter charges, to reduce IRQ-disabling and re-enabling. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Cc: Naoya Horiguchi Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 806b8fa15c5f..e0752d204d9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -59,12 +59,8 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); - void mem_cgroup_uncharge(struct page *page); - -/* Batched uncharging */ -void mem_cgroup_uncharge_start(void); -void mem_cgroup_uncharge_end(void); +void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, bool lrucare); @@ -233,11 +229,7 @@ static inline void mem_cgroup_uncharge(struct page *page) { } -static inline void mem_cgroup_uncharge_start(void) -{ -} - -static inline void mem_cgroup_uncharge_end(void) +static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -- cgit v1.2.2