From 1af8bb43269563e458ebcf0ece812e9a970864b3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:44:52 -0700 Subject: mm, oom: fortify task_will_free_mem() task_will_free_mem is rather weak. It doesn't really tell whether the task has chance to drop its mm. 98748bd72200 ("oom: consider multi-threaded tasks in task_will_free_mem") made a first step into making it more robust for multi-threaded applications so now we know that the whole process is going down and probably drop the mm. This patch builds on top for more complex scenarios where mm is shared between different processes - CLONE_VM without CLONE_SIGHAND, or in kernel use_mm(). Make sure that all processes sharing the mm are killed or exiting. This will allow us to replace try_oom_reaper by wake_oom_reaper because task_will_free_mem implies the task is reapable now. Therefore all paths which bypass the oom killer are now reapable and so they shouldn't lock up the oom killer. Link: http://lkml.kernel.org/r/1466426628-15074-8-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f3a84c64f35c..3e8f9e5e9291 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1276,9 +1276,9 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || task_will_free_mem(current)) { + if (task_will_free_mem(current)) { mark_oom_victim(current); - try_oom_reaper(current); + wake_oom_reaper(current); goto unlock; } -- cgit v1.2.3-55-g7522 From 55779ec759ccc3c12b917b3712a7716e1140c652 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 28 Jul 2016 15:45:10 -0700 Subject: mm: fix vm-scalability regression in cgroup-aware workingset code Commit 23047a96d7cf ("mm: workingset: per-cgroup cache thrash detection") added a page->mem_cgroup lookup to the cache eviction, refault, and activation paths, as well as locking to the activation path, and the vm-scalability tests showed a regression of -23%. While the test in question is an artificial worst-case scenario that doesn't occur in real workloads - reading two sparse files in parallel at full CPU speed just to hammer the LRU paths - there is still some optimizations that can be done in those paths. Inline the lookup functions to eliminate calls. Also, page->mem_cgroup doesn't need to be stabilized when counting an activation; we merely need to hold the RCU lock to prevent the memcg from being freed. This cuts down on overhead quite a bit: 23047a96d7cfcfca 063f6715e77a7be5770d6081fe ---------------- -------------------------- %stddev %change %stddev \ | \ 21621405 +- 0% +11.3% 24069657 +- 2% vm-scalability.throughput [linux@roeck-us.net: drop unnecessary include file] [hannes@cmpxchg.org: add WARN_ON_ONCE()s] Link: http://lkml.kernel.org/r/20160707194024.GA26580@cmpxchg.org Link: http://lkml.kernel.org/r/20160624175101.GA3024@cmpxchg.org Reported-by: Ye Xiaolong Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 43 ++++++++++++++++++++++++++++++++++++++++++- include/linux/mm.h | 10 ++++++++++ mm/memcontrol.c | 42 ------------------------------------------ mm/workingset.c | 10 ++++++---- 4 files changed, 58 insertions(+), 47 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 71aff733a497..1c4df4420258 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -314,7 +314,48 @@ void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); -struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); +static inline struct mem_cgroup_per_zone * +mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) +{ + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); + + return &memcg->nodeinfo[nid]->zoneinfo[zid]; +} + +/** + * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg + * @zone: zone of the wanted lruvec + * @memcg: memcg of the wanted lruvec + * + * Returns the lru list vector holding pages for the given @zone and + * @mem. This can be the global zone lruvec, if the memory controller + * is disabled. + */ +static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, + struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_zone *mz; + struct lruvec *lruvec; + + if (mem_cgroup_disabled()) { + lruvec = &zone->lruvec; + goto out; + } + + mz = mem_cgroup_zone_zoneinfo(memcg, zone); + lruvec = &mz->lruvec; +out: + /* + * Since a node can be onlined after the mem_cgroup was created, + * we have to be prepared to initialize lruvec->zone here; + * and if offlined then reonlined, we need to reinitialize it. + */ + if (unlikely(lruvec->zone != zone)) + lruvec->zone = zone; + return lruvec; +} + struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); diff --git a/include/linux/mm.h b/include/linux/mm.h index c606fe4f9a7f..97065e1f0237 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -973,11 +973,21 @@ static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return READ_ONCE(page->mem_cgroup); +} #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return NULL; +} #endif /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3e8f9e5e9291..40dfca3ef4bb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -323,15 +323,6 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /* !CONFIG_SLOB */ -static struct mem_cgroup_per_zone * -mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) -{ - int nid = zone_to_nid(zone); - int zid = zone_idx(zone); - - return &memcg->nodeinfo[nid]->zoneinfo[zid]; -} - /** * mem_cgroup_css_from_page - css of the memcg associated with a page * @page: page of interest @@ -943,39 +934,6 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) -/** - * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg - * @zone: zone of the wanted lruvec - * @memcg: memcg of the wanted lruvec - * - * Returns the lru list vector holding pages for the given @zone and - * @mem. This can be the global zone lruvec, if the memory controller - * is disabled. - */ -struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_zone *mz; - struct lruvec *lruvec; - - if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; - goto out; - } - - mz = mem_cgroup_zone_zoneinfo(memcg, zone); - lruvec = &mz->lruvec; -out: - /* - * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; - * and if offlined then reonlined, we need to reinitialize it. - */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; - return lruvec; -} - /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page diff --git a/mm/workingset.c b/mm/workingset.c index 577277546d98..d7cc4bbd7e1b 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -305,9 +305,10 @@ bool workingset_refault(void *shadow) */ void workingset_activation(struct page *page) { + struct mem_cgroup *memcg; struct lruvec *lruvec; - lock_page_memcg(page); + rcu_read_lock(); /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. @@ -315,12 +316,13 @@ void workingset_activation(struct page *page) * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ - if (!mem_cgroup_disabled() && !page_memcg(page)) + memcg = page_memcg_rcu(page); + if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_zone_lruvec(page_zone(page), page_memcg(page)); + lruvec = mem_cgroup_zone_lruvec(page_zone(page), memcg); atomic_long_inc(&lruvec->inactive_age); out: - unlock_page_memcg(page); + rcu_read_unlock(); } /* -- cgit v1.2.3-55-g7522 From a52633d8e9c35832f1409dc5fa166019048a3f1f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:28 -0700 Subject: mm, vmscan: move lru_lock to the node Node-based reclaim requires node-based LRUs and locking. This is a preparation patch that just moves the lru_lock to the node so later patches are easier to review. It is a mechanical change but note this patch makes contention worse because the LRU lock is hotter and direct reclaim and kswapd can contend on the same lock even when reclaiming from different zones. Link: http://lkml.kernel.org/r/1467970510-21195-3-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroup-v1/memcg_test.txt | 4 +-- Documentation/cgroup-v1/memory.txt | 4 +-- include/linux/mm_types.h | 2 +- include/linux/mmzone.h | 10 +++++-- mm/compaction.c | 10 +++---- mm/filemap.c | 4 +-- mm/huge_memory.c | 6 ++--- mm/memcontrol.c | 6 ++--- mm/mlock.c | 10 +++---- mm/page_alloc.c | 4 +-- mm/page_idle.c | 4 +-- mm/rmap.c | 2 +- mm/swap.c | 30 ++++++++++----------- mm/vmscan.c | 48 +++++++++++++++++----------------- 14 files changed, 75 insertions(+), 69 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt index 8870b0212150..78a8c2963b38 100644 --- a/Documentation/cgroup-v1/memcg_test.txt +++ b/Documentation/cgroup-v1/memcg_test.txt @@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. 8. LRU Each memcg has its own private LRU. Now, its handling is under global - VM's control (means that it's handled under global zone->lru_lock). + VM's control (means that it's handled under global zone_lru_lock). Almost all routines around memcg's LRU is called by global LRU's - list management functions under zone->lru_lock(). + list management functions under zone_lru_lock(). A special function is mem_cgroup_isolate_pages(). This scans memcg's private LRU and call __isolate_lru_page() to extract a page diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt index b14abf217239..946e69103cdd 100644 --- a/Documentation/cgroup-v1/memory.txt +++ b/Documentation/cgroup-v1/memory.txt @@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered. Other lock order is following: PG_locked. mm->page_table_lock - zone->lru_lock + zone_lru_lock lock_page_cgroup. In many cases, just lock_page_cgroup() is called. per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by - zone->lru_lock, it has no lock of its own. + zone_lru_lock, it has no lock of its own. 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 79472b22d23f..903200f4ec41 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -118,7 +118,7 @@ struct page { */ union { struct list_head lru; /* Pageout list, eg. active_list - * protected by zone->lru_lock ! + * protected by zone_lru_lock ! * Can be used as a generic list * by the page owner. */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 078ecb81e209..cfa870107abe 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -93,7 +93,7 @@ struct free_area { struct pglist_data; /* - * zone->lock and zone->lru_lock are two of the hottest locks in the kernel. + * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. * So add a wild amount of padding here to ensure that they fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. @@ -496,7 +496,6 @@ struct zone { /* Write-intensive fields used by page reclaim */ /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; struct lruvec lruvec; /* @@ -690,6 +689,9 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + /* Write-intensive fields used by page reclaim */ + ZONE_PADDING(_pad1_) + spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -721,6 +723,10 @@ typedef struct pglist_data { #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) +static inline spinlock_t *zone_lru_lock(struct zone *zone) +{ + return &zone->zone_pgdat->lru_lock; +} static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { diff --git a/mm/compaction.c b/mm/compaction.c index 45eaa2a56517..5c65fad3f330 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -752,7 +752,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * if contended. */ if (!(low_pfn % SWAP_CLUSTER_MAX) - && compact_unlock_should_abort(&zone->lru_lock, flags, + && compact_unlock_should_abort(zone_lru_lock(zone), flags, &locked, cc)) break; @@ -813,7 +813,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (unlikely(__PageMovable(page)) && !PageIsolated(page)) { if (locked) { - spin_unlock_irqrestore(&zone->lru_lock, + spin_unlock_irqrestore(zone_lru_lock(zone), flags); locked = false; } @@ -836,7 +836,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* If we already hold the lock, we can skip some rechecking */ if (!locked) { - locked = compact_trylock_irqsave(&zone->lru_lock, + locked = compact_trylock_irqsave(zone_lru_lock(zone), &flags, cc); if (!locked) break; @@ -899,7 +899,7 @@ isolate_fail: */ if (nr_isolated) { if (locked) { - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); locked = false; } acct_isolated(zone, cc); @@ -927,7 +927,7 @@ isolate_fail: low_pfn = end_pfn; if (locked) - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); /* * Update the pageblock-skip information and cached scanner pfn, diff --git a/mm/filemap.c b/mm/filemap.c index e90c1543ec2d..7ec50bd6f88c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -95,8 +95,8 @@ * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->tree_lock (try_to_unmap_one) - * ->zone.lru_lock (follow_page->mark_page_accessed) - * ->zone.lru_lock (check_pte_range->isolate_lru_page) + * ->zone_lru_lock(zone) (follow_page->mark_page_accessed) + * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->tree_lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3647334c2ef9..99578b63814b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1848,7 +1848,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, spin_unlock(&head->mapping->tree_lock); } - spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); unfreeze_page(head); @@ -2034,7 +2034,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irqsave(&page_zone(head)->lru_lock, flags); + spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags); if (mapping) { void **pslot; @@ -2077,7 +2077,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) spin_unlock(&pgdata->split_queue_lock); fail: if (mapping) spin_unlock(&mapping->tree_lock); - spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); unfreeze_page(head); ret = -EBUSY; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 40dfca3ef4bb..9b70f9ca8ddf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2065,7 +2065,7 @@ static void lock_page_lru(struct page *page, int *isolated) { struct zone *zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (PageLRU(page)) { struct lruvec *lruvec; @@ -2089,7 +2089,7 @@ static void unlock_page_lru(struct page *page, int isolated) SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } static void commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -2389,7 +2389,7 @@ void memcg_kmem_uncharge(struct page *page, int order) /* * Because tail pages are not marked as "used", set it. We're under - * zone->lru_lock and migration entries setup in all page mappings. + * zone_lru_lock and migration entries setup in all page mappings. */ void mem_cgroup_split_huge_fixup(struct page *head) { diff --git a/mm/mlock.c b/mm/mlock.c index ef8dc9f395c4..997f63082ff5 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -188,7 +188,7 @@ unsigned int munlock_vma_page(struct page *page) * might otherwise copy PageMlocked to part of the tail pages before * we clear it in the head page. It also stabilizes hpage_nr_pages(). */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); nr_pages = hpage_nr_pages(page); if (!TestClearPageMlocked(page)) @@ -197,14 +197,14 @@ unsigned int munlock_vma_page(struct page *page) __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); __munlock_isolated_page(page); goto out; } __munlock_isolation_failed(page); unlock_out: - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); out: return nr_pages - 1; @@ -289,7 +289,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pagevec_init(&pvec_putback, 0); /* Phase 1: page isolation */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; @@ -315,7 +315,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) } delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); /* Now we can release pins of pages that we are not munlocking */ pagevec_release(&pvec_putback); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7d4ff81b973f..5760c626c309 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5904,6 +5904,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kcompactd_wait); #endif pgdat_page_ext_init(pgdat); + spin_lock_init(&pgdat->lru_lock); for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; @@ -5958,10 +5959,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; + zone->zone_pgdat = pgdat; spin_lock_init(&zone->lock); - spin_lock_init(&zone->lru_lock); zone_seqlock_init(zone); - zone->zone_pgdat = pgdat; zone_pcp_init(zone); /* For bootup, initialized properly in watermark setup */ diff --git a/mm/page_idle.c b/mm/page_idle.c index 4ea9c4ef5146..ae11aa914e55 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -41,12 +41,12 @@ static struct page *page_idle_get_page(unsigned long pfn) return NULL; zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (unlikely(!PageLRU(page))) { put_page(page); page = NULL; } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); return page; } diff --git a/mm/rmap.c b/mm/rmap.c index 8a13d9f7b566..dc28bfecbf80 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -27,7 +27,7 @@ * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock - * zone->lru_lock (in mark_page_accessed, isolate_lru_page) + * zone_lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) diff --git a/mm/swap.c b/mm/swap.c index 616df4ddd870..bf37e5cfae81 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -62,12 +62,12 @@ static void __page_cache_release(struct page *page) struct lruvec *lruvec; unsigned long flags; - spin_lock_irqsave(&zone->lru_lock, flags); + spin_lock_irqsave(zone_lru_lock(zone), flags); lruvec = mem_cgroup_page_lruvec(page, zone); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); } mem_cgroup_uncharge(page); } @@ -189,16 +189,16 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, if (pagezone != zone) { if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); + spin_lock_irqsave(zone_lru_lock(zone), flags); } lruvec = mem_cgroup_page_lruvec(page, zone); (*move_fn)(page, lruvec, arg); } if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); release_pages(pvec->pages, pvec->nr, pvec->cold); pagevec_reinit(pvec); } @@ -318,9 +318,9 @@ void activate_page(struct page *page) struct zone *zone = page_zone(page); page = compound_head(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); __activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } #endif @@ -448,13 +448,13 @@ void add_page_to_unevictable_list(struct page *page) struct zone *zone = page_zone(page); struct lruvec *lruvec; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); lruvec = mem_cgroup_page_lruvec(page, zone); ClearPageActive(page); SetPageUnevictable(page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } /** @@ -744,7 +744,7 @@ void release_pages(struct page **pages, int nr, bool cold) * same zone. The lock is held only if zone != NULL. */ if (zone && ++lock_batch == SWAP_CLUSTER_MAX) { - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); zone = NULL; } @@ -759,7 +759,7 @@ void release_pages(struct page **pages, int nr, bool cold) if (PageCompound(page)) { if (zone) { - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); zone = NULL; } __put_compound_page(page); @@ -771,11 +771,11 @@ void release_pages(struct page **pages, int nr, bool cold) if (pagezone != zone) { if (zone) - spin_unlock_irqrestore(&zone->lru_lock, + spin_unlock_irqrestore(zone_lru_lock(zone), flags); lock_batch = 0; zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); + spin_lock_irqsave(zone_lru_lock(zone), flags); } lruvec = mem_cgroup_page_lruvec(page, zone); @@ -790,7 +790,7 @@ void release_pages(struct page **pages, int nr, bool cold) list_add(&page->lru, &pages_to_free); } if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); mem_cgroup_uncharge_list(&pages_to_free); free_hot_cold_page_list(&pages_to_free, cold); @@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); VM_BUG_ON(NR_CPUS != 1 && - !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); + !spin_is_locked(zone_lru_lock(lruvec_zone(lruvec)))); if (!list) SetPageLRU(page_tail); diff --git a/mm/vmscan.c b/mm/vmscan.c index 21d417ccff69..e7ffcd259cc4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1349,7 +1349,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) } /* - * zone->lru_lock is heavily contended. Some of the functions that + * zone_lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * @@ -1444,7 +1444,7 @@ int isolate_lru_page(struct page *page) struct zone *zone = page_zone(page); struct lruvec *lruvec; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); lruvec = mem_cgroup_page_lruvec(page, zone); if (PageLRU(page)) { int lru = page_lru(page); @@ -1453,7 +1453,7 @@ int isolate_lru_page(struct page *page) del_page_from_lru_list(page, lruvec, lru); ret = 0; } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } return ret; } @@ -1512,9 +1512,9 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); putback_lru_page(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); continue; } @@ -1535,10 +1535,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); } else list_add(&page->lru, &pages_to_free); } @@ -1600,7 +1600,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, isolate_mode, lru); @@ -1616,7 +1616,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, else __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); if (nr_taken == 0) return 0; @@ -1626,7 +1626,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, &nr_writeback, &nr_immediate, false); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (global_reclaim(sc)) { if (current_is_kswapd()) @@ -1641,7 +1641,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); mem_cgroup_uncharge_list(&page_list); free_hot_cold_page_list(&page_list, true); @@ -1715,9 +1715,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is - * appropriate to hold zone->lru_lock across the whole operation. But if + * appropriate to hold zone_lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we - * should drop zone->lru_lock around each page. It's impossible to balance + * should drop zone_lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. @@ -1754,10 +1754,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); } else list_add(&page->lru, pages_to_free); } @@ -1792,7 +1792,7 @@ static void shrink_active_list(unsigned long nr_to_scan, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); @@ -1805,7 +1805,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); __count_zone_vm_events(PGREFILL, zone, nr_scanned); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); while (!list_empty(&l_hold)) { cond_resched(); @@ -1850,7 +1850,7 @@ static void shrink_active_list(unsigned long nr_to_scan, /* * Move pages back to the lru list. */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); /* * Count referenced pages from currently used mappings as rotated, * even though only some of them are actually re-activated. This @@ -1862,7 +1862,7 @@ static void shrink_active_list(unsigned long nr_to_scan, move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); mem_cgroup_uncharge_list(&l_hold); free_hot_cold_page_list(&l_hold, true); @@ -2077,7 +2077,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) + lruvec_lru_size(lruvec, LRU_INACTIVE_FILE); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; reclaim_stat->recent_rotated[0] /= 2; @@ -2098,7 +2098,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); fp /= reclaim_stat->recent_rotated[1] + 1; - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); fraction[0] = ap; fraction[1] = fp; @@ -3791,9 +3791,9 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) pagezone = page_zone(page); if (pagezone != zone) { if (zone) - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); zone = pagezone; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); } lruvec = mem_cgroup_page_lruvec(page, zone); @@ -3814,7 +3814,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) if (zone) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } } #endif /* CONFIG_SHMEM */ -- cgit v1.2.3-55-g7522 From 599d0c954f91d0689c9bb421b5bc04ea02437a41 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:31 -0700 Subject: mm, vmscan: move LRU lists to node This moves the LRU lists from the zone to the node and related data such as counters, tracing, congestion tracking and writeback tracking. Unfortunately, due to reclaim and compaction retry logic, it is necessary to account for the number of LRU pages on both zone and node logic. Most reclaim logic is based on the node counters but the retry logic uses the zone counters which do not distinguish inactive and active sizes. It would be possible to leave the LRU counters on a per-zone basis but it's a heavier calculation across multiple cache lines that is much more frequent than the retry checks. Other than the LRU counters, this is mostly a mechanical patch but note that it introduces a number of anomalies. For example, the scans are per-zone but using per-node counters. We also mark a node as congested when a zone is congested. This causes weird problems that are fixed later but is easier to review. In the event that there is excessive overhead on 32-bit systems due to the nodes being on LRU then there are two potential solutions 1. Long-term isolation of highmem pages when reclaim is lowmem When pages are skipped, they are immediately added back onto the LRU list. If lowmem reclaim persisted for long periods of time, the same highmem pages get continually scanned. The idea would be that lowmem keeps those pages on a separate list until a reclaim for highmem pages arrives that splices the highmem pages back onto the LRU. It potentially could be implemented similar to the UNEVICTABLE list. That would reduce the skip rate with the potential corner case is that highmem pages have to be scanned and reclaimed to free lowmem slab pages. 2. Linear scan lowmem pages if the initial LRU shrink fails This will break LRU ordering but may be preferable and faster during memory pressure than skipping LRU pages. Link: http://lkml.kernel.org/r/1467970510-21195-4-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/tile/mm/pgtable.c | 8 +- drivers/base/node.c | 19 +-- drivers/staging/android/lowmemorykiller.c | 8 +- include/linux/backing-dev.h | 2 +- include/linux/memcontrol.h | 18 +-- include/linux/mm_inline.h | 21 ++- include/linux/mmzone.h | 68 +++++---- include/linux/swap.h | 1 + include/linux/vm_event_item.h | 10 +- include/linux/vmstat.h | 17 +++ include/trace/events/vmscan.h | 12 +- kernel/power/snapshot.c | 10 +- mm/backing-dev.c | 15 +- mm/compaction.c | 18 +-- mm/huge_memory.c | 2 +- mm/internal.h | 2 +- mm/khugepaged.c | 4 +- mm/memcontrol.c | 17 +-- mm/memory-failure.c | 4 +- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 2 +- mm/migrate.c | 21 +-- mm/mlock.c | 2 +- mm/page-writeback.c | 8 +- mm/page_alloc.c | 68 +++++---- mm/swap.c | 50 +++---- mm/vmscan.c | 226 +++++++++++++++++------------- mm/vmstat.c | 47 ++++--- mm/workingset.c | 4 +- 29 files changed, 386 insertions(+), 300 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index c4d5bf841a7f..9e389213580d 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -45,10 +45,10 @@ void show_mem(unsigned int filter) struct zone *zone; pr_err("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu free:%lu\n slab:%lu mapped:%lu pagetables:%lu bounce:%lu pagecache:%lu swap:%lu\n", - (global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_ACTIVE_FILE)), - (global_page_state(NR_INACTIVE_ANON) + - global_page_state(NR_INACTIVE_FILE)), + (global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE)), + (global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_FILE)), global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), diff --git a/drivers/base/node.c b/drivers/base/node.c index 0a1b6433a76c..d4698f096209 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -56,6 +56,7 @@ static ssize_t node_read_meminfo(struct device *dev, { int n; int nid = dev->id; + struct pglist_data *pgdat = NODE_DATA(nid); struct sysinfo i; si_meminfo_node(&i, nid); @@ -74,15 +75,15 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(i.totalram), nid, K(i.freeram), nid, K(i.totalram - i.freeram), - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON) + - sum_zone_node_page_state(nid, NR_ACTIVE_FILE)), - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON) + - sum_zone_node_page_state(nid, NR_INACTIVE_FILE)), - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_ANON)), - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_ANON)), - nid, K(sum_zone_node_page_state(nid, NR_ACTIVE_FILE)), - nid, K(sum_zone_node_page_state(nid, NR_INACTIVE_FILE)), - nid, K(sum_zone_node_page_state(nid, NR_UNEVICTABLE)), + nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) + + node_page_state(pgdat, NR_ACTIVE_FILE)), + nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) + + node_page_state(pgdat, NR_INACTIVE_FILE)), + nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)), + nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)), + nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)), + nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)), + nid, K(node_page_state(pgdat, NR_UNEVICTABLE)), nid, K(sum_zone_node_page_state(nid, NR_MLOCK))); #ifdef CONFIG_HIGHMEM diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c index 24d2745e9437..93dbcc38eb0f 100644 --- a/drivers/staging/android/lowmemorykiller.c +++ b/drivers/staging/android/lowmemorykiller.c @@ -72,10 +72,10 @@ static unsigned long lowmem_deathpending_timeout; static unsigned long lowmem_count(struct shrinker *s, struct shrink_control *sc) { - return global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_ACTIVE_FILE) + - global_page_state(NR_INACTIVE_ANON) + - global_page_state(NR_INACTIVE_FILE); + return global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_FILE); } static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c82794f20110..491a91717788 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(struct zone *zone, int sync, long timeout); +long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1c4df4420258..6d2321c148cd 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -339,7 +339,7 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; + lruvec = zone_lruvec(zone); goto out; } @@ -348,15 +348,15 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, out: /* * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; + * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; + if (unlikely(lruvec->pgdat != zone->zone_pgdat)) + lruvec->pgdat = zone->zone_pgdat; return lruvec; } -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); +struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); @@ -437,7 +437,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages); + enum zone_type zid, int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); @@ -612,13 +612,13 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct mem_cgroup *memcg) { - return &zone->lruvec; + return zone_lruvec(zone); } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct zone *zone) + struct pglist_data *pgdat) { - return &zone->lruvec; + return &pgdat->lruvec; } static inline bool mm_match_cgroup(struct mm_struct *mm, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 5bd29ba4f174..9aadcc781857 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -23,25 +23,32 @@ static inline int page_is_file_cache(struct page *page) } static __always_inline void __update_lru_size(struct lruvec *lruvec, - enum lru_list lru, int nr_pages) + enum lru_list lru, enum zone_type zid, + int nr_pages) { - __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); + __mod_zone_page_state(&pgdat->node_zones[zid], + NR_ZONE_LRU_BASE + !!is_file_lru(lru), + nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, - enum lru_list lru, int nr_pages) + enum lru_list lru, enum zone_type zid, + int nr_pages) { #ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #else - __update_lru_size(lruvec, lru, nr_pages); + __update_lru_size(lruvec, lru, zid, nr_pages); #endif } static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - update_lru_size(lruvec, lru, hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); } @@ -49,7 +56,7 @@ static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { list_del(&page->lru); - update_lru_size(lruvec, lru, -hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page)); } /** diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cfa870107abe..d4f5cac0a8c3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -111,12 +111,9 @@ enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ALLOC_BATCH, - NR_LRU_BASE, - NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ - NR_ACTIVE_ANON, /* " " " " " */ - NR_INACTIVE_FILE, /* " " " " " */ - NR_ACTIVE_FILE, /* " " " " " */ - NR_UNEVICTABLE, /* " " " " " */ + NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ + NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, + NR_ZONE_LRU_FILE, NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_ANON_PAGES, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. @@ -134,12 +131,9 @@ enum zone_stat_item { NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ - NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ - NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif @@ -161,6 +155,15 @@ enum zone_stat_item { NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { + NR_LRU_BASE, + NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ + NR_ACTIVE_ANON, /* " " " " " */ + NR_INACTIVE_FILE, /* " " " " " */ + NR_ACTIVE_FILE, /* " " " " " */ + NR_UNEVICTABLE, /* " " " " " */ + NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ + NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ NR_VM_NODE_STAT_ITEMS }; @@ -219,7 +222,7 @@ struct lruvec { /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; #ifdef CONFIG_MEMCG - struct zone *zone; + struct pglist_data *pgdat; #endif }; @@ -357,13 +360,6 @@ struct zone { #ifdef CONFIG_NUMA int node; #endif - - /* - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on - * this zone's LRU. Maintained by the pageout code. - */ - unsigned int inactive_ratio; - struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; @@ -495,9 +491,6 @@ struct zone { /* Write-intensive fields used by page reclaim */ - /* Fields commonly accessed by the page reclaim scanner */ - struct lruvec lruvec; - /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter @@ -537,17 +530,20 @@ struct zone { enum zone_flags { ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ - ZONE_CONGESTED, /* zone has many dirty pages backed by + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ +}; + +enum pgdat_flags { + PGDAT_CONGESTED, /* pgdat has many dirty pages backed by * a congested BDI */ - ZONE_DIRTY, /* reclaim scanning has recently found + PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ - ZONE_WRITEBACK, /* reclaim scanning has recently found + PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ - ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ }; static inline unsigned long zone_end_pfn(const struct zone *zone) @@ -707,6 +703,19 @@ typedef struct pglist_data { unsigned long split_queue_len; #endif + /* Fields commonly accessed by the page reclaim scanner */ + struct lruvec lruvec; + + /* + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this node's LRU. Maintained by the pageout code. + */ + unsigned int inactive_ratio; + + unsigned long flags; + + ZONE_PADDING(_pad2_) + /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; @@ -728,6 +737,11 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone) return &zone->zone_pgdat->lru_lock; } +static inline struct lruvec *zone_lruvec(struct zone *zone) +{ + return &zone->zone_pgdat->lruvec; +} + static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; @@ -779,12 +793,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, extern void lruvec_init(struct lruvec *lruvec); -static inline struct zone *lruvec_zone(struct lruvec *lruvec) +static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG - return lruvec->zone; + return lruvec->pgdat; #else - return container_of(lruvec, struct zone, lruvec); + return container_of(lruvec, struct pglist_data, lruvec); #endif } diff --git a/include/linux/swap.h b/include/linux/swap.h index 0af2bb2028fd..c82f916008b7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -317,6 +317,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page, /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); +extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern int __isolate_lru_page(struct page *page, isolate_mode_t mode); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 42604173f122..1798ff542517 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -26,11 +26,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFREE, PGACTIVATE, PGDEACTIVATE, PGFAULT, PGMAJFAULT, PGLAZYFREED, - FOR_ALL_ZONES(PGREFILL), - FOR_ALL_ZONES(PGSTEAL_KSWAPD), - FOR_ALL_ZONES(PGSTEAL_DIRECT), - FOR_ALL_ZONES(PGSCAN_KSWAPD), - FOR_ALL_ZONES(PGSCAN_DIRECT), + PGREFILL, + PGSTEAL_KSWAPD, + PGSTEAL_DIRECT, + PGSCAN_KSWAPD, + PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d1744aa3ab9c..fee321c98550 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -178,6 +178,23 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, return x; } +static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat, + enum node_stat_item item) +{ + long x = atomic_long_read(&pgdat->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + + #ifdef CONFIG_NUMA extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 0101ef37f1ee..897f1aa1ee5f 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -352,15 +352,14 @@ TRACE_EVENT(mm_vmscan_writepage, TRACE_EVENT(mm_vmscan_lru_shrink_inactive, - TP_PROTO(struct zone *zone, + TP_PROTO(int nid, unsigned long nr_scanned, unsigned long nr_reclaimed, int priority, int file), - TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file), + TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file), TP_STRUCT__entry( __field(int, nid) - __field(int, zid) __field(unsigned long, nr_scanned) __field(unsigned long, nr_reclaimed) __field(int, priority) @@ -368,16 +367,15 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, ), TP_fast_assign( - __entry->nid = zone_to_nid(zone); - __entry->zid = zone_idx(zone); + __entry->nid = nid; __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->priority = priority; __entry->reclaim_flags = trace_shrink_flags(file); ), - TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", - __entry->nid, __entry->zid, + TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", + __entry->nid, __entry->nr_scanned, __entry->nr_reclaimed, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index d90df926b59f..9a0178c2ac1d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1627,11 +1627,11 @@ static unsigned long minimum_image_size(unsigned long saveable) unsigned long size; size = global_page_state(NR_SLAB_RECLAIMABLE) - + global_page_state(NR_ACTIVE_ANON) - + global_page_state(NR_INACTIVE_ANON) - + global_page_state(NR_ACTIVE_FILE) - + global_page_state(NR_INACTIVE_FILE) - - global_page_state(NR_FILE_MAPPED); + + global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + - global_node_page_state(NR_FILE_MAPPED); return saveable <= size ? 0 : saveable - size; } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index ed173b8ae8f2..efe237742074 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -947,24 +947,24 @@ long congestion_wait(int sync, long timeout) EXPORT_SYMBOL(congestion_wait); /** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes - * @zone: A zone to check if it is heavily congested + * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes + * @pgdat: A pgdat to check if it is heavily congested * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * In the event of a congested backing_dev (any backing_dev) and the given - * @zone has experienced recent congestion, this waits for up to @timeout + * @pgdat has experienced recent congestion, this waits for up to @timeout * jiffies for either a BDI to exit congestion of the given @sync queue * or a write to complete. * - * In the absence of zone congestion, cond_resched() is called to yield + * In the absence of pgdat congestion, cond_resched() is called to yield * the processor if necessary but otherwise does not sleep. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function * returned. return_value == timeout implies the function did not sleep. */ -long wait_iff_congested(struct zone *zone, int sync, long timeout) +long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout) { long ret; unsigned long start = jiffies; @@ -973,12 +973,13 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) /* * If there is no congestion, or heavy congestion is not being - * encountered in the current zone, yield if necessary instead + * encountered in the current pgdat, yield if necessary instead * of sleeping on the congestion queue */ if (atomic_read(&nr_wb_congested[sync]) == 0 || - !test_bit(ZONE_CONGESTED, &zone->flags)) { + !test_bit(PGDAT_CONGESTED, &pgdat->flags)) { cond_resched(); + /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); if (ret < 0) diff --git a/mm/compaction.c b/mm/compaction.c index 5c65fad3f330..e5995f38d677 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -646,8 +646,8 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc) list_for_each_entry(page, &cc->migratepages, lru) count[!!page_is_file_cache(page)]++; - mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); - mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, count[0]); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, count[1]); } /* Similar to reclaim, but different enough that they don't share logic */ @@ -655,12 +655,12 @@ static bool too_many_isolated(struct zone *zone) { unsigned long active, inactive, isolated; - inactive = zone_page_state(zone, NR_INACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_ANON); - active = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_ACTIVE_ANON); - isolated = zone_page_state(zone, NR_ISOLATED_FILE) + - zone_page_state(zone, NR_ISOLATED_ANON); + inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) + + node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON); + active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) + + node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON); + isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) + + node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON); return isolated > (inactive + active) / 2; } @@ -856,7 +856,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); /* Try isolate the page */ if (__isolate_lru_page(page, isolate_mode) != 0) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 99578b63814b..481fb0128d21 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1818,7 +1818,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end = -1; int i; - lruvec = mem_cgroup_page_lruvec(head, zone); + lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat); /* complete memcg works before add pages to LRU */ mem_cgroup_split_huge_fixup(head); diff --git a/mm/internal.h b/mm/internal.h index 9b6a6c43ac39..2f80d0343c56 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -78,7 +78,7 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); -extern bool zone_reclaimable(struct zone *zone); +extern bool pgdat_reclaimable(struct pglist_data *pgdat); /* * in mm/rmap.c: diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 7dbee698d6aa..374237bb059d 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -480,7 +480,7 @@ void __khugepaged_exit(struct mm_struct *mm) static void release_pte_page(struct page *page) { /* 0 stands for page_is_file_cache(page) == false */ - dec_zone_page_state(page, NR_ISOLATED_ANON + 0); + dec_node_page_state(page, NR_ISOLATED_ANON + 0); unlock_page(page); putback_lru_page(page); } @@ -576,7 +576,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } /* 0 stands for page_is_file_cache(page) == false */ - inc_zone_page_state(page, NR_ISOLATED_ANON + 0); + inc_node_page_state(page, NR_ISOLATED_ANON + 0); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9b70f9ca8ddf..50c86ad121bc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -943,14 +943,14 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) * and putback protocol: the LRU lock must be held, and the page must * either be PageLRU() or the caller must have isolated/allocated it. */ -struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) +struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { struct mem_cgroup_per_zone *mz; struct mem_cgroup *memcg; struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; + lruvec = &pgdat->lruvec; goto out; } @@ -970,8 +970,8 @@ out: * we have to be prepared to initialize lruvec->zone here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; + if (unlikely(lruvec->pgdat != pgdat)) + lruvec->pgdat = pgdat; return lruvec; } @@ -979,6 +979,7 @@ out: * mem_cgroup_update_lru_size - account for adding or removing an lru page * @lruvec: mem_cgroup per zone lru vector * @lru: index of lru list the page is sitting on + * @zid: Zone ID of the zone pages have been added to * @nr_pages: positive when adding or negative when removing * * This function must be called under lru_lock, just before a page is added @@ -986,14 +987,14 @@ out: * so as to allow it to check that lru_size 0 is consistent with list_empty). */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages) + enum zone_type zid, int nr_pages) { struct mem_cgroup_per_zone *mz; unsigned long *lru_size; long size; bool empty; - __update_lru_size(lruvec, lru, nr_pages); + __update_lru_size(lruvec, lru, zid, nr_pages); if (mem_cgroup_disabled()) return; @@ -2069,7 +2070,7 @@ static void lock_page_lru(struct page *page, int *isolated) if (PageLRU(page)) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_lru(page)); *isolated = 1; @@ -2084,7 +2085,7 @@ static void unlock_page_lru(struct page *page, int isolated) if (isolated) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2fcca6b0e005..11de752ccaf5 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1663,7 +1663,7 @@ static int __soft_offline_page(struct page *page, int flags) put_hwpoison_page(page); if (!ret) { LIST_HEAD(pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, @@ -1671,7 +1671,7 @@ static int __soft_offline_page(struct page *page, int flags) if (ret) { if (!list_empty(&pagelist)) { list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 82d0b98d27f8..c5278360ca66 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1586,7 +1586,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) put_page(page); list_add_tail(&page->lru, &source); move_pages--; - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } else { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 53e40d3f3933..d8c4e38fb5f4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -962,7 +962,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) { if (!isolate_lru_page(page)) { list_add_tail(&page->lru, pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } } diff --git a/mm/migrate.c b/mm/migrate.c index 2232f6923cc7..3033dae33a0a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -168,7 +168,7 @@ void putback_movable_pages(struct list_head *l) continue; } list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); /* * We isolated non-lru movable page so here we can use @@ -1119,7 +1119,7 @@ out: * restored. */ list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } @@ -1460,7 +1460,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, err = isolate_lru_page(page); if (!err) { list_add_tail(&page->lru, &pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } put_and_set: @@ -1726,15 +1726,16 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, unsigned long nr_migrate_pages) { int z; + + if (!pgdat_reclaimable(pgdat)) + return false; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; - if (!zone_reclaimable(zone)) - continue; - /* Avoid waking kswapd by allocating pages_to_migrate pages. */ if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone) + @@ -1828,7 +1829,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) } page_lru = page_is_file_cache(page); - mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, hpage_nr_pages(page)); /* @@ -1886,7 +1887,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } @@ -1979,7 +1980,7 @@ fail_putback: /* Retake the callers reference and putback on LRU */ get_page(page); putback_lru_page(page); - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); goto out_unlock; @@ -2030,7 +2031,7 @@ fail_putback: count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); return isolated; diff --git a/mm/mlock.c b/mm/mlock.c index 997f63082ff5..14645be06e30 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -103,7 +103,7 @@ static bool __munlock_isolate_lru_page(struct page *page, bool getpage) if (PageLRU(page)) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, page_zone(page)); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (getpage) get_page(page); ClearPageLRU(page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d578d2a56b19..0ada2b2954b0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -285,8 +285,8 @@ static unsigned long zone_dirtyable_memory(struct zone *zone) */ nr_pages -= min(nr_pages, zone->totalreserve_pages); - nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); - nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); + nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE); + nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE); return nr_pages; } @@ -348,8 +348,8 @@ static unsigned long global_dirtyable_memory(void) */ x -= min(x, totalreserve_pages); - x += global_page_state(NR_INACTIVE_FILE); - x += global_page_state(NR_ACTIVE_FILE); + x += global_node_page_state(NR_INACTIVE_FILE); + x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5760c626c309..35e2d0f9d44f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1078,9 +1078,9 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); while (count) { struct page *page; @@ -1135,9 +1135,9 @@ static void free_one_page(struct zone *zone, { unsigned long nr_scanned; spin_lock(&zone->lock); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { @@ -4288,6 +4288,7 @@ void show_free_areas(unsigned int filter) unsigned long free_pcp = 0; int cpu; struct zone *zone; + pg_data_t *pgdat; for_each_populated_zone(zone) { if (skip_free_areas_node(filter, zone_to_nid(zone))) @@ -4306,13 +4307,13 @@ void show_free_areas(unsigned int filter) " anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n" #endif " free:%lu free_pcp:%lu free_cma:%lu\n", - global_page_state(NR_ACTIVE_ANON), - global_page_state(NR_INACTIVE_ANON), - global_page_state(NR_ISOLATED_ANON), - global_page_state(NR_ACTIVE_FILE), - global_page_state(NR_INACTIVE_FILE), - global_page_state(NR_ISOLATED_FILE), - global_page_state(NR_UNEVICTABLE), + global_node_page_state(NR_ACTIVE_ANON), + global_node_page_state(NR_INACTIVE_ANON), + global_node_page_state(NR_ISOLATED_ANON), + global_node_page_state(NR_ACTIVE_FILE), + global_node_page_state(NR_INACTIVE_FILE), + global_node_page_state(NR_ISOLATED_FILE), + global_node_page_state(NR_UNEVICTABLE), global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), @@ -4331,6 +4332,28 @@ void show_free_areas(unsigned int filter) free_pcp, global_page_state(NR_FREE_CMA_PAGES)); + for_each_online_pgdat(pgdat) { + printk("Node %d" + " active_anon:%lukB" + " inactive_anon:%lukB" + " active_file:%lukB" + " inactive_file:%lukB" + " unevictable:%lukB" + " isolated(anon):%lukB" + " isolated(file):%lukB" + " all_unreclaimable? %s" + "\n", + pgdat->node_id, + K(node_page_state(pgdat, NR_ACTIVE_ANON)), + K(node_page_state(pgdat, NR_INACTIVE_ANON)), + K(node_page_state(pgdat, NR_ACTIVE_FILE)), + K(node_page_state(pgdat, NR_INACTIVE_FILE)), + K(node_page_state(pgdat, NR_UNEVICTABLE)), + K(node_page_state(pgdat, NR_ISOLATED_ANON)), + K(node_page_state(pgdat, NR_ISOLATED_FILE)), + !pgdat_reclaimable(pgdat) ? "yes" : "no"); + } + for_each_populated_zone(zone) { int i; @@ -4347,13 +4370,6 @@ void show_free_areas(unsigned int filter) " min:%lukB" " low:%lukB" " high:%lukB" - " active_anon:%lukB" - " inactive_anon:%lukB" - " active_file:%lukB" - " inactive_file:%lukB" - " unevictable:%lukB" - " isolated(anon):%lukB" - " isolated(file):%lukB" " present:%lukB" " managed:%lukB" " mlocked:%lukB" @@ -4376,21 +4392,13 @@ void show_free_areas(unsigned int filter) " local_pcp:%ukB" " free_cma:%lukB" " writeback_tmp:%lukB" - " pages_scanned:%lu" - " all_unreclaimable? %s" + " node_pages_scanned:%lu" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), - K(zone_page_state(zone, NR_ACTIVE_ANON)), - K(zone_page_state(zone, NR_INACTIVE_ANON)), - K(zone_page_state(zone, NR_ACTIVE_FILE)), - K(zone_page_state(zone, NR_INACTIVE_FILE)), - K(zone_page_state(zone, NR_UNEVICTABLE)), - K(zone_page_state(zone, NR_ISOLATED_ANON)), - K(zone_page_state(zone, NR_ISOLATED_FILE)), K(zone->present_pages), K(zone->managed_pages), K(zone_page_state(zone, NR_MLOCK)), @@ -4415,9 +4423,7 @@ void show_free_areas(unsigned int filter) K(this_cpu_read(zone->pageset->pcp.count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - K(zone_page_state(zone, NR_PAGES_SCANNED)), - (!zone_reclaimable(zone) ? "yes" : "no") - ); + K(node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) printk(" %ld", zone->lowmem_reserve[i]); @@ -5967,7 +5973,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) /* For bootup, initialized properly in watermark setup */ mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); - lruvec_init(&zone->lruvec); + lruvec_init(zone_lruvec(zone)); if (!size) continue; diff --git a/mm/swap.c b/mm/swap.c index bf37e5cfae81..77af473635fe 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -63,7 +63,7 @@ static void __page_cache_release(struct page *page) unsigned long flags; spin_lock_irqsave(zone_lru_lock(zone), flags); - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); @@ -194,7 +194,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, spin_lock_irqsave(zone_lru_lock(zone), flags); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); (*move_fn)(page, lruvec, arg); } if (zone) @@ -319,7 +319,7 @@ void activate_page(struct page *page) page = compound_head(page); spin_lock_irq(zone_lru_lock(zone)); - __activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL); + __activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL); spin_unlock_irq(zone_lru_lock(zone)); } #endif @@ -445,16 +445,16 @@ void lru_cache_add(struct page *page) */ void add_page_to_unevictable_list(struct page *page) { - struct zone *zone = page_zone(page); + struct pglist_data *pgdat = page_pgdat(page); struct lruvec *lruvec; - spin_lock_irq(zone_lru_lock(zone)); - lruvec = mem_cgroup_page_lruvec(page, zone); + spin_lock_irq(&pgdat->lru_lock); + lruvec = mem_cgroup_page_lruvec(page, pgdat); ClearPageActive(page); SetPageUnevictable(page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); } /** @@ -730,7 +730,7 @@ void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); - struct zone *zone = NULL; + struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; unsigned long uninitialized_var(flags); unsigned int uninitialized_var(lock_batch); @@ -741,11 +741,11 @@ void release_pages(struct page **pages, int nr, bool cold) /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the - * same zone. The lock is held only if zone != NULL. + * same pgdat. The lock is held only if pgdat != NULL. */ - if (zone && ++lock_batch == SWAP_CLUSTER_MAX) { - spin_unlock_irqrestore(zone_lru_lock(zone), flags); - zone = NULL; + if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; } if (is_huge_zero_page(page)) { @@ -758,27 +758,27 @@ void release_pages(struct page **pages, int nr, bool cold) continue; if (PageCompound(page)) { - if (zone) { - spin_unlock_irqrestore(zone_lru_lock(zone), flags); - zone = NULL; + if (locked_pgdat) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { - struct zone *pagezone = page_zone(page); + struct pglist_data *pgdat = page_pgdat(page); - if (pagezone != zone) { - if (zone) - spin_unlock_irqrestore(zone_lru_lock(zone), + if (pgdat != locked_pgdat) { + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); lock_batch = 0; - zone = pagezone; - spin_lock_irqsave(zone_lru_lock(zone), flags); + locked_pgdat = pgdat; + spin_lock_irqsave(&locked_pgdat->lru_lock, flags); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); @@ -789,8 +789,8 @@ void release_pages(struct page **pages, int nr, bool cold) list_add(&page->lru, &pages_to_free); } - if (zone) - spin_unlock_irqrestore(zone_lru_lock(zone), flags); + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); mem_cgroup_uncharge_list(&pages_to_free); free_hot_cold_page_list(&pages_to_free, cold); @@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); VM_BUG_ON(NR_CPUS != 1 && - !spin_is_locked(zone_lru_lock(lruvec_zone(lruvec)))); + !spin_is_locked(&lruvec_pgdat(lruvec)->lru_lock)); if (!list) SetPageLRU(page_tail); diff --git a/mm/vmscan.c b/mm/vmscan.c index e7ffcd259cc4..86a523a761c9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -191,26 +191,42 @@ static bool sane_reclaim(struct scan_control *sc) } #endif +/* + * This misses isolated pages which are not accounted for to save counters. + * As the data only determines if reclaim or compaction continues, it is + * not expected that isolated pages will be a dominating factor. + */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; - nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) + - zone_page_state_snapshot(zone, NR_INACTIVE_FILE) + - zone_page_state_snapshot(zone, NR_ISOLATED_FILE); + nr = zone_page_state_snapshot(zone, NR_ZONE_LRU_FILE); + if (get_nr_swap_pages() > 0) + nr += zone_page_state_snapshot(zone, NR_ZONE_LRU_ANON); + + return nr; +} + +unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat) +{ + unsigned long nr; + + nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) + + node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) + + node_page_state_snapshot(pgdat, NR_ISOLATED_FILE); if (get_nr_swap_pages() > 0) - nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) + - zone_page_state_snapshot(zone, NR_INACTIVE_ANON) + - zone_page_state_snapshot(zone, NR_ISOLATED_ANON); + nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) + + node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) + + node_page_state_snapshot(pgdat, NR_ISOLATED_ANON); return nr; } -bool zone_reclaimable(struct zone *zone) +bool pgdat_reclaimable(struct pglist_data *pgdat) { - return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) < - zone_reclaimable_pages(zone) * 6; + return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) < + pgdat_reclaimable_pages(pgdat) * 6; } unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -218,7 +234,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) if (!mem_cgroup_disabled()) return mem_cgroup_get_lru_size(lruvec, lru); - return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru); + return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); } /* @@ -877,7 +893,7 @@ static void page_check_dirty_writeback(struct page *page, * shrink_page_list() returns the number of reclaimed pages */ static unsigned long shrink_page_list(struct list_head *page_list, - struct zone *zone, + struct pglist_data *pgdat, struct scan_control *sc, enum ttu_flags ttu_flags, unsigned long *ret_nr_dirty, @@ -917,7 +933,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep; VM_BUG_ON_PAGE(PageActive(page), page); - VM_BUG_ON_PAGE(page_zone(page) != zone, page); sc->nr_scanned++; @@ -996,7 +1011,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Case 1 above */ if (current_is_kswapd() && PageReclaim(page) && - test_bit(ZONE_WRITEBACK, &zone->flags)) { + test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { nr_immediate++; goto keep_locked; @@ -1092,7 +1107,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ if (page_is_file_cache(page) && (!current_is_kswapd() || - !test_bit(ZONE_DIRTY, &zone->flags))) { + !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() @@ -1266,11 +1281,11 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, } } - ret = shrink_page_list(&clean_pages, zone, &sc, + ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret); return ret; } @@ -1375,7 +1390,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; - unsigned long scan; + unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; + unsigned long scan, nr_pages; for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src); scan++) { @@ -1388,7 +1404,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, switch (__isolate_lru_page(page, mode)) { case 0: - nr_taken += hpage_nr_pages(page); + nr_pages = hpage_nr_pages(page); + nr_taken += nr_pages; + nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); break; @@ -1405,6 +1423,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, *nr_scanned = scan; trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan, nr_taken, mode, is_file_lru(lru)); + for (scan = 0; scan < MAX_NR_ZONES; scan++) { + nr_pages = nr_zone_taken[scan]; + if (!nr_pages) + continue; + + update_lru_size(lruvec, lru, scan, -nr_pages); + } return nr_taken; } @@ -1445,7 +1470,7 @@ int isolate_lru_page(struct page *page) struct lruvec *lruvec; spin_lock_irq(zone_lru_lock(zone)); - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); @@ -1465,7 +1490,7 @@ int isolate_lru_page(struct page *page) * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ -static int too_many_isolated(struct zone *zone, int file, +static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; @@ -1477,11 +1502,11 @@ static int too_many_isolated(struct zone *zone, int file, return 0; if (file) { - inactive = zone_page_state(zone, NR_INACTIVE_FILE); - isolated = zone_page_state(zone, NR_ISOLATED_FILE); + inactive = node_page_state(pgdat, NR_INACTIVE_FILE); + isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { - inactive = zone_page_state(zone, NR_INACTIVE_ANON); - isolated = zone_page_state(zone, NR_ISOLATED_ANON); + inactive = node_page_state(pgdat, NR_INACTIVE_ANON); + isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* @@ -1499,7 +1524,7 @@ static noinline_for_stack void putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) { struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); LIST_HEAD(pages_to_free); /* @@ -1512,13 +1537,13 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); putback_lru_page(page); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); continue; } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); SetPageLRU(page); lru = page_lru(page); @@ -1535,10 +1560,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); } @@ -1582,10 +1607,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned long nr_immediate = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - while (unlikely(too_many_isolated(zone, file, sc))) { + while (unlikely(too_many_isolated(pgdat, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); /* We are about to die and free our memory. Return now. */ @@ -1600,48 +1625,45 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, isolate_mode, lru); - update_lru_size(lruvec, lru, -nr_taken); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); reclaim_stat->recent_scanned[file] += nr_taken; if (global_reclaim(sc)) { - __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); + __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) - __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); + __count_vm_events(PGSCAN_KSWAPD, nr_scanned); else - __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); + __count_vm_events(PGSCAN_DIRECT, nr_scanned); } - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) return 0; - nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP, + nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP, &nr_dirty, &nr_unqueued_dirty, &nr_congested, &nr_writeback, &nr_immediate, false); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); if (global_reclaim(sc)) { if (current_is_kswapd()) - __count_zone_vm_events(PGSTEAL_KSWAPD, zone, - nr_reclaimed); + __count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed); else - __count_zone_vm_events(PGSTEAL_DIRECT, zone, - nr_reclaimed); + __count_vm_events(PGSTEAL_DIRECT, nr_reclaimed); } putback_inactive_pages(lruvec, &page_list); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&page_list); free_hot_cold_page_list(&page_list, true); @@ -1661,7 +1683,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * are encountered in the nr_immediate check below. */ if (nr_writeback && nr_writeback == nr_taken) - set_bit(ZONE_WRITEBACK, &zone->flags); + set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* * Legacy memcg will stall in page writeback so avoid forcibly @@ -1673,16 +1695,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * backed by a congested BDI and wait_iff_congested will stall. */ if (nr_dirty && nr_dirty == nr_congested) - set_bit(ZONE_CONGESTED, &zone->flags); + set_bit(PGDAT_CONGESTED, &pgdat->flags); /* * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not keeping up. In this case, flag - * the zone ZONE_DIRTY and kswapd will start writing pages from + * the pgdat PGDAT_DIRTY and kswapd will start writing pages from * reclaim context. */ if (nr_unqueued_dirty == nr_taken) - set_bit(ZONE_DIRTY, &zone->flags); + set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked marked for immediate @@ -1701,9 +1723,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, */ if (!sc->hibernation_mode && !current_is_kswapd() && current_may_throttle()) - wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); + wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10); - trace_mm_vmscan_lru_shrink_inactive(zone, nr_scanned, nr_reclaimed, + trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, + nr_scanned, nr_reclaimed, sc->priority, file); return nr_reclaimed; } @@ -1731,20 +1754,20 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, struct list_head *pages_to_free, enum lru_list lru) { - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long pgmoved = 0; struct page *page; int nr_pages; while (!list_empty(list)) { page = lru_to_page(list); - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); nr_pages = hpage_nr_pages(page); - update_lru_size(lruvec, lru, nr_pages); + update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); pgmoved += nr_pages; @@ -1754,10 +1777,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, pages_to_free); } @@ -1783,7 +1806,7 @@ static void shrink_active_list(unsigned long nr_to_scan, unsigned long nr_rotated = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); @@ -1792,20 +1815,19 @@ static void shrink_active_list(unsigned long nr_to_scan, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); - update_lru_size(lruvec, lru, -nr_taken); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); reclaim_stat->recent_scanned[file] += nr_taken; if (global_reclaim(sc)) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); - __count_zone_vm_events(PGREFILL, zone, nr_scanned); + __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); + __count_vm_events(PGREFILL, nr_scanned); - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); while (!list_empty(&l_hold)) { cond_resched(); @@ -1850,7 +1872,7 @@ static void shrink_active_list(unsigned long nr_to_scan, /* * Move pages back to the lru list. */ - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); /* * Count referenced pages from currently used mappings as rotated, * even though only some of them are actually re-activated. This @@ -1861,8 +1883,8 @@ static void shrink_active_list(unsigned long nr_to_scan, move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(zone_lru_lock(zone)); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_hold); free_hot_cold_page_list(&l_hold, true); @@ -1956,7 +1978,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; u64 denominator = 0; /* gcc */ - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; @@ -1977,7 +1999,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * well. */ if (current_is_kswapd()) { - if (!zone_reclaimable(zone)) + if (!pgdat_reclaimable(pgdat)) force_scan = true; if (!mem_cgroup_online(memcg)) force_scan = true; @@ -2023,14 +2045,24 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anon pages. Try to detect this based on file LRU size. */ if (global_reclaim(sc)) { - unsigned long zonefile; - unsigned long zonefree; + unsigned long pgdatfile; + unsigned long pgdatfree; + int z; + unsigned long total_high_wmark = 0; - zonefree = zone_page_state(zone, NR_FREE_PAGES); - zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); + pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); + pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) + + node_page_state(pgdat, NR_INACTIVE_FILE); + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!populated_zone(zone)) + continue; + + total_high_wmark += high_wmark_pages(zone); + } - if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { + if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) { scan_balance = SCAN_ANON; goto out; } @@ -2077,7 +2109,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) + lruvec_lru_size(lruvec, LRU_INACTIVE_FILE); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; reclaim_stat->recent_rotated[0] /= 2; @@ -2098,7 +2130,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); fp /= reclaim_stat->recent_rotated[1] + 1; - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); fraction[0] = ap; fraction[1] = fp; @@ -2352,9 +2384,9 @@ static inline bool should_continue_reclaim(struct zone *zone, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE); + inactive_lru_pages = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) - inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON); + inactive_lru_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; @@ -2554,7 +2586,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; if (sc->priority != DEF_PRIORITY && - !zone_reclaimable(zone)) + !pgdat_reclaimable(zone->zone_pgdat)) continue; /* Let kswapd poll it */ /* @@ -2692,7 +2724,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!populated_zone(zone) || - zone_reclaimable_pages(zone) == 0) + pgdat_reclaimable_pages(pgdat) == 0) continue; pfmemalloc_reserve += min_wmark_pages(zone); @@ -3000,7 +3032,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * DEF_PRIORITY. Effectively, it considers them balanced so * they must be considered balanced here as well! */ - if (!zone_reclaimable(zone)) { + if (!pgdat_reclaimable(zone->zone_pgdat)) { balanced_pages += zone->managed_pages; continue; } @@ -3063,6 +3095,7 @@ static bool kswapd_shrink_zone(struct zone *zone, { unsigned long balance_gap; bool lowmem_pressure; + struct pglist_data *pgdat = zone->zone_pgdat; /* Reclaim above the high watermark. */ sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone)); @@ -3087,7 +3120,8 @@ static bool kswapd_shrink_zone(struct zone *zone, shrink_zone(zone, sc, zone_idx(zone) == classzone_idx); - clear_bit(ZONE_WRITEBACK, &zone->flags); + /* TODO: ANOMALY */ + clear_bit(PGDAT_WRITEBACK, &pgdat->flags); /* * If a zone reaches its high watermark, consider it to be no longer @@ -3095,10 +3129,10 @@ static bool kswapd_shrink_zone(struct zone *zone, * BDIs but as pressure is relieved, speculatively avoid congestion * waits. */ - if (zone_reclaimable(zone) && + if (pgdat_reclaimable(zone->zone_pgdat) && zone_balanced(zone, sc->order, false, 0, classzone_idx)) { - clear_bit(ZONE_CONGESTED, &zone->flags); - clear_bit(ZONE_DIRTY, &zone->flags); + clear_bit(PGDAT_CONGESTED, &pgdat->flags); + clear_bit(PGDAT_DIRTY, &pgdat->flags); } return sc->nr_scanned >= sc->nr_to_reclaim; @@ -3157,7 +3191,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) continue; if (sc.priority != DEF_PRIORITY && - !zone_reclaimable(zone)) + !pgdat_reclaimable(zone->zone_pgdat)) continue; /* @@ -3184,9 +3218,11 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) /* * If balanced, clear the dirty and congested * flags + * + * TODO: ANOMALY */ - clear_bit(ZONE_CONGESTED, &zone->flags); - clear_bit(ZONE_DIRTY, &zone->flags); + clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags); + clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags); } } @@ -3216,7 +3252,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) continue; if (sc.priority != DEF_PRIORITY && - !zone_reclaimable(zone)) + !pgdat_reclaimable(zone->zone_pgdat)) continue; sc.nr_scanned = 0; @@ -3612,8 +3648,8 @@ int sysctl_min_slab_ratio = 5; static inline unsigned long zone_unmapped_file_pages(struct zone *zone) { unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED); - unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) + - zone_page_state(zone, NR_ACTIVE_FILE); + unsigned long file_lru = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) + + node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than @@ -3716,7 +3752,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) return ZONE_RECLAIM_FULL; - if (!zone_reclaimable(zone)) + if (!pgdat_reclaimable(zone->zone_pgdat)) return ZONE_RECLAIM_FULL; /* @@ -3795,7 +3831,7 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) zone = pagezone; spin_lock_irq(zone_lru_lock(zone)); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); if (!PageLRU(page) || !PageUnevictable(page)) continue; diff --git a/mm/vmstat.c b/mm/vmstat.c index 3345d396a99b..de0c17076270 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -936,11 +936,8 @@ const char * const vmstat_text[] = { /* enum zone_stat_item countes */ "nr_free_pages", "nr_alloc_batch", - "nr_inactive_anon", - "nr_active_anon", - "nr_inactive_file", - "nr_active_file", - "nr_unevictable", + "nr_zone_anon_lru", + "nr_zone_file_lru", "nr_mlock", "nr_anon_pages", "nr_mapped", @@ -956,12 +953,9 @@ const char * const vmstat_text[] = { "nr_vmscan_write", "nr_vmscan_immediate_reclaim", "nr_writeback_temp", - "nr_isolated_anon", - "nr_isolated_file", "nr_shmem", "nr_dirtied", "nr_written", - "nr_pages_scanned", #if IS_ENABLED(CONFIG_ZSMALLOC) "nr_zspages", #endif @@ -981,6 +975,16 @@ const char * const vmstat_text[] = { "nr_shmem_pmdmapped", "nr_free_cma", + /* Node-based counters */ + "nr_inactive_anon", + "nr_active_anon", + "nr_inactive_file", + "nr_active_file", + "nr_unevictable", + "nr_isolated_anon", + "nr_isolated_file", + "nr_pages_scanned", + /* enum writeback_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -1002,11 +1006,11 @@ const char * const vmstat_text[] = { "pgmajfault", "pglazyfreed", - TEXTS_FOR_ZONES("pgrefill") - TEXTS_FOR_ZONES("pgsteal_kswapd") - TEXTS_FOR_ZONES("pgsteal_direct") - TEXTS_FOR_ZONES("pgscan_kswapd") - TEXTS_FOR_ZONES("pgscan_direct") + "pgrefill", + "pgsteal_kswapd", + "pgsteal_direct", + "pgscan_kswapd", + "pgscan_direct", "pgscan_direct_throttle", #ifdef CONFIG_NUMA @@ -1434,7 +1438,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n min %lu" "\n low %lu" "\n high %lu" - "\n scanned %lu" + "\n node_scanned %lu" "\n spanned %lu" "\n present %lu" "\n managed %lu", @@ -1442,13 +1446,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone_page_state(zone, NR_PAGES_SCANNED), + node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], + seq_printf(m, "\n %-12s %lu", vmstat_text[i], zone_page_state(zone, i)); seq_printf(m, @@ -1478,12 +1482,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, #endif } seq_printf(m, - "\n all_unreclaimable: %u" - "\n start_pfn: %lu" - "\n inactive_ratio: %u", - !zone_reclaimable(zone), + "\n node_unreclaimable: %u" + "\n start_pfn: %lu" + "\n node_inactive_ratio: %u", + !pgdat_reclaimable(zone->zone_pgdat), zone->zone_start_pfn, - zone->inactive_ratio); + zone->zone_pgdat->inactive_ratio); seq_putc(m, '\n'); } @@ -1574,7 +1578,6 @@ static int vmstat_show(struct seq_file *m, void *arg) { unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); return 0; } diff --git a/mm/workingset.c b/mm/workingset.c index 5ffba0c0adc6..7820a7e1ca98 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -355,8 +355,8 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); } else { - pages = sum_zone_node_page_state(sc->nid, NR_ACTIVE_FILE) + - sum_zone_node_page_state(sc->nid, NR_INACTIVE_FILE); + pages = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); } /* -- cgit v1.2.3-55-g7522 From a9dd0a83104c01269ea36a9b4ec42b51edf85427 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:02 -0700 Subject: mm, vmscan: make shrink_node decisions more node-centric Earlier patches focused on having direct reclaim and kswapd use data that is node-centric for reclaiming but shrink_node() itself still uses too much zone information. This patch removes unnecessary zone-based information with the most important decision being whether to continue reclaim or not. Some memcg APIs are adjusted as a result even though memcg itself still uses some zone information. [mgorman@techsingularity.net: optimization] Link: http://lkml.kernel.org/r/1468588165-12461-2-git-send-email-mgorman@techsingularity.net Link: http://lkml.kernel.org/r/1467970510-21195-14-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 ++++++++------- include/linux/mmzone.h | 4 +-- include/linux/swap.h | 2 +- mm/memcontrol.c | 4 +-- mm/page_alloc.c | 2 +- mm/vmscan.c | 61 ++++++++++++++++++++++++++-------------------- mm/workingset.c | 6 ++--- 7 files changed, 54 insertions(+), 44 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6d2321c148cd..f4963ee4fdbc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -324,22 +324,23 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) } /** - * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg + * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone + * @node: node of the wanted lruvec * @zone: zone of the wanted lruvec * @memcg: memcg of the wanted lruvec * - * Returns the lru list vector holding pages for the given @zone and - * @mem. This can be the global zone lruvec, if the memory controller + * Returns the lru list vector holding pages for a given @node or a given + * @memcg and @zone. This can be the node lruvec, if the memory controller * is disabled. */ -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, + struct zone *zone, struct mem_cgroup *memcg) { struct mem_cgroup_per_zone *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = zone_lruvec(zone); + lruvec = node_lruvec(pgdat); goto out; } @@ -609,10 +610,10 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, + struct zone *zone, struct mem_cgroup *memcg) { - return zone_lruvec(zone); + return node_lruvec(pgdat); } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4062fa74526f..895c365e3259 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -739,9 +739,9 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone) return &zone->zone_pgdat->lru_lock; } -static inline struct lruvec *zone_lruvec(struct zone *zone) +static inline struct lruvec *node_lruvec(struct pglist_data *pgdat) { - return &zone->zone_pgdat->lruvec; + return &pgdat->lruvec; } static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) diff --git a/include/linux/swap.h b/include/linux/swap.h index 916e2eddecd6..0ad616d7c381 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -316,7 +316,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap); -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, +extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, struct zone *zone, unsigned long *nr_scanned); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 50c86ad121bc..c9ebec98e92a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1432,8 +1432,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, } continue; } - total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, - zone, &nr_scanned); + total += mem_cgroup_shrink_node(victim, gfp_mask, false, + zone, &nr_scanned); *total_scanned += nr_scanned; if (!soft_limit_excess(root_memcg)) break; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 81586410c59c..749b3c358ead 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5911,6 +5911,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) #endif pgdat_page_ext_init(pgdat); spin_lock_init(&pgdat->lru_lock); + lruvec_init(node_lruvec(pgdat)); for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; @@ -5973,7 +5974,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) /* For bootup, initialized properly in watermark setup */ mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); - lruvec_init(zone_lruvec(zone)); if (!size) continue; diff --git a/mm/vmscan.c b/mm/vmscan.c index b7a276f4b1b0..46f7a71ed13b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2224,12 +2224,13 @@ static inline void init_tlb_ubc(void) #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* - * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. + * This is a basic per-node page freer. Used by both kswapd and direct reclaim. */ -static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg, +static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg, struct scan_control *sc, unsigned long *lru_pages) { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + struct zone *zone = &pgdat->node_zones[sc->reclaim_idx]; + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg); unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; @@ -2362,13 +2363,14 @@ static bool in_reclaim_compaction(struct scan_control *sc) * calls try_to_compact_zone() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ -static inline bool should_continue_reclaim(struct zone *zone, +static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, unsigned long nr_scanned, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; + int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) @@ -2402,21 +2404,29 @@ static inline bool should_continue_reclaim(struct zone *zone, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE); + inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) - inactive_lru_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON); + inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; /* If compaction would go ahead or the allocation would succeed, stop */ - switch (compaction_suitable(zone, sc->order, 0, 0)) { - case COMPACT_PARTIAL: - case COMPACT_CONTINUE: - return false; - default: - return true; + for (z = 0; z <= sc->reclaim_idx; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!populated_zone(zone)) + continue; + + switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { + case COMPACT_PARTIAL: + case COMPACT_CONTINUE: + return false; + default: + /* check next zone */ + ; + } } + return true; } static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, @@ -2425,15 +2435,14 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; bool reclaimable = false; - struct zone *zone = &pgdat->node_zones[classzone_idx]; do { struct mem_cgroup *root = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, + .zone = &pgdat->node_zones[classzone_idx], .priority = sc->priority, }; - unsigned long zone_lru_pages = 0; + unsigned long node_lru_pages = 0; struct mem_cgroup *memcg; nr_reclaimed = sc->nr_reclaimed; @@ -2454,11 +2463,11 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; - shrink_zone_memcg(zone, memcg, sc, &lru_pages); - zone_lru_pages += lru_pages; + shrink_node_memcg(pgdat, memcg, sc, &lru_pages); + node_lru_pages += lru_pages; if (!global_reclaim(sc)) - shrink_slab(sc->gfp_mask, zone_to_nid(zone), + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->nr_scanned - scanned, lru_pages); @@ -2470,7 +2479,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the - * zone. + * node. * * Limit reclaim, on the other hand, only cares about * nr_to_reclaim pages to be reclaimed and it will @@ -2489,9 +2498,9 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, * the eligible LRU pages were scanned. */ if (global_reclaim(sc)) - shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL, + shrink_slab(sc->gfp_mask, pgdat->node_id, NULL, sc->nr_scanned - nr_scanned, - zone_lru_pages); + node_lru_pages); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; @@ -2506,7 +2515,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; - } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, + } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); return reclaimable; @@ -2906,7 +2915,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #ifdef CONFIG_MEMCG -unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, +unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, struct zone *zone, unsigned long *nr_scanned) @@ -2931,11 +2940,11 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. - * if we don't reclaim here, the shrink_zone from balance_pgdat + * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_zone_memcg(zone, memcg, &sc, &lru_pages); + shrink_node_memcg(zone->zone_pgdat, memcg, &sc, &lru_pages); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); @@ -2994,7 +3003,7 @@ static void age_active_anon(struct pglist_data *pgdat, memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg); if (inactive_list_is_low(lruvec, false)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, diff --git a/mm/workingset.c b/mm/workingset.c index 7820a7e1ca98..df0dacaf54ee 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -218,7 +218,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - lruvec = mem_cgroup_zone_lruvec(zone, memcg); + lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); return pack_shadow(memcgid, zone, eviction); } @@ -267,7 +267,7 @@ bool workingset_refault(void *shadow) rcu_read_unlock(); return false; } - lruvec = mem_cgroup_zone_lruvec(zone, memcg); + lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE); rcu_read_unlock(); @@ -319,7 +319,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_zone_lruvec(page_zone(page), memcg); + lruvec = mem_cgroup_lruvec(page_pgdat(page), page_zone(page), memcg); atomic_long_inc(&lruvec->inactive_age); out: rcu_read_unlock(); -- cgit v1.2.3-55-g7522 From ef8f2327996b5c20f11420f64e439e87c7a01604 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:05 -0700 Subject: mm, memcg: move memcg limit enforcement from zones to nodes Memcg needs adjustment after moving LRUs to the node. Limits are tracked per memcg but the soft-limit excess is tracked per zone. As global page reclaim is based on the node, it is easy to imagine a situation where a zone soft limit is exceeded even though the memcg limit is fine. This patch moves the soft limit tree the node. Technically, all the variable names should also change but people are already familiar by the meaning of "mz" even if "mn" would be a more appropriate name now. Link: http://lkml.kernel.org/r/1467970510-21195-15-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Michal Hocko Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 38 ++++----- include/linux/swap.h | 2 +- mm/memcontrol.c | 190 ++++++++++++++++++++------------------------- mm/vmscan.c | 19 +++-- mm/workingset.c | 6 +- 5 files changed, 111 insertions(+), 144 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f4963ee4fdbc..b759827b2f1e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -60,7 +60,7 @@ enum mem_cgroup_stat_index { }; struct mem_cgroup_reclaim_cookie { - struct zone *zone; + pg_data_t *pgdat; int priority; unsigned int generation; }; @@ -118,7 +118,7 @@ struct mem_cgroup_reclaim_iter { /* * per-zone information in memory controller. */ -struct mem_cgroup_per_zone { +struct mem_cgroup_per_node { struct lruvec lruvec; unsigned long lru_size[NR_LRU_LISTS]; @@ -132,10 +132,6 @@ struct mem_cgroup_per_zone { /* use container_of */ }; -struct mem_cgroup_per_node { - struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; -}; - struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; @@ -314,19 +310,15 @@ void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); -static inline struct mem_cgroup_per_zone * -mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) +static struct mem_cgroup_per_node * +mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { - int nid = zone_to_nid(zone); - int zid = zone_idx(zone); - - return &memcg->nodeinfo[nid]->zoneinfo[zid]; + return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone * @node: node of the wanted lruvec - * @zone: zone of the wanted lruvec * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @node or a given @@ -334,9 +326,9 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) * is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct zone *zone, struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { @@ -344,7 +336,7 @@ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, goto out; } - mz = mem_cgroup_zone_zoneinfo(memcg, zone); + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* @@ -352,8 +344,8 @@ out: * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->pgdat != zone->zone_pgdat)) - lruvec->pgdat = zone->zone_pgdat; + if (unlikely(lruvec->pgdat != pgdat)) + lruvec->pgdat = pgdat; return lruvec; } @@ -446,9 +438,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; - mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->lru_size[lru]; } @@ -519,7 +511,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); @@ -611,7 +603,7 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) } static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct zone *zone, struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { return node_lruvec(pgdat); } @@ -723,7 +715,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 0ad616d7c381..2a23ddc96edd 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -318,7 +318,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, bool may_swap); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, - struct zone *zone, + pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c9ebec98e92a..9cbd40ebccd1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -132,15 +132,11 @@ static const char * const mem_cgroup_lru_names[] = { * their hierarchy representation */ -struct mem_cgroup_tree_per_zone { +struct mem_cgroup_tree_per_node { struct rb_root rb_root; spinlock_t lock; }; -struct mem_cgroup_tree_per_node { - struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; -}; - struct mem_cgroup_tree { struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; }; @@ -374,37 +370,35 @@ ino_t page_cgroup_ino(struct page *page) return ino; } -static struct mem_cgroup_per_zone * -mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) +static struct mem_cgroup_per_node * +mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); - int zid = page_zonenum(page); - return &memcg->nodeinfo[nid]->zoneinfo[zid]; + return memcg->nodeinfo[nid]; } -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_node_zone(int nid, int zid) +static struct mem_cgroup_tree_per_node * +soft_limit_tree_node(int nid) { - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; + return soft_limit_tree.rb_tree_per_node[nid]; } -static struct mem_cgroup_tree_per_zone * +static struct mem_cgroup_tree_per_node * soft_limit_tree_from_page(struct page *page) { int nid = page_to_nid(page); - int zid = page_zonenum(page); - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; + return soft_limit_tree.rb_tree_per_node[nid]; } -static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz, unsigned long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; - struct mem_cgroup_per_zone *mz_node; + struct mem_cgroup_per_node *mz_node; if (mz->on_tree) return; @@ -414,7 +408,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, return; while (*p) { parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + mz_node = rb_entry(parent, struct mem_cgroup_per_node, tree_node); if (mz->usage_in_excess < mz_node->usage_in_excess) p = &(*p)->rb_left; @@ -430,8 +424,8 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, mz->on_tree = true; } -static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) { if (!mz->on_tree) return; @@ -439,8 +433,8 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, mz->on_tree = false; } -static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) { unsigned long flags; @@ -464,8 +458,8 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg) static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) { unsigned long excess; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_per_node *mz; + struct mem_cgroup_tree_per_node *mctz; mctz = soft_limit_tree_from_page(page); /* @@ -473,7 +467,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_page_zoneinfo(memcg, page); + mz = mem_cgroup_page_nodeinfo(memcg, page); excess = soft_limit_excess(memcg); /* * We have to update the tree if mz is on RB-tree or @@ -498,24 +492,22 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { - struct mem_cgroup_tree_per_zone *mctz; - struct mem_cgroup_per_zone *mz; - int nid, zid; + struct mem_cgroup_tree_per_node *mctz; + struct mem_cgroup_per_node *mz; + int nid; for_each_node(nid) { - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - mctz = soft_limit_tree_node_zone(nid, zid); - mem_cgroup_remove_exceeded(mz, mctz); - } + mz = mem_cgroup_nodeinfo(memcg, nid); + mctz = soft_limit_tree_node(nid); + mem_cgroup_remove_exceeded(mz, mctz); } } -static struct mem_cgroup_per_zone * -__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +static struct mem_cgroup_per_node * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) { struct rb_node *rightmost = NULL; - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; retry: mz = NULL; @@ -523,7 +515,7 @@ retry: if (!rightmost) goto done; /* Nothing to reclaim from */ - mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node); /* * Remove the node now but someone else can add it back, * we will to add it back at the end of reclaim to its correct @@ -537,10 +529,10 @@ done: return mz; } -static struct mem_cgroup_per_zone * -mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +static struct mem_cgroup_per_node * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; spin_lock_irq(&mctz->lock); mz = __mem_cgroup_largest_soft_limit_node(mctz); @@ -634,20 +626,16 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) { unsigned long nr = 0; - int zid; + struct mem_cgroup_per_node *mz; + enum lru_list lru; VM_BUG_ON((unsigned)nid >= nr_node_ids); - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - struct mem_cgroup_per_zone *mz; - enum lru_list lru; - - for_each_lru(lru) { - if (!(BIT(lru) & lru_mask)) - continue; - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - nr += mz->lru_size[lru]; - } + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + mz = mem_cgroup_nodeinfo(memcg, nid); + nr += mz->lru_size[lru]; } return nr; } @@ -800,9 +788,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, rcu_read_lock(); if (reclaim) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; - mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); + mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); iter = &mz->iter[reclaim->priority]; if (prev && reclaim->generation != iter->generation) @@ -901,19 +889,17 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) { struct mem_cgroup *memcg = dead_memcg; struct mem_cgroup_reclaim_iter *iter; - struct mem_cgroup_per_zone *mz; - int nid, zid; + struct mem_cgroup_per_node *mz; + int nid; int i; while ((memcg = parent_mem_cgroup(memcg))) { for_each_node(nid) { - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + mz = mem_cgroup_nodeinfo(memcg, nid); + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); } } } @@ -945,7 +931,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) */ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; struct mem_cgroup *memcg; struct lruvec *lruvec; @@ -962,7 +948,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd if (!memcg) memcg = root_mem_cgroup; - mz = mem_cgroup_page_zoneinfo(memcg, page); + mz = mem_cgroup_page_nodeinfo(memcg, page); lruvec = &mz->lruvec; out: /* @@ -989,7 +975,7 @@ out: void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, int nr_pages) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; unsigned long *lru_size; long size; bool empty; @@ -999,7 +985,7 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, if (mem_cgroup_disabled()) return; - mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); lru_size = mz->lru_size + lru; empty = list_empty(lruvec->lists + lru); @@ -1392,7 +1378,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) #endif static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, - struct zone *zone, + pg_data_t *pgdat, gfp_t gfp_mask, unsigned long *total_scanned) { @@ -1402,7 +1388,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, unsigned long excess; unsigned long nr_scanned; struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, + .pgdat = pgdat, .priority = 0, }; @@ -1433,7 +1419,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, continue; } total += mem_cgroup_shrink_node(victim, gfp_mask, false, - zone, &nr_scanned); + pgdat, &nr_scanned); *total_scanned += nr_scanned; if (!soft_limit_excess(root_memcg)) break; @@ -2560,22 +2546,22 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { unsigned long nr_reclaimed = 0; - struct mem_cgroup_per_zone *mz, *next_mz = NULL; + struct mem_cgroup_per_node *mz, *next_mz = NULL; unsigned long reclaimed; int loop = 0; - struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_tree_per_node *mctz; unsigned long excess; unsigned long nr_scanned; if (order > 0) return 0; - mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone)); + mctz = soft_limit_tree_node(pgdat->node_id); /* * This loop can run a while, specially if mem_cgroup's continuously * keep exceeding their soft limit and putting the system under @@ -2590,7 +2576,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; nr_scanned = 0; - reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat, gfp_mask, &nr_scanned); nr_reclaimed += reclaimed; *total_scanned += nr_scanned; @@ -3211,22 +3197,21 @@ static int memcg_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_DEBUG_VM { - int nid, zid; - struct mem_cgroup_per_zone *mz; + pg_data_t *pgdat; + struct mem_cgroup_per_node *mz; struct zone_reclaim_stat *rstat; unsigned long recent_rotated[2] = {0, 0}; unsigned long recent_scanned[2] = {0, 0}; - for_each_online_node(nid) - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - rstat = &mz->lruvec.reclaim_stat; + for_each_online_pgdat(pgdat) { + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + rstat = &mz->lruvec.reclaim_stat; - recent_rotated[0] += rstat->recent_rotated[0]; - recent_rotated[1] += rstat->recent_rotated[1]; - recent_scanned[0] += rstat->recent_scanned[0]; - recent_scanned[1] += rstat->recent_scanned[1]; - } + recent_rotated[0] += rstat->recent_rotated[0]; + recent_rotated[1] += rstat->recent_rotated[1]; + recent_scanned[0] += rstat->recent_scanned[0]; + recent_scanned[1] += rstat->recent_scanned[1]; + } seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]); seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]); seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]); @@ -4106,11 +4091,10 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return idr_find(&mem_cgroup_idr, id); } -static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) +static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_zone *mz; - int zone, tmp = node; + int tmp = node; /* * This routine is called against possible nodes. * But it's BUG to call kmalloc() against offline node. @@ -4125,18 +4109,16 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) if (!pn) return 1; - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = &pn->zoneinfo[zone]; - lruvec_init(&mz->lruvec); - mz->usage_in_excess = 0; - mz->on_tree = false; - mz->memcg = memcg; - } + lruvec_init(&pn->lruvec); + pn->usage_in_excess = 0; + pn->on_tree = false; + pn->memcg = memcg; + memcg->nodeinfo[node] = pn; return 0; } -static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) +static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { kfree(memcg->nodeinfo[node]); } @@ -4147,7 +4129,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) memcg_wb_domain_exit(memcg); for_each_node(node) - free_mem_cgroup_per_zone_info(memcg, node); + free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } @@ -4176,7 +4158,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) goto fail; for_each_node(node) - if (alloc_mem_cgroup_per_zone_info(memcg, node)) + if (alloc_mem_cgroup_per_node_info(memcg, node)) goto fail; if (memcg_wb_domain_init(memcg, GFP_KERNEL)) @@ -5779,18 +5761,12 @@ static int __init mem_cgroup_init(void) for_each_node(node) { struct mem_cgroup_tree_per_node *rtpn; - int zone; rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE); - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - struct mem_cgroup_tree_per_zone *rtpz; - - rtpz = &rtpn->rb_tree_per_zone[zone]; - rtpz->rb_root = RB_ROOT; - spin_lock_init(&rtpz->lock); - } + rtpn->rb_root = RB_ROOT; + spin_lock_init(&rtpn->lock); soft_limit_tree.rb_tree_per_node[node] = rtpn; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 46f7a71ed13b..9f6e673efba7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2229,8 +2229,7 @@ static inline void init_tlb_ubc(void) static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg, struct scan_control *sc, unsigned long *lru_pages) { - struct zone *zone = &pgdat->node_zones[sc->reclaim_idx]; - struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; @@ -2439,7 +2438,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc, do { struct mem_cgroup *root = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { - .zone = &pgdat->node_zones[classzone_idx], + .pgdat = pgdat, .priority = sc->priority, }; unsigned long node_lru_pages = 0; @@ -2647,7 +2646,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; @@ -2917,7 +2916,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, - struct zone *zone, + pg_data_t *pgdat, unsigned long *nr_scanned) { struct scan_control sc = { @@ -2944,7 +2943,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_node_memcg(zone->zone_pgdat, memcg, &sc, &lru_pages); + shrink_node_memcg(pgdat, memcg, &sc, &lru_pages); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); @@ -2994,7 +2993,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, #endif static void age_active_anon(struct pglist_data *pgdat, - struct zone *zone, struct scan_control *sc) + struct scan_control *sc) { struct mem_cgroup *memcg; @@ -3003,7 +3002,7 @@ static void age_active_anon(struct pglist_data *pgdat, memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, zone, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); if (inactive_list_is_low(lruvec, false)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, @@ -3193,7 +3192,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * pages are rotated regardless of classzone as this is * about consistent aging. */ - age_active_anon(pgdat, &pgdat->node_zones[MAX_NR_ZONES - 1], &sc); + age_active_anon(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage @@ -3205,7 +3204,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, sc.order, + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; diff --git a/mm/workingset.c b/mm/workingset.c index df0dacaf54ee..2af14bb5a349 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -218,7 +218,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg); + lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); return pack_shadow(memcgid, zone, eviction); } @@ -267,7 +267,7 @@ bool workingset_refault(void *shadow) rcu_read_unlock(); return false; } - lruvec = mem_cgroup_lruvec(zone->zone_pgdat, zone, memcg); + lruvec = mem_cgroup_lruvec(zone->zone_pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE); rcu_read_unlock(); @@ -319,7 +319,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_lruvec(page_pgdat(page), page_zone(page), memcg); + lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); atomic_long_inc(&lruvec->inactive_age); out: rcu_read_unlock(); -- cgit v1.2.3-55-g7522 From 7ee36a14f06cc937f6b2c2932c2e48f590970581 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:47:17 -0700 Subject: mm, vmscan: Update all zone LRU sizes before updating memcg Minchan Kim reported setting the following warning on a 32-bit system although it can affect 64-bit systems. WARNING: CPU: 4 PID: 1322 at mm/memcontrol.c:998 mem_cgroup_update_lru_size+0x103/0x110 mem_cgroup_update_lru_size(f44b4000, 1, -7): zid 1 lru_size 1 but empty Modules linked in: CPU: 4 PID: 1322 Comm: cp Not tainted 4.7.0-rc4-mm1+ #143 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x76/0xaf __warn+0xea/0x110 ? mem_cgroup_update_lru_size+0x103/0x110 warn_slowpath_fmt+0x3b/0x40 mem_cgroup_update_lru_size+0x103/0x110 isolate_lru_pages.isra.61+0x2e2/0x360 shrink_active_list+0xac/0x2a0 ? __delay+0xe/0x10 shrink_node_memcg+0x53c/0x7a0 shrink_node+0xab/0x2a0 do_try_to_free_pages+0xc6/0x390 try_to_free_pages+0x245/0x590 LRU list contents and counts are updated separately. Counts are updated before pages are added to the LRU and updated after pages are removed. The warning above is from a check in mem_cgroup_update_lru_size that ensures that list sizes of zero are empty. The problem is that node-lru needs to account for highmem pages if CONFIG_HIGHMEM is set. One impact of the implementation is that the sizes are updated in multiple passes when pages from multiple zones were isolated. This happens whether HIGHMEM is set or not. When multiple zones are isolated, it's possible for a debugging check in memcg to be tripped. This patch forces all the zone counts to be updated before the memcg function is called. Link: http://lkml.kernel.org/r/1468588165-12461-6-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Tested-by: Minchan Kim Reported-by: Minchan Kim Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- include/linux/mm_inline.h | 5 ++--- mm/memcontrol.c | 5 +---- mm/vmscan.c | 40 +++++++++++++++++++++++++++++++++------- 4 files changed, 37 insertions(+), 15 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b759827b2f1e..5147e650287a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -430,7 +430,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - enum zone_type zid, int nr_pages); + int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index dd22b08c47be..bcc4ed07fa90 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -52,10 +52,9 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, int nr_pages) { -#ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); -#else __update_lru_size(lruvec, lru, zid, nr_pages); +#ifdef CONFIG_MEMCG + mem_cgroup_update_lru_size(lruvec, lru, nr_pages); #endif } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9cbd40ebccd1..13be30c3ea78 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -965,7 +965,6 @@ out: * mem_cgroup_update_lru_size - account for adding or removing an lru page * @lruvec: mem_cgroup per zone lru vector * @lru: index of lru list the page is sitting on - * @zid: Zone ID of the zone pages have been added to * @nr_pages: positive when adding or negative when removing * * This function must be called under lru_lock, just before a page is added @@ -973,15 +972,13 @@ out: * so as to allow it to check that lru_size 0 is consistent with list_empty). */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - enum zone_type zid, int nr_pages) + int nr_pages) { struct mem_cgroup_per_node *mz; unsigned long *lru_size; long size; bool empty; - __update_lru_size(lruvec, lru, zid, nr_pages); - if (mem_cgroup_disabled()) return; diff --git a/mm/vmscan.c b/mm/vmscan.c index 5625eccc0140..b3f5b359280d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1350,6 +1350,38 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) return ret; } + +/* + * Update LRU sizes after isolating pages. The LRU size updates must + * be complete before mem_cgroup_update_lru_size due to a santity check. + */ +static __always_inline void update_lru_sizes(struct lruvec *lruvec, + enum lru_list lru, unsigned long *nr_zone_taken, + unsigned long nr_taken) +{ +#ifdef CONFIG_HIGHMEM + int zid; + + /* + * Highmem has separate accounting for highmem pages so each zone + * is updated separately. + */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + if (!nr_zone_taken[zid]) + continue; + + __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); + } +#else + /* Zone ID does not matter on !HIGHMEM */ + __update_lru_size(lruvec, lru, 0, -nr_taken); +#endif + +#ifdef CONFIG_MEMCG + mem_cgroup_update_lru_size(lruvec, lru, -nr_taken); +#endif +} + /* * zone_lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages @@ -1436,13 +1468,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, *nr_scanned = scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan, nr_taken, mode, is_file_lru(lru)); - for (scan = 0; scan < MAX_NR_ZONES; scan++) { - nr_pages = nr_zone_taken[scan]; - if (!nr_pages) - continue; - - update_lru_size(lruvec, lru, scan, -nr_pages); - } + update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken); return nr_taken; } -- cgit v1.2.3-55-g7522 From efdc94907977d2db84b4b00cb9bd98ca011f6819 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 28 Jul 2016 15:48:17 -0700 Subject: mm: fix memcg stack accounting for sub-page stacks We should account for stacks regardless of stack size, and we need to account in sub-page units if THREAD_SIZE < PAGE_SIZE. Change the units to kilobytes and Move it into account_kernel_stack(). Fixes: 12580e4b54ba8 ("mm: memcontrol: report kernel stack usage in cgroup2 memory.stat") Link: http://lkml.kernel.org/r/9b5314e3ee5eda61b0317ec1563768602c1ef438.1468523549.git.luto@kernel.org Signed-off-by: Andy Lutomirski Cc: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Reviewed-by: Josh Poimboeuf Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- kernel/fork.c | 19 ++++++++----------- mm/memcontrol.c | 2 +- 3 files changed, 10 insertions(+), 13 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5147e650287a..5d8ca6e02e39 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,7 +52,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, + MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS, MEMCG_SLAB_RECLAIMABLE, MEMCG_SLAB_UNRECLAIMABLE, MEMCG_SOCK, diff --git a/kernel/fork.c b/kernel/fork.c index af3637e0ee52..52e725d4a866 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -165,20 +165,12 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); - if (page) - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - 1 << THREAD_SIZE_ORDER); - return page ? page_address(page) : NULL; } static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(stack); - - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - -(1 << THREAD_SIZE_ORDER)); - __free_pages(page, THREAD_SIZE_ORDER); + __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; @@ -223,10 +215,15 @@ static struct kmem_cache *mm_cachep; static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(stack)); + /* All stack pages are in the same zone and belong to the same memcg. */ + struct page *first_page = virt_to_page(stack); - mod_zone_page_state(zone, NR_KERNEL_STACK_KB, + mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, THREAD_SIZE / 1024 * account); + + memcg_kmem_update_page_stat( + first_page, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); } void free_task(struct task_struct *tsk) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 13be30c3ea78..c265212bec8c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5171,7 +5171,7 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "file %llu\n", (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE); seq_printf(m, "kernel_stack %llu\n", - (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE); + (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024); seq_printf(m, "slab %llu\n", (u64)(stat[MEMCG_SLAB_RECLAIMABLE] + stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE); -- cgit v1.2.3-55-g7522