From d8c6546b1aea843fbeb4d54a1202f1adda6504be Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 23 Sep 2019 15:34:30 -0700 Subject: mm: introduce compound_nr() Replace 1 << compound_order(page) with compound_nr(page). Minor improvements in readability. Link: http://lkml.kernel.org/r/20190721104612.19120-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Andrew Morton Reviewed-by: Ira Weiny Acked-by: Kirill A. Shutemov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ff5484fdbdf9..df566c0f6729 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8196,7 +8196,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, if (!hugepage_migration_supported(page_hstate(head))) goto unmovable; - skip_pages = (1 << compound_order(head)) - (page - head); + skip_pages = compound_nr(head) - (page - head); iter += skip_pages - 1; continue; } -- cgit v1.2.3-70-g09d2 From 494330855641269c8a49f1580f0d4e2ead693245 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 23 Sep 2019 15:37:32 -0700 Subject: mm, compaction: raise compaction priority after it withdrawns Mike Kravetz reports that "hugetlb allocations could stall for minutes or hours when should_compact_retry() would return true more often then it should. Specifically, this was in the case where compact_result was COMPACT_DEFERRED and COMPACT_PARTIAL_SKIPPED and no progress was being made." The problem is that the compaction_withdrawn() test in should_compact_retry() includes compaction outcomes that are only possible on low compaction priority, and results in a retry without increasing the priority. This may result in furter reclaim, and more incomplete compaction attempts. With this patch, compaction priority is raised when possible, or should_compact_retry() returns false. The COMPACT_SKIPPED result doesn't really fit together with the other outcomes in compaction_withdrawn(), as that's a result caused by insufficient order-0 pages, not due to low compaction priority. With this patch, it is moved to a new compaction_needs_reclaim() function, and for that outcome we keep the current logic of retrying if it looks like reclaim will be able to help. Link: http://lkml.kernel.org/r/20190806014744.15446-4-mike.kravetz@oracle.com Reported-by: Mike Kravetz Signed-off-by: Vlastimil Babka Signed-off-by: Mike Kravetz Tested-by: Mike Kravetz Cc: Hillf Danton Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 22 +++++++++++++++++----- mm/page_alloc.c | 16 ++++++++++++---- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 9569e7c786d3..4b898cdbdf05 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -129,11 +129,8 @@ static inline bool compaction_failed(enum compact_result result) return false; } -/* - * Compaction has backed off for some reason. It might be throttling or - * lock contention. Retrying is still worthwhile. - */ -static inline bool compaction_withdrawn(enum compact_result result) +/* Compaction needs reclaim to be performed first, so it can continue. */ +static inline bool compaction_needs_reclaim(enum compact_result result) { /* * Compaction backed off due to watermark checks for order-0 @@ -142,6 +139,16 @@ static inline bool compaction_withdrawn(enum compact_result result) if (result == COMPACT_SKIPPED) return true; + return false; +} + +/* + * Compaction has backed off for some reason after doing some work or none + * at all. It might be throttling or lock contention. Retrying might be still + * worthwhile, but with a higher priority if allowed. + */ +static inline bool compaction_withdrawn(enum compact_result result) +{ /* * If compaction is deferred for high-order allocations, it is * because sync compaction recently failed. If this is the case @@ -207,6 +214,11 @@ static inline bool compaction_failed(enum compact_result result) return false; } +static inline bool compaction_needs_reclaim(enum compact_result result) +{ + return false; +} + static inline bool compaction_withdrawn(enum compact_result result) { return true; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df566c0f6729..591e026534c2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3954,15 +3954,23 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, if (compaction_failed(compact_result)) goto check_priority; + /* + * compaction was skipped because there are not enough order-0 pages + * to work with, so we retry only if it looks like reclaim can help. + */ + if (compaction_needs_reclaim(compact_result)) { + ret = compaction_zonelist_suitable(ac, order, alloc_flags); + goto out; + } + /* * make sure the compaction wasn't deferred or didn't bail out early * due to locks contention before we declare that we should give up. - * But do not retry if the given zonelist is not suitable for - * compaction. + * But the next retry should use a higher priority if allowed, so + * we don't just keep bailing out endlessly. */ if (compaction_withdrawn(compact_result)) { - ret = compaction_zonelist_suitable(ac, order, alloc_flags); - goto out; + goto check_priority; } /* -- cgit v1.2.3-70-g09d2 From 364c1eebe453f06f0c1e837eb155a5725c9cd272 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Mon, 23 Sep 2019 15:38:06 -0700 Subject: mm: thp: extract split_queue_* into a struct Patch series "Make deferred split shrinker memcg aware", v6. Currently THP deferred split shrinker is not memcg aware, this may cause premature OOM with some configuration. For example the below test would run into premature OOM easily: $ cgcreate -g memory:thp $ echo 4G > /sys/fs/cgroup/memory/thp/memory/limit_in_bytes $ cgexec -g memory:thp transhuge-stress 4000 transhuge-stress comes from kernel selftest. It is easy to hit OOM, but there are still a lot THP on the deferred split queue, memcg direct reclaim can't touch them since the deferred split shrinker is not memcg aware. Convert deferred split shrinker memcg aware by introducing per memcg deferred split queue. The THP should be on either per node or per memcg deferred split queue if it belongs to a memcg. When the page is immigrated to the other memcg, it will be immigrated to the target memcg's deferred split queue too. Reuse the second tail page's deferred_list for per memcg list since the same THP can't be on multiple deferred split queues. Make deferred split shrinker not depend on memcg kmem since it is not slab. It doesn't make sense to not shrink THP even though memcg kmem is disabled. With the above change the test demonstrated above doesn't trigger OOM even though with cgroup.memory=nokmem. This patch (of 4): Put split_queue, split_queue_lock and split_queue_len into a struct in order to reduce code duplication when we convert deferred_split to memcg aware in the later patches. Link: http://lkml.kernel.org/r/1565144277-36240-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: "Kirill A . Shutemov" Acked-by: Kirill A. Shutemov Reviewed-by: Kirill Tkhai Cc: Johannes Weiner Cc: Michal Hocko Cc: Hugh Dickins Cc: Shakeel Butt Cc: David Rientjes Cc: Qian Cai Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 12 +++++++++--- mm/huge_memory.c | 45 +++++++++++++++++++++++++-------------------- mm/page_alloc.c | 8 +++++--- 3 files changed, 39 insertions(+), 26 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index aafb7c38c627..bda20282746b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -679,6 +679,14 @@ struct zonelist { extern struct page *mem_map; #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct deferred_split { + spinlock_t split_queue_lock; + struct list_head split_queue; + unsigned long split_queue_len; +}; +#endif + /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which @@ -758,9 +766,7 @@ typedef struct pglist_data { #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE - spinlock_t split_queue_lock; - struct list_head split_queue; - unsigned long split_queue_len; + struct deferred_split deferred_split_queue; #endif /* Fields commonly accessed by the page reclaim scanner */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 483b07b2d6ae..c642c0394690 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2691,6 +2691,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int count, mapcount, extra_pins, ret; @@ -2777,17 +2778,17 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } /* Prevent deferred_split_scan() touching ->_refcount */ - spin_lock(&pgdata->split_queue_lock); + spin_lock(&ds_queue->split_queue_lock); count = page_count(head); mapcount = total_mapcount(head); if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { - pgdata->split_queue_len--; + ds_queue->split_queue_len--; list_del(page_deferred_list(head)); } if (mapping) __dec_node_page_state(page, NR_SHMEM_THPS); - spin_unlock(&pgdata->split_queue_lock); + spin_unlock(&ds_queue->split_queue_lock); __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; @@ -2804,7 +2805,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) dump_page(page, "total_mapcount(head) > 0"); BUG(); } - spin_unlock(&pgdata->split_queue_lock); + spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(&pgdata->lru_lock, flags); @@ -2827,52 +2828,56 @@ out: void free_transhuge_page(struct page *page) { struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; - spin_lock_irqsave(&pgdata->split_queue_lock, flags); + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { - pgdata->split_queue_len--; + ds_queue->split_queue_len--; list_del(page_deferred_list(page)); } - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); - spin_lock_irqsave(&pgdata->split_queue_lock, flags); + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { count_vm_event(THP_DEFERRED_SPLIT_PAGE); - list_add_tail(page_deferred_list(page), &pgdata->split_queue); - pgdata->split_queue_len++; + list_add_tail(page_deferred_list(page), &ds_queue->split_queue); + ds_queue->split_queue_len++; } - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); - return READ_ONCE(pgdata->split_queue_len); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; + return READ_ONCE(ds_queue->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; - spin_lock_irqsave(&pgdata->split_queue_lock, flags); + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ - list_for_each_safe(pos, next, &pgdata->split_queue) { + list_for_each_safe(pos, next, &ds_queue->split_queue) { page = list_entry((void *)pos, struct page, mapping); page = compound_head(page); if (get_page_unless_zero(page)) { @@ -2880,12 +2885,12 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } else { /* We lost race with put_compound_page() */ list_del_init(page_deferred_list(page)); - pgdata->split_queue_len--; + ds_queue->split_queue_len--; } if (!--sc->nr_to_scan) break; } - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); @@ -2899,15 +2904,15 @@ next: put_page(page); } - spin_lock_irqsave(&pgdata->split_queue_lock, flags); - list_splice_tail(&list, &pgdata->split_queue); - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); + list_splice_tail(&list, &ds_queue->split_queue); + spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. */ - if (!split && list_empty(&pgdata->split_queue)) + if (!split && list_empty(&ds_queue->split_queue)) return SHRINK_STOP; return split; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 591e026534c2..a41436cca563 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6646,9 +6646,11 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void pgdat_init_split_queue(struct pglist_data *pgdat) { - spin_lock_init(&pgdat->split_queue_lock); - INIT_LIST_HEAD(&pgdat->split_queue); - pgdat->split_queue_len = 0; + struct deferred_split *ds_queue = &pgdat->deferred_split_queue; + + spin_lock_init(&ds_queue->split_queue_lock); + INIT_LIST_HEAD(&ds_queue->split_queue); + ds_queue->split_queue_len = 0; } #else static void pgdat_init_split_queue(struct pglist_data *pgdat) {} -- cgit v1.2.3-70-g09d2 From 7ae88534cdd96235cd775c03b32a75009355740b Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Mon, 23 Sep 2019 15:38:09 -0700 Subject: mm: move mem_cgroup_uncharge out of __page_cache_release() A later patch makes THP deferred split shrinker memcg aware, but it needs page->mem_cgroup information in THP destructor, which is called after mem_cgroup_uncharge() now. So move mem_cgroup_uncharge() from __page_cache_release() to compound page destructor, which is called by both THP and other compound pages except HugeTLB. And call it in __put_single_page() for single order page. Link: http://lkml.kernel.org/r/1565144277-36240-3-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: "Kirill A . Shutemov" Acked-by: Kirill A. Shutemov Reviewed-by: Kirill Tkhai Cc: Johannes Weiner Cc: Michal Hocko Cc: Hugh Dickins Cc: Shakeel Butt Cc: David Rientjes Cc: Qian Cai Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 + mm/swap.c | 2 +- mm/vmscan.c | 6 ++---- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a41436cca563..3334a769eb91 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -670,6 +670,7 @@ out: void free_compound_page(struct page *page) { + mem_cgroup_uncharge(page); __free_pages_ok(page, compound_order(page)); } diff --git a/mm/swap.c b/mm/swap.c index 0226c5346560..784dc1620620 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -71,12 +71,12 @@ static void __page_cache_release(struct page *page) spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); - mem_cgroup_uncharge(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); + mem_cgroup_uncharge(page); free_unref_page(page); } diff --git a/mm/vmscan.c b/mm/vmscan.c index c27dd62ed594..c4ef8681637b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1487,10 +1487,9 @@ free_it: * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ - if (unlikely(PageTransHuge(page))) { - mem_cgroup_uncharge(page); + if (unlikely(PageTransHuge(page))) (*get_compound_page_dtor(page))(page); - } else + else list_add(&page->lru, &free_pages); continue; @@ -1911,7 +1910,6 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, if (unlikely(PageCompound(page))) { spin_unlock_irq(&pgdat->lru_lock); - mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); spin_lock_irq(&pgdat->lru_lock); } else -- cgit v1.2.3-70-g09d2