From: Yang Shi yang.shi@linux.alibaba.com
mainline inclusion from mainline-v5.4-rc1 commit 364c1eebe453f06f0c1e837eb155a5725c9cd272 category: bugfix bugzilla: 47240 CVE: NA
-------------------------------------------------
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.al... Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Suggested-by: "Kirill A . Shutemov" kirill.shutemov@linux.intel.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Kirill Tkhai ktkhai@virtuozzo.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@suse.com Cc: Hugh Dickins hughd@google.com Cc: Shakeel Butt shakeelb@google.com Cc: David Rientjes rientjes@google.com Cc: Qian Cai cai@lca.pw Cc: Vladimir Davydov vdavydov.dev@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Liu Shixin liushixin2@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/linux/mmzone.h | 12 ++++++++--- mm/huge_memory.c | 45 +++++++++++++++++++++++------------------- mm/page_alloc.c | 8 +++++--- 3 files changed, 39 insertions(+), 26 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1d7c5dd03ed89..3bd2f5e2a344f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -612,6 +612,14 @@ 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 @@ -698,9 +706,7 @@ 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 c2013b3e92e74..936092f8d4b16 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2697,6 +2697,7 @@ 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; @@ -2786,17 +2787,17 @@ 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); ret = 0; } else { @@ -2808,7 +2809,7 @@ 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(zone_lru_lock(page_zone(head)), flags); @@ -2831,52 +2832,56 @@ fail: if (mapping) 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)) { @@ -2884,12 +2889,12 @@ 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); @@ -2903,15 +2908,15 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, 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 67768c56d412c..91d820248690c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6371,9 +6371,11 @@ 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) {}