From b8f593cd0896b8b14c2b494a9776531b5cd54d98 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 6 Jul 2017 15:37:28 -0700 Subject: [PATCH] mm, THP, swap: check whether THP can be split firstly To swap out THP (Transparent Huage Page), before splitting the THP, the swap cluster will be allocated and the THP will be added into the swap cache. But it is possible that the THP cannot be split, so that we must delete the THP from the swap cache and free the swap cluster. To avoid that, in this patch, whether the THP can be split is checked firstly. The check can only be done racy, but it is good enough for most cases. With the patch, the swap out throughput improves 3.6% (from about 4.16GB/s to about 4.31GB/s) in the vm-scalability swap-w-seq test case with 8 processes. The test is done on a Xeon E5 v3 system. The swap device used is a RAM simulated PMEM (persistent memory) device. To test the sequential swapping out, the test case creates 8 processes, which sequentially allocate and write to the anonymous pages until the RAM and part of the swap device is used up. Link: http://lkml.kernel.org/r/20170515112522.32457-5-ying.huang@intel.com Signed-off-by: "Huang, Ying" Acked-by: Kirill A. Shutemov [for can_split_huge_page()] Cc: Johannes Weiner Cc: Andrea Arcangeli Cc: Ebru Akagunduz Cc: Hugh Dickins Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 7 +++++++ mm/huge_memory.c | 20 ++++++++++++++++---- mm/vmscan.c | 4 ++++ 3 files changed, 27 insertions(+), 4 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a3762d49ba39..d3b3e8fcc717 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -113,6 +113,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp, extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); +bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -231,6 +232,12 @@ static inline void prep_transhuge_page(struct page *page) {} #define thp_get_unmapped_area NULL +static inline bool +can_split_huge_page(struct page *page, int *pextra_pins) +{ + BUILD_BUG(); + return false; +} static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1a168e4bac4b..86975dec0ba1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2390,6 +2390,21 @@ int page_trans_huge_mapcount(struct page *page, int *total_mapcount) return ret; } +/* Racy check whether the huge page can be split */ +bool can_split_huge_page(struct page *page, int *pextra_pins) +{ + int extra_pins; + + /* Additional pins from radix tree */ + if (PageAnon(page)) + extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0; + else + extra_pins = HPAGE_PMD_NR; + if (pextra_pins) + *pextra_pins = extra_pins; + return total_mapcount(page) == page_count(page) - extra_pins - 1; +} + /* * This function splits huge page into normal pages. @page can point to any * subpage of huge page to split. Split doesn't change the position of @page. @@ -2437,7 +2452,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ret = -EBUSY; goto out; } - extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0; mapping = NULL; anon_vma_lock_write(anon_vma); } else { @@ -2449,8 +2463,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) goto out; } - /* Addidional pins from radix tree */ - extra_pins = HPAGE_PMD_NR; anon_vma = NULL; i_mmap_lock_read(mapping); } @@ -2459,7 +2471,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) * Racy check if we can split the page, before freeze_page() will * split PMDs */ - if (total_mapcount(head) != page_count(head) - extra_pins - 1) { + if (!can_split_huge_page(head, &extra_pins)) { ret = -EBUSY; goto out_unlock; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 729e37f02de6..abaf0215a352 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1125,6 +1125,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; + /* cannot split THP, skip it */ + if (PageTransHuge(page) && + !can_split_huge_page(page, NULL)) + goto activate_locked; if (!add_to_swap(page)) { if (!PageTransHuge(page)) goto activate_locked;