From 53f9263baba69fc1630e3c780c4d11b72643f962 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:53:42 -0800 Subject: mm: rework mapcount accounting to enable 4k mapping of THPs We're going to allow mapping of individual 4k pages of THP compound. It means we need to track mapcount on per small page basis. Straight-forward approach is to use ->_mapcount in all subpages to track how many time this subpage is mapped with PMDs or PTEs combined. But this is rather expensive: mapping or unmapping of a THP page with PMD would require HPAGE_PMD_NR atomic operations instead of single we have now. The idea is to store separately how many times the page was mapped as whole -- compound_mapcount. This frees up ->_mapcount in subpages to track PTE mapcount. We use the same approach as with compound page destructor and compound order to store compound_mapcount: use space in first tail page, ->mapping this time. Any time we map/unmap whole compound page (THP or hugetlb) -- we increment/decrement compound_mapcount. When we map part of compound page with PTE we operate on ->_mapcount of the subpage. page_mapcount() counts both: PTE and PMD mappings of the page. Basically, we have mapcount for a subpage spread over two counters. It makes tricky to detect when last mapcount for a page goes away. We introduced PageDoubleMap() for this. When we split THP PMD for the first time and there's other PMD mapping left we offset up ->_mapcount in all subpages by one and set PG_double_map on the compound page. These additional references go away with last compound_mapcount. This approach provides a way to detect when last mapcount goes away on per small page basis without introducing new overhead for most common cases. [akpm@linux-foundation.org: fix typo in comment] [mhocko@suse.com: ignore partial THP when moving task] Signed-off-by: Kirill A. Shutemov Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand Cc: Sasha Levin Cc: Aneesh Kumar K.V Cc: Jerome Marchand Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Steve Capper Cc: Johannes Weiner Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d02d6436add0..3221091da513 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -469,6 +469,7 @@ void prep_compound_page(struct page *page, unsigned int order) p->mapping = TAIL_MAPPING; set_compound_head(p, page); } + atomic_set(compound_mapcount_ptr(page), -1); } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -733,7 +734,7 @@ static inline int free_pages_check(struct page *page) const char *bad_reason = NULL; unsigned long bad_flags = 0; - if (unlikely(page_mapcount(page))) + if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; @@ -857,7 +858,13 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) ret = 0; goto out; } - if (page->mapping != TAIL_MAPPING) { + /* mapping in first tail page is used for compound_mapcount() */ + if (page - head_page == 1) { + if (unlikely(compound_mapcount(page))) { + bad_page(page, "nonzero compound_mapcount", 0); + goto out; + } + } else if (page->mapping != TAIL_MAPPING) { bad_page(page, "corrupted mapping in tail page", 0); goto out; } @@ -1335,7 +1342,7 @@ static inline int check_new_page(struct page *page) const char *bad_reason = NULL; unsigned long bad_flags = 0; - if (unlikely(page_mapcount(page))) + if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; -- cgit v1.2.3