From f7f99100d8d95dbcf09e0216a143211e79418b9f Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Wed, 15 Nov 2017 17:36:44 -0800 Subject: [PATCH] mm: stop zeroing memory during allocation in vmemmap vmemmap_alloc_block() will no longer zero the block, so zero memory at its call sites for everything except struct pages. Struct page memory is zero'd by struct page initialization. Replace allocators in sparse-vmemmap to use the non-zeroing version. So, we will get the performance improvement by zeroing the memory in parallel when struct pages are zeroed. Add struct page zeroing as a part of initialization of other fields in __init_single_page(). This single thread performance collected on: Intel(R) Xeon(R) CPU E7-8895 v3 @ 2.60GHz with 1T of memory (268400646 pages in 8 nodes): BASE FIX sparse_init 11.244671836s 0.007199623s zone_sizes_init 4.879775891s 8.355182299s -------------------------- Total 16.124447727s 8.362381922s sparse_init is where memory for struct pages is zeroed, and the zeroing part is moved later in this patch into __init_single_page(), which is called from zone_sizes_init(). [akpm@linux-foundation.org: make vmemmap_alloc_block_zero() private to sparse-vmemmap.c] Link: http://lkml.kernel.org/r/20171013173214.27300-10-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Steven Sistare Reviewed-by: Daniel Jordan Reviewed-by: Bob Picco Tested-by: Bob Picco Acked-by: Michal Hocko Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Christian Borntraeger Cc: David S. Miller Cc: Dmitry Vyukov Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Mark Rutland Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Sam Ravnborg Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 + mm/sparse-vmemmap.c | 26 ++++++++++++++++++-------- mm/sparse.c | 6 +++--- 3 files changed, 22 insertions(+), 11 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c37343ef2889..39e847cd1484 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1168,6 +1168,7 @@ static void free_one_page(struct zone *zone, static void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { + mm_zero_struct_page(page); set_page_links(page, zone, nid, pfn); init_page_count(page); page_mapcount_reset(page); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 478ce6d4a2c4..4e49762599c8 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -42,7 +42,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return memblock_virt_alloc_try_nid(size, align, goal, + return memblock_virt_alloc_try_nid_raw(size, align, goal, BOOTMEM_ALLOC_ACCESSIBLE, node); } @@ -55,9 +55,8 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) if (slab_is_available()) { struct page *page; - page = alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, - get_order(size)); + page = alloc_pages_node(node, GFP_KERNEL | __GFP_RETRY_MAYFAIL, + get_order(size)); if (page) return page_address(page); return NULL; @@ -180,11 +179,22 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node) return pte; } +static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node) +{ + void *p = vmemmap_alloc_block(size, node); + + if (!p) + return NULL; + memset(p, 0, size); + + return p; +} + pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) { pmd_t *pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, node); + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; pmd_populate_kernel(&init_mm, pmd, p); @@ -196,7 +206,7 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, node); + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; pud_populate(&init_mm, pud, p); @@ -208,7 +218,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) { p4d_t *p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, node); + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; p4d_populate(&init_mm, p4d, p); @@ -220,7 +230,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, node); + void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; pgd_populate(&init_mm, pgd, p); diff --git a/mm/sparse.c b/mm/sparse.c index 60805abf98af..7a5dacaa06e3 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -453,9 +453,9 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, } size = PAGE_ALIGN(size); - map = memblock_virt_alloc_try_nid(size * map_count, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, nodeid); + map = memblock_virt_alloc_try_nid_raw(size * map_count, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nodeid); if (map) { for (pnum = pnum_begin; pnum < pnum_end; pnum++) { if (!present_section_nr(pnum))