From 78c943662f4b1d53ddbfc515e427827915781377 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Wed, 15 Nov 2017 17:36:48 -0800 Subject: sparc64: optimize struct page zeroing Add an optimized mm_zero_struct_page(), so struct page's are zeroed without calling memset(). We do eight to ten regular stores based on the size of struct page. Compiler optimizes out the conditions of switch() statement. SPARC-M6 with 15T of memory, single thread performance: BASE FIX OPTIMIZED_FIX bootmem_init 28.440467985s 2.305674818s 2.305161615s free_area_init_nodes 202.845901673s 225.343084508s 172.556506560s -------------------------------------------- Total 231.286369658s 227.648759326s 174.861668175s BASE: current linux FIX: This patch series without "optimized struct page zeroing" OPTIMIZED_FIX: This patch series including the current patch. bootmem_init() is where memory for struct pages is zeroed during allocation. Note, about two seconds in this function is a fixed time: it does not increase as memory is increased. Link: http://lkml.kernel.org/r/20171013173214.27300-11-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Steven Sistare Reviewed-by: Daniel Jordan Reviewed-by: Bob Picco Acked-by: David S. Miller Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Christian Borntraeger 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: Michal Hocko Cc: Sam Ravnborg Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/include/asm/pgtable_64.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'arch/sparc') diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index fd9d9bac7cfa..5a9e96be1665 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -231,6 +231,36 @@ extern unsigned long _PAGE_ALL_SZ_BITS; extern struct page *mem_map_zero; #define ZERO_PAGE(vaddr) (mem_map_zero) +/* This macro must be updated when the size of struct page grows above 80 + * or reduces below 64. + * The idea that compiler optimizes out switch() statement, and only + * leaves clrx instructions + */ +#define mm_zero_struct_page(pp) do { \ + unsigned long *_pp = (void *)(pp); \ + \ + /* Check that struct page is either 64, 72, or 80 bytes */ \ + BUILD_BUG_ON(sizeof(struct page) & 7); \ + BUILD_BUG_ON(sizeof(struct page) < 64); \ + BUILD_BUG_ON(sizeof(struct page) > 80); \ + \ + switch (sizeof(struct page)) { \ + case 80: \ + _pp[9] = 0; /* fallthrough */ \ + case 72: \ + _pp[8] = 0; /* fallthrough */ \ + default: \ + _pp[7] = 0; \ + _pp[6] = 0; \ + _pp[5] = 0; \ + _pp[4] = 0; \ + _pp[3] = 0; \ + _pp[2] = 0; \ + _pp[1] = 0; \ + _pp[0] = 0; \ + } \ +} while (0) + /* PFNs are real physical page numbers. However, mem_map only begins to record * per-page information starting at pfn_base. This is to handle systems where * the first physical page in the machine is at some huge physical address, -- cgit