From a9b0f8618d46ba027243b8ecb5c2468a7112d235 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 4 Jun 2014 16:10:54 -0700 Subject: [PATCH] mm: nominate faultaround area in bytes rather than page order There is evidencs that the faultaround feature is less relevant on architectures with page size bigger then 4k. Which makes sense since page fault overhead per byte of mapped area should be less there. Let's rework the feature to specify faultaround area in bytes instead of page order. It's 64 kilobytes for now. The patch effectively disables faultaround on architectures with page size >= 64k (like ppc64). It's possible that some other size of faultaround area is relevant for a platform. We can expose `fault_around_bytes' variable to arch-specific code once such platforms will be found. Signed-off-by: Kirill A. Shutemov Cc: Rusty Russell Cc: Hugh Dickins Cc: Madhavan Srinivasan Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Rik van Riel Cc: Mel Gorman Cc: Andi Kleen Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 62 ++++++++++++++++++++--------------------------------- 1 file changed, 23 insertions(+), 39 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index e7ccbac25b72..62a08a7badc4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2758,63 +2758,47 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, update_mmu_cache(vma, address, pte); } -#define FAULT_AROUND_ORDER 4 +static unsigned long fault_around_bytes = 65536; + +static inline unsigned long fault_around_pages(void) +{ + return rounddown_pow_of_two(fault_around_bytes) / PAGE_SIZE; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~(rounddown_pow_of_two(fault_around_bytes) - 1) & PAGE_MASK; +} -#ifdef CONFIG_DEBUG_FS -static unsigned int fault_around_order = FAULT_AROUND_ORDER; -static int fault_around_order_get(void *data, u64 *val) +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) { - *val = fault_around_order; + *val = fault_around_bytes; return 0; } -static int fault_around_order_set(void *data, u64 val) +static int fault_around_bytes_set(void *data, u64 val) { - BUILD_BUG_ON((1UL << FAULT_AROUND_ORDER) > PTRS_PER_PTE); - if (1UL << val > PTRS_PER_PTE) + if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; - fault_around_order = val; + fault_around_bytes = val; return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fault_around_order_fops, - fault_around_order_get, fault_around_order_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { void *ret; - ret = debugfs_create_file("fault_around_order", 0644, NULL, NULL, - &fault_around_order_fops); + ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); if (!ret) - pr_warn("Failed to create fault_around_order in debugfs"); + pr_warn("Failed to create fault_around_bytes in debugfs"); return 0; } late_initcall(fault_around_debugfs); - -static inline unsigned long fault_around_pages(void) -{ - return 1UL << fault_around_order; -} - -static inline unsigned long fault_around_mask(void) -{ - return ~((1UL << (PAGE_SHIFT + fault_around_order)) - 1); -} -#else -static inline unsigned long fault_around_pages(void) -{ - unsigned long nr_pages; - - nr_pages = 1UL << FAULT_AROUND_ORDER; - BUILD_BUG_ON(nr_pages > PTRS_PER_PTE); - return nr_pages; -} - -static inline unsigned long fault_around_mask(void) -{ - return ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1); -} #endif static void do_fault_around(struct vm_area_struct *vma, unsigned long address, @@ -2871,7 +2855,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages) { + if (vma->vm_ops->map_pages && fault_around_pages() > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) -- 2.34.1