From: Andi Kleen <ak@xxxxxxxxxxxxxxx> Clearing a 2MB huge page will typically blow away several levels of CPU caches. To avoid this only cache clear the 4K area around the fault address and use a cache avoiding clears for the rest of the 2MB area. Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> --- mm/memory.c | 37 +++++++++++++++++++++++++++++-------- 1 files changed, 29 insertions(+), 8 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index dfc179b..625ca33 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3969,18 +3969,32 @@ EXPORT_SYMBOL(might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) + +#ifndef ARCH_HAS_USER_NOCACHE +#define ARCH_HAS_USER_NOCACHE 0 +#endif + +#if ARCH_HAS_USER_NOCACHE == 0 +#define clear_user_highpage_nocache clear_user_highpage +#endif + static void clear_gigantic_page(struct page *page, - unsigned long addr, - unsigned int pages_per_huge_page) + unsigned long haddr, unsigned long fault_address, + unsigned int pages_per_huge_page) { int i; struct page *p = page; + unsigned long vaddr; + int target = (fault_address - haddr) >> PAGE_SHIFT; might_sleep(); - for (i = 0; i < pages_per_huge_page; - i++, p = mem_map_next(p, page, i)) { + for (i = 0, vaddr = haddr; i < pages_per_huge_page; + i++, p = mem_map_next(p, page, i), vaddr += PAGE_SIZE) { cond_resched(); - clear_user_highpage(p, addr + i * PAGE_SIZE); + if (!ARCH_HAS_USER_NOCACHE || i == target) + clear_user_highpage(p, vaddr); + else + clear_user_highpage_nocache(p, vaddr); } } void clear_huge_page(struct page *page, @@ -3988,16 +4002,23 @@ void clear_huge_page(struct page *page, unsigned int pages_per_huge_page) { int i; + unsigned long vaddr; + int target = (fault_address - haddr) >> PAGE_SHIFT; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { - clear_gigantic_page(page, haddr, pages_per_huge_page); + clear_gigantic_page(page, haddr, fault_address, + pages_per_huge_page); return; } might_sleep(); - for (i = 0; i < pages_per_huge_page; i++) { + for (i = 0, vaddr = haddr; i < pages_per_huge_page; + i++, page++, vaddr += PAGE_SIZE) { cond_resched(); - clear_user_highpage(page + i, haddr + i * PAGE_SIZE); + if (!ARCH_HAS_USER_NOCACHE || i == target) + clear_user_highpage(page, vaddr); + else + clear_user_highpage_nocache(page, vaddr); } } -- 1.7.7.6