From: Fengguang Wu Subject: [RFC][PATCH v2 13/21] x86/pgtable: dont check PMD accessed bit Date: Wed, 26 Dec 2018 21:14:59 +0800 Message-ID: <20181226133351.828074959@intel.com> References: <20181226131446.330864849@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Cc: Linux Memory Management List , Jingqi Liu , Fengguang Wu To: Andrew Morton Return-path: cc: kvm@vger.kernel.org Cc: LKML cc: Fan Du cc: Yao Yuan cc: Peng Dong cc: Huang Ying cc: Dong Eddie cc: Dave Hansen cc: Zhang Yi cc: Dan Williams Content-Disposition: inline; filename=0006-pgtable-don-t-check-the-page-accessed-bit.patch Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org From: Jingqi Liu ept-idle will clear PMD accessed bit to speedup PTE scan -- if the bit remains unset in the next scan, all the 512 PTEs can be skipped. So don't complain on !_PAGE_ACCESSED in pmd_bad(). Note that clearing PMD accessed bit has its own cost, the optimization may only be worthwhile for - large idle area - sparsely populated area Signed-off-by: Jingqi Liu Signed-off-by: Fengguang Wu --- arch/x86/include/asm/pgtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- linux.orig/arch/x86/include/asm/pgtable.h 2018-12-23 19:50:50.917902600 +0800 +++ linux/arch/x86/include/asm/pgtable.h 2018-12-23 19:50:50.913902605 +0800 @@ -821,7 +821,8 @@ static inline pte_t *pte_offset_kernel(p static inline int pmd_bad(pmd_t pmd) { - return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE; + return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != + (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg)