Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753091AbcDPA2m (ORCPT ); Fri, 15 Apr 2016 20:28:42 -0400 Received: from mga01.intel.com ([192.55.52.88]:42401 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752914AbcDPAYk (ORCPT ); Fri, 15 Apr 2016 20:24:40 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.24,489,1455004800"; d="scan'208";a="86104397" From: "Kirill A. Shutemov" To: Hugh Dickins , Andrea Arcangeli , Andrew Morton Cc: Dave Hansen , Vlastimil Babka , Christoph Lameter , Naoya Horiguchi , Jerome Marchand , Yang Shi , Sasha Levin , Andres Lagar-Cavilla , Ning Qu , linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, "Kirill A. Shutemov" Subject: [PATCHv7 11/29] thp: skip file huge pmd on copy_huge_pmd() Date: Sat, 16 Apr 2016 03:23:42 +0300 Message-Id: <1460766240-84565-12-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.8.0.rc3 In-Reply-To: <1460766240-84565-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1460766240-84565-1-git-send-email-kirill.shutemov@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2453 Lines: 76 copy_page_range() has a check for "Don't copy ptes where a page fault will fill them correctly." It works on VMA level. We still copy all page table entries from private mappings, even if they map page cache. We can simplify copy_huge_pmd() a bit by skipping file PMDs. We don't map file private pages with PMDs, so they only can map page cache. It's safe to skip them as they can be re-faulted later. Signed-off-by: Kirill A. Shutemov --- mm/huge_memory.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 67830a6ed8b0..3a3f9ff45e3f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1094,14 +1094,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct page *src_page; pmd_t pmd; pgtable_t pgtable = NULL; - int ret; + int ret = -ENOMEM; - if (!vma_is_dax(vma)) { - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; - } + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1109,7 +1110,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { + if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -1132,16 +1133,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (!vma_is_dax(vma)) { - /* thp accounting separate from pmd_devmap accounting */ - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page, true); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&dst_mm->nr_ptes); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - } + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); -- 2.8.0.rc3