From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757173AbbICPTr (ORCPT ); Thu, 3 Sep 2015 11:19:47 -0400 Received: from mga14.intel.com ([192.55.52.115]:1033 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932418AbbICPNr (ORCPT ); Thu, 3 Sep 2015 11:13:47 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.17,462,1437462000"; d="scan'208";a="797524992" From: "Kirill A. Shutemov" To: Andrew Morton , Andrea Arcangeli , Hugh Dickins Cc: Dave Hansen , Mel Gorman , Rik van Riel , Vlastimil Babka , Christoph Lameter , Naoya Horiguchi , Steve Capper , "Aneesh Kumar K.V" , Johannes Weiner , Michal Hocko , Jerome Marchand , Sasha Levin , linux-kernel@vger.kernel.org, linux-mm@kvack.org, "Kirill A. Shutemov" Subject: [PATCHv10 29/36] thp: implement split_huge_pmd() Date: Thu, 3 Sep 2015 18:13:15 +0300 Message-Id: <1441293202-137314-30-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.5.0 In-Reply-To: <1441293202-137314-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1441293202-137314-1-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 Original split_huge_page() combined two operations: splitting PMDs into tables of PTEs and splitting underlying compound page. This patch implements split_huge_pmd() which split given PMD without splitting other PMDs this page mapped with or underlying compound page. Without tail page refcounting, implementation of split_huge_pmd() is pretty straight-forward. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand --- include/linux/huge_mm.h | 11 ++++- mm/huge_memory.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 134 insertions(+), 1 deletion(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b82c0c2a96f6..60b5448bf37d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,7 +96,16 @@ extern unsigned long transparent_hugepage_flags; #define split_huge_page_to_list(page, list) BUILD_BUG() #define split_huge_page(page) BUILD_BUG() -#define split_huge_pmd(__vma, __pmd, __address) BUILD_BUG() + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address); + +#define split_huge_pmd(__vma, __pmd, __address) \ + do { \ + pmd_t *____pmd = (__pmd); \ + if (pmd_trans_huge(*____pmd)) \ + __split_huge_pmd(__vma, __pmd, __address); \ + } while (0) #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 55b337f5a4a0..f30af16c2b16 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2596,6 +2596,130 @@ static int khugepaged(void *none) return 0; } +static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, + unsigned long haddr, pmd_t *pmd) +{ + struct mm_struct *mm = vma->vm_mm; + pgtable_t pgtable; + pmd_t _pmd; + int i; + + /* leave pmd empty until pte is filled */ + pmdp_huge_clear_flush_notify(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t *pte, entry; + entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); + entry = pte_mkspecial(entry); + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + pte_unmap(pte); + } + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); + put_huge_zero_page(); +} + +static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long haddr) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + pgtable_t pgtable; + pmd_t _pmd; + bool young, write; + int i; + + VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); + VM_BUG_ON(!pmd_trans_huge(*pmd)); + + count_vm_event(THP_SPLIT_PMD); + + if (vma_is_dax(vma)) { + pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + if (is_huge_zero_pmd(_pmd)) + put_huge_zero_page(); + return; + } else if (is_huge_zero_pmd(*pmd)) { + return __split_huge_zero_page_pmd(vma, haddr, pmd); + } + + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!page_count(page), page); + atomic_add(HPAGE_PMD_NR - 1, &page->_count); + write = pmd_write(*pmd); + young = pmd_young(*pmd); + + /* leave pmd empty until pte is filled */ + pmdp_huge_clear_flush_notify(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t entry, *pte; + /* + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. + */ + entry = mk_pte(page + i, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (!write) + entry = pte_wrprotect(entry); + if (!young) + entry = pte_mkold(entry); + pte = pte_offset_map(&_pmd, haddr); + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + atomic_inc(&page[i]._mapcount); + pte_unmap(pte); + } + + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_inc(&page[i]._mapcount); + } + + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } + } + + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); +} + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl; + struct mm_struct *mm = vma->vm_mm; + unsigned long haddr = address & HPAGE_PMD_MASK; + + mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); + ptl = pmd_lock(mm, pmd); + if (likely(pmd_trans_huge(*pmd))) + __split_huge_pmd_locked(vma, pmd, haddr); + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE); +} + static void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address) { -- 2.5.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oi0-f48.google.com (mail-oi0-f48.google.com [209.85.218.48]) by kanga.kvack.org (Postfix) with ESMTP id BA7CA9003CD for ; Thu, 3 Sep 2015 11:20:33 -0400 (EDT) Received: by oixx17 with SMTP id x17so29576956oix.0 for ; Thu, 03 Sep 2015 08:20:33 -0700 (PDT) Received: from mga09.intel.com (mga09.intel.com. [134.134.136.24]) by mx.google.com with ESMTP id nj6si8193469pdb.45.2015.09.03.08.14.05 for ; Thu, 03 Sep 2015 08:14:06 -0700 (PDT) From: "Kirill A. Shutemov" Subject: [PATCHv10 29/36] thp: implement split_huge_pmd() Date: Thu, 3 Sep 2015 18:13:15 +0300 Message-Id: <1441293202-137314-30-git-send-email-kirill.shutemov@linux.intel.com> In-Reply-To: <1441293202-137314-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1441293202-137314-1-git-send-email-kirill.shutemov@linux.intel.com> Sender: owner-linux-mm@kvack.org List-ID: To: Andrew Morton , Andrea Arcangeli , Hugh Dickins Cc: Dave Hansen , Mel Gorman , Rik van Riel , Vlastimil Babka , Christoph Lameter , Naoya Horiguchi , Steve Capper , "Aneesh Kumar K.V" , Johannes Weiner , Michal Hocko , Jerome Marchand , Sasha Levin , linux-kernel@vger.kernel.org, linux-mm@kvack.org, "Kirill A. Shutemov" Original split_huge_page() combined two operations: splitting PMDs into tables of PTEs and splitting underlying compound page. This patch implements split_huge_pmd() which split given PMD without splitting other PMDs this page mapped with or underlying compound page. Without tail page refcounting, implementation of split_huge_pmd() is pretty straight-forward. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand --- include/linux/huge_mm.h | 11 ++++- mm/huge_memory.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 134 insertions(+), 1 deletion(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b82c0c2a96f6..60b5448bf37d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,7 +96,16 @@ extern unsigned long transparent_hugepage_flags; #define split_huge_page_to_list(page, list) BUILD_BUG() #define split_huge_page(page) BUILD_BUG() -#define split_huge_pmd(__vma, __pmd, __address) BUILD_BUG() + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address); + +#define split_huge_pmd(__vma, __pmd, __address) \ + do { \ + pmd_t *____pmd = (__pmd); \ + if (pmd_trans_huge(*____pmd)) \ + __split_huge_pmd(__vma, __pmd, __address); \ + } while (0) #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 55b337f5a4a0..f30af16c2b16 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2596,6 +2596,130 @@ static int khugepaged(void *none) return 0; } +static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, + unsigned long haddr, pmd_t *pmd) +{ + struct mm_struct *mm = vma->vm_mm; + pgtable_t pgtable; + pmd_t _pmd; + int i; + + /* leave pmd empty until pte is filled */ + pmdp_huge_clear_flush_notify(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t *pte, entry; + entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); + entry = pte_mkspecial(entry); + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + pte_unmap(pte); + } + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); + put_huge_zero_page(); +} + +static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long haddr) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + pgtable_t pgtable; + pmd_t _pmd; + bool young, write; + int i; + + VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); + VM_BUG_ON(!pmd_trans_huge(*pmd)); + + count_vm_event(THP_SPLIT_PMD); + + if (vma_is_dax(vma)) { + pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + if (is_huge_zero_pmd(_pmd)) + put_huge_zero_page(); + return; + } else if (is_huge_zero_pmd(*pmd)) { + return __split_huge_zero_page_pmd(vma, haddr, pmd); + } + + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!page_count(page), page); + atomic_add(HPAGE_PMD_NR - 1, &page->_count); + write = pmd_write(*pmd); + young = pmd_young(*pmd); + + /* leave pmd empty until pte is filled */ + pmdp_huge_clear_flush_notify(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t entry, *pte; + /* + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. + */ + entry = mk_pte(page + i, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (!write) + entry = pte_wrprotect(entry); + if (!young) + entry = pte_mkold(entry); + pte = pte_offset_map(&_pmd, haddr); + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + atomic_inc(&page[i]._mapcount); + pte_unmap(pte); + } + + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_inc(&page[i]._mapcount); + } + + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } + } + + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); +} + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl; + struct mm_struct *mm = vma->vm_mm; + unsigned long haddr = address & HPAGE_PMD_MASK; + + mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); + ptl = pmd_lock(mm, pmd); + if (likely(pmd_trans_huge(*pmd))) + __split_huge_pmd_locked(vma, pmd, haddr); + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE); +} + static void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address) { -- 2.5.0 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org