Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 20 May 2021 00:53:45 -0600
In-Reply-To: <20210520065355.2736558-1-yuzhao@google.com>
Message-Id: <20210520065355.2736558-5-yuzhao@google.com>
Mime-Version: 1.0
References: <20210520065355.2736558-1-yuzhao@google.com>
Subject: [PATCH v3 04/14] mm, x86: support the access bit on non-leaf PMD entries
From:   Yu Zhao <yuzhao@google.com>
To:     linux-mm@kvack.org
Cc:     Alex Shi <alexs@kernel.org>, Andi Kleen <ak@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Dave Chinner <david@fromorbit.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Donald Carr <sirspudd@gmail.com>,
        Hillf Danton <hdanton@sina.com>, Jens Axboe <axboe@kernel.dk>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Jonathan Corbet <corbet@lwn.net>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>,
        Konstantin Kharlamov <hi-angel@yandex.ru>,
        Marcus Seyfarth <m.seyfarth@gmail.com>,
        Matthew Wilcox <willy@infradead.org>,
        Mel Gorman <mgorman@suse.de>,
        Miaohe Lin <linmiaohe@huawei.com>,
        Michael Larabel <michael@michaellarabel.com>,
        Michal Hocko <mhocko@suse.com>,
        Michel Lespinasse <michel@lespinasse.org>,
        Rik van Riel <riel@surriel.com>,
        Roman Gushchin <guro@fb.com>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Yang Shi <shy828301@gmail.com>,
        Ying Huang <ying.huang@intel.com>, Zi Yan <ziy@nvidia.com>,
        linux-kernel@vger.kernel.org, lkp@lists.01.org,
        page-reclaim@google.com, Yu Zhao <yuzhao@google.com>,
        Konstantin Kharlamov <Hi-Angel@yandex.ru>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Some architectures support the accessed bit on non-leaf PMD entries
(parents) in addition to leaf PTE entries (children) where pages are
mapped, e.g., x86_64 sets the accessed bit on a parent when using it
as part of linear-address translation [1]. Page table walkers who are
interested in the accessed bit on children can take advantage of this:
they do not need to search the children when the accessed bit is not
set on a parent, given that they have previously cleared the accessed
bit on this parent.

[1]: Intel 64 and IA-32 Architectures Software Developer's Manual
     Volume 3 (October 2019), section 4.8

Signed-off-by: Yu Zhao <yuzhao@google.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
---
 arch/Kconfig                   | 9 +++++++++
 arch/x86/Kconfig               | 1 +
 arch/x86/include/asm/pgtable.h | 2 +-
 arch/x86/mm/pgtable.c          | 5 ++++-
 include/linux/pgtable.h        | 4 ++--
 5 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index c45b770d3579..e3812adc69f7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -826,6 +826,15 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 	bool
 
+config HAVE_ARCH_PARENT_PMD_YOUNG
+	bool
+	depends on PGTABLE_LEVELS > 2
+	help
+	  Architectures that select this are able to set the accessed bit on
+	  non-leaf PMD entries in addition to leaf PTE entries where pages are
+	  mapped. For them, page table walkers that clear the accessed bit may
+	  stop at non-leaf PMD entries if they do not see the accessed bit.
+
 config HAVE_ARCH_HUGE_VMAP
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0045e1b44190..f619055c4537 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -170,6 +170,7 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
+	select HAVE_ARCH_PARENT_PMD_YOUNG	if X86_64
 	select HAVE_ARCH_USERFAULTFD_WP         if X86_64 && USERFAULTFD
 	select HAVE_ARCH_USERFAULTFD_MINOR	if X86_64 && USERFAULTFD
 	select HAVE_ARCH_VMAP_STACK		if X86_64
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b1099f2d9800..3a24d2af4e9b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -846,7 +846,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	return ((pmd_flags(pmd) | _PAGE_ACCESSED) & ~_PAGE_USER) != _KERNPG_TABLE;
 }
 
 static inline unsigned long pages_to_mb(unsigned long npg)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d27cf69e811d..b968d6bd28b6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return ret;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HAVE_ARCH_PARENT_PMD_YOUNG)
 int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pmd_t *pmdp)
 {
@@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 
 	return ret;
 }
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pudp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pud_t *pudp)
 {
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 46b13780c2c8..94ecc1d277a2 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -193,7 +193,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HAVE_ARCH_PARENT_PMD_YOUNG)
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
 					    pmd_t *pmdp)
@@ -214,7 +214,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 	BUILD_BUG();
 	return 0;
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HAVE_ARCH_PARENT_PMD_YOUNG */
 #endif
 
 #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-- 
2.31.1.751.gd2f1c929bd-goog