Some architectures support the accessed bit on non-leaf PMD entries,
e.g., x86_64 sets the accessed bit on a non-leaf PMD entry when using
it as part of linear address translation [1]. As an optimization, page
table walkers who are interested in the accessed bit can skip the PTEs
under a non-leaf PMD entry if the accessed bit is cleared on this
non-leaf PMD entry.
Although an inline function may be preferable, this capability is
added as a configuration option to look consistent when used with the
existing macros.
[1]: Intel 64 and IA-32 Architectures Software Developer's Manual
Volume 3 (October 2019), section 4.8
Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Tested-by: Konstantin Kharlamov <Hi-Angel@xxxxxxxxx>
---
arch/Kconfig | 9 +++++++++
arch/x86/Kconfig | 1 +
arch/x86/include/asm/pgtable.h | 3 ++-
arch/x86/mm/pgtable.c | 5 ++++-
include/linux/pgtable.h | 4 ++--
5 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 129df498a8e1..5b6b4f95372f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1282,6 +1282,15 @@ config ARCH_SPLIT_ARG64
config ARCH_HAS_ELFCORE_COMPAT
bool
+config ARCH_HAS_NONLEAF_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.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 88fb922c23a0..36a81d31f711 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -84,6 +84,7 @@ config X86
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PTE_DEVMAP if X86_64
select ARCH_HAS_PTE_SPECIAL
+ select ARCH_HAS_NONLEAF_PMD_YOUNG if X86_64
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
select ARCH_HAS_COPY_MC if X86_64
select ARCH_HAS_SET_MEMORY
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3908780fc408..01a1763123ff 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -817,7 +817,8 @@ 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_USER | _PAGE_ACCESSED)) !=
+ (_KERNPG_TABLE & ~_PAGE_ACCESSED);
}
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 3481b35cb4ec..a224193d84bf 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_ARCH_HAS_NONLEAF_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 3a8221fa2c76..483d5ff7a33e 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -211,7 +211,7 @@ 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_ARCH_HAS_NONLEAF_PMD_YOUNG)
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
@@ -232,7 +232,7 @@ 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_ARCH_HAS_NONLEAF_PMD_YOUNG */
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
--
2.33.0.rc1.237.g0d66db33f3-goog
