mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG

Some architectures support the accessed bit in non-leaf PMD entries, e.g.,
x86 sets the accessed bit in a non-leaf PMD entry when using it as part of
linear address translation [1].  Page table walkers that clear the
accessed bit may use this capability to reduce their search space.

Note that:
1. Although an inline function is preferable, this capability is added
   as a configuration option for consistency with the existing macros.
2. Due to the little interest in other varieties, this capability was
   only tested on Intel and AMD CPUs.

Thanks to the following developers for their efforts [2][3].
  Randy Dunlap <rdunlap@infradead.org>
  Stephen Rothwell <sfr@canb.auug.org.au>

[1]: Intel 64 and IA-32 Architectures Software Developer's Manual
     Volume 3 (June 2021), section 4.8
[2] https://lore.kernel.org/r/bfdcc7c8-922f-61a9-aa15-7e7250f04af7@infradead.org/
[3] https://lore.kernel.org/r/20220413151513.5a0d7a7e@canb.auug.org.au/

Link: https://lkml.kernel.org/r/20220918080010.2920238-3-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 17 insertions, 4 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 5dbf11a5ba4e..1c2599618eeb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1415,6 +1415,14 @@ config DYNAMIC_SIGFRAME
 config HAVE_ARCH_NODE_DEV_GROUP
 	bool
 
+config ARCH_HAS_NONLEAF_PMD_YOUNG
+	bool
+	help
+	  Architectures that select this option are capable of setting the
+	  accessed bit in non-leaf PMD entries when using them as part of linear
+	  address translations. Page table walkers that clear the accessed bit
+	  may use this capability to reduce their search space.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f9920f1341c8..674d694a665e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ 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 PGTABLE_LEVELS > 2
 	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 dc5f7d8ef68a..5059799bebe3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -815,7 +815,8 @@ 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 a932d7712d85..8525f2876fb4 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 375e8e7e64f4..a108b60a6962 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -213,7 +213,7 @@ 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)
@@ -234,7 +234,7 @@ 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