From: Zi Yan <ziy@xxxxxxxxxx>
madvise can set this bit via MADV_HUGEPAGE | MADV_HUGEPAGE_1GB and unset
it via MADV_NOHUGEPAGE | MADV_HUGEPAGE_1GB. Later, kernel will check
this bit to decide whether to allocate PUD THPs or not on a VMA when the
global PUD THP is set to madvise.
Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
---
include/linux/mm.h | 6 ++++++
mm/khugepaged.c | 9 +++++++++
2 files changed, 15 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 51b75ffa6a6c..78bee63c64da 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -305,11 +305,13 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0)
#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1)
#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2)
#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3)
#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4)
+#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5)
#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -325,6 +327,10 @@ extern unsigned int kobjsize(const void *objp);
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+#define VM_HUGEPAGE_PUD VM_HIGH_ARCH_5
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
#if defined(CONFIG_X86)
# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */
#elif defined(CONFIG_PPC)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b34c78085017..f085c218ea84 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -345,6 +345,9 @@ struct attribute_group khugepaged_attr_group = {
int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
{
+ /* only support 1GB PUD THP on x86 now */
+ bool use_pud_page = advice & MADV_HUGEPAGE_1GB;
+
advice = advice & MADV_BEHAVIOR_MASK;
switch (advice) {
case MADV_HUGEPAGE:
@@ -359,6 +362,9 @@ int hugepage_madvise(struct vm_area_struct *vma,
#endif
*vm_flags &= ~VM_NOHUGEPAGE;
*vm_flags |= VM_HUGEPAGE;
+
+ if (use_pud_page)
+ *vm_flags |= VM_HUGEPAGE_PUD;
/*
* If the vma become good for khugepaged to scan,
* register it here without waiting a page fault that
@@ -371,6 +377,9 @@ int hugepage_madvise(struct vm_area_struct *vma,
case MADV_NOHUGEPAGE:
*vm_flags &= ~VM_HUGEPAGE;
*vm_flags |= VM_NOHUGEPAGE;
+
+ if (use_pud_page)
+ *vm_flags &= ~VM_HUGEPAGE_PUD;
/*
* Setting VM_NOHUGEPAGE will prevent khugepaged from scanning
* this vma even if we leave the mm registered in khugepaged if
--
2.28.0
