[PATCH v3] mm/THP: use hugepage_vma_check() in khugepaged_enter_vma_merge()
From: Song Liu
Date: Mon May 28 2018 - 14:04:31 EST
khugepaged_enter_vma_merge() is using a different approach to check
whether a vma is valid for khugepaged_enter():
if (!vma->anon_vma)
/*
* Not yet faulted in so we will register later in the
* page fault if needed.
*/
return 0;
if (vma->vm_ops || (vm_flags & VM_NO_KHUGEPAGED))
/* khugepaged not yet working on file or special mappings */
return 0;
This check has some problems. One of the obvious problems is that
it doesn't check shmem_file(), so that vma backed with shmem files
will not call khugepaged_enter(). Here is an example of failed madvise():
/* mount /dev/shm with huge=advise:
* mount -o remount,huge=advise /dev/shm */
/* create file /dev/shm/huge */
#define HUGE_FILE "/dev/shm/huge"
fd = open(HUGE_FILE, O_RDONLY);
ptr = mmap(NULL, FILE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0);
ret = madvise(ptr, FILE_SIZE, MADV_HUGEPAGE);
madvise() will return 0, but this memory region is never put in huge
page (check from /proc/meminfo: ShmemHugePages).
This patch fixes these problems by reusing hugepage_vma_check() in
khugepaged_enter_vma_merge().
vma->vm_flags is not yet updated in khugepaged_enter_vma_merge(),
so we need to pass the new vm_flags to hugepage_vma_check() through
a separate argument.
Signed-off-by: Song Liu <songliubraving@xxxxxx>
---
mm/khugepaged.c | 53 ++++++++++++++++++++++++-----------------------------
1 file changed, 24 insertions(+), 29 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d7b2a4b..e0a3bdf 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -430,18 +430,32 @@ int __khugepaged_enter(struct mm_struct *mm)
return 0;
}
+static bool hugepage_vma_check(struct vm_area_struct *vma,
+ unsigned long vm_flags)
+{
+ if ((!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
+ (vm_flags & VM_NOHUGEPAGE) ||
+ test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+ return false;
+ if (shmem_file(vma->vm_file)) {
+ if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
+ return false;
+ return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
+ HPAGE_PMD_NR);
+ }
+ if (!vma->anon_vma || vma->vm_ops)
+ return false;
+ if (is_vma_temporary_stack(vma))
+ return false;
+ return !(vm_flags & VM_NO_KHUGEPAGED);
+}
+
int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
unsigned long vm_flags)
{
unsigned long hstart, hend;
- if (!vma->anon_vma)
- /*
- * Not yet faulted in so we will register later in the
- * page fault if needed.
- */
- return 0;
- if (vma->vm_ops || (vm_flags & VM_NO_KHUGEPAGED))
- /* khugepaged not yet working on file or special mappings */
+
+ if (!hugepage_vma_check(vma, vm_flags))
return 0;
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = vma->vm_end & HPAGE_PMD_MASK;
@@ -819,25 +833,6 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
}
#endif
-static bool hugepage_vma_check(struct vm_area_struct *vma)
-{
- if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
- (vma->vm_flags & VM_NOHUGEPAGE) ||
- test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
- return false;
- if (shmem_file(vma->vm_file)) {
- if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
- return false;
- return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR);
- }
- if (!vma->anon_vma || vma->vm_ops)
- return false;
- if (is_vma_temporary_stack(vma))
- return false;
- return !(vma->vm_flags & VM_NO_KHUGEPAGED);
-}
-
/*
* If mmap_sem temporarily dropped, revalidate vma
* before taking mmap_sem.
@@ -862,7 +857,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
hend = vma->vm_end & HPAGE_PMD_MASK;
if (address < hstart || address + HPAGE_PMD_SIZE > hend)
return SCAN_ADDRESS_RANGE;
- if (!hugepage_vma_check(vma))
+ if (!hugepage_vma_check(vma, vma->vm_flags))
return SCAN_VMA_CHECK;
return 0;
}
@@ -1694,7 +1689,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
progress++;
break;
}
- if (!hugepage_vma_check(vma)) {
+ if (!hugepage_vma_check(vma, vma->vm_flags)) {
skip:
progress++;
continue;
--
2.9.5