mm, thp: fix collapsing of hugepages on madvise

If an anonymous mapping is not allowed to fault thp memory and then
madvise(MADV_HUGEPAGE) is used after fault, khugepaged will never
collapse this memory into thp memory.

This occurs because the madvise(2) handler for thp, hugepage_madvise(),
clears VM_NOHUGEPAGE on the stack and it isn't stored in vma->vm_flags
until the final action of madvise_behavior().  This causes the
khugepaged_enter_vma_merge() to be a no-op in hugepage_madvise() when
the vma had previously had VM_NOHUGEPAGE set.

Fix this by passing the correct vma flags to the khugepaged mm slot
handler.  There's no chance khugepaged can run on this vma until after
madvise_behavior() returns since we hold mm->mmap_sem.

It would be possible to clear VM_NOHUGEPAGE directly from vma->vm_flags
in hugepage_advise(), but I didn't want to introduce special case
behavior into madvise_behavior().  I think it's best to just let it
always set vma->vm_flags itself.

Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Suleiman Souhlal <suleiman@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 10 insertions, 7 deletions

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 6b394f0b514..eeb30798571 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -6,7 +6,8 @@
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern int __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
-extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma);
+extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+				      unsigned long vm_flags);
 
 #define khugepaged_enabled()					       \
 	(transparent_hugepage_flags &				       \
@@ -35,13 +36,13 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 		__khugepaged_exit(mm);
 }
 
-static inline int khugepaged_enter(struct vm_area_struct *vma)
+static inline int khugepaged_enter(struct vm_area_struct *vma,
+				   unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
 		if ((khugepaged_always() ||
-		     (khugepaged_req_madv() &&
-		      vma->vm_flags & VM_HUGEPAGE)) &&
-		    !(vma->vm_flags & VM_NOHUGEPAGE))
+		     (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
+		    !(vm_flags & VM_NOHUGEPAGE))
 			if (__khugepaged_enter(vma->vm_mm))
 				return -ENOMEM;
 	return 0;
@@ -54,11 +55,13 @@ static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 static inline void khugepaged_exit(struct mm_struct *mm)
 {
 }
-static inline int khugepaged_enter(struct vm_area_struct *vma)
+static inline int khugepaged_enter(struct vm_area_struct *vma,
+				   unsigned long vm_flags)
 {
 	return 0;
 }
-static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+					     unsigned long vm_flags)
 {
 	return 0;
 }