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>

2 files changed, 10 insertions, 9 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 780d12c000e9..de984159cf0b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -803,7 +803,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 return VM_FAULT_FALLBACK;
         if (unlikely(anon_vma_prepare(vma)))
                 return VM_FAULT_OOM;
-        if (unlikely(khugepaged_enter(vma)))
+        if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
                 return VM_FAULT_OOM;
         if (!(flags & FAULT_FLAG_WRITE) &&
                         transparent_hugepage_use_zero_page()) {
@@ -1970,7 +1970,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
                  * register it here without waiting a page fault that
                  * may not happen any time soon.
                  */
-                if (unlikely(khugepaged_enter_vma_merge(vma)))
+                if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
                         return -ENOMEM;
                 break;
         case MADV_NOHUGEPAGE:
@@ -2071,7 +2071,8 @@ int __khugepaged_enter(struct mm_struct *mm)
         return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+                               unsigned long vm_flags)
 {
         unsigned long hstart, hend;
         if (!vma->anon_vma)
@@ -2083,11 +2084,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
         if (vma->vm_ops)
                 /* khugepaged not yet working on file or special mappings */
                 return 0;
-        VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
+        VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
         hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
         hend = vma->vm_end & HPAGE_PMD_MASK;
         if (hstart < hend)
-                return khugepaged_enter(vma);
+                return khugepaged_enter(vma, vm_flags);
         return 0;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f855206e7fb..87e82b38453c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1080,7 +1080,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
                                 end, prev->vm_pgoff, NULL);
                 if (err)
                         return NULL;
-                khugepaged_enter_vma_merge(prev);
+                khugepaged_enter_vma_merge(prev, vm_flags);
                 return prev;
         }
 
@@ -1099,7 +1099,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
                                 next->vm_pgoff - pglen, NULL);
                 if (err)
                         return NULL;
-                khugepaged_enter_vma_merge(area);
+                khugepaged_enter_vma_merge(area, vm_flags);
                 return area;
         }
 
@@ -2208,7 +2208,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
                 }
         }
         vma_unlock_anon_vma(vma);
-        khugepaged_enter_vma_merge(vma);
+        khugepaged_enter_vma_merge(vma, vma->vm_flags);
         validate_mm(vma->vm_mm);
         return error;
 }
@@ -2277,7 +2277,7 @@ int expand_downwards(struct vm_area_struct *vma,
                 }
         }
         vma_unlock_anon_vma(vma);
-        khugepaged_enter_vma_merge(vma);
+        khugepaged_enter_vma_merge(vma, vma->vm_flags);
         validate_mm(vma->vm_mm);
         return error;
 }