[PATCH v2 1/3] mm: enable MADV_DONTNEED for hugetlb mappings

[Mike Kravetz]

MADV_DONTNEED is currently disabled for hugetlb mappings.  This
certainly makes sense in shared file mappings as the pagecache maintains
a reference to the page and it will never be freed.  However, it could
be useful to unmap and free pages in private mappings.

The only thing preventing MADV_DONTNEED from working on hugetlb mappings
is a check in can_madv_lru_vma().  To allow support for hugetlb mappings
create and use a new routine madvise_dontneed_free_valid_vma() that will
allow hugetlb mappings.  Also, before calling zap_page_range in the
DONTNEED case align start and size to huge page size for hugetlb vmas.
madvise only requires PAGE_SIZE alignment, but the hugetlb unmap routine
requires huge page size alignment.

Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 mm/madvise.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index 5604064df464..7ae891e030a4 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -796,10 +796,30 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 					unsigned long start, unsigned long end)
 {
+	/*
+	 * start and size (end - start) must be huge page size aligned
+	 * for hugetlb vmas.
+	 */
+	if (is_vm_hugetlb_page(vma)) {
+		struct hstate *h = hstate_vma(vma);
+
+		start = ALIGN_DOWN(start, huge_page_size(h));
+		end = ALIGN(end, huge_page_size(h));
+	}
+
 	zap_page_range(vma, start, end - start);
 	return 0;
 }
 
+static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
+						int behavior)
+{
+	if (is_vm_hugetlb_page(vma))
+		return behavior == MADV_DONTNEED;
+	else
+		return can_madv_lru_vma(vma);
+}
+
 static long madvise_dontneed_free(struct vm_area_struct *vma,
 				  struct vm_area_struct **prev,
 				  unsigned long start, unsigned long end,
@@ -808,7 +828,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 
 	*prev = vma;
-	if (!can_madv_lru_vma(vma))
+	if (!madvise_dontneed_free_valid_vma(vma, behavior))
 		return -EINVAL;
 
 	if (!userfaultfd_remove(vma, start, end)) {
@@ -830,7 +850,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 			 */
 			return -ENOMEM;
 		}
-		if (!can_madv_lru_vma(vma))
+		if (!madvise_dontneed_free_valid_vma(vma, behavior))
 			return -EINVAL;
 		if (end > vma->vm_end) {
 			/*
-- 
2.34.1