Moving a part of a private hugetlb mapping with mremap() leaks the huge
page reservations of the parts that stay. They are not returned when the
mapping is unmapped, when the process exits or when the pool is resized.

fixup_hugetlb_reservations() takes the reservation map away from the old
VMA while that VMA still spans its whole range, because the moved part is
only split off by the unmap at the end of the move. hugetlb_vm_op_close()
then finds no map in the parts that remain and returns nothing for them:

    mmap() of 4 pages, MAP_PRIVATE | MAP_HUGETLB    HugePages_Rsvd: 4
    mremap() of the second page to a new address    HugePages_Rsvd: 4
    munmap() of all of it                           HugePages_Rsvd: 3

The source is unmapped in this case, so the number of VMAs ends up where it
did before and the check against sysctl_max_map_count stays as it is.

Fix by splitting a hugetlb VMA in prep_move_vma() before a part of it is
moved, as commit 597e4b9ab48a ("mm/mremap: fix locked_vm leak by splitting
VMA for MREMAP_DONTUNMAP") does for an mlock()'d VMA. A backport needs that
commit, which is tagged for stable itself.

Fixes: 550a7d60bd5e ("mm, hugepages: add mremap() support for hugepage backed vma")
Cc: <stable@vger.kernel.org>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 mm/mremap.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index 0d06d7f37f19..cf746bafdee4 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1038,7 +1038,7 @@ static void vrm_stat_account(struct vma_remap_struct *vrm,
 }
 
 static bool __check_map_count_against_split(struct mm_struct *mm,
-					    bool pre_split,
+					    bool source_stays,
 					    bool before_unmaps)
 {
 	const int sys_map_count = get_sysctl_max_map_count();
@@ -1092,14 +1092,15 @@ static bool __check_map_count_against_split(struct mm_struct *mm,
 	 */
 	map_count += 2;
 
-	/* If pre-split, the -1 observed above doesn't apply. */
-	if (pre_split)
+	/* If the split off source stays, the -1 observed above doesn't apply. */
+	if (source_stays)
 		map_count++;
 
 	return map_count <= sys_map_count;
 }
 
-static bool needs_pre_split(struct vma_remap_struct *vrm)
+/* Is the source range split off its VMA, to then stay mapped? */
+static bool split_source_stays(struct vma_remap_struct *vrm)
 {
 	/*
 	 * An MREMAP_DONTUNMAP of a mlock()'d VMA needs to unlock the
@@ -1109,11 +1110,23 @@ static bool needs_pre_split(struct vma_remap_struct *vrm)
 		vma_test(vrm->vma, VMA_LOCKED_BIT);
 }
 
+static bool needs_pre_split(struct vma_remap_struct *vrm)
+{
+	/*
+	 * fixup_hugetlb_reservations() takes the reservations away from the
+	 * source VMA.  The parts of it that do not move have to keep theirs.
+	 */
+	if (vma_is_hugetlb(vrm->vma))
+		return true;
+
+	return split_source_stays(vrm);
+}
+
 /* Do we violate the map count limit if we split VMAs when moving the VMA? */
 static bool check_map_count_against_split(struct vma_remap_struct *vrm)
 {
 	return __check_map_count_against_split(current->mm,
-		needs_pre_split(vrm), /*before_unmaps=*/false);
+		split_source_stays(vrm), /*before_unmaps=*/false);
 }
 
 /* Do we violate the map count limit if we split VMAs prior to early unmaps? */
@@ -1162,10 +1175,7 @@ static unsigned long prep_move_vma(struct vma_remap_struct *vrm)
 	if (err)
 		return err;
 
-	/*
-	 * To account mlock()'d pages correctly in the MREMAP_DONTUNMAP
-	 * case perform any split ahead of time for an mlock()'d VMA.
-	 */
+	/* Perform any split ahead of time if the source VMA has to be distinct. */
 	if (needs_pre_split(vrm)) {
 		VMA_ITERATOR(vmi, vma->vm_mm, old_addr);
 

-- 
2.55.0