[PATCH 4.9 05/38] mm, hugetlbfs: introduce ->split() to vm_operations_struct

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@xxxxxxxxx>

commit 31383c6865a578834dd953d9dbc88e6b19fe3997 upstream.

Patch series "device-dax: fix unaligned munmap handling"

When device-dax is operating in huge-page mode we want it to behave like
hugetlbfs and fail attempts to split vmas into unaligned ranges.  It
would be messy to teach the munmap path about device-dax alignment
constraints in the same (hstate) way that hugetlbfs communicates this
constraint.  Instead, these patches introduce a new ->split() vm
operation.

This patch (of 2):

The device-dax interface has similar constraints as hugetlbfs in that it
requires the munmap path to unmap in huge page aligned units.  Rather
than add more custom vma handling code in __split_vma() introduce a new
vm operation to perform this vma specific check.

Link: http://lkml.kernel.org/r/151130418135.4029.6783191281930729710.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap")
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 include/linux/mm.h |    1 +
 mm/hugetlb.c       |    8 ++++++++
 mm/mmap.c          |    8 +++++---
 3 files changed, 14 insertions(+), 3 deletions(-)

--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,6 +347,7 @@ struct fault_env {
 struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
+	int (*split)(struct vm_area_struct * area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3135,6 +3135,13 @@ static void hugetlb_vm_op_close(struct v
 	}
 }
 
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	if (addr & ~(huge_page_mask(hstate_vma(vma))))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3151,6 +3158,7 @@ const struct vm_operations_struct hugetl
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
+	.split = hugetlb_vm_op_split,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2538,9 +2538,11 @@ static int __split_vma(struct mm_struct
 	struct vm_area_struct *new;
 	int err;
 
-	if (is_vm_hugetlb_page(vma) && (addr &
-					~(huge_page_mask(hstate_vma(vma)))))
-		return -EINVAL;
+	if (vma->vm_ops && vma->vm_ops->split) {
+		err = vma->vm_ops->split(vma, addr);
+		if (err)
+			return err;
+	}
 
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)