[PATCH v10 07/18] mm: allow vma_start_read_locked/vma_start_read_locked_nested to fail

[Suren Baghdasaryan]

With upcoming replacement of vm_lock with vm_refcnt, we need to handle a
possibility of vma_start_read_locked/vma_start_read_locked_nested failing
due to refcount overflow. Prepare for such possibility by changing these
APIs and adjusting their users.

Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Lokesh Gidra <lokeshgidra@xxxxxxxxxx>
---
Changes since v9 [1]:
- Refactor the code, per Lorenzo Stoakes
- Remove Vlastimil's Acked-by since code is changed

[1] https://lore.kernel.org/all/20250111042604.3230628-8-surenb@xxxxxxxxxx/

 include/linux/mm.h |  6 ++++--
 mm/userfaultfd.c   | 30 +++++++++++++++++++++++-------
 2 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1b8e72888124..7fa7c39162fd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -747,10 +747,11 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
  * not be used in such cases because it might fail due to mm_lock_seq overflow.
  * This functionality is used to obtain vma read lock and drop the mmap read lock.
  */
-static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
+static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
 {
 	mmap_assert_locked(vma->vm_mm);
 	down_read_nested(&vma->vm_lock.lock, subclass);
+	return true;
 }
 
 /*
@@ -759,10 +760,11 @@ static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int
  * not be used in such cases because it might fail due to mm_lock_seq overflow.
  * This functionality is used to obtain vma read lock and drop the mmap read lock.
  */
-static inline void vma_start_read_locked(struct vm_area_struct *vma)
+static inline bool vma_start_read_locked(struct vm_area_struct *vma)
 {
 	mmap_assert_locked(vma->vm_mm);
 	down_read(&vma->vm_lock.lock);
+	return true;
 }
 
 static inline void vma_end_read(struct vm_area_struct *vma)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 4527c385935b..867898c4e30b 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -84,8 +84,12 @@ static struct vm_area_struct *uffd_lock_vma(struct mm_struct *mm,
 
 	mmap_read_lock(mm);
 	vma = find_vma_and_prepare_anon(mm, address);
-	if (!IS_ERR(vma))
-		vma_start_read_locked(vma);
+	if (!IS_ERR(vma)) {
+		bool locked = vma_start_read_locked(vma);
+
+		if (!locked)
+			vma = ERR_PTR(-EAGAIN);
+	}
 
 	mmap_read_unlock(mm);
 	return vma;
@@ -1482,12 +1486,24 @@ static int uffd_move_lock(struct mm_struct *mm,
 
 	mmap_read_lock(mm);
 	err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
-	if (!err) {
-		vma_start_read_locked(*dst_vmap);
-		if (*dst_vmap != *src_vmap)
-			vma_start_read_locked_nested(*src_vmap,
-						SINGLE_DEPTH_NESTING);
+	if (err)
+		goto out;
+
+	if (!vma_start_read_locked(*dst_vmap)) {
+		err = -EAGAIN;
+		goto out;
 	}
+
+	/* Nothing further to do if both vmas are locked. */
+	if (*dst_vmap == *src_vmap)
+		goto out;
+
+	if (!vma_start_read_locked_nested(*src_vmap, SINGLE_DEPTH_NESTING)) {
+		/* Undo dst_vmap locking if src_vmap failed to lock */
+		vma_end_read(*dst_vmap);
+		err = -EAGAIN;
+	}
+out:
 	mmap_read_unlock(mm);
 	return err;
 }
-- 
2.48.1.601.g30ceb7b040-goog