mm: allow vma_start_read_locked/vma_start_read_locked_nested to fail

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.

Link: https://lkml.kernel.org/r/20250213224655.1680278-8-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Tested-by: Shivank Garg <shivankg@amd.com>
  Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Klara Modin <klarasmodin@gmail.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Sourav Panda <souravpanda@google.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 27 insertions, 9 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 003c3e5c0a96..09b48af68699 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 48ac81bbfee6..fbf2cf62ab9f 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -85,8 +85,12 @@ 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;
@@ -1555,12 +1559,24 @@ 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;
 }