VFS: introduce start_removing_dentry()

start_removing_dentry() is similar to start_removing() but instead of
providing a name for lookup, the target dentry is given.

start_removing_dentry() checks that the dentry is still hashed and in
the parent, and if so it locks and increases the refcount so that
end_removing() can be used to finish the operation.

This is used in cachefiles, overlayfs, smb/server, and apparmor.

There will be other users including ecryptfs.

As start_removing_dentry() takes an extra reference to the dentry (to be
put by end_removing()), there is no need to explicitly take an extra
reference to stop d_delete() from using dentry_unlink_inode() to negate
the dentry - as in cachefiles_delete_object(), and ksmbd_vfs_unlink().

cachefiles_bury_object() now gets an extra ref to the victim, which is
drops.  As it includes the needed end_removing() calls, the caller
doesn't need them.

Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/20251113002050.676694-9-neilb@ownmail.net
Signed-off-by: Christian Brauner <brauner@kernel.org>

3 files changed, 27 insertions, 23 deletions

diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 3e63cfe15874..a08250d244ea 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -9,6 +9,7 @@
 #include <linux/mount.h>
 #include <linux/xattr.h>
 #include <linux/file.h>
+#include <linux/namei.h>
 #include <linux/falloc.h>
 #include <trace/events/fscache.h>
 #include "internal.h"
@@ -428,11 +429,13 @@ static bool cachefiles_invalidate_cookie(struct fscache_cookie *cookie)
 		if (!old_tmpfile) {
 			struct cachefiles_volume *volume = object->volume;
 			struct dentry *fan = volume->fanout[(u8)cookie->key_hash];
+			struct dentry *obj;
 
-			inode_lock_nested(d_inode(fan), I_MUTEX_PARENT);
-			cachefiles_bury_object(volume->cache, object, fan,
-					       old_file->f_path.dentry,
-					       FSCACHE_OBJECT_INVALIDATED);
+			obj = start_removing_dentry(fan, old_file->f_path.dentry);
+			if (!IS_ERR(obj))
+				cachefiles_bury_object(volume->cache, object,
+						       fan, obj,
+						       FSCACHE_OBJECT_INVALIDATED);
 		}
 		fput(old_file);
 	}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index c7f0c6ab9b88..0104ac00485d 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -261,6 +261,7 @@ static int cachefiles_unlink(struct cachefiles_cache *cache,
  * - Directory backed objects are stuffed into the graveyard for userspace to
  *   delete
  * On entry dir must be locked.  It will be unlocked on exit.
+ * On entry there must be at least 2 refs on rep, one will be dropped on exit.
  */
 int cachefiles_bury_object(struct cachefiles_cache *cache,
 			   struct cachefiles_object *object,
@@ -275,12 +276,6 @@ int cachefiles_bury_object(struct cachefiles_cache *cache,
 
 	_enter(",'%pd','%pd'", dir, rep);
 
-	/* end_removing() will dput() @rep but we need to keep
-	 * a ref, so take one now.  This also stops the dentry
-	 * being negated when unlinked which we need.
-	 */
-	dget(rep);
-
 	if (rep->d_parent != dir) {
 		end_removing(rep);
 		_leave(" = -ESTALE");
@@ -425,13 +420,12 @@ int cachefiles_delete_object(struct cachefiles_object *object,
 
 	_enter(",OBJ%x{%pD}", object->debug_id, object->file);
 
-	/* Stop the dentry being negated if it's only pinned by a file struct. */
-	dget(dentry);
-
-	inode_lock_nested(d_backing_inode(fan), I_MUTEX_PARENT);
-	ret = cachefiles_unlink(volume->cache, object, fan, dentry, why);
-	inode_unlock(d_backing_inode(fan));
-	dput(dentry);
+	dentry = start_removing_dentry(fan, dentry);
+	if (IS_ERR(dentry))
+		ret = PTR_ERR(dentry);
+	else
+		ret = cachefiles_unlink(volume->cache, object, fan, dentry, why);
+	end_removing(dentry);
 	return ret;
 }
 
@@ -644,9 +638,13 @@ bool cachefiles_look_up_object(struct cachefiles_object *object)
 
 	if (!d_is_reg(dentry)) {
 		pr_err("%pd is not a file\n", dentry);
-		inode_lock_nested(d_inode(fan), I_MUTEX_PARENT);
-		ret = cachefiles_bury_object(volume->cache, object, fan, dentry,
-					     FSCACHE_OBJECT_IS_WEIRD);
+		struct dentry *de = start_removing_dentry(fan, dentry);
+		if (IS_ERR(de))
+			ret = PTR_ERR(de);
+		else
+			ret = cachefiles_bury_object(volume->cache, object,
+						     fan, de,
+						     FSCACHE_OBJECT_IS_WEIRD);
 		dput(dentry);
 		if (ret < 0)
 			return false;
diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c
index 781aac4ef274..90ba926f488e 100644
--- a/fs/cachefiles/volume.c
+++ b/fs/cachefiles/volume.c
@@ -7,6 +7,7 @@
 
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/namei.h>
 #include "internal.h"
 #include <trace/events/fscache.h>
 
@@ -58,9 +59,11 @@ retry:
 		if (ret < 0) {
 			if (ret != -ESTALE)
 				goto error_dir;
-			inode_lock_nested(d_inode(cache->store), I_MUTEX_PARENT);
-			cachefiles_bury_object(cache, NULL, cache->store, vdentry,
-					       FSCACHE_VOLUME_IS_WEIRD);
+			vdentry = start_removing_dentry(cache->store, vdentry);
+			if (!IS_ERR(vdentry))
+				cachefiles_bury_object(cache, NULL, cache->store,
+						       vdentry,
+						       FSCACHE_VOLUME_IS_WEIRD);
 			cachefiles_put_directory(volume->dentry);
 			cond_resched();
 			goto retry;