fs: use backing_file container for internal files with "fake" f_path

Overlayfs uses open_with_fake_path() to allocate internal kernel files,
with a "fake" path - whose f_path is not on the same fs as f_inode.

Allocate a container struct backing_file for those internal files, that
is used to hold the "fake" ovl path along with the real path.

backing_file_real_path() can be used to access the stored real path.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Message-Id: <20230615112229.2143178-5-amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

4 files changed, 86 insertions, 18 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 4bc713865212..e06c68e2d757 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -44,18 +44,40 @@ static struct kmem_cache *filp_cachep __read_mostly;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
+/* Container for backing file with optional real path */
+struct backing_file {
+	struct file file;
+	struct path real_path;
+};
+
+static inline struct backing_file *backing_file(struct file *f)
+{
+	return container_of(f, struct backing_file, file);
+}
+
+struct path *backing_file_real_path(struct file *f)
+{
+	return &backing_file(f)->real_path;
+}
+EXPORT_SYMBOL_GPL(backing_file_real_path);
+
 static void file_free_rcu(struct rcu_head *head)
 {
 	struct file *f = container_of(head, struct file, f_rcuhead);
 
 	put_cred(f->f_cred);
-	kmem_cache_free(filp_cachep, f);
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		kfree(backing_file(f));
+	else
+		kmem_cache_free(filp_cachep, f);
 }
 
 static inline void file_free(struct file *f)
 {
 	security_file_free(f);
-	if (!(f->f_mode & FMODE_NOACCOUNT))
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		path_put(backing_file_real_path(f));
+	if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
 		percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_rcuhead, file_free_rcu);
 }
@@ -226,6 +248,30 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
+/*
+ * Variant of alloc_empty_file() that allocates a backing_file container
+ * and doesn't check and modify nr_files.
+ *
+ * This is only for kernel internal use, and the allocate file must not be
+ * installed into file tables or such.
+ */
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
+{
+	struct backing_file *ff;
+	int error;
+
+	ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL);
+	if (unlikely(!ff))
+		return ERR_PTR(-ENOMEM);
+
+	error = init_file(&ff->file, flags, cred);
+	if (unlikely(error))
+		return ERR_PTR(error);
+
+	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
+	return &ff->file;
+}
+
 /**
  * alloc_file - allocate and initialize a 'struct file'
  *
diff --git a/fs/internal.h b/fs/internal.h
index bd3b2810a36b..9c31078e0d16 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -97,8 +97,9 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *alloc_empty_file(int, const struct cred *);
-extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
+struct file *alloc_empty_file(int flags, const struct cred *cred);
+struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
 
 static inline void put_file_access(struct file *file)
 {
diff --git a/fs/open.c b/fs/open.c
index 322e017bf480..81186b277815 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1149,23 +1149,44 @@ struct file *kernel_file_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
 
-struct file *open_with_fake_path(const struct path *path, int flags,
-				struct inode *inode, const struct cred *cred)
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @path:	path of the file to open
+ * @flags:	open flags
+ * @path:	path of the backing file
+ * @cred:	credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @path may be on the stackable filesystem and backing inode on the
+ * underlying filesystem. In this case, we want to be able to return
+ * the @real_path of the backing inode. This is done by embedding the
+ * returned file into a container structure that also stores the path of
+ * the backing inode on the underlying filesystem, which can be
+ * retrieved using backing_file_real_path().
+ */
+struct file *backing_file_open(const struct path *path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred)
 {
-	struct file *f = alloc_empty_file_noaccount(flags, cred);
-	if (!IS_ERR(f)) {
-		int error;
+	struct file *f;
+	int error;
 
-		f->f_path = *path;
-		error = do_dentry_open(f, inode, NULL);
-		if (error) {
-			fput(f);
-			f = ERR_PTR(error);
-		}
+	f = alloc_empty_backing_file(flags, cred);
+	if (IS_ERR(f))
+		return f;
+
+	f->f_path = *path;
+	path_get(real_path);
+	*backing_file_real_path(f) = *real_path;
+	error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
 	}
+
 	return f;
 }
-EXPORT_SYMBOL(open_with_fake_path);
+EXPORT_SYMBOL_GPL(backing_file_open);
 
 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 7c04f033aadd..71fa6c83f093 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -61,8 +61,8 @@ static struct file *ovl_open_realfile(const struct file *file,
 		if (!inode_owner_or_capable(real_idmap, realinode))
 			flags &= ~O_NOATIME;
 
-		realfile = open_with_fake_path(&file->f_path, flags, realinode,
-					       current_cred());
+		realfile = backing_file_open(&file->f_path, flags, realpath,
+					     current_cred());
 	}
 	revert_creds(old_cred);