fuse: implement ioctls to manage backing files

FUSE server calls the FUSE_DEV_IOC_BACKING_OPEN ioctl with a backing file
descriptor.  If the call succeeds, a backing file identifier is returned.

A later change will be using this backing file id in a reply to OPEN
request with the flag FOPEN_PASSTHROUGH to setup passthrough of file
operations on the open FUSE file to the backing file.

The FUSE server should call FUSE_DEV_IOC_BACKING_CLOSE ioctl to close the
backing file by its id.

This can be done at any time, but if an open reply with FOPEN_PASSTHROUGH
flag is still in progress, the open may fail if the backing file is
closed before the fuse file was opened.

Setting up backing files requires a server with CAP_SYS_ADMIN privileges.
For the backing file to be successfully setup, the backing file must
implement both read_iter and write_iter file operations.

The limitation on the level of filesystem stacking allowed for the
backing file is enforced before setting up the backing file.

Signed-off-by: Alessio Balsini <balsini@android.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/dev.c

@@ -2283,6 +2283,41 @@ static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
 	return res;
 }
 
+static long fuse_dev_ioctl_backing_open(struct file *file,
+					struct fuse_backing_map __user *argp)
+{
+	struct fuse_dev *fud = fuse_get_dev(file);
+	struct fuse_backing_map map;
+
+	if (!fud)
+		return -EPERM;
+
+	if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&map, argp, sizeof(map)))
+		return -EFAULT;
+
+	return fuse_backing_open(fud->fc, &map);
+}
+
+static long fuse_dev_ioctl_backing_close(struct file *file, __u32 __user *argp)
+{
+	struct fuse_dev *fud = fuse_get_dev(file);
+	int backing_id;
+
+	if (!fud)
+		return -EPERM;
+
+	if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		return -EOPNOTSUPP;
+
+	if (get_user(backing_id, argp))
+		return -EFAULT;
+
+	return fuse_backing_close(fud->fc, backing_id);
+}
+
 static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 			   unsigned long arg)
 {
@@ -2292,6 +2327,12 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 	case FUSE_DEV_IOC_CLONE:
 		return fuse_dev_ioctl_clone(file, argp);
 
+	case FUSE_DEV_IOC_BACKING_OPEN:
+		return fuse_dev_ioctl_backing_open(file, argp);
+
+	case FUSE_DEV_IOC_BACKING_CLOSE:
+		return fuse_dev_ioctl_backing_close(file, argp);
+
 	default:
 		return -ENOTTY;
 	}

fs/fuse/fuse_i.h

@@ -79,6 +79,7 @@ struct fuse_submount_lookup {
 /** Container for data related to mapping to backing file */
 struct fuse_backing {
 	struct file *file;
+	struct cred *cred;
 
 	/** refcount */
 	refcount_t count;
@@ -897,6 +898,11 @@ struct fuse_conn {
 
 	/* New writepages go into this bucket */
 	struct fuse_sync_bucket __rcu *curr_bucket;
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	/** IDR for backing files ids */
+	struct idr backing_files_map;
+#endif
 };
 
 /*
@@ -1409,5 +1415,9 @@ static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi,
 
 struct fuse_backing *fuse_backing_get(struct fuse_backing *fb);
 void fuse_backing_put(struct fuse_backing *fb);
+void fuse_backing_files_init(struct fuse_conn *fc);
+void fuse_backing_files_free(struct fuse_conn *fc);
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map);
+int fuse_backing_close(struct fuse_conn *fc, int backing_id);
 
 #endif /* _FS_FUSE_I_H */

fs/fuse/inode.c

@@ -930,6 +930,9 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
 	fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
 
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_files_init(fc);
+
 	INIT_LIST_HEAD(&fc->mounts);
 	list_add(&fm->fc_entry, &fc->mounts);
 	fm->fc = fc;
@@ -953,6 +956,8 @@ void fuse_conn_put(struct fuse_conn *fc)
 			WARN_ON(atomic_read(&bucket->count) != 1);
 			kfree(bucket);
 		}
+		if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+			fuse_backing_files_free(fc);
 		fc->release(fc);
 	}
 }

fs/fuse/passthrough.c

@@ -18,8 +18,11 @@ struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
 
 static void fuse_backing_free(struct fuse_backing *fb)
 {
+	pr_debug("%s: fb=0x%p\n", __func__, fb);
+
 	if (fb->file)
 		fput(fb->file);
+	put_cred(fb->cred);
 	kfree_rcu(fb, rcu);
 }
 
@@ -28,3 +31,136 @@ void fuse_backing_put(struct fuse_backing *fb)
 	if (fb && refcount_dec_and_test(&fb->count))
 		fuse_backing_free(fb);
 }
+
+void fuse_backing_files_init(struct fuse_conn *fc)
+{
+	idr_init(&fc->backing_files_map);
+}
+
+static int fuse_backing_id_alloc(struct fuse_conn *fc, struct fuse_backing *fb)
+{
+	int id;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock(&fc->lock);
+	/* FIXME: xarray might be space inefficient */
+	id = idr_alloc_cyclic(&fc->backing_files_map, fb, 1, 0, GFP_ATOMIC);
+	spin_unlock(&fc->lock);
+	idr_preload_end();
+
+	WARN_ON_ONCE(id == 0);
+	return id;
+}
+
+static struct fuse_backing *fuse_backing_id_remove(struct fuse_conn *fc,
+						   int id)
+{
+	struct fuse_backing *fb;
+
+	spin_lock(&fc->lock);
+	fb = idr_remove(&fc->backing_files_map, id);
+	spin_unlock(&fc->lock);
+
+	return fb;
+}
+
+static int fuse_backing_id_free(int id, void *p, void *data)
+{
+	struct fuse_backing *fb = p;
+
+	WARN_ON_ONCE(refcount_read(&fb->count) != 1);
+	fuse_backing_free(fb);
+	return 0;
+}
+
+void fuse_backing_files_free(struct fuse_conn *fc)
+{
+	idr_for_each(&fc->backing_files_map, fuse_backing_id_free, NULL);
+	idr_destroy(&fc->backing_files_map);
+}
+
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
+{
+	struct file *file;
+	struct super_block *backing_sb;
+	struct fuse_backing *fb = NULL;
+	int res;
+
+	pr_debug("%s: fd=%d flags=0x%x\n", __func__, map->fd, map->flags);
+
+	/* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+	res = -EPERM;
+	if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+		goto out;
+
+	res = -EINVAL;
+	if (map->flags)
+		goto out;
+
+	file = fget(map->fd);
+	res = -EBADF;
+	if (!file)
+		goto out;
+
+	res = -EOPNOTSUPP;
+	if (!file->f_op->read_iter || !file->f_op->write_iter)
+		goto out_fput;
+
+	backing_sb = file_inode(file)->i_sb;
+	res = -ELOOP;
+	if (backing_sb->s_stack_depth >= fc->max_stack_depth)
+		goto out_fput;
+
+	fb = kmalloc(sizeof(struct fuse_backing), GFP_KERNEL);
+	res = -ENOMEM;
+	if (!fb)
+		goto out_fput;
+
+	fb->file = file;
+	fb->cred = prepare_creds();
+	refcount_set(&fb->count, 1);
+
+	res = fuse_backing_id_alloc(fc, fb);
+	if (res < 0) {
+		fuse_backing_free(fb);
+		fb = NULL;
+	}
+
+out:
+	pr_debug("%s: fb=0x%p, ret=%i\n", __func__, fb, res);
+
+	return res;
+
+out_fput:
+	fput(file);
+	goto out;
+}
+
+int fuse_backing_close(struct fuse_conn *fc, int backing_id)
+{
+	struct fuse_backing *fb = NULL;
+	int err;
+
+	pr_debug("%s: backing_id=%d\n", __func__, backing_id);
+
+	/* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+	err = -EPERM;
+	if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+		goto out;
+
+	err = -EINVAL;
+	if (backing_id <= 0)
+		goto out;
+
+	err = -ENOENT;
+	fb = fuse_backing_id_remove(fc, backing_id);
+	if (!fb)
+		goto out;
+
+	fuse_backing_put(fb);
+	err = 0;
+out:
+	pr_debug("%s: fb=0x%p, err=%i\n", __func__, fb, err);
+
+	return err;
+}

include/uapi/linux/fuse.h

@@ -1057,9 +1057,18 @@ struct fuse_notify_retrieve_in {
 	uint64_t	dummy4;
 };
 
+struct fuse_backing_map {
+	int32_t		fd;
+	uint32_t	flags;
+	uint64_t	padding;
+};
+
 /* Device ioctls: */
 #define FUSE_DEV_IOC_MAGIC		229
 #define FUSE_DEV_IOC_CLONE		_IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t)
+#define FUSE_DEV_IOC_BACKING_OPEN	_IOW(FUSE_DEV_IOC_MAGIC, 1, \
+					     struct fuse_backing_map)
+#define FUSE_DEV_IOC_BACKING_CLOSE	_IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t)
 
 struct fuse_lseek_in {
 	uint64_t	fh;