[CRIU] [RFC PATCH 7/9] fuse: add fuse device ioctl(FUSE_DEV_IOC_REINIT)

[Bernd Schubert]

On 2/20/23 20:37, Alexander Mikhalitsyn wrote:
> This ioctl aborts fuse connection and then reinitializes it,
> sends FUSE_INIT request to allow a new userspace daemon
> to pick up the fuse connection.
> 
> Cc: Miklos Szeredi <mszeredi at redhat.com>
> Cc: Al Viro <viro at zeniv.linux.org.uk>
> Cc: Amir Goldstein <amir73il at gmail.com>
> Cc: Stéphane Graber <stgraber at ubuntu.com>
> Cc: Seth Forshee <sforshee at kernel.org>
> Cc: Christian Brauner <brauner at kernel.org>
> Cc: Andrei Vagin <avagin at gmail.com>
> Cc: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
> Cc: linux-fsdevel at vger.kernel.org
> Cc: linux-kernel at vger.kernel.org
> Cc: criu at openvz.org
> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn at canonical.com>
> ---
>   fs/fuse/dev.c             | 132 ++++++++++++++++++++++++++++++++++++++
>   include/uapi/linux/fuse.h |   1 +
>   2 files changed, 133 insertions(+)
> 
> diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
> index 737764c2295e..0f53ffd63957 100644
> --- a/fs/fuse/dev.c
> +++ b/fs/fuse/dev.c
> @@ -2187,6 +2187,112 @@ void fuse_abort_conn(struct fuse_conn *fc)
>   }
>   EXPORT_SYMBOL_GPL(fuse_abort_conn);
>   
> +static int fuse_reinit_conn(struct fuse_conn *fc)
> +{
> +	struct fuse_iqueue *fiq = &fc->iq;
> +	struct fuse_dev *fud;
> +	unsigned int i;

Assuming you have a malicious daemon that tries to cause bad behavior, 
only allow one ioctl at at time? I.e. add a value that reinit is in 
progress? And unset at the end of the function?

> +
> +	if (fc->conn_gen + 1 < fc->conn_gen)
> +		return -EOVERFLOW;
> +

Add a comment, like

/* Unsets fc->connected and fiq->connected and ensures that no new 
requests can be queued */

?

> +	fuse_abort_conn(fc);
> +	fuse_wait_aborted(fc);
> +
> +	spin_lock(&fc->lock);
> +	if (fc->connected) {
> +		spin_unlock(&fc->lock);
> +		return -EINVAL;
> +	}
> +
> +	if (fc->conn_gen + 1 < fc->conn_gen) {
> +		spin_unlock(&fc->lock);
> +		return -EOVERFLOW;
> +	}
> +
> +	fc->conn_gen++;
> +
> +	spin_lock(&fiq->lock);
> +	if (request_pending(fiq) || fiq->forget_list_tail != &fiq->forget_list_head) {
> +		spin_unlock(&fiq->lock);
> +		spin_unlock(&fc->lock);
> +		return -EINVAL;
> +	}
> +
> +	if (&fuse_dev_fiq_ops != fiq->ops) {
> +		spin_unlock(&fiq->lock);
> +		spin_unlock(&fc->lock);
> +		return -EOPNOTSUPP;
> +	}
> +
> +	fiq->connected = 1;
> +	spin_unlock(&fiq->lock);
> +
> +	spin_lock(&fc->bg_lock);
> +	if (!list_empty(&fc->bg_queue)) {
> +		spin_unlock(&fc->bg_lock);
> +		spin_unlock(&fc->lock);
> +		return -EINVAL;
> +	}
> +
> +	fc->blocked = 0;
> +	fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND;
> +	spin_unlock(&fc->bg_lock);
> +
> +	list_for_each_entry(fud, &fc->devices, entry) {
> +		struct fuse_pqueue *fpq = &fud->pq;
> +
> +		spin_lock(&fpq->lock);
> +		if (!list_empty(&fpq->io)) {
> +			spin_unlock(&fpq->lock);
> +			spin_unlock(&fc->lock);
> +			return -EINVAL;
> +		}
> +
> +		for (i = 0; i < FUSE_PQ_HASH_SIZE; i++) {
> +			if (!list_empty(&fpq->processing[i])) {
> +				spin_unlock(&fpq->lock);
> +				spin_unlock(&fc->lock);
> +				return -EINVAL;
> +			}
> +		}
> +
> +		fpq->connected = 1;
> +		spin_unlock(&fpq->lock);
> +	}
> +
> +	fuse_set_initialized(fc);

I'm not sure about this, why not the common way via FUSE_INIT reply?

> +
> +	/* Background queuing checks fc->connected under bg_lock */
> +	spin_lock(&fc->bg_lock);
> +	fc->connected = 1;
> +	spin_unlock(&fc->bg_lock);
> +
> +	fc->aborted = false;
> +	fc->abort_err = 0;
> +
> +	/* nullify all the flags */
> +	memset(&fc->flags, 0, sizeof(struct fuse_conn_flags));
> +
> +	spin_unlock(&fc->lock);
> +
> +	down_read(&fc->killsb);
> +	if (!list_empty(&fc->mounts)) {
> +		struct fuse_mount *fm;
> +
> +		fm = list_first_entry(&fc->mounts, struct fuse_mount, fc_entry);
> +		if (!fm->sb) {
> +			up_read(&fc->killsb);
> +			return -EINVAL;
> +		}
> +
> +		fuse_send_init(fm);
> +	}
> +	up_read(&fc->killsb);
> +
> +	return 0;
> +}
> +
>   void fuse_wait_aborted(struct fuse_conn *fc)
>   {
>   	/* matches implicit memory barrier in fuse_drop_waiting() */
> @@ -2282,6 +2388,32 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
>   			}
>   		}
>   		break;
> +	case FUSE_DEV_IOC_REINIT:
> +		struct fuse_conn *fc;
> +
> +		if (!checkpoint_restore_ns_capable(file->f_cred->user_ns))
> +			return -EPERM;
> +
> +		res = -EINVAL;
> +		fud = fuse_get_dev(file);
> +
> +		/*
> +		 * Only fuse mounts with an already initialized fuse
> +		 * connection are supported
> +		 */
> +		if (file->f_op == &fuse_dev_operations && fud) {
> +			mutex_lock(&fuse_mutex);
> +			fc = fud->fc;
> +			if (fc)
> +				fc = fuse_conn_get(fc);
> +			mutex_unlock(&fuse_mutex);
> +
> +			if (fc) {
> +				res = fuse_reinit_conn(fc);
> +				fuse_conn_put(fc);
> +			}
> +		}
> +		break;
>   	default:
>   		res = -ENOTTY;
>   		break;
> diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
> index 1b9d0dfae72d..3dac67b25eae 100644
> --- a/include/uapi/linux/fuse.h
> +++ b/include/uapi/linux/fuse.h
> @@ -989,6 +989,7 @@ struct fuse_notify_retrieve_in {
>   /* 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_REINIT		_IO(FUSE_DEV_IOC_MAGIC, 0)
>   
>   struct fuse_lseek_in {
>   	uint64_t	fh;