fuse: Support fuse filesystems outside of init_user_ns

In order to support mounts from namespaces other than init_user_ns, fuse
must translate uids and gids to/from the userns of the process servicing
requests on /dev/fuse. This patch does that, with a couple of restrictions
on the namespace:

- The userns for the fuse connection is fixed to the namespace
from which /dev/fuse is opened.

- The namespace must be the same as s_user_ns.

These restrictions simplify the implementation by avoiding the need to pass
around userns references and by allowing fuse to rely on the checks in
setattr_prepare for ownership changes. Either restriction could be relaxed
in the future if needed.

For cuse the userns used is the opener of /dev/cuse. Semantically the cuse
support does not appear safe for unprivileged users. Practically the
permissions on /dev/cuse only make it accessible to the global root user.
If something slips through the cracks in a user namespace the only users
who will be able to use the cuse device are those users mapped into the
user namespace.

Translation in the posix acl is updated to use the uuser namespace of the
filesystem. Avoiding cases which might bypass this translation is handled
in a following change.

This change is stronlgy based on a similar change from Seth Forshee and
Dongsu Park.

Cc: Seth Forshee <[e-mail]>
Cc: Dongsu Park <[e-mail]>
Signed-off-by: Eric W. Biederman <[e-mail]>
Signed-off-by: Miklos Szeredi <[e-mail]>

fs/fuse/acl.c

···
 		return ERR_PTR(-ENOMEM);
 	size = fuse_getxattr(inode, name, value, PAGE_SIZE);
 	if (size > 0)
-		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		acl = posix_acl_from_xattr(fc->user_ns, value, size);
 	else if ((size == 0) || (size == -ENODATA) ||
 		 (size == -EOPNOTSUPP && fc->no_getxattr))
 		acl = NULL;
···
 		if (!value)
 			return -ENOMEM;
 
-		ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+		ret = posix_acl_to_xattr(fc->user_ns, acl, value, size);
 		if (ret < 0) {
 			kfree(value);
 			return ret;

fs/fuse/cuse.c

···
 #include <linux/stat.h>
 #include <linux/module.h>
 #include <linux/uio.h>
+#include <linux/user_namespace.h>
 
 #include "fuse_i.h"
 
···
 	if (!cc)
 		return -ENOMEM;
 
-	fuse_conn_init(&cc->fc);
+	/*
+	 * Limit the cuse channel to requests that can
+	 * be represented in file->f_cred->user_ns.
+	 */
+	fuse_conn_init(&cc->fc, file->f_cred->user_ns);
 
 	fud = fuse_dev_alloc(&cc->fc);
 	if (!fud) {

fs/fuse/dev.c

···
 		goto out;
 	}
 
-	req->in.h.uid = from_kuid(&init_user_ns, current_fsuid());
-	req->in.h.gid = from_kgid(&init_user_ns, current_fsgid());
+	req->in.h.uid = from_kuid(fc->user_ns, current_fsuid());
+	req->in.h.gid = from_kgid(fc->user_ns, current_fsgid());
 	req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
 
 	__set_bit(FR_WAITING, &req->flags);
···
 	if (!req)
 		req = get_reserved_req(fc, file);
 
-	req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
-	req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
+	req->in.h.uid = from_kuid_munged(fc->user_ns, current_fsuid());
+	req->in.h.gid = from_kgid_munged(fc->user_ns, current_fsgid());
 	req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
 
 	__set_bit(FR_WAITING, &req->flags);

fs/fuse/dir.c

···
 	stat->ino = attr->ino;
 	stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
 	stat->nlink = attr->nlink;
-	stat->uid = make_kuid(&init_user_ns, attr->uid);
-	stat->gid = make_kgid(&init_user_ns, attr->gid);
+	stat->uid = make_kuid(fc->user_ns, attr->uid);
+	stat->gid = make_kgid(fc->user_ns, attr->gid);
 	stat->rdev = inode->i_rdev;
 	stat->atime.tv_sec = attr->atime;
 	stat->atime.tv_nsec = attr->atimensec;
···
 	return true;
 }
 
-static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg,
-			   bool trust_local_cmtime)
+static void iattr_to_fattr(struct fuse_conn *fc, struct iattr *iattr,
+			   struct fuse_setattr_in *arg, bool trust_local_cmtime)
 {
 	unsigned ivalid = iattr->ia_valid;
 
 	if (ivalid & ATTR_MODE)
 		arg->valid |= FATTR_MODE,   arg->mode = iattr->ia_mode;
 	if (ivalid & ATTR_UID)
-		arg->valid |= FATTR_UID,    arg->uid = from_kuid(&init_user_ns, iattr->ia_uid);
+		arg->valid |= FATTR_UID,    arg->uid = from_kuid(fc->user_ns, iattr->ia_uid);
 	if (ivalid & ATTR_GID)
-		arg->valid |= FATTR_GID,    arg->gid = from_kgid(&init_user_ns, iattr->ia_gid);
+		arg->valid |= FATTR_GID,    arg->gid = from_kgid(fc->user_ns, iattr->ia_gid);
 	if (ivalid & ATTR_SIZE)
 		arg->valid |= FATTR_SIZE,   arg->size = iattr->ia_size;
 	if (ivalid & ATTR_ATIME) {
···
 
 	memset(&inarg, 0, sizeof(inarg));
 	memset(&outarg, 0, sizeof(outarg));
-	iattr_to_fattr(attr, &inarg, trust_local_cmtime);
+	iattr_to_fattr(fc, attr, &inarg, trust_local_cmtime);
 	if (file) {
 		struct fuse_file *ff = file->private_data;
 		inarg.valid |= FATTR_FH;

fs/fuse/fuse_i.h

···
 #include <linux/xattr.h>
 #include <linux/pid_namespace.h>
 #include <linux/refcount.h>
+#include <linux/user_namespace.h>
 
 /** Max number of pages that can be used in a single read request */
 #define FUSE_MAX_PAGES_PER_REQ 32
···
 	/** The pid namespace for this mount */
 	struct pid_namespace *pid_ns;
 
+	/** The user namespace for this mount */
+	struct user_namespace *user_ns;
+
 	/** Maximum read size */
 	unsigned max_read;
 
···
 /**
  * Initialize fuse_conn
  */
-void fuse_conn_init(struct fuse_conn *fc);
+void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns);
 
 /**
  * Release reference to fuse_conn

fs/fuse/inode.c

···
 	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
 	set_nlink(inode, attr->nlink);
-	inode->i_uid     = make_kuid(&init_user_ns, attr->uid);
-	inode->i_gid     = make_kgid(&init_user_ns, attr->gid);
+	inode->i_uid     = make_kuid(fc->user_ns, attr->uid);
+	inode->i_gid     = make_kgid(fc->user_ns, attr->gid);
 	inode->i_blocks  = attr->blocks;
 	inode->i_atime.tv_sec   = attr->atime;
 	inode->i_atime.tv_nsec  = attr->atimensec;
···
 	return err;
 }
 
-static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
+static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
+			  struct user_namespace *user_ns)
 {
 	char *p;
 	memset(d, 0, sizeof(struct fuse_mount_data));
···
 		case OPT_USER_ID:
 			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), uv);
+			d->user_id = make_kuid(user_ns, uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
···
 		case OPT_GROUP_ID:
 			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), uv);
+			d->group_id = make_kgid(user_ns, uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
···
 	struct super_block *sb = root->d_sb;
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
 
-	seq_printf(m, ",user_id=%u", from_kuid_munged(&init_user_ns, fc->user_id));
-	seq_printf(m, ",group_id=%u", from_kgid_munged(&init_user_ns, fc->group_id));
+	seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
+	seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
 	if (fc->default_permissions)
 		seq_puts(m, ",default_permissions");
 	if (fc->allow_other)
···
 	fpq->connected = 1;
 }
 
-void fuse_conn_init(struct fuse_conn *fc)
+void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
···
 	fc->attr_version = 1;
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	fc->user_ns = get_user_ns(user_ns);
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
···
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
 		put_pid_ns(fc->pid_ns);
+		put_user_ns(fc->user_ns);
 		fc->release(fc);
 	}
 }
···
 
 	sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
 
-	if (!parse_fuse_opt(data, &d, is_bdev))
+	if (!parse_fuse_opt(data, &d, is_bdev, sb->s_user_ns))
 		goto err;
 
 	if (is_bdev) {
···
 	if (!file)
 		goto err;
 
-	if ((file->f_op != &fuse_dev_operations) ||
-	    (file->f_cred->user_ns != &init_user_ns))
+	/*
+	 * Require mount to happen from the same user namespace which
+	 * opened /dev/fuse to prevent potential attacks.
+	 */
+	if (file->f_op != &fuse_dev_operations ||
+	    file->f_cred->user_ns != sb->s_user_ns)
 		goto err_fput;
 
 	fc = kmalloc(sizeof(*fc), GFP_KERNEL);
···
 	if (!fc)
 		goto err_fput;
 
-	fuse_conn_init(fc);
+	fuse_conn_init(fc, sb->s_user_ns);
 	fc->release = fuse_free_conn;
 
 	fud = fuse_dev_alloc(fc);