[PATCH 00/34] VFS: Introduce filesystem context [ver #12]

@@ -402,3 +402,4 @@
 388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
 389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen
 390	i386	fsconfig		sys_fsconfig			__ia32_sys_fsconfig
+391	i386	fsmount			sys_fsmount			__ia32_sys_fsmount

@@ -347,6 +347,7 @@
 336	common	move_mount		__x64_sys_move_mount
 337	common	fsopen			__x64_sys_fsopen
 338	common	fsconfig		__x64_sys_fsconfig
+339	common	fsmount			__x64_sys_fsmount
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -2463,7 +2463,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path)
 
 	attached = mnt_has_parent(old);
 	/*
-	 * We need to allow open_tree(OPEN_TREE_CLONE) followed by
+	 * We need to allow open_tree(OPEN_TREE_CLONE) or fsmount() followed by
 	 * move_mount(), but mustn't allow "/" to be moved.
 	 */
 	if (old->mnt_ns && !attached)

@@ -3329,9 +3329,126 @@ struct vfsmount *kern_mount(struct file_system_type *type)
 EXPORT_SYMBOL_GPL(kern_mount);
 
 /*
- * Move a mount from one place to another.
- * In combination with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be
- * used to copy a mount subtree.
+ * Create a kernel mount representation for a new, prepared superblock
+ * (specified by fs_fd) and attach to an open_tree-like file descriptor.
+ */
+SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, ms_flags)
+{
+	struct fs_context *fc;
+	struct file *file;
+	struct path newmount;
+	struct fd f;
+	unsigned int mnt_flags = 0;
+	long ret;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if ((flags & ~(FSMOUNT_CLOEXEC)) != 0)
+		return -EINVAL;
+
+	if (ms_flags & ~(MS_RDONLY | MS_NOSUID | MS_NODEV | MS_NOEXEC |
+			 MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+			 MS_STRICTATIME))
+		return -EINVAL;
+
+	if (ms_flags & MS_RDONLY)
+		mnt_flags |= MNT_READONLY;
+	if (ms_flags & MS_NOSUID)
+		mnt_flags |= MNT_NOSUID;
+	if (ms_flags & MS_NODEV)
+		mnt_flags |= MNT_NODEV;
+	if (ms_flags & MS_NOEXEC)
+		mnt_flags |= MNT_NOEXEC;
+	if (ms_flags & MS_NODIRATIME)
+		mnt_flags |= MNT_NODIRATIME;
+
+	if (ms_flags & MS_STRICTATIME) {
+		if (ms_flags & MS_NOATIME)
+			return -EINVAL;
+	} else if (ms_flags & MS_NOATIME) {
+		mnt_flags |= MNT_NOATIME;
+	} else {
+		mnt_flags |= MNT_RELATIME;
+	}
+
+	f = fdget(fs_fd);
+	if (!f.file)
+		return -EBADF;
+
+	ret = -EINVAL;
+	if (f.file->f_op != &fscontext_fops)
+		goto err_fsfd;
+
+	fc = f.file->private_data;
+
+	/* There must be a valid superblock or we can't mount it */
+	ret = -EINVAL;
+	if (!fc->root)
+		goto err_fsfd;
+
+	ret = -EPERM;
+	if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
+		pr_warn("VFS: Mount too revealing\n");
+		goto err_fsfd;
+	}
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret < 0)
+		goto err_fsfd;
+
+	ret = -EBUSY;
+	if (fc->phase != FS_CONTEXT_AWAITING_MOUNT)
+		goto err_unlock;
+
+	ret = -EPERM;
+	if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock())
+		goto err_unlock;
+
+	newmount.mnt = vfs_create_mount(fc, mnt_flags);
+	if (IS_ERR(newmount.mnt)) {
+		ret = PTR_ERR(newmount.mnt);
+		goto err_unlock;
+	}
+	newmount.dentry = dget(fc->root);
+
+	/* We've done the mount bit - now move the file context into more or
+	 * less the same state as if we'd done an fspick().  We don't want to
+	 * do any memory allocation or anything like that at this point as we
+	 * don't want to have to handle any errors incurred.
+	 */
+	vfs_clean_context(fc);
+
+	/* Attach to an apparent O_PATH fd with a note that we need to unmount
+	 * it, not just simply put it.
+	 */
+	file = dentry_open(&newmount, O_PATH, fc->cred);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto err_path;
+	}
+	file->f_mode |= FMODE_NEED_UNMOUNT;
+
+	ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0);
+	if (ret >= 0)
+		fd_install(ret, file);
+	else
+		fput(file);
+
+err_path:
+	path_put(&newmount);
+err_unlock:
+	mutex_unlock(&fc->uapi_mutex);
+err_fsfd:
+	fdput(f);
+	return ret;
+}
+
+/*
+ * Move a mount from one place to another.  In combination with
+ * fsopen()/fsmount() this is used to install a new mount and in combination
+ * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy
+ * a mount subtree.
  *
  * Note the flags value is a combination of MOVE_MOUNT_* flags.
  */

@@ -913,6 +913,7 @@ asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
 asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags);
 asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key,
 			     const void __user *value, int aux);
+asmlinkage long sys_fsmount(int fs_fd, unsigned int flags, unsigned int ms_flags);
 
 /*
  * Architecture-specific system calls

@@ -349,6 +349,8 @@ typedef int __bitwise __kernel_rwf_t;
  */
 #define FSOPEN_CLOEXEC		0x00000001
 
+#define FSMOUNT_CLOEXEC		0x00000001
+
 /*
  * The type of fsconfig() call made.
  */

@@ -398,3 +398,4 @@
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
+387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree

@@ -343,6 +343,7 @@
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
+335	common	open_tree		__x64_sys_open_tree
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -255,6 +255,7 @@ static void __fput(struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
+	fmode_t mode = file->f_mode;
 
 	if (unlikely(!(file->f_mode & FMODE_OPENED)))
 		goto out;

@@ -277,18 +278,20 @@ static void __fput(struct file *file)
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
-		     !(file->f_mode & FMODE_PATH))) {
+		     !(mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
 	}
 	fops_put(file->f_op);
 	put_pid(file->f_owner.pid);
-	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_dec(inode);
-	if (file->f_mode & FMODE_WRITER) {
+	if (mode & FMODE_WRITER) {
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
 	dput(dentry);
+	if (unlikely(mode & FMODE_NEED_UNMOUNT))
+		dissolve_on_fput(mnt);
 	mntput(mnt);
 out:
 	file_free(file);

@@ -85,6 +85,7 @@ extern int __mnt_want_write_file(struct file *);
 extern void __mnt_drop_write(struct vfsmount *);
 extern void __mnt_drop_write_file(struct file *);
 
+extern void dissolve_on_fput(struct vfsmount *);
 /*
  * fs_struct.c
  */

@@ -20,12 +20,14 @@
 #include <linux/init.h>		/* init_rootfs */
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
 #include <linux/fsnotify.h>	/* fsnotify_vfsmount_delete */
+#include <linux/file.h>
 #include <linux/uaccess.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
 #include <linux/bootmem.h>
 #include <linux/task_work.h>
 #include <linux/sched/task.h>
+#include <uapi/linux/mount.h>
 
 #include "pnode.h"
 #include "internal.h"

@@ -1779,6 +1781,16 @@ struct vfsmount *collect_mounts(const struct path *path)
 	return &tree->mnt;
 }
 
+void dissolve_on_fput(struct vfsmount *mnt)
+{
+	namespace_lock();
+	lock_mount_hash();
+	mntget(mnt);
+	umount_tree(real_mount(mnt), UMOUNT_CONNECTED);
+	unlock_mount_hash();
+	namespace_unlock();
+}
+
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();

@@ -2138,6 +2150,30 @@ static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
 	return false;
 }
 
+static struct mount *__do_loopback(struct path *old_path, int recurse)
+{
+	struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);
+
+	if (IS_MNT_UNBINDABLE(old))
+		return mnt;
+
+	if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations)
+		return mnt;
+
+	if (!recurse && has_locked_children(old, old_path->dentry))
+		return mnt;
+
+	if (recurse)
+		mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE);
+	else
+		mnt = clone_mnt(old, old_path->dentry, 0);
+
+	if (!IS_ERR(mnt))
+		mnt->mnt.mnt_flags &= ~MNT_LOCKED;
+
+	return mnt;
+}
+
 /*
  * do loopback mount.
  */

@@ -2145,7 +2181,7 @@ static int do_loopback(struct path *path, const char *old_name,
 				int recurse)
 {
 	struct path old_path;
-	struct mount *mnt = NULL, *old, *parent;
+	struct mount *mnt = NULL, *parent;
 	struct mountpoint *mp;
 	int err;
 	if (!old_name || !*old_name)

@@ -2159,38 +2195,21 @@ static int do_loopback(struct path *path, const char *old_name,
 		goto out;
 
 	mp = lock_mount(path);
-	err = PTR_ERR(mp);
-	if (IS_ERR(mp))
+	if (IS_ERR(mp)) {
+		err = PTR_ERR(mp);
 		goto out;
+	}
 
-	old = real_mount(old_path.mnt);
 	parent = real_mount(path->mnt);
-
-	err = -EINVAL;
-	if (IS_MNT_UNBINDABLE(old))
-		goto out2;
-
 	if (!check_mnt(parent))
 		goto out2;
 
-	if (!check_mnt(old) && old_path.dentry->d_op != &ns_dentry_operations)
-		goto out2;
-
-	if (!recurse && has_locked_children(old, old_path.dentry))
-		goto out2;
-
-	if (recurse)
-		mnt = copy_tree(old, old_path.dentry, CL_COPY_MNT_NS_FILE);
-	else
-		mnt = clone_mnt(old, old_path.dentry, 0);
-
+	mnt = __do_loopback(&old_path, recurse);
 	if (IS_ERR(mnt)) {
 		err = PTR_ERR(mnt);
 		goto out2;
 	}
 
-	mnt->mnt.mnt_flags &= ~MNT_LOCKED;
-
 	err = graft_tree(mnt, parent, mp);
 	if (err) {
 		lock_mount_hash();

@@ -2204,6 +2223,75 @@ static int do_loopback(struct path *path, const char *old_name,
 	return err;
 }
 
+SYSCALL_DEFINE3(open_tree, int, dfd, const char *, filename, unsigned, flags)
+{
+	struct file *file;
+	struct path path;
+	int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
+	bool detached = flags & OPEN_TREE_CLONE;
+	int error;
+	int fd;
+
+	BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC);
+
+	if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE |
+		      AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE |
+		      OPEN_TREE_CLOEXEC))
+		return -EINVAL;
+
+	if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE)
+		return -EINVAL;
+
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	if (detached && !may_mount())
+		return -EPERM;
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	error = user_path_at(dfd, filename, lookup_flags, &path);
+	if (error)
+		goto out;
+
+	if (detached) {
+		struct mount *mnt = __do_loopback(&path, flags & AT_RECURSIVE);
+		if (IS_ERR(mnt)) {
+			error = PTR_ERR(mnt);
+			goto out2;
+		}
+		mntput(path.mnt);
+		path.mnt = &mnt->mnt;
+	}
+
+	file = dentry_open(&path, O_PATH, current_cred());
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto out3;
+	}
+
+	if (detached)
+		file->f_mode |= FMODE_NEED_UNMOUNT;
+	path_put(&path);
+	fd_install(fd, file);
+	return fd;
+
+out3:
+	if (detached)
+		dissolve_on_fput(path.mnt);
+out2:
+	path_put(&path);
+out:
+	put_unused_fd(fd);
+	return error;
+}
+
 static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 {
 	int error = 0;

@@ -157,10 +157,13 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
 /* File is capable of returning -EAGAIN if I/O will block */
-#define FMODE_NOWAIT	((__force fmode_t)0x8000000)
+#define FMODE_NOWAIT		((__force fmode_t)0x8000000)
+
+/* File represents mount that needs unmounting */
+#define FMODE_NEED_UNMOUNT	((__force fmode_t)0x10000000)
 
 /* File does not contribute to nr_files count */
-#define FMODE_NOACCOUNT	((__force fmode_t)0x20000000)
+#define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector

@@ -906,6 +906,7 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
 
 /*
  * Architecture-specific system calls

@@ -90,5 +90,7 @@
 #define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
 #define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
 
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
 
 #endif /* _UAPI_LINUX_FCNTL_H */

@@ -0,0 +1,10 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
+
+#endif /* _UAPI_LINUX_MOUNT_H */

@@ -399,3 +399,4 @@
 385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
 387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
+388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount

@@ -344,6 +344,7 @@
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
 335	common	open_tree		__x64_sys_open_tree
+336	common	move_mount		__x64_sys_move_mount
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -2386,43 +2386,37 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
-static int do_move_mount(struct path *path, const char *old_name)
+static int do_move_mount(struct path *old_path, struct path *new_path)
 {
-	struct path old_path, parent_path;
+	struct path parent_path = {.mnt = NULL, .dentry = NULL};
 	struct mount *p;
 	struct mount *old;
 	struct mountpoint *mp;
 	int err;
-	if (!old_name || !*old_name)
-		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
-	if (err)
-		return err;
 
-	mp = lock_mount(path);
+	mp = lock_mount(new_path);
 	err = PTR_ERR(mp);
 	if (IS_ERR(mp))
 		goto out;
 
-	old = real_mount(old_path.mnt);
-	p = real_mount(path->mnt);
+	old = real_mount(old_path->mnt);
+	p = real_mount(new_path->mnt);
 
 	err = -EINVAL;
 	if (!check_mnt(p) || !check_mnt(old))
 		goto out1;
 
-	if (old->mnt.mnt_flags & MNT_LOCKED)
+	if (!mnt_has_parent(old))
 		goto out1;
 
-	err = -EINVAL;
-	if (old_path.dentry != old_path.mnt->mnt_root)
+	if (old->mnt.mnt_flags & MNT_LOCKED)
 		goto out1;
 
-	if (!mnt_has_parent(old))
+	if (old_path->dentry != old_path->mnt->mnt_root)
 		goto out1;
 
-	if (d_is_dir(path->dentry) !=
-	      d_is_dir(old_path.dentry))
+	if (d_is_dir(new_path->dentry) !=
+	    d_is_dir(old_path->dentry))
 		goto out1;
 	/*
 	 * Don't move a mount residing in a shared parent.

@@ -2440,7 +2434,8 @@ static int do_move_mount(struct path *path, const char *old_name)
 		if (p == old)
 			goto out1;
 
-	err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path);
+	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp,
+				   &parent_path);
 	if (err)
 		goto out1;
 

@@ -2452,6 +2447,22 @@ static int do_move_mount(struct path *path, const char *old_name)
 out:
 	if (!err)
 		path_put(&parent_path);
+	return err;
+}
+
+static int do_move_mount_old(struct path *path, const char *old_name)
+{
+	struct path old_path;
+	int err;
+
+	if (!old_name || !*old_name)
+		return -EINVAL;
+
+	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	if (err)
+		return err;
+
+	err = do_move_mount(&old_path, path);
 	path_put(&old_path);
 	return err;
 }

@@ -2873,7 +2884,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
 		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
-		retval = do_move_mount(&path, dev_name);
+		retval = do_move_mount_old(&path, dev_name);
 	else
 		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
 				      dev_name, data_page, data_size);

@@ -3108,6 +3119,61 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	return ksys_mount(dev_name, dir_name, type, flags, data);
 }
 
+/*
+ * Move a mount from one place to another.
+ *
+ * Note the flags value is a combination of MOVE_MOUNT_* flags.
+ */
+SYSCALL_DEFINE5(move_mount,
+		int, from_dfd, const char *, from_pathname,
+		int, to_dfd, const char *, to_pathname,
+		unsigned int, flags)
+{
+	struct path from_path, to_path;
+	unsigned int lflags;
+	int ret = 0;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if (flags & ~MOVE_MOUNT__MASK)
+		return -EINVAL;
+
+	/* If someone gives a pathname, they aren't permitted to move
+	 * from an fd that requires unmount as we can't get at the flag
+	 * to clear it afterwards.
+	 */
+	lflags = 0;
+	if (flags & MOVE_MOUNT_F_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_F_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(from_dfd, from_pathname, lflags, &from_path);
+	if (ret < 0)
+		return ret;
+
+	lflags = 0;
+	if (flags & MOVE_MOUNT_T_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_T_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_T_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(to_dfd, to_pathname, lflags, &to_path);
+	if (ret < 0)
+		goto out_from;
+
+	ret = security_move_mount(&from_path, &to_path);
+	if (ret < 0)
+		goto out_to;
+
+	ret = do_move_mount(&from_path, &to_path);
+
+out_to:
+	path_put(&to_path);
+out_from:
+	path_put(&from_path);
+	return ret;
+}
+
 /*
  * Return true if path is reachable from root
  *

@@ -147,6 +147,10 @@
  *	Parse a string of security data filling in the opts structure
  *	@options string containing all mount options known by the LSM
  *	@opts binary data structure usable by the LSM
+ * @move_mount:
+ *	Check permission before a mount is moved.
+ *	@from_path indicates the mount that is going to be moved.
+ *	@to_path indicates the mountpoint that will be mounted upon.
  * @dentry_init_security:
  *	Compute a context for a dentry as the inode is not yet available
  *	since NFSv4 has no label backed by an EA anyway.

@@ -1484,6 +1488,7 @@ union security_list_options {
 					unsigned long kern_flags,
 					unsigned long *set_kern_flags);
 	int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts);
+	int (*move_mount)(const struct path *from_path, const struct path *to_path);
 	int (*dentry_init_security)(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);

@@ -1816,6 +1821,7 @@ struct security_hook_heads {
 	struct hlist_head sb_set_mnt_opts;
 	struct hlist_head sb_clone_mnt_opts;
 	struct hlist_head sb_parse_opts_str;
+	struct hlist_head move_mount;
 	struct hlist_head dentry_init_security;
 	struct hlist_head dentry_create_files_as;
 #ifdef CONFIG_SECURITY_PATH

@@ -266,6 +266,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb,
 				unsigned long kern_flags,
 				unsigned long *set_kern_flags);
 int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts);
+int security_move_mount(const struct path *from_path, const struct path *to_path);
 int security_dentry_init_security(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);

@@ -621,6 +622,12 @@ static inline int security_sb_parse_opts_str(char *options, struct security_mnt_
 	return 0;
 }
 
+static inline int security_move_mount(const struct path *from_path,
+				      const struct path *to_path)
+{
+	return 0;
+}
+
 static inline int security_inode_alloc(struct inode *inode)
 {
 	return 0;

@@ -907,6 +907,9 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
 asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
+asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
+			       int to_dfd, const char __user *to_path,
+			       unsigned int ms_flags);
 
 /*
  * Architecture-specific system calls

@@ -7,4 +7,15 @@
 #define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
 #define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
 
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT__MASK		0x00000077
+
 #endif /* _UAPI_LINUX_MOUNT_H */

@@ -444,6 +444,11 @@ int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts)
 }
 EXPORT_SYMBOL(security_sb_parse_opts_str);
 
+int security_move_mount(const struct path *from_path, const struct path *to_path)
+{
+	return call_int_hook(move_mount, 0, from_path, to_path);
+}
+
 int security_inode_alloc(struct inode *inode)
 {
 	inode->i_security = NULL;

@@ -400,3 +400,4 @@
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
 387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
 388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
+389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen

@@ -345,6 +345,7 @@
 334	common	rseq			__x64_sys_rseq
 335	common	open_tree		__x64_sys_open_tree
 336	common	move_mount		__x64_sys_move_mount
+337	common	fsopen			__x64_sys_fsopen
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -13,7 +13,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_context.o fs_parser.o
+		fs_context.o fs_parser.o fsopen.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o

@@ -267,6 +267,8 @@ struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type,
 	fc->fs_type	= get_filesystem(fs_type);
 	fc->cred	= get_current_cred();
 
+	mutex_init(&fc->uapi_mutex);
+
 	switch (purpose) {
 	case FS_CONTEXT_FOR_KERNEL_MOUNT:
 		fc->sb_flags |= SB_KERNMOUNT;

@@ -334,6 +336,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc,
 	if (!fc)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&fc->uapi_mutex);
+
 	fc->fs_private	= NULL;
 	fc->s_fs_info	= NULL;
 	fc->source	= NULL;

@@ -0,0 +1,87 @@
+/* Filesystem access-by-fd.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fs_context.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/anon_inodes.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include "mount.h"
+
+static int fscontext_release(struct inode *inode, struct file *file)
+{
+	struct fs_context *fc = file->private_data;
+
+	if (fc) {
+		file->private_data = NULL;
+		put_fs_context(fc);
+	}
+	return 0;
+}
+
+const struct file_operations fscontext_fops = {
+	.release	= fscontext_release,
+	.llseek		= no_llseek,
+};
+
+/*
+ * Attach a filesystem context to a file and an fd.
+ */
+static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags)
+{
+	int fd;
+
+	fd = anon_inode_getfd("fscontext", &fscontext_fops, fc,
+			      O_RDWR | o_flags);
+	if (fd < 0)
+		put_fs_context(fc);
+	return fd;
+}
+
+/*
+ * Open a filesystem by name so that it can be configured for mounting.
+ *
+ * We are allowed to specify a container in which the filesystem will be
+ * opened, thereby indicating which namespaces will be used (notably, which
+ * network namespace will be used for network filesystems).
+ */
+SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
+{
+	struct file_system_type *fs_type;
+	struct fs_context *fc;
+	const char *fs_name;
+
+	if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (flags & ~FSOPEN_CLOEXEC)
+		return -EINVAL;
+
+	fs_name = strndup_user(_fs_name, PAGE_SIZE);
+	if (IS_ERR(fs_name))
+		return PTR_ERR(fs_name);
+
+	fs_type = get_fs_type(fs_name);
+	kfree(fs_name);
+	if (!fs_type)
+		return -ENODEV;
+
+	fc = vfs_new_fs_context(fs_type, NULL, 0, 0, FS_CONTEXT_FOR_USER_MOUNT);
+	put_filesystem(fs_type);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	fc->phase = FS_CONTEXT_CREATE_PARAMS;
+	return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0);
+}

@@ -14,6 +14,7 @@
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/mutex.h>
 
 struct cred;
 struct dentry;

@@ -37,6 +38,19 @@ enum fs_context_purpose {
 	FS_CONTEXT_FOR_EMERGENCY_RO,	/* Emergency reconfiguration to R/O */
 };
 
+/*
+ * Userspace usage phase for fsopen/fspick.
+ */
+enum fs_context_phase {
+	FS_CONTEXT_CREATE_PARAMS,	/* Loading params for sb creation */
+	FS_CONTEXT_CREATING,		/* A superblock is being created */
+	FS_CONTEXT_AWAITING_MOUNT,	/* Superblock created, awaiting fsmount() */
+	FS_CONTEXT_AWAITING_RECONF,	/* Awaiting initialisation for reconfiguration */
+	FS_CONTEXT_RECONF_PARAMS,	/* Loading params for reconfiguration */
+	FS_CONTEXT_RECONFIGURING,	/* Reconfiguring the superblock */
+	FS_CONTEXT_FAILED,		/* Failed to correctly transition a context */
+};
+
 /*
  * Type of parameter value.
  */

@@ -77,6 +91,7 @@ struct fs_parameter {
  */
 struct fs_context {
 	const struct fs_context_operations *ops;
+	struct mutex		uapi_mutex;	/* Userspace access mutex */
 	struct file_system_type	*fs_type;
 	void			*fs_private;	/* The filesystem's context */
 	struct dentry		*root;		/* The root and superblock */

@@ -91,6 +106,7 @@ struct fs_context {
 	unsigned int		sb_flags_mask;	/* Superblock flags that were changed */
 	unsigned int		lsm_flags;	/* Information flags from the fs to the LSM */
 	enum fs_context_purpose	purpose:8;
+	enum fs_context_phase	phase:8;	/* The phase the context is in */
 	bool			sloppy:1;	/* T if unrecognised options are okay */
 	bool			silent:1;	/* T if "o silent" specified */
 	bool			need_free:1;	/* Need to call ops->free() */

@@ -136,6 +152,8 @@ extern int vfs_get_super(struct fs_context *fc,
 			 int (*fill_super)(struct super_block *sb,
 					   struct fs_context *fc));
 
+extern const struct file_operations fscontext_fops;
+
 #define logfc(FC, FMT, ...) pr_notice(FMT, ## __VA_ARGS__)
 
 /**

@@ -910,6 +910,7 @@ asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
 asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
 			       int to_dfd, const char __user *to_path,
 			       unsigned int ms_flags);
+asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags);
 
 /*
  * Architecture-specific system calls

@@ -344,4 +344,9 @@ typedef int __bitwise __kernel_rwf_t;
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
 			 RWF_APPEND)
 
+/*
+ * Flags for fsopen() and co.
+ */
+#define FSOPEN_CLOEXEC		0x00000001
+
 #endif /* _UAPI_LINUX_FS_H */

@@ -401,3 +401,4 @@
 387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
 388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
 389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen
+390	i386	fsconfig		sys_fsconfig			__ia32_sys_fsconfig

@@ -346,6 +346,7 @@
 335	common	open_tree		__x64_sys_open_tree
 336	common	move_mount		__x64_sys_move_mount
 337	common	fsopen			__x64_sys_fsopen
+338	common	fsconfig		__x64_sys_fsconfig
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -10,6 +10,7 @@
  */
 
 #include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/syscalls.h>

@@ -17,6 +18,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/namei.h>
 #include <linux/file.h>
+#include "internal.h"
 #include "mount.h"
 
 /*

@@ -152,3 +154,356 @@ SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
 	put_fs_context(fc);
 	return ret;
 }
+
+/*
+ * Check the state and apply the configuration.  Note that this function is
+ * allowed to 'steal' the value by setting param->xxx to NULL before returning.
+ */
+static int vfs_fsconfig(struct fs_context *fc, struct fs_parameter *param)
+{
+	int ret;
+
+	/* We need to reinitialise the context if we have reconfiguration
+	 * pending after creation or a previous reconfiguration.
+	 */
+	if (fc->phase == FS_CONTEXT_AWAITING_RECONF) {
+		if (fc->fs_type->init_fs_context) {
+			ret = fc->fs_type->init_fs_context(fc, fc->root);
+			if (ret < 0) {
+				fc->phase = FS_CONTEXT_FAILED;
+				return ret;
+			}
+			fc->need_free = true;
+		} else {
+			/* Leave legacy context ops in place */
+		}
+
+		/* Do the security check last because ->init_fs_context may
+		 * change the namespace subscriptions.
+		 */
+		ret = security_fs_context_alloc(fc, fc->root);
+		if (ret < 0) {
+			fc->phase = FS_CONTEXT_FAILED;
+			return ret;
+		}
+
+		fc->phase = FS_CONTEXT_RECONF_PARAMS;
+	}
+
+	if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
+	    fc->phase != FS_CONTEXT_RECONF_PARAMS)
+		return -EBUSY;
+
+	return vfs_parse_fs_param(fc, param);
+}
+
+/*
+ * Reconfigure a superblock.
+ */
+int vfs_reconfigure_sb(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	int ret;
+
+	if (fc->ops->validate) {
+		ret = fc->ops->validate(fc);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = security_fs_context_validate(fc);
+	if (ret)
+		return ret;
+
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	down_write(&sb->s_umount);
+	ret = reconfigure_super(fc);
+	up_write(&sb->s_umount);
+	return ret;
+}
+
+/*
+ * Clean up a context after performing an action on it and put it into a state
+ * from where it can be used to reconfigure a superblock.
+ */
+void vfs_clean_context(struct fs_context *fc)
+{
+	if (fc->ops && fc->ops->free)
+		fc->ops->free(fc);
+	fc->need_free = false;
+	fc->fs_private = NULL;
+	fc->s_fs_info = NULL;
+	fc->sb_flags = 0;
+	fc->sloppy = false;
+	fc->silent = false;
+	security_fs_context_free(fc);
+	fc->security = NULL;
+	kfree(fc->subtype);
+	fc->subtype = NULL;
+	kfree(fc->source);
+	fc->source = NULL;
+
+	fc->purpose = FS_CONTEXT_FOR_RECONFIGURE;
+	fc->phase = FS_CONTEXT_AWAITING_RECONF;
+}
+
+/*
+ * Perform an action on a context.
+ */
+static int vfs_fsconfig_action(struct fs_context *fc, enum fsconfig_command cmd)
+{
+	int ret = -EINVAL;
+
+	switch (cmd) {
+	case FSCONFIG_CMD_CREATE:
+		if (fc->phase != FS_CONTEXT_CREATE_PARAMS)
+			return -EBUSY;
+		fc->phase = FS_CONTEXT_CREATING;
+		ret = vfs_get_tree(fc);
+		if (ret == 0)
+			fc->phase = FS_CONTEXT_AWAITING_MOUNT;
+		else
+			fc->phase = FS_CONTEXT_FAILED;
+		return ret;
+
+	case FSCONFIG_CMD_RECONFIGURE:
+		if (fc->phase == FS_CONTEXT_AWAITING_RECONF) {
+			/* This is probably pointless, since no changes have
+			 * been proposed.
+			 */
+			if (fc->fs_type->init_fs_context) {
+				ret = fc->fs_type->init_fs_context(fc, fc->root);
+				if (ret < 0) {
+					fc->phase = FS_CONTEXT_FAILED;
+					return ret;
+				}
+				fc->need_free = true;
+			}
+			fc->phase = FS_CONTEXT_RECONF_PARAMS;
+		}
+
+		fc->phase = FS_CONTEXT_RECONFIGURING;
+		ret = vfs_reconfigure_sb(fc);
+		if (ret == 0)
+			vfs_clean_context(fc);
+		else
+			fc->phase = FS_CONTEXT_FAILED;
+		return ret;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * sys_fsconfig - Set parameters and trigger actions on a context
+ * @fd: The filesystem context to act upon
+ * @cmd: The action to take
+ * @_key: Where appropriate, the parameter key to set
+ * @_value: Where appropriate, the parameter value to set
+ * @aux: Additional information for the value
+ *
+ * This system call is used to set parameters on a context, including
+ * superblock settings, data source and security labelling.
+ *
+ * Actions include triggering the creation of a superblock and the
+ * reconfiguration of the superblock attached to the specified context.
+ *
+ * When setting a parameter, @cmd indicates the type of value being proposed
+ * and @_key indicates the parameter to be altered.
+ *
+ * @_value and @aux are used to specify the value, should a value be required:
+ *
+ * (*) fsconfig_set_flag: No value is specified.  The parameter must be boolean
+ *     in nature.  The key may be prefixed with "no" to invert the
+ *     setting. @_value must be NULL and @aux must be 0.
+ *
+ * (*) fsconfig_set_string: A string value is specified.  The parameter can be
+ *     expecting boolean, integer, string or take a path.  A conversion to an
+ *     appropriate type will be attempted (which may include looking up as a
+ *     path).  @_value points to a NUL-terminated string and @aux must be 0.
+ *
+ * (*) fsconfig_set_binary: A binary blob is specified.  @_value points to the
+ *     blob and @aux indicates its size.  The parameter must be expecting a
+ *     blob.
+ *
+ * (*) fsconfig_set_path: A non-empty path is specified.  The parameter must be
+ *     expecting a path object.  @_value points to a NUL-terminated string that
+ *     is the path and @aux is a file descriptor at which to start a relative
+ *     lookup or AT_FDCWD.
+ *
+ * (*) fsconfig_set_path_empty: As fsconfig_set_path, but with AT_EMPTY_PATH
+ *     implied.
+ *
+ * (*) fsconfig_set_fd: An open file descriptor is specified.  @_value must be
+ *     NULL and @aux indicates the file descriptor.
+ */
+SYSCALL_DEFINE5(fsconfig,
+		int, fd,
+		unsigned int, cmd,
+		const char __user *, _key,
+		const void __user *, _value,
+		int, aux)
+{
+	struct fs_context *fc;
+	struct fd f;
+	int ret;
+
+	struct fs_parameter param = {
+		.type	= fs_value_is_undefined,
+	};
+
+	if (fd < 0)
+		return -EINVAL;
+
+	switch (cmd) {
+	case FSCONFIG_SET_FLAG:
+		if (!_key || _value || aux)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_STRING:
+		if (!_key || !_value || aux)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_BINARY:
+		if (!_key || !_value || aux <= 0 || aux > 1024 * 1024)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_PATH:
+	case FSCONFIG_SET_PATH_EMPTY:
+		if (!_key || !_value || (aux != AT_FDCWD && aux < 0))
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_FD:
+		if (!_key || _value || aux < 0)
+			return -EINVAL;
+		break;
+	case FSCONFIG_CMD_CREATE:
+	case FSCONFIG_CMD_RECONFIGURE:
+		if (_key || _value || aux)
+			return -EINVAL;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+	ret = -EINVAL;
+	if (f.file->f_op != &fscontext_fops)
+		goto out_f;
+
+	fc = f.file->private_data;
+	if (fc->ops == &legacy_fs_context_ops) {
+		switch (cmd) {
+		case FSCONFIG_SET_BINARY:
+		case FSCONFIG_SET_PATH:
+		case FSCONFIG_SET_PATH_EMPTY:
+		case FSCONFIG_SET_FD:
+			ret = -EOPNOTSUPP;
+			goto out_f;
+		}
+	}
+
+	if (_key) {
+		param.key = strndup_user(_key, 256);
+		if (IS_ERR(param.key)) {
+			ret = PTR_ERR(param.key);
+			goto out_f;
+		}
+	}
+
+	switch (cmd) {
+	case FSCONFIG_SET_STRING:
+		param.type = fs_value_is_string;
+		param.string = strndup_user(_value, 256);
+		if (IS_ERR(param.string)) {
+			ret = PTR_ERR(param.string);
+			goto out_key;
+		}
+		param.size = strlen(param.string);
+		break;
+	case FSCONFIG_SET_BINARY:
+		param.type = fs_value_is_blob;
+		param.size = aux;
+		param.blob = memdup_user_nul(_value, aux);
+		if (IS_ERR(param.blob)) {
+			ret = PTR_ERR(param.blob);
+			goto out_key;
+		}
+		break;
+	case FSCONFIG_SET_PATH:
+		param.type = fs_value_is_filename;
+		param.name = getname_flags(_value, 0, NULL);
+		if (IS_ERR(param.name)) {
+			ret = PTR_ERR(param.name);
+			goto out_key;
+		}
+		param.dirfd = aux;
+		param.size = strlen(param.name->name);
+		break;
+	case FSCONFIG_SET_PATH_EMPTY:
+		param.type = fs_value_is_filename_empty;
+		param.name = getname_flags(_value, LOOKUP_EMPTY, NULL);
+		if (IS_ERR(param.name)) {
+			ret = PTR_ERR(param.name);
+			goto out_key;
+		}
+		param.dirfd = aux;
+		param.size = strlen(param.name->name);
+		break;
+	case FSCONFIG_SET_FD:
+		param.type = fs_value_is_file;
+		ret = -EBADF;
+		param.file = fget(aux);
+		if (!param.file)
+			goto out_key;
+		break;
+	default:
+		break;
+	}
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret == 0) {
+		switch (cmd) {
+		case FSCONFIG_CMD_CREATE:
+		case FSCONFIG_CMD_RECONFIGURE:
+			ret = vfs_fsconfig_action(fc, cmd);
+			break;
+		default:
+			ret = vfs_fsconfig(fc, &param);
+			break;
+		}
+		mutex_unlock(&fc->uapi_mutex);
+	}
+
+	/* Clean up the our record of any value that we obtained from
+	 * userspace.  Note that the value may have been stolen by the LSM or
+	 * filesystem, in which case the value pointer will have been cleared.
+	 */
+	switch (cmd) {
+	case FSCONFIG_SET_STRING:
+	case FSCONFIG_SET_BINARY:
+		kfree(param.string);
+		break;
+	case FSCONFIG_SET_PATH:
+	case FSCONFIG_SET_PATH_EMPTY:
+		if (param.name)
+			putname(param.name);
+		break;
+	case FSCONFIG_SET_FD:
+		if (param.file)
+			fput(param.file);
+		break;
+	default:
+		break;
+	}
+out_key:
+	kfree(param.key);
+out_f:
+	fdput(f);
+	return ret;
+}