Merge branch 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull mount ABI updates from Al Viro:
 "The syscalls themselves, finally.

  That's not all there is to that stuff, but switching individual
  filesystems to new methods is fortunately independent from everything
  else, so e.g. NFS series can go through NFS tree, etc.

  As those conversions get done, we'll be finally able to get rid of a
  bunch of duplication in fs/super.c introduced in the beginning of the
  entire thing. I expect that to be finished in the next window..."

* 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  vfs: Add a sample program for the new mount API
  vfs: syscall: Add fspick() to select a superblock for reconfiguration
  vfs: syscall: Add fsmount() to create a mount for a superblock
  vfs: syscall: Add fsconfig() for configuring and managing a context
  vfs: Implement logging through fs_context
  vfs: syscall: Add fsopen() to prepare for superblock creation
  Make anon_inodes unconditional
  teach move_mount(2) to work with OPEN_TREE_CLONE
  vfs: syscall: Add move_mount(2) to move mounts around
  vfs: syscall: Add open_tree(2) to reference or clone a mount

arch/x86/entry/syscalls/syscall_32.tbl

@@ -398,7 +398,12 @@
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
-# don't use numbers 387 through 392, add new calls at the end
+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
+391	i386	fsmount			sys_fsmount			__ia32_sys_fsmount
+392	i386	fspick			sys_fspick			__ia32_sys_fspick
 393	i386	semget			sys_semget    			__ia32_sys_semget
 394	i386	semctl			sys_semctl    			__ia32_compat_sys_semctl
 395	i386	shmget			sys_shmget    			__ia32_sys_shmget

arch/x86/entry/syscalls/syscall_64.tbl

@@ -343,6 +343,12 @@
 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
+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
+340	common	fspick			__x64_sys_fspick
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal

fs/Makefile

@@ -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_types.o fs_context.o fs_parser.o
+		fs_types.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

fs/file_table.c

@@ -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);

fs/fs_context.c

@@ -11,6 +11,7 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/fs.h>
@@ -23,6 +24,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <net/net_namespace.h>
+#include <asm/sections.h>
 #include "mount.h"
 #include "internal.h"
 
@@ -271,6 +273,8 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type,
 	fc->cred	= get_current_cred();
 	fc->net_ns	= get_net(current->nsproxy->net_ns);
 
+	mutex_init(&fc->uapi_mutex);
+
 	switch (purpose) {
 	case FS_CONTEXT_FOR_MOUNT:
 		fc->user_ns = get_user_ns(fc->cred->user_ns);
@@ -353,6 +357,8 @@ 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;
@@ -361,6 +367,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc)
 	get_net(fc->net_ns);
 	get_user_ns(fc->user_ns);
 	get_cred(fc->cred);
+	if (fc->log)
+		refcount_inc(&fc->log->usage);
 
 	/* Can't call put until we've called ->dup */
 	ret = fc->ops->dup(fc, src_fc);
@@ -378,7 +386,6 @@ err_fc:
 }
 EXPORT_SYMBOL(vfs_dup_fs_context);
 
-#ifdef CONFIG_PRINTK
 /**
  * logfc - Log a message to a filesystem context
  * @fc: The filesystem context to log to.
@@ -386,27 +393,100 @@ EXPORT_SYMBOL(vfs_dup_fs_context);
  */
 void logfc(struct fs_context *fc, const char *fmt, ...)
 {
+	static const char store_failure[] = "OOM: Can't store error string";
+	struct fc_log *log = fc ? fc->log : NULL;
+	const char *p;
 	va_list va;
+	char *q;
+	u8 freeable;
 
 	va_start(va, fmt);
-
+	if (!strchr(fmt, '%')) {
-	switch (fmt[0]) {
+		p = fmt;
-	case 'w':
+		goto unformatted_string;
-		vprintk_emit(0, LOGLEVEL_WARNING, NULL, 0, fmt, va);
+	}
-		break;
+	if (strcmp(fmt, "%s") == 0) {
-	case 'e':
+		p = va_arg(va, const char *);
-		vprintk_emit(0, LOGLEVEL_ERR, NULL, 0, fmt, va);
+		goto unformatted_string;
-		break;
-	default:
-		vprintk_emit(0, LOGLEVEL_NOTICE, NULL, 0, fmt, va);
-		break;
 	}
 
-	pr_cont("\n");
+	q = kvasprintf(GFP_KERNEL, fmt, va);
+copied_string:
+	if (!q)
+		goto store_failure;
+	freeable = 1;
+	goto store_string;
+
+unformatted_string:
+	if ((unsigned long)p >= (unsigned long)__start_rodata &&
+	    (unsigned long)p <  (unsigned long)__end_rodata)
+		goto const_string;
+	if (log && within_module_core((unsigned long)p, log->owner))
+		goto const_string;
+	q = kstrdup(p, GFP_KERNEL);
+	goto copied_string;
+
+store_failure:
+	p = store_failure;
+const_string:
+	q = (char *)p;
+	freeable = 0;
+store_string:
+	if (!log) {
+		switch (fmt[0]) {
+		case 'w':
+			printk(KERN_WARNING "%s\n", q + 2);
+			break;
+		case 'e':
+			printk(KERN_ERR "%s\n", q + 2);
+			break;
+		default:
+			printk(KERN_NOTICE "%s\n", q + 2);
+			break;
+		}
+		if (freeable)
+			kfree(q);
+	} else {
+		unsigned int logsize = ARRAY_SIZE(log->buffer);
+		u8 index;
+
+		index = log->head & (logsize - 1);
+		BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) ||
+			     sizeof(log->tail) != sizeof(u8));
+		if ((u8)(log->head - log->tail) == logsize) {
+			/* The buffer is full, discard the oldest message */
+			if (log->need_free & (1 << index))
+				kfree(log->buffer[index]);
+			log->tail++;
+		}
+
+		log->buffer[index] = q;
+		log->need_free &= ~(1 << index);
+		log->need_free |= freeable << index;
+		log->head++;
+	}
 	va_end(va);
 }
 EXPORT_SYMBOL(logfc);
-#endif
+
+/*
+ * Free a logging structure.
+ */
+static void put_fc_log(struct fs_context *fc)
+{
+	struct fc_log *log = fc->log;
+	int i;
+
+	if (log) {
+		if (refcount_dec_and_test(&log->usage)) {
+			fc->log = NULL;
+			for (i = 0; i <= 7; i++)
+				if (log->need_free & (1 << i))
+					kfree(log->buffer[i]);
+			kfree(log);
+		}
+	}
+}
 
 /**
  * put_fs_context - Dispose of a superblock configuration context.
@@ -431,6 +511,7 @@ void put_fs_context(struct fs_context *fc)
 	put_user_ns(fc->user_ns);
 	put_cred(fc->cred);
 	kfree(fc->subtype);
+	put_fc_log(fc);
 	put_filesystem(fc->fs_type);
 	kfree(fc->source);
 	kfree(fc);
@@ -640,3 +721,54 @@ int parse_monolithic_mount_data(struct fs_context *fc, void *data)
 
 	return monolithic_mount_data(fc, data);
 }
+
+/*
+ * 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.
+ *
+ * Note that here we do only the parts that can't fail; the rest is in
+ * finish_clean_context() below and in between those fs_context is marked
+ * FS_CONTEXT_AWAITING_RECONF.  The reason for splitup is that after
+ * successful mount or remount we need to report success to userland.
+ * Trying to do full reinit (for the sake of possible subsequent remount)
+ * and failing to allocate memory would've put us into a nasty situation.
+ * So here we only discard the old state and reinitialization is left
+ * until we actually try to reconfigure.
+ */
+void vfs_clean_context(struct fs_context *fc)
+{
+	if (fc->need_free && 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;
+	security_free_mnt_opts(&fc->security);
+	kfree(fc->subtype);
+	fc->subtype = NULL;
+	kfree(fc->source);
+	fc->source = NULL;
+
+	fc->purpose = FS_CONTEXT_FOR_RECONFIGURE;
+	fc->phase = FS_CONTEXT_AWAITING_RECONF;
+}
+
+int finish_clean_context(struct fs_context *fc)
+{
+	int error;
+
+	if (fc->phase != FS_CONTEXT_AWAITING_RECONF)
+		return 0;
+
+	if (fc->fs_type->init_fs_context)
+		error = fc->fs_type->init_fs_context(fc);
+	else
+		error = legacy_init_fs_context(fc);
+	if (unlikely(error)) {
+		fc->phase = FS_CONTEXT_FAILED;
+		return error;
+	}
+	fc->need_free = true;
+	fc->phase = FS_CONTEXT_RECONF_PARAMS;
+	return 0;
+}

fs/fsopen.c

@@ -0,0 +1,477 @@
+/* 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/fs_parser.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 <uapi/linux/mount.h>
+#include "internal.h"
+#include "mount.h"
+
+/*
+ * Allow the user to read back any error, warning or informational messages.
+ */
+static ssize_t fscontext_read(struct file *file,
+			      char __user *_buf, size_t len, loff_t *pos)
+{
+	struct fs_context *fc = file->private_data;
+	struct fc_log *log = fc->log;
+	unsigned int logsize = ARRAY_SIZE(log->buffer);
+	ssize_t ret;
+	char *p;
+	bool need_free;
+	int index, n;
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret < 0)
+		return ret;
+
+	if (log->head == log->tail) {
+		mutex_unlock(&fc->uapi_mutex);
+		return -ENODATA;
+	}
+
+	index = log->tail & (logsize - 1);
+	p = log->buffer[index];
+	need_free = log->need_free & (1 << index);
+	log->buffer[index] = NULL;
+	log->need_free &= ~(1 << index);
+	log->tail++;
+	mutex_unlock(&fc->uapi_mutex);
+
+	ret = -EMSGSIZE;
+	n = strlen(p);
+	if (n > len)
+		goto err_free;
+	ret = -EFAULT;
+	if (copy_to_user(_buf, p, n) != 0)
+		goto err_free;
+	ret = n;
+
+err_free:
+	if (need_free)
+		kfree(p);
+	return ret;
+}
+
+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 = {
+	.read		= fscontext_read,
+	.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;
+}
+
+static int fscontext_alloc_log(struct fs_context *fc)
+{
+	fc->log = kzalloc(sizeof(*fc->log), GFP_KERNEL);
+	if (!fc->log)
+		return -ENOMEM;
+	refcount_set(&fc->log->usage, 1);
+	fc->log->owner = fc->fs_type->owner;
+	return 0;
+}
+
+/*
+ * 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;
+	int ret;
+
+	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 = fs_context_for_mount(fs_type, 0);
+	put_filesystem(fs_type);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	fc->phase = FS_CONTEXT_CREATE_PARAMS;
+
+	ret = fscontext_alloc_log(fc);
+	if (ret < 0)
+		goto err_fc;
+
+	return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0);
+
+err_fc:
+	put_fs_context(fc);
+	return ret;
+}
+
+/*
+ * Pick a superblock into a context for reconfiguration.
+ */
+SYSCALL_DEFINE3(fspick, int, dfd, const char __user *, path, unsigned int, flags)
+{
+	struct fs_context *fc;
+	struct path target;
+	unsigned int lookup_flags;
+	int ret;
+
+	if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if ((flags & ~(FSPICK_CLOEXEC |
+		       FSPICK_SYMLINK_NOFOLLOW |
+		       FSPICK_NO_AUTOMOUNT |
+		       FSPICK_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	if (flags & FSPICK_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & FSPICK_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & FSPICK_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	ret = user_path_at(dfd, path, lookup_flags, &target);
+	if (ret < 0)
+		goto err;
+
+	ret = -EINVAL;
+	if (target.mnt->mnt_root != target.dentry)
+		goto err_path;
+
+	fc = fs_context_for_reconfigure(target.dentry, 0, 0);
+	if (IS_ERR(fc)) {
+		ret = PTR_ERR(fc);
+		goto err_path;
+	}
+
+	fc->phase = FS_CONTEXT_RECONF_PARAMS;
+
+	ret = fscontext_alloc_log(fc);
+	if (ret < 0)
+		goto err_fc;
+
+	path_put(&target);
+	return fscontext_create_fd(fc, flags & FSPICK_CLOEXEC ? O_CLOEXEC : 0);
+
+err_fc:
+	put_fs_context(fc);
+err_path:
+	path_put(&target);
+err:
+	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_locked(struct fs_context *fc, int cmd,
+			       struct fs_parameter *param)
+{
+	struct super_block *sb;
+	int ret;
+
+	ret = finish_clean_context(fc);
+	if (ret)
+		return ret;
+	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)
+			break;
+		sb = fc->root->d_sb;
+		ret = security_sb_kern_mount(sb);
+		if (unlikely(ret)) {
+			fc_drop_locked(fc);
+			break;
+		}
+		up_write(&sb->s_umount);
+		fc->phase = FS_CONTEXT_AWAITING_MOUNT;
+		return 0;
+	case FSCONFIG_CMD_RECONFIGURE:
+		if (fc->phase != FS_CONTEXT_RECONF_PARAMS)
+			return -EBUSY;
+		fc->phase = FS_CONTEXT_RECONFIGURING;
+		sb = fc->root->d_sb;
+		if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			break;
+		}
+		down_write(&sb->s_umount);
+		ret = reconfigure_super(fc);
+		up_write(&sb->s_umount);
+		if (ret)
+			break;
+		vfs_clean_context(fc);
+		return 0;
+	default:
+		if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
+		    fc->phase != FS_CONTEXT_RECONF_PARAMS)
+			return -EBUSY;
+
+		return vfs_parse_fs_param(fc, param);
+	}
+	fc->phase = FS_CONTEXT_FAILED;
+	return ret;
+}
+
+/**
+ * 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_FLAG:
+		param.type = fs_value_is_flag;
+		break;
+	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) {
+		ret = vfs_fsconfig_locked(fc, cmd, &param);
+		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;
+}

fs/internal.h

@@ -55,8 +55,11 @@ extern void __init chrdev_init(void);
 /*
  * fs_context.c
  */
+extern const struct fs_context_operations legacy_fs_context_ops;
 extern int parse_monolithic_mount_data(struct fs_context *, void *);
 extern void fc_drop_locked(struct fs_context *);
+extern void vfs_clean_context(struct fs_context *fc);
+extern int finish_clean_context(struct fs_context *fc);
 
 /*
  * namei.c
@@ -92,6 +95,7 @@ extern void __init mnt_init(void);
 extern int __mnt_want_write_file(struct file *);
 extern void __mnt_drop_write_file(struct file *);
 
+extern void dissolve_on_fput(struct vfsmount *);
 /*
  * fs_struct.c
  */

fs/namespace.c

@@ -20,6 +20,7 @@
 #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>
@@ -1832,6 +1833,27 @@ struct vfsmount *collect_mounts(const struct path *path)
 	return &tree->mnt;
 }
 
+static void free_mnt_ns(struct mnt_namespace *);
+static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
+
+void dissolve_on_fput(struct vfsmount *mnt)
+{
+	struct mnt_namespace *ns;
+	namespace_lock();
+	lock_mount_hash();
+	ns = real_mount(mnt)->mnt_ns;
+	if (ns) {
+		if (is_anon_ns(ns))
+			umount_tree(real_mount(mnt), UMOUNT_CONNECTED);
+		else
+			ns = NULL;
+	}
+	unlock_mount_hash();
+	namespace_unlock();
+	if (ns)
+		free_mnt_ns(ns);
+}
+
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
@@ -2065,6 +2087,10 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		attach_mnt(source_mnt, dest_mnt, dest_mp);
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
+		if (source_mnt->mnt_ns) {
+			/* move from anon - the caller will destroy */
+			list_del_init(&source_mnt->mnt_ns->list);
+		}
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
 		commit_tree(source_mnt);
 	}
@@ -2222,6 +2248,30 @@ 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.
  */
@@ -2229,7 +2279,7 @@ 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)
@@ -2243,38 +2293,21 @@ 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)
+	mnt = __do_loopback(&old_path, recurse);
-		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);
-
 	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();
@@ -2288,6 +2321,96 @@ out:
 	return err;
 }
 
+static struct file *open_detached_copy(struct path *path, bool recursive)
+{
+	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
+	struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true);
+	struct mount *mnt, *p;
+	struct file *file;
+
+	if (IS_ERR(ns))
+		return ERR_CAST(ns);
+
+	namespace_lock();
+	mnt = __do_loopback(path, recursive);
+	if (IS_ERR(mnt)) {
+		namespace_unlock();
+		free_mnt_ns(ns);
+		return ERR_CAST(mnt);
+	}
+
+	lock_mount_hash();
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		p->mnt_ns = ns;
+		ns->mounts++;
+	}
+	ns->root = mnt;
+	list_add_tail(&ns->list, &mnt->mnt_list);
+	mntget(&mnt->mnt);
+	unlock_mount_hash();
+	namespace_unlock();
+
+	mntput(path->mnt);
+	path->mnt = &mnt->mnt;
+	file = dentry_open(path, O_PATH, current_cred());
+	if (IS_ERR(file))
+		dissolve_on_fput(path->mnt);
+	else
+		file->f_mode |= FMODE_NEED_UNMOUNT;
+	return file;
+}
+
+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 (unlikely(error)) {
+		file = ERR_PTR(error);
+	} else {
+		if (detached)
+			file = open_detached_copy(&path, flags & AT_RECURSIVE);
+		else
+			file = dentry_open(&path, O_PATH, current_cred());
+		path_put(&path);
+	}
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+	fd_install(fd, file);
+	return fd;
+}
+
 /*
  * Don't allow locked mount flags to be cleared.
  *
@@ -2426,72 +2549,117 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
-static int do_move_mount(struct path *path, const char *old_name)
+/*
+ * Check that there aren't references to earlier/same mount namespaces in the
+ * specified subtree.  Such references can act as pins for mount namespaces
+ * that aren't checked by the mount-cycle checking code, thereby allowing
+ * cycles to be made.
+ */
+static bool check_for_nsfs_mounts(struct mount *subtree)
 {
-	struct path old_path, parent_path;
+	struct mount *p;
+	bool ret = false;
+
+	lock_mount_hash();
+	for (p = subtree; p; p = next_mnt(p, subtree))
+		if (mnt_ns_loop(p->mnt.mnt_root))
+			goto out;
+
+	ret = true;
+out:
+	unlock_mount_hash();
+	return ret;
+}
+
+static int do_move_mount(struct path *old_path, struct path *new_path)
+{
+	struct path parent_path = {.mnt = NULL, .dentry = NULL};
+	struct mnt_namespace *ns;
 	struct mount *p;
 	struct mount *old;
 	struct mountpoint *mp;
 	int err;
-	if (!old_name || !*old_name)
+	bool attached;
-		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))
+		return PTR_ERR(mp);
+
+	old = real_mount(old_path->mnt);
+	p = real_mount(new_path->mnt);
+	attached = mnt_has_parent(old);
+	ns = old->mnt_ns;
+
+	err = -EINVAL;
+	/* The mountpoint must be in our namespace. */
+	if (!check_mnt(p))
 		goto out;
 
-	old = real_mount(old_path.mnt);
+	/* The thing moved should be either ours or completely unattached. */
-	p = real_mount(path->mnt);
+	if (attached && !check_mnt(old))
+		goto out;
 
-	err = -EINVAL;
+	if (!attached && !is_anon_ns(ns))
-	if (!check_mnt(p) || !check_mnt(old))
+		goto out;
-		goto out1;
 
 	if (old->mnt.mnt_flags & MNT_LOCKED)
-		goto out1;
+		goto out;
 
-	err = -EINVAL;
+	if (old_path->dentry != old_path->mnt->mnt_root)
-	if (old_path.dentry != old_path.mnt->mnt_root)
+		goto out;
-		goto out1;
 
-	if (!mnt_has_parent(old))
+	if (d_is_dir(new_path->dentry) !=
-		goto out1;
+	    d_is_dir(old_path->dentry))
-
+		goto out;
-	if (d_is_dir(path->dentry) !=
-	      d_is_dir(old_path.dentry))
-		goto out1;
 	/*
 	 * Don't move a mount residing in a shared parent.
 	 */
-	if (IS_MNT_SHARED(old->mnt_parent))
+	if (attached && IS_MNT_SHARED(old->mnt_parent))
-		goto out1;
+		goto out;
 	/*
 	 * Don't move a mount tree containing unbindable mounts to a destination
 	 * mount which is shared.
 	 */
 	if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
-		goto out1;
+		goto out;
 	err = -ELOOP;
+	if (!check_for_nsfs_mounts(old))
+		goto out;
 	for (; mnt_has_parent(p); p = p->mnt_parent)
 		if (p == old)
-			goto out1;
+			goto out;
 
-	err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path);
+	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp,
+				   attached ? &parent_path : NULL);
 	if (err)
-		goto out1;
+		goto out;
 
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
-out1:
-	unlock_mount(mp);
 out:
-	if (!err)
+	unlock_mount(mp);
+	if (!err) {
 		path_put(&parent_path);
+		if (!attached)
+			free_mnt_ns(ns);
+	}
+	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;
 }
@@ -2937,7 +3105,7 @@ 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);
@@ -3165,6 +3333,203 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	return ksys_mount(dev_name, dir_name, type, flags, data);
 }
 
+/*
+ * 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, attr_flags)
+{
+	struct mnt_namespace *ns;
+	struct fs_context *fc;
+	struct file *file;
+	struct path newmount;
+	struct mount *mnt;
+	struct fd f;
+	unsigned int mnt_flags = 0;
+	long ret;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if ((flags & ~(FSMOUNT_CLOEXEC)) != 0)
+		return -EINVAL;
+
+	if (attr_flags & ~(MOUNT_ATTR_RDONLY |
+			   MOUNT_ATTR_NOSUID |
+			   MOUNT_ATTR_NODEV |
+			   MOUNT_ATTR_NOEXEC |
+			   MOUNT_ATTR__ATIME |
+			   MOUNT_ATTR_NODIRATIME))
+		return -EINVAL;
+
+	if (attr_flags & MOUNT_ATTR_RDONLY)
+		mnt_flags |= MNT_READONLY;
+	if (attr_flags & MOUNT_ATTR_NOSUID)
+		mnt_flags |= MNT_NOSUID;
+	if (attr_flags & MOUNT_ATTR_NODEV)
+		mnt_flags |= MNT_NODEV;
+	if (attr_flags & MOUNT_ATTR_NOEXEC)
+		mnt_flags |= MNT_NOEXEC;
+	if (attr_flags & MOUNT_ATTR_NODIRATIME)
+		mnt_flags |= MNT_NODIRATIME;
+
+	switch (attr_flags & MOUNT_ATTR__ATIME) {
+	case MOUNT_ATTR_STRICTATIME:
+		break;
+	case MOUNT_ATTR_NOATIME:
+		mnt_flags |= MNT_NOATIME;
+		break;
+	case MOUNT_ATTR_RELATIME:
+		mnt_flags |= MNT_RELATIME;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	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;
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret < 0)
+		goto err_fsfd;
+
+	/* There must be a valid superblock or we can't mount it */
+	ret = -EINVAL;
+	if (!fc->root)
+		goto err_unlock;
+
+	ret = -EPERM;
+	if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
+		pr_warn("VFS: Mount too revealing\n");
+		goto err_unlock;
+	}
+
+	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);
+	if (IS_ERR(newmount.mnt)) {
+		ret = PTR_ERR(newmount.mnt);
+		goto err_unlock;
+	}
+	newmount.dentry = dget(fc->root);
+	newmount.mnt->mnt_flags = mnt_flags;
+
+	/* 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);
+
+	ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true);
+	if (IS_ERR(ns)) {
+		ret = PTR_ERR(ns);
+		goto err_path;
+	}
+	mnt = real_mount(newmount.mnt);
+	mnt->mnt_ns = ns;
+	ns->root = mnt;
+	ns->mounts = 1;
+	list_add(&mnt->mnt_list, &ns->list);
+
+	/* 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)) {
+		dissolve_on_fput(newmount.mnt);
+		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.
+ */
+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
  *

include/linux/fs.h

@@ -165,10 +165,13 @@ 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

include/linux/fs_context.h

@@ -13,8 +13,10 @@
 #define _LINUX_FS_CONTEXT_H
 
 #include <linux/kernel.h>
+#include <linux/refcount.h>
 #include <linux/errno.h>
 #include <linux/security.h>
+#include <linux/mutex.h>
 
 struct cred;
 struct dentry;
@@ -34,6 +36,19 @@ enum fs_context_purpose {
 	FS_CONTEXT_FOR_RECONFIGURE,	/* Superblock reconfiguration (remount) */
 };
 
+/*
+ * 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.
  */
@@ -74,12 +89,14 @@ 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 */
 	struct user_namespace	*user_ns;	/* The user namespace for this mount */
 	struct net		*net_ns;	/* The network namespace for this mount */
 	const struct cred	*cred;		/* The mounter's credentials */
+	struct fc_log		*log;		/* Logging buffer */
 	const char		*source;	/* The source name (eg. dev path) */
 	const char		*subtype;	/* The subtype to set on the superblock */
 	void			*security;	/* Linux S&M options */
@@ -88,6 +105,7 @@ 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			need_free:1;	/* Need to call ops->free() */
 	bool			global:1;	/* Goes into &init_user_ns */
 };
@@ -135,15 +153,21 @@ extern int vfs_get_super(struct fs_context *fc,
 
 extern const struct file_operations fscontext_fops;
 
-#ifdef CONFIG_PRINTK
+/*
+ * Mount error, warning and informational message logging.  This structure is
+ * shareable between a mount and a subordinate mount.
+ */
+struct fc_log {
+	refcount_t	usage;
+	u8		head;		/* Insertion index in buffer[] */
+	u8		tail;		/* Removal index in buffer[] */
+	u8		need_free;	/* Mask of kfree'able items in buffer[] */
+	struct module	*owner;		/* Owner module for strings that don't then need freeing */
+	char		*buffer[8];
+};
+
 extern __attribute__((format(printf, 2, 3)))
 void logfc(struct fs_context *fc, const char *fmt, ...);
-#else
-static inline __attribute__((format(printf, 2, 3)))
-void logfc(struct fs_context *fc, const char *fmt, ...)
-{
-}
-#endif
 
 /**
  * infof - Store supplementary informational message

include/linux/lsm_hooks.h

@@ -159,6 +159,10 @@
  *	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.
@@ -1502,6 +1506,7 @@ union security_list_options {
 					unsigned long *set_kern_flags);
 	int (*sb_add_mnt_opt)(const char *option, const char *val, int len,
 			      void **mnt_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);
@@ -1839,6 +1844,7 @@ struct security_hook_heads {
 	struct hlist_head sb_set_mnt_opts;
 	struct hlist_head sb_clone_mnt_opts;
 	struct hlist_head sb_add_mnt_opt;
+	struct hlist_head move_mount;
 	struct hlist_head dentry_init_security;
 	struct hlist_head dentry_create_files_as;
 #ifdef CONFIG_SECURITY_PATH

include/linux/module.h

@@ -709,6 +709,12 @@ static inline bool is_module_text_address(unsigned long addr)
 	return false;
 }
 
+static inline bool within_module_core(unsigned long addr,
+				      const struct module *mod)
+{
+	return false;
+}
+
 /* Get/put a kernel symbol (calls should be symmetric) */
 #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
 #define symbol_put(x) do { } while (0)

include/linux/security.h

@@ -251,6 +251,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb,
 				unsigned long *set_kern_flags);
 int security_add_mnt_opt(const char *option, const char *val,
 				int len, void **mnt_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);
@@ -614,6 +615,12 @@ static inline int security_add_mnt_opt(const char *option, const char *val,
 	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;

include/linux/syscalls.h

@@ -985,6 +985,15 @@ 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);
+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);
+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);
+asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags);
 asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);

include/uapi/linux/fcntl.h

@@ -91,5 +91,7 @@
 #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 */

include/uapi/linux/mount.h

@@ -55,4 +55,66 @@
 #define MS_MGC_VAL 0xC0ED0000
 #define MS_MGC_MSK 0xffff0000
 
+/*
+ * 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() */
+
+/*
+ * 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
+
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC		0x00000001
+
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC		0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW	0x00000002
+#define FSPICK_NO_AUTOMOUNT	0x00000004
+#define FSPICK_EMPTY_PATH	0x00000008
+
+/*
+ * The type of fsconfig() call made.
+ */
+enum fsconfig_command {
+	FSCONFIG_SET_FLAG	= 0,	/* Set parameter, supplying no value */
+	FSCONFIG_SET_STRING	= 1,	/* Set parameter, supplying a string value */
+	FSCONFIG_SET_BINARY	= 2,	/* Set parameter, supplying a binary blob value */
+	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
+	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
+	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
+	FSCONFIG_CMD_CREATE	= 6,	/* Invoke superblock creation */
+	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC		0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+
 #endif /* _UAPI_LINUX_MOUNT_H */

samples/Kconfig

@@ -154,10 +154,11 @@ config SAMPLE_ANDROID_BINDERFS
 	  Builds a sample program to illustrate the use of the Android binderfs
 	  filesystem.
 
-config SAMPLE_STATX
+config SAMPLE_VFS
-	bool "Build example extended-stat using code"
+	bool "Build example programs that use new VFS system calls"
-	depends on BROKEN
 	help
-	  Build example userspace program to use the new extended-stat syscall.
+	  Build example userspace programs that use new VFS system calls such
+	  as mount API and statx().  Note that this is restricted to the x86
+	  arch whilst it accesses system calls that aren't yet in all arches.
 
 endif # SAMPLES

samples/Makefile

@@ -3,4 +3,4 @@
 obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ livepatch/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
 			   configfs/ connector/ v4l/ trace_printk/ \
-			   vfio-mdev/ statx/ qmi/ binderfs/ pidfd/
+			   vfio-mdev/ vfs/ qmi/ binderfs/ pidfd/

samples/vfs/Makefile

@@ -1,7 +1,10 @@
 # List of programs to build
-hostprogs-$(CONFIG_SAMPLE_STATX) := test-statx
+hostprogs-$(CONFIG_SAMPLE_VFS) := \
+	test-fsmount \
+	test-statx
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
 
+HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include
 HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include

samples/vfs/test-fsmount.c

@@ -0,0 +1,133 @@
+/* fd-based mount test.
+ *
+ * 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 <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <linux/mount.h>
+#include <linux/unistd.h>
+
+#define E(x) do { if ((x) == -1) { perror(#x); exit(1); } } while(0)
+
+static void check_messages(int fd)
+{
+	char buf[4096];
+	int err, n;
+
+	err = errno;
+
+	for (;;) {
+		n = read(fd, buf, sizeof(buf));
+		if (n < 0)
+			break;
+		n -= 2;
+
+		switch (buf[0]) {
+		case 'e':
+			fprintf(stderr, "Error: %*.*s\n", n, n, buf + 2);
+			break;
+		case 'w':
+			fprintf(stderr, "Warning: %*.*s\n", n, n, buf + 2);
+			break;
+		case 'i':
+			fprintf(stderr, "Info: %*.*s\n", n, n, buf + 2);
+			break;
+		}
+	}
+
+	errno = err;
+}
+
+static __attribute__((noreturn))
+void mount_error(int fd, const char *s)
+{
+	check_messages(fd);
+	fprintf(stderr, "%s: %m\n", s);
+	exit(1);
+}
+
+/* Hope -1 isn't a syscall */
+#ifndef __NR_fsopen
+#define __NR_fsopen -1
+#endif
+#ifndef __NR_fsmount
+#define __NR_fsmount -1
+#endif
+#ifndef __NR_fsconfig
+#define __NR_fsconfig -1
+#endif
+#ifndef __NR_move_mount
+#define __NR_move_mount -1
+#endif
+
+
+static inline int fsopen(const char *fs_name, unsigned int flags)
+{
+	return syscall(__NR_fsopen, fs_name, flags);
+}
+
+static inline int fsmount(int fsfd, unsigned int flags, unsigned int ms_flags)
+{
+	return syscall(__NR_fsmount, fsfd, flags, ms_flags);
+}
+
+static inline int fsconfig(int fsfd, unsigned int cmd,
+			   const char *key, const void *val, int aux)
+{
+	return syscall(__NR_fsconfig, fsfd, cmd, key, val, aux);
+}
+
+static inline int move_mount(int from_dfd, const char *from_pathname,
+			     int to_dfd, const char *to_pathname,
+			     unsigned int flags)
+{
+	return syscall(__NR_move_mount,
+		       from_dfd, from_pathname,
+		       to_dfd, to_pathname, flags);
+}
+
+#define E_fsconfig(fd, cmd, key, val, aux)				\
+	do {								\
+		if (fsconfig(fd, cmd, key, val, aux) == -1)		\
+			mount_error(fd, key ?: "create");		\
+	} while (0)
+
+int main(int argc, char *argv[])
+{
+	int fsfd, mfd;
+
+	/* Mount a publically available AFS filesystem */
+	fsfd = fsopen("afs", 0);
+	if (fsfd == -1) {
+		perror("fsopen");
+		exit(1);
+	}
+
+	E_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell.", 0);
+	E_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+	mfd = fsmount(fsfd, 0, MOUNT_ATTR_RDONLY);
+	if (mfd < 0)
+		mount_error(fsfd, "fsmount");
+	E(close(fsfd));
+
+	if (move_mount(mfd, "", AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH) < 0) {
+		perror("move_mount");
+		exit(1);
+	}
+
+	E(close(mfd));
+	exit(0);
+}

samples/vfs/test-statx.c

@@ -25,13 +25,21 @@
 #include <sys/types.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
+#define statx foo
+#define statx_timestamp foo_timestamp
 #include <sys/stat.h>
+#undef statx
+#undef statx_timestamp
 
 #define AT_STATX_SYNC_TYPE	0x6000
 #define AT_STATX_SYNC_AS_STAT	0x0000
 #define AT_STATX_FORCE_SYNC	0x2000
 #define AT_STATX_DONT_SYNC	0x4000
 
+#ifndef __NR_statx
+#define __NR_statx -1
+#endif
+
 static __attribute__((unused))
 ssize_t statx(int dfd, const char *filename, unsigned flags,
 	      unsigned int mask, struct statx *buffer)
@@ -157,7 +165,8 @@ static void dump_statx(struct statx *stx)
 			"?dai?c??"	/*  7- 0	0x00000000-000000ff */
 			;
 
-		printf("Attributes: %016llx (", stx->stx_attributes);
+		printf("Attributes: %016llx (",
+		       (unsigned long long)stx->stx_attributes);
 		for (byte = 64 - 8; byte >= 0; byte -= 8) {
 			bits = stx->stx_attributes >> byte;
 			mbits = stx->stx_attributes_mask >> byte;

security/security.c

@@ -866,6 +866,11 @@ int security_add_mnt_opt(const char *option, const char *val, int len,
 }
 EXPORT_SYMBOL(security_add_mnt_opt);
 
+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)
 {
 	int rc = lsm_inode_alloc(inode);