[3/9] VFS: Introduce a mount context

Commit Message

David Howells May 3, 2017, 4:04 p.m. UTC

Introduce a mount context concept.  This is allocated at the beginning of
the mount procedure and into it is placed:

 (1) Filesystem type.

 (2) Namespaces.

 (3) Device name.

 (4) Superblock flags (MS_*) and mount flags (MNT_*).

 (5) Security details.

 (6) Filesystem-specific data, as set by the mount options.

It also gives a place in which to hang an error message for later retrieval
(see the mount-by-fd syscall later in this series).

Rather than calling fs_type->mount(), a mount_context struct is created and
fs_type->fsopen() is called to set it up.  fs_type->mc_size says how much
should be added on to the mount context for the filesystem's use.

A set of operations have to be set by ->fsopen() to provide freeing,
duplication, option parsing, binary data parsing, validation, mounting and
superblock filling.

It should be noted that, whilst this patch adds a lot of lines of code,
there is quite a bit of duplication with existing code that can be
eliminated should all filesystems be converted over.

Signed-off-by: David Howells <[e-mail]>
---

 Documentation/filesystems/mounting.txt |  445 ++++++++++++++++++++++++++++++++
 fs/Makefile                            |    3 
 fs/internal.h                          |    2 
 fs/mount.h                             |    3 
 fs/mount_context.c                     |  343 +++++++++++++++++++++++++
 fs/namespace.c                         |  270 +++++++++++++++++--
 fs/super.c                             |   50 +++-
 include/linux/fs.h                     |   11 +
 include/linux/lsm_hooks.h              |   37 +++
 include/linux/mount.h                  |   67 +++++
 include/linux/security.h               |   29 ++
 security/security.c                    |   32 ++
 security/selinux/hooks.c               |  179 +++++++++++++
 13 files changed, 1435 insertions(+), 36 deletions(-)
 create mode 100644 Documentation/filesystems/mounting.txt
 create mode 100644 fs/mount_context.c


--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Jeff Layton May 3, 2017, 6:13 p.m. UTC | #1

On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> Introduce a mount context concept.  This is allocated at the beginning of
> the mount procedure and into it is placed:
> 
>  (1) Filesystem type.
> 
>  (2) Namespaces.
> 
>  (3) Device name.
> 
>  (4) Superblock flags (MS_*) and mount flags (MNT_*).
> 
>  (5) Security details.
> 
>  (6) Filesystem-specific data, as set by the mount options.
> 
> It also gives a place in which to hang an error message for later retrieval
> (see the mount-by-fd syscall later in this series).
> 
> Rather than calling fs_type->mount(), a mount_context struct is created and
> fs_type->fsopen() is called to set it up.  fs_type->mc_size says how much
> should be added on to the mount context for the filesystem's use.
> 
> A set of operations have to be set by ->fsopen() to provide freeing,
> duplication, option parsing, binary data parsing, validation, mounting and
> superblock filling.
> 
> It should be noted that, whilst this patch adds a lot of lines of code,
> there is quite a bit of duplication with existing code that can be
> eliminated should all filesystems be converted over.
> 
> Signed-off-by: David Howells <[e-mail]>
> ---
> 
>  Documentation/filesystems/mounting.txt |  445 ++++++++++++++++++++++++++++++++
>  fs/Makefile                            |    3 
>  fs/internal.h                          |    2 
>  fs/mount.h                             |    3 
>  fs/mount_context.c                     |  343 +++++++++++++++++++++++++
>  fs/namespace.c                         |  270 +++++++++++++++++--
>  fs/super.c                             |   50 +++-
>  include/linux/fs.h                     |   11 +
>  include/linux/lsm_hooks.h              |   37 +++
>  include/linux/mount.h                  |   67 +++++
>  include/linux/security.h               |   29 ++
>  security/security.c                    |   32 ++
>  security/selinux/hooks.c               |  179 +++++++++++++
>  13 files changed, 1435 insertions(+), 36 deletions(-)
>  create mode 100644 Documentation/filesystems/mounting.txt
>  create mode 100644 fs/mount_context.c
> 
> diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
> new file mode 100644
> index 000000000000..a942ccd08376
> --- /dev/null
> +++ b/Documentation/filesystems/mounting.txt
> @@ -0,0 +1,445 @@
> +			      ===================
> +			      FILESYSTEM MOUNTING
> +			      ===================
> +
> +CONTENTS
> +
> + (1) Overview.
> +
> + (2) The mount context.
> +
> + (3) The mount context operations.
> +
> + (4) Mount context security.
> +
> + (5) VFS mount context operations.
> +
> +
> +========
> +OVERVIEW
> +========
> +
> +The creation of new mounts is now to be done in a multistep process:
> +
> + (1) Create a mount context.
> +
> + (2) Parse the options and attach them to the mount context.  Options may be
> +     passed individually from userspace.
> +
> + (3) Validate and pre-process the mount context.
> +
> + (4) Perform the mount.
> +
> + (5) Return an error message attached to the mount context.
> +
> + (6) Destroy the mount context.
> +
> +To support this, the file_system_type struct gains two new fields:
> +
> +	unsigned short mc_size;
> +
> +which indicates how much space the filesystem would like tacked onto the end of
> +the mount_context struct for its own purposes, and:
> +
> +	int (*fsopen)(struct mount_context *mc, struct super_block *src_sb);
> +
> +which is invoked to set up the filesystem-specific parts of a mount context,
> +including the additional space.  The src_sb parameter is used to convey the
> +superblock from which the filesystem may draw extra information (such as
> +namespaces), for submount (MS_SUBMOUNT) or remount (MS_REMOUNT) purposes or it
> +will be NULL.
> +
> +Note that security initialisation is done *after* the filesystem is called so
> +that the namespaces may be adjusted first.
> +
> +And the super_operations struct gains one:
> +
> +	int (*remount_fs_mc) (struct super_block *, struct mount_context *);
> +
> +This shadows the ->remount_fs() operation and takes a prepared mount context
> +instead of the mount flags and data page.  It may modify the ms_flags in the
> +context for the caller to pick up.
> +
> +[NOTE] remount_fs_mc is intended as a replacement for remount_fs.
> +
> +
> +=================
> +THE MOUNT CONTEXT
> +=================
> +
> +The mount process is governed by a mount context.  This is represented by the
> +mount_context structure:
> +
> +	struct mount_context {
> +		const struct mount_context_operations *ops;
> +		struct file_system_type *fs;
> +		struct user_namespace	*user_ns;
> +		struct mnt_namespace	*mnt_ns;
> +		struct pid_namespace	*pid_ns;
> +		struct net		*net_ns;
> +		const struct cred	*cred;
> +		char			*device;
> +		char			*root_path;
> +		void			*security;
> +		const char		*error;
> +		unsigned int		ms_flags;
> +		unsigned int		mnt_flags;
> +		bool			mounted;
> +		bool			sloppy;
> +		bool			silent;
> +		enum mount_type		mount_type : 8;
> +	};
> +
> +When allocated, the mount_context struct is extended by ->mc_size bytes as
> +specified by the specified file_system_type struct.  This is for use by the
> +filesystem.  The filesystem should wrap the struct in its own, e.g.:
> +
> +	struct nfs_mount_context {
> +		struct mount_context mc;
> +		...
> +	};
> +
> +placing the mount_context struct first.  container_of() can then be used.
> +
> +The mount_context fields are as follows:
> +
> + (*) const struct mount_context_operations *ops
> +
> +     These are operations that can be done on a mount context.  See below.
> +     This must be set by the ->fsopen() file_system_type operation.
> +
> + (*) struct file_system_type *fs
> +
> +     A pointer to the file_system_type of the filesystem that is being
> +     mounted.  This retains a ref on the type owner.
> +
> + (*) struct user_namespace *user_ns
> + (*) struct mnt_namespace *mnt_ns
> + (*) struct pid_namespace *pid_ns
> + (*) struct net *net_ns
> +
> +     This is a subset of the namespaces in use by the invoking process.  This
> +     retains a ref on each namespace.  The subscribed namespaces may be
> +     replaced by the filesystem to reflect other sources, such as the parent
> +     mount superblock on an automount.
> +
> + (*) struct cred *cred
> +
> +     The mounter's credentials.  This retains a ref on the credentials.
> +
> + (*) char *device
> +
> +     This is the device to be mounted.  It may be a block device
> +     (e.g. /dev/sda1) or something more exotic, such as the "host:/path" that
> +     NFS desires.
> +
> + (*) char *root_path
> +
> +     A path to the place inside the filesystem to actually mount.  This allows
> +     a mount and bind-mount to be combined.
> +
> +     [NOTE] This isn't implemented yet, but NFS has the code to do this which
> +     could be moved to the VFS.
> +
> + (*) void *security
> +
> +     A place for the LSMs to hang their security data for the mount.  The
> +     relevant security operations are described below.
> +
> + (*) const char *error
> +
> +     A place for the VFS and the filesystem to hang an error message.  This
> +     should be in the form of a static string that doesn't need deallocation
> +     and the pointer to which can just be overwritten.  Under some
> +     circumstances, this can be retrieved by userspace.
> +
> +     Note that the existence of the error string is expected to be guaranteed
> +     by the reference on the file_system_type object held by ->fs or any
> +     filesystem-specific reference held in the filesystem context until the
> +     ->free() operation is called.
> +
> + (*) unsigned int ms_flags
> + (*) unsigned int mnt_flags
> +
> +     These hold the mount flags.  ms_flags holds MS_* flags and mnt_flags holds
> +     MNT_* flags.
> +
> + (*) bool mounted
> +
> +     This is set to true once a mount attempt is made.  This causes an error to
> +     be given on subsequent mount attempts with the same context and prevents
> +     multiple mount attempts.
> +
> + (*) bool sloppy
> + (*) bool silent
> +
> +     These are set if the sloppy or silent mount options are given.
> +
> +     [NOTE] sloppy is probably unnecessary when userspace passes over one
> +     option at a time since the error can just be ignored if userspace deems it
> +     to be unimportant.
> +
> +     [NOTE] silent is probably redundant with ms_flags & MS_SILENT.
> +
> + (*) enum mount_type
> +
> +     This indicates the type of mount operation.  The available values are:
> +
> +	MOUNT_TYPE_NEW		-- New mount
> +	MOUNT_TYPE_SUBMOUNT	-- New automatic submount of extant mount
> +	MOUNT_TYPE_REMOUNT	-- Change an existing mount
> +
> +The mount context is created by calling __vfs_fsopen(), vfs_fsopen(),
> +vfs_mntopen() or vfs_dup_mount_context() and is destroyed with
> +put_mount_context().  Note that the structure is not refcounted.
> +
> +VFS, security and filesystem mount options are set individually with
> +vfs_mount_option() or in bulk with generic_monolithic_mount_data().
> +
> +When mounting, the filesystem is allowed to take data from any of the pointers
> +and attach it to the superblock (or whatever), provided it clears the pointer
> +in the mount context.
> +
> +The filesystem is also allowed to allocate resources and pin them with the
> +mount context.  For instance, NFS might pin the appropriate protocol version
> +module.
> +
> +
> +============================
> +THE MOUNT CONTEXT OPERATIONS
> +============================
> +
> +The mount context points to a table of operations:
> +
> +	struct mount_context_operations {
> +		void (*free)(struct mount_context *mc);
> +		int (*dup)(struct mount_context *mc, struct mount_context *src);
> +		int (*option)(struct mount_context *mc, char *p);
> +		int (*monolithic_mount_data)(struct mount_context *mc, void *data);
> +		int (*validate)(struct mount_context *mc);
> +		struct dentry *(*mount)(struct mount_context *mc);
> +		int (*fill_super)(struct super_block *s, struct mount_context *mc);
> +	};
> +
> +These operations are invoked by the various stages of the mount procedure to
> +manage the mount context.  They are as follows:
> +
> + (*) void (*free)(struct mount_context *mc);
> +
> +     Called to clean up the filesystem-specific part of the mount context when
> +     the context is destroyed.  It should be aware that parts of the context
> +     may have been removed and NULL'd out by ->mount().
> +
> + (*) int (*dup)(struct mount_context *mc, struct mount_context *src);
> +
> +     Called when a mount context has been duplicated to get any refs or copy
> +     any non-referenced resources held in the filesystem-specific part of the
> +     mount context.  An error may be returned to indicate failure to do this.
> +
> +     [!] Note that if this fails, put_mount_context() will be called
> +     	 immediately thereafter, so ->dup() *must* make the
> +     	 filesystem-specific part safe for ->free().
> +
> + (*) int (*option)(struct mount_context *mc, char *p);
> +
> +     Called when an option is to be added to the mount context.  p points to
> +     the option string, likely in "key[=val]" format.  VFS-specific options
> +     will have been weeded out and mc->ms_flags and mc->mnt_flags updated in
> +     the context.  Security options will also have been weeded out and
> +     mc->security updated.
> +
> +     If successful, 0 should be returned and a negative error code otherwise.
> +     If an ambiguous error (such as -EINVAL) is returned, mc->error should be
> +     set in the context to a string that provides more information.
> +
> + (*) int (*monolithic_mount_data)(struct mount_context *mc, void *data);
> +
> +     Called when the mount(2) system call is invoked to pass the entire data
> +     page in one go.  If this is expected to be just a list of "key[=val]"
> +     items separated by commas, then this may be set to NULL.
> +
> +     The return value is as for ->option().
> +
> +     If the filesystem (eg. NFS) needs to examine the data first and then
> +     finds it's the standard key-val list then it may pass it off to:
> +
> +	int generic_monolithic_mount_data(struct mount_context *mc, void *data);
> +
> + (*) int (*validate)(struct mount_context *mc);
> +
> +     Called when all the options have been applied and the mount is about to
> +     take place.  It is should check for inconsistencies from mount options
> +     and it is also allowed to do preliminary resource acquisition.  For
> +     instance, the core NFS module could load the NFS protocol module here.
> +
> +     Note that if mc->mount_type == MOUNT_TYPE_REMOUNT, some of the options
> +     necessary for a new mount may not be set.
> +
> +     The return value is as for ->option().
> +
> + (*) struct dentry *(*mount)(struct mount_context *mc);
> +
> +     Called to effect a new mount or new submount using the information stored
> +     in the mount context (remounts go via a different vector).  It may detach
> +     any resources it desires from the mount context and transfer them to the
> +     superblock it creates.
> +
> +     On success it should return the dentry that's at the root of the mount.
> +     In future, mc->root_path will then be applied to this.
> +
> +     In the case of an error, it should return a negative error code and set
> +     mc->error.
> +
> + (*) int (*fill_super)(struct super_block *s, struct mount_context *mc);
> +
> +     This is available to be used by things like mount_ns_mc() that are called
> +     by ->mount() to transfer information/resources from the mount context to
> +     the superblock.
> +
> +
> +======================
> +MOUNT CONTEXT SECURITY
> +======================
> +
> +The mount context contains a security points that the LSMs can use for
> +building up a security context for the superblock to be mounted.  There are a
> +number of operations used by the new mount code for this purpose:
> +
> + (*) int security_mount_ctx_alloc(struct mount_context *mc,
> +				  struct super_block *src_sb);
> +
> +     Called to initialise mc->security (which is preset to NULL) and allocate
> +     any resources needed.  It should return 0 on success and a negative error
> +     code on failure.
> +
> +     src_sb is non-NULL in the case of a remount (MS_REMOUNT) in which case it
> +     indicates the superblock to be remounted or in the case of a submount
> +     (MS_SUBMOUNT) in which case it indicates the parent superblock.
> +
> + (*) int security_mount_ctx_dup(struct mount_context *mc,
> +				struct mount_context *src_mc);
> +
> +     Called to initialise mc->security (which is preset to NULL) and allocate
> +     any resources needed.  The original mount context is pointed to by src_mc
> +     and may be used for reference.  It should return 0 on success and a
> +     negative error code on failure.
> +
> + (*) void security_mount_ctx_free(struct mount_context *mc);
> +
> +     Called to clean up anything attached to mc->security.  Note that the
> +     contents may have been transferred to a superblock and the pointer NULL'd
> +     out during mount.
> +
> + (*) int security_mount_ctx_option(struct mount_context *mc, char *opt);
> +
> +     Called for each mount option.  The mount options are in "key[=val]"
> +     form.  An active LSM may reject one with an error, pass one over and
> +     return 0 or consume one and return 1.  If consumed, the option isn't
> +     passed on to the filesystem.
> +
> +     If it returns an error, it should set mc->error if the error is
> +     ambiguous.
> +
> + (*) int security_mount_ctx_kern_mount(struct mount_context *mc,
> +				       struct super_block *sb);
> +
> +     Called during mount to verify that the specified superblock is allowed to
> +     be mounted and to transfer the security data there.
> +
> +     On success, it should return 0; otherwise it should return an error and
> +     set mc->error to indicate the problem.  It should not return -ENOMEM as
> +     this should be taken care of in advance.
> +
> +     [NOTE] Should I add a security_mount_ctx_validate() operation so that the
> +     LSM has the opportunity to allocate stuff and check the options as a
> +     whole?
> +
> +
> +============================
> +VFS MOUNT CONTEXT OPERATIONS
> +============================
> +
> +There are four operations for creating a mount context and one for destroying
> +a context:
> +
> + (*) struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
> +					struct super_block *src_sb;
> +					unsigned int ms_flags,
> +					unsigned int mnt_flags);
> +
> +     Create a mount context given a filesystem type pointer.  This allocates
> +     the mount context, sets the flags, initialises the security and calls
> +     fs_type->fsopen() to initialise the filesystem context.
> +
> +     src_sb can be NULL or it may indicate a superblock that is going to be
> +     remounted (MS_REMOUNT) or a superblock that is the parent of a submount
> +     (MS_SUBMOUNT).  This superblock is provided as a source of namespace
> +     information.
> +
> + (*) struct mount_context *vfs_mntopen(struct vfsmount *mnt,
> +				       unsigned int ms_flags,
> +				       unsigned int mnt_flags);
> +
> +     Create a mount context from the same filesystem as an extant mount and
> +     initialise the mount parameters from the superblock underlying that
> +     mount.  This is used by remount.
> +
> + (*) struct mount_context *vfs_fsopen(const char *fs_name);
> +
> +     Create a mount context given a filesystem name.  It is assumed that the
> +     mount flags will be passed in as text options later.  This is intended to
> +     be called from sys_fsopen().  This copies current's namespaces to the
> +     mount context.
> +
> + (*) struct mount_context *vfs_dup_mount_context(struct mount_context *src);
> +
> +     Duplicate a mount context, copying any options noted and duplicating or
> +     additionally referencing any resources held therein.  This is available
> +     for use where a filesystem has to get a mount within a mount, such as
> +     NFS4 does by internally mounting the root of the target server and then
> +     doing a private pathwalk to the target directory.
> +
> + (*) void put_mount_context(struct mount_context *ctx);
> +
> +     Destroy a mount context, releasing any resources it holds.  This calls
> +     the ->free() operation.  This is intended to be called by anyone who
> +     created a mount context.
> +
> +     [!] Mount contexts are not refcounted, so this causes unconditional
> +     	 destruction.
> +
> +In all the above operations, apart from the put op, the return is a mount
> +context pointer or a negative error code.  No error string is saved as the
> +error string is only guaranteed as long as the file_system_type is pinned (and
> +thus the module).
> +
> +In the remaining operations, if an error occurs, a negative error code is
> +returned and, if not obvious, mc->error should be set to point to a useful
> +string.  The string should not be freed.
> +
> + (*) struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc);
> +
> +     Create a mount given the parameters in the specified mount context.  This
> +     invokes the ->validate() op and then the ->mount() op.
> +
> + (*) struct vfsmount *vfs_submount_mc(const struct dentry *mountpoint,
> +				      struct mount_context *mc);
> +
> +     Create a mount given a mount context and set MS_SUBMOUNT on it.  A
> +     wrapper around vfs_kern_mount_mc().  This is intended to be called from
> +     filesystems that have automount points (NFS, AFS, ...).
> +
> + (*) int vfs_mount_option(struct mount_context *mc, char *data);
> +
> +     Supply a single mount option to the mount context.  The mount option
> +     should likely be in a "key[=val]" string form.  The option is first
> +     checked to see if it corresponds to a standard mount flag (in which case
> +     it is used to mark an MS_xxx flag and consumed) or a security option (in
> +     which case the LSM consumes it) before it is passed on to the filesystem.
> +
> + (*) int generic_monolithic_mount_data(struct mount_context *ctx, void *data);
> +
> +     Parse a sys_mount() data page, assuming the form to be a text list
> +     consisting of key[=val] options separated by commas.  Each item in the
> +     list is passed to vfs_mount_option().  This is the default when the
> +     ->monolithic_mount_data() operation is NULL.
> diff --git a/fs/Makefile b/fs/Makefile
> index 7bbaca9c67b1..308a104a9a07 100644
> --- a/fs/Makefile
> +++ b/fs/Makefile
> @@ -11,7 +11,8 @@ obj-y :=	open.o read_write.o file_table.o super.o \
>  		attr.o bad_inode.o file.o filesystems.o namespace.o \
>  		seq_file.o xattr.o libfs.o fs-writeback.o \
>  		pnode.o splice.o sync.o utimes.o \
> -		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
> +		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
> +		mount_context.o
>  
>  ifeq ($(CONFIG_BLOCK),y)
>  obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
> diff --git a/fs/internal.h b/fs/internal.h
> index 076751d90ba2..ef8c5e93f364 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -87,7 +87,7 @@ extern struct file *get_empty_filp(void);
>  /*
>   * super.c
>   */
> -extern int do_remount_sb(struct super_block *, int, void *, int);
> +extern int do_remount_sb(struct super_block *, int, void *, int, struct mount_context *);
>  extern bool trylock_super(struct super_block *sb);
>  extern struct dentry *mount_fs(struct file_system_type *,
>  			       int, const char *, void *);
> diff --git a/fs/mount.h b/fs/mount.h
> index 2826543a131d..b1e99b38f2ee 100644
> --- a/fs/mount.h
> +++ b/fs/mount.h
> @@ -108,9 +108,10 @@ static inline void detach_mounts(struct dentry *dentry)
>  	__detach_mounts(dentry);
>  }
>  
> -static inline void get_mnt_ns(struct mnt_namespace *ns)
> +static inline struct mnt_namespace *get_mnt_ns(struct mnt_namespace *ns)
>  {
>  	atomic_inc(&ns->count);
> +	return ns;
>  }
>  
>  extern seqlock_t mount_lock;
> diff --git a/fs/mount_context.c b/fs/mount_context.c
> new file mode 100644
> index 000000000000..7d765c100bf1
> --- /dev/null
> +++ b/fs/mount_context.c
> @@ -0,0 +1,343 @@
> +/* Provide a way to create a mount context within the kernel that can be
> + * configured before mounting.
> + *
> + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
> + * Written by David Howells ([e-mail])
> + *
> + * 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.
> + */
> +
> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> +#include <linux/fs.h>
> +#include <linux/mount.h>
> +#include <linux/nsproxy.h>
> +#include <linux/slab.h>
> +#include <linux/magic.h>
> +#include <linux/security.h>
> +#include <linux/parser.h>
> +#include <linux/mnt_namespace.h>
> +#include <linux/pid_namespace.h>
> +#include <linux/user_namespace.h>
> +#include <net/net_namespace.h>
> +#include "mount.h"
> +
> +static const match_table_t common_set_mount_options = {
> +	{ MS_DIRSYNC,		"dirsync" },
> +	{ MS_I_VERSION,		"iversion" },
> +	{ MS_LAZYTIME,		"lazytime" },
> +	{ MS_MANDLOCK,		"mand" },
> +	{ MS_NOATIME,		"noatime" },
> +	{ MS_NODEV,		"nodev" },
> +	{ MS_NODIRATIME,	"nodiratime" },
> +	{ MS_NOEXEC,		"noexec" },
> +	{ MS_NOSUID,		"nosuid" },
> +	{ MS_POSIXACL,		"posixacl" },
> +	{ MS_RDONLY,		"ro" },
> +	{ MS_REC,		"rec" },
> +	{ MS_RELATIME,		"relatime" },
> +	{ MS_STRICTATIME,	"strictatime" },
> +	{ MS_SYNCHRONOUS,	"sync" },
> +	{ MS_VERBOSE,		"verbose" },
> +	{ },
> +};
> +
> +static const match_table_t common_clear_mount_options = {
> +	{ MS_LAZYTIME,		"nolazytime" },
> +	{ MS_MANDLOCK,		"nomand" },
> +	{ MS_NODEV,		"dev" },
> +	{ MS_NOEXEC,		"exec" },
> +	{ MS_NOSUID,		"suid" },
> +	{ MS_RDONLY,		"rw" },
> +	{ MS_RELATIME,		"norelatime" },
> +	{ MS_SILENT,		"silent" },
> +	{ MS_STRICTATIME,	"nostrictatime" },
> +	{ MS_SYNCHRONOUS,	"async" },
> +	{ },
> +};
> +
> +static const match_table_t forbidden_mount_options = {
> +	{ MS_BIND,		"bind" },
> +	{ MS_KERNMOUNT,		"ro" },
> +	{ MS_MOVE,		"move" },
> +	{ MS_PRIVATE,		"private" },
> +	{ MS_REMOUNT,		"remount" },
> +	{ MS_SHARED,		"shared" },
> +	{ MS_SLAVE,		"slave" },
> +	{ MS_UNBINDABLE,	"unbindable" },
> +	{ },
> +};
> +
> +/*
> + * Check for a common mount option.
> + */
> +static noinline int vfs_common_mount_option(struct mount_context *mc, char *data)
> +{
> +	substring_t args[MAX_OPT_ARGS];
> +	unsigned int token;
> +
> +	token = match_token(data, common_set_mount_options, args);
> +	if (token) {
> +		mc->ms_flags |= token;
> +		return 1;
> +	}
> +
> +	token = match_token(data, common_clear_mount_options, args);
> +	if (token) {
> +		mc->ms_flags &= ~token;
> +		return 1;
> +	}
> +
> +	token = match_token(data, forbidden_mount_options, args);
> +	if (token) {
> +		mc->error = "Mount option, not superblock option";
> +		return -EINVAL;
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * vfs_mount_option - Add a single mount option to a mount context
> + * @mc: The mount context to modify
> + * @option: The option to apply.
> + *
> + * A single mount option in string form is applied to the mount being set up in
> + * the mount context.  Certain standard options (for example "ro") are
> + * translated into flag bits without going to the filesystem.  The active
> + * security module allowed to observe and poach options.  Any other options are

"module is allowed"

> + * passed over to the filesystem to parse.
> + *
> + * This may be called multiple times for a context.
> + *
> + * Returns 0 on success and a negative error code on failure.  In the event of
> + * failure, mc->error may have been set to a non-allocated string that gives
> + * more information.
> + */
> +int vfs_mount_option(struct mount_context *mc, char *data)
> +{
> +	int ret;
> +
> +	if (mc->mounted)
> +		return -EBUSY;
> +
> +	ret = vfs_common_mount_option(mc, data);
> +	if (ret < 0)
> +		return ret;
> +	if (ret == 1)
> +		return 0;
> +
> +	ret = security_mount_ctx_option(mc, data);
> +	if (ret < 0)
> +		return ret;
> +	if (ret == 1)
> +		return 0;
> +
> +	return mc->ops->option(mc, data);
> +}
> +EXPORT_SYMBOL(vfs_mount_option);
> +
> +/**
> + * generic_monolithic_mount_data - Parse key[=val][,key[=val]]* mount data
> + * @mc: The mount context to populate
> + * @data: The data to parse
> + *
> + * Parse a blob of data that's in key[=val][,key[=val]]* form.  This can be
> + * called from the ->monolithic_mount_data() mount context operation.
> + *
> + * Returns 0 on success or the error returned by the ->option() mount context
> + * operation on failure.
> + */
> +int generic_monolithic_mount_data(struct mount_context *ctx, void *data)
> +{
> +	char *options = data, *p;
> +	int ret;
> +
> +	if (!options)
> +		return 0;
> +
> +	while ((p = strsep(&options, ",")) != NULL) {
> +		if (*p) {
> +			ret = vfs_mount_option(ctx, p);
> +			if (ret < 0)
> +				return ret;
> +		}
> +	}
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL(generic_monolithic_mount_data);
> +
> +/**
> + * __vfs_fsopen - Open a filesystem and create a mount context
> + * @fs_type: The filesystem type
> + * @src_sb: A superblock from which this one derives (or NULL)
> + * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
> + * @mnt_flags: Mountpoint flags, such as MNT_READONLY
> + * @mount_type: Type of mount
> + *
> + * Open a filesystem and create a mount context.  The mount context is
> + * initialised with the supplied flags and, if a submount/automount from
> + * another superblock (@src_sb), may have parameters such as namespaces copied
> + * across from that superblock.
> + */
> +struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
> +				   struct super_block *src_sb,
> +				   unsigned int ms_flags, unsigned int mnt_flags,
> +				   enum mount_type mount_type)
> +{
> +	struct mount_context *mc;
> +	int ret;
> +
> +	if (fs_type->fsopen && fs_type->mc_size < sizeof(*mc))
> +		BUG();
> +
> +	mc = kzalloc(max_t(size_t, fs_type->mc_size, sizeof(*mc)), GFP_KERNEL);
> +	if (!mc)
> +		return ERR_PTR(-ENOMEM);
> +
> +	mc->mount_type = mount_type;
> +	mc->ms_flags = ms_flags;
> +	mc->mnt_flags = mnt_flags;
> +	mc->fs_type = fs_type;
> +	get_filesystem(fs_type);
> +	mc->mnt_ns = get_mnt_ns(current->nsproxy->mnt_ns);
> +	mc->pid_ns = get_pid_ns(task_active_pid_ns(current));
> +	mc->net_ns = get_net(current->nsproxy->net_ns);
> +	mc->user_ns = get_user_ns(current_user_ns());
> +	mc->cred = get_current_cred();
> +
> +
> +	/* TODO: Make all filesystems support this unconditionally */
> +	if (mc->fs_type->fsopen) {
> +		ret = mc->fs_type->fsopen(mc, src_sb);
> +		if (ret < 0)
> +			goto err_mc;
> +	}
> +
> +	/* Do the security check last because ->fsopen may change the
> +	 * namespace subscriptions.
> +	 */
> +	ret = security_mount_ctx_alloc(mc, src_sb);
> +	if (ret < 0)
> +		goto err_mc;
> +
> +	return mc;
> +
> +err_mc:
> +	put_mount_context(mc);
> +	return ERR_PTR(ret);
> +}
> +EXPORT_SYMBOL(__vfs_fsopen);
> +
> +/**
> + * vfs_fsopen - Open a filesystem and create a mount context
> + * @fs_name: The name of the filesystem
> + *
> + * Open a filesystem and create a mount context that will hold the mount
> + * options, device name, security details, etc..  Note that the caller should
> + * check the ->ops pointer in the returned context to determine whether the
> + * filesystem actually supports the mount context itself.
> + */
> +struct mount_context *vfs_fsopen(const char *fs_name)
> +{
> +	struct file_system_type *fs_type;
> +	struct mount_context *mc;
> +
> +	fs_type = get_fs_type(fs_name);
> +	if (!fs_type)
> +		return ERR_PTR(-ENODEV);
> +
> +	mc = __vfs_fsopen(fs_type, NULL, 0, 0, MOUNT_TYPE_NEW);
> +	put_filesystem(fs_type);
> +	return mc;
> +}
> +EXPORT_SYMBOL(vfs_fsopen);
> +
> +/**
> + * vfs_mntopen - Create a mount context and initialise it from an extant mount
> + * @mnt: The mountpoint to open
> + * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
> + * @mnt_flags: Mountpoint flags, such as MNT_READONLY
> + * @mount_type: Type of mount
> + *
> + * Open a mounted filesystem and create a mount context such that a remount can
> + * be effected.
> + */
> +struct mount_context *vfs_mntopen(struct vfsmount *mnt,
> +				  unsigned int ms_flags,
> +				  unsigned int mnt_flags,
> +				  enum mount_type mount_type)
> +{
> +	return __vfs_fsopen(mnt->mnt_sb->s_type, mnt->mnt_sb,
> +			    ms_flags, mnt_flags, mount_type);
> +}
> +
> +/**
> + * vfs_dup_mount_context: Duplicate a mount context.
> + * @src: The mount context to copy.
> + */
> +struct mount_context *vfs_dup_mount_context(struct mount_context *src)
> +{
> +	struct mount_context *mc;
> +	int ret;
> +
> +	if (!src->ops->dup)
> +		return ERR_PTR(-ENOTSUPP);
> +
> +	mc = kmemdup(src, src->fs_type->mc_size, GFP_KERNEL);
> +	if (!mc)
> +		return ERR_PTR(-ENOMEM);
> +
> +	mc->device	= NULL;
> +	mc->root_path	= NULL;
> +	mc->security	= NULL;
> +	mc->error	= NULL;
> +	get_filesystem(mc->fs_type);
> +	get_mnt_ns(mc->mnt_ns);
> +	get_pid_ns(mc->pid_ns);
> +	get_net(mc->net_ns);
> +	get_user_ns(mc->user_ns);
> +	get_cred(mc->cred);
> +
> +	/* Can't call put until we've called ->dup */
> +	ret = mc->ops->dup(mc, src);
> +	if (ret < 0)
> +		goto err_mc;
> +
> +	ret = security_mount_ctx_dup(mc, src);
> +	if (ret < 0)
> +		goto err_mc;
> +	return mc;
> +
> +err_mc:
> +	put_mount_context(mc);
> +	return ERR_PTR(ret);
> +}
> +EXPORT_SYMBOL(vfs_dup_mount_context);
> +
> +/*
> + * Dispose of a mount context.
> + */
> +void put_mount_context(struct mount_context *mc)
> +{
> +	if (mc->ops && mc->ops->free)
> +		mc->ops->free(mc);
> +	security_mount_ctx_free(mc);
> +	if (mc->mnt_ns)
> +		put_mnt_ns(mc->mnt_ns);
> +	if (mc->pid_ns)
> +		put_pid_ns(mc->pid_ns);
> +	if (mc->net_ns)
> +		put_net(mc->net_ns);
> +	put_user_ns(mc->user_ns);
> +	if (mc->cred)
> +		put_cred(mc->cred);
> +	put_filesystem(mc->fs_type);
> +	kfree(mc->device);
> +	kfree(mc->root_path);
> +	kfree(mc);
> +}
> +EXPORT_SYMBOL(put_mount_context);
> diff --git a/fs/namespace.c b/fs/namespace.c
> index db034b6afd43..e0edab9af308 100644
> --- a/fs/namespace.c
> +++ b/fs/namespace.c
> @@ -25,6 +25,7 @@
>  #include <linux/magic.h>
>  #include <linux/bootmem.h>
>  #include <linux/task_work.h>
> +#include <linux/file.h>
>  #include <linux/sched/task.h>
>  
>  #include "pnode.h"
> @@ -783,9 +784,14 @@ static void put_mountpoint(struct mountpoint *mp)
>  	}
>  }
>  
> +static inline int __check_mnt(struct mount *mnt, struct mnt_namespace *mnt_ns)
> +{
> +	return mnt->mnt_ns == mnt_ns;
> +}
> +
>  static inline int check_mnt(struct mount *mnt)
>  {
> -	return mnt->mnt_ns == current->nsproxy->mnt_ns;
> +	return __check_mnt(mnt, current->nsproxy->mnt_ns);
>  }
>  
>  /*
> @@ -1596,7 +1602,7 @@ static int do_umount(struct mount *mnt, int flags)
>  			return -EPERM;
>  		down_write(&sb->s_umount);
>  		if (!(sb->s_flags & MS_RDONLY))
> -			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
> +			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0, NULL);
>  		up_write(&sb->s_umount);
>  		return retval;
>  	}
> @@ -2279,6 +2285,26 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
>  }
>  
>  /*
> + * Parse the monolithic page of mount data given to sys_mount().
> + */
> +static int parse_monolithic_mount_data(struct mount_context *mc, void *data)
> +{
> +	int (*monolithic_mount_data)(struct mount_context *, void *);
> +	int ret;
> +
> +	monolithic_mount_data = mc->ops->monolithic_mount_data;
> +	if (!monolithic_mount_data)
> +		monolithic_mount_data = generic_monolithic_mount_data;
> +
> +	ret = monolithic_mount_data(mc, data);
> +	if (ret < 0)
> +		return ret;
> +	if (mc->ops->validate)
> +		return mc->ops->validate(mc);
> +	return 0;
> +}
> +
> +/*
>   * change filesystem flags. dir should be a physical root of filesystem.
>   * If you've mounted a non-root directory somewhere and want to do remount
>   * on it - tough luck.
> @@ -2286,13 +2312,14 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
>  static int do_remount(struct path *path, int flags, int mnt_flags,
>  		      void *data)
>  {
> +	struct mount_context *mc = NULL;
>  	int err;
>  	struct super_block *sb = path->mnt->mnt_sb;
>  	struct mount *mnt = real_mount(path->mnt);
> +	struct file_system_type *type = sb->s_type;
>  
>  	if (!check_mnt(mnt))
>  		return -EINVAL;
> -
>  	if (path->dentry != path->mnt->mnt_root)
>  		return -EINVAL;
>  
> @@ -2323,9 +2350,19 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
>  		return -EPERM;
>  	}
>  
> -	err = security_sb_remount(sb, data);
> -	if (err)
> -		return err;
> +	if (type->fsopen) {
> +		mc = vfs_mntopen(path->mnt, flags, mnt_flags, MOUNT_TYPE_REMOUNT);
> +		if (IS_ERR(mc))
> +			return PTR_ERR(mc);
> +
> +		err = parse_monolithic_mount_data(mc, data);
> +		if (err < 0)
> +			goto err_mc;
> +	} else {
> +		err = security_sb_remount(sb, data);
> +		if (err)
> +			return err;
> +	}
>  
>  	down_write(&sb->s_umount);
>  	if (flags & MS_BIND)
> @@ -2333,7 +2370,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
>  	else if (!capable(CAP_SYS_ADMIN))
>  		err = -EPERM;
>  	else
> -		err = do_remount_sb(sb, flags, data, 0);
> +		err = do_remount_sb(sb, flags, data, 0, mc);
>  	if (!err) {
>  		lock_mount_hash();
>  		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
> @@ -2342,6 +2379,9 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
>  		unlock_mount_hash();
>  	}
>  	up_write(&sb->s_umount);
> +err_mc:
> +	if (mc)
> +		put_mount_context(mc);
>  	return err;
>  }
>  
> @@ -2451,7 +2491,8 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
>  /*
>   * add a mount into a namespace's mount tree
>   */
> -static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
> +static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags,
> +			struct mnt_namespace *mnt_ns)
>  {
>  	struct mountpoint *mp;
>  	struct mount *parent;
> @@ -2465,7 +2506,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
>  
>  	parent = real_mount(path->mnt);
>  	err = -EINVAL;
> -	if (unlikely(!check_mnt(parent))) {
> +	if (unlikely(!__check_mnt(parent, mnt_ns))) {
>  		/* that's acceptable only for automounts done in private ns */
>  		if (!(mnt_flags & MNT_SHRINKABLE))
>  			goto unlock;
> @@ -2493,42 +2534,73 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
>  }
>  
>  static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);
> +static int do_new_mount_mc(struct mount_context *mc, struct path *mountpoint,
> +			   unsigned int mnt_flags);
>  
>  /*
>   * create a new mount for userspace and request it to be added into the
>   * namespace's tree
>   */
> -static int do_new_mount(struct path *path, const char *fstype, int flags,
> +static int do_new_mount(struct path *mountpoint, const char *fstype, int flags,
>  			int mnt_flags, const char *name, void *data)
>  {
> -	struct file_system_type *type;
> +	struct mount_context *mc;
>  	struct vfsmount *mnt;
>  	int err;
>  
>  	if (!fstype)
>  		return -EINVAL;
>  
> -	type = get_fs_type(fstype);
> -	if (!type)
> -		return -ENODEV;
> +	mc = vfs_fsopen(fstype);
> +	if (IS_ERR(mc))
> +		return PTR_ERR(mc);
> +	mc->ms_flags = flags;
> +	mc->mnt_flags = mnt_flags;
>  
> -	mnt = vfs_kern_mount(type, flags, name, data);
> -	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
> -	    !mnt->mnt_sb->s_subtype)
> -		mnt = fs_set_subtype(mnt, fstype);
> +	err = -ENOMEM;
> +	mc->device = kstrdup(name, GFP_KERNEL);
> +	if (!mc->device)
> +		goto err_mc;
>  
> -	put_filesystem(type);
> -	if (IS_ERR(mnt))
> -		return PTR_ERR(mnt);
> +	if (mc->ops) {
> +		err = parse_monolithic_mount_data(mc, data);
> +		if (err < 0)
> +			goto err_mc;
>  
> -	if (mount_too_revealing(mnt, &mnt_flags)) {
> -		mntput(mnt);
> -		return -EPERM;
> +		err = do_new_mount_mc(mc, mountpoint, mnt_flags);
> +		if (err)
> +			goto err_mc;
> +
> +	} else {
> +		mnt = vfs_kern_mount(mc->fs_type, flags, name, data);
> +		if (!IS_ERR(mnt) && (mc->fs_type->fs_flags & FS_HAS_SUBTYPE) &&
> +		    !mnt->mnt_sb->s_subtype)
> +			mnt = fs_set_subtype(mnt, fstype);
> +
> +		if (IS_ERR(mnt)) {
> +			err = PTR_ERR(mnt);
> +			goto err_mc;
> +		}
> +
> +		err = -EPERM;
> +		if (mount_too_revealing(mnt, &mnt_flags))
> +			goto err_mnt;
> +
> +		err = do_add_mount(real_mount(mnt), mountpoint, mnt_flags,
> +				   mc->mnt_ns);
> +		if (err)
> +			goto err_mnt;
>  	}
>  
> -	err = do_add_mount(real_mount(mnt), path, mnt_flags);
> -	if (err)
> -		mntput(mnt);
> +	put_mount_context(mc);
> +	return 0;
> +
> +err_mnt:
> +	mntput(mnt);
> +err_mc:
> +	if (mc->error)
> +		pr_info("Mount failed: %s\n", mc->error);
> +	put_mount_context(mc);
>  	return err;
>  }
>  
> @@ -2547,7 +2619,8 @@ int finish_automount(struct vfsmount *m, struct path *path)
>  		goto fail;
>  	}
>  
> -	err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
> +	err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE,
> +			   current->nsproxy->mnt_ns);
>  	if (!err)
>  		return 0;
>  fail:
> @@ -3061,6 +3134,130 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
>  	return ret;
>  }
>  
> +static struct dentry *__do_mount_mc(struct mount_context *mc)
> +{
> +	struct super_block *sb;
> +	struct dentry *root;
> +	int ret;
> +
> +	root = mc->ops->mount(mc);
> +	if (IS_ERR(root))
> +		return root;
> +
> +	sb = root->d_sb;
> +	BUG_ON(!sb);
> +	WARN_ON(!sb->s_bdi);
> +	sb->s_flags |= MS_BORN;
> +
> +	ret = security_mount_ctx_kern_mount(mc, sb);
> +	if (ret < 0)
> +		goto err_sb;
> +
> +	/*
> +	 * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
> +	 * but s_maxbytes was an unsigned long long for many releases. Throw
> +	 * this warning for a little while to try and catch filesystems that
> +	 * violate this rule.
> +	 */
> +	WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
> +		"negative value (%lld)\n", mc->fs_type->name, sb->s_maxbytes);
> +
> +	up_write(&sb->s_umount);
> +	return root;
> +
> +err_sb:
> +	dput(root);
> +	deactivate_locked_super(sb);
> +	return ERR_PTR(ret);
> +}
> +
> +struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc)
> +{
> +	struct dentry *root;
> +	struct mount *mnt;
> +	int ret;
> +
> +	if (mc->ops->validate) {
> +		ret = mc->ops->validate(mc);
> +		if (ret < 0)
> +			return ERR_PTR(ret);
> +	}
> +
> +	mnt = alloc_vfsmnt(mc->device ?: "none");
> +	if (!mnt)
> +		return ERR_PTR(-ENOMEM);
> +
> +	if (mc->ms_flags & MS_KERNMOUNT)
> +		mnt->mnt.mnt_flags = MNT_INTERNAL;
> +
> +	root = __do_mount_mc(mc);
> +	if (IS_ERR(root)) {
> +		mnt_free_id(mnt);
> +		free_vfsmnt(mnt);
> +		return ERR_CAST(root);
> +	}
> +
> +	mnt->mnt.mnt_root	= root;
> +	mnt->mnt.mnt_sb		= root->d_sb;
> +	mnt->mnt_mountpoint	= mnt->mnt.mnt_root;
> +	mnt->mnt_parent		= mnt;
> +	lock_mount_hash();
> +	list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
> +	unlock_mount_hash();
> +	return &mnt->mnt;
> +}
> +EXPORT_SYMBOL_GPL(vfs_kern_mount_mc);
> +
> +struct vfsmount *
> +vfs_submount_mc(const struct dentry *mountpoint, struct mount_context *mc)
> +{
> +	/* Until it is worked out how to pass the user namespace
> +	 * through from the parent mount to the submount don't support
> +	 * unprivileged mounts with submounts.
> +	 */
> +	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
> +		return ERR_PTR(-EPERM);
> +
> +	mc->ms_flags = MS_SUBMOUNT;
> +	return vfs_kern_mount_mc(mc);
> +}
> +EXPORT_SYMBOL_GPL(vfs_submount_mc);
> +
> +static int do_new_mount_mc(struct mount_context *mc, struct path *mountpoint,
> +			   unsigned int mnt_flags)
> +{
> +	struct vfsmount *mnt;
> +	int ret;
> +
> +	mnt = vfs_kern_mount_mc(mc);
> +	if (IS_ERR(mnt))
> +		return PTR_ERR(mnt);
> +
> +	if ((mc->fs_type->fs_flags & FS_HAS_SUBTYPE) &&
> +	    !mnt->mnt_sb->s_subtype) {
> +		mnt = fs_set_subtype(mnt, mc->fs_type->name);
> +		if (IS_ERR(mnt))
> +			return PTR_ERR(mnt);
> +	}
> +
> +	ret = -EPERM;
> +	if (mount_too_revealing(mnt, &mnt_flags)) {
> +		mc->error = "VFS: Mount too revealing";
> +		goto err_mnt;
> +	}
> +
> +	ret = do_add_mount(real_mount(mnt), mountpoint, mnt_flags, mc->mnt_ns);
> +	if (ret < 0) {
> +		mc->error = "VFS: Failed to add mount";
> +		goto err_mnt;
> +	}
> +	return ret;
> +
> +err_mnt:
> +	mntput(mnt);
> +	return ret;
> +}
> +
>  /*
>   * Return true if path is reachable from root
>   *
> @@ -3302,6 +3499,23 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
>  }
>  EXPORT_SYMBOL_GPL(kern_mount_data);
>  
> +struct vfsmount *kern_mount_data_mc(struct mount_context *mc)
> +{
> +	struct vfsmount *mnt;
> +
> +	mc->ms_flags = MS_KERNMOUNT;
> +	mnt = vfs_kern_mount_mc(mc);
> +	if (!IS_ERR(mnt)) {
> +		/*
> +		 * it is a longterm mount, don't release mnt until
> +		 * we unmount before file sys is unregistered
> +		*/
> +		real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
> +	}
> +	return mnt;
> +}
> +EXPORT_SYMBOL_GPL(kern_mount_data_mc);
> +
>  void kern_unmount(struct vfsmount *mnt)
>  {
>  	/* release long term mount so mount point can be released */
> diff --git a/fs/super.c b/fs/super.c
> index adb0c0de428c..6e7b86520337 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -805,10 +805,13 @@ struct super_block *user_get_super(dev_t dev)
>   *	@flags:	numeric part of options
>   *	@data:	the rest of options
>   *      @force: whether or not to force the change
> + *	@mc:	the mount context for filesystems that support it
> + *		(NULL if called from emergency or umount)
>   *
>   *	Alters the mount options of a mounted file system.
>   */
> -int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
> +int do_remount_sb(struct super_block *sb, int flags, void *data, int force,
> +		  struct mount_context *mc)
>  {
>  	int retval;
>  	int remount_ro;
> @@ -850,8 +853,14 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
>  		}
>  	}
>  
> -	if (sb->s_op->remount_fs) {
> -		retval = sb->s_op->remount_fs(sb, &flags, data);
> +	if (sb->s_op->remount_fs_mc ||
> +	    sb->s_op->remount_fs) {
> +		if (sb->s_op->remount_fs_mc) {
> +		    retval = sb->s_op->remount_fs_mc(sb, mc);
> +		    flags = mc->ms_flags;
> +		} else {
> +			retval = sb->s_op->remount_fs(sb, &flags, data);
> +		}
>  		if (retval) {
>  			if (!force)
>  				goto cancel_readonly;
> @@ -898,7 +907,7 @@ static void do_emergency_remount(struct work_struct *work)
>  			/*
>  			 * What lock protects sb->s_flags??
>  			 */
> -			do_remount_sb(sb, MS_RDONLY, NULL, 1);
> +			do_remount_sb(sb, MS_RDONLY, NULL, 1, NULL);
>  		}
>  		up_write(&sb->s_umount);
>  		spin_lock(&sb_lock);
> @@ -1048,6 +1057,37 @@ struct dentry *mount_ns(struct file_system_type *fs_type,
>  
>  EXPORT_SYMBOL(mount_ns);
>  
> +struct dentry *mount_ns_mc(struct mount_context *mc, void *ns)
> +{
> +	struct super_block *sb;
> +
> +	/* Don't allow mounting unless the caller has CAP_SYS_ADMIN
> +	 * over the namespace.
> +	 */
> +	if (!(mc->ms_flags & MS_KERNMOUNT) &&
> +	    !ns_capable(mc->user_ns, CAP_SYS_ADMIN))
> +		return ERR_PTR(-EPERM);
> +
> +	sb = sget_userns(mc->fs_type, ns_test_super, ns_set_super,
> +			 mc->ms_flags, mc->user_ns, ns);
> +	if (IS_ERR(sb))
> +		return ERR_CAST(sb);
> +
> +	if (!sb->s_root) {
> +		int err;
> +		err = mc->ops->fill_super(sb, mc);
> +		if (err) {
> +			deactivate_locked_super(sb);
> +			return ERR_PTR(err);
> +		}
> +
> +		sb->s_flags |= MS_ACTIVE;
> +	}
> +
> +	return dget(sb->s_root);
> +}
> +EXPORT_SYMBOL(mount_ns_mc);
> +
>  #ifdef CONFIG_BLOCK
>  static int set_bdev_super(struct super_block *s, void *data)
>  {
> @@ -1196,7 +1236,7 @@ struct dentry *mount_single(struct file_system_type *fs_type,
>  		}
>  		s->s_flags |= MS_ACTIVE;
>  	} else {
> -		do_remount_sb(s, flags, data, 0);
> +		do_remount_sb(s, flags, data, 0, NULL);
>  	}
>  	return dget(s->s_root);
>  }
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 30e5c14bd743..40fe5c5054ec 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -55,6 +55,7 @@ struct workqueue_struct;
>  struct iov_iter;
>  struct fscrypt_info;
>  struct fscrypt_operations;
> +struct mount_context;
>  
>  extern void __init inode_init(void);
>  extern void __init inode_init_early(void);
> @@ -701,6 +702,11 @@ static inline void inode_unlock(struct inode *inode)
>  	up_write(&inode->i_rwsem);
>  }
>  
> +static inline int inode_lock_killable(struct inode *inode)
> +{
> +	return down_write_killable(&inode->i_rwsem);
> +}
> +
>  static inline void inode_lock_shared(struct inode *inode)
>  {
>  	down_read(&inode->i_rwsem);
> @@ -1786,6 +1792,7 @@ struct super_operations {
>  	int (*unfreeze_fs) (struct super_block *);
>  	int (*statfs) (struct dentry *, struct kstatfs *);
>  	int (*remount_fs) (struct super_block *, int *, char *);
> +	int (*remount_fs_mc) (struct super_block *, struct mount_context *);
>  	void (*umount_begin) (struct super_block *);
>  
>  	int (*show_options)(struct seq_file *, struct dentry *);
> @@ -2020,8 +2027,10 @@ struct file_system_type {
>  #define FS_HAS_SUBTYPE		4
>  #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
>  #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
> +	unsigned short mc_size;		/* Size of mount context to allocate */
>  	struct dentry *(*mount) (struct file_system_type *, int,
>  		       const char *, void *);
> +	int (*fsopen)(struct mount_context *, struct super_block *);
>  	void (*kill_sb) (struct super_block *);
>  	struct module *owner;
>  	struct file_system_type * next;
> @@ -2039,6 +2048,7 @@ struct file_system_type {
>  
>  #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
>  
> +extern struct dentry *mount_ns_mc(struct mount_context *mc, void *ns);
>  extern struct dentry *mount_ns(struct file_system_type *fs_type,
>  	int flags, void *data, void *ns, struct user_namespace *user_ns,
>  	int (*fill_super)(struct super_block *, void *, int));
> @@ -2105,6 +2115,7 @@ extern int register_filesystem(struct file_system_type *);
>  extern int unregister_filesystem(struct file_system_type *);
>  extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
>  #define kern_mount(type) kern_mount_data(type, NULL)
> +extern struct vfsmount *kern_mount_data_mc(struct mount_context *);
>  extern void kern_unmount(struct vfsmount *mnt);
>  extern int may_umount_tree(struct vfsmount *);
>  extern int may_umount(struct vfsmount *);
> diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
> index e29d4c62a3c8..f6aa68b8e68e 100644
> --- a/include/linux/lsm_hooks.h
> +++ b/include/linux/lsm_hooks.h
> @@ -75,6 +75,32 @@
>   *	should enable secure mode.
>   *	@bprm contains the linux_binprm structure.
>   *
> + * Security hooks for mount using fd context.
> + *
> + * @mount_ctx_alloc:
> + *	Allocate and attach a security structure to mc->security.  This pointer
> + *	is initialised to NULL by the caller.
> + *	@mc indicates the new mount context.
> + *	@src_sb indicates the source superblock of a submount.
> + * @mount_ctx_dup:
> + *	Allocate and attach a security structure to mc->security.  This pointer
> + *	is initialised to NULL by the caller.
> + *	@mc indicates the new mount context.
> + *	@src_mc indicates the original mount context.
> + * @mount_ctx_free:
> + *	Clean up a mount context.
> + *	@mc indicates the mount context.
> + * @mount_ctx_option:
> + *	Userspace provided an option to configure a mount.  The LSM may reject
> + *	it with an error and may use it for itself, in which case it should
> + *	return 1; otherwise it should return 0 to pass it on to the filesystem.
> + *	@mc indicates the mount context.
> + *	@p indicates the option in "key[=val]" form.
> + * @mount_ctx_kern_mount:
> + *	Equivalent of sb_kern_mount, but with a mount_context.
> + *	@mc indicates the mount context.
> + *	@src_sb indicates the new superblock.
> + *
>   * Security hooks for filesystem operations.
>   *
>   * @sb_alloc_security:
> @@ -1358,6 +1384,12 @@ union security_list_options {
>  	void (*bprm_committing_creds)(struct linux_binprm *bprm);
>  	void (*bprm_committed_creds)(struct linux_binprm *bprm);
>  
> +	int (*mount_ctx_alloc)(struct mount_context *mc, struct super_block *src_sb);
> +	int (*mount_ctx_dup)(struct mount_context *mc, struct mount_context *src_mc);
> +	void (*mount_ctx_free)(struct mount_context *mc);
> +	int (*mount_ctx_option)(struct mount_context *mc, char *opt);
> +	int (*mount_ctx_kern_mount)(struct mount_context *mc, struct super_block *sb);
> +
>  	int (*sb_alloc_security)(struct super_block *sb);
>  	void (*sb_free_security)(struct super_block *sb);
>  	int (*sb_copy_data)(char *orig, char *copy);
> @@ -1666,6 +1698,11 @@ struct security_hook_heads {
>  	struct list_head bprm_secureexec;
>  	struct list_head bprm_committing_creds;
>  	struct list_head bprm_committed_creds;
> +	struct list_head mount_ctx_alloc;
> +	struct list_head mount_ctx_dup;
> +	struct list_head mount_ctx_free;
> +	struct list_head mount_ctx_option;
> +	struct list_head mount_ctx_kern_mount;
>  	struct list_head sb_alloc_security;
>  	struct list_head sb_free_security;
>  	struct list_head sb_copy_data;
> diff --git a/include/linux/mount.h b/include/linux/mount.h
> index 8e0352af06b7..cf2583406986 100644
> --- a/include/linux/mount.h
> +++ b/include/linux/mount.h
> @@ -69,6 +69,56 @@ struct vfsmount {
>  	int mnt_flags;
>  };
>  
> +struct mount_context;
> +struct mount_context_operations {
> +	void (*free)(struct mount_context *mc);
> +	int (*dup)(struct mount_context *mc, struct mount_context *src);
> +	/* An option has been specified. */
> +	int (*option)(struct mount_context *mc, char *p);
> +	/* Parse monolithic mount data. */
> +	int (*monolithic_mount_data)(struct mount_context *mc, void *data);
> +	/* Validate the mount options */
> +	int (*validate)(struct mount_context *mc);
> +	/* Perform the mount. */
> +	struct dentry *(*mount)(struct mount_context *mc);
> +	/* Fill in a superblock */
> +	int (*fill_super)(struct super_block *s, struct mount_context *mc);
> +};
> +
> +enum mount_type {
> +	MOUNT_TYPE_NEW,		/* New mount made directly */
> +	MOUNT_TYPE_SUBMOUNT,	/* New mount made automatically */
> +	MOUNT_TYPE_REMOUNT,	/* Change of an existing mount */
> +};
> +
> +/*
> + * Mount context as allocated and constructed by fsopen().  The filesystem must
> + * support the ->ctx_*() operations.  The size of the object allocated is in
> + * struct file_system_type::mount_context_size; this must be embedded as the
> + * fist thing in the filesystem's own context.
> + */
> +struct mount_context {
> +	const struct mount_context_operations *ops;
> +	struct file_system_type	*fs_type;
> +	struct user_namespace	*user_ns;	/* The user namespace for this mount */
> +	struct mnt_namespace	*mnt_ns;	/* The mount namespace for this mount */
> +	struct pid_namespace	*pid_ns;	/* The process ID namespace for this mount */
> +	struct net		*net_ns;	/* The network namespace for this mount */
> +	const struct cred	*cred;		/* The mounter's credentials */
> +	char			*device;	/* The device name or mount target */
> +	char			*root_path;	/* The path within the mount to mount */
> +	void			*security;	/* The LSM context */
> +	const char		*error;		/* Error string to be read by read() */
> +	unsigned int		ms_flags;	/* The superblock flags (MS_*) */
> +	unsigned int		mnt_flags;	/* The mount flags (MNT_*) */
> +	bool			mounted;	/* Set when mounted */
> +	bool			sloppy;		/* Unrecognised options are okay */
> +	bool			silent;
> +	enum mount_type		mount_type : 8;
> +};
> +
> +extern const struct file_operations fs_fs_fops;
> +
>  struct file; /* forward dec */
>  struct path;
>  
> @@ -90,9 +140,26 @@ struct file_system_type;
>  extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
>  				      int flags, const char *name,
>  				      void *data);
> +extern struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc);
>  extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
>  				     struct file_system_type *type,
>  				     const char *name, void *data);
> +extern struct vfsmount *vfs_submount_mc(const struct dentry *mountpoint,
> +					struct mount_context *mc);
> +extern struct mount_context *vfs_fsopen(const char *fs_name);
> +extern struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
> +					  struct super_block *src_sb,
> +					  unsigned int ms_flags,
> +					  unsigned int mnt_flags,
> +					  enum mount_type mount_type);
> +extern struct mount_context *vfs_mntopen(struct vfsmount *mnt,
> +					 unsigned int ms_flags,
> +					 unsigned int mnt_flags,
> +					 enum mount_type mount_type);
> +extern struct mount_context *vfs_dup_mount_context(struct mount_context *src);
> +extern int vfs_mount_option(struct mount_context *mc, char *data);
> +extern int generic_monolithic_mount_data(struct mount_context *ctx, void *data);
> +extern void put_mount_context(struct mount_context *ctx);
>  
>  extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
>  extern void mark_mounts_for_expiry(struct list_head *mounts);
> diff --git a/include/linux/security.h b/include/linux/security.h
> index 96899fad7016..91efe3039bff 100644
> --- a/include/linux/security.h
> +++ b/include/linux/security.h
> @@ -55,6 +55,7 @@ struct msg_queue;
>  struct xattr;
>  struct xfrm_sec_ctx;
>  struct mm_struct;
> +struct mount_context;
>  
>  /* If capable should audit the security request */
>  #define SECURITY_CAP_NOAUDIT 0
> @@ -220,6 +221,11 @@ int security_bprm_check(struct linux_binprm *bprm);
>  void security_bprm_committing_creds(struct linux_binprm *bprm);
>  void security_bprm_committed_creds(struct linux_binprm *bprm);
>  int security_bprm_secureexec(struct linux_binprm *bprm);
> +int security_mount_ctx_alloc(struct mount_context *mc, struct super_block *sb);
> +int security_mount_ctx_dup(struct mount_context *mc, struct mount_context *src);
> +void security_mount_ctx_free(struct mount_context *mc);
> +int security_mount_ctx_option(struct mount_context *mc, char *opt);
> +int security_mount_ctx_kern_mount(struct mount_context *mc, struct super_block *sb);
>  int security_sb_alloc(struct super_block *sb);
>  void security_sb_free(struct super_block *sb);
>  int security_sb_copy_data(char *orig, char *copy);
> @@ -513,6 +519,29 @@ static inline int security_bprm_secureexec(struct linux_binprm *bprm)
>  	return cap_bprm_secureexec(bprm);
>  }
>  
> +static inline int security_mount_ctx_alloc(struct mount_context *mc,
> +					   struct super_block *src_sb)
> +{
> +	return 0;
> +}
> +static inline int security_mount_ctx_dup(struct mount_context *mc,
> +					 struct mount_context *src)
> +{
> +	return 0;
> +}
> +static inline void security_mount_ctx_free(struct mount_context *mc)
> +{
> +}
> +static inline int security_mount_ctx_option(struct mount_context *mc, char *opt)
> +{
> +	return 0;
> +}
> +static inline int security_mount_ctx_kern_mount(struct mount_context *mc,
> +						struct super_block *sb)
> +{
> +	return 0;
> +}
> +
>  static inline int security_sb_alloc(struct super_block *sb)
>  {
>  	return 0;
> diff --git a/security/security.c b/security/security.c
> index 23555c5504f6..2e522361df66 100644
> --- a/security/security.c
> +++ b/security/security.c
> @@ -309,6 +309,31 @@ int security_bprm_secureexec(struct linux_binprm *bprm)
>  	return call_int_hook(bprm_secureexec, 0, bprm);
>  }
>  
> +int security_mount_ctx_alloc(struct mount_context *mc, struct super_block *src_sb)
> +{
> +	return call_int_hook(mount_ctx_alloc, 0, mc, src_sb);
> +}
> +
> +int security_mount_ctx_dup(struct mount_context *mc, struct mount_context *src_mc)
> +{
> +	return call_int_hook(mount_ctx_dup, 0, mc, src_mc);
> +}
> +
> +void security_mount_ctx_free(struct mount_context *mc)
> +{
> +	call_void_hook(mount_ctx_free, mc);
> +}
> +
> +int security_mount_ctx_option(struct mount_context *mc, char *opt)
> +{
> +	return call_int_hook(mount_ctx_option, 0, mc, opt);
> +}
> +
> +int security_mount_ctx_kern_mount(struct mount_context *mc, struct super_block *sb)
> +{
> +	return call_int_hook(mount_ctx_kern_mount, 0, mc, sb);
> +}
> +
>  int security_sb_alloc(struct super_block *sb)
>  {
>  	return call_int_hook(sb_alloc_security, 0, sb);
> @@ -1659,6 +1684,13 @@ struct security_hook_heads security_hook_heads = {
>  		LIST_HEAD_INIT(security_hook_heads.bprm_committing_creds),
>  	.bprm_committed_creds =
>  		LIST_HEAD_INIT(security_hook_heads.bprm_committed_creds),
> +	.mount_ctx_alloc = LIST_HEAD_INIT(security_hook_heads.mount_ctx_alloc),
> +	.mount_ctx_dup = LIST_HEAD_INIT(security_hook_heads.mount_ctx_dup),
> +	.mount_ctx_free = LIST_HEAD_INIT(security_hook_heads.mount_ctx_free),
> +	.mount_ctx_option =
> +		LIST_HEAD_INIT(security_hook_heads.mount_ctx_option),
> +	.mount_ctx_kern_mount =
> +		LIST_HEAD_INIT(security_hook_heads.mount_ctx_kern_mount),
>  	.sb_alloc_security =
>  		LIST_HEAD_INIT(security_hook_heads.sb_alloc_security),
>  	.sb_free_security =
> diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
> index 0c2ac318aa7f..cf38db840f71 100644
> --- a/security/selinux/hooks.c
> +++ b/security/selinux/hooks.c
> @@ -2826,6 +2826,179 @@ static int selinux_umount(struct vfsmount *mnt, int flags)
>  				   FILESYSTEM__UNMOUNT, NULL);
>  }
>  
> +/* fsopen mount context operations */
> +
> +static int selinux_mount_ctx_alloc(struct mount_context *mc,
> +				   struct super_block *src_sb)
> +{
> +	struct security_mnt_opts *opts;
> +
> +	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
> +	if (!opts)
> +		return -ENOMEM;
> +
> +	mc->security = opts;
> +	return 0;
> +}
> +
> +static int selinux_mount_ctx_dup(struct mount_context *mc,
> +				 struct mount_context *src_mc)
> +{
> +	const struct security_mnt_opts *src = src_mc->security;
> +	struct security_mnt_opts *opts;
> +	int i, n;
> +
> +	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
> +	if (!opts)
> +		return -ENOMEM;
> +	mc->security = opts;
> +
> +	if (!src || !src->num_mnt_opts)
> +		return 0;
> +	n = opts->num_mnt_opts = src->num_mnt_opts;
> +
> +	if (opts->mnt_opts) {
> +		opts->mnt_opts = kcalloc(n, sizeof(char *), GFP_KERNEL);
> +		if (!opts->mnt_opts)
> +			return -ENOMEM;
> +
> +		for (i = 0; i < n; i++) {
> +			if (src->mnt_opts[i]) {
> +				opts->mnt_opts[i] = kstrdup(src->mnt_opts[i],
> +							    GFP_KERNEL);
> +				if (!opts->mnt_opts[i])
> +					return -ENOMEM;
> +			}
> +		}
> +	}
> +
> +	if (src->mnt_opts_flags) {
> +		opts->mnt_opts_flags = kmemdup(src->mnt_opts_flags,
> +					       n * sizeof(int), GFP_KERNEL);
> +		if (!opts->mnt_opts_flags)
> +			return -ENOMEM;
> +	}
> +
> +	return 0;
> +}
> +
> +static void selinux_mount_ctx_free(struct mount_context *mc)
> +{
> +	struct security_mnt_opts *opts = mc->security;
> +
> +	security_free_mnt_opts(opts);
> +	mc->security = NULL;
> +}
> +
> +static int selinux_mount_ctx_option(struct mount_context *mc, char *opt)
> +{
> +	struct security_mnt_opts *opts = mc->security;
> +	substring_t args[MAX_OPT_ARGS];
> +	unsigned int have;
> +	char *c, **oo;
> +	void *old;
> +	int token, ctx, i;
> +
> +	token = match_token(opt, tokens, args);
> +	if (token == Opt_error)
> +		return 0; /* Doesn't belong to us. */
> +
> +	have = 0;
> +	for (i = 0; i < opts->num_mnt_opts; i++)
> +		have |= 1 << opts->mnt_opts_flags[i];
> +	if (have & (1 << token)) {
> +		mc->error = "SELinux: Duplicate mount options";
> +		return -EINVAL;
> +	}
> +
> +	switch (token) {
> +	case Opt_context:
> +		if (have & (1 << Opt_defcontext))
> +			goto incompatible;
> +		ctx = CONTEXT_MNT;
> +		goto copy_context_string;
> +
> +	case Opt_fscontext:
> +		ctx = FSCONTEXT_MNT;
> +		goto copy_context_string;
> +
> +	case Opt_rootcontext:
> +		ctx = ROOTCONTEXT_MNT;
> +		goto copy_context_string;
> +
> +	case Opt_defcontext:
> +		if (have & (1 << Opt_context))
> +			goto incompatible;
> +		ctx = DEFCONTEXT_MNT;
> +		goto copy_context_string;
> +
> +	case Opt_labelsupport:
> +		return 1;
> +
> +	default:
> +		mc->error = "SELinux: Unknown mount option";
> +		return -EINVAL;
> +	}
> +
> +copy_context_string:
> +	if (opts->num_mnt_opts > 3) {
> +		mc->error = "SELinux: Too many options";
> +		return -EINVAL;
> +	}
> +	if (!opts->mnt_opts_flags) {
> +		opts->mnt_opts_flags = kcalloc(3, sizeof(int), GFP_KERNEL);
> +		if (!opts->mnt_opts_flags)
> +			return -ENOMEM;
> +	}
> +
> +	if (opts->mnt_opts) {
> +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> +			     GFP_KERNEL);
> +		if (!oo)
> +			return -ENOMEM;
> +		memcpy(oo, opts->mnt_opts, opts->num_mnt_opts * sizeof(char *));
> +		oo[opts->num_mnt_opts] = NULL;
> +		old = opts->mnt_opts;
> +		opts->mnt_opts = oo;
> +		kfree(old);
> +	}
> +
> +	c = match_strdup(&args[0]);
> +	if (!c)
> +		return -ENOMEM;
> +	opts->mnt_opts[opts->num_mnt_opts] = c;
> +	opts->mnt_opts_flags[opts->num_mnt_opts] = ctx;
> +	opts->num_mnt_opts++;
> +	return 1;
> +
> +incompatible:
> +	mc->error = "SELinux: Incompatible mount options";
> +	return -EINVAL;
> +}
> +
> +static int selinux_mount_ctx_kern_mount(struct mount_context *mc,
> +					struct super_block *sb)
> +{
> +	const struct cred *cred = current_cred();
> +	struct common_audit_data ad;
> +	int rc;
> +
> +	rc = selinux_set_mnt_opts(sb, mc->security, 0, NULL);
> +	if (rc)
> +		return rc;
> +
> +	/* Allow all mounts performed by the kernel */
> +	if (mc->ms_flags & MS_KERNMOUNT)
> +		return 0;
> +
> +	ad.type = LSM_AUDIT_DATA_DENTRY;
> +	ad.u.dentry = sb->s_root;
> +	rc = superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
> +	if (rc < 0)
> +		mc->error = "SELinux: Mount of superblock not permitted";
> +	return rc;
> +}
> +
>  /* inode security operations */
>  
>  static int selinux_inode_alloc_security(struct inode *inode)
> @@ -6131,6 +6304,12 @@ static struct security_hook_list selinux_hooks[] = {
>  	LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds),
>  	LSM_HOOK_INIT(bprm_secureexec, selinux_bprm_secureexec),
>  
> +	LSM_HOOK_INIT(mount_ctx_alloc, selinux_mount_ctx_alloc),
> +	LSM_HOOK_INIT(mount_ctx_dup, selinux_mount_ctx_dup),
> +	LSM_HOOK_INIT(mount_ctx_free, selinux_mount_ctx_free),
> +	LSM_HOOK_INIT(mount_ctx_option, selinux_mount_ctx_option),
> +	LSM_HOOK_INIT(mount_ctx_kern_mount, selinux_mount_ctx_kern_mount),
> +
>  	LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security),
>  	LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security),
>  	LSM_HOOK_INIT(sb_copy_data, selinux_sb_copy_data),
> 

Whew, big patch. It all looks fairly sane at first glance though and
it's well documented AFAICT. It would be nice if this were in more
easily digestible chunks, but I don't see how to break it up right
offhand.

Joe Perches May 3, 2017, 6:26 p.m. UTC | #2

On Wed, 2017-05-03 at 14:13 -0400, Jeff Layton wrote:
> On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> > Introduce a mount context concept.

trivia:

> > static int selinux_mount_ctx_option(struct mount_context *mc, char *opt)
> > +{
[]
> > +	if (opts->mnt_opts) {
> > +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> > +			     GFP_KERNEL);
> > +		if (!oo)
> > +			return -ENOMEM;
> > +		memcpy(oo, opts->mnt_opts, opts->num_mnt_opts * sizeof(char *));
> > +		oo[opts->num_mnt_opts] = NULL;
> > +		old = opts->mnt_opts;
> > +		opts->mnt_opts = oo;
> > +		kfree(old);
> > +	}

krealloc would probably be more efficient and possible
readable as likely there's already padding in the original
allocation.

Are there no locking constraints?

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 3, 2017, 6:37 p.m. UTC | #3

Joe Perches <[e-mail]> wrote:

> krealloc would probably be more efficient and possible
> readable as likely there's already padding in the original
> allocation.

The problem is if krealloc() fails: you've lost all those pointers to things
you then need to free.

> Are there no locking constraints?

Generally, no, not until you do the ->mount() op.  Also remounting needs a
lock, but that's already done with the sb->s_umount lock.

However, that said, if you do:

	fd = fsopen("foofs");
	write(fd, "o foo=bar", ...);
	fsmount(fd, "/foo");

then the fsmount() and write() calls have to lock against other fsmount() and
write() calls.  I use the inode lock for this.  [Note that it probably should
be interruptible rather than just killable, but there's no primitive for that
as yet].

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Joe Perches May 3, 2017, 6:43 p.m. UTC | #4

On Wed, 2017-05-03 at 19:37 +0100, David Howells wrote:
> Joe Perches <[e-mail]> wrote:
> 
> > krealloc would probably be more efficient and possible
> > readable as likely there's already padding in the original
> > allocation.
> 
> The problem is if krealloc() fails: you've lost all those pointers to things
> you then need to free.

Huh?  How could that happen?

krealloc must always use a temporary.
If krealloc returns NULL, the original allocation is kept.

> > Are there no locking constraints?
> 
> Generally, no, not until you do the ->mount() op.  Also remounting needs a
> lock, but that's already done with the sb->s_umount lock.
> 
> However, that said, if you do:
> 
> 	fd = fsopen("foofs");
> 	write(fd, "o foo=bar", ...);
> 	fsmount(fd, "/foo");
> 
> then the fsmount() and write() calls have to lock against other fsmount() and
> write() calls.  I use the inode lock for this.  [Note that it probably should
> be interruptible rather than just killable, but there's no primitive for that
> as yet].
> 
> David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 3, 2017, 8:11 p.m. UTC | #5

Joe Perches <[e-mail]> wrote:

> > > krealloc would probably be more efficient and possible
> > > readable as likely there's already padding in the original
> > > allocation.
> > 
> > The problem is if krealloc() fails: you've lost all those pointers to things
> > you then need to free.
> 
> Huh?  How could that happen?
> 
> krealloc must always use a temporary.
> If krealloc returns NULL, the original allocation is kept.

Hmmm...  Good point.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Matthew Wilcox May 3, 2017, 8:38 p.m. UTC | #6

On Wed, May 03, 2017 at 11:26:38AM -0700, Joe Perches wrote:
> On Wed, 2017-05-03 at 14:13 -0400, Jeff Layton wrote:
> > On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> > > +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> > > +			     GFP_KERNEL);

If we're picking nits, then this should be kcalloc in case somebody
passed in 2^31 in num_mnt_opts.

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 3, 2017, 9:17 p.m. UTC | #7

Matthew Wilcox <[e-mail]> wrote:

> On Wed, May 03, 2017 at 11:26:38AM -0700, Joe Perches wrote:
> > On Wed, 2017-05-03 at 14:13 -0400, Jeff Layton wrote:
> > > On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> > > > +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> > > > +			     GFP_KERNEL);
> 
> If we're picking nits, then this should be kcalloc in case somebody
> passed in 2^31 in num_mnt_opts.

A few lines previously there is:

	if (opts->num_mnt_opts > 3) {
		mc->error = "SELinux: Too many options";
		return -EINVAL;
	}

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Joe Perches May 3, 2017, 9:36 p.m. UTC | #8

(adding Julia Lawall and cocci)

On Wed, 2017-05-03 at 13:38 -0700, Matthew Wilcox wrote:
> On Wed, May 03, 2017 at 11:26:38AM -0700, Joe Perches wrote:
> > On Wed, 2017-05-03 at 14:13 -0400, Jeff Layton wrote:
> > > On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> > > > +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> > > > +			     GFP_KERNEL);
> 
> If we're picking nits, then this should be kcalloc in case somebody
> passed in 2^31 in num_mnt_opts.

There are likely dozens to hundreds of possible/silent
multiplication overflow defects in the kernel, not just
in allocations.

Auditing the sources would seem labor intensive.

Perhaps coccinelle could help find them.

Perhaps there should be some overflow checking functions
added to math64.h

Maybe some form like:

u32 u32_mul_u32_u32(u32 a, u32 b)
{
	u32 res = a * b;

	WARN_ON(a != 0 && res / a != b);

	return res;
}

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Rasmus Villemoes May 3, 2017, 9:43 p.m. UTC | #9

On Wed, May 03 2017, David Howells <[e-mail]> wrote:

> fs_type->fsopen() is called to set it up.  fs_type->mc_size says how much
> should be added on to the mount context for the filesystem's use.

This is repeated several times in the documentation, but the code says
that ->mc_size should be the full size of the struct wrapping struct
mount_context.

> diff --git a/fs/mount.h b/fs/mount.h
> index 2826543a131d..b1e99b38f2ee 100644
> --- a/fs/mount.h
> +++ b/fs/mount.h
> @@ -108,9 +108,10 @@ static inline void detach_mounts(struct dentry *dentry)
>  	__detach_mounts(dentry);
>  }
>  
> -static inline void get_mnt_ns(struct mnt_namespace *ns)
> +static inline struct mnt_namespace *get_mnt_ns(struct mnt_namespace *ns)
>  {
>  	atomic_inc(&ns->count);
> +	return ns;
>  }
>
>  extern seqlock_t mount_lock;

it's not much, but at least this could go into a patch of its own.

> +/**
> + * __vfs_fsopen - Open a filesystem and create a mount context
> + * @fs_type: The filesystem type
> + * @src_sb: A superblock from which this one derives (or NULL)
> + * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
> + * @mnt_flags: Mountpoint flags, such as MNT_READONLY
> + * @mount_type: Type of mount
> + *
> + * Open a filesystem and create a mount context.  The mount context is
> + * initialised with the supplied flags and, if a submount/automount from
> + * another superblock (@src_sb), may have parameters such as namespaces copied
> + * across from that superblock.
> + */
> +struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
> +				   struct super_block *src_sb,
> +				   unsigned int ms_flags, unsigned int mnt_flags,
> +				   enum mount_type mount_type)
> +{
> +	struct mount_context *mc;
> +	int ret;
> +
> +	if (fs_type->fsopen && fs_type->mc_size < sizeof(*mc))
> +		BUG();

So ->mc_size can be 0 (i.e. not explicitly initialized) if fs_type does
not have ->fsopen. OK.

> +	mc = kzalloc(max_t(size_t, fs_type->mc_size, sizeof(*mc)), GFP_KERNEL);

In which case we round up to sizeof(*mc). OK.

> +	if (!mc)
> +		return ERR_PTR(-ENOMEM);
> +
> +	mc->mount_type = mount_type;
> +	mc->ms_flags = ms_flags;
> +	mc->mnt_flags = mnt_flags;
> +	mc->fs_type = fs_type;
> +	get_filesystem(fs_type);

Maybe get_filesystem should also be taught to return its argument so
this could be written like the below assignments.

> +	mc->mnt_ns = get_mnt_ns(current->nsproxy->mnt_ns);
> +	mc->pid_ns = get_pid_ns(task_active_pid_ns(current));
> +	mc->net_ns = get_net(current->nsproxy->net_ns);
> +	mc->user_ns = get_user_ns(current_user_ns());
> +	mc->cred = get_current_cred();
> +
> +
> +/**
> + * vfs_dup_mount_context: Duplicate a mount context.
> + * @src: The mount context to copy.
> + */
> +struct mount_context *vfs_dup_mount_context(struct mount_context *src)
> +{
> +	struct mount_context *mc;
> +	int ret;
> +
> +	if (!src->ops->dup)
> +		return ERR_PTR(-ENOTSUPP);
> +
> +	mc = kmemdup(src, src->fs_type->mc_size, GFP_KERNEL);

So this assumes that vfs_dup_mount_context is only used if ->mc_size is
explicitly initialized. A max_t here as well probably wouldn't hurt.

> +	unsigned short mc_size;		/* Size of mount context to allocate */

Any particular reason to use a short? The struct doesn't pack any better.

> +static int selinux_mount_ctx_dup(struct mount_context *mc,
> +				 struct mount_context *src_mc)
> +{
> +	const struct security_mnt_opts *src = src_mc->security;
> +	struct security_mnt_opts *opts;
> +	int i, n;
> +
> +	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
> +	if (!opts)
> +		return -ENOMEM;
> +	mc->security = opts;
> +
> +	if (!src || !src->num_mnt_opts)
> +		return 0;
> +	n = opts->num_mnt_opts = src->num_mnt_opts;
> +
> +	if (opts->mnt_opts) {

should probably be src->mnt_opts

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Julia Lawall May 4, 2017, 6:28 a.m. UTC | #10

On Wed, 3 May 2017, Joe Perches wrote:

> (adding Julia Lawall and cocci)
>
> On Wed, 2017-05-03 at 13:38 -0700, Matthew Wilcox wrote:
> > On Wed, May 03, 2017 at 11:26:38AM -0700, Joe Perches wrote:
> > > On Wed, 2017-05-03 at 14:13 -0400, Jeff Layton wrote:
> > > > On Wed, 2017-05-03 at 17:04 +0100, David Howells wrote:
> > > > > +		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
> > > > > +			     GFP_KERNEL);
> >
> > If we're picking nits, then this should be kcalloc in case somebody
> > passed in 2^31 in num_mnt_opts.
>
> There are likely dozens to hundreds of possible/silent
> multiplication overflow defects in the kernel, not just
> in allocations.
>
> Auditing the sources would seem labor intensive.
>
> Perhaps coccinelle could help find them.
>
> Perhaps there should be some overflow checking functions
> added to math64.h
>
> Maybe some form like:
>
> u32 u32_mul_u32_u32(u32 a, u32 b)
> {
> 	u32 res = a * b;
>
> 	WARN_ON(a != 0 && res / a != b);
>
> 	return res;
> }

Coccinelle doesn't kow about the values of variables.  It would need some
heuristics about where potentially large values can come from.

julia

David Howells May 4, 2017, 9:27 a.m. UTC | #11

Joe Perches <[e-mail]> wrote:

> krealloc would probably be more efficient and possible
> readable as likely there's already padding in the original
> allocation.

Given there's a maximum of 3 slots, I think it makes better sense to just
allocate them all up front.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 4, 2017, 10:22 a.m. UTC | #12

Rasmus Villemoes <[e-mail]> wrote:

> > +	if (fs_type->fsopen && fs_type->mc_size < sizeof(*mc))
> > +		BUG();
> 
> So ->mc_size can be 0 (i.e. not explicitly initialized) if fs_type does
> not have ->fsopen. OK.

I need to be able to handle filesystems that don't support this yet.  Once all
filesystems support this, I would be able to take away the max_t() thing.

> > +	if (!src->ops->dup)
> > +		return ERR_PTR(-ENOTSUPP);
> > +
> > +	mc = kmemdup(src, src->fs_type->mc_size, GFP_KERNEL);
> 
> So this assumes that vfs_dup_mount_context is only used if ->mc_size is
> explicitly initialized. A max_t here as well probably wouldn't hurt.

If you don't provide an ->fsopen() op, you can't set src->ops, you don't see a
mount context and you can't call this function.  If you did supply an
->fsopen() op, the BUG() would've got you if you didn't set ->mc_size.

> > +	unsigned short mc_size;		/* Size of mount context to allocate */
> 
> Any particular reason to use a short? The struct doesn't pack any better.

But it leaves a hole someone else can use.  I try not to use fields larger
than I need to.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Joe Perches May 4, 2017, 2:34 p.m. UTC | #13

On Thu, 2017-05-04 at 10:27 +0100, David Howells wrote:
> Joe Perches <[e-mail]> wrote:
> 
> > krealloc would probably be more efficient and possible
> > readable as likely there's already padding in the original
> > allocation.
> 
> Given there's a maximum of 3 slots, I think it makes better sense to just
> allocate them all up front.

Sounds good to me.
Simpler is frequently better.

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 8, 2017, 3:05 p.m. UTC | #14

On Wed, May 3, 2017 at 6:04 PM, David Howells <[e-mail]> wrote:
> Introduce a mount context concept.  This is allocated at the beginning of
> the mount procedure and into it is placed:
>
>  (1) Filesystem type.
>
>  (2) Namespaces.
>
>  (3) Device name.
>
>  (4) Superblock flags (MS_*) and mount flags (MNT_*).
>
>  (5) Security details.
>
>  (6) Filesystem-specific data, as set by the mount options.
>
> It also gives a place in which to hang an error message for later retrieval
> (see the mount-by-fd syscall later in this series).
>
> Rather than calling fs_type->mount(), a mount_context struct is created and
> fs_type->fsopen() is called to set it up.  fs_type->mc_size says how much
> should be added on to the mount context for the filesystem's use.
>
> A set of operations have to be set by ->fsopen() to provide freeing,
> duplication, option parsing, binary data parsing, validation, mounting and
> superblock filling.
>
> It should be noted that, whilst this patch adds a lot of lines of code,
> there is quite a bit of duplication with existing code that can be
> eliminated should all filesystems be converted over.
>
> Signed-off-by: David Howells <[e-mail]>
> ---
>
>  Documentation/filesystems/mounting.txt |  445 ++++++++++++++++++++++++++++++++
>  fs/Makefile                            |    3
>  fs/internal.h                          |    2
>  fs/mount.h                             |    3
>  fs/mount_context.c                     |  343 +++++++++++++++++++++++++
>  fs/namespace.c                         |  270 +++++++++++++++++--
>  fs/super.c                             |   50 +++-
>  include/linux/fs.h                     |   11 +
>  include/linux/lsm_hooks.h              |   37 +++
>  include/linux/mount.h                  |   67 +++++
>  include/linux/security.h               |   29 ++
>  security/security.c                    |   32 ++
>  security/selinux/hooks.c               |  179 +++++++++++++
>  13 files changed, 1435 insertions(+), 36 deletions(-)
>  create mode 100644 Documentation/filesystems/mounting.txt
>  create mode 100644 fs/mount_context.c
>
> diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
> new file mode 100644
> index 000000000000..a942ccd08376
> --- /dev/null
> +++ b/Documentation/filesystems/mounting.txt
> @@ -0,0 +1,445 @@
> +                             ===================
> +                             FILESYSTEM MOUNTING
> +                             ===================
> +
> +CONTENTS
> +
> + (1) Overview.
> +
> + (2) The mount context.
> +
> + (3) The mount context operations.
> +
> + (4) Mount context security.
> +
> + (5) VFS mount context operations.
> +
> +
> +========
> +OVERVIEW
> +========
> +
> +The creation of new mounts is now to be done in a multistep process:
> +
> + (1) Create a mount context.
> +
> + (2) Parse the options and attach them to the mount context.  Options may be
> +     passed individually from userspace.
> +
> + (3) Validate and pre-process the mount context.

(3.5) Create super block

I think this need to be triggered by something like a "commit" command
from userspace.  Basically this is where the options are atomically
set on the new (create) or existing (reconfigure) superblock.

> +
> + (4) Perform the mount.
> +
> + (5) Return an error message attached to the mount context.

Swap the order of the above.  There's no fs specific actions performed
at fsmount() time, and normal errno reporting should be perfectly
fine.

> +
> + (6) Destroy the mount context.
> +
> +To support this, the file_system_type struct gains two new fields:
> +
> +       unsigned short mc_size;
> +
> +which indicates how much space the filesystem would like tacked onto the end of
> +the mount_context struct for its own purposes, and:
> +
> +       int (*fsopen)(struct mount_context *mc, struct super_block *src_sb);
> +
> +which is invoked to set up the filesystem-specific parts of a mount context,
> +including the additional space.  The src_sb parameter is used to convey the
> +superblock from which the filesystem may draw extra information (such as
> +namespaces), for submount (MS_SUBMOUNT) or remount (MS_REMOUNT) purposes or it
> +will be NULL.

I think reconfigure (don't call it remount, there's no "mounting"
going on there) should start out with a context populated with with
the current state of the superblock.  User can then reset and start
over or individually add/remove options.   This should be a good place
to allow querying the options as well, as Karel suggested.  Then when
the configuration is finished the changes are committed to the
superblock.

> +
> +Note that security initialisation is done *after* the filesystem is called so
> +that the namespaces may be adjusted first.
> +
> +And the super_operations struct gains one:
> +
> +       int (*remount_fs_mc) (struct super_block *, struct mount_context *);
> +
> +This shadows the ->remount_fs() operation and takes a prepared mount context
> +instead of the mount flags and data page.  It may modify the ms_flags in the
> +context for the caller to pick up.
> +
> +[NOTE] remount_fs_mc is intended as a replacement for remount_fs.
> +
> +
> +=================
> +THE MOUNT CONTEXT
> +=================
> +
> +The mount process is governed by a mount context.  This is represented by the
> +mount_context structure:
> +
> +       struct mount_context {
> +               const struct mount_context_operations *ops;
> +               struct file_system_type *fs;
> +               struct user_namespace   *user_ns;
> +               struct mnt_namespace    *mnt_ns;
> +               struct pid_namespace    *pid_ns;
> +               struct net              *net_ns;
> +               const struct cred       *cred;
> +               char                    *device;
> +               char                    *root_path;
> +               void                    *security;
> +               const char              *error;
> +               unsigned int            ms_flags;
> +               unsigned int            mnt_flags;
> +               bool                    mounted;
> +               bool                    sloppy;
> +               bool                    silent;
> +               enum mount_type         mount_type : 8;
> +       };
> +
> +When allocated, the mount_context struct is extended by ->mc_size bytes as
> +specified by the specified file_system_type struct.  This is for use by the
> +filesystem.  The filesystem should wrap the struct in its own, e.g.:
> +
> +       struct nfs_mount_context {
> +               struct mount_context mc;
> +               ...
> +       };
> +
> +placing the mount_context struct first.  container_of() can then be used.
> +
> +The mount_context fields are as follows:
> +
> + (*) const struct mount_context_operations *ops
> +
> +     These are operations that can be done on a mount context.  See below.
> +     This must be set by the ->fsopen() file_system_type operation.
> +
> + (*) struct file_system_type *fs
> +
> +     A pointer to the file_system_type of the filesystem that is being
> +     mounted.  This retains a ref on the type owner.
> +
> + (*) struct user_namespace *user_ns
> + (*) struct mnt_namespace *mnt_ns
> + (*) struct pid_namespace *pid_ns
> + (*) struct net *net_ns
> +
> +     This is a subset of the namespaces in use by the invoking process.  This
> +     retains a ref on each namespace.  The subscribed namespaces may be
> +     replaced by the filesystem to reflect other sources, such as the parent
> +     mount superblock on an automount.
> +
> + (*) struct cred *cred
> +
> +     The mounter's credentials.  This retains a ref on the credentials.
> +
> + (*) char *device
> +
> +     This is the device to be mounted.  It may be a block device
> +     (e.g. /dev/sda1) or something more exotic, such as the "host:/path" that
> +     NFS desires.
> +
> + (*) char *root_path
> +
> +     A path to the place inside the filesystem to actually mount.  This allows
> +     a mount and bind-mount to be combined.
> +
> +     [NOTE] This isn't implemented yet, but NFS has the code to do this which
> +     could be moved to the VFS.
> +
> + (*) void *security
> +
> +     A place for the LSMs to hang their security data for the mount.  The
> +     relevant security operations are described below.
> +
> + (*) const char *error
> +
> +     A place for the VFS and the filesystem to hang an error message.  This
> +     should be in the form of a static string that doesn't need deallocation
> +     and the pointer to which can just be overwritten.  Under some
> +     circumstances, this can be retrieved by userspace.
> +
> +     Note that the existence of the error string is expected to be guaranteed
> +     by the reference on the file_system_type object held by ->fs or any
> +     filesystem-specific reference held in the filesystem context until the
> +     ->free() operation is called.
> +
> + (*) unsigned int ms_flags
> + (*) unsigned int mnt_flags
> +
> +     These hold the mount flags.  ms_flags holds MS_* flags and mnt_flags holds
> +     MNT_* flags.
> +
> + (*) bool mounted
> +
> +     This is set to true once a mount attempt is made.  This causes an error to
> +     be given on subsequent mount attempts with the same context and prevents
> +     multiple mount attempts.

No point.  A context is mountable if the superblock is non-NULL.
Don't even need to have the context committed, if not, it would simply
mount the sb in the previous state.

I'd hope some simplifications would fall out from this model.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 8, 2017, 10:57 p.m. UTC | #15

Miklos Szeredi <[e-mail]> wrote:

> > + (3) Validate and pre-process the mount context.
> 
> (3.5) Create super block
> 
> I think this need to be triggered by something like a "commit" command
> from userspace.  Basically this is where the options are atomically
> set on the new (create) or existing (reconfigure) superblock.

Why do you need to expose this step to userspace?  Assuming in the "new" case
you do, say:

	fd = fsopen("nfs");
	write(fd, "s foo.bar:/bar", ...);
	write(fd, "o intr", ...);
	write(fd, "o fsc", ...);
	...
	write(fd, "c", ...); /* commit operation to get a superblock */
	fsmount(fd, AT_FDCWD, "/mnt");  /* mount the superblock we just got */

Then the "commit" op is dissimilar to "mount -o remount" since remount may
alter the superblock parameters *and* the mountpoint parameters, but commit
can only affect the superblock.

On the other hand, I could see that you might want to do:

	fd = fsopen("nfs");
	...
	write(fd, "c", ...); /* commit operation to get a superblock */
	fstatfs(fd, &buf); /* get info about the superblock */
	fsmount(fd, AT_FDCWD, "/mnt");  /* mount the superblock we just got */

> > + (4) Perform the mount.
> > +
> > + (5) Return an error message attached to the mount context.
> 
> Swap the order of the above.  There's no fs specific actions performed
> at fsmount() time, and normal errno reporting should be perfectly
> fine.

There's no reason not to allow error messages to be attached by the actual
vfsmount creation and insertion - and reasons that one might want to do so.
Think LSMs, for instance.  We don't look up the mountpoint until this point,
and so we can't do the security checks on them till this point.  It could make
it easier to debug problems if we can return a more comprehensive message at
this point.

> I think reconfigure (don't call it remount, there's no "mounting"
> going on there)

There's adjustment of the vfsmount structure too; besides, it is called
MS_REMOUNT in the UAPI and "mount -o remount", so we're somewhat stuck with
the label whether we like it or not.

> should start out with a context populated with with the current state of the
> superblock.

Hence why ->fsopen() takes a super_block parameter.

> User can then reset and start over

No, not really.  You cannot reset all options - the source for example,
probably has to remain the same.  IP addresses on NFS mounts possibly should
remain the same - though I can see situations where it might be convenient to
change these.

> or individually add/remove options.

This is very per-filesystem-type dependent.

> This should be a good place to allow querying the options as well, as Karel
> suggested.

I'm not sure it's worth the code unless we allow opening extant mounts and
querying using this mechanism.

> Then when the configuration is finished the changes are committed to the
> superblock.

You're going a lot beyond remount here.  Remount can, in one go, change some
options which are superblock-only, some options which are mountpoint-only and
at least one which crosses both domains.

> > + (*) bool mounted
> > +
> > +     This is set to true once a mount attempt is made.  This causes an error to
> > +     be given on subsequent mount attempts with the same context and prevents
> > +     multiple mount attempts.
> 
> No point.  A context is mountable if the superblock is non-NULL.
> Don't even need to have the context committed,

Ummm...  Doesn't that render "commit" unnecessary?

> if not, it would simply mount the sb in the previous state.

You want to be able to open a filesystem fd, create or reference a superblock
and then mount it several times?

> I'd hope some simplifications would fall out from this model.

Not really.  It makes things slightly less simple, particularly with the
"commit" operation that you want.  I'm not sure that sys_mount() and
sys_fsmount() will be able to share as much code.

It also makes the remount process less similar to the mount process because
the "commit" operation doesn't seem useful in the former because remount also
alters the vfsmount.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 9, 2017, 8:03 a.m. UTC | #16

On Tue, May 9, 2017 at 12:57 AM, David Howells <[e-mail]> wrote:
> Miklos Szeredi <[e-mail]> wrote:
>
>> > + (3) Validate and pre-process the mount context.
>>
>> (3.5) Create super block
>>
>> I think this need to be triggered by something like a "commit" command
>> from userspace.  Basically this is where the options are atomically
>> set on the new (create) or existing (reconfigure) superblock.
>
> Why do you need to expose this step to userspace?  Assuming in the "new" case
> you do, say:
>
>         fd = fsopen("nfs");
>         write(fd, "s foo.bar:/bar", ...);
>         write(fd, "o intr", ...);
>         write(fd, "o fsc", ...);
>         ...
>         write(fd, "c", ...); /* commit operation to get a superblock */
>         fsmount(fd, AT_FDCWD, "/mnt");  /* mount the superblock we just got */
>
> Then the "commit" op is dissimilar to "mount -o remount" since remount may
> alter the superblock parameters *and* the mountpoint parameters, but commit
> can only affect the superblock.

Forget remount, it's a historical remnant.  We need fsreconfig(sb) and
setmntattr(mnt).  They are changing properties of different objects.
Remount is like fcntl(fd, F_SETFL) and fchmod(fd, ...) rolled into
one.   They have nothing in common except the fact that the old
mount(2) API included both in one single operation, and I'm sure that
was a "oh we don't want to introduce a new flag for this, so lets
reuse the old one" sort of design decision.

>
> On the other hand, I could see that you might want to do:
>
>         fd = fsopen("nfs");
>         ...
>         write(fd, "c", ...); /* commit operation to get a superblock */
>         fstatfs(fd, &buf); /* get info about the superblock */
>         fsmount(fd, AT_FDCWD, "/mnt");  /* mount the superblock we just got */
>
>> > + (4) Perform the mount.
>> > +
>> > + (5) Return an error message attached to the mount context.
>>
>> Swap the order of the above.  There's no fs specific actions performed
>> at fsmount() time, and normal errno reporting should be perfectly
>> fine.
>
> There's no reason not to allow error messages to be attached by the actual
> vfsmount creation and insertion - and reasons that one might want to do so.
> Think LSMs, for instance.  We don't look up the mountpoint until this point,
> and so we can't do the security checks on them till this point.  It could make
> it easier to debug problems if we can return a more comprehensive message at
> this point.

I think that's crazy.  We don't return detailed errors for any other
syscall for path lookup, so why would path lookup for mount be
special.

And why would

    fd = open("/foo/bar", O_PATH);
    fsmount(fsfd, fd, NULL);

behave differently from

    fsmount(fsfd, -1, "/foo/bar");

?

>
>> I think reconfigure (don't call it remount, there's no "mounting"
>> going on there)
>
> There's adjustment of the vfsmount structure too; besides, it is called
> MS_REMOUNT in the UAPI and "mount -o remount", so we're somewhat stuck with
> the label whether we like it or not.

Oh, uapi compatibility: they can use the old mount(2) API for that and
introduce saner utils for the new stuff.  I'm sure we don't need to be
100% feature compatible with old  mount(2).

What we need is mount(2) to stay 100% compatible with itself while the
kernel internal APIs are reshuffled.


>> should start out with a context populated with with the current state of the
>> superblock.
>
> Hence why ->fsopen() takes a super_block parameter.
>
>> User can then reset and start over
>
> No, not really.  You cannot reset all options - the source for example,
> probably has to remain the same.  IP addresses on NFS mounts possibly should
> remain the same - though I can see situations where it might be convenient to
> change these.

Well, the current remount API is like that: you give a new set of
options (i.e. reset and replace anything that can be changed and leave
the rest).  Obviously "reset options" wouldn't allow you to change
options that cannot be changed.

>
>> or individually add/remove options.
>
> This is very per-filesystem-type dependent.

So say we have commands like

"o+ foo"
"o- bar"

The generic option parser would just add or remove the option in the
current set of options, and commit would just call ->remount_fs() with
the new set of options.  It would probably not work for the NFS case,
but that's okay, NFS can implement its own option parsing.

>> This should be a good place to allow querying the options as well, as Karel
>> suggested.
>
> I'm not sure it's worth the code unless we allow opening extant mounts and
> querying using this mechanism.

I'm saying we should allow opening an existent superblock and allow
query and change of options.

>> Then when the configuration is finished the changes are committed to the
>> superblock.
>
> You're going a lot beyond remount here.  Remount can, in one go, change some
> options which are superblock-only, some options which are mountpoint-only and
> at least one which crosses both domains.

We'll have s_op->remount_fs() for some time yet, but that's a clean,
super-block only operation.  MS_REMOUNT is a flag from hell, leave
that for mount(2) compatibility and forget it for the new API.

>
>> > + (*) bool mounted
>> > +
>> > +     This is set to true once a mount attempt is made.  This causes an error to
>> > +     be given on subsequent mount attempts with the same context and prevents
>> > +     multiple mount attempts.
>>
>> No point.  A context is mountable if the superblock is non-NULL.
>> Don't even need to have the context committed,
>
> Ummm...  Doesn't that render "commit" unnecessary?

No.   "commit" is a superblock operation.  fsmount() is a mount
operation.    fsmount() should not do anything to the superblock and
"commit" should not do anything to any mount.

>> if not, it would simply mount the sb in the previous state.
>
> You want to be able to open a filesystem fd, create or reference a superblock
> and then mount it several times?

Maybe.  I'm looking at this from the point of view of what objects we
have and what operations we want to do on them.  In that view it makes
no sense that fsmount() changes the state of the fsfd, since it's an
operation done on the mount tree and not on the superblock
configuration context.  The fact that you can do any number of mounts
on the fsfd just falls out from this premise.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 9, 2017, 9:32 a.m. UTC | #17

Miklos Szeredi <[e-mail]> wrote:

> Forget remount, it's a historical remnant.

I don't think it can't be set aside so lightly.  Within the kernel, the option
parsing should share as much code as possible between new superblock config,
old new mount and old remount.

The 'trickiest' function we need to support is MS_RDONLY flipping.  That one
affects both the mount and the superblock.  I think all the rest only affect
one side or the other.

Given that a superblock can be mounted in multiple places, do we need to count
the number of read-only mounts that are holding a particular superblock and
only flip the superblock when they're all read-only?

Or do you advocate replacing "mount -o remount,[ro|rw]" with a pair of
operations - one to flip the mount and the other to flip the superblock?

Further, "emergency remount r/o" needs to be supported - though it might make
sense to add a special op just for that.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 9, 2017, 9:41 a.m. UTC | #18

Miklos Szeredi <[e-mail]> wrote:

> I think that's crazy.  We don't return detailed errors for any other
> syscall for path lookup, so why would path lookup for mount be
> special.

Firstly, we don't return detailed errors for mount() at the moment either.

Secondly, path lookup might entail automounts, so perhaps we should do it for
path lookup too.  Particularly in light of the fact that NFS4 mount uses
pathwalk to get from server:/ to server:/the/dir/I/actually/wanted/ so I'm
currently losing that error:-/

Thirdly, the security operation I'm talking about is separate to path lookup -
though perhaps we should pass LOOKUP_MOUNT as an intent flag into pathwalk so
that the security check can be done there; perhaps combined with another one.

Fourthly, why shouldn't we consider extending the facility to other system
calls in future?  It would involve copying the string to task_struct and
providing a way to retrieve it, but that's not that hard to achieve.

> And why would
> 
>     fd = open("/foo/bar", O_PATH);
>     fsmount(fsfd, fd, NULL);
> 
> behave differently from
> 
>     fsmount(fsfd, -1, "/foo/bar");
> 
> ?

There's argument that the former should return EFAULT.  And that you should
set the path to "" and pass AT_EMPTY_PATH.  I should probably make sure it
does that - and add a flags field.  statx() was fixed to work this way.

Question for you: Should the MNT_* flags be passed to fsmount(), perhaps in
MS_* form?

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 9, 2017, 9:56 a.m. UTC | #19

Miklos Szeredi <[e-mail]> wrote:

> So say we have commands like
> 
> "o+ foo"
> "o- bar"

The convention seems to be to prepend "no" to things you want to disable, so
let's stick with that, e.g.:

	"o foo"
	"o nobar"

otherwise we will have to have separate parsers for old mount() and the new sb
config code - and not just for NFS, but at least for ext2/3/4 also.

Further, we can only publish one format in /proc/mounts - and we cannot change
that from the foo/nofoo standard we already use as it's part of the UAPI.

> The generic option parser would just add or remove the option in the
> current set of options,

It sounds like you want to build up a string of "opt1,opt2,opt3" then have the
VFS add and remove things from it and then parse it into the filesystem's
internal structures on "commit".

> and commit would just call ->remount_fs() with the new set of options.

You're defining "commit" to do different things depending on the situation.
You need a separation between "commit create" and "commit update".

> It would probably not work for the NFS case, but that's okay, NFS can
> implement its own option parsing.

If NFS has to implement its own option parsing, we've done it wrong.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 9, 2017, 11:04 a.m. UTC | #20

On Tue, May 9, 2017 at 11:32 AM, David Howells <[e-mail]> wrote:
> Miklos Szeredi <[e-mail]> wrote:
>
>> Forget remount, it's a historical remnant.
>
> I don't think it can't be set aside so lightly.  Within the kernel, the option
> parsing should share as much code as possible between new superblock config,
> old new mount and old remount.

Lets make things clear:  VFS didn't do any option parsing for
mount(2), it was all in filesystem's fstype->mount() and
s_op->remount_fs() operations.  What the VFS did do is filter out the
junk from MS_xxx options and pass only the relevant ones to the
filesystem creation functions, which was mount_fs() and
do_remount_sb().   Note how those functions are in super.c and don't
have a vfsmount argument.

So I propose introducing a third way of parsing arguments, which a
filesystem may implement via sb_config_ops (or whatever we want to
call it) that allows it to parse options into its internal structures
and have it be passed to superblock creation and superblock
reconfiguration ops (which also need to be new ones, that thake the
parsed options in the sb_config structure instead of as a comma
delimited string).  With the fsopen() API the generic code (possibly
via helpers called from fs code) would need to parse the "MS_xxx" type
options now, and the infrastructure for that is new, since previously
those options were parsed in userland instead of in the kernel.

There would be no duplication as filesystems would either implement
the old option parsing or the new one.

Also we could have various helpers that do most of the dirty work of
option parsing, allowing easy migration of filesystems.   In the end
the old method taking the unparsed options can go away.

And, as you say, the option parsing would be shared between old "new
mount", old "remount" and new sb config.  And it would be shared for
the unmigrated fs case as well as the migrated fs case.

And we are still only taking about sb config, not a word about mount
attributes; they should be irrelevant to any of this API shuffling and
new API additions.

> The 'trickiest' function we need to support is MS_RDONLY flipping.  That one
> affects both the mount and the superblock.  I think all the rest only affect
> one side or the other.
>
> Given that a superblock can be mounted in multiple places, do we need to count
> the number of read-only mounts that are holding a particular superblock and
> only flip the superblock when they're all read-only?

Nothing special going on here.  If sb is ro then adding a rw mount
should either fail or automatically go ro.  I think just erroring out
is the better of the two.


> Or do you advocate replacing "mount -o remount,[ro|rw]" with a pair of
> operations - one to flip the mount and the other to flip the superblock?

Yes, definitely.  That's exactly what users have been asking for
(there's even a bugzilla somewhere I don't remember)

Thanks
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 9, 2017, 12:02 p.m. UTC | #21

On Tue, May 9, 2017 at 11:41 AM, David Howells <[e-mail]> wrote:
> Miklos Szeredi <[e-mail]> wrote:
>
>> I think that's crazy.  We don't return detailed errors for any other
>> syscall for path lookup, so why would path lookup for mount be
>> special.
>
> Firstly, we don't return detailed errors for mount() at the moment either.
>
> Secondly, path lookup might entail automounts, so perhaps we should do it for
> path lookup too.  Particularly in light of the fact that NFS4 mount uses
> pathwalk to get from server:/ to server:/the/dir/I/actually/wanted/ so I'm
> currently losing that error:-/
>
> Thirdly, the security operation I'm talking about is separate to path lookup -
> though perhaps we should pass LOOKUP_MOUNT as an intent flag into pathwalk so
> that the security check can be done there; perhaps combined with another one.
>
> Fourthly, why shouldn't we consider extending the facility to other system
> calls in future?  It would involve copying the string to task_struct and
> providing a way to retrieve it, but that's not that hard to achieve.

Maybe we should.   In fact that sounds like a splendid idea.  IMO even
better, than having errors go via the fsfd descriptor.  Pretty cheap
on the kernel side, and completely optional on the userspace side.

>
>> And why would
>>
>>     fd = open("/foo/bar", O_PATH);
>>     fsmount(fsfd, fd, NULL);
>>
>> behave differently from
>>
>>     fsmount(fsfd, -1, "/foo/bar");
>>
>> ?
>
> There's argument that the former should return EFAULT.  And that you should
> set the path to "" and pass AT_EMPTY_PATH.  I should probably make sure it
> does that - and add a flags field.  statx() was fixed to work this way.
>
> Question for you: Should the MNT_* flags be passed to fsmount(), perhaps in
> MS_* form?

MS_* flags are a mess.  I don't think they should be used for any new
functionality.  MNT_* flags are much better, but there are some
internal flags there as well.

I think the struct file model is better, where we have the external
O_* flags and the internal FMODE_* flags.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 9, 2017, 12:38 p.m. UTC | #22

On Tue, May 9, 2017 at 11:56 AM, David Howells <[e-mail]> wrote:
> Miklos Szeredi <[e-mail]> wrote:
>
>> So say we have commands like
>>
>> "o+ foo"
>> "o- bar"
>
> The convention seems to be to prepend "no" to things you want to disable, so
> let's stick with that, e.g.:
>
>         "o foo"
>         "o nobar"
>
> otherwise we will have to have separate parsers for old mount() and the new sb
> config code - and not just for NFS, but at least for ext2/3/4 also.
>
> Further, we can only publish one format in /proc/mounts - and we cannot change
> that from the foo/nofoo standard we already use as it's part of the UAPI.

You're right, that this is a complicated issue and worth more
discussion.  And also you are right that we cannot change existing
UAPI, which is going to cause some headaches.

But that doesn't mean the new UAPI must follow the conventions of the
badly defined existing UAPI.

And the "no*" convention is anything but well defined, so we cannot
just stick it into generic code, because you'll find exceptions
everywhere.

And one more reason to have a new, unambiguous UAPI for retrieving
superblock options.

>
>> The generic option parser would just add or remove the option in the
>> current set of options,
>
> It sounds like you want to build up a string of "opt1,opt2,opt3" then have the
> VFS add and remove things from it and then parse it into the filesystem's
> internal structures on "commit".

That would be the default operation, if the filesystem doesn't define
its own parser.

>> and commit would just call ->remount_fs() with the new set of options.
>
> You're defining "commit" to do different things depending on the situation.
> You need a separation between "commit create" and "commit update".

It would be different, yes, at least until the superblock creation api
is completely transformed, at which point it may actually become the
same thing.  But lets not jump ahead.

>> It would probably not work for the NFS case, but that's okay, NFS can
>> implement its own option parsing.
>
> If NFS has to implement its own option parsing, we've done it wrong.

My above sentence was not clear.  What I meant to say that NFS needs
to implement the non-generic option parsing function in order to be
able to handle the case of "you can't change the server IP address".
Which it would want to do anyway, since it will result in cleaner
code.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Jeff Layton May 9, 2017, 6:51 p.m. UTC | #23

On Tue, 2017-05-09 at 14:02 +0200, Miklos Szeredi wrote:
> On Tue, May 9, 2017 at 11:41 AM, David Howells <[e-mail]> wrote:
> > Miklos Szeredi <[e-mail]> wrote:
> > 
> > > I think that's crazy.  We don't return detailed errors for any other
> > > syscall for path lookup, so why would path lookup for mount be
> > > special.
> > 
> > Firstly, we don't return detailed errors for mount() at the moment either.
> > 
> > Secondly, path lookup might entail automounts, so perhaps we should do it for
> > path lookup too.  Particularly in light of the fact that NFS4 mount uses
> > pathwalk to get from server:/ to server:/the/dir/I/actually/wanted/ so I'm
> > currently losing that error:-/
> > 
> > Thirdly, the security operation I'm talking about is separate to path lookup -
> > though perhaps we should pass LOOKUP_MOUNT as an intent flag into pathwalk so
> > that the security check can be done there; perhaps combined with another one.
> > 
> > Fourthly, why shouldn't we consider extending the facility to other system
> > calls in future?  It would involve copying the string to task_struct and
> > providing a way to retrieve it, but that's not that hard to achieve.
> 
> Maybe we should.   In fact that sounds like a splendid idea.  IMO even
> better, than having errors go via the fsfd descriptor.  Pretty cheap
> on the kernel side, and completely optional on the userspace side.
> 

A question here: What should happen if you go to set an error here, and
one is already set? Should it just free the string and replace it with
the new one? IOW, just keep the latest error? Or is it better to keep
the earlier one?

If you want to put this in the task_struct then I think you'll want to
sort that out. You could easily end up in this situation if a lot of
different kernel subsystems started using it to pass back detailed
errors.

> > 
> > > And why would
> > > 
> > >     fd = open("/foo/bar", O_PATH);
> > >     fsmount(fsfd, fd, NULL);
> > > 
> > > behave differently from
> > > 
> > >     fsmount(fsfd, -1, "/foo/bar");
> > > 
> > > ?
> > 
> > There's argument that the former should return EFAULT.  And that you should
> > set the path to "" and pass AT_EMPTY_PATH.  I should probably make sure it
> > does that - and add a flags field.  statx() was fixed to work this way.
> > 
> > Question for you: Should the MNT_* flags be passed to fsmount(), perhaps in
> > MS_* form?
> 
> MS_* flags are a mess.  I don't think they should be used for any new
> functionality.  MNT_* flags are much better, but there are some
> internal flags there as well.
> 
> I think the struct file model is better, where we have the external
> O_* flags and the internal FMODE_* flags.
> 
> Thanks,
> Miklos
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to [e-mail]
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 10, 2017, 7:24 a.m. UTC | #24

On Tue, May 9, 2017 at 8:51 PM, Jeff Layton <[e-mail]> wrote:
> On Tue, 2017-05-09 at 14:02 +0200, Miklos Szeredi wrote:
>> On Tue, May 9, 2017 at 11:41 AM, David Howells <[e-mail]> wrote:
>> > Miklos Szeredi <[e-mail]> wrote:
>> >
>> > > I think that's crazy.  We don't return detailed errors for any other
>> > > syscall for path lookup, so why would path lookup for mount be
>> > > special.
>> >
>> > Firstly, we don't return detailed errors for mount() at the moment either.
>> >
>> > Secondly, path lookup might entail automounts, so perhaps we should do it for
>> > path lookup too.  Particularly in light of the fact that NFS4 mount uses
>> > pathwalk to get from server:/ to server:/the/dir/I/actually/wanted/ so I'm
>> > currently losing that error:-/
>> >
>> > Thirdly, the security operation I'm talking about is separate to path lookup -
>> > though perhaps we should pass LOOKUP_MOUNT as an intent flag into pathwalk so
>> > that the security check can be done there; perhaps combined with another one.
>> >
>> > Fourthly, why shouldn't we consider extending the facility to other system
>> > calls in future?  It would involve copying the string to task_struct and
>> > providing a way to retrieve it, but that's not that hard to achieve.
>>
>> Maybe we should.   In fact that sounds like a splendid idea.  IMO even
>> better, than having errors go via the fsfd descriptor.  Pretty cheap
>> on the kernel side, and completely optional on the userspace side.
>>
>
> A question here: What should happen if you go to set an error here, and
> one is already set? Should it just free the string and replace it with
> the new one? IOW, just keep the latest error? Or is it better to keep
> the earlier one?
>
> If you want to put this in the task_struct then I think you'll want to
> sort that out. You could easily end up in this situation if a lot of
> different kernel subsystems started using it to pass back detailed
> errors.

Possible rule of thumb: use it only at the place where the error
originates and not where errors are just passed on.  This would result
in at most one report per syscall, normally.

And the static string thing that David implemented is also a very good
idea, IMO.

So it would look something like this (possibly needs better naming:

   error_detail("description of error");

or

   return error_detail(-EINVAL, "description of error");

Compiler could automatically include source file/line information as
well, although it may be enough if the string is uniquely greppable
(we could check uniqueness at compile time).

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 10, 2017, 8:05 a.m. UTC | #25

Miklos Szeredi <[e-mail]> wrote:

> And the static string thing that David implemented is also a very good
> idea, IMO.

There is an issue with it: it's fine as long as you keep a ref on the module
that generated it or clear all strings as part of module removal (which the
mount context in this patchset does).  With the NFS mount context I did, I
have to keep a ref on the NFS protocol module as well as the NFS filesystem
module.

I'm tempted to make it conditionally copy the string using kvasprintf_const()
- which would also permit format substitution.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Karel Zak May 10, 2017, 12:41 p.m. UTC | #26

On Tue, May 09, 2017 at 10:03:43AM +0200, Miklos Szeredi wrote:
> On Tue, May 9, 2017 at 12:57 AM, David Howells <[e-mail]> wrote:
> > Miklos Szeredi <[e-mail]> wrote:
> >
> >> > + (3) Validate and pre-process the mount context.
> >>
> >> (3.5) Create super block
> >>
> >> I think this need to be triggered by something like a "commit" command
> >> from userspace.  Basically this is where the options are atomically
> >> set on the new (create) or existing (reconfigure) superblock.
> >
> > Why do you need to expose this step to userspace?  Assuming in the "new" case
> > you do, say:
> >
> >         fd = fsopen("nfs");
> >         write(fd, "s foo.bar:/bar", ...);
> >         write(fd, "o intr", ...);
> >         write(fd, "o fsc", ...);
> >         ...
> >         write(fd, "c", ...); /* commit operation to get a superblock */
> >         fsmount(fd, AT_FDCWD, "/mnt");  /* mount the superblock we just got */
> >
> > Then the "commit" op is dissimilar to "mount -o remount" since remount may
> > alter the superblock parameters *and* the mountpoint parameters, but commit
> > can only affect the superblock.
> 
> Forget remount, it's a historical remnant.  We need fsreconfig(sb) and
> setmntattr(mnt).  They are changing properties of different objects.

I agree and I'd like to highlight another issue we have with the
current mount(2). The problem is non-atomic work with more
propagation flags if you want to mount a filesystem. For example:

  mount /dev/sda1 /A -o private,unbindable,ro

this is supported by mount(8), but it's implemented by three
independent mount(2) calls

    - 1st mounts /dev/sda1 with MS_RDONLY
    - 2nd sets MS_PRIVATE flag
    - 3rd sets MS_UNBINDABLE flag.

it would be nice set all the VFS flags and then as atomic operation attach
the context to the tree.

    Karel

Jeff Layton May 10, 2017, 1:20 p.m. UTC | #27

On Wed, 2017-05-10 at 09:05 +0100, David Howells wrote:
> Miklos Szeredi <[e-mail]> wrote:
>
> > Possible rule of thumb: use it only at the place where the error
> > originates and not where errors are just passed on.  This would result
> > in at most one report per syscall, normally.
> >

That might be hard to enforce in practice once you get into some
complicated layering. What if we have device_mapper setting this along
with filesystems too? We need clear rules here.

> > And the static string thing that David implemented is also a very good
> > idea, IMO.
> 
> There is an issue with it: it's fine as long as you keep a ref on the module
> that generated it or clear all strings as part of module removal (which the
> mount context in this patchset does).  With the NFS mount context I did, I
> have to keep a ref on the NFS protocol module as well as the NFS filesystem
> module.
> 
> I'm tempted to make it conditionally copy the string using kvasprintf_const()
> - which would also permit format substitution.
> 

On balance, I think this is a reasonable way to pass back detailed
errors. Up until now, we've mostly relied on just printk'ing them. Now
though, a lot of larger machines are running containerized setups. Good
luck scraping dmesg for _your_ error in that situation. There may be
tons of mounts failing all over the place.

That said, I have some concerns here:

What's the lifetime of these strings? Do they just hang around forever
until the process goes away or they're replaced? If this becomes common,
then you could easily end up with an extra string allocation per task in
some cases. That could add up.

One idea might be to always kfree it on syscall entry, and that might
mitigate the problem assuming that not everything is erroring out. Then
you could always do some trivial syscall to clear it manually.

There's also the problem of how these should be formatted. Is English ok
everywhere? Do we need a facility to allow translating these things?

Miklos Szeredi May 10, 2017, 1:30 p.m. UTC | #28

On Wed, May 10, 2017 at 3:20 PM, Jeff Layton <[e-mail]> wrote:
> On Wed, 2017-05-10 at 09:05 +0100, David Howells wrote:
>> Miklos Szeredi <[e-mail]> wrote:
>>
>> > Possible rule of thumb: use it only at the place where the error
>> > originates and not where errors are just passed on.  This would result
>> > in at most one report per syscall, normally.
>> >
>
> That might be hard to enforce in practice once you get into some
> complicated layering. What if we have device_mapper setting this along
> with filesystems too? We need clear rules here.

If the error originates in the devicemapper, then why would the
filesystem set it?

There's always a root cause of an error and that should be where the
detailed error is set.

Am I missing something?

>
>> > And the static string thing that David implemented is also a very good
>> > idea, IMO.
>>
>> There is an issue with it: it's fine as long as you keep a ref on the module
>> that generated it or clear all strings as part of module removal (which the
>> mount context in this patchset does).  With the NFS mount context I did, I
>> have to keep a ref on the NFS protocol module as well as the NFS filesystem
>> module.
>>
>> I'm tempted to make it conditionally copy the string using kvasprintf_const()
>> - which would also permit format substitution.
>>
>
> On balance, I think this is a reasonable way to pass back detailed
> errors. Up until now, we've mostly relied on just printk'ing them. Now
> though, a lot of larger machines are running containerized setups. Good
> luck scraping dmesg for _your_ error in that situation. There may be
> tons of mounts failing all over the place.
>
> That said, I have some concerns here:
>
> What's the lifetime of these strings? Do they just hang around forever
> until the process goes away or they're replaced? If this becomes common,
> then you could easily end up with an extra string allocation per task in
> some cases. That could add up.

That's why I liked the static string thing.  It's just one assignment
and no worries about freeing.  Not sure what to do about modules,
though.  Can we somehow move the cost of checking the validity to the
place where the error is retrieved?

>
> One idea might be to always kfree it on syscall entry, and that might
> mitigate the problem assuming that not everything is erroring out. Then
> you could always do some trivial syscall to clear it manually.
>
> There's also the problem of how these should be formatted. Is English ok
> everywhere? Do we need a facility to allow translating these things?

Messages in dmesg are in English too.  If necessary userspace will do
the translation.  I don't think the kernel would need to worry about
that.

Thanks,
Miklos


> --
> Jeff Layton <[e-mail]>
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

David Howells May 10, 2017, 1:31 p.m. UTC | #29

Jeff Layton <[e-mail]> wrote:

> One idea might be to always kfree it on syscall entry

You can't do that otherwise there's no way to retrieve the strings.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Miklos Szeredi May 10, 2017, 1:33 p.m. UTC | #30

> That's why I liked the static string thing.  It's just one assignment
> and no worries about freeing.  Not sure what to do about modules,
> though.  Can we somehow move the cost of checking the validity to the
> place where the error is retrieved?

I'm thinking along the lines of not allowing module virtual addresses
to be recycled after module remove...

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Jeff Layton May 10, 2017, 1:37 p.m. UTC | #31

On Wed, 2017-05-10 at 14:31 +0100, David Howells wrote:
> Jeff Layton <[e-mail]> wrote:
> 
> > One idea might be to always kfree it on syscall entry
> 
> You can't do that otherwise there's no way to retrieve the strings.
> 
> 

True...you'd have to exempt the syscall that does the retrieving.

Jeff Layton May 10, 2017, 1:48 p.m. UTC | #32

On Wed, 2017-05-10 at 15:30 +0200, Miklos Szeredi wrote:
> On Wed, May 10, 2017 at 3:20 PM, Jeff Layton <[e-mail]> wrote:
> > On Wed, 2017-05-10 at 09:05 +0100, David Howells wrote:
> > > Miklos Szeredi <[e-mail]> wrote:
> > > 
> > > > Possible rule of thumb: use it only at the place where the error
> > > > originates and not where errors are just passed on.  This would result
> > > > in at most one report per syscall, normally.
> > > > 
> > 
> > That might be hard to enforce in practice once you get into some
> > complicated layering. What if we have device_mapper setting this along
> > with filesystems too? We need clear rules here.
> 
> If the error originates in the devicemapper, then why would the
> filesystem set it?
> 
> There's always a root cause of an error and that should be where the
> detailed error is set.
> 
> Am I missing something?
> 

I was thinking that you'd need some well-defined way to tell whether the
string should be replaced. If the thing just hangs out across syscalls,
then you don't know when it got put there. Is it a leftover from a
previous syscall or did a lower layer just put it there?

But...maybe I'm making assumptions about how this would work and I
should just wait until there are patches in flight. Getting the lifetime
of these strings right will be crucial though.

> > 
> > > > And the static string thing that David implemented is also a very good
> > > > idea, IMO.
> > > 
> > > There is an issue with it: it's fine as long as you keep a ref on the module
> > > that generated it or clear all strings as part of module removal (which the
> > > mount context in this patchset does).  With the NFS mount context I did, I
> > > have to keep a ref on the NFS protocol module as well as the NFS filesystem
> > > module.
> > > 
> > > I'm tempted to make it conditionally copy the string using kvasprintf_const()
> > > - which would also permit format substitution.
> > > 
> > 
> > On balance, I think this is a reasonable way to pass back detailed
> > errors. Up until now, we've mostly relied on just printk'ing them. Now
> > though, a lot of larger machines are running containerized setups. Good
> > luck scraping dmesg for _your_ error in that situation. There may be
> > tons of mounts failing all over the place.
> > 
> > That said, I have some concerns here:
> > 
> > What's the lifetime of these strings? Do they just hang around forever
> > until the process goes away or they're replaced? If this becomes common,
> > then you could easily end up with an extra string allocation per task in
> > some cases. That could add up.
> 
> That's why I liked the static string thing.  It's just one assignment
> and no worries about freeing.  Not sure what to do about modules,
> though.  Can we somehow move the cost of checking the validity to the
> place where the error is retrieved?
> 

Seems a little dangerous, and could be limiting. Dynamically allocated
strings seem like they could be more useful.

> > 
> > One idea might be to always kfree it on syscall entry, and that might
> > mitigate the problem assuming that not everything is erroring out. Then
> > you could always do some trivial syscall to clear it manually.
> > 
> > There's also the problem of how these should be formatted. Is English ok
> > everywhere? Do we need a facility to allow translating these things?
> 
> Messages in dmesg are in English too.  If necessary userspace will do
> the translation.  I don't think the kernel would need to worry about
> that.

Fair enough. It _is_ still an improvement over dmesg, IMO.

Miklos Szeredi May 12, 2017, 8:15 a.m. UTC | #33

On Wed, May 10, 2017 at 3:48 PM, Jeff Layton <[e-mail]> wrote:

> I was thinking that you'd need some well-defined way to tell whether the
> string should be replaced. If the thing just hangs out across syscalls,
> then you don't know when it got put there. Is it a leftover from a
> previous syscall or did a lower layer just put it there?

Example userspace code:

    /* Throw away previous error string */
    get_detailed_error(NULL, 0);
    ret = somesyscall(...);
    if (ret == -1) {
        char errbuf[1024];

        /* Get detailed error string for somesyscall */
        get_detailed_error(errbuf, sizeof(errbuf));
        err(1, errbuf);
    }

>> That's why I liked the static string thing.  It's just one assignment
>> and no worries about freeing.  Not sure what to do about modules,
>> though.  Can we somehow move the cost of checking the validity to the
>> place where the error is retrieved?
>>
>
> Seems a little dangerous,

True.

>  and could be limiting. Dynamically allocated
> strings seem like they could be more useful.

Overdesign always starts with that.  A static string is infinitely
more descriptive than an error num, and we've done pretty well with
the latter, so I'm not convinced that we really need a formatted
string.

Maybe just use kstrdup_const() if CONFIG_MODULE_UNLOAD is set,
otherwise plain assignment.  Then free the string when retrieving and
on task exit.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
new file mode 100644
index 000000000000..a942ccd08376
--- /dev/null
+++ b/Documentation/filesystems/mounting.txt
@@ -0,0 +1,445 @@ 
+			      ===================
+			      FILESYSTEM MOUNTING
+			      ===================
+
+CONTENTS
+
+ (1) Overview.
+
+ (2) The mount context.
+
+ (3) The mount context operations.
+
+ (4) Mount context security.
+
+ (5) VFS mount context operations.
+
+
+========
+OVERVIEW
+========
+
+The creation of new mounts is now to be done in a multistep process:
+
+ (1) Create a mount context.
+
+ (2) Parse the options and attach them to the mount context.  Options may be
+     passed individually from userspace.
+
+ (3) Validate and pre-process the mount context.
+
+ (4) Perform the mount.
+
+ (5) Return an error message attached to the mount context.
+
+ (6) Destroy the mount context.
+
+To support this, the file_system_type struct gains two new fields:
+
+	unsigned short mc_size;
+
+which indicates how much space the filesystem would like tacked onto the end of
+the mount_context struct for its own purposes, and:
+
+	int (*fsopen)(struct mount_context *mc, struct super_block *src_sb);
+
+which is invoked to set up the filesystem-specific parts of a mount context,
+including the additional space.  The src_sb parameter is used to convey the
+superblock from which the filesystem may draw extra information (such as
+namespaces), for submount (MS_SUBMOUNT) or remount (MS_REMOUNT) purposes or it
+will be NULL.
+
+Note that security initialisation is done *after* the filesystem is called so
+that the namespaces may be adjusted first.
+
+And the super_operations struct gains one:
+
+	int (*remount_fs_mc) (struct super_block *, struct mount_context *);
+
+This shadows the ->remount_fs() operation and takes a prepared mount context
+instead of the mount flags and data page.  It may modify the ms_flags in the
+context for the caller to pick up.
+
+[NOTE] remount_fs_mc is intended as a replacement for remount_fs.
+
+
+=================
+THE MOUNT CONTEXT
+=================
+
+The mount process is governed by a mount context.  This is represented by the
+mount_context structure:
+
+	struct mount_context {
+		const struct mount_context_operations *ops;
+		struct file_system_type *fs;
+		struct user_namespace	*user_ns;
+		struct mnt_namespace	*mnt_ns;
+		struct pid_namespace	*pid_ns;
+		struct net		*net_ns;
+		const struct cred	*cred;
+		char			*device;
+		char			*root_path;
+		void			*security;
+		const char		*error;
+		unsigned int		ms_flags;
+		unsigned int		mnt_flags;
+		bool			mounted;
+		bool			sloppy;
+		bool			silent;
+		enum mount_type		mount_type : 8;
+	};
+
+When allocated, the mount_context struct is extended by ->mc_size bytes as
+specified by the specified file_system_type struct.  This is for use by the
+filesystem.  The filesystem should wrap the struct in its own, e.g.:
+
+	struct nfs_mount_context {
+		struct mount_context mc;
+		...
+	};
+
+placing the mount_context struct first.  container_of() can then be used.
+
+The mount_context fields are as follows:
+
+ (*) const struct mount_context_operations *ops
+
+     These are operations that can be done on a mount context.  See below.
+     This must be set by the ->fsopen() file_system_type operation.
+
+ (*) struct file_system_type *fs
+
+     A pointer to the file_system_type of the filesystem that is being
+     mounted.  This retains a ref on the type owner.
+
+ (*) struct user_namespace *user_ns
+ (*) struct mnt_namespace *mnt_ns
+ (*) struct pid_namespace *pid_ns
+ (*) struct net *net_ns
+
+     This is a subset of the namespaces in use by the invoking process.  This
+     retains a ref on each namespace.  The subscribed namespaces may be
+     replaced by the filesystem to reflect other sources, such as the parent
+     mount superblock on an automount.
+
+ (*) struct cred *cred
+
+     The mounter's credentials.  This retains a ref on the credentials.
+
+ (*) char *device
+
+     This is the device to be mounted.  It may be a block device
+     (e.g. /dev/sda1) or something more exotic, such as the "host:/path" that
+     NFS desires.
+
+ (*) char *root_path
+
+     A path to the place inside the filesystem to actually mount.  This allows
+     a mount and bind-mount to be combined.
+
+     [NOTE] This isn't implemented yet, but NFS has the code to do this which
+     could be moved to the VFS.
+
+ (*) void *security
+
+     A place for the LSMs to hang their security data for the mount.  The
+     relevant security operations are described below.
+
+ (*) const char *error
+
+     A place for the VFS and the filesystem to hang an error message.  This
+     should be in the form of a static string that doesn't need deallocation
+     and the pointer to which can just be overwritten.  Under some
+     circumstances, this can be retrieved by userspace.
+
+     Note that the existence of the error string is expected to be guaranteed
+     by the reference on the file_system_type object held by ->fs or any
+     filesystem-specific reference held in the filesystem context until the
+     ->free() operation is called.
+
+ (*) unsigned int ms_flags
+ (*) unsigned int mnt_flags
+
+     These hold the mount flags.  ms_flags holds MS_* flags and mnt_flags holds
+     MNT_* flags.
+
+ (*) bool mounted
+
+     This is set to true once a mount attempt is made.  This causes an error to
+     be given on subsequent mount attempts with the same context and prevents
+     multiple mount attempts.
+
+ (*) bool sloppy
+ (*) bool silent
+
+     These are set if the sloppy or silent mount options are given.
+
+     [NOTE] sloppy is probably unnecessary when userspace passes over one
+     option at a time since the error can just be ignored if userspace deems it
+     to be unimportant.
+
+     [NOTE] silent is probably redundant with ms_flags & MS_SILENT.
+
+ (*) enum mount_type
+
+     This indicates the type of mount operation.  The available values are:
+
+	MOUNT_TYPE_NEW		-- New mount
+	MOUNT_TYPE_SUBMOUNT	-- New automatic submount of extant mount
+	MOUNT_TYPE_REMOUNT	-- Change an existing mount
+
+The mount context is created by calling __vfs_fsopen(), vfs_fsopen(),
+vfs_mntopen() or vfs_dup_mount_context() and is destroyed with
+put_mount_context().  Note that the structure is not refcounted.
+
+VFS, security and filesystem mount options are set individually with
+vfs_mount_option() or in bulk with generic_monolithic_mount_data().
+
+When mounting, the filesystem is allowed to take data from any of the pointers
+and attach it to the superblock (or whatever), provided it clears the pointer
+in the mount context.
+
+The filesystem is also allowed to allocate resources and pin them with the
+mount context.  For instance, NFS might pin the appropriate protocol version
+module.
+
+
+============================
+THE MOUNT CONTEXT OPERATIONS
+============================
+
+The mount context points to a table of operations:
+
+	struct mount_context_operations {
+		void (*free)(struct mount_context *mc);
+		int (*dup)(struct mount_context *mc, struct mount_context *src);
+		int (*option)(struct mount_context *mc, char *p);
+		int (*monolithic_mount_data)(struct mount_context *mc, void *data);
+		int (*validate)(struct mount_context *mc);
+		struct dentry *(*mount)(struct mount_context *mc);
+		int (*fill_super)(struct super_block *s, struct mount_context *mc);
+	};
+
+These operations are invoked by the various stages of the mount procedure to
+manage the mount context.  They are as follows:
+
+ (*) void (*free)(struct mount_context *mc);
+
+     Called to clean up the filesystem-specific part of the mount context when
+     the context is destroyed.  It should be aware that parts of the context
+     may have been removed and NULL'd out by ->mount().
+
+ (*) int (*dup)(struct mount_context *mc, struct mount_context *src);
+
+     Called when a mount context has been duplicated to get any refs or copy
+     any non-referenced resources held in the filesystem-specific part of the
+     mount context.  An error may be returned to indicate failure to do this.
+
+     [!] Note that if this fails, put_mount_context() will be called
+     	 immediately thereafter, so ->dup() *must* make the
+     	 filesystem-specific part safe for ->free().
+
+ (*) int (*option)(struct mount_context *mc, char *p);
+
+     Called when an option is to be added to the mount context.  p points to
+     the option string, likely in "key[=val]" format.  VFS-specific options
+     will have been weeded out and mc->ms_flags and mc->mnt_flags updated in
+     the context.  Security options will also have been weeded out and
+     mc->security updated.
+
+     If successful, 0 should be returned and a negative error code otherwise.
+     If an ambiguous error (such as -EINVAL) is returned, mc->error should be
+     set in the context to a string that provides more information.
+
+ (*) int (*monolithic_mount_data)(struct mount_context *mc, void *data);
+
+     Called when the mount(2) system call is invoked to pass the entire data
+     page in one go.  If this is expected to be just a list of "key[=val]"
+     items separated by commas, then this may be set to NULL.
+
+     The return value is as for ->option().
+
+     If the filesystem (eg. NFS) needs to examine the data first and then
+     finds it's the standard key-val list then it may pass it off to:
+
+	int generic_monolithic_mount_data(struct mount_context *mc, void *data);
+
+ (*) int (*validate)(struct mount_context *mc);
+
+     Called when all the options have been applied and the mount is about to
+     take place.  It is should check for inconsistencies from mount options
+     and it is also allowed to do preliminary resource acquisition.  For
+     instance, the core NFS module could load the NFS protocol module here.
+
+     Note that if mc->mount_type == MOUNT_TYPE_REMOUNT, some of the options
+     necessary for a new mount may not be set.
+
+     The return value is as for ->option().
+
+ (*) struct dentry *(*mount)(struct mount_context *mc);
+
+     Called to effect a new mount or new submount using the information stored
+     in the mount context (remounts go via a different vector).  It may detach
+     any resources it desires from the mount context and transfer them to the
+     superblock it creates.
+
+     On success it should return the dentry that's at the root of the mount.
+     In future, mc->root_path will then be applied to this.
+
+     In the case of an error, it should return a negative error code and set
+     mc->error.
+
+ (*) int (*fill_super)(struct super_block *s, struct mount_context *mc);
+
+     This is available to be used by things like mount_ns_mc() that are called
+     by ->mount() to transfer information/resources from the mount context to
+     the superblock.
+
+
+======================
+MOUNT CONTEXT SECURITY
+======================
+
+The mount context contains a security points that the LSMs can use for
+building up a security context for the superblock to be mounted.  There are a
+number of operations used by the new mount code for this purpose:
+
+ (*) int security_mount_ctx_alloc(struct mount_context *mc,
+				  struct super_block *src_sb);
+
+     Called to initialise mc->security (which is preset to NULL) and allocate
+     any resources needed.  It should return 0 on success and a negative error
+     code on failure.
+
+     src_sb is non-NULL in the case of a remount (MS_REMOUNT) in which case it
+     indicates the superblock to be remounted or in the case of a submount
+     (MS_SUBMOUNT) in which case it indicates the parent superblock.
+
+ (*) int security_mount_ctx_dup(struct mount_context *mc,
+				struct mount_context *src_mc);
+
+     Called to initialise mc->security (which is preset to NULL) and allocate
+     any resources needed.  The original mount context is pointed to by src_mc
+     and may be used for reference.  It should return 0 on success and a
+     negative error code on failure.
+
+ (*) void security_mount_ctx_free(struct mount_context *mc);
+
+     Called to clean up anything attached to mc->security.  Note that the
+     contents may have been transferred to a superblock and the pointer NULL'd
+     out during mount.
+
+ (*) int security_mount_ctx_option(struct mount_context *mc, char *opt);
+
+     Called for each mount option.  The mount options are in "key[=val]"
+     form.  An active LSM may reject one with an error, pass one over and
+     return 0 or consume one and return 1.  If consumed, the option isn't
+     passed on to the filesystem.
+
+     If it returns an error, it should set mc->error if the error is
+     ambiguous.
+
+ (*) int security_mount_ctx_kern_mount(struct mount_context *mc,
+				       struct super_block *sb);
+
+     Called during mount to verify that the specified superblock is allowed to
+     be mounted and to transfer the security data there.
+
+     On success, it should return 0; otherwise it should return an error and
+     set mc->error to indicate the problem.  It should not return -ENOMEM as
+     this should be taken care of in advance.
+
+     [NOTE] Should I add a security_mount_ctx_validate() operation so that the
+     LSM has the opportunity to allocate stuff and check the options as a
+     whole?
+
+
+============================
+VFS MOUNT CONTEXT OPERATIONS
+============================
+
+There are four operations for creating a mount context and one for destroying
+a context:
+
+ (*) struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
+					struct super_block *src_sb;
+					unsigned int ms_flags,
+					unsigned int mnt_flags);
+
+     Create a mount context given a filesystem type pointer.  This allocates
+     the mount context, sets the flags, initialises the security and calls
+     fs_type->fsopen() to initialise the filesystem context.
+
+     src_sb can be NULL or it may indicate a superblock that is going to be
+     remounted (MS_REMOUNT) or a superblock that is the parent of a submount
+     (MS_SUBMOUNT).  This superblock is provided as a source of namespace
+     information.
+
+ (*) struct mount_context *vfs_mntopen(struct vfsmount *mnt,
+				       unsigned int ms_flags,
+				       unsigned int mnt_flags);
+
+     Create a mount context from the same filesystem as an extant mount and
+     initialise the mount parameters from the superblock underlying that
+     mount.  This is used by remount.
+
+ (*) struct mount_context *vfs_fsopen(const char *fs_name);
+
+     Create a mount context given a filesystem name.  It is assumed that the
+     mount flags will be passed in as text options later.  This is intended to
+     be called from sys_fsopen().  This copies current's namespaces to the
+     mount context.
+
+ (*) struct mount_context *vfs_dup_mount_context(struct mount_context *src);
+
+     Duplicate a mount context, copying any options noted and duplicating or
+     additionally referencing any resources held therein.  This is available
+     for use where a filesystem has to get a mount within a mount, such as
+     NFS4 does by internally mounting the root of the target server and then
+     doing a private pathwalk to the target directory.
+
+ (*) void put_mount_context(struct mount_context *ctx);
+
+     Destroy a mount context, releasing any resources it holds.  This calls
+     the ->free() operation.  This is intended to be called by anyone who
+     created a mount context.
+
+     [!] Mount contexts are not refcounted, so this causes unconditional
+     	 destruction.
+
+In all the above operations, apart from the put op, the return is a mount
+context pointer or a negative error code.  No error string is saved as the
+error string is only guaranteed as long as the file_system_type is pinned (and
+thus the module).
+
+In the remaining operations, if an error occurs, a negative error code is
+returned and, if not obvious, mc->error should be set to point to a useful
+string.  The string should not be freed.
+
+ (*) struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc);
+
+     Create a mount given the parameters in the specified mount context.  This
+     invokes the ->validate() op and then the ->mount() op.
+
+ (*) struct vfsmount *vfs_submount_mc(const struct dentry *mountpoint,
+				      struct mount_context *mc);
+
+     Create a mount given a mount context and set MS_SUBMOUNT on it.  A
+     wrapper around vfs_kern_mount_mc().  This is intended to be called from
+     filesystems that have automount points (NFS, AFS, ...).
+
+ (*) int vfs_mount_option(struct mount_context *mc, char *data);
+
+     Supply a single mount option to the mount context.  The mount option
+     should likely be in a "key[=val]" string form.  The option is first
+     checked to see if it corresponds to a standard mount flag (in which case
+     it is used to mark an MS_xxx flag and consumed) or a security option (in
+     which case the LSM consumes it) before it is passed on to the filesystem.
+
+ (*) int generic_monolithic_mount_data(struct mount_context *ctx, void *data);
+
+     Parse a sys_mount() data page, assuming the form to be a text list
+     consisting of key[=val] options separated by commas.  Each item in the
+     list is passed to vfs_mount_option().  This is the default when the
+     ->monolithic_mount_data() operation is NULL.
diff --git a/fs/Makefile b/fs/Makefile
index 7bbaca9c67b1..308a104a9a07 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,8 @@  obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o \
-		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
+		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
+		mount_context.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/internal.h b/fs/internal.h
index 076751d90ba2..ef8c5e93f364 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -87,7 +87,7 @@  extern struct file *get_empty_filp(void);
 /*
  * super.c
  */
-extern int do_remount_sb(struct super_block *, int, void *, int);
+extern int do_remount_sb(struct super_block *, int, void *, int, struct mount_context *);
 extern bool trylock_super(struct super_block *sb);
 extern struct dentry *mount_fs(struct file_system_type *,
 			       int, const char *, void *);
diff --git a/fs/mount.h b/fs/mount.h
index 2826543a131d..b1e99b38f2ee 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -108,9 +108,10 @@  static inline void detach_mounts(struct dentry *dentry)
 	__detach_mounts(dentry);
 }
 
-static inline void get_mnt_ns(struct mnt_namespace *ns)
+static inline struct mnt_namespace *get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
+	return ns;
 }
 
 extern seqlock_t mount_lock;
diff --git a/fs/mount_context.c b/fs/mount_context.c
new file mode 100644
index 000000000000..7d765c100bf1
--- /dev/null
+++ b/fs/mount_context.c
@@ -0,0 +1,343 @@ 
+/* Provide a way to create a mount context within the kernel that can be
+ * configured before mounting.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([e-mail])
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <linux/slab.h>
+#include <linux/magic.h>
+#include <linux/security.h>
+#include <linux/parser.h>
+#include <linux/mnt_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include <net/net_namespace.h>
+#include "mount.h"
+
+static const match_table_t common_set_mount_options = {
+	{ MS_DIRSYNC,		"dirsync" },
+	{ MS_I_VERSION,		"iversion" },
+	{ MS_LAZYTIME,		"lazytime" },
+	{ MS_MANDLOCK,		"mand" },
+	{ MS_NOATIME,		"noatime" },
+	{ MS_NODEV,		"nodev" },
+	{ MS_NODIRATIME,	"nodiratime" },
+	{ MS_NOEXEC,		"noexec" },
+	{ MS_NOSUID,		"nosuid" },
+	{ MS_POSIXACL,		"posixacl" },
+	{ MS_RDONLY,		"ro" },
+	{ MS_REC,		"rec" },
+	{ MS_RELATIME,		"relatime" },
+	{ MS_STRICTATIME,	"strictatime" },
+	{ MS_SYNCHRONOUS,	"sync" },
+	{ MS_VERBOSE,		"verbose" },
+	{ },
+};
+
+static const match_table_t common_clear_mount_options = {
+	{ MS_LAZYTIME,		"nolazytime" },
+	{ MS_MANDLOCK,		"nomand" },
+	{ MS_NODEV,		"dev" },
+	{ MS_NOEXEC,		"exec" },
+	{ MS_NOSUID,		"suid" },
+	{ MS_RDONLY,		"rw" },
+	{ MS_RELATIME,		"norelatime" },
+	{ MS_SILENT,		"silent" },
+	{ MS_STRICTATIME,	"nostrictatime" },
+	{ MS_SYNCHRONOUS,	"async" },
+	{ },
+};
+
+static const match_table_t forbidden_mount_options = {
+	{ MS_BIND,		"bind" },
+	{ MS_KERNMOUNT,		"ro" },
+	{ MS_MOVE,		"move" },
+	{ MS_PRIVATE,		"private" },
+	{ MS_REMOUNT,		"remount" },
+	{ MS_SHARED,		"shared" },
+	{ MS_SLAVE,		"slave" },
+	{ MS_UNBINDABLE,	"unbindable" },
+	{ },
+};
+
+/*
+ * Check for a common mount option.
+ */
+static noinline int vfs_common_mount_option(struct mount_context *mc, char *data)
+{
+	substring_t args[MAX_OPT_ARGS];
+	unsigned int token;
+
+	token = match_token(data, common_set_mount_options, args);
+	if (token) {
+		mc->ms_flags |= token;
+		return 1;
+	}
+
+	token = match_token(data, common_clear_mount_options, args);
+	if (token) {
+		mc->ms_flags &= ~token;
+		return 1;
+	}
+
+	token = match_token(data, forbidden_mount_options, args);
+	if (token) {
+		mc->error = "Mount option, not superblock option";
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * vfs_mount_option - Add a single mount option to a mount context
+ * @mc: The mount context to modify
+ * @option: The option to apply.
+ *
+ * A single mount option in string form is applied to the mount being set up in
+ * the mount context.  Certain standard options (for example "ro") are
+ * translated into flag bits without going to the filesystem.  The active
+ * security module allowed to observe and poach options.  Any other options are
+ * passed over to the filesystem to parse.
+ *
+ * This may be called multiple times for a context.
+ *
+ * Returns 0 on success and a negative error code on failure.  In the event of
+ * failure, mc->error may have been set to a non-allocated string that gives
+ * more information.
+ */
+int vfs_mount_option(struct mount_context *mc, char *data)
+{
+	int ret;
+
+	if (mc->mounted)
+		return -EBUSY;
+
+	ret = vfs_common_mount_option(mc, data);
+	if (ret < 0)
+		return ret;
+	if (ret == 1)
+		return 0;
+
+	ret = security_mount_ctx_option(mc, data);
+	if (ret < 0)
+		return ret;
+	if (ret == 1)
+		return 0;
+
+	return mc->ops->option(mc, data);
+}
+EXPORT_SYMBOL(vfs_mount_option);
+
+/**
+ * generic_monolithic_mount_data - Parse key[=val][,key[=val]]* mount data
+ * @mc: The mount context to populate
+ * @data: The data to parse
+ *
+ * Parse a blob of data that's in key[=val][,key[=val]]* form.  This can be
+ * called from the ->monolithic_mount_data() mount context operation.
+ *
+ * Returns 0 on success or the error returned by the ->option() mount context
+ * operation on failure.
+ */
+int generic_monolithic_mount_data(struct mount_context *ctx, void *data)
+{
+	char *options = data, *p;
+	int ret;
+
+	if (!options)
+		return 0;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		if (*p) {
+			ret = vfs_mount_option(ctx, p);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(generic_monolithic_mount_data);
+
+/**
+ * __vfs_fsopen - Open a filesystem and create a mount context
+ * @fs_type: The filesystem type
+ * @src_sb: A superblock from which this one derives (or NULL)
+ * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
+ * @mnt_flags: Mountpoint flags, such as MNT_READONLY
+ * @mount_type: Type of mount
+ *
+ * Open a filesystem and create a mount context.  The mount context is
+ * initialised with the supplied flags and, if a submount/automount from
+ * another superblock (@src_sb), may have parameters such as namespaces copied
+ * across from that superblock.
+ */
+struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
+				   struct super_block *src_sb,
+				   unsigned int ms_flags, unsigned int mnt_flags,
+				   enum mount_type mount_type)
+{
+	struct mount_context *mc;
+	int ret;
+
+	if (fs_type->fsopen && fs_type->mc_size < sizeof(*mc))
+		BUG();
+
+	mc = kzalloc(max_t(size_t, fs_type->mc_size, sizeof(*mc)), GFP_KERNEL);
+	if (!mc)
+		return ERR_PTR(-ENOMEM);
+
+	mc->mount_type = mount_type;
+	mc->ms_flags = ms_flags;
+	mc->mnt_flags = mnt_flags;
+	mc->fs_type = fs_type;
+	get_filesystem(fs_type);
+	mc->mnt_ns = get_mnt_ns(current->nsproxy->mnt_ns);
+	mc->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	mc->net_ns = get_net(current->nsproxy->net_ns);
+	mc->user_ns = get_user_ns(current_user_ns());
+	mc->cred = get_current_cred();
+
+
+	/* TODO: Make all filesystems support this unconditionally */
+	if (mc->fs_type->fsopen) {
+		ret = mc->fs_type->fsopen(mc, src_sb);
+		if (ret < 0)
+			goto err_mc;
+	}
+
+	/* Do the security check last because ->fsopen may change the
+	 * namespace subscriptions.
+	 */
+	ret = security_mount_ctx_alloc(mc, src_sb);
+	if (ret < 0)
+		goto err_mc;
+
+	return mc;
+
+err_mc:
+	put_mount_context(mc);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(__vfs_fsopen);
+
+/**
+ * vfs_fsopen - Open a filesystem and create a mount context
+ * @fs_name: The name of the filesystem
+ *
+ * Open a filesystem and create a mount context that will hold the mount
+ * options, device name, security details, etc..  Note that the caller should
+ * check the ->ops pointer in the returned context to determine whether the
+ * filesystem actually supports the mount context itself.
+ */
+struct mount_context *vfs_fsopen(const char *fs_name)
+{
+	struct file_system_type *fs_type;
+	struct mount_context *mc;
+
+	fs_type = get_fs_type(fs_name);
+	if (!fs_type)
+		return ERR_PTR(-ENODEV);
+
+	mc = __vfs_fsopen(fs_type, NULL, 0, 0, MOUNT_TYPE_NEW);
+	put_filesystem(fs_type);
+	return mc;
+}
+EXPORT_SYMBOL(vfs_fsopen);
+
+/**
+ * vfs_mntopen - Create a mount context and initialise it from an extant mount
+ * @mnt: The mountpoint to open
+ * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
+ * @mnt_flags: Mountpoint flags, such as MNT_READONLY
+ * @mount_type: Type of mount
+ *
+ * Open a mounted filesystem and create a mount context such that a remount can
+ * be effected.
+ */
+struct mount_context *vfs_mntopen(struct vfsmount *mnt,
+				  unsigned int ms_flags,
+				  unsigned int mnt_flags,
+				  enum mount_type mount_type)
+{
+	return __vfs_fsopen(mnt->mnt_sb->s_type, mnt->mnt_sb,
+			    ms_flags, mnt_flags, mount_type);
+}
+
+/**
+ * vfs_dup_mount_context: Duplicate a mount context.
+ * @src: The mount context to copy.
+ */
+struct mount_context *vfs_dup_mount_context(struct mount_context *src)
+{
+	struct mount_context *mc;
+	int ret;
+
+	if (!src->ops->dup)
+		return ERR_PTR(-ENOTSUPP);
+
+	mc = kmemdup(src, src->fs_type->mc_size, GFP_KERNEL);
+	if (!mc)
+		return ERR_PTR(-ENOMEM);
+
+	mc->device	= NULL;
+	mc->root_path	= NULL;
+	mc->security	= NULL;
+	mc->error	= NULL;
+	get_filesystem(mc->fs_type);
+	get_mnt_ns(mc->mnt_ns);
+	get_pid_ns(mc->pid_ns);
+	get_net(mc->net_ns);
+	get_user_ns(mc->user_ns);
+	get_cred(mc->cred);
+
+	/* Can't call put until we've called ->dup */
+	ret = mc->ops->dup(mc, src);
+	if (ret < 0)
+		goto err_mc;
+
+	ret = security_mount_ctx_dup(mc, src);
+	if (ret < 0)
+		goto err_mc;
+	return mc;
+
+err_mc:
+	put_mount_context(mc);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(vfs_dup_mount_context);
+
+/*
+ * Dispose of a mount context.
+ */
+void put_mount_context(struct mount_context *mc)
+{
+	if (mc->ops && mc->ops->free)
+		mc->ops->free(mc);
+	security_mount_ctx_free(mc);
+	if (mc->mnt_ns)
+		put_mnt_ns(mc->mnt_ns);
+	if (mc->pid_ns)
+		put_pid_ns(mc->pid_ns);
+	if (mc->net_ns)
+		put_net(mc->net_ns);
+	put_user_ns(mc->user_ns);
+	if (mc->cred)
+		put_cred(mc->cred);
+	put_filesystem(mc->fs_type);
+	kfree(mc->device);
+	kfree(mc->root_path);
+	kfree(mc);
+}
+EXPORT_SYMBOL(put_mount_context);
diff --git a/fs/namespace.c b/fs/namespace.c
index db034b6afd43..e0edab9af308 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -25,6 +25,7 @@ 
 #include <linux/magic.h>
 #include <linux/bootmem.h>
 #include <linux/task_work.h>
+#include <linux/file.h>
 #include <linux/sched/task.h>
 
 #include "pnode.h"
@@ -783,9 +784,14 @@  static void put_mountpoint(struct mountpoint *mp)
 	}
 }
 
+static inline int __check_mnt(struct mount *mnt, struct mnt_namespace *mnt_ns)
+{
+	return mnt->mnt_ns == mnt_ns;
+}
+
 static inline int check_mnt(struct mount *mnt)
 {
-	return mnt->mnt_ns == current->nsproxy->mnt_ns;
+	return __check_mnt(mnt, current->nsproxy->mnt_ns);
 }
 
 /*
@@ -1596,7 +1602,7 @@  static int do_umount(struct mount *mnt, int flags)
 			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
-			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
+			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0, NULL);
 		up_write(&sb->s_umount);
 		return retval;
 	}
@@ -2279,6 +2285,26 @@  static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 }
 
 /*
+ * Parse the monolithic page of mount data given to sys_mount().
+ */
+static int parse_monolithic_mount_data(struct mount_context *mc, void *data)
+{
+	int (*monolithic_mount_data)(struct mount_context *, void *);
+	int ret;
+
+	monolithic_mount_data = mc->ops->monolithic_mount_data;
+	if (!monolithic_mount_data)
+		monolithic_mount_data = generic_monolithic_mount_data;
+
+	ret = monolithic_mount_data(mc, data);
+	if (ret < 0)
+		return ret;
+	if (mc->ops->validate)
+		return mc->ops->validate(mc);
+	return 0;
+}
+
+/*
  * change filesystem flags. dir should be a physical root of filesystem.
  * If you've mounted a non-root directory somewhere and want to do remount
  * on it - tough luck.
@@ -2286,13 +2312,14 @@  static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 static int do_remount(struct path *path, int flags, int mnt_flags,
 		      void *data)
 {
+	struct mount_context *mc = NULL;
 	int err;
 	struct super_block *sb = path->mnt->mnt_sb;
 	struct mount *mnt = real_mount(path->mnt);
+	struct file_system_type *type = sb->s_type;
 
 	if (!check_mnt(mnt))
 		return -EINVAL;
-
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
@@ -2323,9 +2350,19 @@  static int do_remount(struct path *path, int flags, int mnt_flags,
 		return -EPERM;
 	}
 
-	err = security_sb_remount(sb, data);
-	if (err)
-		return err;
+	if (type->fsopen) {
+		mc = vfs_mntopen(path->mnt, flags, mnt_flags, MOUNT_TYPE_REMOUNT);
+		if (IS_ERR(mc))
+			return PTR_ERR(mc);
+
+		err = parse_monolithic_mount_data(mc, data);
+		if (err < 0)
+			goto err_mc;
+	} else {
+		err = security_sb_remount(sb, data);
+		if (err)
+			return err;
+	}
 
 	down_write(&sb->s_umount);
 	if (flags & MS_BIND)
@@ -2333,7 +2370,7 @@  static int do_remount(struct path *path, int flags, int mnt_flags,
 	else if (!capable(CAP_SYS_ADMIN))
 		err = -EPERM;
 	else
-		err = do_remount_sb(sb, flags, data, 0);
+		err = do_remount_sb(sb, flags, data, 0, mc);
 	if (!err) {
 		lock_mount_hash();
 		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
@@ -2342,6 +2379,9 @@  static int do_remount(struct path *path, int flags, int mnt_flags,
 		unlock_mount_hash();
 	}
 	up_write(&sb->s_umount);
+err_mc:
+	if (mc)
+		put_mount_context(mc);
 	return err;
 }
 
@@ -2451,7 +2491,8 @@  static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
 /*
  * add a mount into a namespace's mount tree
  */
-static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
+static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags,
+			struct mnt_namespace *mnt_ns)
 {
 	struct mountpoint *mp;
 	struct mount *parent;
@@ -2465,7 +2506,7 @@  static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 
 	parent = real_mount(path->mnt);
 	err = -EINVAL;
-	if (unlikely(!check_mnt(parent))) {
+	if (unlikely(!__check_mnt(parent, mnt_ns))) {
 		/* that's acceptable only for automounts done in private ns */
 		if (!(mnt_flags & MNT_SHRINKABLE))
 			goto unlock;
@@ -2493,42 +2534,73 @@  static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 }
 
 static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);
+static int do_new_mount_mc(struct mount_context *mc, struct path *mountpoint,
+			   unsigned int mnt_flags);
 
 /*
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct path *path, const char *fstype, int flags,
+static int do_new_mount(struct path *mountpoint, const char *fstype, int flags,
 			int mnt_flags, const char *name, void *data)
 {
-	struct file_system_type *type;
+	struct mount_context *mc;
 	struct vfsmount *mnt;
 	int err;
 
 	if (!fstype)
 		return -EINVAL;
 
-	type = get_fs_type(fstype);
-	if (!type)
-		return -ENODEV;
+	mc = vfs_fsopen(fstype);
+	if (IS_ERR(mc))
+		return PTR_ERR(mc);
+	mc->ms_flags = flags;
+	mc->mnt_flags = mnt_flags;
 
-	mnt = vfs_kern_mount(type, flags, name, data);
-	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
-	    !mnt->mnt_sb->s_subtype)
-		mnt = fs_set_subtype(mnt, fstype);
+	err = -ENOMEM;
+	mc->device = kstrdup(name, GFP_KERNEL);
+	if (!mc->device)
+		goto err_mc;
 
-	put_filesystem(type);
-	if (IS_ERR(mnt))
-		return PTR_ERR(mnt);
+	if (mc->ops) {
+		err = parse_monolithic_mount_data(mc, data);
+		if (err < 0)
+			goto err_mc;
 
-	if (mount_too_revealing(mnt, &mnt_flags)) {
-		mntput(mnt);
-		return -EPERM;
+		err = do_new_mount_mc(mc, mountpoint, mnt_flags);
+		if (err)
+			goto err_mc;
+
+	} else {
+		mnt = vfs_kern_mount(mc->fs_type, flags, name, data);
+		if (!IS_ERR(mnt) && (mc->fs_type->fs_flags & FS_HAS_SUBTYPE) &&
+		    !mnt->mnt_sb->s_subtype)
+			mnt = fs_set_subtype(mnt, fstype);
+
+		if (IS_ERR(mnt)) {
+			err = PTR_ERR(mnt);
+			goto err_mc;
+		}
+
+		err = -EPERM;
+		if (mount_too_revealing(mnt, &mnt_flags))
+			goto err_mnt;
+
+		err = do_add_mount(real_mount(mnt), mountpoint, mnt_flags,
+				   mc->mnt_ns);
+		if (err)
+			goto err_mnt;
 	}
 
-	err = do_add_mount(real_mount(mnt), path, mnt_flags);
-	if (err)
-		mntput(mnt);
+	put_mount_context(mc);
+	return 0;
+
+err_mnt:
+	mntput(mnt);
+err_mc:
+	if (mc->error)
+		pr_info("Mount failed: %s\n", mc->error);
+	put_mount_context(mc);
 	return err;
 }
 
@@ -2547,7 +2619,8 @@  int finish_automount(struct vfsmount *m, struct path *path)
 		goto fail;
 	}
 
-	err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
+	err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE,
+			   current->nsproxy->mnt_ns);
 	if (!err)
 		return 0;
 fail:
@@ -3061,6 +3134,130 @@  SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	return ret;
 }
 
+static struct dentry *__do_mount_mc(struct mount_context *mc)
+{
+	struct super_block *sb;
+	struct dentry *root;
+	int ret;
+
+	root = mc->ops->mount(mc);
+	if (IS_ERR(root))
+		return root;
+
+	sb = root->d_sb;
+	BUG_ON(!sb);
+	WARN_ON(!sb->s_bdi);
+	sb->s_flags |= MS_BORN;
+
+	ret = security_mount_ctx_kern_mount(mc, sb);
+	if (ret < 0)
+		goto err_sb;
+
+	/*
+	 * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
+	 * but s_maxbytes was an unsigned long long for many releases. Throw
+	 * this warning for a little while to try and catch filesystems that
+	 * violate this rule.
+	 */
+	WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
+		"negative value (%lld)\n", mc->fs_type->name, sb->s_maxbytes);
+
+	up_write(&sb->s_umount);
+	return root;
+
+err_sb:
+	dput(root);
+	deactivate_locked_super(sb);
+	return ERR_PTR(ret);
+}
+
+struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc)
+{
+	struct dentry *root;
+	struct mount *mnt;
+	int ret;
+
+	if (mc->ops->validate) {
+		ret = mc->ops->validate(mc);
+		if (ret < 0)
+			return ERR_PTR(ret);
+	}
+
+	mnt = alloc_vfsmnt(mc->device ?: "none");
+	if (!mnt)
+		return ERR_PTR(-ENOMEM);
+
+	if (mc->ms_flags & MS_KERNMOUNT)
+		mnt->mnt.mnt_flags = MNT_INTERNAL;
+
+	root = __do_mount_mc(mc);
+	if (IS_ERR(root)) {
+		mnt_free_id(mnt);
+		free_vfsmnt(mnt);
+		return ERR_CAST(root);
+	}
+
+	mnt->mnt.mnt_root	= root;
+	mnt->mnt.mnt_sb		= root->d_sb;
+	mnt->mnt_mountpoint	= mnt->mnt.mnt_root;
+	mnt->mnt_parent		= mnt;
+	lock_mount_hash();
+	list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
+	unlock_mount_hash();
+	return &mnt->mnt;
+}
+EXPORT_SYMBOL_GPL(vfs_kern_mount_mc);
+
+struct vfsmount *
+vfs_submount_mc(const struct dentry *mountpoint, struct mount_context *mc)
+{
+	/* Until it is worked out how to pass the user namespace
+	 * through from the parent mount to the submount don't support
+	 * unprivileged mounts with submounts.
+	 */
+	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+		return ERR_PTR(-EPERM);
+
+	mc->ms_flags = MS_SUBMOUNT;
+	return vfs_kern_mount_mc(mc);
+}
+EXPORT_SYMBOL_GPL(vfs_submount_mc);
+
+static int do_new_mount_mc(struct mount_context *mc, struct path *mountpoint,
+			   unsigned int mnt_flags)
+{
+	struct vfsmount *mnt;
+	int ret;
+
+	mnt = vfs_kern_mount_mc(mc);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	if ((mc->fs_type->fs_flags & FS_HAS_SUBTYPE) &&
+	    !mnt->mnt_sb->s_subtype) {
+		mnt = fs_set_subtype(mnt, mc->fs_type->name);
+		if (IS_ERR(mnt))
+			return PTR_ERR(mnt);
+	}
+
+	ret = -EPERM;
+	if (mount_too_revealing(mnt, &mnt_flags)) {
+		mc->error = "VFS: Mount too revealing";
+		goto err_mnt;
+	}
+
+	ret = do_add_mount(real_mount(mnt), mountpoint, mnt_flags, mc->mnt_ns);
+	if (ret < 0) {
+		mc->error = "VFS: Failed to add mount";
+		goto err_mnt;
+	}
+	return ret;
+
+err_mnt:
+	mntput(mnt);
+	return ret;
+}
+
 /*
  * Return true if path is reachable from root
  *
@@ -3302,6 +3499,23 @@  struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
 }
 EXPORT_SYMBOL_GPL(kern_mount_data);
 
+struct vfsmount *kern_mount_data_mc(struct mount_context *mc)
+{
+	struct vfsmount *mnt;
+
+	mc->ms_flags = MS_KERNMOUNT;
+	mnt = vfs_kern_mount_mc(mc);
+	if (!IS_ERR(mnt)) {
+		/*
+		 * it is a longterm mount, don't release mnt until
+		 * we unmount before file sys is unregistered
+		*/
+		real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
+	}
+	return mnt;
+}
+EXPORT_SYMBOL_GPL(kern_mount_data_mc);
+
 void kern_unmount(struct vfsmount *mnt)
 {
 	/* release long term mount so mount point can be released */
diff --git a/fs/super.c b/fs/super.c
index adb0c0de428c..6e7b86520337 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -805,10 +805,13 @@  struct super_block *user_get_super(dev_t dev)
  *	@flags:	numeric part of options
  *	@data:	the rest of options
  *      @force: whether or not to force the change
+ *	@mc:	the mount context for filesystems that support it
+ *		(NULL if called from emergency or umount)
  *
  *	Alters the mount options of a mounted file system.
  */
-int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
+int do_remount_sb(struct super_block *sb, int flags, void *data, int force,
+		  struct mount_context *mc)
 {
 	int retval;
 	int remount_ro;
@@ -850,8 +853,14 @@  int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 		}
 	}
 
-	if (sb->s_op->remount_fs) {
-		retval = sb->s_op->remount_fs(sb, &flags, data);
+	if (sb->s_op->remount_fs_mc ||
+	    sb->s_op->remount_fs) {
+		if (sb->s_op->remount_fs_mc) {
+		    retval = sb->s_op->remount_fs_mc(sb, mc);
+		    flags = mc->ms_flags;
+		} else {
+			retval = sb->s_op->remount_fs(sb, &flags, data);
+		}
 		if (retval) {
 			if (!force)
 				goto cancel_readonly;
@@ -898,7 +907,7 @@  static void do_emergency_remount(struct work_struct *work)
 			/*
 			 * What lock protects sb->s_flags??
 			 */
-			do_remount_sb(sb, MS_RDONLY, NULL, 1);
+			do_remount_sb(sb, MS_RDONLY, NULL, 1, NULL);
 		}
 		up_write(&sb->s_umount);
 		spin_lock(&sb_lock);
@@ -1048,6 +1057,37 @@  struct dentry *mount_ns(struct file_system_type *fs_type,
 
 EXPORT_SYMBOL(mount_ns);
 
+struct dentry *mount_ns_mc(struct mount_context *mc, void *ns)
+{
+	struct super_block *sb;
+
+	/* Don't allow mounting unless the caller has CAP_SYS_ADMIN
+	 * over the namespace.
+	 */
+	if (!(mc->ms_flags & MS_KERNMOUNT) &&
+	    !ns_capable(mc->user_ns, CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	sb = sget_userns(mc->fs_type, ns_test_super, ns_set_super,
+			 mc->ms_flags, mc->user_ns, ns);
+	if (IS_ERR(sb))
+		return ERR_CAST(sb);
+
+	if (!sb->s_root) {
+		int err;
+		err = mc->ops->fill_super(sb, mc);
+		if (err) {
+			deactivate_locked_super(sb);
+			return ERR_PTR(err);
+		}
+
+		sb->s_flags |= MS_ACTIVE;
+	}
+
+	return dget(sb->s_root);
+}
+EXPORT_SYMBOL(mount_ns_mc);
+
 #ifdef CONFIG_BLOCK
 static int set_bdev_super(struct super_block *s, void *data)
 {
@@ -1196,7 +1236,7 @@  struct dentry *mount_single(struct file_system_type *fs_type,
 		}
 		s->s_flags |= MS_ACTIVE;
 	} else {
-		do_remount_sb(s, flags, data, 0);
+		do_remount_sb(s, flags, data, 0, NULL);
 	}
 	return dget(s->s_root);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 30e5c14bd743..40fe5c5054ec 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -55,6 +55,7 @@  struct workqueue_struct;
 struct iov_iter;
 struct fscrypt_info;
 struct fscrypt_operations;
+struct mount_context;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -701,6 +702,11 @@  static inline void inode_unlock(struct inode *inode)
 	up_write(&inode->i_rwsem);
 }
 
+static inline int inode_lock_killable(struct inode *inode)
+{
+	return down_write_killable(&inode->i_rwsem);
+}
+
 static inline void inode_lock_shared(struct inode *inode)
 {
 	down_read(&inode->i_rwsem);
@@ -1786,6 +1792,7 @@  struct super_operations {
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
+	int (*remount_fs_mc) (struct super_block *, struct mount_context *);
 	void (*umount_begin) (struct super_block *);
 
 	int (*show_options)(struct seq_file *, struct dentry *);
@@ -2020,8 +2027,10 @@  struct file_system_type {
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
+	unsigned short mc_size;		/* Size of mount context to allocate */
 	struct dentry *(*mount) (struct file_system_type *, int,
 		       const char *, void *);
+	int (*fsopen)(struct mount_context *, struct super_block *);
 	void (*kill_sb) (struct super_block *);
 	struct module *owner;
 	struct file_system_type * next;
@@ -2039,6 +2048,7 @@  struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
+extern struct dentry *mount_ns_mc(struct mount_context *mc, void *ns);
 extern struct dentry *mount_ns(struct file_system_type *fs_type,
 	int flags, void *data, void *ns, struct user_namespace *user_ns,
 	int (*fill_super)(struct super_block *, void *, int));
@@ -2105,6 +2115,7 @@  extern int register_filesystem(struct file_system_type *);
 extern int unregister_filesystem(struct file_system_type *);
 extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 #define kern_mount(type) kern_mount_data(type, NULL)
+extern struct vfsmount *kern_mount_data_mc(struct mount_context *);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index e29d4c62a3c8..f6aa68b8e68e 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -75,6 +75,32 @@ 
  *	should enable secure mode.
  *	@bprm contains the linux_binprm structure.
  *
+ * Security hooks for mount using fd context.
+ *
+ * @mount_ctx_alloc:
+ *	Allocate and attach a security structure to mc->security.  This pointer
+ *	is initialised to NULL by the caller.
+ *	@mc indicates the new mount context.
+ *	@src_sb indicates the source superblock of a submount.
+ * @mount_ctx_dup:
+ *	Allocate and attach a security structure to mc->security.  This pointer
+ *	is initialised to NULL by the caller.
+ *	@mc indicates the new mount context.
+ *	@src_mc indicates the original mount context.
+ * @mount_ctx_free:
+ *	Clean up a mount context.
+ *	@mc indicates the mount context.
+ * @mount_ctx_option:
+ *	Userspace provided an option to configure a mount.  The LSM may reject
+ *	it with an error and may use it for itself, in which case it should
+ *	return 1; otherwise it should return 0 to pass it on to the filesystem.
+ *	@mc indicates the mount context.
+ *	@p indicates the option in "key[=val]" form.
+ * @mount_ctx_kern_mount:
+ *	Equivalent of sb_kern_mount, but with a mount_context.
+ *	@mc indicates the mount context.
+ *	@src_sb indicates the new superblock.
+ *
  * Security hooks for filesystem operations.
  *
  * @sb_alloc_security:
@@ -1358,6 +1384,12 @@  union security_list_options {
 	void (*bprm_committing_creds)(struct linux_binprm *bprm);
 	void (*bprm_committed_creds)(struct linux_binprm *bprm);
 
+	int (*mount_ctx_alloc)(struct mount_context *mc, struct super_block *src_sb);
+	int (*mount_ctx_dup)(struct mount_context *mc, struct mount_context *src_mc);
+	void (*mount_ctx_free)(struct mount_context *mc);
+	int (*mount_ctx_option)(struct mount_context *mc, char *opt);
+	int (*mount_ctx_kern_mount)(struct mount_context *mc, struct super_block *sb);
+
 	int (*sb_alloc_security)(struct super_block *sb);
 	void (*sb_free_security)(struct super_block *sb);
 	int (*sb_copy_data)(char *orig, char *copy);
@@ -1666,6 +1698,11 @@  struct security_hook_heads {
 	struct list_head bprm_secureexec;
 	struct list_head bprm_committing_creds;
 	struct list_head bprm_committed_creds;
+	struct list_head mount_ctx_alloc;
+	struct list_head mount_ctx_dup;
+	struct list_head mount_ctx_free;
+	struct list_head mount_ctx_option;
+	struct list_head mount_ctx_kern_mount;
 	struct list_head sb_alloc_security;
 	struct list_head sb_free_security;
 	struct list_head sb_copy_data;
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 8e0352af06b7..cf2583406986 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -69,6 +69,56 @@  struct vfsmount {
 	int mnt_flags;
 };
 
+struct mount_context;
+struct mount_context_operations {
+	void (*free)(struct mount_context *mc);
+	int (*dup)(struct mount_context *mc, struct mount_context *src);
+	/* An option has been specified. */
+	int (*option)(struct mount_context *mc, char *p);
+	/* Parse monolithic mount data. */
+	int (*monolithic_mount_data)(struct mount_context *mc, void *data);
+	/* Validate the mount options */
+	int (*validate)(struct mount_context *mc);
+	/* Perform the mount. */
+	struct dentry *(*mount)(struct mount_context *mc);
+	/* Fill in a superblock */
+	int (*fill_super)(struct super_block *s, struct mount_context *mc);
+};
+
+enum mount_type {
+	MOUNT_TYPE_NEW,		/* New mount made directly */
+	MOUNT_TYPE_SUBMOUNT,	/* New mount made automatically */
+	MOUNT_TYPE_REMOUNT,	/* Change of an existing mount */
+};
+
+/*
+ * Mount context as allocated and constructed by fsopen().  The filesystem must
+ * support the ->ctx_*() operations.  The size of the object allocated is in
+ * struct file_system_type::mount_context_size; this must be embedded as the
+ * fist thing in the filesystem's own context.
+ */
+struct mount_context {
+	const struct mount_context_operations *ops;
+	struct file_system_type	*fs_type;
+	struct user_namespace	*user_ns;	/* The user namespace for this mount */
+	struct mnt_namespace	*mnt_ns;	/* The mount namespace for this mount */
+	struct pid_namespace	*pid_ns;	/* The process ID namespace for this mount */
+	struct net		*net_ns;	/* The network namespace for this mount */
+	const struct cred	*cred;		/* The mounter's credentials */
+	char			*device;	/* The device name or mount target */
+	char			*root_path;	/* The path within the mount to mount */
+	void			*security;	/* The LSM context */
+	const char		*error;		/* Error string to be read by read() */
+	unsigned int		ms_flags;	/* The superblock flags (MS_*) */
+	unsigned int		mnt_flags;	/* The mount flags (MNT_*) */
+	bool			mounted;	/* Set when mounted */
+	bool			sloppy;		/* Unrecognised options are okay */
+	bool			silent;
+	enum mount_type		mount_type : 8;
+};
+
+extern const struct file_operations fs_fs_fops;
+
 struct file; /* forward dec */
 struct path;
 
@@ -90,9 +140,26 @@  struct file_system_type;
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
 				      void *data);
+extern struct vfsmount *vfs_kern_mount_mc(struct mount_context *mc);
 extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
 				     struct file_system_type *type,
 				     const char *name, void *data);
+extern struct vfsmount *vfs_submount_mc(const struct dentry *mountpoint,
+					struct mount_context *mc);
+extern struct mount_context *vfs_fsopen(const char *fs_name);
+extern struct mount_context *__vfs_fsopen(struct file_system_type *fs_type,
+					  struct super_block *src_sb,
+					  unsigned int ms_flags,
+					  unsigned int mnt_flags,
+					  enum mount_type mount_type);
+extern struct mount_context *vfs_mntopen(struct vfsmount *mnt,
+					 unsigned int ms_flags,
+					 unsigned int mnt_flags,
+					 enum mount_type mount_type);
+extern struct mount_context *vfs_dup_mount_context(struct mount_context *src);
+extern int vfs_mount_option(struct mount_context *mc, char *data);
+extern int generic_monolithic_mount_data(struct mount_context *ctx, void *data);
+extern void put_mount_context(struct mount_context *ctx);
 
 extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);
diff --git a/include/linux/security.h b/include/linux/security.h
index 96899fad7016..91efe3039bff 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -55,6 +55,7 @@  struct msg_queue;
 struct xattr;
 struct xfrm_sec_ctx;
 struct mm_struct;
+struct mount_context;
 
 /* If capable should audit the security request */
 #define SECURITY_CAP_NOAUDIT 0
@@ -220,6 +221,11 @@  int security_bprm_check(struct linux_binprm *bprm);
 void security_bprm_committing_creds(struct linux_binprm *bprm);
 void security_bprm_committed_creds(struct linux_binprm *bprm);
 int security_bprm_secureexec(struct linux_binprm *bprm);
+int security_mount_ctx_alloc(struct mount_context *mc, struct super_block *sb);
+int security_mount_ctx_dup(struct mount_context *mc, struct mount_context *src);
+void security_mount_ctx_free(struct mount_context *mc);
+int security_mount_ctx_option(struct mount_context *mc, char *opt);
+int security_mount_ctx_kern_mount(struct mount_context *mc, struct super_block *sb);
 int security_sb_alloc(struct super_block *sb);
 void security_sb_free(struct super_block *sb);
 int security_sb_copy_data(char *orig, char *copy);
@@ -513,6 +519,29 @@  static inline int security_bprm_secureexec(struct linux_binprm *bprm)
 	return cap_bprm_secureexec(bprm);
 }
 
+static inline int security_mount_ctx_alloc(struct mount_context *mc,
+					   struct super_block *src_sb)
+{
+	return 0;
+}
+static inline int security_mount_ctx_dup(struct mount_context *mc,
+					 struct mount_context *src)
+{
+	return 0;
+}
+static inline void security_mount_ctx_free(struct mount_context *mc)
+{
+}
+static inline int security_mount_ctx_option(struct mount_context *mc, char *opt)
+{
+	return 0;
+}
+static inline int security_mount_ctx_kern_mount(struct mount_context *mc,
+						struct super_block *sb)
+{
+	return 0;
+}
+
 static inline int security_sb_alloc(struct super_block *sb)
 {
 	return 0;
diff --git a/security/security.c b/security/security.c
index 23555c5504f6..2e522361df66 100644
--- a/security/security.c
+++ b/security/security.c
@@ -309,6 +309,31 @@  int security_bprm_secureexec(struct linux_binprm *bprm)
 	return call_int_hook(bprm_secureexec, 0, bprm);
 }
 
+int security_mount_ctx_alloc(struct mount_context *mc, struct super_block *src_sb)
+{
+	return call_int_hook(mount_ctx_alloc, 0, mc, src_sb);
+}
+
+int security_mount_ctx_dup(struct mount_context *mc, struct mount_context *src_mc)
+{
+	return call_int_hook(mount_ctx_dup, 0, mc, src_mc);
+}
+
+void security_mount_ctx_free(struct mount_context *mc)
+{
+	call_void_hook(mount_ctx_free, mc);
+}
+
+int security_mount_ctx_option(struct mount_context *mc, char *opt)
+{
+	return call_int_hook(mount_ctx_option, 0, mc, opt);
+}
+
+int security_mount_ctx_kern_mount(struct mount_context *mc, struct super_block *sb)
+{
+	return call_int_hook(mount_ctx_kern_mount, 0, mc, sb);
+}
+
 int security_sb_alloc(struct super_block *sb)
 {
 	return call_int_hook(sb_alloc_security, 0, sb);
@@ -1659,6 +1684,13 @@  struct security_hook_heads security_hook_heads = {
 		LIST_HEAD_INIT(security_hook_heads.bprm_committing_creds),
 	.bprm_committed_creds =
 		LIST_HEAD_INIT(security_hook_heads.bprm_committed_creds),
+	.mount_ctx_alloc = LIST_HEAD_INIT(security_hook_heads.mount_ctx_alloc),
+	.mount_ctx_dup = LIST_HEAD_INIT(security_hook_heads.mount_ctx_dup),
+	.mount_ctx_free = LIST_HEAD_INIT(security_hook_heads.mount_ctx_free),
+	.mount_ctx_option =
+		LIST_HEAD_INIT(security_hook_heads.mount_ctx_option),
+	.mount_ctx_kern_mount =
+		LIST_HEAD_INIT(security_hook_heads.mount_ctx_kern_mount),
 	.sb_alloc_security =
 		LIST_HEAD_INIT(security_hook_heads.sb_alloc_security),
 	.sb_free_security =
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 0c2ac318aa7f..cf38db840f71 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2826,6 +2826,179 @@  static int selinux_umount(struct vfsmount *mnt, int flags)
 				   FILESYSTEM__UNMOUNT, NULL);
 }
 
+/* fsopen mount context operations */
+
+static int selinux_mount_ctx_alloc(struct mount_context *mc,
+				   struct super_block *src_sb)
+{
+	struct security_mnt_opts *opts;
+
+	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
+	if (!opts)
+		return -ENOMEM;
+
+	mc->security = opts;
+	return 0;
+}
+
+static int selinux_mount_ctx_dup(struct mount_context *mc,
+				 struct mount_context *src_mc)
+{
+	const struct security_mnt_opts *src = src_mc->security;
+	struct security_mnt_opts *opts;
+	int i, n;
+
+	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
+	if (!opts)
+		return -ENOMEM;
+	mc->security = opts;
+
+	if (!src || !src->num_mnt_opts)
+		return 0;
+	n = opts->num_mnt_opts = src->num_mnt_opts;
+
+	if (opts->mnt_opts) {
+		opts->mnt_opts = kcalloc(n, sizeof(char *), GFP_KERNEL);
+		if (!opts->mnt_opts)
+			return -ENOMEM;
+
+		for (i = 0; i < n; i++) {
+			if (src->mnt_opts[i]) {
+				opts->mnt_opts[i] = kstrdup(src->mnt_opts[i],
+							    GFP_KERNEL);
+				if (!opts->mnt_opts[i])
+					return -ENOMEM;
+			}
+		}
+	}
+
+	if (src->mnt_opts_flags) {
+		opts->mnt_opts_flags = kmemdup(src->mnt_opts_flags,
+					       n * sizeof(int), GFP_KERNEL);
+		if (!opts->mnt_opts_flags)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void selinux_mount_ctx_free(struct mount_context *mc)
+{
+	struct security_mnt_opts *opts = mc->security;
+
+	security_free_mnt_opts(opts);
+	mc->security = NULL;
+}
+
+static int selinux_mount_ctx_option(struct mount_context *mc, char *opt)
+{
+	struct security_mnt_opts *opts = mc->security;
+	substring_t args[MAX_OPT_ARGS];
+	unsigned int have;
+	char *c, **oo;
+	void *old;
+	int token, ctx, i;
+
+	token = match_token(opt, tokens, args);
+	if (token == Opt_error)
+		return 0; /* Doesn't belong to us. */
+
+	have = 0;
+	for (i = 0; i < opts->num_mnt_opts; i++)
+		have |= 1 << opts->mnt_opts_flags[i];
+	if (have & (1 << token)) {
+		mc->error = "SELinux: Duplicate mount options";
+		return -EINVAL;
+	}
+
+	switch (token) {
+	case Opt_context:
+		if (have & (1 << Opt_defcontext))
+			goto incompatible;
+		ctx = CONTEXT_MNT;
+		goto copy_context_string;
+
+	case Opt_fscontext:
+		ctx = FSCONTEXT_MNT;
+		goto copy_context_string;
+
+	case Opt_rootcontext:
+		ctx = ROOTCONTEXT_MNT;
+		goto copy_context_string;
+
+	case Opt_defcontext:
+		if (have & (1 << Opt_context))
+			goto incompatible;
+		ctx = DEFCONTEXT_MNT;
+		goto copy_context_string;
+
+	case Opt_labelsupport:
+		return 1;
+
+	default:
+		mc->error = "SELinux: Unknown mount option";
+		return -EINVAL;
+	}
+
+copy_context_string:
+	if (opts->num_mnt_opts > 3) {
+		mc->error = "SELinux: Too many options";
+		return -EINVAL;
+	}
+	if (!opts->mnt_opts_flags) {
+		opts->mnt_opts_flags = kcalloc(3, sizeof(int), GFP_KERNEL);
+		if (!opts->mnt_opts_flags)
+			return -ENOMEM;
+	}
+
+	if (opts->mnt_opts) {
+		oo = kmalloc((opts->num_mnt_opts + 1) * sizeof(char *),
+			     GFP_KERNEL);
+		if (!oo)
+			return -ENOMEM;
+		memcpy(oo, opts->mnt_opts, opts->num_mnt_opts * sizeof(char *));
+		oo[opts->num_mnt_opts] = NULL;
+		old = opts->mnt_opts;
+		opts->mnt_opts = oo;
+		kfree(old);
+	}
+
+	c = match_strdup(&args[0]);
+	if (!c)
+		return -ENOMEM;
+	opts->mnt_opts[opts->num_mnt_opts] = c;
+	opts->mnt_opts_flags[opts->num_mnt_opts] = ctx;
+	opts->num_mnt_opts++;
+	return 1;
+
+incompatible:
+	mc->error = "SELinux: Incompatible mount options";
+	return -EINVAL;
+}
+
+static int selinux_mount_ctx_kern_mount(struct mount_context *mc,
+					struct super_block *sb)
+{
+	const struct cred *cred = current_cred();
+	struct common_audit_data ad;
+	int rc;
+
+	rc = selinux_set_mnt_opts(sb, mc->security, 0, NULL);
+	if (rc)
+		return rc;
+
+	/* Allow all mounts performed by the kernel */
+	if (mc->ms_flags & MS_KERNMOUNT)
+		return 0;
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = sb->s_root;
+	rc = superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
+	if (rc < 0)
+		mc->error = "SELinux: Mount of superblock not permitted";
+	return rc;
+}
+
 /* inode security operations */
 
 static int selinux_inode_alloc_security(struct inode *inode)
@@ -6131,6 +6304,12 @@  static struct security_hook_list selinux_hooks[] = {
 	LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds),
 	LSM_HOOK_INIT(bprm_secureexec, selinux_bprm_secureexec),
 
+	LSM_HOOK_INIT(mount_ctx_alloc, selinux_mount_ctx_alloc),
+	LSM_HOOK_INIT(mount_ctx_dup, selinux_mount_ctx_dup),
+	LSM_HOOK_INIT(mount_ctx_free, selinux_mount_ctx_free),
+	LSM_HOOK_INIT(mount_ctx_option, selinux_mount_ctx_option),
+	LSM_HOOK_INIT(mount_ctx_kern_mount, selinux_mount_ctx_kern_mount),
+
 	LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security),
 	LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security),
 	LSM_HOOK_INIT(sb_copy_data, selinux_sb_copy_data),