[08/27] VFS: Introduce the structs and doc for a filesystem context [ver #5]

Commit Message

David Howells June 14, 2017, 3:16 p.m. UTC

Introduce a filesystem context concept to be used during superblock
creation for mount and superblock reconfiguration for remount.  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_*).

 (5) Security details.

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

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

 Documentation/filesystems/mounting.txt |  436 ++++++++++++++++++++++++++++++++
 include/linux/fs_context.h             |   72 +++++
 2 files changed, 508 insertions(+)
 create mode 100644 Documentation/filesystems/mounting.txt
 create mode 100644 include/linux/fs_context.h

Comments

Randy Dunlap June 14, 2017, 6:02 p.m. UTC | #1

On 06/14/17 08:16, David Howells wrote:
> Introduce a filesystem context concept to be used during superblock
> creation for mount and superblock reconfiguration for remount.  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_*).
> 
>  (5) Security details.
> 
>  (6) Filesystem-specific data, as set by the mount options.
> 
> Signed-off-by: David Howells <[e-mail]>
> ---
> 
>  Documentation/filesystems/mounting.txt |  436 ++++++++++++++++++++++++++++++++
>  include/linux/fs_context.h             |   72 +++++
>  2 files changed, 508 insertions(+)
>  create mode 100644 Documentation/filesystems/mounting.txt
>  create mode 100644 include/linux/fs_context.h
> 
> diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
> new file mode 100644
> index 000000000000..315a5a4ff5cc
> --- /dev/null
> +++ b/Documentation/filesystems/mounting.txt
> @@ -0,0 +1,436 @@
> +			      ===================
> +			      FILESYSTEM MOUNTING
> +			      ===================
> +
> +CONTENTS
> +
> + (1) Overview.
> +
> + (2) The filesystem context.
> +
> + (3) The filesystem context operations.
> +
> + (4) Filesystem context security.
> +
> + (5) VFS filesystem context operations.
> +
> +
> +========
> +OVERVIEW
> +========
> +
> +The creation of new mounts is now to be done in a multistep process:
> +
> + (1) Create a filesystem context.
> +
> + (2) Parse the options and attach them to the context.  Options may be passed
> +     individually from userspace.
> +
> + (3) Validate and pre-process the context.
> +
> + (4) Get or create a superblock and mountable root.
> +
> + (5) Perform the mount.
> +
> + (6) Return an error message attached to the context.
> +
> + (7) Destroy the context.
> +
> +To support this, the file_system_type struct gains two new fields:
> +
> +	unsigned short fs_context_size;
> +
> +which indicates the total amount of space that should be allocated for context
> +data (see the Filesystem Context section), and:
> +
> +	int (*init_fs_context)(struct fs_context *fc, struct super_block *src_sb);
> +
> +which is invoked to set up the filesystem-specific parts of a filesystem
> +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 (FS_CONTEXT_FOR_SUBMOUNT) or remount

                       ;

> +(FS_CONTEXT_FOR_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:

                                         one field:

> +
> +	int (*remount_fs_fc) (struct super_block *, struct fs_context *);
> +
> +This shadows the ->remount_fs() operation and takes a prepared filesystem
> +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_fc is intended as a replacement for remount_fs.
> +
> +
> +======================
> +THE FILESYSTEM CONTEXT
> +======================
> +
> +The creation and reconfiguration of a superblock is governed by a filesystem
> +context.  This is represented by the fs_context structure:
> +
> +	struct fs_context {
> +		const struct fs_context_operations *ops;
> +		struct file_system_type *fs;
> +		struct dentry		*root;
> +		struct user_namespace	*user_ns;
> +		struct net		*net_ns;
> +		const struct cred	*cred;
> +		char			*device;
> +		void			*security;
> +		unsigned int		sb_flags;
> +		bool			sloppy;
> +		bool			silent;
> +		bool			degraded;
> +		enum fs_context_purpose	purpose : 8;
> +	};
> +
> +When the VFS creates this, it allocates ->fs_context_size bytes (as specified
> +by the file_system_type object) to hold both the fs_context struct and any
> +extra data required by the filesystem.  The fs_context struct is placed at the
> +beginning of this space.  Any extra space beyond that is for use by the
> +filesystem.  The filesystem should wrap the struct in its own, e.g.:
> +
> +	struct nfs_fs_context {
> +		struct fs_context fc;
> +		...
> +	};
> +
> +placing the fs_context struct first.  container_of() can then be used.  The
> +file_system_type would be initialised thus:
> +
> +	struct file_system_type nfs = {
> +		...
> +		.fs_context_size	= sizeof(struct nfs_fs_context),
> +		.init_fs_context	= nfs_init_fs_context,
> +		...
> +	};
> +
> +The fs_context fields are as follows:
> +
> + (*) const struct fs_context_operations *ops
> +
> +     These are operations that can be done on a filesystem context (see
> +     below).  This must be set by the ->init_fs_context() file_system_type
> +     operation.
> +
> + (*) struct file_system_type *fs
> +
> +     A pointer to the file_system_type of the filesystem that is being
> +     constructed or reconfigured.  This retains a ref on the type owner.

s/ref/reference/

> +
> + (*) struct dentry *root
> +
> +     A pointer to the root of the mountable tree (and indirectly, the
> +     superblock thereof).  This is filled in by the ->get_tree() op.
> +
> + (*) struct user_namespace *user_ns
> + (*) struct net *net_ns
> +
> +     This is a subset of the namespaces in use by the invoking process.  This

	These are                                                           They

> +     retains a ref on each namespace.  The subscribed namespaces may be

	retain a reference

> +     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.

s/ref/reference/

> +
> + (*) 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.
> +
> + (*) void *security
> +
> +     A place for the LSMs to hang their security data for the superblock.  The
> +     relevant security operations are described below.
> +
> + (*) unsigned int sb_flags
> +
> +     This holds the MS_* flags mount flags.
> +
> + (*) 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.
> +
> + (*) bool degraded
> +
> +     This is set if any preallocated resources in the context have been used
> +     up, thereby rendering it unreusable for the ->get_tree() op.
> +
> + (*) enum fs_context_purpose
> +
> +     This indicates the purpose for which the context is intended.  The
> +     available values are:
> +
> +	FS_CONTEXT_FOR_NEW	-- New mount
> +	FS_CONTEXT_FOR_SUBMOUNT	-- New automatic submount of extant mount
> +	FS_CONTEXT_FOR_REMOUNT	-- Change an existing mount
> +
> +The mount context is created by calling vfs_new_fs_context(), vfs_sb_reconfig()
> +or vfs_dup_fs_context() and is destroyed with put_fs_context().  Note that the
> +structure is not refcounted.
> +
> +VFS, security and filesystem mount options are set individually with
> +vfs_parse_mount_option().  Options provided by the old mount(2) system call as
> +a page of data can be parsed 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 FILESYSTEM CONTEXT OPERATIONS
> +=================================
> +
> +The filesystem context points to a table of operations:
> +
> +	struct fs_context_operations {
> +		void (*free)(struct fs_context *fc);
> +		int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
> +		int (*parse_option)(struct fs_context *fc, char *p);
> +		int (*monolithic_mount_data)(struct fs_context *fc, void *data);
> +		int (*validate)(struct fs_context *fc);
> +		int (*get_tree)(struct fs_context *fc);
> +	};
> +
> +These operations are invoked by the various stages of the mount procedure to
> +manage the filesystem context.  They are as follows:
> +
> + (*) void (*free)(struct fs_context *fc);
> +
> +     Called to clean up the filesystem-specific part of the filesystem context
> +     when the context is destroyed.  It should be aware that parts of the
> +     context may have been removed and NULL'd out by ->get_tree().
> +
> + (*) int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
> +
> +     Called when a filesystem context has been duplicated to get any refs or
> +     copy any non-referenced resources held in the filesystem-specific part of
> +     the filesystem context.  An error may be returned to indicate failure to
> +     do this.
> +
> +     [!] Note that even if this fails, put_fs_context() will be called
> +	 immediately thereafter, so ->dup() *must* make the
> +	 filesystem-specific part safe for ->free().
> +
> + (*) int (*parse_option)(struct fs_context *fc, char *p);
> +
> +     Called when an option is to be added to the filesystem context.  p points
> +     to the option string, likely in "key[=val]" format.  VFS-specific options
> +     will have been weeded out and fc->sb_flags updated in the context.
> +     Security options will also have been weeded out and fc->security updated.
> +
> +     If successful, 0 should be returned and a negative error code otherwise.
> +     If an ambiguous error (such as -EINVAL) is returned, sb_cfg_error() or
> +     sb_cfg_inval() should be used to provide a string that provides more
> +     information.
> +
> + (*) int (*monolithic_mount_data)(struct fs_context *fc, 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 ->parse_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
> +     generic_monolithic_mount_data().
> +
> + (*) int (*validate)(struct fs_context *fc);
> +
> +     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 fc->mount_type == FS_CONTEXT_FOR_REMOUNT, some of the options
> +     necessary for a new mount may not be set.
> +
> +     The return value is as for ->parse_option().
> +
> + (*) int (*get_tree)(struct fs_context *fc);
> +
> +     Called to get or create the mountable root and superblock, using the
> +     information stored in the filesystem context (remounts go
> +     via a different vector).  It may detach any resources it desires from the
> +     filesystem context and transfer them to the superblock it
> +     creates.
> +
> +     On success it should set fc->root to the mountable root.
> +
> +     In the case of an error, it should return a negative error code and
> +     consider invoking sb_cfg_inval() or sb_cfg_error().
> +
> +
> +=========================================
> +FILESYSTEM CONTEXT SECURITY
> +========================================
> +
> +The filesystem context contains a security points that the LSMs

                                              point or pointer ?

> +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:

Casey Schaufler June 14, 2017, 8:03 p.m. UTC | #2

On 6/14/2017 8:16 AM, David Howells wrote:
> Introduce a filesystem context concept to be used during superblock
> creation for mount and superblock reconfiguration for remount.  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_*).
>
>  (5) Security details.
>
>  (6) Filesystem-specific data, as set by the mount options.
>
> Signed-off-by: David Howells <[e-mail]>
> ---
>
>  Documentation/filesystems/mounting.txt |  436 ++++++++++++++++++++++++++++++++
>  include/linux/fs_context.h             |   72 +++++
>  2 files changed, 508 insertions(+)
>  create mode 100644 Documentation/filesystems/mounting.txt
>  create mode 100644 include/linux/fs_context.h
>
> diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
> new file mode 100644
> index 000000000000..315a5a4ff5cc
> --- /dev/null
> +++ b/Documentation/filesystems/mounting.txt
> @@ -0,0 +1,436 @@
> +			      ===================
> +			      FILESYSTEM MOUNTING
> +			      ===================
> +
> +CONTENTS
> +
> + (1) Overview.
> +
> + (2) The filesystem context.
> +
> + (3) The filesystem context operations.
> +
> + (4) Filesystem context security.
> +
> + (5) VFS filesystem context operations.
> +
> +
> +========
> +OVERVIEW
> +========
> +
> +The creation of new mounts is now to be done in a multistep process:
> +
> + (1) Create a filesystem context.
> +
> + (2) Parse the options and attach them to the context.  Options may be passed
> +     individually from userspace.
> +
> + (3) Validate and pre-process the context.
> +
> + (4) Get or create a superblock and mountable root.
> +
> + (5) Perform the mount.
> +
> + (6) Return an error message attached to the context.
> +
> + (7) Destroy the context.
> +
> +To support this, the file_system_type struct gains two new fields:
> +
> +	unsigned short fs_context_size;
> +
> +which indicates the total amount of space that should be allocated for context
> +data (see the Filesystem Context section), and:
> +
> +	int (*init_fs_context)(struct fs_context *fc, struct super_block *src_sb);
> +
> +which is invoked to set up the filesystem-specific parts of a filesystem
> +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 (FS_CONTEXT_FOR_SUBMOUNT) or remount
> +(FS_CONTEXT_FOR_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_fc) (struct super_block *, struct fs_context *);
> +
> +This shadows the ->remount_fs() operation and takes a prepared filesystem
> +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_fc is intended as a replacement for remount_fs.
> +
> +
> +======================
> +THE FILESYSTEM CONTEXT
> +======================
> +
> +The creation and reconfiguration of a superblock is governed by a filesystem
> +context.  This is represented by the fs_context structure:
> +
> +	struct fs_context {
> +		const struct fs_context_operations *ops;
> +		struct file_system_type *fs;
> +		struct dentry		*root;
> +		struct user_namespace	*user_ns;
> +		struct net		*net_ns;
> +		const struct cred	*cred;
> +		char			*device;
> +		void			*security;
> +		unsigned int		sb_flags;
> +		bool			sloppy;
> +		bool			silent;
> +		bool			degraded;
> +		enum fs_context_purpose	purpose : 8;
> +	};

Could you namespace the fields of this structure?
e.g. fs_cred, fs_security
It makes it so much easier to determine which ->cred
you're looking at.

> +
> +When the VFS creates this, it allocates ->fs_context_size bytes (as specified
> +by the file_system_type object) to hold both the fs_context struct and any
> +extra data required by the filesystem.  The fs_context struct is placed at the
> +beginning of this space.  Any extra space beyond that is for use by the
> +filesystem.  The filesystem should wrap the struct in its own, e.g.:
> +
> +	struct nfs_fs_context {
> +		struct fs_context fc;
> +		...
> +	};
> +
> +placing the fs_context struct first.  container_of() can then be used.  The
> +file_system_type would be initialised thus:
> +
> +	struct file_system_type nfs = {
> +		...
> +		.fs_context_size	= sizeof(struct nfs_fs_context),
> +		.init_fs_context	= nfs_init_fs_context,
> +		...
> +	};
> +
> +The fs_context fields are as follows:
> +
> + (*) const struct fs_context_operations *ops
> +
> +     These are operations that can be done on a filesystem context (see
> +     below).  This must be set by the ->init_fs_context() file_system_type
> +     operation.
> +
> + (*) struct file_system_type *fs
> +
> +     A pointer to the file_system_type of the filesystem that is being
> +     constructed or reconfigured.  This retains a ref on the type owner.
> +
> + (*) struct dentry *root
> +
> +     A pointer to the root of the mountable tree (and indirectly, the
> +     superblock thereof).  This is filled in by the ->get_tree() op.
> +
> + (*) struct user_namespace *user_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.
> +
> + (*) void *security
> +
> +     A place for the LSMs to hang their security data for the superblock.  The
> +     relevant security operations are described below.
> +
> + (*) unsigned int sb_flags
> +
> +     This holds the MS_* flags mount flags.
> +
> + (*) 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.
> +
> + (*) bool degraded
> +
> +     This is set if any preallocated resources in the context have been used
> +     up, thereby rendering it unreusable for the ->get_tree() op.
> +
> + (*) enum fs_context_purpose
> +
> +     This indicates the purpose for which the context is intended.  The
> +     available values are:
> +
> +	FS_CONTEXT_FOR_NEW	-- New mount
> +	FS_CONTEXT_FOR_SUBMOUNT	-- New automatic submount of extant mount
> +	FS_CONTEXT_FOR_REMOUNT	-- Change an existing mount
> +
> +The mount context is created by calling vfs_new_fs_context(), vfs_sb_reconfig()
> +or vfs_dup_fs_context() and is destroyed with put_fs_context().  Note that the
> +structure is not refcounted.
> +
> +VFS, security and filesystem mount options are set individually with
> +vfs_parse_mount_option().  Options provided by the old mount(2) system call as
> +a page of data can be parsed 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 FILESYSTEM CONTEXT OPERATIONS
> +=================================
> +
> +The filesystem context points to a table of operations:
> +
> +	struct fs_context_operations {
> +		void (*free)(struct fs_context *fc);
> +		int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
> +		int (*parse_option)(struct fs_context *fc, char *p);
> +		int (*monolithic_mount_data)(struct fs_context *fc, void *data);
> +		int (*validate)(struct fs_context *fc);
> +		int (*get_tree)(struct fs_context *fc);
> +	};
> +
> +These operations are invoked by the various stages of the mount procedure to
> +manage the filesystem context.  They are as follows:
> +
> + (*) void (*free)(struct fs_context *fc);
> +
> +     Called to clean up the filesystem-specific part of the filesystem context
> +     when the context is destroyed.  It should be aware that parts of the
> +     context may have been removed and NULL'd out by ->get_tree().
> +
> + (*) int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
> +
> +     Called when a filesystem context has been duplicated to get any refs or
> +     copy any non-referenced resources held in the filesystem-specific part of
> +     the filesystem context.  An error may be returned to indicate failure to
> +     do this.
> +
> +     [!] Note that even if this fails, put_fs_context() will be called
> +	 immediately thereafter, so ->dup() *must* make the
> +	 filesystem-specific part safe for ->free().
> +
> + (*) int (*parse_option)(struct fs_context *fc, char *p);
> +
> +     Called when an option is to be added to the filesystem context.  p points
> +     to the option string, likely in "key[=val]" format.  VFS-specific options
> +     will have been weeded out and fc->sb_flags updated in the context.
> +     Security options will also have been weeded out and fc->security updated.
> +
> +     If successful, 0 should be returned and a negative error code otherwise.
> +     If an ambiguous error (such as -EINVAL) is returned, sb_cfg_error() or
> +     sb_cfg_inval() should be used to provide a string that provides more
> +     information.
> +
> + (*) int (*monolithic_mount_data)(struct fs_context *fc, 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 ->parse_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
> +     generic_monolithic_mount_data().
> +
> + (*) int (*validate)(struct fs_context *fc);
> +
> +     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 fc->mount_type == FS_CONTEXT_FOR_REMOUNT, some of the options
> +     necessary for a new mount may not be set.
> +
> +     The return value is as for ->parse_option().
> +
> + (*) int (*get_tree)(struct fs_context *fc);
> +
> +     Called to get or create the mountable root and superblock, using the
> +     information stored in the filesystem context (remounts go
> +     via a different vector).  It may detach any resources it desires from the
> +     filesystem context and transfer them to the superblock it
> +     creates.
> +
> +     On success it should set fc->root to the mountable root.
> +
> +     In the case of an error, it should return a negative error code and
> +     consider invoking sb_cfg_inval() or sb_cfg_error().
> +
> +
> +=========================================
> +FILESYSTEM CONTEXT SECURITY
> +========================================
> +
> +The filesystem 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_fs_context_alloc(struct fs_context *fc,
> +				  struct super_block *src_sb);
> +
> +     Called to initialise fc->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 (FS_CONTEXT_FOR_REMOUNT) in
> +     which case it indicates the superblock to be remounted or in the case of a
> +     submount (FS_CONTEXT_FOR_SUBMOUNT) in which case it indicates the parent
> +     superblock.
> +
> + (*) int security_fs_context_dup(struct fs_context *fc,
> +				struct fs_context *src_mc);
> +
> +     Called to initialise fc->security (which is preset to NULL) and allocate
> +     any resources needed.  The original filesystem 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_fs_context_free(struct fs_context *fc);
> +
> +     Called to clean up anything attached to fc->security.  Note that the
> +     contents may have been transferred to a superblock and the pointer NULL'd
> +     out during mount.
> +
> + (*) int security_fs_context_parse_option(struct fs_context *fc, 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, more information can be returned with
> +     sb_cfg_inval() or sb_cfg_error().
> +
> + (*) int security_sb_get_tree(struct fs_context *fc);
> +
> +     Called during the mount procedure 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
> +     perhaps call invalf() or errorf() to indicate the problem.  It should not
> +     return -ENOMEM as this should be taken care of in advance.
> +
> +     [NOTE] Should I add a security_fs_context_validate() operation so that the
> +     LSM has the opportunity to allocate stuff and check the options as a
> +     whole?
> +
> +
> +=================================
> +VFS FILESYSTEM CONTEXT OPERATIONS
> +=================================
> +
> +There are four operations for creating a filesystem context and
> +one for destroying a context:
> +
> + (*) struct fs_context *__vfs_new_fs_context(struct file_system_type *fs_type,
> +					     struct super_block *src_sb;
> +					     unsigned int ms_flags);
> +
> +     Create a filesystem context given a filesystem type pointer.
> +     This allocates the filesystem context, sets the flags,
> +     initialises the security and calls fs_type->init_fs_context() to initialise
> +     the filesystem context.
> +
> +     src_sb can be NULL or it may indicate a superblock that is going to be
> +     remounted (FS_CONTEXT_FOR_REMOUNT) or a superblock that is the parent of a
> +     submount (FS_CONTEXT_FOR_SUBMOUNT).  This superblock is provided as a
> +     source of namespace information.
> +
> + (*) struct fs_context *vfs_sb_reconfig(struct vfsmount *mnt,
> +					unsigned int ms_flags);
> +
> +     Create a filesystem context from the same filesystem as an
> +     extant mount and initialise the mount parameters from the superblock
> +     underlying that mount.  This is for use by remount.
> +
> + (*) struct fs_context *vfs_new_fs_context(const char *fs_name);
> +
> +     Create a filesystem context given a filesystem name.  It is assumed that
> +     the mount flags will be passed in as text options or set directly later.
> +     This is intended to be called from sys_mount() or sys_fsopen().  This
> +     copies current's namespaces to the context.
> +
> + (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc);
> +
> +     Duplicate a filesystem 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_fs_context(struct fs_context *fc);
> +
> +     Destroy a filesystem context, releasing any resources it holds.  This
> +     calls the ->free() operation.  This is intended to be called by anyone
> +     who created a filesystem context.
> +
> +     [!] filesystem 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, fc->error_msg may have been set to point to a
> +useful string.  This string should not be freed.
> +
> + (*) int vfs_get_tree(struct fs_context *fc);
> +
> +     Get or create the mountable root and superblock, using the parameters in
> +     the filesystem context to select/configure the superblock.  This invokes
> +     the ->validate() op and then the ->get_tree() op.
> +
> +     [NOTE] ->validate() can probably be rolled into ->get_tree() and
> +     ->remount_fs_fc().
> +
> + (*) struct vfsmount *vfs_kern_mount_fc(struct fs_context *fc);
> +
> +     Create a mount given the parameters in the specified filesystem context.
> +
> + (*) struct vfsmount *vfs_submount_fc(const struct dentry *mountpoint,
> +				      struct fs_context *fc);
> +
> +     Create a mount given a filesystem context and set MS_SUBMOUNT on it.  A
> +     wrapper around vfs_kern_mount_fc().  This is intended to be called from
> +     filesystems that have automount points (NFS, AFS, ...).
> +
> + (*) int vfs_parse_mount_option(struct fs_context *fc, char *data);
> +
> +     Supply a single mount option to the filesystem 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 fs_context *fc, 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/include/linux/fs_context.h b/include/linux/fs_context.h
> new file mode 100644
> index 000000000000..429c40be2c9e
> --- /dev/null
> +++ b/include/linux/fs_context.h
> @@ -0,0 +1,72 @@
> +/* Filesystem superblock creation and reconfiguration context.
> + *
> + * 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.
> + */
> +
> +#ifndef _LINUX_FS_CONTEXT_H
> +#define _LINUX_FS_CONTEXT_H
> +
> +#include <linux/kernel.h>
> +#include <linux/errno.h>
> +
> +struct cred;
> +struct dentry;
> +struct file_operations;
> +struct file_system_type;
> +struct mnt_namespace;
> +struct net;
> +struct pid_namespace;
> +struct super_block;
> +struct user_namespace;
> +struct vfsmount;
> +
> +enum fs_context_purpose {
> +	FS_CONTEXT_FOR_NEW,	/* New superblock for direct mount */
> +	FS_CONTEXT_FOR_SUBMOUNT,	/* New superblock for automatic submount */
> +	FS_CONTEXT_FOR_REMOUNT,	/* Superblock reconfiguration for remount */
> +};
> +
> +/*
> + * Filesystem context as allocated and constructed by the ->init_fs_context()
> + * file_system_type operation.  The size of the object allocated is specified
> + * in struct file_system_type::fs_context_size and this must include sufficient
> + * space for the fs_context struct.
> + *
> + * Superblock creation fills in ->root whereas reconfiguration begins with this
> + * already set.
> + *
> + * See Documentation/filesystems/mounting.txt
> + */
> +struct fs_context {
> +	const struct fs_context_operations *ops;
> +	struct file_system_type	*fs_type;
> +	struct dentry		*root;		/* The root and superblock */
> +	struct user_namespace	*user_ns;	/* The user namespace for this mount */
> +	struct net		*net_ns;	/* The network namespace for this mount */
> +	const struct cred	*cred;		/* The mounter's credentials */
> +	char			*device;	/* The device name or mount target */
> +	char			*subtype;	/* The subtype to set on the superblock */
> +	void			*security;	/* The LSM context */
> +	unsigned int		sb_flags;	/* The superblock flags (MS_*) */
> +	bool			sloppy;		/* Unrecognised options are okay */
> +	bool			silent;
> +	bool			degraded;	/* True if the context can't be reused */
> +	enum fs_context_purpose	purpose : 8;
> +};
> +
> +struct fs_context_operations {
> +	void (*free)(struct fs_context *fc);
> +	int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
> +	int (*parse_option)(struct fs_context *fc, char *p);
> +	int (*monolithic_mount_data)(struct fs_context *fc, void *data);
> +	int (*validate)(struct fs_context *fc);
> +	int (*get_tree)(struct fs_context *fc);
> +};
> +
> +#endif /* _LINUX_FS_CONTEXT_H */
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-security-module" in
> the body of a message to [e-mail]
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>

David Howells June 14, 2017, 8:42 p.m. UTC | #3

Casey Schaufler <[e-mail]> wrote:

> Could you namespace the fields of this structure?
> e.g. fs_cred, fs_security

Linus objects to that practice.

David

Casey Schaufler June 14, 2017, 8:53 p.m. UTC | #4

On 6/14/2017 1:42 PM, David Howells wrote:
> Casey Schaufler <[e-mail]> wrote:
>
>> Could you namespace the fields of this structure?
>> e.g. fs_cred, fs_security
> Linus objects to that practice.

Sigh. Never mind. Thank you.

>
> David
>

David Howells June 14, 2017, 10:58 p.m. UTC | #5

Randy Dunlap <[e-mail]> wrote:

> > +which is invoked to set up the filesystem-specific parts of a filesystem
> > +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 (FS_CONTEXT_FOR_SUBMOUNT) or remount
> 
>                        ;

Actually, this should rather be something like:

    which is invoked to set up the filesystem-specific parts of a filesystem
    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 (FS_CONTEXT_FOR_SUBMOUNT) or remount
    (FS_CONTEXT_FOR_REMOUNT) purposes - otherwise it will be NULL.

I forgot to thoroughly update the docs, so here they are.

David
---
			      ===================
			      FILESYSTEM MOUNTING
			      ===================

CONTENTS

 (1) Overview.

 (2) The filesystem context.

 (3) The filesystem context operations.

 (4) Filesystem context security.

 (5) VFS filesystem context operations.


========
OVERVIEW
========

The creation of new mounts is now to be done in a multistep process:

 (1) Create a filesystem context.

 (2) Parse the options and attach them to the context.  Options may be passed
     individually from userspace.

 (3) Validate and pre-process the context.

 (4) Get or create a superblock and mountable root.

 (5) Perform the mount.

 (6) Return an error message attached to the context.

 (7) Destroy the context.

To support this, the file_system_type struct gains two new fields:

	unsigned short fs_context_size;

which indicates the total amount of space that should be allocated for context
data (see the Filesystem Context section), and:

	int (*init_fs_context)(struct fs_context *fc, struct super_block *src_sb);

which is invoked to set up the filesystem-specific parts of a filesystem
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 (FS_CONTEXT_FOR_SUBMOUNT) or remount
(FS_CONTEXT_FOR_REMOUNT) purposes - otherwise 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 field:

	int (*remount_fs_fc) (struct super_block *, struct fs_context *);

This shadows the ->remount_fs() operation and takes a prepared filesystem
context instead of the mount flags and data page.  It may modify the sb_flags
in the context for the caller to pick up.

[NOTE] remount_fs_fc is intended as a replacement for remount_fs.


======================
THE FILESYSTEM CONTEXT
======================

The creation and reconfiguration of a superblock is governed by a filesystem
context.  This is represented by the fs_context structure:

	struct fs_context {
		const struct fs_context_operations *ops;
		struct file_system_type *fs;
		struct dentry		*root;
		struct user_namespace	*user_ns;
		struct net		*net_ns;
		const struct cred	*cred;
		char			*device;
		char			*subtype;
		void			*security;
		unsigned int		sb_flags;
		bool			sloppy;
		bool			silent;
		bool			degraded;
		enum fs_context_purpose	purpose : 8;
	};

When the VFS creates this, it allocates ->fs_context_size bytes (as specified
by the file_system_type object) to hold both the fs_context struct and any
extra data required by the filesystem.  The fs_context struct is placed at the
beginning of this space.  Any extra space beyond that is for use by the
filesystem.  The filesystem should wrap the struct in its own, e.g.:

	struct nfs_fs_context {
		struct fs_context fc;
		...
	};

placing the fs_context struct first.  container_of() can then be used.  The
file_system_type would be initialised thus:

	struct file_system_type nfs = {
		...
		.fs_context_size	= sizeof(struct nfs_fs_context),
		.init_fs_context	= nfs_init_fs_context,
		...
	};

The fs_context fields are as follows:

 (*) const struct fs_context_operations *ops

     These are operations that can be done on a filesystem context (see
     below).  This must be set by the ->init_fs_context() file_system_type
     operation.

 (*) struct file_system_type *fs

     A pointer to the file_system_type of the filesystem that is being
     constructed or reconfigured.  This retains a reference on the type owner.

 (*) struct dentry *root

     A pointer to the root of the mountable tree (and indirectly, the
     superblock thereof).  This is filled in by the ->get_tree() op.

 (*) struct user_namespace *user_ns
 (*) struct net *net_ns

     There are a subset of the namespaces in use by the invoking process.  They
     retain references 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 reference 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 *subtype

     This is a string to be added to the type displayed in /proc/mounts to
     qualify it (used by FUSE).  This is available for the filesystem to set if
     desired.

 (*) void *security

     A place for the LSMs to hang their security data for the superblock.  The
     relevant security operations are described below.

 (*) unsigned int sb_flags

     This holds the SB_* flags to be set in super_block::s_flags.

 (*) 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 sb_flags & SB_SILENT.

 (*) bool degraded

     This is set if any preallocated resources in the context have been used
     up, thereby rendering it unreusable for the ->get_tree() op.

 (*) enum fs_context_purpose

     This indicates the purpose for which the context is intended.  The
     available values are:

	FS_CONTEXT_FOR_NEW	-- New mount
	FS_CONTEXT_FOR_SUBMOUNT	-- New automatic submount of extant mount
	FS_CONTEXT_FOR_REMOUNT	-- Change an existing mount

The mount context is created by calling vfs_new_fs_context(), vfs_sb_reconfig()
or vfs_dup_fs_context() and is destroyed with put_fs_context().  Note that the
structure is not refcounted.

VFS, security and filesystem mount options are set individually with
vfs_parse_mount_option().  Options provided by the old mount(2) system call as
a page of data can be parsed 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 FILESYSTEM CONTEXT OPERATIONS
=================================

The filesystem context points to a table of operations:

	struct fs_context_operations {
		void (*free)(struct fs_context *fc);
		int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
		int (*parse_option)(struct fs_context *fc, char *p);
		int (*monolithic_mount_data)(struct fs_context *fc, void *data);
		int (*validate)(struct fs_context *fc);
		int (*get_tree)(struct fs_context *fc);
	};

These operations are invoked by the various stages of the mount procedure to
manage the filesystem context.  They are as follows:

 (*) void (*free)(struct fs_context *fc);

     Called to clean up the filesystem-specific part of the filesystem context
     when the context is destroyed.  It should be aware that parts of the
     context may have been removed and NULL'd out by ->get_tree().

 (*) int (*dup)(struct fs_context *fc, struct fs_context *src_fc);

     Called when a filesystem context has been duplicated to get any refs or
     copy any non-referenced resources held in the filesystem-specific part of
     the filesystem context.  An error may be returned to indicate failure to
     do this.

     [!] Note that even if this fails, put_fs_context() will be called
	 immediately thereafter, so ->dup() *must* make the
	 filesystem-specific part safe for ->free().

 (*) int (*parse_option)(struct fs_context *fc, char *p);

     Called when an option is to be added to the filesystem context.  p points
     to the option string, likely in "key[=val]" format.  VFS-specific options
     will have been weeded out and fc->sb_flags updated in the context.
     Security options will also have been weeded out and fc->security updated.

     If successful, 0 should be returned and a negative error code otherwise.
     If an ambiguous error (such as -EINVAL) is returned, sb_cfg_error() or
     sb_cfg_inval() should be used to provide a string that provides more
     information.

 (*) int (*monolithic_mount_data)(struct fs_context *fc, 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 ->parse_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
     generic_monolithic_mount_data().

 (*) int (*validate)(struct fs_context *fc);

     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 fc->purpose == FS_CONTEXT_FOR_REMOUNT, some of the options
     necessary for a new mount may not be set.

     The return value is as for ->parse_option().

 (*) int (*get_tree)(struct fs_context *fc);

     Called to get or create the mountable root and superblock, using the
     information stored in the filesystem context (remounts go
     via a different vector).  It may detach any resources it desires from the
     filesystem context and transfer them to the superblock it
     creates.

     On success it should set fc->root to the mountable root.

     In the case of an error, it should return a negative error code and
     consider invoking sb_cfg_inval() or sb_cfg_error().


===========================
FILESYSTEM CONTEXT SECURITY
===========================

The filesystem context contains a security pointer 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_fs_context_alloc(struct fs_context *fc,
				   struct super_block *src_sb);

     Called to initialise fc->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 (FS_CONTEXT_FOR_REMOUNT) in
     which case it indicates the superblock to be remounted or in the case of a
     submount (FS_CONTEXT_FOR_SUBMOUNT) in which case it indicates the parent
     superblock.

 (*) int security_fs_context_dup(struct fs_context *fc,
				 struct fs_context *src_fc);

     Called to initialise fc->security (which is preset to NULL) and allocate
     any resources needed.  The original filesystem context is pointed to by
     src_fc and may be used for reference.  It should return 0 on success and a
     negative error code on failure.

 (*) void security_fs_context_free(struct fs_context *fc);

     Called to clean up anything attached to fc->security.  Note that the
     contents may have been transferred to a superblock and the pointer NULL'd
     out during mount.

 (*) int security_fs_context_parse_option(struct fs_context *fc, 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, more information can be returned with
     invalf() or errorf().

 (*) int security_sb_get_tree(struct fs_context *fc);

     Called during the mount procedure 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
     perhaps call invalf() or errorf() to indicate the problem.  It should not
     return -ENOMEM as this should be taken care of in advance.

     [NOTE] Should I add a security_fs_context_validate() operation so that the
     LSM has the opportunity to allocate stuff and check the options as a
     whole?

 (*) int security_sb_mountpoint(struct fs_context *fc, struct path *mountpoint)

     Called during the mount procedure to verify that the root dentry attached
     to the context is permitted to be attached to the specified mountpoint.
     It should return 0 on success and a negative error code on failure.


=================================
VFS FILESYSTEM CONTEXT OPERATIONS
=================================

There are four operations for creating a filesystem context and
one for destroying a context:

 (*) struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type,
					   struct super_block *src_sb;
					   unsigned int sb_flags);

     Create a filesystem context for a given filesystem type.  This allocates
     the filesystem context, sets the flags, initialises the security and calls
     fs_type->init_fs_context() to initialise the filesystem context.

     src_sb can be NULL or it may indicate a superblock that is going to be
     remounted (FS_CONTEXT_FOR_REMOUNT) or a superblock that is the parent of a
     submount (FS_CONTEXT_FOR_SUBMOUNT).  This superblock is provided as a
     source of namespace information.

 (*) struct fs_context *vfs_sb_reconfig(struct vfsmount *mnt,
					unsigned int sb_flags);

     Create a filesystem context from the same filesystem as an extant mount
     and initialise the mount parameters from the superblock underlying that
     mount.  This is for use by remount.

 (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc);

     Duplicate a filesystem 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_fs_context(struct fs_context *fc);

     Destroy a filesystem context, releasing any resources it holds.  This
     calls the ->free() operation.  This is intended to be called by anyone who
     created a filesystem context.

     [!] filesystem 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.

In the remaining operations, if an error occurs, a negative error code is
returned and, if not obvious, invalf() or errorf() may have been invoked to set
a supplementary error message.

 (*) int vfs_get_tree(struct fs_context *fc);

     Get or create the mountable root and superblock, using the parameters in
     the filesystem context to select/configure the superblock.  This invokes
     the ->validate() op and then the ->get_tree() op.

     [NOTE] ->validate() could perhaps be rolled into ->get_tree() and
     ->remount_fs_fc().

 (*) struct vfsmount *vfs_kern_mount_fc(struct fs_context *fc);

     Create a mount given the parameters in the specified filesystem context.

 (*) int vfs_parse_mount_option(struct fs_context *fc, char *data);

     Supply a single mount option to the filesystem 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 set 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 fs_context *fc, 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.

Randy Dunlap June 15, 2017, 1:53 a.m. UTC | #6

Thanks for the update.  I have 2 more things for you to consider.

a.  In multiple places, there is something like "return 0 when no error
and return a negative error code otherwise."

I would say "or return a negative error code otherwise."

b. (below)

> ===========================
> FILESYSTEM CONTEXT SECURITY
> ===========================
> 
> The filesystem context contains a security pointer 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_fs_context_alloc(struct fs_context *fc,
> 				   struct super_block *src_sb);
> 
>      Called to initialise fc->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 (FS_CONTEXT_FOR_REMOUNT) in
>      which case it indicates the superblock to be remounted or in the case of a
>      submount (FS_CONTEXT_FOR_SUBMOUNT) in which case it indicates the parent
>      superblock.
> 

-ETOOMANYCASES

Maybe:
	For a remount (FS_CONTEXT_FOR_REMOUNT), src_sb is non-NULL and indicates
	the superblock to be remounted.  For a submount (FS_CONTEXT_FOR_SUBMOUNT),
	src_sb is also non-NULL and represents the parent superblock.


cheers.

Theodore Ts'o June 17, 2017, 9:57 a.m. UTC | #7

On Wed, Jun 14, 2017 at 01:53:09PM -0700, Casey Schaufler wrote:
> On 6/14/2017 1:42 PM, David Howells wrote:
> > Casey Schaufler <[e-mail]> wrote:
> >
> >> Could you namespace the fields of this structure?
> >> e.g. fs_cred, fs_security
> > Linus objects to that practice.
> 
> Sigh. Never mind. Thank you.

I don't know that this is a hard and fast rule.  Struct bio uses a
"bi_" prefix (e.g., bi_error, bi_opf, bi_iter, etc.).

I find it's really helpful when I'm doing a "git grep" over the whole
tree; "git grep bi_flags" returns a much more specific and focused
results than "git grep flags".   :-)

						- Ted

David Howells June 17, 2017, 2:18 p.m. UTC | #8

Theodore Ts'o <[e-mail]> wrote:

> I don't know that this is a hard and fast rule.  Struct bio uses a
> "bi_" prefix (e.g., bi_error, bi_opf, bi_iter, etc.).

Linus told me to stop doing it.

David

Jeff Layton June 17, 2017, 2:56 p.m. UTC | #9

On Sat, 2017-06-17 at 15:18 +0100, David Howells wrote:
> Theodore Ts'o <[e-mail]> wrote:
> 
> > I don't know that this is a hard and fast rule.  Struct bio uses a
> > "bi_" prefix (e.g., bi_error, bi_opf, bi_iter, etc.).
> 
> Linus told me to stop doing it.
> 
> David


That's a pity... I tend to like little prefixes on fields too. Trying to
find all occurrences of a symbol called "flags" in cscope is a losing
exercise.

Do you have a reference to the discussion so I can understand the
rationale there?

Thanks,

Randy Dunlap June 17, 2017, 3:11 p.m. UTC | #10

On 06/17/2017 07:56 AM, Jeff Layton wrote:
> On Sat, 2017-06-17 at 15:18 +0100, David Howells wrote:
>> Theodore Ts'o <[e-mail]> wrote:
>>
>>> I don't know that this is a hard and fast rule.  Struct bio uses a
>>> "bi_" prefix (e.g., bi_error, bi_opf, bi_iter, etc.).
>>
>> Linus told me to stop doing it.
>>
>> David
> 
> 
> That's a pity... I tend to like little prefixes on fields too. Trying to
> find all occurrences of a symbol called "flags" in cscope is a losing
> exercise.
> 
> Do you have a reference to the discussion so I can understand the
> rationale there?

Ack. This doesn't seem helpful.

He also objected to drivers with file names that begin with the parent
directory name, but we still have hundreds of those (see clk/, extcon/,
gpio/, hid/, i2c/, leds/ [then I stopped looking]).

David Howells June 19, 2017, 7:47 a.m. UTC | #11

Jeff Layton <[e-mail]> wrote:

> Do you have a reference to the discussion so I can understand the
> rationale there?

I'm afraid not - it was around 15-20 years ago, I think.  I seem to remember
the rationale being something like "because it's a stupid idea".

David

Patch

diff --git a/Documentation/filesystems/mounting.txt b/Documentation/filesystems/mounting.txt
new file mode 100644
index 000000000000..315a5a4ff5cc
--- /dev/null
+++ b/Documentation/filesystems/mounting.txt
@@ -0,0 +1,436 @@ 
+			      ===================
+			      FILESYSTEM MOUNTING
+			      ===================
+
+CONTENTS
+
+ (1) Overview.
+
+ (2) The filesystem context.
+
+ (3) The filesystem context operations.
+
+ (4) Filesystem context security.
+
+ (5) VFS filesystem context operations.
+
+
+========
+OVERVIEW
+========
+
+The creation of new mounts is now to be done in a multistep process:
+
+ (1) Create a filesystem context.
+
+ (2) Parse the options and attach them to the context.  Options may be passed
+     individually from userspace.
+
+ (3) Validate and pre-process the context.
+
+ (4) Get or create a superblock and mountable root.
+
+ (5) Perform the mount.
+
+ (6) Return an error message attached to the context.
+
+ (7) Destroy the context.
+
+To support this, the file_system_type struct gains two new fields:
+
+	unsigned short fs_context_size;
+
+which indicates the total amount of space that should be allocated for context
+data (see the Filesystem Context section), and:
+
+	int (*init_fs_context)(struct fs_context *fc, struct super_block *src_sb);
+
+which is invoked to set up the filesystem-specific parts of a filesystem
+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 (FS_CONTEXT_FOR_SUBMOUNT) or remount
+(FS_CONTEXT_FOR_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_fc) (struct super_block *, struct fs_context *);
+
+This shadows the ->remount_fs() operation and takes a prepared filesystem
+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_fc is intended as a replacement for remount_fs.
+
+
+======================
+THE FILESYSTEM CONTEXT
+======================
+
+The creation and reconfiguration of a superblock is governed by a filesystem
+context.  This is represented by the fs_context structure:
+
+	struct fs_context {
+		const struct fs_context_operations *ops;
+		struct file_system_type *fs;
+		struct dentry		*root;
+		struct user_namespace	*user_ns;
+		struct net		*net_ns;
+		const struct cred	*cred;
+		char			*device;
+		void			*security;
+		unsigned int		sb_flags;
+		bool			sloppy;
+		bool			silent;
+		bool			degraded;
+		enum fs_context_purpose	purpose : 8;
+	};
+
+When the VFS creates this, it allocates ->fs_context_size bytes (as specified
+by the file_system_type object) to hold both the fs_context struct and any
+extra data required by the filesystem.  The fs_context struct is placed at the
+beginning of this space.  Any extra space beyond that is for use by the
+filesystem.  The filesystem should wrap the struct in its own, e.g.:
+
+	struct nfs_fs_context {
+		struct fs_context fc;
+		...
+	};
+
+placing the fs_context struct first.  container_of() can then be used.  The
+file_system_type would be initialised thus:
+
+	struct file_system_type nfs = {
+		...
+		.fs_context_size	= sizeof(struct nfs_fs_context),
+		.init_fs_context	= nfs_init_fs_context,
+		...
+	};
+
+The fs_context fields are as follows:
+
+ (*) const struct fs_context_operations *ops
+
+     These are operations that can be done on a filesystem context (see
+     below).  This must be set by the ->init_fs_context() file_system_type
+     operation.
+
+ (*) struct file_system_type *fs
+
+     A pointer to the file_system_type of the filesystem that is being
+     constructed or reconfigured.  This retains a ref on the type owner.
+
+ (*) struct dentry *root
+
+     A pointer to the root of the mountable tree (and indirectly, the
+     superblock thereof).  This is filled in by the ->get_tree() op.
+
+ (*) struct user_namespace *user_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.
+
+ (*) void *security
+
+     A place for the LSMs to hang their security data for the superblock.  The
+     relevant security operations are described below.
+
+ (*) unsigned int sb_flags
+
+     This holds the MS_* flags mount flags.
+
+ (*) 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.
+
+ (*) bool degraded
+
+     This is set if any preallocated resources in the context have been used
+     up, thereby rendering it unreusable for the ->get_tree() op.
+
+ (*) enum fs_context_purpose
+
+     This indicates the purpose for which the context is intended.  The
+     available values are:
+
+	FS_CONTEXT_FOR_NEW	-- New mount
+	FS_CONTEXT_FOR_SUBMOUNT	-- New automatic submount of extant mount
+	FS_CONTEXT_FOR_REMOUNT	-- Change an existing mount
+
+The mount context is created by calling vfs_new_fs_context(), vfs_sb_reconfig()
+or vfs_dup_fs_context() and is destroyed with put_fs_context().  Note that the
+structure is not refcounted.
+
+VFS, security and filesystem mount options are set individually with
+vfs_parse_mount_option().  Options provided by the old mount(2) system call as
+a page of data can be parsed 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 FILESYSTEM CONTEXT OPERATIONS
+=================================
+
+The filesystem context points to a table of operations:
+
+	struct fs_context_operations {
+		void (*free)(struct fs_context *fc);
+		int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
+		int (*parse_option)(struct fs_context *fc, char *p);
+		int (*monolithic_mount_data)(struct fs_context *fc, void *data);
+		int (*validate)(struct fs_context *fc);
+		int (*get_tree)(struct fs_context *fc);
+	};
+
+These operations are invoked by the various stages of the mount procedure to
+manage the filesystem context.  They are as follows:
+
+ (*) void (*free)(struct fs_context *fc);
+
+     Called to clean up the filesystem-specific part of the filesystem context
+     when the context is destroyed.  It should be aware that parts of the
+     context may have been removed and NULL'd out by ->get_tree().
+
+ (*) int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
+
+     Called when a filesystem context has been duplicated to get any refs or
+     copy any non-referenced resources held in the filesystem-specific part of
+     the filesystem context.  An error may be returned to indicate failure to
+     do this.
+
+     [!] Note that even if this fails, put_fs_context() will be called
+	 immediately thereafter, so ->dup() *must* make the
+	 filesystem-specific part safe for ->free().
+
+ (*) int (*parse_option)(struct fs_context *fc, char *p);
+
+     Called when an option is to be added to the filesystem context.  p points
+     to the option string, likely in "key[=val]" format.  VFS-specific options
+     will have been weeded out and fc->sb_flags updated in the context.
+     Security options will also have been weeded out and fc->security updated.
+
+     If successful, 0 should be returned and a negative error code otherwise.
+     If an ambiguous error (such as -EINVAL) is returned, sb_cfg_error() or
+     sb_cfg_inval() should be used to provide a string that provides more
+     information.
+
+ (*) int (*monolithic_mount_data)(struct fs_context *fc, 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 ->parse_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
+     generic_monolithic_mount_data().
+
+ (*) int (*validate)(struct fs_context *fc);
+
+     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 fc->mount_type == FS_CONTEXT_FOR_REMOUNT, some of the options
+     necessary for a new mount may not be set.
+
+     The return value is as for ->parse_option().
+
+ (*) int (*get_tree)(struct fs_context *fc);
+
+     Called to get or create the mountable root and superblock, using the
+     information stored in the filesystem context (remounts go
+     via a different vector).  It may detach any resources it desires from the
+     filesystem context and transfer them to the superblock it
+     creates.
+
+     On success it should set fc->root to the mountable root.
+
+     In the case of an error, it should return a negative error code and
+     consider invoking sb_cfg_inval() or sb_cfg_error().
+
+
+=========================================
+FILESYSTEM CONTEXT SECURITY
+========================================
+
+The filesystem 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_fs_context_alloc(struct fs_context *fc,
+				  struct super_block *src_sb);
+
+     Called to initialise fc->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 (FS_CONTEXT_FOR_REMOUNT) in
+     which case it indicates the superblock to be remounted or in the case of a
+     submount (FS_CONTEXT_FOR_SUBMOUNT) in which case it indicates the parent
+     superblock.
+
+ (*) int security_fs_context_dup(struct fs_context *fc,
+				struct fs_context *src_mc);
+
+     Called to initialise fc->security (which is preset to NULL) and allocate
+     any resources needed.  The original filesystem 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_fs_context_free(struct fs_context *fc);
+
+     Called to clean up anything attached to fc->security.  Note that the
+     contents may have been transferred to a superblock and the pointer NULL'd
+     out during mount.
+
+ (*) int security_fs_context_parse_option(struct fs_context *fc, 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, more information can be returned with
+     sb_cfg_inval() or sb_cfg_error().
+
+ (*) int security_sb_get_tree(struct fs_context *fc);
+
+     Called during the mount procedure 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
+     perhaps call invalf() or errorf() to indicate the problem.  It should not
+     return -ENOMEM as this should be taken care of in advance.
+
+     [NOTE] Should I add a security_fs_context_validate() operation so that the
+     LSM has the opportunity to allocate stuff and check the options as a
+     whole?
+
+
+=================================
+VFS FILESYSTEM CONTEXT OPERATIONS
+=================================
+
+There are four operations for creating a filesystem context and
+one for destroying a context:
+
+ (*) struct fs_context *__vfs_new_fs_context(struct file_system_type *fs_type,
+					     struct super_block *src_sb;
+					     unsigned int ms_flags);
+
+     Create a filesystem context given a filesystem type pointer.
+     This allocates the filesystem context, sets the flags,
+     initialises the security and calls fs_type->init_fs_context() to initialise
+     the filesystem context.
+
+     src_sb can be NULL or it may indicate a superblock that is going to be
+     remounted (FS_CONTEXT_FOR_REMOUNT) or a superblock that is the parent of a
+     submount (FS_CONTEXT_FOR_SUBMOUNT).  This superblock is provided as a
+     source of namespace information.
+
+ (*) struct fs_context *vfs_sb_reconfig(struct vfsmount *mnt,
+					unsigned int ms_flags);
+
+     Create a filesystem context from the same filesystem as an
+     extant mount and initialise the mount parameters from the superblock
+     underlying that mount.  This is for use by remount.
+
+ (*) struct fs_context *vfs_new_fs_context(const char *fs_name);
+
+     Create a filesystem context given a filesystem name.  It is assumed that
+     the mount flags will be passed in as text options or set directly later.
+     This is intended to be called from sys_mount() or sys_fsopen().  This
+     copies current's namespaces to the context.
+
+ (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc);
+
+     Duplicate a filesystem 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_fs_context(struct fs_context *fc);
+
+     Destroy a filesystem context, releasing any resources it holds.  This
+     calls the ->free() operation.  This is intended to be called by anyone
+     who created a filesystem context.
+
+     [!] filesystem 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, fc->error_msg may have been set to point to a
+useful string.  This string should not be freed.
+
+ (*) int vfs_get_tree(struct fs_context *fc);
+
+     Get or create the mountable root and superblock, using the parameters in
+     the filesystem context to select/configure the superblock.  This invokes
+     the ->validate() op and then the ->get_tree() op.
+
+     [NOTE] ->validate() can probably be rolled into ->get_tree() and
+     ->remount_fs_fc().
+
+ (*) struct vfsmount *vfs_kern_mount_fc(struct fs_context *fc);
+
+     Create a mount given the parameters in the specified filesystem context.
+
+ (*) struct vfsmount *vfs_submount_fc(const struct dentry *mountpoint,
+				      struct fs_context *fc);
+
+     Create a mount given a filesystem context and set MS_SUBMOUNT on it.  A
+     wrapper around vfs_kern_mount_fc().  This is intended to be called from
+     filesystems that have automount points (NFS, AFS, ...).
+
+ (*) int vfs_parse_mount_option(struct fs_context *fc, char *data);
+
+     Supply a single mount option to the filesystem 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 fs_context *fc, 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/include/linux/fs_context.h b/include/linux/fs_context.h
new file mode 100644
index 000000000000..429c40be2c9e
--- /dev/null
+++ b/include/linux/fs_context.h
@@ -0,0 +1,72 @@ 
+/* Filesystem superblock creation and reconfiguration context.
+ *
+ * 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.
+ */
+
+#ifndef _LINUX_FS_CONTEXT_H
+#define _LINUX_FS_CONTEXT_H
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+struct cred;
+struct dentry;
+struct file_operations;
+struct file_system_type;
+struct mnt_namespace;
+struct net;
+struct pid_namespace;
+struct super_block;
+struct user_namespace;
+struct vfsmount;
+
+enum fs_context_purpose {
+	FS_CONTEXT_FOR_NEW,	/* New superblock for direct mount */
+	FS_CONTEXT_FOR_SUBMOUNT,	/* New superblock for automatic submount */
+	FS_CONTEXT_FOR_REMOUNT,	/* Superblock reconfiguration for remount */
+};
+
+/*
+ * Filesystem context as allocated and constructed by the ->init_fs_context()
+ * file_system_type operation.  The size of the object allocated is specified
+ * in struct file_system_type::fs_context_size and this must include sufficient
+ * space for the fs_context struct.
+ *
+ * Superblock creation fills in ->root whereas reconfiguration begins with this
+ * already set.
+ *
+ * See Documentation/filesystems/mounting.txt
+ */
+struct fs_context {
+	const struct fs_context_operations *ops;
+	struct file_system_type	*fs_type;
+	struct dentry		*root;		/* The root and superblock */
+	struct user_namespace	*user_ns;	/* The user namespace for this mount */
+	struct net		*net_ns;	/* The network namespace for this mount */
+	const struct cred	*cred;		/* The mounter's credentials */
+	char			*device;	/* The device name or mount target */
+	char			*subtype;	/* The subtype to set on the superblock */
+	void			*security;	/* The LSM context */
+	unsigned int		sb_flags;	/* The superblock flags (MS_*) */
+	bool			sloppy;		/* Unrecognised options are okay */
+	bool			silent;
+	bool			degraded;	/* True if the context can't be reused */
+	enum fs_context_purpose	purpose : 8;
+};
+
+struct fs_context_operations {
+	void (*free)(struct fs_context *fc);
+	int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
+	int (*parse_option)(struct fs_context *fc, char *p);
+	int (*monolithic_mount_data)(struct fs_context *fc, void *data);
+	int (*validate)(struct fs_context *fc);
+	int (*get_tree)(struct fs_context *fc);
+};
+
+#endif /* _LINUX_FS_CONTEXT_H */