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 <dhowells@xxxxxxxxxx>
---
Documentation/filesystems/mounting.txt | 445 ++++++++++++++++++++++++++++++++
include/linux/fs_context.h | 76 +++++
2 files changed, 521 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..805135a66b64
--- /dev/null
+++ b/Documentation/filesystems/mounting.txt
@@ -0,0 +1,445 @@
+ ===================
+ 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 reconfiguration
+(FS_CONTEXT_FOR_RECONFIGURE) 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 (*reconfigure) (struct super_block *, struct fs_context *);
+
+This shadows the ->reconfigure() 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] reconfigure 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;
+ void *s_fs_info;
+ unsigned int sb_flags;
+ bool sloppy;
+ bool silent;
+ bool degraded;
+ bool drop_sb;
+ 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.
+
+ (*) void *s_fs_info
+
+ The proposed s_fs_info for a new superblock, set in the superblock by
+ sget_fc(). This can be used to distinguish superblocks.
+
+ (*) 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.
+
+ (*) bool drop_sb
+
+ This is set if a superblock reference needs to be deactivated when the
+ context is put.
+
+ (*) enum fs_context_purpose
+
+ This indicates the purpose for which the context is intended. The
+ available values are:
+
+ FS_CONTEXT_FOR_USER_MOUNT, -- New superblock for user-specified mount
+ FS_CONTEXT_FOR_KERNEL_MOUNT, -- New superblock for kernel-internal mount
+ FS_CONTEXT_FOR_SUBMOUNT -- New automatic submount of extant mount
+ FS_CONTEXT_FOR_RECONFIGURE -- 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_parse_monolithic().
+
+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_source)(struct fs_context *fc);
+ int (*parse_option)(struct fs_context *fc, char *opt);
+ int (*parse_monolithic)(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_source)(struct fs_context *fc);
+
+ Called when the source or device is specified for a filesystem context.
+ The string will have been stored in fc->source prior to calling. If
+ successful, 0 should be returned and a negative error code otherwise.
+
+ (*) 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.
+
+ (*) int (*parse_monolithic)(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_parse_monolithic().
+
+ (*) 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_RECONFIGURE, 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 (reconfiguration goes 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 and return 0. In
+ the case of an error, it should return a negative error code.
+
+
+===========================
+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 reconfiguration
+ (FS_CONTEXT_FOR_RECONFIGURE) in which case it indicates the superblock to
+ be reconfigured 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 arguments are as for the
+ ->parse_option() method. 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.
+
+ (*) 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. It
+ should return 0 or a negative error code.
+
+ [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
+ reconfigured (FS_CONTEXT_FOR_RECONFIGURE) 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_reconfigure(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 superblock parameter reconfiguration.
+
+ (*) 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.
+
+For the remaining operations, if an error occurs, a negative error code will be
+returned.
+
+ (*) 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
+ ->reconfigure().
+
+ (*) struct vfsmount *vfs_create_mount(struct fs_context *fc);
+
+ Create a mount given the parameters in the specified filesystem context.
+ Note that this does not attach the mount to anything.
+
+ (*) int vfs_set_fs_source(struct fs_context *fc, char *source);
+
+ Supply the source name or device name for the mount. This may cause the
+ filesystem to access the device.
+
+ (*) int vfs_parse_fs_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 SB_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_parse_monolithic(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
+ ->parse_monolithic() operation is NULL.
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
new file mode 100644
index 000000000000..732a11898242
--- /dev/null
+++ b/include/linux/fs_context.h
@@ -0,0 +1,76 @@
+/* Filesystem superblock creation and reconfiguration context.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@xxxxxxxxxx)
+ *
+ * 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_USER_MOUNT, /* New superblock for user-specified mount */
+ FS_CONTEXT_FOR_KERNEL_MOUNT, /* New superblock for kernel-internal mount */
+ FS_CONTEXT_FOR_SUBMOUNT, /* New superblock for automatic submount */
+ FS_CONTEXT_FOR_RECONFIGURE, /* Superblock reconfiguration (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 *source; /* The source name (eg. device) */
+ char *subtype; /* The subtype to set on the superblock */
+ void *security; /* The LSM context */
+ void *s_fs_info; /* Proposed s_fs_info */
+ unsigned int sb_flags; /* Proposed superblock flags (SB_*) */
+ bool sloppy; /* Unrecognised options are okay */
+ bool silent;
+ bool degraded; /* True if the context can't be reused */
+ bool drop_sb; /* T if need to drop an SB reference */
+ 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_source)(struct fs_context *fc);
+ int (*parse_option)(struct fs_context *fc, char *opt, size_t len);
+ int (*parse_monolithic)(struct fs_context *fc, void *data);
+ int (*validate)(struct fs_context *fc);
+ int (*get_tree)(struct fs_context *fc);
+};
+
+#endif /* _LINUX_FS_CONTEXT_H */
