1
0
Fork 0
alistair23-linux/include/linux/fs_context.h

209 lines
6.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* Filesystem superblock creation and reconfiguration context.
*
* Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef _LINUX_FS_CONTEXT_H
#define _LINUX_FS_CONTEXT_H
#include <linux/kernel.h>
#include <linux/refcount.h>
#include <linux/errno.h>
#include <linux/security.h>
vfs: syscall: Add fsopen() to prepare for superblock creation Provide an fsopen() system call that starts the process of preparing to create a superblock that will then be mountable, using an fd as a context handle. fsopen() is given the name of the filesystem that will be used: int mfd = fsopen(const char *fsname, unsigned int flags); where flags can be 0 or FSOPEN_CLOEXEC. For example: sfd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD); fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0); fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0); fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); fsinfo(sfd, NULL, ...); // query new superblock attributes mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); sfd = fsopen("afs", -1); fsconfig(fd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); mfd = fsmount(sfd, 0, MS_NODEV); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); If an error is reported at any step, an error message may be available to be read() back (ENODATA will be reported if there isn't an error available) in the form: "e <subsys>:<problem>" "e SELinux:Mount on mountpoint not permitted" Once fsmount() has been called, further fsconfig() calls will incur EBUSY, even if the fsmount() fails. read() is still possible to retrieve error information. The fsopen() syscall creates a mount context and hangs it of the fd that it returns. Netlink is not used because it is optional and would make the core VFS dependent on the networking layer and also potentially add network namespace issues. Note that, for the moment, the caller must have SYS_CAP_ADMIN to use fsopen(). Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:33:31 -06:00
#include <linux/mutex.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;
struct path;
enum fs_context_purpose {
FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */
FS_CONTEXT_FOR_SUBMOUNT, /* New superblock for automatic submount */
FS_CONTEXT_FOR_RECONFIGURE, /* Superblock reconfiguration (remount) */
};
vfs: syscall: Add fsopen() to prepare for superblock creation Provide an fsopen() system call that starts the process of preparing to create a superblock that will then be mountable, using an fd as a context handle. fsopen() is given the name of the filesystem that will be used: int mfd = fsopen(const char *fsname, unsigned int flags); where flags can be 0 or FSOPEN_CLOEXEC. For example: sfd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD); fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0); fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0); fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); fsinfo(sfd, NULL, ...); // query new superblock attributes mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); sfd = fsopen("afs", -1); fsconfig(fd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); mfd = fsmount(sfd, 0, MS_NODEV); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); If an error is reported at any step, an error message may be available to be read() back (ENODATA will be reported if there isn't an error available) in the form: "e <subsys>:<problem>" "e SELinux:Mount on mountpoint not permitted" Once fsmount() has been called, further fsconfig() calls will incur EBUSY, even if the fsmount() fails. read() is still possible to retrieve error information. The fsopen() syscall creates a mount context and hangs it of the fd that it returns. Netlink is not used because it is optional and would make the core VFS dependent on the networking layer and also potentially add network namespace issues. Note that, for the moment, the caller must have SYS_CAP_ADMIN to use fsopen(). Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:33:31 -06:00
/*
* Userspace usage phase for fsopen/fspick.
*/
enum fs_context_phase {
FS_CONTEXT_CREATE_PARAMS, /* Loading params for sb creation */
FS_CONTEXT_CREATING, /* A superblock is being created */
FS_CONTEXT_AWAITING_MOUNT, /* Superblock created, awaiting fsmount() */
FS_CONTEXT_AWAITING_RECONF, /* Awaiting initialisation for reconfiguration */
FS_CONTEXT_RECONF_PARAMS, /* Loading params for reconfiguration */
FS_CONTEXT_RECONFIGURING, /* Reconfiguring the superblock */
FS_CONTEXT_FAILED, /* Failed to correctly transition a context */
};
vfs: Add configuration parser helpers Because the new API passes in key,value parameters, match_token() cannot be used with it. Instead, provide three new helpers to aid with parsing: (1) fs_parse(). This takes a parameter and a simple static description of all the parameters and maps the key name to an ID. It returns 1 on a match, 0 on no match if unknowns should be ignored and some other negative error code on a parse error. The parameter description includes a list of key names to IDs, desired parameter types and a list of enumeration name -> ID mappings. [!] Note that for the moment I've required that the key->ID mapping array is expected to be sorted and unterminated. The size of the array is noted in the fsconfig_parser struct. This allows me to use bsearch(), but I'm not sure any performance gain is worth the hassle of requiring people to keep the array sorted. The parameter type array is sized according to the number of parameter IDs and is indexed directly. The optional enum mapping array is an unterminated, unsorted list and the size goes into the fsconfig_parser struct. The function can do some additional things: (a) If it's not ambiguous and no value is given, the prefix "no" on a key name is permitted to indicate that the parameter should be considered negatory. (b) If the desired type is a single simple integer, it will perform an appropriate conversion and store the result in a union in the parse result. (c) If the desired type is an enumeration, {key ID, name} will be looked up in the enumeration list and the matching value will be stored in the parse result union. (d) Optionally generate an error if the key is unrecognised. This is called something like: enum rdt_param { Opt_cdp, Opt_cdpl2, Opt_mba_mpbs, nr__rdt_params }; const struct fs_parameter_spec rdt_param_specs[nr__rdt_params] = { [Opt_cdp] = { fs_param_is_bool }, [Opt_cdpl2] = { fs_param_is_bool }, [Opt_mba_mpbs] = { fs_param_is_bool }, }; const const char *const rdt_param_keys[nr__rdt_params] = { [Opt_cdp] = "cdp", [Opt_cdpl2] = "cdpl2", [Opt_mba_mpbs] = "mba_mbps", }; const struct fs_parameter_description rdt_parser = { .name = "rdt", .nr_params = nr__rdt_params, .keys = rdt_param_keys, .specs = rdt_param_specs, .no_source = true, }; int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result parse; struct rdt_fs_context *ctx = rdt_fc2context(fc); int ret; ret = fs_parse(fc, &rdt_parser, param, &parse); if (ret < 0) return ret; switch (parse.key) { case Opt_cdp: ctx->enable_cdpl3 = true; return 0; case Opt_cdpl2: ctx->enable_cdpl2 = true; return 0; case Opt_mba_mpbs: ctx->enable_mba_mbps = true; return 0; } return -EINVAL; } (2) fs_lookup_param(). This takes a { dirfd, path, LOOKUP_EMPTY? } or string value and performs an appropriate path lookup to convert it into a path object, which it will then return. If the desired type was a blockdev, the type of the looked up inode will be checked to make sure it is one. This can be used like: enum foo_param { Opt_source, nr__foo_params }; const struct fs_parameter_spec foo_param_specs[nr__foo_params] = { [Opt_source] = { fs_param_is_blockdev }, }; const char *char foo_param_keys[nr__foo_params] = { [Opt_source] = "source", }; const struct constant_table foo_param_alt_keys[] = { { "device", Opt_source }, }; const struct fs_parameter_description foo_parser = { .name = "foo", .nr_params = nr__foo_params, .nr_alt_keys = ARRAY_SIZE(foo_param_alt_keys), .keys = foo_param_keys, .alt_keys = foo_param_alt_keys, .specs = foo_param_specs, }; int foo_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result parse; struct foo_fs_context *ctx = foo_fc2context(fc); int ret; ret = fs_parse(fc, &foo_parser, param, &parse); if (ret < 0) return ret; switch (parse.key) { case Opt_source: return fs_lookup_param(fc, &foo_parser, param, &parse, &ctx->source); default: return -EINVAL; } } (3) lookup_constant(). This takes a table of named constants and looks up the given name within it. The table is expected to be sorted such that bsearch() be used upon it. Possibly I should require the table be terminated and just use a for-loop to scan it instead of using bsearch() to reduce hassle. Tables look something like: static const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, { "no", false }, { "true", true }, { "yes", true }, }; and a lookup is done with something like: b = lookup_constant(bool_names, param->string, -1); Additionally, optional validation routines for the parameter description are provided that can be enabled at compile time. A later patch will invoke these when a filesystem is registered. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:07:24 -06:00
/*
* Type of parameter value.
*/
enum fs_value_type {
fs_value_is_undefined,
fs_value_is_flag, /* Value not given a value */
fs_value_is_string, /* Value is a string */
fs_value_is_blob, /* Value is a binary blob */
fs_value_is_filename, /* Value is a filename* + dirfd */
fs_value_is_filename_empty, /* Value is a filename* + dirfd + AT_EMPTY_PATH */
fs_value_is_file, /* Value is a file* */
};
/*
* Configuration parameter.
*/
struct fs_parameter {
const char *key; /* Parameter name */
enum fs_value_type type:8; /* The type of value here */
union {
char *string;
void *blob;
struct filename *name;
struct file *file;
};
size_t size;
int dirfd;
};
/*
* Filesystem context for holding the parameters used in the creation or
* reconfiguration of a superblock.
*
* 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;
vfs: syscall: Add fsopen() to prepare for superblock creation Provide an fsopen() system call that starts the process of preparing to create a superblock that will then be mountable, using an fd as a context handle. fsopen() is given the name of the filesystem that will be used: int mfd = fsopen(const char *fsname, unsigned int flags); where flags can be 0 or FSOPEN_CLOEXEC. For example: sfd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD); fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0); fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0); fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); fsinfo(sfd, NULL, ...); // query new superblock attributes mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); sfd = fsopen("afs", -1); fsconfig(fd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); mfd = fsmount(sfd, 0, MS_NODEV); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); If an error is reported at any step, an error message may be available to be read() back (ENODATA will be reported if there isn't an error available) in the form: "e <subsys>:<problem>" "e SELinux:Mount on mountpoint not permitted" Once fsmount() has been called, further fsconfig() calls will incur EBUSY, even if the fsmount() fails. read() is still possible to retrieve error information. The fsopen() syscall creates a mount context and hangs it of the fd that it returns. Netlink is not used because it is optional and would make the core VFS dependent on the networking layer and also potentially add network namespace issues. Note that, for the moment, the caller must have SYS_CAP_ADMIN to use fsopen(). Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:33:31 -06:00
struct mutex uapi_mutex; /* Userspace access mutex */
struct file_system_type *fs_type;
void *fs_private; /* The filesystem's context */
struct dentry *root; /* The root and superblock */
struct user_namespace *user_ns; /* The user namespace for this mount */
struct net *net_ns; /* The network namespace for this mount */
const struct cred *cred; /* The mounter's credentials */
struct fc_log *log; /* Logging buffer */
const char *source; /* The source name (eg. dev path) */
const char *subtype; /* The subtype to set on the superblock */
void *security; /* Linux S&M options */
void *s_fs_info; /* Proposed s_fs_info */
unsigned int sb_flags; /* Proposed superblock flags (SB_*) */
unsigned int sb_flags_mask; /* Superblock flags that were changed */
unsigned int lsm_flags; /* Information flags from the fs to the LSM */
enum fs_context_purpose purpose:8;
vfs: syscall: Add fsopen() to prepare for superblock creation Provide an fsopen() system call that starts the process of preparing to create a superblock that will then be mountable, using an fd as a context handle. fsopen() is given the name of the filesystem that will be used: int mfd = fsopen(const char *fsname, unsigned int flags); where flags can be 0 or FSOPEN_CLOEXEC. For example: sfd = fsopen("ext4", FSOPEN_CLOEXEC); fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD); fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0); fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0); fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0); fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); fsinfo(sfd, NULL, ...); // query new superblock attributes mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); sfd = fsopen("afs", -1); fsconfig(fd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell", 0); fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); mfd = fsmount(sfd, 0, MS_NODEV); move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH); If an error is reported at any step, an error message may be available to be read() back (ENODATA will be reported if there isn't an error available) in the form: "e <subsys>:<problem>" "e SELinux:Mount on mountpoint not permitted" Once fsmount() has been called, further fsconfig() calls will incur EBUSY, even if the fsmount() fails. read() is still possible to retrieve error information. The fsopen() syscall creates a mount context and hangs it of the fd that it returns. Netlink is not used because it is optional and would make the core VFS dependent on the networking layer and also potentially add network namespace issues. Note that, for the moment, the caller must have SYS_CAP_ADMIN to use fsopen(). Signed-off-by: David Howells <dhowells@redhat.com> cc: linux-api@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:33:31 -06:00
enum fs_context_phase phase:8; /* The phase the context is in */
bool need_free:1; /* Need to call ops->free() */
bool global:1; /* Goes into &init_user_ns */
};
struct fs_context_operations {
void (*free)(struct fs_context *fc);
int (*dup)(struct fs_context *fc, struct fs_context *src_fc);
vfs: Implement a filesystem superblock creation/configuration context [AV - unfuck kern_mount_data(); we want non-NULL ->mnt_ns on long-living mounts] [AV - reordering fs/namespace.c is badly overdue, but let's keep it separate from that series] [AV - drop simple_pin_fs() change] [AV - clean vfs_kern_mount() failure exits up] Implement a filesystem context concept to be used during superblock creation for mount and superblock reconfiguration for remount. The mounting procedure then becomes: (1) Allocate new fs_context context. (2) Configure the context. (3) Create superblock. (4) Query the superblock. (5) Create a mount for the superblock. (6) Destroy the context. Rather than calling fs_type->mount(), an fs_context struct is created and fs_type->init_fs_context() is called to set it up. Pointers exist for the filesystem and LSM to hang their private data off. A set of operations has to be set by ->init_fs_context() to provide freeing, duplication, option parsing, binary data parsing, validation, mounting and superblock filling. Legacy filesystems are supported by the provision of a set of legacy fs_context operations that build up a list of mount options and then invoke fs_type->mount() from within the fs_context ->get_tree() operation. This allows all filesystems to be accessed using fs_context. It should be noted that, whilst this patch adds a lot of lines of code, there is quite a bit of duplication with existing code that can be eliminated should all filesystems be converted over. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:07:25 -06:00
int (*parse_param)(struct fs_context *fc, struct fs_parameter *param);
int (*parse_monolithic)(struct fs_context *fc, void *data);
int (*get_tree)(struct fs_context *fc);
int (*reconfigure)(struct fs_context *fc);
};
/*
* fs_context manipulation functions.
*/
extern struct fs_context *fs_context_for_mount(struct file_system_type *fs_type,
unsigned int sb_flags);
extern struct fs_context *fs_context_for_reconfigure(struct dentry *dentry,
unsigned int sb_flags,
unsigned int sb_flags_mask);
extern struct fs_context *fs_context_for_submount(struct file_system_type *fs_type,
struct dentry *reference);
extern struct fs_context *vfs_dup_fs_context(struct fs_context *fc);
vfs: Implement a filesystem superblock creation/configuration context [AV - unfuck kern_mount_data(); we want non-NULL ->mnt_ns on long-living mounts] [AV - reordering fs/namespace.c is badly overdue, but let's keep it separate from that series] [AV - drop simple_pin_fs() change] [AV - clean vfs_kern_mount() failure exits up] Implement a filesystem context concept to be used during superblock creation for mount and superblock reconfiguration for remount. The mounting procedure then becomes: (1) Allocate new fs_context context. (2) Configure the context. (3) Create superblock. (4) Query the superblock. (5) Create a mount for the superblock. (6) Destroy the context. Rather than calling fs_type->mount(), an fs_context struct is created and fs_type->init_fs_context() is called to set it up. Pointers exist for the filesystem and LSM to hang their private data off. A set of operations has to be set by ->init_fs_context() to provide freeing, duplication, option parsing, binary data parsing, validation, mounting and superblock filling. Legacy filesystems are supported by the provision of a set of legacy fs_context operations that build up a list of mount options and then invoke fs_type->mount() from within the fs_context ->get_tree() operation. This allows all filesystems to be accessed using fs_context. It should be noted that, whilst this patch adds a lot of lines of code, there is quite a bit of duplication with existing code that can be eliminated should all filesystems be converted over. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 17:07:25 -06:00
extern int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param);
extern int vfs_parse_fs_string(struct fs_context *fc, const char *key,
const char *value, size_t v_size);
extern int generic_parse_monolithic(struct fs_context *fc, void *data);
extern int vfs_get_tree(struct fs_context *fc);
extern void put_fs_context(struct fs_context *fc);
/*
* sget() wrapper to be called from the ->get_tree() op.
*/
enum vfs_get_super_keying {
vfs_get_single_super, /* Only one such superblock may exist */
vfs_get_keyed_super, /* Superblocks with different s_fs_info keys may exist */
vfs_get_independent_super, /* Multiple independent superblocks may exist */
};
extern int vfs_get_super(struct fs_context *fc,
enum vfs_get_super_keying keying,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc));
extern const struct file_operations fscontext_fops;
/*
* Mount error, warning and informational message logging. This structure is
* shareable between a mount and a subordinate mount.
*/
struct fc_log {
refcount_t usage;
u8 head; /* Insertion index in buffer[] */
u8 tail; /* Removal index in buffer[] */
u8 need_free; /* Mask of kfree'able items in buffer[] */
struct module *owner; /* Owner module for strings that don't then need freeing */
char *buffer[8];
};
extern __attribute__((format(printf, 2, 3)))
void logfc(struct fs_context *fc, const char *fmt, ...);
/**
* infof - Store supplementary informational message
* @fc: The context in which to log the informational message
* @fmt: The format string
*
* Store the supplementary informational message for the process if the process
* has enabled the facility.
*/
#define infof(fc, fmt, ...) ({ logfc(fc, "i "fmt, ## __VA_ARGS__); })
/**
* warnf - Store supplementary warning message
* @fc: The context in which to log the error message
* @fmt: The format string
*
* Store the supplementary warning message for the process if the process has
* enabled the facility.
*/
#define warnf(fc, fmt, ...) ({ logfc(fc, "w "fmt, ## __VA_ARGS__); })
/**
* errorf - Store supplementary error message
* @fc: The context in which to log the error message
* @fmt: The format string
*
* Store the supplementary error message for the process if the process has
* enabled the facility.
*/
#define errorf(fc, fmt, ...) ({ logfc(fc, "e "fmt, ## __VA_ARGS__); })
/**
* invalf - Store supplementary invalid argument error message
* @fc: The context in which to log the error message
* @fmt: The format string
*
* Store the supplementary error message for the process if the process has
* enabled the facility and return -EINVAL.
*/
#define invalf(fc, fmt, ...) ({ errorf(fc, fmt, ## __VA_ARGS__); -EINVAL; })
#endif /* _LINUX_FS_CONTEXT_H */