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

Pull vfs mount infrastructure updates from Al Viro:
 "The rest of core infrastructure; no new syscalls in that pile, but the
  old parts are switched to new infrastructure. At that point
  conversions of individual filesystems can happen independently; some
  are done here (afs, cgroup, procfs, etc.), there's also a large series
  outside of that pile dealing with NFS (quite a bit of option-parsing
  stuff is getting used there - it's one of the most convoluted
  filesystems in terms of mount-related logics), but NFS bits are the
  next cycle fodder.

  It got seriously simplified since the last cycle; documentation is
  probably the weakest bit at the moment - I considered dropping the
  commit introducing Documentation/filesystems/mount_api.txt (cutting
  the size increase by quarter ;-), but decided that it would be better
  to fix it up after -rc1 instead.

  That pile allows to do followup work in independent branches, which
  should make life much easier for the next cycle. fs/super.c size
  increase is unpleasant; there's a followup series that allows to
  shrink it considerably, but I decided to leave that until the next
  cycle"

* 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (41 commits)
  afs: Use fs_context to pass parameters over automount
  afs: Add fs_context support
  vfs: Add some logging to the core users of the fs_context log
  vfs: Implement logging through fs_context
  vfs: Provide documentation for new mount API
  vfs: Remove kern_mount_data()
  hugetlbfs: Convert to fs_context
  cpuset: Use fs_context
  kernfs, sysfs, cgroup, intel_rdt: Support fs_context
  cgroup: store a reference to cgroup_ns into cgroup_fs_context
  cgroup1_get_tree(): separate "get cgroup_root to use" into a separate helper
  cgroup_do_mount(): massage calling conventions
  cgroup: stash cgroup_root reference into cgroup_fs_context
  cgroup2: switch to option-by-option parsing
  cgroup1: switch to option-by-option parsing
  cgroup: take options parsing into ->parse_monolithic()
  cgroup: fold cgroup1_mount() into cgroup1_get_tree()
  cgroup: start switching to fs_context
  ipc: Convert mqueue fs to fs_context
  proc: Add fs_context support to procfs
  ...
This commit is contained in:
Linus Torvalds
2019-03-12 14:08:19 -07:00
45 changed files with 4377 additions and 1352 deletions

View File

@@ -18,6 +18,7 @@
#define ERESTART_RESTARTBLOCK 516 /* restart by calling sys_restart_syscall */
#define EPROBE_DEFER 517 /* Driver requests probe retry */
#define EOPENSTALE 518 /* open found a stale dentry */
#define ENOPARAM 519 /* Parameter not supported */
/* Defined for the NFSv3 protocol */
#define EBADHANDLE 521 /* Illegal NFS file handle */

View File

@@ -64,6 +64,8 @@ struct workqueue_struct;
struct iov_iter;
struct fscrypt_info;
struct fscrypt_operations;
struct fs_context;
struct fs_parameter_description;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -1349,6 +1351,7 @@ extern int send_sigurg(struct fown_struct *fown);
/* These sb flags are internal to the kernel */
#define SB_SUBMOUNT (1<<26)
#define SB_FORCE (1<<27)
#define SB_NOSEC (1<<28)
#define SB_BORN (1<<29)
#define SB_ACTIVE (1<<30)
@@ -1459,7 +1462,7 @@ struct super_block {
* Filesystem subtype. If non-empty the filesystem type field
* in /proc/mounts will be "type.subtype"
*/
char *s_subtype;
const char *s_subtype;
const struct dentry_operations *s_d_op; /* default d_op for dentries */
@@ -2170,6 +2173,8 @@ struct file_system_type {
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_description *parameters;
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
@@ -2225,8 +2230,12 @@ void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
int set_anon_super_fc(struct super_block *s, struct fs_context *fc);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
struct super_block *sget_fc(struct fs_context *fc,
int (*test)(struct super_block *, struct fs_context *),
int (*set)(struct super_block *, struct fs_context *));
struct super_block *sget_userns(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
@@ -2269,8 +2278,7 @@ mount_pseudo(struct file_system_type *fs_type, char *name,
extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
extern struct vfsmount *kern_mount(struct file_system_type *);
extern void kern_unmount(struct vfsmount *mnt);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);

188
include/linux/fs_context.h Normal file
View File

@@ -0,0 +1,188 @@
/* Filesystem superblock creation and reconfiguration context.
*
* Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#ifndef _LINUX_FS_CONTEXT_H
#define _LINUX_FS_CONTEXT_H
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/security.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) */
};
/*
* 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;
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 */
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;
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);
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);
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;
#ifdef CONFIG_PRINTK
extern __attribute__((format(printf, 2, 3)))
void logfc(struct fs_context *fc, const char *fmt, ...);
#else
static inline __attribute__((format(printf, 2, 3)))
void logfc(struct fs_context *fc, const char *fmt, ...)
{
}
#endif
/**
* infof - Store supplementary informational message
* @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 */

151
include/linux/fs_parser.h Normal file
View File

@@ -0,0 +1,151 @@
/* Filesystem parameter description and parser
*
* Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#ifndef _LINUX_FS_PARSER_H
#define _LINUX_FS_PARSER_H
#include <linux/fs_context.h>
struct path;
struct constant_table {
const char *name;
int value;
};
/*
* The type of parameter expected.
*/
enum fs_parameter_type {
__fs_param_wasnt_defined,
fs_param_is_flag,
fs_param_is_bool,
fs_param_is_u32,
fs_param_is_u32_octal,
fs_param_is_u32_hex,
fs_param_is_s32,
fs_param_is_u64,
fs_param_is_enum,
fs_param_is_string,
fs_param_is_blob,
fs_param_is_blockdev,
fs_param_is_path,
fs_param_is_fd,
nr__fs_parameter_type,
};
/*
* Specification of the type of value a parameter wants.
*
* Note that the fsparam_flag(), fsparam_string(), fsparam_u32(), ... macros
* should be used to generate elements of this type.
*/
struct fs_parameter_spec {
const char *name;
u8 opt; /* Option number (returned by fs_parse()) */
enum fs_parameter_type type:8; /* The desired parameter type */
unsigned short flags;
#define fs_param_v_optional 0x0001 /* The value is optional */
#define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */
#define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */
#define fs_param_deprecated 0x0008 /* The param is deprecated */
};
struct fs_parameter_enum {
u8 opt; /* Option number (as fs_parameter_spec::opt) */
char name[14];
u8 value;
};
struct fs_parameter_description {
const char name[16]; /* Name for logging purposes */
const struct fs_parameter_spec *specs; /* List of param specifications */
const struct fs_parameter_enum *enums; /* Enum values */
};
/*
* Result of parse.
*/
struct fs_parse_result {
bool negated; /* T if param was "noxxx" */
bool has_value; /* T if value supplied to param */
union {
bool boolean; /* For spec_bool */
int int_32; /* For spec_s32/spec_enum */
unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */
u64 uint_64; /* For spec_u64 */
};
};
extern int fs_parse(struct fs_context *fc,
const struct fs_parameter_description *desc,
struct fs_parameter *value,
struct fs_parse_result *result);
extern int fs_lookup_param(struct fs_context *fc,
struct fs_parameter *param,
bool want_bdev,
struct path *_path);
extern int __lookup_constant(const struct constant_table tbl[], size_t tbl_size,
const char *name, int not_found);
#define lookup_constant(t, n, nf) __lookup_constant(t, ARRAY_SIZE(t), (n), (nf))
#ifdef CONFIG_VALIDATE_FS_PARSER
extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size,
int low, int high, int special);
extern bool fs_validate_description(const struct fs_parameter_description *desc);
#else
static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size,
int low, int high, int special)
{ return true; }
static inline bool fs_validate_description(const struct fs_parameter_description *desc)
{ return true; }
#endif
/*
* Parameter type, name, index and flags element constructors. Use as:
*
* fsparam_xxxx("foo", Opt_foo)
*
* If existing helpers are not enough, direct use of __fsparam() would
* work, but any such case is probably a sign that new helper is needed.
* Helpers will remain stable; low-level implementation may change.
*/
#define __fsparam(TYPE, NAME, OPT, FLAGS) \
{ \
.name = NAME, \
.opt = OPT, \
.type = TYPE, \
.flags = FLAGS \
}
#define fsparam_flag(NAME, OPT) __fsparam(fs_param_is_flag, NAME, OPT, 0)
#define fsparam_flag_no(NAME, OPT) \
__fsparam(fs_param_is_flag, NAME, OPT, \
fs_param_neg_with_no)
#define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0)
#define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0)
#define fsparam_u32oct(NAME, OPT) \
__fsparam(fs_param_is_u32_octal, NAME, OPT, 0)
#define fsparam_u32hex(NAME, OPT) \
__fsparam(fs_param_is_u32_hex, NAME, OPT, 0)
#define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0)
#define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0)
#define fsparam_enum(NAME, OPT) __fsparam(fs_param_is_enum, NAME, OPT, 0)
#define fsparam_string(NAME, OPT) \
__fsparam(fs_param_is_string, NAME, OPT, 0)
#define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0)
#define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0)
#define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0)
#define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0)
#endif /* _LINUX_FS_PARSER_H */

View File

@@ -26,7 +26,9 @@ struct vm_area_struct;
struct super_block;
struct file_system_type;
struct poll_table_struct;
struct fs_context;
struct kernfs_fs_context;
struct kernfs_open_node;
struct kernfs_iattrs;
@@ -168,7 +170,6 @@ struct kernfs_node {
* kernfs_node parameter.
*/
struct kernfs_syscall_ops {
int (*remount_fs)(struct kernfs_root *root, int *flags, char *data);
int (*show_options)(struct seq_file *sf, struct kernfs_root *root);
int (*mkdir)(struct kernfs_node *parent, const char *name,
@@ -272,6 +273,18 @@ struct kernfs_ops {
#endif
};
/*
* The kernfs superblock creation/mount parameter context.
*/
struct kernfs_fs_context {
struct kernfs_root *root; /* Root of the hierarchy being mounted */
void *ns_tag; /* Namespace tag of the mount (or NULL) */
unsigned long magic; /* File system specific magic number */
/* The following are set/used by kernfs_mount() */
bool new_sb_created; /* Set to T if we allocated a new sb */
};
#ifdef CONFIG_KERNFS
static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
@@ -359,11 +372,9 @@ __poll_t kernfs_generic_poll(struct kernfs_open_file *of,
void kernfs_notify(struct kernfs_node *kn);
const void *kernfs_super_ns(struct super_block *sb);
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
struct kernfs_root *root, unsigned long magic,
bool *new_sb_created, const void *ns);
int kernfs_get_tree(struct fs_context *fc);
void kernfs_free_fs_context(struct fs_context *fc);
void kernfs_kill_sb(struct super_block *sb);
struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns);
void kernfs_init(void);
@@ -465,11 +476,10 @@ static inline void kernfs_notify(struct kernfs_node *kn) { }
static inline const void *kernfs_super_ns(struct super_block *sb)
{ return NULL; }
static inline struct dentry *
kernfs_mount_ns(struct file_system_type *fs_type, int flags,
struct kernfs_root *root, unsigned long magic,
bool *new_sb_created, const void *ns)
{ return ERR_PTR(-ENOSYS); }
static inline int kernfs_get_tree(struct fs_context *fc)
{ return -ENOSYS; }
static inline void kernfs_free_fs_context(struct fs_context *fc) { }
static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -552,13 +562,4 @@ static inline int kernfs_rename(struct kernfs_node *kn,
return kernfs_rename_ns(kn, new_parent, new_name, NULL);
}
static inline struct dentry *
kernfs_mount(struct file_system_type *fs_type, int flags,
struct kernfs_root *root, unsigned long magic,
bool *new_sb_created)
{
return kernfs_mount_ns(fs_type, flags, root,
magic, new_sb_created, NULL);
}
#endif /* __LINUX_KERNFS_H */

View File

@@ -76,6 +76,22 @@
* changes on the process such as clearing out non-inheritable signal
* state. This is called immediately after commit_creds().
*
* Security hooks for mount using fs_context.
* [See also Documentation/filesystems/mounting.txt]
*
* @fs_context_dup:
* Allocate and attach a security structure to sc->security. This pointer
* is initialised to NULL by the caller.
* @fc indicates the new filesystem context.
* @src_fc indicates the original filesystem context.
* @fs_context_parse_param:
* Userspace provided a parameter to configure a superblock. The LSM may
* reject it with an error and may use it for itself, in which case it
* should return 0; otherwise it should return -ENOPARAM to pass it on to
* the filesystem.
* @fc indicates the filesystem context.
* @param The parameter
*
* Security hooks for filesystem operations.
*
* @sb_alloc_security:
@@ -1460,6 +1476,9 @@ union security_list_options {
void (*bprm_committing_creds)(struct linux_binprm *bprm);
void (*bprm_committed_creds)(struct linux_binprm *bprm);
int (*fs_context_dup)(struct fs_context *fc, struct fs_context *src_sc);
int (*fs_context_parse_param)(struct fs_context *fc, struct fs_parameter *param);
int (*sb_alloc_security)(struct super_block *sb);
void (*sb_free_security)(struct super_block *sb);
void (*sb_free_mnt_opts)(void *mnt_opts);
@@ -1800,6 +1819,8 @@ struct security_hook_heads {
struct hlist_head bprm_check_security;
struct hlist_head bprm_committing_creds;
struct hlist_head bprm_committed_creds;
struct hlist_head fs_context_dup;
struct hlist_head fs_context_parse_param;
struct hlist_head sb_alloc_security;
struct hlist_head sb_free_security;
struct hlist_head sb_free_mnt_opts;

View File

@@ -21,6 +21,7 @@ struct super_block;
struct vfsmount;
struct dentry;
struct mnt_namespace;
struct fs_context;
#define MNT_NOSUID 0x01
#define MNT_NODEV 0x02
@@ -88,6 +89,8 @@ struct path;
extern struct vfsmount *clone_private_mount(const struct path *path);
struct file_system_type;
extern struct vfsmount *fc_mount(struct fs_context *fc);
extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
int flags, const char *name,
void *data);

View File

@@ -53,6 +53,9 @@ struct msg_msg;
struct xattr;
struct xfrm_sec_ctx;
struct mm_struct;
struct fs_context;
struct fs_parameter;
enum fs_value_type;
/* Default (no) options for the capable function */
#define CAP_OPT_NONE 0x0
@@ -61,7 +64,7 @@ struct mm_struct;
/* If capable is being called by a setid function */
#define CAP_OPT_INSETID BIT(2)
/* LSM Agnostic defines for sb_set_mnt_opts */
/* LSM Agnostic defines for fs_context::lsm_flags */
#define SECURITY_LSM_NATIVE_LABELS 1
struct ctl_table;
@@ -223,6 +226,8 @@ int security_bprm_set_creds(struct linux_binprm *bprm);
int security_bprm_check(struct linux_binprm *bprm);
void security_bprm_committing_creds(struct linux_binprm *bprm);
void security_bprm_committed_creds(struct linux_binprm *bprm);
int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc);
int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param);
int security_sb_alloc(struct super_block *sb);
void security_sb_free(struct super_block *sb);
void security_free_mnt_opts(void **mnt_opts);
@@ -519,6 +524,17 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm)
{
}
static inline int security_fs_context_dup(struct fs_context *fc,
struct fs_context *src_fc)
{
return 0;
}
static inline int security_fs_context_parse_param(struct fs_context *fc,
struct fs_parameter *param)
{
return -ENOPARAM;
}
static inline int security_sb_alloc(struct super_block *sb)
{
return 0;