linux-stable/include/linux/fs_context.h
Linus Torvalds 511fb5bafe v6.6-vfs.super
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZOXpbgAKCRCRxhvAZXjc
 oi8PAQCtXelGZHmTcmevsO8p4Qz7hFpkonZ/TnxKf+RdnlNgPgD+NWi+LoRBpaAj
 xk4z8SqJaTTP4WXrG5JZ6o7EQkUL8gE=
 =2e9I
 -----END PGP SIGNATURE-----

Merge tag 'v6.6-vfs.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull superblock updates from Christian Brauner:
 "This contains the super rework that was ready for this cycle. The
  first part changes the order of how we open block devices and allocate
  superblocks, contains various cleanups, simplifications, and a new
  mechanism to wait on superblock state changes.

  This unblocks work to ultimately limit the number of writers to a
  block device. Jan has already scheduled follow-up work that will be
  ready for v6.7 and allows us to restrict the number of writers to a
  given block device. That series builds on this work right here.

  The second part contains filesystem freezing updates.

  Overview:

  The generic superblock changes are rougly organized as follows
  (ignoring additional minor cleanups):

   (1) Removal of the bd_super member from struct block_device.

       This was a very odd back pointer to struct super_block with
       unclear rules. For all relevant places we have other means to get
       the same information so just get rid of this.

   (2) Simplify rules for superblock cleanup.

       Roughly, everything that is allocated during fs_context
       initialization and that's stored in fs_context->s_fs_info needs
       to be cleaned up by the fs_context->free() implementation before
       the superblock allocation function has been called successfully.

       After sget_fc() returned fs_context->s_fs_info has been
       transferred to sb->s_fs_info at which point sb->kill_sb() if
       fully responsible for cleanup. Adhering to these rules means that
       cleanup of sb->s_fs_info in fill_super() is to be avoided as it's
       brittle and inconsistent.

       Cleanup shouldn't be duplicated between sb->put_super() as
       sb->put_super() is only called if sb->s_root has been set aka
       when the filesystem has been successfully born (SB_BORN). That
       complexity should be avoided.

       This also means that block devices are to be closed in
       sb->kill_sb() instead of sb->put_super(). More details in the
       lower section.

   (3) Make it possible to lookup or create a superblock before opening
       block devices

       There's a subtle dependency on (2) as some filesystems did rely
       on fill_super() to be called in order to correctly clean up
       sb->s_fs_info. All these filesystems have been fixed.

   (4) Switch most filesystem to follow the same logic as the generic
       mount code now does as outlined in (3).

   (5) Use the superblock as the holder of the block device. We can now
       easily go back from block device to owning superblock.

   (6) Export and extend the generic fs_holder_ops and use them as
       holder ops everywhere and remove the filesystem specific holder
       ops.

   (7) Call from the block layer up into the filesystem layer when the
       block device is removed, allowing to shut down the filesystem
       without risk of deadlocks.

   (8) Get rid of get_super().

       We can now easily go back from the block device to owning
       superblock and can call up from the block layer into the
       filesystem layer when the device is removed. So no need to wade
       through all registered superblock to find the owning superblock
       anymore"

Link: https://lore.kernel.org/lkml/20230824-prall-intakt-95dbffdee4a0@brauner/

* tag 'v6.6-vfs.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (47 commits)
  super: use higher-level helper for {freeze,thaw}
  super: wait until we passed kill super
  super: wait for nascent superblocks
  super: make locking naming consistent
  super: use locking helpers
  fs: simplify invalidate_inodes
  fs: remove get_super
  block: call into the file system for ioctl BLKFLSBUF
  block: call into the file system for bdev_mark_dead
  block: consolidate __invalidate_device and fsync_bdev
  block: drop the "busy inodes on changed media" log message
  dasd: also call __invalidate_device when setting the device offline
  amiflop: don't call fsync_bdev in FDFMTBEG
  floppy: call disk_force_media_change when changing the format
  block: simplify the disk_force_media_change interface
  nbd: call blk_mark_disk_dead in nbd_clear_sock_ioctl
  xfs use fs_holder_ops for the log and RT devices
  xfs: drop s_umount over opening the log and RT devices
  ext4: use fs_holder_ops for the log device
  ext4: drop s_umount over opening the log device
  ...
2023-08-28 11:04:18 -07:00

235 lines
8.1 KiB
C

/* 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>
#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) */
};
/*
* 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 */
};
/*
* 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_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;
};
struct p_log {
const char *prefix;
struct fc_log *log;
};
/*
* 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/mount_api.rst
*/
struct fs_context {
const struct fs_context_operations *ops;
struct mutex uapi_mutex; /* Userspace access mutex */
struct file_system_type *fs_type;
void *fs_private; /* The filesystem's context */
void *sget_key;
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 p_log log; /* Logging buffer */
const char *source; /* The source name (eg. dev path) */
void *security; /* LSM 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 s_iflags; /* OR'd with sb->s_iflags */
enum fs_context_purpose purpose:8;
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 */
bool oldapi:1; /* Coming from mount(2) */
bool exclusive:1; /* create new superblock, reject existing one */
};
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);
extern int vfs_parse_fs_param_source(struct fs_context *fc,
struct fs_parameter *param);
extern void fc_drop_locked(struct fs_context *fc);
int reconfigure_single(struct super_block *s,
int flags, void *data);
extern int get_tree_nodev(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc));
extern int get_tree_single(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc));
extern int get_tree_keyed(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc),
void *key);
int setup_bdev_super(struct super_block *sb, int sb_flags,
struct fs_context *fc);
extern int get_tree_bdev(struct fs_context *fc,
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, 4, 5)))
void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...);
#define __logfc(fc, l, fmt, ...) logfc((fc)->log.log, NULL, \
l, fmt, ## __VA_ARGS__)
#define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \
l, fmt, ## __VA_ARGS__)
/**
* 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__)
#define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__)
#define infofc(p, fmt, ...) __plog((&(fc)->log), '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__)
#define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__)
#define warnfc(fc, fmt, ...) __plog((&(fc)->log), '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__)
#define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__)
#define errorfc(fc, fmt, ...) __plog((&(fc)->log), '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)
#define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL)
#define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL)
#endif /* _LINUX_FS_CONTEXT_H */