// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/super.c * * Copyright (C) 1991, 1992 Linus Torvalds * * super.c contains code to handle: - mount structures * - super-block tables * - filesystem drivers list * - mount system call * - umount system call * - ustat system call * * GK 2/5/95 - Changed to support mounting the root fs via NFS * * Added kerneld support: Jacques Gelinas and Bjorn Ekwall * Added change_root: Werner Almesberger & Hans Lermen, Feb '96 * Added options to /proc/mounts: * Torbjörn Lindh ([email protected]), April 14, 1996. * Added devfs support: Richard Gooch <[email protected]>, 13-JAN-1998 * Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000 */ #include <linux/export.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/writeback.h> /* for the emergency remount stuff */ #include <linux/idr.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/rculist_bl.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <uapi/linux/mount.h> #include "internal.h" static int thaw_super_locked(struct super_block *sb, enum freeze_holder who); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = …; static inline void __super_lock(struct super_block *sb, bool excl) { … } static inline void super_unlock(struct super_block *sb, bool excl) { … } static inline void __super_lock_excl(struct super_block *sb) { … } static inline void super_unlock_excl(struct super_block *sb) { … } static inline void super_unlock_shared(struct super_block *sb) { … } static bool super_flags(const struct super_block *sb, unsigned int flags) { … } /** * super_lock - wait for superblock to become ready and lock it * @sb: superblock to wait for * @excl: whether exclusive access is required * * If the superblock has neither passed through vfs_get_tree() or * generic_shutdown_super() yet wait for it to happen. Either superblock * creation will succeed and SB_BORN is set by vfs_get_tree() or we're * woken and we'll see SB_DYING. * * The caller must have acquired a temporary reference on @sb->s_count. * * Return: The function returns true if SB_BORN was set and with * s_umount held. The function returns false if SB_DYING was * set and without s_umount held. */ static __must_check bool super_lock(struct super_block *sb, bool excl) { … } /* wait and try to acquire read-side of @sb->s_umount */ static inline bool super_lock_shared(struct super_block *sb) { … } /* wait and try to acquire write-side of @sb->s_umount */ static inline bool super_lock_excl(struct super_block *sb) { … } /* wake waiters */ #define SUPER_WAKE_FLAGS … static void super_wake(struct super_block *sb, unsigned int flag) { … } /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { … } static unsigned long super_cache_count(struct shrinker *shrink, struct shrink_control *sc) { … } static void destroy_super_work(struct work_struct *work) { … } static void destroy_super_rcu(struct rcu_head *head) { … } /* Free a superblock that has never been seen by anyone */ static void destroy_unused_super(struct super_block *s) { … } /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to * @flags: the mount flags * @user_ns: User namespace for the super_block * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { … } /* Superblock refcounting */ /* * Drop a superblock's refcount. The caller must hold sb_lock. */ static void __put_super(struct super_block *s) { … } /** * put_super - drop a temporary reference to superblock * @sb: superblock in question * * Drops a temporary reference, frees superblock if there's no * references left. */ void put_super(struct super_block *sb) { … } static void kill_super_notify(struct super_block *sb) { … } /** * deactivate_locked_super - drop an active reference to superblock * @s: superblock to deactivate * * Drops an active reference to superblock, converting it into a temporary * one if there is no other active references left. In that case we * tell fs driver to shut it down and drop the temporary reference we * had just acquired. * * Caller holds exclusive lock on superblock; that lock is released. */ void deactivate_locked_super(struct super_block *s) { … } EXPORT_SYMBOL(…); /** * deactivate_super - drop an active reference to superblock * @s: superblock to deactivate * * Variant of deactivate_locked_super(), except that superblock is *not* * locked by caller. If we are going to drop the final active reference, * lock will be acquired prior to that. */ void deactivate_super(struct super_block *s) { … } EXPORT_SYMBOL(…); /** * grab_super - acquire an active reference to a superblock * @sb: superblock to acquire * * Acquire a temporary reference on a superblock and try to trade it for * an active reference. This is used in sget{_fc}() to wait for a * superblock to either become SB_BORN or for it to pass through * sb->kill() and be marked as SB_DEAD. * * Return: This returns true if an active reference could be acquired, * false if not. */ static bool grab_super(struct super_block *sb) { … } /* * super_trylock_shared - try to grab ->s_umount shared * @sb: reference we are trying to grab * * Try to prevent fs shutdown. This is used in places where we * cannot take an active reference but we need to ensure that the * filesystem is not shut down while we are working on it. It returns * false if we cannot acquire s_umount or if we lose the race and * filesystem already got into shutdown, and returns true with the s_umount * lock held in read mode in case of success. On successful return, * the caller must drop the s_umount lock when done. * * Note that unlike get_super() et.al. this one does *not* bump ->s_count. * The reason why it's safe is that we are OK with doing trylock instead * of down_read(). There's a couple of places that are OK with that, but * it's very much not a general-purpose interface. */ bool super_trylock_shared(struct super_block *sb) { … } /** * retire_super - prevents superblock from being reused * @sb: superblock to retire * * The function marks superblock to be ignored in superblock test, which * prevents it from being reused for any new mounts. If the superblock has * a private bdi, it also unregisters it, but doesn't reduce the refcount * of the superblock to prevent potential races. The refcount is reduced * by generic_shutdown_super(). The function can not be called * concurrently with generic_shutdown_super(). It is safe to call the * function multiple times, subsequent calls have no effect. * * The marker will affect the re-use only for block-device-based * superblocks. Other superblocks will still get marked if this function * is used, but that will not affect their reusability. */ void retire_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill * * generic_shutdown_super() does all fs-independent work on superblock * shutdown. Typical ->kill_sb() should pick all fs-specific objects * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. * * Upon calling this function, the filesystem may no longer alter or * rearrange the set of dentries belonging to this super_block, nor may it * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); bool mount_capable(struct fs_context *fc) { … } /** * sget_fc - Find or create a superblock * @fc: Filesystem context. * @test: Comparison callback * @set: Setup callback * * Create a new superblock or find an existing one. * * The @test callback is used to find a matching existing superblock. * Whether or not the requested parameters in @fc are taken into account * is specific to the @test callback that is used. They may even be * completely ignored. * * If an extant superblock is matched, it will be returned unless: * * (1) the namespace the filesystem context @fc and the extant * superblock's namespace differ * * (2) the filesystem context @fc has requested that reusing an extant * superblock is not allowed * * In both cases EBUSY will be returned. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info and s_id will be * set and the @set callback will be invoked), the superblock will be * published and it will be returned in a partially constructed state * with SB_BORN and SB_ACTIVE as yet unset. * * Return: On success, an extant or newly created superblock is * returned. On failure an error pointer is returned. */ 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 *)) { … } EXPORT_SYMBOL(…); /** * sget - find or create a superblock * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback * @flags: mount flags * @data: argument to each of them */ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data) { … } EXPORT_SYMBOL(…); void drop_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); void drop_super_exclusive(struct super_block *sb) { … } EXPORT_SYMBOL(…); static void __iterate_supers(void (*f)(struct super_block *)) { … } /** * iterate_supers - call function for all active superblocks * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) { … } /** * iterate_supers_type - call function for superblocks of given type * @type: fs type * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { … } EXPORT_SYMBOL(…); struct super_block *user_get_super(dev_t dev, bool excl) { … } /** * reconfigure_super - asks filesystem to change superblock parameters * @fc: The superblock and configuration * * Alters the configuration parameters of a live superblock. */ int reconfigure_super(struct fs_context *fc) { … } static void do_emergency_remount_callback(struct super_block *sb) { … } static void do_emergency_remount(struct work_struct *work) { … } void emergency_remount(void) { … } static void do_thaw_all_callback(struct super_block *sb) { … } static void do_thaw_all(struct work_struct *work) { … } /** * emergency_thaw_all -- forcibly thaw every frozen filesystem * * Used for emergency unfreeze of all filesystems via SysRq */ void emergency_thaw_all(void) { … } static DEFINE_IDA(unnamed_dev_ida); /** * get_anon_bdev - Allocate a block device for filesystems which don't have one. * @p: Pointer to a dev_t. * * Filesystems which don't use real block devices can call this function * to allocate a virtual block device. * * Context: Any context. Frequently called while holding sb_lock. * Return: 0 on success, -EMFILE if there are no anonymous bdevs left * or -ENOMEM if memory allocation failed. */ int get_anon_bdev(dev_t *p) { … } EXPORT_SYMBOL(…); void free_anon_bdev(dev_t dev) { … } EXPORT_SYMBOL(…); int set_anon_super(struct super_block *s, void *data) { … } EXPORT_SYMBOL(…); void kill_anon_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); void kill_litter_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); int set_anon_super_fc(struct super_block *sb, struct fs_context *fc) { … } EXPORT_SYMBOL(…); static int test_keyed_super(struct super_block *sb, struct fs_context *fc) { … } static int test_single_super(struct super_block *s, struct fs_context *fc) { … } static int vfs_get_super(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { … } int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { … } EXPORT_SYMBOL(…); int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { … } EXPORT_SYMBOL(…); int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key) { … } EXPORT_SYMBOL(…); static int set_bdev_super(struct super_block *s, void *data) { … } static int super_s_dev_set(struct super_block *s, struct fs_context *fc) { … } static int super_s_dev_test(struct super_block *s, struct fs_context *fc) { … } /** * sget_dev - Find or create a superblock by device number * @fc: Filesystem context. * @dev: device number * * Find or create a superblock using the provided device number that * will be stored in fc->sget_key. * * If an extant superblock is matched, then that will be returned with * an elevated reference count that the caller must transfer or discard. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info, s_id, s_dev will * be set). The superblock will be published and it will be returned in * a partially constructed state with SB_BORN and SB_ACTIVE as yet * unset. * * Return: an existing or newly created superblock on success, an error * pointer on failure. */ struct super_block *sget_dev(struct fs_context *fc, dev_t dev) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_BLOCK /* * Lock the superblock that is holder of the bdev. Returns the superblock * pointer if we successfully locked the superblock and it is alive. Otherwise * we return NULL and just unlock bdev->bd_holder_lock. * * The function must be called with bdev->bd_holder_lock and releases it. */ static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl) __releases(&bdev->bd_holder_lock) { … } static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { … } static void fs_bdev_sync(struct block_device *bdev) { … } static struct super_block *get_bdev_super(struct block_device *bdev) { … } /** * fs_bdev_freeze - freeze owning filesystem of block device * @bdev: block device * * Freeze the filesystem that owns this block device if it is still * active. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ static int fs_bdev_freeze(struct block_device *bdev) { … } /** * fs_bdev_thaw - thaw owning filesystem of block device * @bdev: block device * * Thaw the filesystem that owns this block device. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the thaw was successful zero is returned. If the thaw * failed a negative error code is returned. If this function * returns zero it doesn't mean that the filesystem is unfrozen * as it may have been frozen multiple times (kernel may hold a * freeze or might be frozen from other block devices). */ static int fs_bdev_thaw(struct block_device *bdev) { … } const struct blk_holder_ops fs_holder_ops = …; EXPORT_SYMBOL_GPL(…); int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc) { … } EXPORT_SYMBOL_GPL(…); /** * get_tree_bdev - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock */ int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *, struct fs_context *)) { … } EXPORT_SYMBOL(…); static int test_bdev_super(struct super_block *s, void *data) { … } struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)) { … } EXPORT_SYMBOL(…); void kill_block_super(struct super_block *sb) { … } EXPORT_SYMBOL(…); #endif struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { … } EXPORT_SYMBOL(…); int reconfigure_single(struct super_block *s, int flags, void *data) { … } static int compare_single(struct super_block *s, void *p) { … } struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { … } EXPORT_SYMBOL(…); /** * vfs_get_tree - Get the mountable root * @fc: The superblock configuration context. * * The filesystem is invoked to get or create a superblock which can then later * be used for mounting. The filesystem places a pointer to the root to be * used for mounting in @fc->root. */ int vfs_get_tree(struct fs_context *fc) { … } EXPORT_SYMBOL(…); /* * Setup private BDI for given superblock. It gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) { … } EXPORT_SYMBOL(…); /* * Setup private BDI for given superblock. I gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi(struct super_block *sb) { … } EXPORT_SYMBOL(…); /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait * @level: type of writers we wait for (normal vs page fault) * * This function waits until there are no writers of given type to given file * system. */ static void sb_wait_write(struct super_block *sb, int level) { … } /* * We are going to return to userspace and forget about these locks, the * ownership goes to the caller of thaw_super() which does unlock(). */ static void lockdep_sb_freeze_release(struct super_block *sb) { … } /* * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb). */ static void lockdep_sb_freeze_acquire(struct super_block *sb) { … } static void sb_freeze_unlock(struct super_block *sb, int level) { … } static int wait_for_partially_frozen(struct super_block *sb) { … } #define FREEZE_HOLDERS … #define FREEZE_FLAGS … static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) { … } static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) { … } static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) { … } /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock * @who: context that wants to freeze * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs may return * -EBUSY. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed. * * The @who argument distinguishes between the kernel and userspace trying to * freeze the filesystem. Although there cannot be multiple kernel freezes or * multiple userspace freezes in effect at any given time, the kernel and * userspace can both hold a filesystem frozen. The filesystem remains frozen * until there are no kernel or userspace freezes in effect. * * A filesystem may hold multiple devices and thus a filesystems may be * frozen through the block layer via multiple block devices. In this * case the request is marked as being allowed to nest by passing * FREEZE_MAY_NEST. The filesystem remains frozen until all block * devices are unfrozen. If multiple freezes are attempted without * FREEZE_MAY_NEST -EBUSY will be returned. * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. * * SB_FREEZE_WRITE: The file system is in the process of being frozen. New * writes should be blocked, though page faults are still allowed. We wait for * all writes to complete and then proceed to the next stage. * * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked * but internal fs threads can still modify the filesystem (although they * should not dirty new pages or inodes), writeback can run etc. After waiting * for all running page faults we sync the filesystem which will clean all * dirty pages and inodes (no new dirty pages or inodes can be created when * sync is running). * * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs * modification are blocked (e.g. XFS preallocation truncation on inode * reclaim). This is usually implemented by blocking new transactions for * filesystems that have them and need this additional guard. After all * internal writers are finished we call ->freeze_fs() to finish filesystem * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ int freeze_super(struct super_block *sb, enum freeze_holder who) { … } EXPORT_SYMBOL(…); /* * Undoes the effect of a freeze_super_locked call. If the filesystem is * frozen both by userspace and the kernel, a thaw call from either source * removes that state without releasing the other state or unlocking the * filesystem. */ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) { … } /** * thaw_super -- unlock filesystem * @sb: the super to thaw * @who: context that wants to freeze * * Unlocks the filesystem and marks it writeable again after freeze_super() * if there are no remaining freezes on the filesystem. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed * * A filesystem may hold multiple devices and thus a filesystems may * have been frozen through the block layer via multiple block devices. * The filesystem remains frozen until all block devices are unfrozen. */ int thaw_super(struct super_block *sb, enum freeze_holder who) { … } EXPORT_SYMBOL(…); /* * Create workqueue for deferred direct IO completions. We allocate the * workqueue when it's first needed. This avoids creating workqueue for * filesystems that don't need it and also allows us to create the workqueue * late enough so the we can include s_id in the name of the workqueue. */ int sb_init_dio_done_wq(struct super_block *sb) { … } EXPORT_SYMBOL_GPL(…);
Codebase Browser
linux