// 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 (torbjorn.lindh@gopta.se), April 14, 1996. *  Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 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/memcontrol.h>#include <linux/rhashtable.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 <linux/fserror.h>#include <uapi/linux/mount.h>#include "internal.h" static int thaw_super_locked(struct super_block *sb, enum freeze_holder who,			     const void *freeze_owner); static LIST_HEAD(super_blocks);static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = {	"sb_writers",	"sb_pagefaults",	"sb_internal",}; static inline void __super_lock(struct super_block *sb, bool excl){	if (excl)		down_write(&sb->s_umount);	else		down_read(&sb->s_umount);} static inline void super_unlock(struct super_block *sb, bool excl){	if (excl)		up_write(&sb->s_umount);	else		up_read(&sb->s_umount);} static inline void __super_lock_excl(struct super_block *sb){	__super_lock(sb, true);} static inline void super_unlock_excl(struct super_block *sb){	super_unlock(sb, true);} static inline void super_unlock_shared(struct super_block *sb){	super_unlock(sb, false);} static bool super_flags(const struct super_block *sb, unsigned int flags){	/*	 * Pairs with smp_store_release() in super_wake() and ensures	 * that we see @flags after we're woken.	 */	return smp_load_acquire(&sb->s_flags) & 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_passive. * * 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){	lockdep_assert_not_held(&sb->s_umount); 	/* wait until the superblock is ready or dying */	wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING)); 	/* Don't pointlessly acquire s_umount. */	if (super_flags(sb, SB_DYING))		return false; 	__super_lock(sb, excl); 	/*	 * Has gone through generic_shutdown_super() in the meantime.	 * @sb->s_root is NULL and @sb->s_active is 0. No one needs to	 * grab a reference to this. Tell them so.	 */	if (sb->s_flags & SB_DYING) {		super_unlock(sb, excl);		return false;	} 	WARN_ON_ONCE(!(sb->s_flags & SB_BORN));	return true;} /* wait and try to acquire read-side of @sb->s_umount */static inline bool super_lock_shared(struct super_block *sb){	return super_lock(sb, false);} /* wait and try to acquire write-side of @sb->s_umount */static inline bool super_lock_excl(struct super_block *sb){	return super_lock(sb, true);} /* wake waiters */#define SUPER_WAKE_FLAGS (SB_BORN | SB_DYING | SB_DEAD)static void super_wake(struct super_block *sb, unsigned int flag){	WARN_ON_ONCE((flag & ~SUPER_WAKE_FLAGS));	WARN_ON_ONCE(hweight32(flag & SUPER_WAKE_FLAGS) > 1); 	/*	 * Pairs with smp_load_acquire() in super_lock() to make sure	 * all initializations in the superblock are seen by the user	 * seeing SB_BORN sent.	 */	smp_store_release(&sb->s_flags, sb->s_flags | flag);	/*	 * Pairs with the barrier in prepare_to_wait_event() to make sure	 * ___wait_var_event() either sees SB_BORN set or	 * waitqueue_active() check in wake_up_var() sees the waiter.	 */	smp_mb();	wake_up_var(&sb->s_flags);} /* * The s_op->nr_cached_objects hooks (used for example by btrfs and xfs) * operate on filesystem-global state and ignore sc->memcg. Driving them * from per-memcg shrink_slab_memcg() invocations only burns CPU walking * per-cpu counters and queueing duplicate work: the actual reclaim happens on * the global path (kswapd or root direct reclaim) regardless. Restrict them * to that path. */static inline bool super_fs_objects_eligible(struct shrink_control *sc){	return !sc->memcg || mem_cgroup_is_root(sc->memcg);} /* * 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){	struct super_block *sb;	long	fs_objects = 0;	long	total_objects;	long	freed = 0;	long	dentries;	long	inodes; 	sb = shrink->private_data; 	/*	 * Deadlock avoidance.  We may hold various FS locks, and we don't want	 * to recurse into the FS that called us in clear_inode() and friends..	 */	if (!(sc->gfp_mask & __GFP_FS))		return SHRINK_STOP; 	if (!super_trylock_shared(sb))		return SHRINK_STOP; 	if (sb->s_op->nr_cached_objects && super_fs_objects_eligible(sc))		fs_objects = sb->s_op->nr_cached_objects(sb, sc); 	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);	total_objects = dentries + inodes + fs_objects;	if (!total_objects)		total_objects = 1; 	/* proportion the scan between the caches */	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects); 	/*	 * prune the dcache first as the icache is pinned by it, then	 * prune the icache, followed by the filesystem specific caches	 *	 * Ensure that we always scan at least one object - memcg kmem	 * accounting uses this to fully empty the caches.	 */	sc->nr_to_scan = dentries + 1;	freed = prune_dcache_sb(sb, sc);	sc->nr_to_scan = inodes + 1;	freed += prune_icache_sb(sb, sc); 	if (fs_objects) {		sc->nr_to_scan = fs_objects + 1;		freed += sb->s_op->free_cached_objects(sb, sc);	} 	super_unlock_shared(sb);	return freed;} static unsigned long super_cache_count(struct shrinker *shrink,				       struct shrink_control *sc){	struct super_block *sb;	long	total_objects = 0; 	sb = shrink->private_data; 	/*	 * We don't call super_trylock_shared() here as it is a scalability	 * bottleneck, so we're exposed to partial setup state. The shrinker	 * rwsem does not protect filesystem operations backing	 * list_lru_shrink_count() or s_op->nr_cached_objects(). Counts can	 * change between super_cache_count and super_cache_scan, so we really	 * don't need locks here.	 *	 * However, if we are currently mounting the superblock, the underlying	 * filesystem might be in a state of partial construction and hence it	 * is dangerous to access it.  super_trylock_shared() uses a SB_BORN check	 * to avoid this situation, so do the same here. The memory barrier is	 * matched with the one in mount_fs() as we don't hold locks here.	 */	if (!(sb->s_flags & SB_BORN))		return 0;	smp_rmb(); 	if (sb->s_op && sb->s_op->nr_cached_objects &&	    super_fs_objects_eligible(sc))		total_objects = sb->s_op->nr_cached_objects(sb, sc); 	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc); 	if (!total_objects)		return SHRINK_EMPTY; 	total_objects = vfs_pressure_ratio(total_objects);	return total_objects;} static struct super_dev *super_dev_alloc(dev_t dev, struct super_block *sb); static void destroy_super_work(struct work_struct *work){	struct super_block *s = container_of(work, struct super_block,							destroy_work);	fsnotify_sb_free(s);	security_sb_free(s);	put_user_ns(s->s_user_ns);	/* Only an unregistered entry is still owned by the superblock. */	kfree(s->s_super_dev);	kfree(s->s_subtype);	for (int i = 0; i < SB_FREEZE_LEVELS; i++)		percpu_free_rwsem(&s->s_writers.rw_sem[i]);	kfree(s);} static void destroy_super_rcu(struct rcu_head *head){	struct super_block *s = container_of(head, struct super_block, rcu);	INIT_WORK(&s->destroy_work, destroy_super_work);	schedule_work(&s->destroy_work);} /* Free a superblock that has never been seen by anyone */static void destroy_unused_super(struct super_block *s){	if (!s)		return;	super_unlock_excl(s);	list_lru_destroy(&s->s_dentry_lru);	list_lru_destroy(&s->s_inode_lru);	shrinker_free(s->s_shrink);	/* no delays needed */	destroy_super_work(&s->destroy_work);} /** *	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){	struct super_block *s = kzalloc_obj(struct super_block);	static const struct super_operations default_op;	int i; 	if (!s)		return NULL; 	s->s_user_ns = get_user_ns(user_ns);	init_rwsem(&s->s_umount);	lockdep_set_class(&s->s_umount, &type->s_umount_key);	/*	 * sget_fc() can have s_umount recursion.	 *	 * When it cannot find a suitable sb, it allocates a new	 * one (this one), and tries again to find a suitable old	 * one.	 *	 * In case that succeeds, it will acquire the s_umount	 * lock of the old one. Since these are clearly distrinct	 * locks, and this object isn't exposed yet, there's no	 * risk of deadlocks.	 *	 * Annotate this by putting this lock in a different	 * subclass.	 */	down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); 	if (security_sb_alloc(s))		goto fail; 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {		if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],					sb_writers_name[i],					&type->s_writers_key[i]))			goto fail;	}	s->s_bdi = &noop_backing_dev_info;	s->s_flags = flags;	if (s->s_user_ns != &init_user_ns)		s->s_iflags |= SB_I_NODEV;	INIT_HLIST_NODE(&s->s_instances);	INIT_HLIST_BL_HEAD(&s->s_roots);	spin_lock_init(&s->s_roots_lock);	mutex_init(&s->s_sync_lock);	INIT_LIST_HEAD(&s->s_inodes);	spin_lock_init(&s->s_inode_list_lock);	INIT_LIST_HEAD(&s->s_inodes_wb);	spin_lock_init(&s->s_inode_wblist_lock);	fserror_mount(s); 	refcount_set(&s->s_passive, 1);	atomic_set(&s->s_active, 1);	mutex_init(&s->s_vfs_rename_mutex);	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);	init_rwsem(&s->s_dquot.dqio_sem);	s->s_maxbytes = MAX_NON_LFS;	s->s_op = &default_op;	s->s_time_gran = 1000000000;	s->s_time_min = TIME64_MIN;	s->s_time_max = TIME64_MAX; 	s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,				     "sb-%s", type->name);	if (!s->s_shrink)		goto fail; 	s->s_shrink->scan_objects = super_cache_scan;	s->s_shrink->count_objects = super_cache_count;	s->s_shrink->batch = 1024;	s->s_shrink->private_data = s; 	if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink))		goto fail;	if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink))		goto fail;	s->s_super_dev = super_dev_alloc(0, s);	if (!s->s_super_dev)		goto fail; 	s->s_min_writeback_pages = MIN_WRITEBACK_PAGES;	return s; fail:	destroy_unused_super(s);	return NULL;} /* Superblock refcounting  */ /* * Drop a superblock's passive reference.  Must be called WITHOUT sb_lock held; * put_super() acquires sb_lock itself when the final reference is dropped. */void put_super(struct super_block *s){	if (refcount_dec_and_test(&s->s_passive)) { 		spin_lock(&sb_lock);		list_del_init(&s->s_list);		spin_unlock(&sb_lock); 		WARN_ON(s->s_dentry_lru.node);		WARN_ON(s->s_inode_lru.node);		WARN_ON(s->s_mounts);		call_rcu(&s->rcu, destroy_super_rcu);	}} struct super_dev {	dev_t			sd_dev;	struct super_block	*sd_sb;	refcount_t		sd_ref;	struct rhlist_head	sd_node;	struct rcu_head		sd_rcu;}; static struct rhltable super_dev_table;static const struct rhashtable_params super_dev_params = {	.key_len	= sizeof(dev_t),	.key_offset	= offsetof(struct super_dev, sd_dev),	.head_offset	= offsetof(struct super_dev, sd_node),}; static struct super_dev *super_dev_alloc(dev_t dev, struct super_block *sb){	struct super_dev *fsd; 	fsd = kzalloc_obj(*fsd);	if (!fsd)		return NULL;	fsd->sd_dev = dev;	fsd->sd_sb = sb;	refcount_set(&fsd->sd_ref, 1);	return fsd;} static void super_dev_put(struct super_dev *fsd){	/* Unlink only once unpinned, so a cursor never resumes from a removed node. */	if (fsd && refcount_dec_and_test(&fsd->sd_ref)) {		rhltable_remove(&super_dev_table, &fsd->sd_node, super_dev_params);		put_super(fsd->sd_sb);		kfree_rcu(fsd, sd_rcu);	}} void __init super_dev_init(void){	if (rhltable_init(&super_dev_table, &super_dev_params))		panic("VFS: Cannot initialise super_dev_table\n");} static int super_dev_insert(struct super_dev *fsd){	int err; 	err = rhltable_insert(&super_dev_table, &fsd->sd_node, super_dev_params);	if (!err)		refcount_inc(&fsd->sd_sb->s_passive);	return err;}

Lines 1–500 of 2468. Load more