// 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/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/cleancache.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); static LIST_HEAD(super_blocks);static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = {	"sb_writers",	"sb_pagefaults",	"sb_internal",}; /* * 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_rwsem. 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 = container_of(shrink, struct super_block, s_shrink); 	/*	 * 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 (!trylock_super(sb))		return SHRINK_STOP; 	if (sb->s_op->nr_cached_objects)		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 + 1;	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);	} 	up_read(&sb->s_umount);	return freed;} static unsigned long super_cache_count(struct shrinker *shrink,				       struct shrink_control *sc){	struct super_block *sb;	long	total_objects = 0; 	sb = container_of(shrink, struct super_block, s_shrink); 	/*	 * We don't call trylock_super() 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.  trylock_super() 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)		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 void destroy_super_work(struct work_struct *work){	struct super_block *s = container_of(work, struct super_block,							destroy_work);	int i; 	for (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;	up_write(&s->s_umount);	list_lru_destroy(&s->s_dentry_lru);	list_lru_destroy(&s->s_inode_lru);	security_sb_free(s);	put_user_ns(s->s_user_ns);	kfree(s->s_subtype);	free_prealloced_shrinker(&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(sizeof(struct super_block),  GFP_USER);	static const struct super_operations default_op;	int i; 	if (!s)		return NULL; 	INIT_LIST_HEAD(&s->s_mounts);	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() 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;	}	init_waitqueue_head(&s->s_writers.wait_unfrozen);	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);	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); 	s->s_count = 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->cleancache_poolid = CLEANCACHE_NO_POOL; 	s->s_shrink.seeks = DEFAULT_SEEKS;	s->s_shrink.scan_objects = super_cache_scan;	s->s_shrink.count_objects = super_cache_count;	s->s_shrink.batch = 1024;	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;	if (prealloc_shrinker(&s->s_shrink))		goto fail;	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;	return s; fail:	destroy_unused_super(s);	return NULL;} /* Superblock refcounting  */ /* * Drop a superblock's refcount.  The caller must hold sb_lock. */static void __put_super(struct super_block *s){	if (!--s->s_count) {		list_del_init(&s->s_list);		WARN_ON(s->s_dentry_lru.node);		WARN_ON(s->s_inode_lru.node);		WARN_ON(!list_empty(&s->s_mounts));		security_sb_free(s);		fscrypt_sb_free(s);		put_user_ns(s->s_user_ns);		kfree(s->s_subtype);		call_rcu(&s->rcu, destroy_super_rcu);	}} /** *	put_super	-	drop a temporary reference to superblock *	@sb: superblock in question * *	Drops a temporary reference, frees superblock if there's no *	references left. */static void put_super(struct super_block *sb){	spin_lock(&sb_lock);	__put_super(sb);	spin_unlock(&sb_lock);}  /** *	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){	struct file_system_type *fs = s->s_type;	if (atomic_dec_and_test(&s->s_active)) {		cleancache_invalidate_fs(s);		unregister_shrinker(&s->s_shrink);		fs->kill_sb(s); 		/*		 * Since list_lru_destroy() may sleep, we cannot call it from		 * put_super(), where we hold the sb_lock. Therefore we destroy		 * the lru lists right now.		 */		list_lru_destroy(&s->s_dentry_lru);		list_lru_destroy(&s->s_inode_lru); 		put_filesystem(fs);		put_super(s);	} else {		up_write(&s->s_umount);	}} EXPORT_SYMBOL(deactivate_locked_super); /** *	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){	if (!atomic_add_unless(&s->s_active, -1, 1)) {		down_write(&s->s_umount);		deactivate_locked_super(s);	}} EXPORT_SYMBOL(deactivate_super); /** *	grab_super - acquire an active reference *	@s: reference we are trying to make active * *	Tries to acquire an active reference.  grab_super() is used when we * 	had just found a superblock in super_blocks or fs_type->fs_supers *	and want to turn it into a full-blown active reference.  grab_super() *	is called with sb_lock held and drops it.  Returns 1 in case of *	success, 0 if we had failed (superblock contents was already dead or *	dying when grab_super() had been called).  Note that this is only *	called for superblocks not in rundown mode (== ones still on ->fs_supers *	of their type), so increment of ->s_count is OK here. */static int grab_super(struct super_block *s) __releases(sb_lock){	s->s_count++;	spin_unlock(&sb_lock);	down_write(&s->s_umount);	if ((s->s_flags & SB_BORN) && atomic_inc_not_zero(&s->s_active)) {		put_super(s);		return 1;	}	up_write(&s->s_umount);	put_super(s);	return 0;} /* *	trylock_super - 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 trylock_super(struct super_block *sb){	if (down_read_trylock(&sb->s_umount)) {		if (!hlist_unhashed(&sb->s_instances) &&		    sb->s_root && (sb->s_flags & SB_BORN))			return true;		up_read(&sb->s_umount);	} 	return false;} /** *	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){	const struct super_operations *sop = sb->s_op; 	if (sb->s_root) {		shrink_dcache_for_umount(sb);		sync_filesystem(sb);		sb->s_flags &= ~SB_ACTIVE; 		cgroup_writeback_umount(); 		/* evict all inodes with zero refcount */		evict_inodes(sb);		/* only nonzero refcount inodes can have marks */		fsnotify_sb_delete(sb); 		if (sb->s_dio_done_wq) {			destroy_workqueue(sb->s_dio_done_wq);			sb->s_dio_done_wq = NULL;		} 		if (sop->put_super)			sop->put_super(sb); 		if (!list_empty(&sb->s_inodes)) {			printk("VFS: Busy inodes after unmount of %s. "			   "Self-destruct in 5 seconds.  Have a nice day...\n",			   sb->s_id);		}	}	spin_lock(&sb_lock);	/* should be initialized for __put_super_and_need_restart() */	hlist_del_init(&sb->s_instances);	spin_unlock(&sb_lock);	up_write(&sb->s_umount);	if (sb->s_bdi != &noop_backing_dev_info) {		bdi_put(sb->s_bdi);		sb->s_bdi = &noop_backing_dev_info;	}} EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc){	if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT))		return capable(CAP_SYS_ADMIN);	else		return ns_capable(fc->user_ns, CAP_SYS_ADMIN);} /** * sget_fc - Find or create a superblock * @fc:	Filesystem context. * @test: Comparison callback * @set: Setup callback * * Find or create a superblock using the parameters stored in the filesystem * context and the two callback functions.

Lines 1–500 of 1867. Load more