path: root/fs/super.c

// 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/fsnotify.h>
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
#include "internal.h"


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);

	/*
	 * Don't call trylock_super as it is a potential
	 * scalability bottleneck. The counts could get updated
	 * between super_cache_count and super_cache_scan anyway.
	 * Call to super_cache_count with shrinker_rwsem held
	 * ensures the safety of call to list_lru_shrink_count() and
	 * s_op->nr_cached_objects().
	 */
	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);

	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);
	/* 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);

	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_anon);
	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);

	if (list_lru_init_memcg(&s->s_dentry_lru))
		goto fail;
	if (list_lru_init_memcg(&s->s_inode_lru))
		goto fail;

	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);
	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->cleancache_pooli