inode.c

/*
 * (C) 1997 Linus Torvalds
 * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
 */
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/backing-dev.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include <trace/events/writeback.h>
#include "internal.h"

/*
 * Inode locking rules:
 *
 * inode->i_lock protects:
 *   inode->i_state, inode->i_hash, __iget()
 * Inode LRU list locks protect:
 *   inode->i_sb->s_inode_lru, inode->i_lru
 * inode->i_sb->s_inode_list_lock protects:
 *   inode->i_sb->s_inodes, inode->i_sb_list
 * bdi->wb.list_lock protects:
 *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
 * inode_hash_lock protects:
 *   inode_hashtable, inode->i_hash
 *
 * Lock ordering:
 *
 * inode->i_sb->s_inode_list_lock
 *   inode->i_lock
 *     Inode LRU list locks
 *
 * bdi->wb.list_lock
 *   inode->i_lock
 *
 * inode_hash_lock
 *   inode->i_sb->s_inode_list_lock
 *   inode->i_lock
 *
 * iunique_lock
 *   inode_hash_lock
 */

static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);

/*
 * Empty aops. Can be used for the cases where the user does not
 * define any of the address_space operations.
 */
const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);

/*
 * Statistics gathering..
 */
struct inodes_stat_t inodes_stat;

static DEFINE_PER_CPU(unsigned long, nr_inodes);
static DEFINE_PER_CPU(unsigned long, nr_unused);

static struct kmem_cache *inode_cachep __read_mostly;

static long get_nr_inodes(void)
{
	int i;
	long sum = 0;
	for_each_possible_cpu(i)
		sum += per_cpu(nr_inodes, i);
	return sum < 0 ? 0 : sum;
}

static inline long get_nr_inodes_unused(void)
{
	int i;
	long sum = 0;
	for_each_possible_cpu(i)
		sum += per_cpu(nr_unused, i);
	return sum < 0 ? 0 : sum;
}

long get_nr_dirty_inodes(void)
{
	/* not actually dirty inodes, but a wild approximation */
	long nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
	return nr_dirty > 0 ? nr_dirty : 0;
}

/*
 * Handle nr_inode sysctl
 */
#ifdef CONFIG_SYSCTL
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos)
{
	inodes_stat.nr_inodes = get_nr_inodes();
	inodes_stat.nr_unused = get_nr_inodes_unused();
	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif

static int no_open(struct inode *inode, struct file *file)
{
	return -ENXIO;
}

/**
 * inode_init_always - perform inode structure intialisation
 * @sb: superblock inode belongs to
 * @inode: inode to initialise
 *
 * These are initializations that need to be done on every inode
 * allocation as the fields are not initialised by slab allocation.
 */
int inode_init_always(struct super_block *sb, struct inode *inode)
{
	static const struct inode_operations empty_iops;
	static const struct file_operations no_open_fops = {.open = no_open};
	struct address_space *const mapping = &inode->i_data;

	inode->i_sb = sb;
	inode->i_blkbits = sb->s_blocksize_bits;
	inode->i_flags = 0;
	atomic_set(&inode->i_count, 1);
	inode->i_op = &empty_iops;
	inode->i_fop = &no_open_fops;
	inode->__i_nlink = 1;
	inode->i_opflags = 0;
	if (sb->s_xattr)
		inode->i_opflags |= IOP_XATTR;
	i_uid_write(inode, 0);
	i_gid_write(inode, 0);
	atomic_set(&inode->i_writecount, 0);
	inode->i_size = 0;
	inode->i_blocks = 0;
	inode->i_bytes = 0;
	inode->i_generation = 0;
	inode->i_pipe = NULL;
	inode->i_bdev = NULL;
	inode->i_cdev = NULL;
	inode->i_link = NULL;
	inode->i_dir_seq = 0;
	inode->i_rdev = 0;
	inode->dirtied_when = 0;

#ifdef CONFIG_CGROUP_WRITEBACK
	inode->i_wb_frn_winner = 0;
	inode->i_wb_frn_avg_time = 0;
	inode->i_wb_frn_history = 0;
#endif

	if (security_inode_alloc(inode))
		goto out;
	spin_lock_init(&inode->i_lock);
	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);

	init_rwsem(&inode->i_rwsem);
	lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key);

	atomic_set(&inode->i_dio_count, 0);

	mapping->a_ops = &empty_aops;
	mapping->host = inode;
	mapping->flags = 0;
	atomic_set(&mapping->i_mmap_writable, 0);
	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
	mapping->private_data = NULL;
	mapping->writeback_index = 0;
	inode->i_private = NULL;
	inode->i_mapping = mapping;
	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif

#ifdef CONFIG_FSNOTIFY
	inode->i_fsnotify_mask = 0;
#endif
	inode->i_flctx = NULL;
	this_cpu_inc(nr_inodes);

	return 0;
out:
	return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);

static struct inode *alloc_inode(struct super_block *sb)
{
	struct inode *inode;

	if (sb->s_op->alloc_inode)
		inode = sb->s_op->alloc_inode(sb);
	else
		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);

	if (!inode)
		return NULL;

	if (unlikely(inode_init_always(sb, inode))) {
		if (inode->i_sb->s_op->destroy_inode)
			inode->i_sb->s_op->destroy_inode(inode);
		else
			kmem_cache_free(inode_cachep, inode);
		return NULL;
	}

	return inode;
}

void free_inode_nonrcu(struct inode *inode)
{
	kmem_cache_free(inode_cachep, inode);
}
EXPORT_SYMBOL(free_inode_nonrcu);

void __destroy_inode(struct inode *inode)
{
	BUG_ON(inode_has_buffers(inode));
	inode_detach_wb(inode);
	security_inode_free(inode);
	fsnotify_inode_delete(inode);
	locks_free_lock_context(inode);
	if (!inode->i_nlink) {
		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
		atomic_long_dec(&inode->i_sb->s_remove_count);
	}

#ifdef CONFIG_FS_POSIX_ACL
	if (inode->i_acl && !is_uncached_acl(inode->i_acl))
		posix_acl_release(inode->i_acl);
	if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl))
		posix_acl_release(inode->i_default_acl);
#endif
	this_cpu_dec(nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);

static void i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(inode_cachep, inode);
}

static void destroy_inode(struct inode *inode)
{
	BUG_ON(!list_empty(&inode->i_lru));
	__destroy_inode(inode);
	if (inode->i_sb->s_op->destroy_inode)
		inode->i_sb->s_op->destroy_inode(inode);
	else
		call_rcu(&inode->i_rcu, i_callback);
}

/**
 * drop_nlink - directly drop an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  In cases
 * where we are attempting to track writes to the
 * filesystem, a decrement to zero means an imminent
 * write when the file is truncated and actually unlinked
 * on the filesystem.
 */
void drop_nlink(struct inode *inode)
{
	WARN_ON(inode->i_nlink == 0);
	inode->__i_nlink--;
	if (!inode->i_nlink)
		atomic_long_inc(&inode->i_sb->s_remove_count);
}
EXPORT_SYMBOL(drop_nlink);

/**
 * clear_nlink - directly zero an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  See
 * drop_nlink() for why we care about i_nlink hitting zero.
 */
void clear_nlink(struct inode *inode)
{
	if (inode->i_nlink) {
		inode->__i_nlink = 0;
		atomic_long_inc(&inode->i_sb->s_remove_count);
	}
}
EXPORT_SYMBOL(clear_nlink);

/**
 * set_nlink - directly set an inode's link count
 * @inode: inode
 * @nlink: new nlink (should be non-zero)
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.
 */
void set_nlink(struct inode *inode, unsigned int nlink)
{
	if (!nlink) {
		clear_nlink(inode);
	} else {
		/* Yes, some filesystems do change nlink from zero to one */
		if (inode->i_nlink == 0)
			atomic_long_dec(&inode->i_sb->s_remove_count);

		inode->__i_nlink = nlink;
	}
}
EXPORT_SYMBOL(set_nlink);

/**
 * inc_nlink - directly increment an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  Currently,
 * it is only here for parity with dec_nlink().
 */
void inc_nlink(struct inode *inode)
{
	if (unlikely(inode->i_nlink == 0)) {
		WARN_ON(!(inode->i_state & I_LINKABLE));
		atomic_long_dec(&inode->i_sb->s_remove_count);
	}

	inode->__i_nlink++;
}
EXPORT_SYMBOL(inc_nlink);

void address_space_init_once(struct address_space *mapping)
{
	memset(mapping, 0, sizeof(*mapping));
	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC | __GFP_ACCOUNT);
	spin_lock_init(&mapping->tree_lock);
	init_rwsem(&mapping->i_mmap_rwsem);
	INIT_LIST_HEAD(&mapping->private_list);
	spin_lock_init(&mapping->private_lock);
	mapping->i_mmap = RB_ROOT;
}
EXPORT_SYMBOL(address_space_init_once);

/*
 * These are initializations that only need to be done
 * once, because the fields are idempotent across use
 * of the inode, so let the slab aware of that.
 */
void inode_init_once(struct inode *inode)
{
	memset(inode, 0, sizeof(*inode));
	INIT_HLIST_NODE(&inode->i_hash);
	INIT_LIST_HEAD(&inode->i_devices);
	INIT_LIST_HEAD(&inode->i_io_list);
	INIT_LIST_HEAD(&inode->i_wb_list);
	INIT_LIST_HEAD(&inode->i_lru);
	address_space_init_once(&inode->i_data);
	i_size_ordered_init(inode);
#ifdef CONFIG_FSNOTIFY
	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
#endif
}
EXPORT_SYMBOL(inode_init_once);

static void init_once(void *foo)
{
	struct inode *inode = (struct inode *) foo;

	inode_init_once(inode);
}

/*
 * inode->i_lock must be held
 */
void __iget(struct inode *inode)
{
	atomic_inc(&inode->i_count);
}

/*
 * get additional reference to inode; caller must already hold one.
 */
void ihold(struct inode *inode)
{
	WARN_ON(atomic_inc_return(&inode->i_count) < 2);
}
EXPORT_SYMBOL(ihold);

static void inode_lru_list_add(struct inode *inode)
{
	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
		this_cpu_inc(nr_unused);
}

/*
 * Add inode to LRU if needed (inode is unused and clean).
 *
 * Needs inode->i_lock held.
 */
void inode_add_lru(struct inode *inode)
{
	if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC |
				I_FREEING | I_WILL_FREE)) &&
	    !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
		inode_lru_list_add(inode);
}


static void inode_lru_list_del(struct inode *inode)
{

	if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
		this_cpu_dec(nr_unused);
}

/**
 * inode_sb_list_add - add inode to the superblock list of inodes
 * @inode: inode to add
 */
void inode_sb_list_add(struct inode *inode)
{
	spin_lock(&inode->i_sb->s_inode_list_lock);
	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
	spin_unlock(&inode->i_sb->s_inode_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);

static inline void inode_sb_list_del(struct inode *inode)
{
	if (!list_empty(&inode->i_sb_list)) {
		spin_lock(&inode->i_sb->s_inode_list_lock);
		list_del_init(&inode->i_sb_list);
		spin_unlock(&inode->i_sb->s_inode_list_lock);
	}
}

static unsigned long hash(struct super_block *sb, unsigned long hashval)
{
	unsigned long tmp;

	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
			L1_CACHE_BYTES;
	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
	return tmp & i_hash_mask;
}

/**
 *	__insert_inode_hash - hash an inode
 *	@inode: unhashed inode
 *	@hashval: unsigned long value used to locate this object in the
 *		inode_hashtable.
 *
 *	Add an inode to the inode hash for this superblock.
 */
void __insert_inode_hash(struct inode *inode, unsigned long hashval)
{
	struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);

	spin_lock(&inode_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_add_head(&inode->i_hash, b);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__insert_inode_hash);

/**
 *	__remove_inode_hash - remove an inode from the hash
 *	@inode: inode to unhash
 *
 *	Remove an inode from the superblock.
 */
void __remove_inode_hash(struct inode *inode)
{
	spin_lock(&inode_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_del_init(&inode->i_hash);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__remove_inode_hash);

void clear_inode(struct inode *inode)
{
	might_sleep();
	/*
	 * We have to cycle tree_lock here because reclaim can be still in the
	 * process of removing the last page (in __delete_from_page_cache())
	 * and we must not free mapping under it.
	 */
	spin_lock_irq(&inode->i_data.tree_lock);
	BUG_ON(inode->i_data.nrpages);
	BUG_ON(inode->i_data.nrexceptional);
	spin_unlock_irq(&inode->i_data.tree_lock);
	BUG_ON(!list_empty(&inode->i_data.private_list));
	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(inode->i_state & I_CLEAR);
	BUG_ON(!list_empty(&inode->i_wb_list));
	/* don't need i_lock here, no concurrent mods to i_state */
	inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(clear_inode);

/*
 * Free the inode passed in, removing it from the lists it is still connected
 * to. We remove any pages still attached to the inode and wait for any IO that
 * is still in progress before finally destroying the inode.
 *
 * An inode must already be marked I_FREEING so that we avoid the inode being
 * moved back onto lists if we race with other code that manipulates the lists
 * (e.g. writeback_single_inode). The caller is responsible for setting this.
 *
 * An inode must already be removed from the LRU list before being evicted from
 * the cache. This should occur atomically with setting the I_FREEING state
 * flag, so no inodes here should ever be on the LRU when being evicted.
 */
static void evict(struct inode *inode)
{
	const struct super_operations *op = inode->i_sb->s_op;

	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(!list_empty(&inode->i_lru));

	if (!list_empty(&inode->i_io_list))
		inode_io_list_del(inode);

	inode_sb_list_del(inode);

	/*
	 * Wait for flusher thread to be done with the inode so that filesystem
	 * does not start destroying it while writeback is still running. Since
	 * the inode has I_FREEING set, flusher thread won't start new work on
	 * the inode.  We just have to wait for running writeback to finish.
	 */
	inode_wait_for_writeback(inode);

	if (op->evict_inode) {
		op->evict_inode(inode);
	} else {
		truncate_inode_pages_final(&inode->i_data);
		clear_inode(inode);
	}
	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
		bd_forget(inode);
	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
		cd_forget(inode);

	remove_inode_hash(inode);

	spin_lock(&inode->i_lock);
	wake_up_bit(&inode->i_state, __I_NEW);
	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
	spin_unlock(&inode->i_lock);

	destroy_inode(inode);
}

/*
 * dispose_list - dispose of the contents of a local list
 * @head: the head of the list to free
 *
 * Dispose-list gets a local list with local inodes in it, so it doesn't
 * need to worry about list corruption and SMP locks.
 */
static void dispose_list(struct list_head *head)
{
	while (!list_empty(head)) {
		struct inode *inode;

		inode = list_first_entry(head, struct inode, i_lru);
		list_del_init(&inode->i_lru);

		evict(inode);
		cond_resched();
	}
}

/**
 * evict_inodes	- evict all evictable inodes for a superblock
 * @sb:		superblock to operate on
 *
 * Make sure that no inodes with zero refcount are retained.  This is
 * called by superblock shutdown after having MS_ACTIVE flag removed,
 * so any inode reaching zero refcount during or after that call will
 * be immediately evicted.
 */
void evict_inodes(struct super_block *sb)
{
	struct inode *inode, *next;
	LIST_HEAD(dispose);

again:
	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		if (atomic_read(&inode->i_count))
			continue;

		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);

		/*
		 * We can have a ton of inodes to evict at unmount time given
		 * enough memory, check to see if we need to go to sleep for a
		 * bit so we don't livelock.
		 */
		if (need_resched()) {
			spin_unlock(&sb->s_inode_list_lock);
			cond_resched();
			dispose_list(&dispose);
			goto again;
		}
	}
	spin_unlock(&sb->s_inode_list_lock);

	dispose_list(&dispose);
}
EXPORT_SYMBOL_GPL(evict_inodes);

/**
 * invalidate_inodes	- attempt to free all inodes on a superblock
 * @sb:		superblock to operate on
 * @kill_dirty: flag to guide handling of dirty inodes
 *
 * Attempts to free all inodes for a given superblock.  If there were any
 * busy inodes return a non-zero value, else zero.
 * If @kill_dirty is set, discard dirty inodes too, otherwise treat
 * them as busy.
 */
int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
	int busy = 0;
	struct inode *inode, *next;
	LIST_HEAD(dispose);

	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_state & I_DIRTY_ALL && !kill_dirty) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}
		if (atomic_read(&inode->i_count)) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
	}
	spin_unlock(&sb->s_inode_list_lock);

	dispose_list(&dispose);

	return busy;
}

/*
 * Isolate the inode from the LRU in preparation for freeing it.
 *
 * Any inodes which are pinned purely because of attached pagecache have their
 * pagecache removed.  If the inode has metadata buffers attached to
 * mapping->private_list then try to remove them.
 *
 * If the inode has the I_REFERENCED flag set, then it means that it has been
 * used recently - the flag is set in iput_final(). When we encounter such an
 * inode, clear the flag and move it to the back of the LRU so it gets another
 * pass through the LRU before it gets reclaimed. This is necessary because of
 * the fact we are doing lazy LRU updates to minimise lock contention so the
 * LRU does not have strict ordering. Hence we don't want to reclaim inodes
 * with this flag set because they are the inodes that are out of order.
 */
static enum lru_status inode_lru_isolate(struct list_head *item,
		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
{
	struct list_head *freeable = arg;
	struct inode	*inode = container_of(item, struct inode, i_lru);

	/*
	 * we are inverting the lru lock/inode->i_lock here, so use a trylock.
	 * If we fail to get the lock, just skip it.
	 */
	if (!spin_trylock(&inode->i_lock))
		return LRU_SKIP;

	/*
	 * Referenced or dirty inodes are still in use. Give them another pass
	 * through the LRU as we canot reclaim them now.
	 */
	if (atomic_read(&inode->i_count) ||
	    (inode->i_state & ~I_REFERENCED)) {
		list_lru_isolate(lru, &inode->i_lru);
		spin_unlock(&inode->i_lock);
		this_cpu_dec(nr_unused);
		return LRU_REMOVED;
	}

	/* recently referenced inodes get one more pass */
	if (inode->i_state & I_REFERENCED) {
		inode->i_state &= ~I_REFERENCED;
		spin_unlock(&inode->i_lock);
		return LRU_ROTATE;
	}

	if (inode_has_buffers(inode) || inode->i_data.nrpages) {
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(lru_lock);
		if (remove_inode_buffers(inode)) {
			unsigned long reap;
			reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
			if (current_is_kswapd())
				__count_vm_events(KSWAPD_INODESTEAL, reap);
			else
				__count_vm_events(PGINODESTEAL, reap);
			if (current->reclaim_state)
				current->reclaim_state->reclaimed_slab += reap;
		}
		iput(inode);
		spin_lock(lru_lock);
		return LRU_RETRY;
	}

	WARN_ON(inode->i_state & I_NEW);
	inode->i_state |= I_FREEING;
	list_lru_isolate_move(lru, &inode->i_lru, freeable);
	spin_unlock(&inode->i_lock);

	this_cpu_dec(nr_unused);
	return LRU_REMOVED;
}

/*
 * Walk the superblock inode LRU for freeable inodes and attempt to free them.
 * This is called from the superblock shrinker function with a number of inodes
 * to trim from the LRU. Inodes to be freed are moved to a temporary list and
 * then are freed outside inode_lock by dispose_list().
 */
long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
{
	LIST_HEAD(freeable);
	long freed;

	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
				     inode_lru_isolate, &freeable);
	dispose_list(&freeable);
	return freed;
}

static void __wait_on_freeing_inode(struct inode *inode);
/*
 * Called with the inode lock held.
 */
static struct inode *find_inode(struct super_block *sb,
				struct hlist_head *head,
				int (*test)(struct inode *, void *),
				void *data)
{
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, head, i_hash) {
		if (inode->i_sb != sb)
			continue;
		if (!test(inode, data))
			continue;
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * find_inode_fast is the fast path version of find_inode, see the comment at
 * iget_locked for details.
 */
static struct inode *find_inode_fast(struct super_block *sb,
				struct hlist_head *head, unsigned long ino)
{
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, head, i_hash) {
		if (inode->i_ino != ino)
			continue;
		if (inode->i_sb != sb)
			continue;
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * Each cpu owns a range of LAST_INO_BATCH numbers.
 * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
 * to renew the exhausted range.
 *
 * This does not significantly increase overflow rate because every CPU can
 * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
 * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
 * 2^32 range, and is a worst-case. Even a 50% wastage would only increase
 * overflow rate by 2x, which does not seem too significant.
 *
 * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
 * error if st_ino won't fit in target struct field. Use 32bit counter
 * here to attempt to avoid that.
 */
#define LAST_INO_BATCH 1024
static DEFINE_PER_CPU(unsigned int, last_ino);

unsigned int get_next_ino(void)
{
	unsigned int *p = &get_cpu_var(last_ino);
	unsigned int res = *p;

#ifdef CONFIG_SMP
	if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
		static atomic_t shared_last_ino;
		int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);

		res = next - LAST_INO_BATCH;
	}
#endif

	res++;
	/* get_next_ino should not provide a 0 inode number */
	if (unlikely(!res))
		res++;
	*p = res;
	put_cpu_var(last_ino);
	return res;
}
EXPORT_SYMBOL(get_next_ino);

/**
 *	new_inode_pseudo 	- obtain an inode
 *	@sb: superblock
 *
 *	Allocates a new inode for given superblock.
 *	Inode wont be chained in superblock s_inodes list
 *	This means :
 *	- fs can't be unmount
 *	- quotas, fsnotify, writeback can't work
 */
struct inode *new_inode_pseudo(struct super_block *sb)
{
	struct inode *inode = alloc_inode(sb);

	if (inode) {
		spin_lock(&inode->i_lock);
		inode->i_state = 0;
		spin_unlock(&inode->i_lock);
		INIT_LIST_HEAD(&inode->i_sb_list);
	}
	return inode;
}

/**
 *	new_inode 	- obtain an inode
 *	@sb: superblock
 *
 *	Allocates a new inode for given superblock. The default gfp_mask
 *	for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
 *	If HIGHMEM pages are unsuitable or it is known that pages allocated
 *	for the page cache are not reclaimable or migratable,
 *	mapping_set_gfp_mask() must be called with suitable flags on the
 *	newly created inode's mapping
 *
 */
struct inode *new_inode(struct super_block *sb)
{
	struct inode *inode;

	spin_lock_prefetch(&sb->s_inode_list_lock);

	inode = new_inode_pseudo(sb);
	if (inode)
		inode_sb_list_add(inode);
	return inode;
}
EXPORT_SYMBOL(new_inode);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void lockdep_annotate_inode_mutex_key(struct inode *inode)
{
	if (S_ISDIR(inode->i_mode)) {
		struct file_system_type *type = inode->i_sb->s_type;

		/* Set new key only if filesystem hasn't already changed it */
		if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
			/*
			 * ensure nobody is actually holding i_mutex
			 */
			// mutex_destroy(&inode->i_mutex);
			init_rwsem(&inode->i_rwsem);
			lockdep_set_class(&inode->i_rwsem,
					  &type->i_mutex_dir_key);
		}
	}
}
EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
#endif

/**
 * unlock_new_inode - clear the I_NEW state and wake up any waiters
 * @inode:	new inode to unlock
 *
 * Called when the inode is fully initialised to clear the new state of the
 * inode and wake up anyone waiting for the inode to finish initialisation.
 */
void unlock_new_inode(struct inode *inode)
{
	lockdep_annotate_inode_mutex_key(inode);
	spin_lock(&inode->i_lock);
	WARN_ON(!(inode->i_state & I_NEW));
	inode->i_state &= ~I_NEW;
	smp_mb();
	wake_up_bit(&inode->i_state, __I_NEW);
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);

/**
 * lock_two_nondirectories - take two i_mutexes on non-directory objects
 *
 * Lock any non-NULL argument that is not a directory.
 * Zero, one or two objects may be locked by this function.
 *
 * @inode1: first inode to lock
 * @inode2: second inode to lock
 */
void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
	if (inode1 > inode2)
		swap(inode1, inode2);

	if (inode1 && !S_ISDIR(inode1->i_mode))
		inode_lock(inode1);
	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
		inode_lock_nested(inode2, I_MUTEX_NONDIR2);
}
EXPORT_SYMBOL(lock_two_nondirectories);

/**
 * unlock_two_nondirectories - release locks from lock_two_nondirectories()
 * @inode1: first inode to unlock
 * @inode2: second inode to unlock
 */
void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
	if (inode1 && !S_ISDIR(inode1->i_mode))
		inode_unlock(inode1);
	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
		inode_unlock(inode2);
}
EXPORT_SYMBOL(unlock_two_nondirectories);