xfs_icache.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_bmap_util.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_reflink.h"
#include "xfs_ialloc.h"
#include "xfs_ag.h"

#include <linux/iversion.h>

/* Radix tree tags for incore inode tree. */

/* inode is to be reclaimed */
#define XFS_ICI_RECLAIM_TAG	0
/* Inode has speculative preallocations (posteof or cow) to clean. */
#define XFS_ICI_BLOCKGC_TAG	1

/*
 * The goal for walking incore inodes.  These can correspond with incore inode
 * radix tree tags when convenient.  Avoid existing XFS_IWALK namespace.
 */
enum xfs_icwalk_goal {
	/* Goals directly associated with tagged inodes. */
	XFS_ICWALK_BLOCKGC	= XFS_ICI_BLOCKGC_TAG,
	XFS_ICWALK_RECLAIM	= XFS_ICI_RECLAIM_TAG,
};

static int xfs_icwalk(struct xfs_mount *mp,
		enum xfs_icwalk_goal goal, struct xfs_icwalk *icw);
static int xfs_icwalk_ag(struct xfs_perag *pag,
		enum xfs_icwalk_goal goal, struct xfs_icwalk *icw);

/*
 * Private inode cache walk flags for struct xfs_icwalk.  Must not
 * coincide with XFS_ICWALK_FLAGS_VALID.
 */

/* Stop scanning after icw_scan_limit inodes. */
#define XFS_ICWALK_FLAG_SCAN_LIMIT	(1U << 28)

#define XFS_ICWALK_FLAG_RECLAIM_SICK	(1U << 27)
#define XFS_ICWALK_FLAG_UNION		(1U << 26) /* union filter algorithm */

#define XFS_ICWALK_PRIVATE_FLAGS	(XFS_ICWALK_FLAG_SCAN_LIMIT | \
					 XFS_ICWALK_FLAG_RECLAIM_SICK | \
					 XFS_ICWALK_FLAG_UNION)

/*
 * Allocate and initialise an xfs_inode.
 */
struct xfs_inode *
xfs_inode_alloc(
	struct xfs_mount	*mp,
	xfs_ino_t		ino)
{
	struct xfs_inode	*ip;

	/*
	 * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL
	 * and return NULL here on ENOMEM.
	 */
	ip = kmem_cache_alloc(xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL);

	if (inode_init_always(mp->m_super, VFS_I(ip))) {
		kmem_cache_free(xfs_inode_cache, ip);
		return NULL;
	}

	/* VFS doesn't initialise i_mode or i_state! */
	VFS_I(ip)->i_mode = 0;
	VFS_I(ip)->i_state = 0;
	mapping_set_large_folios(VFS_I(ip)->i_mapping);

	XFS_STATS_INC(mp, vn_active);
	ASSERT(atomic_read(&ip->i_pincount) == 0);
	ASSERT(ip->i_ino == 0);

	/* initialise the xfs inode */
	ip->i_ino = ino;
	ip->i_mount = mp;
	memset(&ip->i_imap, 0, sizeof(struct xfs_imap));
	ip->i_afp = NULL;
	ip->i_cowfp = NULL;
	memset(&ip->i_df, 0, sizeof(ip->i_df));
	ip->i_flags = 0;
	ip->i_delayed_blks = 0;
	ip->i_diflags2 = mp->m_ino_geo.new_diflags2;
	ip->i_nblocks = 0;
	ip->i_forkoff = 0;
	ip->i_sick = 0;
	ip->i_checked = 0;
	INIT_WORK(&ip->i_ioend_work, xfs_end_io);
	INIT_LIST_HEAD(&ip->i_ioend_list);
	spin_lock_init(&ip->i_ioend_lock);

	return ip;
}

STATIC void
xfs_inode_free_callback(
	struct rcu_head		*head)
{
	struct inode		*inode = container_of(head, struct inode, i_rcu);
	struct xfs_inode	*ip = XFS_I(inode);

	switch (VFS_I(ip)->i_mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
	case S_IFLNK:
		xfs_idestroy_fork(&ip->i_df);
		break;
	}

	if (ip->i_afp) {
		xfs_idestroy_fork(ip->i_afp);
		kmem_cache_free(xfs_ifork_cache, ip->i_afp);
	}
	if (ip->i_cowfp) {
		xfs_idestroy_fork(ip->i_cowfp);
		kmem_cache_free(xfs_ifork_cache, ip->i_cowfp);
	}
	if (ip->i_itemp) {
		ASSERT(!test_bit(XFS_LI_IN_AIL,
				 &ip->i_itemp->ili_item.li_flags));
		xfs_inode_item_destroy(ip);
		ip->i_itemp = NULL;
	}

	kmem_cache_free(xfs_inode_cache, ip);
}

static void
__xfs_inode_free(
	struct xfs_inode	*ip)
{
	/* asserts to verify all state is correct here */
	ASSERT(atomic_read(&ip->i_pincount) == 0);
	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
	XFS_STATS_DEC(ip->i_mount, vn_active);

	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}

void
xfs_inode_free(
	struct xfs_inode	*ip)
{
	ASSERT(!xfs_iflags_test(ip, XFS_IFLUSHING));

	/*
	 * Because we use RCU freeing we need to ensure the inode always
	 * appears to be reclaimed with an invalid inode number when in the
	 * free state. The ip->i_flags_lock provides the barrier against lookup
	 * races.
	 */
	spin_lock(&ip->i_flags_lock);
	ip->i_flags = XFS_IRECLAIM;
	ip->i_ino = 0;
	spin_unlock(&ip->i_flags_lock);

	__xfs_inode_free(ip);
}

/*
 * Queue background inode reclaim work if there are reclaimable inodes and there
 * isn't reclaim work already scheduled or in progress.
 */
static void
xfs_reclaim_work_queue(
	struct xfs_mount        *mp)
{

	rcu_read_lock();
	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
		queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
	}
	rcu_read_unlock();
}

/*
 * Background scanning to trim preallocated space. This is queued based on the
 * 'speculative_prealloc_lifetime' tunable (5m by default).
 */
static inline void
xfs_blockgc_queue(
	struct xfs_perag	*pag)
{
	struct xfs_mount	*mp = pag->pag_mount;

	if (!xfs_is_blockgc_enabled(mp))
		return;

	rcu_read_lock();
	if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
		queue_delayed_work(pag->pag_mount->m_blockgc_wq,
				   &pag->pag_blockgc_work,
				   msecs_to_jiffies(xfs_blockgc_secs * 1000));
	rcu_read_unlock();
}

/* Set a tag on both the AG incore inode tree and the AG radix tree. */
static void
xfs_perag_set_inode_tag(
	struct xfs_perag	*pag,
	xfs_agino_t		agino,
	unsigned int		tag)
{
	struct xfs_mount	*mp = pag->pag_mount;
	bool			was_tagged;

	lockdep_assert_held(&pag->pag_ici_lock);

	was_tagged = radix_tree_tagged(&pag->pag_ici_root, tag);
	radix_tree_tag_set(&pag->pag_ici_root, agino, tag);

	if (tag == XFS_ICI_RECLAIM_TAG)
		pag->pag_ici_reclaimable++;

	if (was_tagged)
		return;

	/* propagate the tag up into the perag radix tree */
	spin_lock(&mp->m_perag_lock);
	radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno, tag);
	spin_unlock(&mp->m_perag_lock);

	/* start background work */
	switch (tag) {
	case XFS_ICI_RECLAIM_TAG:
		xfs_reclaim_work_queue(mp);
		break;
	case XFS_ICI_BLOCKGC_TAG:
		xfs_blockgc_queue(pag);
		break;
	}

	trace_xfs_perag_set_inode_tag(mp, pag->pag_agno, tag, _RET_IP_);
}

/* Clear a tag on both the AG incore inode tree and the AG radix tree. */
static void
xfs_perag_clear_inode_tag(
	struct xfs_perag	*pag,
	xfs_agino_t		agino,
	unsigned int		tag)
{
	struct xfs_mount	*mp = pag->pag_mount;

	lockdep_assert_held(&pag->pag_ici_lock);

	/*
	 * Reclaim can signal (with a null agino) that it cleared its own tag
	 * by removing the inode from the radix tree.
	 */
	if (agino != NULLAGINO)
		radix_tree_tag_clear(&pag->pag_ici_root, agino, tag);
	else
		ASSERT(tag == XFS_ICI_RECLAIM_TAG);

	if (tag == XFS_ICI_RECLAIM_TAG)
		pag->pag_ici_reclaimable--;

	if (radix_tree_tagged(&pag->pag_ici_root, tag))
		return;

	/* clear the tag from the perag radix tree */
	spin_lock(&mp->m_perag_lock);
	radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno, tag);
	spin_unlock(&mp->m_perag_lock);

	trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_);
}

/*
 * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
 * part of the structure. This is made more complex by the fact we store
 * information about the on-disk values in the VFS inode and so we can't just
 * overwrite the values unconditionally. Hence we save the parameters we
 * need to retain across reinitialisation, and rewrite them into the VFS inode
 * after reinitialisation even if it fails.
 */
static int
xfs_reinit_inode(
	struct xfs_mount	*mp,
	struct inode		*inode)
{
	int			error;
	uint32_t		nlink = inode->i_nlink;
	uint32_t		generation = inode->i_generation;
	uint64_t		version = inode_peek_iversion(inode);
	umode_t			mode = inode->i_mode;
	dev_t			dev = inode->i_rdev;
	kuid_t			uid = inode->i_uid;
	kgid_t			gid = inode->i_gid;

	error = inode_init_always(mp->m_super, inode);

	set_nlink(inode, nlink);
	inode->i_generation = generation;
	inode_set_iversion_queried(inode, version);
	inode->i_mode = mode;
	inode->i_rdev = dev;
	inode->i_uid = uid;
	inode->i_gid = gid;
	mapping_set_large_folios(inode->i_mapping);
	return error;
}

/*
 * Carefully nudge an inode whose VFS state has been torn down back into a
 * usable state.  Drops the i_flags_lock and the rcu read lock.
 */
static int
xfs_iget_recycle(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip) __releases(&ip->i_flags_lock)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			error;

	trace_xfs_iget_recycle(ip);

	/*
	 * We need to make it look like the inode is being reclaimed to prevent
	 * the actual reclaim workers from stomping over us while we recycle
	 * the inode.  We can't clear the radix tree tag yet as it requires
	 * pag_ici_lock to be held exclusive.
	 */
	ip->i_flags |= XFS_IRECLAIM;

	spin_unlock(&ip->i_flags_lock);
	rcu_read_unlock();

	ASSERT(!rwsem_is_locked(&inode->i_rwsem));
	error = xfs_reinit_inode(mp, inode);
	if (error) {
		/*
		 * Re-initializing the inode failed, and we are in deep
		 * trouble.  Try to re-add it to the reclaim list.
		 */
		rcu_read_lock();
		spin_lock(&ip->i_flags_lock);
		ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
		ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
		spin_unlock(&ip->i_flags_lock);
		rcu_read_unlock();

		trace_xfs_iget_recycle_fail(ip);
		return error;
	}

	spin_lock(&pag->pag_ici_lock);
	spin_lock(&ip->i_flags_lock);

	/*
	 * Clear the per-lifetime state in the inode as we are now effectively
	 * a new inode and need to return to the initial state before reuse
	 * occurs.
	 */
	ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
	ip->i_flags |= XFS_INEW;
	xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino),
			XFS_ICI_RECLAIM_TAG);
	inode->i_state = I_NEW;
	spin_unlock(&ip->i_flags_lock);
	spin_unlock(&pag->pag_ici_lock);

	return 0;
}

/*
 * If we are allocating a new inode, then check what was returned is
 * actually a free, empty inode. If we are not allocating an inode,
 * then check we didn't find a free inode.
 *
 * Returns:
 *	0		if the inode free state matches the lookup context
 *	-ENOENT		if the inode is free and we are not allocating
 *	-EFSCORRUPTED	if there is any state mismatch at all
 */
static int
xfs_iget_check_free_state(
	struct xfs_inode	*ip,
	int			flags)
{
	if (flags & XFS_IGET_CREATE) {
		/* should be a free inode */
		if (VFS_I(ip)->i_mode != 0) {
			xfs_warn(ip->i_mount,
"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
				ip->i_ino, VFS_I(ip)->i_mode);
			return -EFSCORRUPTED;
		}

		if (ip->i_nblocks != 0) {
			xfs_warn(ip->i_mount,
"Corruption detected! Free inode 0x%llx has blocks allocated!",
				ip->i_ino);
			return -EFSCORRUPTED;
		}
		return 0;
	}

	/* should be an allocated inode */
	if (VFS_I(ip)->i_mode == 0)
		return -ENOENT;

	return 0;
}

/* Make all pending inactivation work start immediately. */
static void
xfs_inodegc_queue_all(
	struct xfs_mount	*mp)
{
	struct xfs_inodegc	*gc;
	int			cpu;

	for_each_online_cpu(cpu) {
		gc = per_cpu_ptr(mp->m_inodegc, cpu);
		if (!llist_empty(&gc->list))
			queue_work_on(cpu, mp->m_inodegc_wq, &gc->work);
	}
}

/*
 * Check the validity of the inode we just found it the cache
 */
static int
xfs_iget_cache_hit(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip,
	xfs_ino_t		ino,
	int			flags,
	int			lock_flags) __releases(RCU)
{
	struct inode		*inode = VFS_I(ip);
	struct xfs_mount	*mp = ip->i_mount;
	int			error;

	/*
	 * check for re-use of an inode within an RCU grace period due to the
	 * radix tree nodes not being updated yet. We monitor for this by
	 * setting the inode number to zero before freeing the inode structure.
	 * If the inode has been reallocated and set up, then the inode number
	 * will not match, so check for that, too.
	 */
	spin_lock(&ip->i_flags_lock);
	if (ip->i_ino != ino)
		goto out_skip;

	/*
	 * If we are racing with another cache hit that is currently
	 * instantiating this inode or currently recycling it out of
	 * reclaimable state, wait for the initialisation to complete
	 * before continuing.
	 *
	 * If we're racing with the inactivation worker we also want to wait.
	 * If we're creating a new file, it's possible that the worker
	 * previously marked the inode as free on disk but hasn't finished
	 * updating the incore state yet.  The AGI buffer will be dirty and
	 * locked to the icreate transaction, so a synchronous push of the
	 * inodegc workers would result in deadlock.  For a regular iget, the
	 * worker is running already, so we might as well wait.
	 *
	 * XXX(hch): eventually we should do something equivalent to
	 *	     wait_on_inode to wait for these flags to be cleared
	 *	     instead of polling for it.
	 */
	if (ip->i_flags & (XFS_INEW | XFS_IRECLAIM | XFS_INACTIVATING))
		goto out_skip;

	if (ip->i_flags & XFS_NEED_INACTIVE) {
		/* Unlinked inodes cannot be re-grabbed. */
		if (VFS_I(ip)->i_nlink == 0) {
			error = -ENOENT;
			goto out_error;
		}
		goto out_inodegc_flush;
	}

	/*
	 * Check the inode free state is valid. This also detects lookup
	 * racing with unlinks.
	 */
	error = xfs_iget_check_free_state(ip, flags);
	if (error)
		goto out_error;

	/* Skip inodes that have no vfs state. */
	if ((flags & XFS_IGET_INCORE) &&
	    (ip->i_flags & XFS_IRECLAIMABLE))
		goto out_skip;

	/* The inode fits the selection criteria; process it. */
	if (ip->i_flags & XFS_IRECLAIMABLE) {
		/* Drops i_flags_lock and RCU read lock. */
		error = xfs_iget_recycle(pag, ip);
		if (error)
			return error;
	} else {
		/* If the VFS inode is being torn down, pause and try again. */
		if (!igrab(inode))
			goto out_skip;

		/* We've got a live one. */
		spin_unlock(&ip->i_flags_lock);
		rcu_read_unlock();
		trace_xfs_iget_hit(ip);
	}

	if (lock_flags != 0)
		xfs_ilock(ip, lock_flags);

	if (!(flags & XFS_IGET_INCORE))
		xfs_iflags_clear(ip, XFS_ISTALE);
	XFS_STATS_INC(mp, xs_ig_found);

	return 0;

out_skip:
	trace_xfs_iget_skip(ip);
	XFS_STATS_INC(mp, xs_ig_frecycle);
	error = -EAGAIN;
out_error:
	spin_unlock(&ip->i_flags_lock);
	rcu_read_unlock();
	return error;

out_inodegc_flush:
	spin_unlock(&ip->i_flags_lock);
	rcu_read_unlock();
	/*
	 * Do not wait for the workers, because the caller could hold an AGI
	 * buffer lock.  We're just going to sleep in a loop anyway.
	 */
	if (xfs_is_inodegc_enabled(mp))
		xfs_inodegc_queue_all(mp);
	return -EAGAIN;
}

static int
xfs_iget_cache_miss(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	xfs_trans_t		*tp,
	xfs_ino_t		ino,
	struct xfs_inode	**ipp,
	int			flags,
	int			lock_flags)
{
	struct xfs_inode	*ip;
	int			error;
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
	int			iflags;

	ip = xfs_inode_alloc(mp, ino);
	if (!ip)
		return -ENOMEM;

	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, flags);
	if (error)
		goto out_destroy;

	/*
	 * For version 5 superblocks, if we are initialising a new inode and we
	 * are not utilising the XFS_FEAT_IKEEP inode cluster mode, we can
	 * simply build the new inode core with a random generation number.
	 *
	 * For version 4 (and older) superblocks, log recovery is dependent on
	 * the i_flushiter field being initialised from the current on-disk
	 * value and hence we must also read the inode off disk even when
	 * initializing new inodes.
	 */
	if (xfs_has_v3inodes(mp) &&
	    (flags & XFS_IGET_CREATE) && !xfs_has_ikeep(mp)) {
		VFS_I(ip)->i_generation = prandom_u32();
	} else {
		struct xfs_buf		*bp;

		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp);
		if (error)
			goto out_destroy;

		error = xfs_inode_from_disk(ip,
				xfs_buf_offset(bp, ip->i_imap.im_boffset));
		if (!error)
			xfs_buf_set_ref(bp, XFS_INO_REF);
		xfs_trans_brelse(tp, bp);

		if (error)
			goto out_destroy;
	}

	trace_xfs_iget_miss(ip);

	/*
	 * Check the inode free state is valid. This also detects lookup
	 * racing with unlinks.
	 */
	error = xfs_iget_check_free_state(ip, flags);
	if (error)
		goto out_destroy;

	/*
	 * Preload the radix tree so we can insert safely under the
	 * write spinlock. Note that we cannot sleep inside the preload
	 * region. Since we can be called from transaction context, don't
	 * recurse into the file system.
	 */
	if (radix_tree_preload(GFP_NOFS)) {
		error = -EAGAIN;
		goto out_destroy;
	}

	/*
	 * Because the inode hasn't been added to the radix-tree yet it can't
	 * be found by another thread, so we can do the non-sleeping lock here.
	 */
	if (lock_flags) {
		if (!xfs_ilock_nowait(ip, lock_flags))
			BUG();
	}

	/*
	 * These values must be set before inserting the inode into the radix
	 * tree as the moment it is inserted a concurrent lookup (allowed by the
	 * RCU locking mechanism) can find it and that lookup must see that this
	 * is an inode currently under construction (i.e. that XFS_INEW is set).
	 * The ip->i_flags_lock that protects the XFS_INEW flag forms the
	 * memory barrier that ensures this detection works correctly at lookup
	 * time.
	 */
	iflags = XFS_INEW;
	if (flags & XFS_IGET_DONTCACHE)
		d_mark_dontcache(VFS_I(ip));
	ip->i_udquot = NULL;
	ip->i_gdquot = NULL;
	ip->i_pdquot = NULL;
	xfs_iflags_set(ip, iflags);

	/* insert the new inode */
	spin_lock(&pag->pag_ici_lock);
	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
	if (unlikely(error)) {
		WARN_ON(error != -EEXIST);
		XFS_STATS_INC(mp, xs_ig_dup);
		error = -EAGAIN;
		goto out_preload_end;
	}
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();

	*ipp = ip;
	return 0;

out_preload_end:
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
out_destroy:
	__destroy_inode(VFS_I(ip));
	xfs_inode_free(ip);
	return error;
}

/*
 * Look up an inode by number in the given file system.  The inode is looked up
 * in the cache held in each AG.  If the inode is found in the cache, initialise
 * the vfs inode if necessary.
 *
 * If it is not in core, read it in from the file system's device, add it to the
 * cache and initialise the vfs inode.
 *
 * The inode is locked according to the value of the lock_flags parameter.
 * Inode lookup is only done during metadata operations and not as part of the
 * data IO path. Hence we only allow locking of the XFS_ILOCK during lookup.
 */
int
xfs_iget(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_ino_t		ino,
	uint			flags,
	uint			lock_flags,
	struct xfs_inode	**ipp)
{
	struct xfs_inode	*ip;
	struct xfs_perag	*pag;
	xfs_agino_t		agino;
	int			error;

	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);

	/* reject inode numbers outside existing AGs */
	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
		return -EINVAL;

	XFS_STATS_INC(mp, xs_ig_attempts);

	/* get the perag structure and ensure that it's inode capable */
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
	agino = XFS_INO_TO_AGINO(mp, ino);

again:
	error = 0;
	rcu_read_lock();
	ip = radix_tree_lookup(&pag->pag_ici_root, agino);

	if (ip) {
		error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
		if (error)
			goto out_error_or_again;
	} else {
		rcu_read_unlock();
		if (flags & XFS_IGET_INCORE) {
			error = -ENODATA;
			goto out_error_or_again;
		}
		XFS_STATS_INC(mp, xs_ig_missed);

		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
							flags, lock_flags);
		if (error)
			goto out_error_or_again;
	}
	xfs_perag_put(pag);

	*ipp = ip;

	/*
	 * If we have a real type for an on-disk inode, we can setup the inode
	 * now.	 If it's a new inode being created, xfs_init_new_inode will
	 * handle it.
	 */
	if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
		xfs_setup_existing_inode(ip);
	return 0;

out_error_or_again:
	if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) {
		delay(1);
		goto again;
	}
	xfs_perag_put(pag);
	return error;
}

/*
 * "Is this a cached inode that's also allocated?"
 *
 * Look up an inode by number in the given file system.  If the inode is
 * in cache and isn't in purgatory, return 1 if the inode is allocated
 * and 0 if it is not.  For all other cases (not in cache, being torn
 * down, etc.), return a negative error code.
 *
 * The caller has to prevent inode allocation and freeing activity,
 * presumably by locking the AGI buffer.   This is to ensure that an
 * inode cannot transition from allocated to freed until the caller is
 * ready to allow that.  If the inode is in an intermediate state (new,
 * reclaimable, or being reclaimed), -EAGAIN will be returned; if the
 * inode is not in the cache, -ENOENT will be returned.  The caller must
 * deal with these scenarios appropriately.
 *
 * This is a specialized use case for the online scrubber; if you're
 * reading this, you probably want xfs_iget.
 */
int
xfs_icache_inode_is_allocated(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_ino_t		ino,
	bool			*inuse)
{
	struct xfs_inode	*ip;
	int			error;

	error = xfs_iget(mp, tp, ino, XFS_IGET_INCORE, 0, &ip);
	if (error)
		return error;

	*inuse = !!(VFS_I(ip)->i_mode);
	xfs_irele(ip);
	return 0;
}

/*
 * Grab the inode for reclaim exclusively.
 *
 * We have found this inode via a lookup under RCU, so the inode may have
 * already been freed, or it may be in the process of being recycled by
 * xfs_iget(). In both cases, the inode will have XFS_IRECLAIM set. If the inode
 * has been fully recycled by the time we get the i_flags_lock, XFS_IRECLAIMABLE
 * will not be set. Hence we need to check for both these flag conditions to
 * avoid inodes that are no longer reclaim candidates.
 *
 * Note: checking for other state flags here, under the i_flags_lock or not, is
 * racy and should be avoided. Those races should be resolved only after we have
 * ensured that we are able to reclaim this inode and the world can see that we
 * are going to reclaim it.
 *
 * Return true if we grabbed it, false otherwise.
 */
static bool
xfs_reclaim_igrab(
	struct xfs_inode	*ip,
	struct xfs_icwalk	*icw)
{
	ASSERT(rcu_read_lock_held());

	spin_lock(&ip->i_flags_lock);
	if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) ||
	    __xfs_iflags_test(ip, XFS_IRECLAIM)) {
		/* not a reclaim candidate. */
		spin_unlock(&ip->i_flags_lock);
		return false;
	}

	/* Don't reclaim a sick inode unless the caller asked for it. */
	if (ip->i_sick &&
	    (!icw || !(icw->icw_flags & XFS_ICWALK_FLAG_RECLAIM_SICK))) {
		spin_unlock(&ip->i_flags_lock);
		return false;
	}

	__xfs_iflags_set(ip, XFS_IRECLAIM);
	spin_unlock(&ip->i_flags_lock);
	return true;
}

/*
 * Inode reclaim is non-blocking, so the default action if progress cannot be
 * made is to "requeue" the inode for reclaim by unlocking it and clearing the
 * XFS_IRECLAIM flag.  If we are in a shutdown state, we don't care about
 * blocking anymore and hence we can wait for the inode to be able to reclaim
 * it.
 *
 * We do no IO here - if callers require inodes to be cleaned they must push the
 * AIL first to trigger writeback of dirty inodes.  This enables writeback to be
 * done in the background in a non-blocking manner, and enables memory reclaim
 * to make progress without blocking.
 */
static void
xfs_reclaim_inode(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag)
{
	xfs_ino_t		ino = ip->i_ino; /* for radix_tree_delete */

	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
		goto out;
	if (xfs_iflags_test_and_set(ip, XFS_IFLUSHING))
		goto out_iunlock;

	if (xfs_is_shutdown(ip->i_mount)) {
		xfs_iunpin_wait(ip);
		xfs_iflush_abort(ip);
		goto reclaim;
	}
	if (xfs_ipincount(ip))
		goto out_clear_flush;
	if (!xfs_inode_clean(ip))
		goto out_clear_flush;

	xfs_iflags_clear(ip, XFS_IFLUSHING);
reclaim:
	trace_xfs_inode_reclaiming(ip);

	/*
	 * Because we use RCU freeing we need to ensure the inode always appears
	 * to be reclaimed with an invalid inode number when in the free state.
	 * We do this as early as possible under the ILOCK so that
	 * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to
	 * detect races with us here. By doing this, we guarantee that once
	 * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that
	 * it will see either a valid inode that will serialise correctly, or it
	 * will see an invalid inode that it can skip.
	 */
	spin_lock(&ip->i_flags_lock);
	ip->i_flags = XFS_IRECLAIM;
	ip->i_ino = 0;
	ip->i_sick = 0;
	ip->i_checked = 0;
	spin_unlock(&ip->i_flags_lock);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
	/*
	 * Remove the inode from the per-AG radix tree.
	 *
	 * Because radix_tree_delete won't complain even if the item was never
	 * added to the tree assert that it's been there before to catch
	 * problems with the inode life time early on.
	 */
	spin_lock(&pag->pag_ici_lock);
	if (!radix_tree_delete(&pag->pag_ici_root,
				XFS_INO_TO_AGINO(ip->i_mount, ino)))
		ASSERT(0);
	xfs_perag_clear_inode_tag(pag, NULLAGINO, XFS_ICI_RECLAIM_TAG);
	spin_unlock(&pag->pag_ici_lock);

	/*
	 * Here we do an (almost) spurious inode lock in order to coordinate
	 * with inode cache radix tree lookups.  This is because the lookup
	 * can reference the inodes in the cache without taking references.
	 *
	 * We make that OK here by ensuring that we wait until the inode is
	 * unlocked after the lookup before we go ahead and free it.
	 */
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	ASSERT(!ip->i_udquot && !ip->i_gdquot && !ip->i_pdquot);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	ASSERT(xfs_inode_clean(ip));

	__xfs_inode_free(ip);
	return;

out_clear_flush:
	xfs_iflags_clear(ip, XFS_IFLUSHING);
out_iunlock:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
	xfs_iflags_clear(ip, XFS_IRECLAIM);
}

/* Reclaim sick inodes if we're unmounting or the fs went down. */
static inline bool
xfs_want_reclaim_sick(
	struct xfs_mount	*mp)
{
	return xfs_is_unmounting(mp) || xfs_has_norecovery(mp) ||
	       xfs_is_shutdown(mp);
}

void
xfs_reclaim_inodes(
	struct xfs_mount	*mp)
{
	struct xfs_icwalk	icw = {
		.icw_flags	= 0,
	};

	if (xfs_want_reclaim_sick(mp))
		icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK;

	while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
		xfs_ail_push_all_sync(mp->m_ail);
		xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw);
	}
}

/*
 * The shrinker infrastructure determines how many inodes we should scan for
 * reclaim. We want as many clean inodes ready to reclaim as possible, so we
 * push the AIL here. We also want to proactively free up memory if we can to
 * minimise the amount of work memory reclaim has to do so we kick the
 * background reclaim if it isn't already scheduled.
 */
long
xfs_reclaim_inodes_nr(
	struct xfs_mount	*mp,
	unsigned long		nr_to_scan)
{
	struct xfs_icwalk	icw = {
		.icw_flags	= XFS_ICWALK_FLAG_SCAN_LIMIT,
		.icw_scan_limit	= min_t(unsigned long, LONG_MAX, nr_to_scan),
	};

	if (xfs_want_reclaim_sick(mp))
		icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK;

	/* kick background reclaimer and push the AIL */
	xfs_reclaim_work_queue(mp);
	xfs_ail_push_all(mp->m_ail);

	xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw);
	return 0;
}