/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_inode.h"
#include "xfs_dinode.h"
#include "xfs_error.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_fsops.h"
#include "xfs_icache.h"

#include <linux/kthread.h>
#include <linux/freezer.h>

/*
 * The inode lookup is done in batches to keep the amount of lock traffic and
 * radix tree lookups to a minimum. The batch size is a trade off between
 * lookup reduction and stack usage. This is in the reclaim path, so we can't
 * be too greedy.
 */
#define XFS_LOOKUP_BATCH	32

STATIC int
xfs_inode_ag_walk_grab(
	struct xfs_inode	*ip)
{
	struct inode		*inode = VFS_I(ip);

	ASSERT(rcu_read_lock_held());

	/*
	 * check for stale RCU freed inode
	 *
	 * If the inode has been reallocated, it doesn't matter if it's not in
	 * the AG we are walking - we are walking for writeback, so if it
	 * passes all the "valid inode" checks and is dirty, then we'll write
	 * it back anyway.  If it has been reallocated and still being
	 * initialised, the XFS_INEW check below will catch it.
	 */
	spin_lock(&ip->i_flags_lock);
	if (!ip->i_ino)
		goto out_unlock_noent;

	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
		goto out_unlock_noent;
	spin_unlock(&ip->i_flags_lock);

	/* nothing to sync during shutdown */
	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return EFSCORRUPTED;

	/* If we can't grab the inode, it must on it's way to reclaim. */
	if (!igrab(inode))
		return ENOENT;

	if (is_bad_inode(inode)) {
		IRELE(ip);
		return ENOENT;
	}

	/* inode is valid */
	return 0;

out_unlock_noent:
	spin_unlock(&ip->i_flags_lock);
	return ENOENT;
}

STATIC int
xfs_inode_ag_walk(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	int			(*execute)(struct xfs_inode *ip,
					   struct xfs_perag *pag, int flags),
	int			flags)
{
	uint32_t		first_index;
	int			last_error = 0;
	int			skipped;
	int			done;
	int			nr_found;

restart:
	done = 0;
	skipped = 0;
	first_index = 0;
	nr_found = 0;
	do {
		struct xfs_inode *batch[XFS_LOOKUP_BATCH];
		int		error = 0;
		int		i;

		rcu_read_lock();
		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH);
		if (!nr_found) {
			rcu_read_unlock();
			break;
		}

		/*
		 * Grab the inodes before we drop the lock. if we found
		 * nothing, nr == 0 and the loop will be skipped.
		 */
		for (i = 0; i < nr_found; i++) {
			struct xfs_inode *ip = batch[i];

			if (done || xfs_inode_ag_walk_grab(ip))
				batch[i] = NULL;

			/*
			 * Update the index for the next lookup. Catch
			 * overflows into the next AG range which can occur if
			 * we have inodes in the last block of the AG and we
			 * are currently pointing to the last inode.
			 *
			 * Because we may see inodes that are from the wrong AG
			 * due to RCU freeing and reallocation, only update the
			 * index if it lies in this AG. It was a race that lead
			 * us to see this inode, so another lookup from the
			 * same index will not find it again.
			 */
			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
				continue;
			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
				done = 1;
		}

		/* unlock now we've grabbed the inodes. */
		rcu_read_unlock();

		for (i = 0; i < nr_found; i++) {
			if (!batch[i])
				continue;
			error = execute(batch[i], pag, flags);
			IRELE(batch[i]);
			if (error == EAGAIN) {
				skipped++;
				continue;
			}
			if (error && last_error != EFSCORRUPTED)
				last_error = error;
		}

		/* bail out if the filesystem is corrupted.  */
		if (error == EFSCORRUPTED)
			break;

		cond_resched();

	} while (nr_found && !done);

	if (skipped) {
		delay(1);
		goto restart;
	}
	return last_error;
}

int
xfs_inode_ag_iterator(
	struct xfs_mount	*mp,
	int			(*execute)(struct xfs_inode *ip,
					   struct xfs_perag *pag, int flags),
	int			flags)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;

	ag = 0;
	while ((pag = xfs_perag_get(mp, ag))) {
		ag = pag->pag_agno + 1;
		error = xfs_inode_ag_walk(mp, pag, execute, flags);
		xfs_perag_put(pag);
		if (error) {
			last_error = error;
			if (error == EFSCORRUPTED)
				break;
		}
	}
	return XFS_ERROR(last_error);
}

/*
 * Queue a new inode reclaim pass if there are reclaimable inodes and there
 * isn't a reclaim pass already in progress. By default it runs every 5s based
 * on the xfs periodic sync default of 30s. Perhaps this should have it's own
 * tunable, but that can be done if this method proves to be ineffective or too
 * aggressive.
 */
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();
}

/*
 * This is a fast pass over the inode cache to try to get reclaim moving on as
 * many inodes as possible in a short period of time. It kicks itself every few
 * seconds, as well as being kicked by the inode cache shrinker when memory
 * goes low. It scans as quickly as possible avoiding locked inodes or those
 * already being flushed, and once done schedules a future pass.
 */
void
xfs_reclaim_worker(
	struct work_struct *work)
{
	struct xfs_mount *mp = container_of(to_delayed_work(work),
					struct xfs_mount, m_reclaim_work);

	xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
	xfs_reclaim_work_queue(mp);
}

void
__xfs_inode_set_reclaim_tag(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip)
{
	radix_tree_tag_set(&pag->pag_ici_root,
			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
			   XFS_ICI_RECLAIM_TAG);

	if (!pag->pag_ici_reclaimable) {
		/* propagate the reclaim tag up into the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_set(&ip->i_mount->m_perag_tree,
				XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				XFS_ICI_RECLAIM_TAG);
		spin_unlock(&ip->i_mount->m_perag_lock);

		/* schedule periodic background inode reclaim */
		xfs_reclaim_work_queue(ip->i_mount);

		trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
							-1, _RET_IP_);
	}
	pag->pag_ici_reclaimable++;
}

/*
 * We set the inode flag atomically with the radix tree tag.
 * Once we get tag lookups on the radix tree, this inode flag
 * can go away.
 */
void
xfs_inode_set_reclaim_tag(
	xfs_inode_t	*ip)
{
	struct xfs_mount *mp = ip->i_mount;
	struct xfs_perag *pag;

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
	spin_lock(&pag->pag_ici_lock);
	spin_lock(&ip->i_flags_lock);
	__xfs_inode_set_reclaim_tag(pag, ip);
	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
	spin_unlock(&ip->i_flags_lock);
	spin_unlock(&pag->pag_ici_lock);
	xfs_perag_put(pag);
}

STATIC void
__xfs_inode_clear_reclaim(
	xfs_perag_t	*pag,
	xfs_inode_t	*ip)
{
	pag->pag_ici_reclaimable--;
	if (!pag->pag_ici_reclaimable) {
		/* clear the reclaim tag from the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
				XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				XFS_ICI_RECLAIM_TAG);
		spin_unlock(&ip->i_mount->m_perag_lock);
		trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
							-1, _RET_IP_);
	}
}

void
__xfs_inode_clear_reclaim_tag(
	xfs_mount_t	*mp,
	xfs_perag_t	*pag,
	xfs_inode_t	*ip)
{
	radix_tree_tag_clear(&pag->pag_ici_root,
			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
	__xfs_inode_clear_reclaim(pag, ip);
}

/*
 * Grab the inode for reclaim exclusively.
 * Return 0 if we grabbed it, non-zero otherwise.
 */
STATIC int
xfs_reclaim_inode_grab(
	struct xfs_inode	*ip,
	int			flags)
{
	ASSERT(rcu_read_lock_held());

	/* quick check for stale RCU freed inode */
	if (!ip->i_ino)
		return 1;

	/*
	 * If we are asked for non-blocking operation, do unlocked checks to
	 * see if the inode already is being flushed or in reclaim to avoid
	 * lock traffic.
	 */
	if ((flags & SYNC_TRYLOCK) &&
	    __xfs_iflags_test(ip, XFS_IFLOCK | XFS_IRECLAIM))
		return 1;

	/*
	 * The radix tree lock here protects a thread in xfs_iget from racing
	 * with us starting reclaim on the inode.  Once we have the
	 * XFS_IRECLAIM flag set it will not touch us.
	 *
	 * Due to RCU lookup, we may find inodes that have been freed and only
	 * have XFS_IRECLAIM set.  Indeed, we may see reallocated inodes that
	 * aren't candidates for reclaim at all, so we must check the
	 * XFS_IRECLAIMABLE is set first before proceeding to reclaim.
	 */
	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 1;
	}
	__xfs_iflags_set(ip, XFS_IRECLAIM);
	spin_unlock(&ip->i_flags_lock);
	return 0;
}

/*
 * Inodes in different states need to be treated differently. The following
 * table lists the inode states and the reclaim actions necessary:
 *
 *	inode state	     iflush ret		required action
 *      ---------------      ----------         ---------------
 *	bad			-		reclaim
 *	shutdown		EIO		unpin and reclaim
 *	clean, unpinned		0		reclaim
 *	stale, unpinned		0		reclaim
 *	clean, pinned(*)	0		requeue
 *	stale, pinned		EAGAIN		requeue
 *	dirty, async		-		requeue
 *	dirty, sync		0		reclaim
 *
 * (*) dgc: I don't think the clean, pinned state is possible but it gets
 * handled anyway given the order of checks implemented.
 *
 * Also, because we get the flush lock first, we know that any inode that has
 * been flushed delwri has had the flush completed by the time we check that
 * the inode is clean.
 *
 * Note that because the inode is flushed delayed write by AIL pushing, the
 * flush lock may already be held here and waiting on it can result in very
 * long latencies.  Hence for sync reclaims, where we wait on the flush lock,
 * the caller should push the AIL first before trying to reclaim inodes to
 * minimise the amount of time spent waiting.  For background relaim, we only
 * bother to reclaim clean inodes anyway.
 *
 * Hence the order of actions after gaining the locks should be:
 *	bad		=> reclaim
 *	shutdown	=> unpin and reclaim
 *	pinned, async	=> requeue
 *	pinned, sync	=> unpin
 *	stale		=> reclaim
 *	clean		=> reclaim
 *	dirty, async	=> requeue
 *	dirty, sync	=> flush, wait and reclaim
 */
STATIC int
xfs_reclaim_inode(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag,
	int			sync_mode)
{
	struct xfs_buf		*bp = NULL;
	int			error;

restart:
	error = 0;
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	if (!xfs_iflock_nowait(ip)) {
		if (!(sync_mode & SYNC_WAIT))
			goto out;
		xfs_iflock(ip);
	}

	if (is_bad_inode(VFS_I(ip)))
		goto reclaim;
	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
		xfs_iunpin_wait(ip);
		xfs_iflush_abort(ip, false);
		goto reclaim;
	}
	if (xfs_ipincount(ip)) {
		if (!(sync_mode & SYNC_WAIT))
			goto out_ifunlock;
		xfs_iunpin_wait(ip);
	}
	if (xfs_iflags_test(ip, XFS_ISTALE))
		goto reclaim;
	if (xfs_inode_clean(ip))
		goto reclaim;

	/*
	 * Never flush out dirty data during non-blocking reclaim, as it would
	 * just contend with AIL pushing trying to do the same job.
	 */
	if (!(sync_mode & SYNC_WAIT))
		goto out_ifunlock;

	/*
	 * Now we have an inode that needs flushing.
	 *
	 * Note that xfs_iflush will never block on the inode buffer lock, as
	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
	 * ip->i_lock, and we are doing the exact opposite here.  As a result,
	 * doing a blocking xfs_imap_to_bp() to get the cluster buffer would
	 * result in an ABBA deadlock with xfs_ifree_cluster().
	 *
	 * As xfs_ifree_cluser() must gather all inodes that are active in the
	 * cache to mark them stale, if we hit this case we don't actually want
	 * to do IO here - we want the inode marked stale so we can simply
	 * reclaim it.  Hence if we get an EAGAIN error here,  just unlock the
	 * inode, back off and try again.  Hopefully the next pass through will
	 * see the stale flag set on the inode.
	 */
	error = xfs_iflush(ip, &bp);
	if (error == EAGAIN) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		/* backoff longer than in xfs_ifree_cluster */
		delay(2);
		goto restart;
	}

	if (!error) {
		error = xfs_bwrite(bp);
		xfs_buf_relse(bp);
	}

	xfs_iflock(ip);
reclaim:
	xfs_ifunlock(ip);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	XFS_STATS_INC(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, ip->i_ino)))
		ASSERT(0);
	__xfs_inode_clear_reclaim(pag, ip);
	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);
	xfs_qm_dqdetach(ip);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	xfs_inode_free(ip);
	return error;

out_ifunlock:
	xfs_ifunlock(ip);
out:
	xfs_iflags_clear(ip, XFS_IRECLAIM);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	/*
	 * We could return EAGAIN here to make reclaim rescan the inode tree in
	 * a short while. However, this just burns CPU time scanning the tree
	 * waiting for IO to complete and the reclaim work never goes back to
	 * the idle state. Instead, return 0 to let the next scheduled
	 * background reclaim attempt to reclaim the inode again.
	 */
	return 0;
}

/*
 * Walk the AGs and reclaim the inodes in them. Even if the filesystem is
 * corrupted, we still want to try to reclaim all the inodes. If we don't,
 * then a shut down during filesystem unmount reclaim walk leak all the
 * unreclaimed inodes.
 */
int
xfs_reclaim_inodes_ag(
	struct xfs_mount	*mp,
	int			flags,
	int			*nr_to_scan)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;
	int			trylock = flags & SYNC_TRYLOCK;
	int			skipped;

restart:
	ag = 0;
	skipped = 0;
	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		unsigned long	first_index = 0;
		int		done = 0;
		int		nr_found = 0;

		ag = pag->pag_agno + 1;

		if (trylock) {
			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
				skipped++;
				xfs_perag_put(pag);
				continue;
			}
			first_index = pag->pag_ici_reclaim_cursor;
		} else
			mutex_lock(&pag->pag_ici_reclaim_lock);

		do {
			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
			int	i;

			rcu_read_lock();
			nr_found = radix_tree_gang_lookup_tag(
					&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH,
					XFS_ICI_RECLAIM_TAG);
			if (!nr_found) {
				done = 1;
				rcu_read_unlock();
				break;
			}

			/*
			 * Grab the inodes before we drop the lock. if we found
			 * nothing, nr == 0 and the loop will be skipped.
			 */
			for (i = 0; i < nr_found; i++) {
				struct xfs_inode *ip = batch[i];

				if (done || xfs_reclaim_inode_grab(ip, flags))
					batch[i] = NULL;

				/*
				 * Update the index for the next lookup. Catch
				 * overflows into the next AG range which can
				 * occur if we have inodes in the last block of
				 * the AG and we are currently pointing to the
				 * last inode.
				 *
				 * Because we may see inodes that are from the
				 * wrong AG due to RCU freeing and
				 * reallocation, only update the index if it
				 * lies in this AG. It was a race that lead us
				 * to see this inode, so another lookup from
				 * the same index will not find it again.
				 */
				if (XFS_INO_TO_AGNO(mp, ip->i_ino) !=
								pag->pag_agno)
					continue;
				first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
				if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
					done = 1;
			}

			/* unlock now we've grabbed the inodes. */
			rcu_read_unlock();

			for (i = 0; i < nr_found; i++) {
				if (!batch[i])
					continue;
				error = xfs_reclaim_inode(batch[i], pag, flags);
				if (error && last_error != EFSCORRUPTED)
					last_error = error;
			}

			*nr_to_scan -= XFS_LOOKUP_BATCH;

			cond_resched();

		} while (nr_found && !done && *nr_to_scan > 0);

		if (trylock && !done)
			pag->pag_ici_reclaim_cursor = first_index;
		else
			pag->pag_ici_reclaim_cursor = 0;
		mutex_unlock(&pag->pag_ici_reclaim_lock);
		xfs_perag_put(pag);
	}

	/*
	 * if we skipped any AG, and we still have scan count remaining, do
	 * another pass this time using blocking reclaim semantics (i.e
	 * waiting on the reclaim locks and ignoring the reclaim cursors). This
	 * ensure that when we get more reclaimers than AGs we block rather
	 * than spin trying to execute reclaim.
	 */
	if (skipped && (flags & SYNC_WAIT) && *nr_to_scan > 0) {
		trylock = 0;
		goto restart;
	}
	return XFS_ERROR(last_error);
}

int
xfs_reclaim_inodes(
	xfs_mount_t	*mp,
	int		mode)
{
	int		nr_to_scan = INT_MAX;

	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
}

/*
 * Scan a certain number of inodes for reclaim.
 *
 * When called we make sure that there is a background (fast) inode reclaim in
 * progress, while we will throttle the speed of reclaim via doing synchronous
 * reclaim of inodes. That means if we come across dirty inodes, we wait for
 * them to be cleaned, which we hope will not be very long due to the
 * background walker having already kicked the IO off on those dirty inodes.
 */
void
xfs_reclaim_inodes_nr(
	struct xfs_mount	*mp,
	int			nr_to_scan)
{
	/* kick background reclaimer and push the AIL */
	xfs_reclaim_work_queue(mp);
	xfs_ail_push_all(mp->m_ail);

	xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
}

/*
 * Return the number of reclaimable inodes in the filesystem for
 * the shrinker to determine how much to reclaim.
 */
int
xfs_reclaim_inodes_count(
	struct xfs_mount	*mp)
{
	struct xfs_perag	*pag;
	xfs_agnumber_t		ag = 0;
	int			reclaimable = 0;

	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		ag = pag->pag_agno + 1;
		reclaimable += pag->pag_ici_reclaimable;
		xfs_perag_put(pag);
	}
	return reclaimable;
}