1 files changed, 112 insertions, 264 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 5daef654956c..101028ebb571 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -37,13 +37,11 @@ xfs_inode_alloc(
 	struct xfs_inode	*ip;
 
 	/*
-	 * if this didn't occur in transactions, we could use
-	 * KM_MAYFAIL and return NULL here on ENOMEM. Set the
-	 * code up to do this anyway.
+	 * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL
+	 * and return NULL here on ENOMEM.
 	 */
-	ip = kmem_zone_alloc(xfs_inode_zone, 0);
-	if (!ip)
-		return NULL;
+	ip = kmem_cache_alloc(xfs_inode_zone, GFP_KERNEL | __GFP_NOFAIL);
+
 	if (inode_init_always(mp->m_super, VFS_I(ip))) {
 		kmem_cache_free(xfs_inode_zone, ip);
 		return NULL;
@@ -115,6 +113,7 @@ __xfs_inode_free(
 {
 	/* 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);
@@ -141,11 +140,8 @@ xfs_inode_free(
 }
 
 /*
- * 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.
+ * 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(
@@ -160,24 +156,6 @@ xfs_reclaim_work_queue(
 	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);
-}
-
 static void
 xfs_perag_set_reclaim_tag(
 	struct xfs_perag	*pag)
@@ -618,48 +596,31 @@ out_destroy:
 }
 
 /*
- * 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.
+ * 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.
+ * 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.
- * This flag parameter indicates how and if the inode's IO lock and inode lock
- * should be taken.
- *
- * mp -- the mount point structure for the current file system.  It points
- *       to the inode hash table.
- * tp -- a pointer to the current transaction if there is one.  This is
- *       simply passed through to the xfs_iread() call.
- * ino -- the number of the inode desired.  This is the unique identifier
- *        within the file system for the inode being requested.
- * lock_flags -- flags indicating how to lock the inode.  See the comment
- *		 for xfs_ilock() for a list of valid values.
+ * 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(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	uint		flags,
-	uint		lock_flags,
-	xfs_inode_t	**ipp)
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino,
+	uint			flags,
+	uint			lock_flags,
+	struct xfs_inode	**ipp)
 {
-	xfs_inode_t	*ip;
-	int		error;
-	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
+	struct xfs_inode	*ip;
+	struct xfs_perag	*pag;
+	xfs_agino_t		agino;
+	int			error;
 
-	/*
-	 * xfs_reclaim_inode() uses the ILOCK to ensure an inode
-	 * doesn't get freed while it's being referenced during a
-	 * radix tree traversal here.  It assumes this function
-	 * aqcuires only the ILOCK (and therefore it has no need to
-	 * involve the IOLOCK in this synchronization).
-	 */
 	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
 
 	/* reject inode numbers outside existing AGs */
@@ -776,15 +737,7 @@ xfs_inode_walk_ag_grab(
 
 	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.
-	 */
+	/* Check for stale RCU freed inode */
 	spin_lock(&ip->i_flags_lock);
 	if (!ip->i_ino)
 		goto out_unlock_noent;
@@ -1028,107 +981,62 @@ xfs_cowblocks_worker(
 
 /*
  * Grab the inode for reclaim exclusively.
- * Return 0 if we grabbed it, non-zero otherwise.
+ *
+ * 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 int
+static bool
 xfs_reclaim_inode_grab(
-	struct xfs_inode	*ip,
-	int			flags)
+	struct xfs_inode	*ip)
 {
 	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;
+		return false;
 	}
 	__xfs_iflags_set(ip, XFS_IRECLAIM);
 	spin_unlock(&ip->i_flags_lock);
-	return 0;
+	return true;
 }
 
 /*
- * 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
+ * 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.
  *
- * (*) 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
+ * 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 int
+static void
 xfs_reclaim_inode(
 	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	int			sync_mode)
+	struct xfs_perag	*pag)
 {
-	struct xfs_buf		*bp = NULL;
 	xfs_ino_t		ino = ip->i_ino; /* for radix_tree_delete */
-	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 (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		goto out;
+	if (!xfs_iflock_nowait(ip))
+		goto out_iunlock;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
@@ -1136,52 +1044,12 @@ restart:
 		xfs_iflush_abort(ip);
 		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) || xfs_inode_clean(ip)) {
-		xfs_ifunlock(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))
+	if (xfs_ipincount(ip))
+		goto out_ifunlock;
+	if (!xfs_inode_clean(ip))
 		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_ifunlock(ip);
 reclaim:
 	ASSERT(!xfs_isiflocked(ip));
 
@@ -1228,23 +1096,17 @@ reclaim:
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_qm_dqdetach(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	ASSERT(xfs_inode_clean(ip));
 
 	__xfs_inode_free(ip);
-	return error;
+	return;
 
 out_ifunlock:
 	xfs_ifunlock(ip);
+out_iunlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 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;
 }
 
 /*
@@ -1252,23 +1114,19 @@ out:
  * 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.
+ *
+ * Returns non-zero if any AGs or inodes were skipped in the reclaim pass
+ * so that callers that want to block until all dirty inodes are written back
+ * and reclaimed can sanely loop.
  */
-STATIC int
+static void
 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;
+	xfs_agnumber_t		ag = 0;
 
-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;
@@ -1276,16 +1134,7 @@ restart:
 
 		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);
-
+		first_index = READ_ONCE(pag->pag_ici_reclaim_cursor);
 		do {
 			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
 			int	i;
@@ -1309,7 +1158,7 @@ restart:
 			for (i = 0; i < nr_found; i++) {
 				struct xfs_inode *ip = batch[i];
 
-				if (done || xfs_reclaim_inode_grab(ip, flags))
+				if (done || !xfs_reclaim_inode_grab(ip))
 					batch[i] = NULL;
 
 				/*
@@ -1338,59 +1187,39 @@ restart:
 			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;
+				if (batch[i])
+					xfs_reclaim_inode(batch[i], pag);
 			}
 
 			*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);
+		if (done)
+			first_index = 0;
+		WRITE_ONCE(pag->pag_ici_reclaim_cursor, first_index);
 		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 last_error;
 }
 
-int
+void
 xfs_reclaim_inodes(
-	xfs_mount_t	*mp,
-	int		mode)
+	struct xfs_mount	*mp)
 {
 	int		nr_to_scan = INT_MAX;
 
-	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
+	while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+		xfs_ail_push_all_sync(mp->m_ail);
+		xfs_reclaim_inodes_ag(mp, &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.
+ * 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(
@@ -1401,7 +1230,8 @@ xfs_reclaim_inodes_nr(
 	xfs_reclaim_work_queue(mp);
 	xfs_ail_push_all(mp->m_ail);
 
-	return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
+	xfs_reclaim_inodes_ag(mp, &nr_to_scan);
+	return 0;
 }
 
 /*
@@ -1498,6 +1328,24 @@ xfs_inode_matches_eofb(
 	return true;
 }
 
+/*
+ * 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.
+ */
+void
+xfs_reclaim_worker(
+	struct work_struct *work)
+{
+	struct xfs_mount *mp = container_of(to_delayed_work(work),
+					struct xfs_mount, m_reclaim_work);
+	int		nr_to_scan = INT_MAX;
+
+	xfs_reclaim_inodes_ag(mp, &nr_to_scan);
+	xfs_reclaim_work_queue(mp);
+}
+
 STATIC int
 xfs_inode_free_eofblocks(
 	struct xfs_inode	*ip,
@@ -1574,7 +1422,7 @@ __xfs_inode_free_quota_eofblocks(
 	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQ_USER);
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_uid = VFS_I(ip)->i_uid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
@@ -1583,7 +1431,7 @@ __xfs_inode_free_quota_eofblocks(
 	}
 
 	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQ_GROUP);
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_gid = VFS_I(ip)->i_gid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_GID;