xfs: use generic percpu counters for free inode counter

XFS has hand-rolled per-cpu counters for the superblock since before
there was any generic implementation. The free inode counter is not
used for any limit enforcement - the per-AG free inode counters are
used during allocation to determine if there are inode available for
allocation.

Hence we don't need any of the complexity of the hand-rolled
counters and we can simply replace them with generic per-cpu
counters similar to the inode counter.

This version introduces a xfs_mod_ifree() helper function from
Christoph Hellwig.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/libxfs/xfs_sb.c

@@ -772,6 +772,7 @@ xfs_log_sb(
 	struct xfs_buf		*bp = xfs_trans_getsb(tp, mp, 0);
 
 	mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+	mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
 
 	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);

fs/xfs/xfs_fsops.c

@@ -639,11 +639,11 @@ xfs_fs_counts(
 {
 	xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
 	cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
+	cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
 
 	spin_lock(&mp->m_sb_lock);
 	cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 	cnt->freertx = mp->m_sb.sb_frextents;
-	cnt->freeino = mp->m_sb.sb_ifree;
 	spin_unlock(&mp->m_sb_lock);
 	return 0;
 }

fs/xfs/xfs_mount.c

@@ -1114,6 +1114,20 @@ xfs_mod_icount(
 	return 0;
 }
 
+
+int
+xfs_mod_ifree(
+	struct xfs_mount	*mp,
+	int64_t			delta)
+{
+	percpu_counter_add(&mp->m_ifree, delta);
+	if (percpu_counter_compare(&mp->m_ifree, 0) < 0) {
+		ASSERT(0);
+		percpu_counter_add(&mp->m_ifree, -delta);
+		return -EINVAL;
+	}
+	return 0;
+}
 /*
  * xfs_mod_incore_sb_unlocked() is a utility routine commonly used to apply
  * a delta to a specified field in the in-core superblock.  Simply
@@ -1142,17 +1156,9 @@ xfs_mod_incore_sb_unlocked(
 	 */
 	switch (field) {
 	case XFS_SBS_ICOUNT:
-		ASSERT(0);
-		return -ENOSPC;
 	case XFS_SBS_IFREE:
-		lcounter = (long long)mp->m_sb.sb_ifree;
+		ASSERT(0);
-		lcounter += delta;
+		return -EINVAL;
-		if (lcounter < 0) {
-			ASSERT(0);
-			return -EINVAL;
-		}
-		mp->m_sb.sb_ifree = lcounter;
-		return 0;
 	case XFS_SBS_FDBLOCKS:
 		lcounter = (long long)
 			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
@@ -1502,7 +1508,6 @@ xfs_icsb_cpu_notify(
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		xfs_icsb_lock(mp);
-		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
 		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
 		xfs_icsb_unlock(mp);
 		break;
@@ -1513,15 +1518,12 @@ xfs_icsb_cpu_notify(
 		 * re-enable the counters. */
 		xfs_icsb_lock(mp);
 		spin_lock(&mp->m_sb_lock);
-		xfs_icsb_disable_counter(mp, XFS_SBS_IFREE);
 		xfs_icsb_disable_counter(mp, XFS_SBS_FDBLOCKS);
 
-		mp->m_sb.sb_ifree += cntp->icsb_ifree;
 		mp->m_sb.sb_fdblocks += cntp->icsb_fdblocks;
 
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
 
-		xfs_icsb_balance_counter_locked(mp, XFS_SBS_IFREE, 0);
 		xfs_icsb_balance_counter_locked(mp, XFS_SBS_FDBLOCKS, 0);
 		spin_unlock(&mp->m_sb_lock);
 		xfs_icsb_unlock(mp);
@@ -1544,10 +1546,14 @@ xfs_icsb_init_counters(
 	if (error)
 		return error;
 
+	error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL);
+	if (error)
+		goto free_icount;
+
 	mp->m_sb_cnts = alloc_percpu(xfs_icsb_cnts_t);
 	if (!mp->m_sb_cnts) {
-		percpu_counter_destroy(&mp->m_icount);
+		error = -ENOMEM;
-		return -ENOMEM;
+		goto free_ifree;
 	}
 
 	for_each_online_cpu(i) {
@@ -1570,6 +1576,12 @@ xfs_icsb_init_counters(
 #endif /* CONFIG_HOTPLUG_CPU */
 
 	return 0;
+
+free_ifree:
+	percpu_counter_destroy(&mp->m_ifree);
+free_icount:
+	percpu_counter_destroy(&mp->m_icount);
+	return error;
 }
 
 void
@@ -1577,6 +1589,7 @@ xfs_icsb_reinit_counters(
 	xfs_mount_t	*mp)
 {
 	percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount);
+	percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree);
 
 	xfs_icsb_lock(mp);
 	/*
@@ -1584,7 +1597,6 @@ xfs_icsb_reinit_counters(
 	 * initial balance kicks us off correctly
 	 */
 	mp->m_icsb_counters = -1;
-	xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
 	xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
 	xfs_icsb_unlock(mp);
 }
@@ -1599,6 +1611,7 @@ xfs_icsb_destroy_counters(
 	}
 
 	percpu_counter_destroy(&mp->m_icount);
+	percpu_counter_destroy(&mp->m_ifree);
 
 	mutex_destroy(&mp->m_icsb_mutex);
 }
@@ -1662,7 +1675,6 @@ xfs_icsb_count(
 
 	for_each_online_cpu(i) {
 		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
-		cnt->icsb_ifree += cntp->icsb_ifree;
 		cnt->icsb_fdblocks += cntp->icsb_fdblocks;
 	}
 
@@ -1675,7 +1687,7 @@ xfs_icsb_counter_disabled(
 	xfs_mount_t	*mp,
 	xfs_sb_field_t	field)
 {
-	ASSERT((field >= XFS_SBS_IFREE) && (field <= XFS_SBS_FDBLOCKS));
+	ASSERT(field == XFS_SBS_FDBLOCKS);
 	return test_bit(field, &mp->m_icsb_counters);
 }
 
@@ -1686,7 +1698,7 @@ xfs_icsb_disable_counter(
 {
 	xfs_icsb_cnts_t	cnt;
 
-	ASSERT((field >= XFS_SBS_IFREE) && (field <= XFS_SBS_FDBLOCKS));
+	ASSERT(field == XFS_SBS_FDBLOCKS);
 
 	/*
 	 * If we are already disabled, then there is nothing to do
@@ -1705,9 +1717,6 @@ xfs_icsb_disable_counter(
 
 		xfs_icsb_count(mp, &cnt, XFS_ICSB_LAZY_COUNT);
 		switch(field) {
-		case XFS_SBS_IFREE:
-			mp->m_sb.sb_ifree = cnt.icsb_ifree;
-			break;
 		case XFS_SBS_FDBLOCKS:
 			mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
 			break;
@@ -1729,15 +1738,12 @@ xfs_icsb_enable_counter(
 	xfs_icsb_cnts_t	*cntp;
 	int		i;
 
-	ASSERT((field >= XFS_SBS_IFREE) && (field <= XFS_SBS_FDBLOCKS));
+	ASSERT(field == XFS_SBS_FDBLOCKS);
 
 	xfs_icsb_lock_all_counters(mp);
 	for_each_online_cpu(i) {
 		cntp = per_cpu_ptr(mp->m_sb_cnts, i);
 		switch (field) {
-		case XFS_SBS_IFREE:
-			cntp->icsb_ifree = count + resid;
-			break;
 		case XFS_SBS_FDBLOCKS:
 			cntp->icsb_fdblocks = count + resid;
 			break;
@@ -1760,8 +1766,6 @@ xfs_icsb_sync_counters_locked(
 
 	xfs_icsb_count(mp, &cnt, flags);
 
-	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_IFREE))
-		mp->m_sb.sb_ifree = cnt.icsb_ifree;
 	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_FDBLOCKS))
 		mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
 }
@@ -1813,12 +1817,6 @@ xfs_icsb_balance_counter_locked(
 
 	/* update counters  - first CPU gets residual*/
 	switch (field) {
-	case XFS_SBS_IFREE:
-		count = mp->m_sb.sb_ifree;
-		resid = do_div(count, weight);
-		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
-			return;
-		break;
 	case XFS_SBS_FDBLOCKS:
 		count = mp->m_sb.sb_fdblocks;
 		resid = do_div(count, weight);
@@ -1873,14 +1871,6 @@ xfs_icsb_modify_counters(
 	}
 
 	switch (field) {
-	case XFS_SBS_IFREE:
-		lcounter = icsbp->icsb_ifree;
-		lcounter += delta;
-		if (unlikely(lcounter < 0))
-			goto balance_counter;
-		icsbp->icsb_ifree = lcounter;
-		break;
-
 	case XFS_SBS_FDBLOCKS:
 		BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0);
 

fs/xfs/xfs_mount.h

@@ -84,6 +84,7 @@ typedef struct xfs_mount {
 	struct xfs_sb		m_sb;		/* copy of fs superblock */
 	spinlock_t		m_sb_lock;	/* sb counter lock */
 	struct percpu_counter	m_icount;	/* allocated inodes counter */
+	struct percpu_counter	m_ifree;	/* free inodes counter */
 
 	struct xfs_buf		*m_sb_bp;	/* buffer for superblock */
 	char			*m_fsname;	/* filesystem name */
@@ -391,6 +392,7 @@ extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 			uint, int);
 extern int	xfs_mod_icount(struct xfs_mount *mp, int64_t delta);
+extern int	xfs_mod_ifree(struct xfs_mount *mp, int64_t delta);
 extern int	xfs_mount_log_sb(xfs_mount_t *);
 extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);

fs/xfs/xfs_super.c

@@ -1086,6 +1086,7 @@ xfs_fs_statfs(
 	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
 	__uint64_t		fakeinos, id;
 	__uint64_t		icount;
+	__uint64_t		ifree;
 	xfs_extlen_t		lsize;
 	__int64_t		ffree;
 
@@ -1098,6 +1099,7 @@ xfs_fs_statfs(
 
 	xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
 	icount = percpu_counter_sum(&mp->m_icount);
+	ifree = percpu_counter_sum(&mp->m_ifree);
 
 	spin_lock(&mp->m_sb_lock);
 	statp->f_bsize = sbp->sb_blocksize;
@@ -1118,7 +1120,7 @@ xfs_fs_statfs(
 					sbp->sb_icount);
 
 	/* make sure statp->f_ffree does not underflow */
-	ffree = statp->f_files - (icount - sbp->sb_ifree);
+	ffree = statp->f_files - (icount - ifree);
 	statp->f_ffree = max_t(__int64_t, ffree, 0);
 
 	spin_unlock(&mp->m_sb_lock);

fs/xfs/xfs_trans.c

@@ -560,8 +560,7 @@ xfs_trans_unreserve_and_mod_sb(
 	}
 
 	if (ifreedelta) {
-		error = xfs_icsb_modify_counters(mp, XFS_SBS_IFREE,
+		error = xfs_mod_ifree(mp, ifreedelta);
-						 ifreedelta, rsvd);
 		if (error)
 			goto out_undo_icount;
 	}
@@ -630,7 +629,7 @@ xfs_trans_unreserve_and_mod_sb(
 
 out_undo_ifreecount:
 	if (ifreedelta)
-		xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, -ifreedelta, rsvd);
+		xfs_mod_ifree(mp, -ifreedelta);
 out_undo_icount:
 	if (idelta)
 		xfs_mod_icount(mp, -idelta);