Merge branch 'xfs-free-inode-btree' into for-next

fs/xfs/xfs_ag.h

@@ -160,30 +160,38 @@ typedef struct xfs_agi {
 	 * still being referenced.
 	 */
 	__be32		agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
-
+	/*
+	 * This marks the end of logging region 1 and start of logging region 2.
+	 */
 	uuid_t		agi_uuid;	/* uuid of filesystem */
 	__be32		agi_crc;	/* crc of agi sector */
 	__be32		agi_pad32;
 	__be64		agi_lsn;	/* last write sequence */
 
+	__be32		agi_free_root; /* root of the free inode btree */
+	__be32		agi_free_level;/* levels in free inode btree */
+
 	/* structure must be padded to 64 bit alignment */
 } xfs_agi_t;
 
 #define XFS_AGI_CRC_OFF		offsetof(struct xfs_agi, agi_crc)
 
-#define	XFS_AGI_MAGICNUM	0x00000001
-#define	XFS_AGI_VERSIONNUM	0x00000002
-#define	XFS_AGI_SEQNO		0x00000004
-#define	XFS_AGI_LENGTH		0x00000008
-#define	XFS_AGI_COUNT		0x00000010
-#define	XFS_AGI_ROOT		0x00000020
-#define	XFS_AGI_LEVEL		0x00000040
-#define	XFS_AGI_FREECOUNT	0x00000080
-#define	XFS_AGI_NEWINO		0x00000100
-#define	XFS_AGI_DIRINO		0x00000200
-#define	XFS_AGI_UNLINKED	0x00000400
-#define	XFS_AGI_NUM_BITS	11
-#define	XFS_AGI_ALL_BITS	((1 << XFS_AGI_NUM_BITS) - 1)
+#define	XFS_AGI_MAGICNUM	(1 << 0)
+#define	XFS_AGI_VERSIONNUM	(1 << 1)
+#define	XFS_AGI_SEQNO		(1 << 2)
+#define	XFS_AGI_LENGTH		(1 << 3)
+#define	XFS_AGI_COUNT		(1 << 4)
+#define	XFS_AGI_ROOT		(1 << 5)
+#define	XFS_AGI_LEVEL		(1 << 6)
+#define	XFS_AGI_FREECOUNT	(1 << 7)
+#define	XFS_AGI_NEWINO		(1 << 8)
+#define	XFS_AGI_DIRINO		(1 << 9)
+#define	XFS_AGI_UNLINKED	(1 << 10)
+#define	XFS_AGI_NUM_BITS_R1	11	/* end of the 1st agi logging region */
+#define	XFS_AGI_ALL_BITS_R1	((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define	XFS_AGI_FREE_ROOT	(1 << 11)
+#define	XFS_AGI_FREE_LEVEL	(1 << 12)
+#define	XFS_AGI_NUM_BITS_R2	13
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))

fs/xfs/xfs_btree.c

@@ -43,9 +43,10 @@ kmem_zone_t	*xfs_btree_cur_zone;
  * Btree magic numbers.
  */
 static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
-	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC },
+	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+	  XFS_FIBT_MAGIC },
 	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
-	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC }
+	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
 };
 #define xfs_btree_magic(cur) \
 	xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
@@ -1115,6 +1116,7 @@ xfs_btree_set_refs(
 		xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
 		break;
 	case XFS_BTNUM_INO:
+	case XFS_BTNUM_FINO:
 		xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
 		break;
 	case XFS_BTNUM_BMAP:

fs/xfs/xfs_btree.h

@@ -62,6 +62,7 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_CNT	((xfs_btnum_t)XFS_BTNUM_CNTi)
 #define	XFS_BTNUM_BMAP	((xfs_btnum_t)XFS_BTNUM_BMAPi)
 #define	XFS_BTNUM_INO	((xfs_btnum_t)XFS_BTNUM_INOi)
+#define	XFS_BTNUM_FINO	((xfs_btnum_t)XFS_BTNUM_FINOi)
 
 /*
  * For logging record fields.
@@ -92,6 +93,7 @@ do {    \
 	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break;	\
 	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break;	\
 	case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break;	\
+	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break;	\
 	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
 	}       \
 } while (0)
@@ -105,6 +107,7 @@ do {    \
 	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
 	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
 	case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
 	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
 	}       \
 } while (0)

fs/xfs/xfs_format.h

@@ -202,6 +202,8 @@ typedef __be32 xfs_alloc_ptr_t;
  */
 #define	XFS_IBT_MAGIC		0x49414254	/* 'IABT' */
 #define	XFS_IBT_CRC_MAGIC	0x49414233	/* 'IAB3' */
+#define	XFS_FIBT_MAGIC		0x46494254	/* 'FIBT' */
+#define	XFS_FIBT_CRC_MAGIC	0x46494233	/* 'FIB3' */
 
 typedef	__uint64_t	xfs_inofree_t;
 #define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
@@ -244,7 +246,17 @@ typedef __be32 xfs_inobt_ptr_t;
  * block numbers in the AG.
  */
 #define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
-#define	XFS_PREALLOC_BLOCKS(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+#define	XFS_FIBT_BLOCK(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+
+/*
+ * The first data block of an AG depends on whether the filesystem was formatted
+ * with the finobt feature. If so, account for the finobt reserved root btree
+ * block.
+ */
+#define XFS_PREALLOC_BLOCKS(mp) \
+	(xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
+	 XFS_FIBT_BLOCK(mp) + 1 : \
+	 XFS_IBT_BLOCK(mp) + 1)
 
 
 

fs/xfs/xfs_fs.h

@@ -238,6 +238,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_LAZYSB	0x4000	/* lazy superblock counters */
 #define XFS_FSOP_GEOM_FLAGS_V5SB	0x8000	/* version 5 superblock */
 #define XFS_FSOP_GEOM_FLAGS_FTYPE	0x10000	/* inode directory types */
+#define XFS_FSOP_GEOM_FLAGS_FINOBT	0x20000	/* free inode btree */
 
 /*
  * Minimum and maximum sizes need for growth checks.

fs/xfs/xfs_fsops.c

@@ -104,7 +104,9 @@ xfs_fs_geometry(
 			(xfs_sb_version_hascrc(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_V5SB : 0) |
 			(xfs_sb_version_hasftype(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_FTYPE : 0);
+				XFS_FSOP_GEOM_FLAGS_FTYPE : 0) |
+			(xfs_sb_version_hasfinobt(&mp->m_sb) ?
+				XFS_FSOP_GEOM_FLAGS_FINOBT : 0);
 		geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ?
 				mp->m_sb.sb_logsectsize : BBSIZE;
 		geo->rtsectsize = mp->m_sb.sb_blocksize;
@@ -316,6 +318,10 @@ xfs_growfs_data_private(
 		agi->agi_dirino = cpu_to_be32(NULLAGINO);
 		if (xfs_sb_version_hascrc(&mp->m_sb))
 			uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_uuid);
+		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+			agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
+			agi->agi_free_level = cpu_to_be32(1);
+		}
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
 			agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
 
@@ -407,6 +413,34 @@ xfs_growfs_data_private(
 		xfs_buf_relse(bp);
 		if (error)
 			goto error0;
+
+		/*
+		 * FINO btree root block
+		 */
+		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+			bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AGB_TO_DADDR(mp, agno, XFS_FIBT_BLOCK(mp)),
+				BTOBB(mp->m_sb.sb_blocksize), 0,
+				&xfs_inobt_buf_ops);
+			if (!bp) {
+				error = ENOMEM;
+				goto error0;
+			}
+
+			if (xfs_sb_version_hascrc(&mp->m_sb))
+				xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC,
+						     0, 0, agno,
+						     XFS_BTREE_CRC_BLOCKS);
+			else
+				xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0,
+						     0, agno, 0);
+
+			error = xfs_bwrite(bp);
+			xfs_buf_relse(bp);
+			if (error)
+				goto error0;
+		}
+
 	}
 	xfs_trans_agblocks_delta(tp, nfree);
 	/*

fs/xfs/xfs_ialloc.c

@@ -111,6 +111,66 @@ xfs_inobt_get_rec(
 	return error;
 }
 
+/*
+ * Insert a single inobt record. Cursor must already point to desired location.
+ */
+STATIC int
+xfs_inobt_insert_rec(
+	struct xfs_btree_cur	*cur,
+	__int32_t		freecount,
+	xfs_inofree_t		free,
+	int			*stat)
+{
+	cur->bc_rec.i.ir_freecount = freecount;
+	cur->bc_rec.i.ir_free = free;
+	return xfs_btree_insert(cur, stat);
+}
+
+/*
+ * Insert records describing a newly allocated inode chunk into the inobt.
+ */
+STATIC int
+xfs_inobt_insert(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_agino_t		newino,
+	xfs_agino_t		newlen,
+	xfs_btnum_t		btnum)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t		agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agino_t		thisino;
+	int			i;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
+
+	for (thisino = newino;
+	     thisino < newino + newlen;
+	     thisino += XFS_INODES_PER_CHUNK) {
+		error = xfs_inobt_lookup(cur, thisino, XFS_LOOKUP_EQ, &i);
+		if (error) {
+			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+			return error;
+		}
+		ASSERT(i == 0);
+
+		error = xfs_inobt_insert_rec(cur, XFS_INODES_PER_CHUNK,
+					     XFS_INOBT_ALL_FREE, &i);
+		if (error) {
+			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+			return error;
+		}
+		ASSERT(i == 1);
+	}
+
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+
+	return 0;
+}
+
 /*
  * Verify that the number of free inodes in the AGI is correct.
  */
@@ -303,13 +363,10 @@ xfs_ialloc_ag_alloc(
 {
 	xfs_agi_t	*agi;		/* allocation group header */
 	xfs_alloc_arg_t	args;		/* allocation argument structure */
-	xfs_btree_cur_t	*cur;		/* inode btree cursor */
 	xfs_agnumber_t	agno;
 	int		error;
-	int		i;
 	xfs_agino_t	newino;		/* new first inode's number */
 	xfs_agino_t	newlen;		/* new number of inodes */
-	xfs_agino_t	thisino;	/* current inode number, for loop */
 	int		isaligned = 0;	/* inode allocation at stripe unit */
 					/* boundary */
 	struct xfs_perag *pag;
@@ -459,29 +516,19 @@ xfs_ialloc_ag_alloc(
 	agi->agi_newino = cpu_to_be32(newino);
 
 	/*
-	 * Insert records describing the new inode chunk into the btree.
+	 * Insert records describing the new inode chunk into the btrees.
 	 */
-	cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
-	for (thisino = newino;
-	     thisino < newino + newlen;
-	     thisino += XFS_INODES_PER_CHUNK) {
-		cur->bc_rec.i.ir_startino = thisino;
-		cur->bc_rec.i.ir_freecount = XFS_INODES_PER_CHUNK;
-		cur->bc_rec.i.ir_free = XFS_INOBT_ALL_FREE;
-		error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, &i);
-		if (error) {
-			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-			return error;
-		}
-		ASSERT(i == 0);
-		error = xfs_btree_insert(cur, &i);
-		if (error) {
-			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+				 XFS_BTNUM_INO);
+	if (error)
+		return error;
+
+	if (xfs_sb_version_hasfinobt(&args.mp->m_sb)) {
+		error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+					 XFS_BTNUM_FINO);
+		if (error)
 			return error;
-		}
-		ASSERT(i == 1);
 	}
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	/*
 	 * Log allocation group header fields
 	 */
@@ -675,13 +722,10 @@ xfs_ialloc_get_rec(
 }
 
 /*
- * Allocate an inode.
- *
- * The caller selected an AG for us, and made sure that free inodes are
- * available.
+ * Allocate an inode using the inobt-only algorithm.
  */
 STATIC int
-xfs_dialloc_ag(
+xfs_dialloc_ag_inobt(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
 	xfs_ino_t		parent,
@@ -707,7 +751,7 @@ xfs_dialloc_ag(
 	ASSERT(pag->pagi_freecount > 0);
 
  restart_pagno:
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -939,6 +983,294 @@ xfs_dialloc_ag(
 	return error;
 }
 
+/*
+ * Use the free inode btree to allocate an inode based on distance from the
+ * parent. Note that the provided cursor may be deleted and replaced.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_near(
+	xfs_agino_t			pagino,
+	struct xfs_btree_cur		**ocur,
+	struct xfs_inobt_rec_incore	*rec)
+{
+	struct xfs_btree_cur		*lcur = *ocur;	/* left search cursor */
+	struct xfs_btree_cur		*rcur;	/* right search cursor */
+	struct xfs_inobt_rec_incore	rrec;
+	int				error;
+	int				i, j;
+
+	error = xfs_inobt_lookup(lcur, pagino, XFS_LOOKUP_LE, &i);
+	if (error)
+		return error;
+
+	if (i == 1) {
+		error = xfs_inobt_get_rec(lcur, rec, &i);
+		if (error)
+			return error;
+		XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+		/*
+		 * See if we've landed in the parent inode record. The finobt
+		 * only tracks chunks with at least one free inode, so record
+		 * existence is enough.
+		 */
+		if (pagino >= rec->ir_startino &&
+		    pagino < (rec->ir_startino + XFS_INODES_PER_CHUNK))
+			return 0;
+	}
+
+	error = xfs_btree_dup_cursor(lcur, &rcur);
+	if (error)
+		return error;
+
+	error = xfs_inobt_lookup(rcur, pagino, XFS_LOOKUP_GE, &j);
+	if (error)
+		goto error_rcur;
+	if (j == 1) {
+		error = xfs_inobt_get_rec(rcur, &rrec, &j);
+		if (error)
+			goto error_rcur;
+		XFS_WANT_CORRUPTED_GOTO(j == 1, error_rcur);
+	}
+
+	XFS_WANT_CORRUPTED_GOTO(i == 1 || j == 1, error_rcur);
+	if (i == 1 && j == 1) {
+		/*
+		 * Both the left and right records are valid. Choose the closer
+		 * inode chunk to the target.
+		 */
+		if ((pagino - rec->ir_startino + XFS_INODES_PER_CHUNK - 1) >
+		    (rrec.ir_startino - pagino)) {
+			*rec = rrec;
+			xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+			*ocur = rcur;
+		} else {
+			xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+		}
+	} else if (j == 1) {
+		/* only the right record is valid */
+		*rec = rrec;
+		xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+		*ocur = rcur;
+	} else if (i == 1) {
+		/* only the left record is valid */
+		xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+	}
+
+	return 0;
+
+error_rcur:
+	xfs_btree_del_cursor(rcur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Use the free inode btree to find a free inode based on a newino hint. If
+ * the hint is NULL, find the first free inode in the AG.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_newino(
+	struct xfs_agi			*agi,
+	struct xfs_btree_cur		*cur,
+	struct xfs_inobt_rec_incore	*rec)
+{
+	int error;
+	int i;
+
+	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
+		error = xfs_inobt_lookup(cur, agi->agi_newino, XFS_LOOKUP_EQ,
+					 &i);
+		if (error)
+			return error;
+		if (i == 1) {
+			error = xfs_inobt_get_rec(cur, rec, &i);
+			if (error)
+				return error;
+			XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+			return 0;
+		}
+	}
+
+	/*
+	 * Find the first inode available in the AG.
+	 */
+	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	error = xfs_inobt_get_rec(cur, rec, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	return 0;
+}
+
+/*
+ * Update the inobt based on a modification made to the finobt. Also ensure that
+ * the records from both trees are equivalent post-modification.
+ */
+STATIC int
+xfs_dialloc_ag_update_inobt(
+	struct xfs_btree_cur		*cur,	/* inobt cursor */
+	struct xfs_inobt_rec_incore	*frec,	/* finobt record */
+	int				offset) /* inode offset */
+{
+	struct xfs_inobt_rec_incore	rec;
+	int				error;
+	int				i;
+
+	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	error = xfs_inobt_get_rec(cur, &rec, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
+				   XFS_INODES_PER_CHUNK) == 0);
+
+	rec.ir_free &= ~XFS_INOBT_MASK(offset);
+	rec.ir_freecount--;
+
+	XFS_WANT_CORRUPTED_RETURN((rec.ir_free == frec->ir_free) &&
+				  (rec.ir_freecount == frec->ir_freecount));
+
+	error = xfs_inobt_update(cur, &rec);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/*
+ * Allocate an inode using the free inode btree, if available. Otherwise, fall
+ * back to the inobt search algorithm.
+ *
+ * The caller selected an AG for us, and made sure that free inodes are
+ * available.
+ */
+STATIC int
+xfs_dialloc_ag(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_ino_t		parent,
+	xfs_ino_t		*inop)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agnumber_t			pagno = XFS_INO_TO_AGNO(mp, parent);
+	xfs_agino_t			pagino = XFS_INO_TO_AGINO(mp, parent);
+	struct xfs_perag		*pag;
+	struct xfs_btree_cur		*cur;	/* finobt cursor */
+	struct xfs_btree_cur		*icur;	/* inobt cursor */
+	struct xfs_inobt_rec_incore	rec;
+	xfs_ino_t			ino;
+	int				error;
+	int				offset;
+	int				i;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return xfs_dialloc_ag_inobt(tp, agbp, parent, inop);
+
+	pag = xfs_perag_get(mp, agno);
+
+	/*
+	 * If pagino is 0 (this is the root inode allocation) use newino.
+	 * This must work because we've just allocated some.
+	 */
+	if (!pagino)
+		pagino = be32_to_cpu(agi->agi_newino);
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error_cur;
+
+	/*
+	 * The search algorithm depends on whether we're in the same AG as the
+	 * parent. If so, find the closest available inode to the parent. If
+	 * not, consider the agi hint or find the first free inode in the AG.
+	 */
+	if (agno == pagno)
+		error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
+	else
+		error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
+	if (error)
+		goto error_cur;
+
+	offset = xfs_lowbit64(rec.ir_free);
+	ASSERT(offset >= 0);
+	ASSERT(offset < XFS_INODES_PER_CHUNK);
+	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
+				   XFS_INODES_PER_CHUNK) == 0);
+	ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
+
+	/*
+	 * Modify or remove the finobt record.
+	 */
+	rec.ir_free &= ~XFS_INOBT_MASK(offset);
+	rec.ir_freecount--;
+	if (rec.ir_freecount)
+		error = xfs_inobt_update(cur, &rec);
+	else
+		error = xfs_btree_delete(cur, &i);
+	if (error)
+		goto error_cur;
+
+	/*
+	 * The finobt has now been updated appropriately. We haven't updated the
+	 * agi and superblock yet, so we can create an inobt cursor and validate
+	 * the original freecount. If all is well, make the equivalent update to
+	 * the inobt using the finobt record and offset information.
+	 */
+	icur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
+
+	error = xfs_check_agi_freecount(icur, agi);
+	if (error)
+		goto error_icur;
+
+	error = xfs_dialloc_ag_update_inobt(icur, &rec, offset);
+	if (error)
+		goto error_icur;
+
+	/*
+	 * Both trees have now been updated. We must update the perag and
+	 * superblock before we can check the freecount for each btree.
+	 */
+	be32_add_cpu(&agi->agi_freecount, -1);
+	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
+	pag->pagi_freecount--;
+
+	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
+
+	error = xfs_check_agi_freecount(icur, agi);
+	if (error)
+		goto error_icur;
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error_icur;
+
+	xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	xfs_perag_put(pag);
+	*inop = ino;
+	return 0;
+
+error_icur:
+	xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
+error_cur:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_perag_put(pag);
+	return error;
+}
+
 /*
  * Allocate an inode on disk.
  *
@@ -1098,78 +1430,34 @@ xfs_dialloc(
 	return XFS_ERROR(error);
 }
 
-/*
- * Free disk inode.  Carefully avoids touching the incore inode, all
- * manipulations incore are the caller's responsibility.
- * The on-disk inode is not changed by this operation, only the
- * btree (free inode mask) is changed.
- */
-int
-xfs_difree(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_ino_t	inode,		/* inode to be freed */
-	xfs_bmap_free_t	*flist,		/* extents to free */
-	int		*delete,	/* set if inode cluster was deleted */
-	xfs_ino_t	*first_ino)	/* first inode in deleted cluster */
+STATIC int
+xfs_difree_inobt(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	struct xfs_buf			*agbp,
+	xfs_agino_t			agino,
+	struct xfs_bmap_free		*flist,
+	int				*delete,
+	xfs_ino_t			*first_ino,
+	struct xfs_inobt_rec_incore	*orec)
 {
-	/* REFERENCED */
-	xfs_agblock_t	agbno;	/* block number containing inode */
-	xfs_buf_t	*agbp;	/* buffer containing allocation group header */
-	xfs_agino_t	agino;	/* inode number relative to allocation group */
-	xfs_agnumber_t	agno;	/* allocation group number */
-	xfs_agi_t	*agi;	/* allocation group header */
-	xfs_btree_cur_t	*cur;	/* inode btree cursor */
-	int		error;	/* error return value */
-	int		i;	/* result code */
-	int		ilen;	/* inodes in an inode cluster */
-	xfs_mount_t	*mp;	/* mount structure for filesystem */
-	int		off;	/* offset of inode in inode chunk */
-	xfs_inobt_rec_incore_t rec;	/* btree record */
-	struct xfs_perag *pag;
-
-	mp = tp->t_mountp;
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	struct xfs_perag		*pag;
+	struct xfs_btree_cur		*cur;
+	struct xfs_inobt_rec_incore	rec;
+	int				ilen;
+	int				error;
+	int				i;
+	int				off;
 
-	/*
-	 * Break up inode number into its components.
-	 */
-	agno = XFS_INO_TO_AGNO(mp, inode);
-	if (agno >= mp->m_sb.sb_agcount)  {
-		xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
-			__func__, agno, mp->m_sb.sb_agcount);
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	agino = XFS_INO_TO_AGINO(mp, inode);
-	if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
-		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
-			__func__, (unsigned long long)inode,
-			(unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
-	if (agbno >= mp->m_sb.sb_agblocks)  {
-		xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
-			__func__, agbno, mp->m_sb.sb_agblocks);
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	/*
-	 * Get the allocation group header.
-	 */
-	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
-	if (error) {
-		xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
-			__func__, error);
-		return error;
-	}
-	agi = XFS_BUF_TO_AGI(agbp);
 	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	ASSERT(agbno < be32_to_cpu(agi->agi_length));
+	ASSERT(XFS_AGINO_TO_AGBNO(mp, agino) < be32_to_cpu(agi->agi_length));
+
 	/*
 	 * Initialize the cursor.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 
 	error = xfs_check_agi_freecount(cur, agi);
 	if (error)
@@ -1261,6 +1549,7 @@ xfs_difree(
 	if (error)
 		goto error0;
 
+	*orec = rec;
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	return 0;
 
@@ -1269,6 +1558,182 @@ xfs_difree(
 	return error;
 }
 
+/*
+ * Free an inode in the free inode btree.
+ */
+STATIC int
+xfs_difree_finobt(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	struct xfs_buf			*agbp,
+	xfs_agino_t			agino,
+	struct xfs_inobt_rec_incore	*ibtrec) /* inobt record */
+{
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	struct xfs_btree_cur		*cur;
+	struct xfs_inobt_rec_incore	rec;
+	int				offset = agino - ibtrec->ir_startino;
+	int				error;
+	int				i;
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+	error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
+	if (error)
+		goto error;
+	if (i == 0) {
+		/*
+		 * If the record does not exist in the finobt, we must have just
+		 * freed an inode in a previously fully allocated chunk. If not,
+		 * something is out of sync.
+		 */
+		XFS_WANT_CORRUPTED_GOTO(ibtrec->ir_freecount == 1, error);
+
+		error = xfs_inobt_insert_rec(cur, ibtrec->ir_freecount,
+					     ibtrec->ir_free, &i);
+		if (error)
+			goto error;
+		ASSERT(i == 1);
+
+		goto out;
+	}
+
+	/*
+	 * Read and update the existing record. We could just copy the ibtrec
+	 * across here, but that would defeat the purpose of having redundant
+	 * metadata. By making the modifications independently, we can catch
+	 * corruptions that we wouldn't see if we just copied from one record
+	 * to another.
+	 */
+	error = xfs_inobt_get_rec(cur, &rec, &i);
+	if (error)
+		goto error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+	rec.ir_free |= XFS_INOBT_MASK(offset);
+	rec.ir_freecount++;
+
+	XFS_WANT_CORRUPTED_GOTO((rec.ir_free == ibtrec->ir_free) &&
+				(rec.ir_freecount == ibtrec->ir_freecount),
+				error);
+
+	/*
+	 * The content of inobt records should always match between the inobt
+	 * and finobt. The lifecycle of records in the finobt is different from
+	 * the inobt in that the finobt only tracks records with at least one
+	 * free inode. Hence, if all of the inodes are free and we aren't
+	 * keeping inode chunks permanently on disk, remove the record.
+	 * Otherwise, update the record with the new information.
+	 */
+	if (rec.ir_freecount == mp->m_ialloc_inos &&
+	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+		error = xfs_btree_delete(cur, &i);
+		if (error)
+			goto error;
+		ASSERT(i == 1);
+	} else {
+		error = xfs_inobt_update(cur, &rec);
+		if (error)
+			goto error;
+	}
+
+out:
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error;
+
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	return 0;
+
+error:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Free disk inode.  Carefully avoids touching the incore inode, all
+ * manipulations incore are the caller's responsibility.
+ * The on-disk inode is not changed by this operation, only the
+ * btree (free inode mask) is changed.
+ */
+int
+xfs_difree(
+	struct xfs_trans	*tp,		/* transaction pointer */
+	xfs_ino_t		inode,		/* inode to be freed */
+	struct xfs_bmap_free	*flist,		/* extents to free */
+	int			*delete,/* set if inode cluster was deleted */
+	xfs_ino_t		*first_ino)/* first inode in deleted cluster */
+{
+	/* REFERENCED */
+	xfs_agblock_t		agbno;	/* block number containing inode */
+	struct xfs_buf		*agbp;	/* buffer for allocation group header */
+	xfs_agino_t		agino;	/* allocation group inode number */
+	xfs_agnumber_t		agno;	/* allocation group number */
+	int			error;	/* error return value */
+	struct xfs_mount	*mp;	/* mount structure for filesystem */
+	struct xfs_inobt_rec_incore rec;/* btree record */
+
+	mp = tp->t_mountp;
+
+	/*
+	 * Break up inode number into its components.
+	 */
+	agno = XFS_INO_TO_AGNO(mp, inode);
+	if (agno >= mp->m_sb.sb_agcount)  {
+		xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
+			__func__, agno, mp->m_sb.sb_agcount);
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	agino = XFS_INO_TO_AGINO(mp, inode);
+	if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
+		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
+			__func__, (unsigned long long)inode,
+			(unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
+	if (agbno >= mp->m_sb.sb_agblocks)  {
+		xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
+			__func__, agbno, mp->m_sb.sb_agblocks);
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	/*
+	 * Get the allocation group header.
+	 */
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+	if (error) {
+		xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
+			__func__, error);
+		return error;
+	}
+
+	/*
+	 * Fix up the inode allocation btree.
+	 */
+	error = xfs_difree_inobt(mp, tp, agbp, agino, flist, delete, first_ino,
+				 &rec);
+	if (error)
+		goto error0;
+
+	/*
+	 * Fix up the free inode btree.
+	 */
+	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+		error = xfs_difree_finobt(mp, tp, agbp, agino, &rec);
+		if (error)
+			goto error0;
+	}
+
+	return 0;
+
+error0:
+	return error;
+}
+
 STATIC int
 xfs_imap_lookup(
 	struct xfs_mount	*mp,
@@ -1300,7 +1765,7 @@ xfs_imap_lookup(
 	 * we have a record, we need to ensure it contains the inode number
 	 * we are looking up.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
@@ -1488,7 +1953,16 @@ xfs_ialloc_compute_maxlevels(
 }
 
 /*
- * Log specified fields for the ag hdr (inode section)
+ * Log specified fields for the ag hdr (inode section). The growth of the agi
+ * structure over time requires that we interpret the buffer as two logical
+ * regions delineated by the end of the unlinked list. This is due to the size
+ * of the hash table and its location in the middle of the agi.
+ *
+ * For example, a request to log a field before agi_unlinked and a field after
+ * agi_unlinked could cause us to log the entire hash table and use an excessive
+ * amount of log space. To avoid this behavior, log the region up through
+ * agi_unlinked in one call and the region after agi_unlinked through the end of
+ * the structure in another.
  */
 void
 xfs_ialloc_log_agi(
@@ -1511,6 +1985,8 @@ xfs_ialloc_log_agi(
 		offsetof(xfs_agi_t, agi_newino),
 		offsetof(xfs_agi_t, agi_dirino),
 		offsetof(xfs_agi_t, agi_unlinked),
+		offsetof(xfs_agi_t, agi_free_root),
+		offsetof(xfs_agi_t, agi_free_level),
 		sizeof(xfs_agi_t)
 	};
 #ifdef DEBUG
@@ -1519,15 +1995,30 @@ xfs_ialloc_log_agi(
 	agi = XFS_BUF_TO_AGI(bp);
 	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
 #endif
+
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
+
 	/*
-	 * Compute byte offsets for the first and last fields.
+	 * Compute byte offsets for the first and last fields in the first
+	 * region and log the agi buffer. This only logs up through
+	 * agi_unlinked.
 	 */
-	xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS, &first, &last);
+	if (fields & XFS_AGI_ALL_BITS_R1) {
+		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1,
+				  &first, &last);
+		xfs_trans_log_buf(tp, bp, first, last);
+	}
+
 	/*
-	 * Log the allocation group inode header buffer.
+	 * Mask off the bits in the first region and calculate the first and
+	 * last field offsets for any bits in the second region.
 	 */
-	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
-	xfs_trans_log_buf(tp, bp, first, last);
+	fields &= ~XFS_AGI_ALL_BITS_R1;
+	if (fields) {
+		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2,
+				  &first, &last);
+		xfs_trans_log_buf(tp, bp, first, last);
+	}
 }
 
 #ifdef DEBUG

fs/xfs/xfs_ialloc_btree.c

@@ -49,7 +49,8 @@ xfs_inobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno);
+			cur->bc_private.a.agbp, cur->bc_private.a.agno,
+			cur->bc_btnum);
 }
 
 STATIC void
@@ -66,6 +67,21 @@ xfs_inobt_set_root(
 	xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
 }
 
+STATIC void
+xfs_finobt_set_root(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*nptr,
+	int			inc)	/* level change */
+{
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+
+	agi->agi_free_root = nptr->s;
+	be32_add_cpu(&agi->agi_free_level, inc);
+	xfs_ialloc_log_agi(cur->bc_tp, agbp,
+			   XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
+}
+
 STATIC int
 xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
@@ -172,6 +188,17 @@ xfs_inobt_init_ptr_from_cur(
 	ptr->s = agi->agi_root;
 }
 
+STATIC void
+xfs_finobt_init_ptr_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
+
+	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
+	ptr->s = agi->agi_free_root;
+}
+
 STATIC __int64_t
 xfs_inobt_key_diff(
 	struct xfs_btree_cur	*cur,
@@ -202,6 +229,7 @@ xfs_inobt_verify(
 	 */
 	switch (block->bb_magic) {
 	case cpu_to_be32(XFS_IBT_CRC_MAGIC):
+	case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
 		if (!xfs_sb_version_hascrc(&mp->m_sb))
 			return false;
 		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
@@ -213,6 +241,7 @@ xfs_inobt_verify(
 			return false;
 		/* fall through */
 	case cpu_to_be32(XFS_IBT_MAGIC):
+	case cpu_to_be32(XFS_FIBT_MAGIC):
 		break;
 	default:
 		return 0;
@@ -316,6 +345,28 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 #endif
 };
 
+static const struct xfs_btree_ops xfs_finobt_ops = {
+	.rec_len		= sizeof(xfs_inobt_rec_t),
+	.key_len		= sizeof(xfs_inobt_key_t),
+
+	.dup_cursor		= xfs_inobt_dup_cursor,
+	.set_root		= xfs_finobt_set_root,
+	.alloc_block		= xfs_inobt_alloc_block,
+	.free_block		= xfs_inobt_free_block,
+	.get_minrecs		= xfs_inobt_get_minrecs,
+	.get_maxrecs		= xfs_inobt_get_maxrecs,
+	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_rec_from_key	= xfs_inobt_init_rec_from_key,
+	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
+	.key_diff		= xfs_inobt_key_diff,
+	.buf_ops		= &xfs_inobt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
+	.keys_inorder		= xfs_inobt_keys_inorder,
+	.recs_inorder		= xfs_inobt_recs_inorder,
+#endif
+};
+
 /*
  * Allocate a new inode btree cursor.
  */
@@ -324,7 +375,8 @@ xfs_inobt_init_cursor(
 	struct xfs_mount	*mp,		/* file system mount point */
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_buf		*agbp,		/* buffer for agi structure */
-	xfs_agnumber_t		agno)		/* allocation group number */
+	xfs_agnumber_t		agno,		/* allocation group number */
+	xfs_btnum_t		btnum)		/* ialloc or free ino btree */
 {
 	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
 	struct xfs_btree_cur	*cur;
@@ -333,11 +385,17 @@ xfs_inobt_init_cursor(
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
-	cur->bc_nlevels = be32_to_cpu(agi->agi_level);
-	cur->bc_btnum = XFS_BTNUM_INO;
+	cur->bc_btnum = btnum;
+	if (btnum == XFS_BTNUM_INO) {
+		cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+		cur->bc_ops = &xfs_inobt_ops;
+	} else {
+		cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+		cur->bc_ops = &xfs_finobt_ops;
+	}
+
 	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 
-	cur->bc_ops = &xfs_inobt_ops;
 	if (xfs_sb_version_hascrc(&mp->m_sb))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 

fs/xfs/xfs_ialloc_btree.h

@@ -58,7 +58,8 @@ struct xfs_mount;
 		 ((index) - 1) * sizeof(xfs_inobt_ptr_t)))
 
 extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
-		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
+		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t,
+		xfs_btnum_t);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
 #endif	/* __XFS_IALLOC_BTREE_H__ */

fs/xfs/xfs_inode.c

@@ -1811,9 +1811,33 @@ xfs_inactive_ifree(
 	int			error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
+
+	/*
+	 * The ifree transaction might need to allocate blocks for record
+	 * insertion to the finobt. We don't want to fail here at ENOSPC, so
+	 * allow ifree to dip into the reserved block pool if necessary.
+	 *
+	 * Freeing large sets of inodes generally means freeing inode chunks,
+	 * directory and file data blocks, so this should be relatively safe.
+	 * Only under severe circumstances should it be possible to free enough
+	 * inodes to exhaust the reserve block pool via finobt expansion while
+	 * at the same time not creating free space in the filesystem.
+	 *
+	 * Send a warning if the reservation does happen to fail, as the inode
+	 * now remains allocated and sits on the unlinked list until the fs is
+	 * repaired.
+	 */
+	tp->t_flags |= XFS_TRANS_RESERVE;
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree,
+				  XFS_IFREE_SPACE_RES(mp), 0);
 	if (error) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		if (error == ENOSPC) {
+			xfs_warn_ratelimited(mp,
+			"Failed to remove inode(s) from unlinked list. "
+			"Please free space, unmount and run xfs_repair.");
+		} else {
+			ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		}
 		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
 		return error;
 	}

fs/xfs/xfs_itable.c

@@ -270,7 +270,8 @@ xfs_bulkstat(
 		/*
 		 * Allocate and initialize a btree cursor for ialloc btree.
 		 */
-		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+					    XFS_BTNUM_INO);
 		irbp = irbuf;
 		irbufend = irbuf + nirbuf;
 		end_of_ag = 0;
@@ -621,7 +622,8 @@ xfs_inumbers(
 				agino = 0;
 				continue;
 			}
-			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+						    XFS_BTNUM_INO);
 			error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_GE,
 						 &tmp);
 			if (error) {

fs/xfs/xfs_log_recover.c

@@ -2138,7 +2138,9 @@ xlog_recover_validate_buf_type(
 			bp->b_ops = &xfs_allocbt_buf_ops;
 			break;
 		case XFS_IBT_CRC_MAGIC:
+		case XFS_FIBT_CRC_MAGIC:
 		case XFS_IBT_MAGIC:
+		case XFS_FIBT_MAGIC:
 			bp->b_ops = &xfs_inobt_buf_ops;
 			break;
 		case XFS_BMAP_CRC_MAGIC:

fs/xfs/xfs_sb.h

@@ -587,7 +587,9 @@ xfs_sb_has_compat_feature(
 	return (sbp->sb_features_compat & feature) != 0;
 }
 
-#define XFS_SB_FEAT_RO_COMPAT_ALL 0
+#define XFS_SB_FEAT_RO_COMPAT_FINOBT   (1 << 0)		/* free inode btree */
+#define XFS_SB_FEAT_RO_COMPAT_ALL \
+		(XFS_SB_FEAT_RO_COMPAT_FINOBT)
 #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
 static inline bool
 xfs_sb_has_ro_compat_feature(
@@ -641,6 +643,12 @@ static inline int xfs_sb_version_hasftype(struct xfs_sb *sbp)
 		 (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE));
 }
 
+static inline int xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
+{
+	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
+		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT);
+}
+
 /*
  * end of superblock version macros
  */

fs/xfs/xfs_stats.c

@@ -59,6 +59,7 @@ static int xfs_stat_proc_show(struct seq_file *m, void *v)
 		{ "abtc2",		XFSSTAT_END_ABTC_V2		},
 		{ "bmbt2",		XFSSTAT_END_BMBT_V2		},
 		{ "ibt2",		XFSSTAT_END_IBT_V2		},
+		{ "fibt2",		XFSSTAT_END_FIBT_V2		},
 		/* we print both series of quota information together */
 		{ "qm",			XFSSTAT_END_QM			},
 	};

fs/xfs/xfs_stats.h

@@ -183,7 +183,23 @@ struct xfsstats {
 	__uint32_t		xs_ibt_2_alloc;
 	__uint32_t		xs_ibt_2_free;
 	__uint32_t		xs_ibt_2_moves;
-#define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_IBT_V2+6)
+#define XFSSTAT_END_FIBT_V2		(XFSSTAT_END_IBT_V2+15)
+	__uint32_t		xs_fibt_2_lookup;
+	__uint32_t		xs_fibt_2_compare;
+	__uint32_t		xs_fibt_2_insrec;
+	__uint32_t		xs_fibt_2_delrec;
+	__uint32_t		xs_fibt_2_newroot;
+	__uint32_t		xs_fibt_2_killroot;
+	__uint32_t		xs_fibt_2_increment;
+	__uint32_t		xs_fibt_2_decrement;
+	__uint32_t		xs_fibt_2_lshift;
+	__uint32_t		xs_fibt_2_rshift;
+	__uint32_t		xs_fibt_2_split;
+	__uint32_t		xs_fibt_2_join;
+	__uint32_t		xs_fibt_2_alloc;
+	__uint32_t		xs_fibt_2_free;
+	__uint32_t		xs_fibt_2_moves;
+#define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_FIBT_V2+6)
 	__uint32_t		xs_qm_dqreclaims;
 	__uint32_t		xs_qm_dqreclaim_misses;
 	__uint32_t		xs_qm_dquot_dups;

fs/xfs/xfs_trans_resv.c

@@ -105,6 +105,47 @@ xfs_calc_inode_res(
 		 2 * XFS_BMBT_BLOCK_LEN(mp));
 }
 
+/*
+ * The free inode btree is a conditional feature and the log reservation
+ * requirements differ slightly from that of the traditional inode allocation
+ * btree. The finobt tracks records for inode chunks with at least one free
+ * inode. A record can be removed from the tree for an inode allocation
+ * or free and thus the finobt reservation is unconditional across:
+ *
+ * 	- inode allocation
+ * 	- inode free
+ * 	- inode chunk allocation
+ *
+ * The 'modify' param indicates to include the record modification scenario. The
+ * 'alloc' param indicates to include the reservation for free space btree
+ * modifications on behalf of finobt modifications. This is required only for
+ * transactions that do not already account for free space btree modifications.
+ *
+ * the free inode btree: max depth * block size
+ * the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the free inode btree entry: block size
+ */
+STATIC uint
+xfs_calc_finobt_res(
+	struct xfs_mount 	*mp,
+	int			alloc,
+	int			modify)
+{
+	uint res;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return 0;
+
+	res = xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1));
+	if (alloc)
+		res += xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1), 
+					XFS_FSB_TO_B(mp, 1));
+	if (modify)
+		res += (uint)XFS_FSB_TO_B(mp, 1);
+
+	return res;
+}
+
 /*
  * Various log reservation values.
  *
@@ -302,6 +343,7 @@ xfs_calc_remove_reservation(
  *    the superblock for the nlink flag: sector size
  *    the directory btree: (max depth + v2) * dir block size
  *    the directory inode's bmap btree: (max depth + v2) * block size
+ *    the finobt (record modification and allocation btrees)
  */
 STATIC uint
 xfs_calc_create_resv_modify(
@@ -310,7 +352,8 @@ xfs_calc_create_resv_modify(
 	return xfs_calc_inode_res(mp, 2) +
 		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
 		(uint)XFS_FSB_TO_B(mp, 1) +
-		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 1, 1);
 }
 
 /*
@@ -348,6 +391,7 @@ __xfs_calc_create_reservation(
  *    the superblock for the nlink flag: sector size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion)
  */
 STATIC uint
 xfs_calc_icreate_resv_alloc(
@@ -357,7 +401,8 @@ xfs_calc_icreate_resv_alloc(
 		mp->m_sb.sb_sectsize +
 		xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
 		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				 XFS_FSB_TO_B(mp, 1));
+				 XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 0, 0);
 }
 
 STATIC uint
@@ -425,6 +470,7 @@ xfs_calc_symlink_reservation(
  *    the on disk inode before ours in the agi hash list: inode cluster size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion, removal or modification)
  */
 STATIC uint
 xfs_calc_ifree_reservation(
@@ -439,7 +485,8 @@ xfs_calc_ifree_reservation(
 		xfs_calc_buf_res(2 + mp->m_ialloc_blks +
 				 mp->m_in_maxlevels, 0) +
 		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				 XFS_FSB_TO_B(mp, 1));
+				 XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 0, 1);
 }
 
 /*

fs/xfs/xfs_trans_space.h

@@ -47,7 +47,9 @@
 #define	XFS_DIRREMOVE_SPACE_RES(mp)	\
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define	XFS_IALLOC_SPACE_RES(mp)	\
-	((mp)->m_ialloc_blks + (mp)->m_in_maxlevels - 1)
+	((mp)->m_ialloc_blks + \
+	 (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+	  ((mp)->m_in_maxlevels - 1)))
 
 /*
  * Space reservation values for various transactions.
@@ -82,5 +84,8 @@
 	(XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
 #define	XFS_SYMLINK_SPACE_RES(mp,nl,b)	\
 	(XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b))
+#define XFS_IFREE_SPACE_RES(mp)		\
+	(xfs_sb_version_hasfinobt(&mp->m_sb) ? (mp)->m_in_maxlevels : 0)
+
 
 #endif	/* __XFS_TRANS_SPACE_H__ */

fs/xfs/xfs_types.h

@@ -134,7 +134,7 @@ typedef enum {
 
 typedef enum {
 	XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi,
-	XFS_BTNUM_MAX
+	XFS_BTNUM_FINOi, XFS_BTNUM_MAX
 } xfs_btnum_t;
 
 struct xfs_name {