Merge tag 'xfs-5.2-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "Here's a big pile of new stuff for XFS for 5.2. XFS has grown the
  ability to report metadata health status to userspace after online
  fsck checks the filesystem. The online metadata checking code is (I
  really hope) feature complete with the addition of checks for the
  global fs counters, though it'll remain EXPERIMENTAL for now.

  There are also fixes for thundering herds of writeback completions and
  some other deadlocks, fixes for theoretical integer overflow attacks
  on space accounting, and removal of the long-defunct 'mntpt' option
  which was deprecated in the mid-2000s and (it turns out) totally
  broken since 2011 (and nobody complained...).

  Summary:

   - Fix some more buffer deadlocks when performing an unmount after a
     hard shutdown.

   - Fix some minor space accounting issues.

   - Fix some use after free problems.

   - Make the (undocumented) FITRIM behavior consistent with other
     filesystems.

   - Embiggen the xfs geometry ioctl's data structure.

   - Introduce a new AG geometry ioctl.

   - Introduce a new online health reporting infrastructure and ioctl
     for userspace to query a filesystem's health status.

   - Enhance online scrub and repair to update the health reports.

   - Reduce thundering herd problems when writeback io completes.

   - Fix some transaction reservation type errors.

   - Fix integer overflow problems with delayed alloc reservation
     counters.

   - Fix some problems where we would exit to userspace without
     unlocking.

   - Fix inconsistent behavior when finishing deferred ops fails.

   - Strengthen scrub to check incore data against ondisk metadata.

   - Remove long-broken mntpt mount option.

   - Add an online scrub function for the filesystem summary counters,
     which should make online metadata scrub more or less feature
     complete for now.

   - Various cleanups"

* tag 'xfs-5.2-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (38 commits)
  xfs: change some error-less functions to void types
  xfs: add online scrub for superblock counters
  xfs: don't parse the mtpt mount option
  xfs: always rejoin held resources during defer roll
  xfs: add missing error check in xfs_prepare_shift()
  xfs: scrub should check incore counters against ondisk headers
  xfs: allow scrubbers to pause background reclaim
  xfs: rename the speculative block allocation reclaim toggle functions
  xfs: track delayed allocation reservations across the filesystem
  xfs: fix broken bhold behavior in xrep_roll_ag_trans
  xfs: unlock inode when xfs_ioctl_setattr_get_trans can't get transaction
  xfs: kill the xfs_dqtrx_t typedef
  xfs: widen inode delalloc block counter to 64-bits
  xfs: widen quota block counters to 64-bit integers
  xfs: abort unaligned nowait directio early
  xfs: assert that we don't enter agfl freeing with a non-permanent transaction
  xfs: make tr_growdata a permanent transaction
  xfs: merge adjacent io completions of the same type
  xfs: remove unused m_data_workqueue
  xfs: implement per-inode writeback completion queues
  ...

59 files changed, 2085 insertions, 313 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7f96bdadc372..1dfc6df2e2bd 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -73,6 +73,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_fsmap.o \
 				   xfs_fsops.o \
 				   xfs_globals.o \
+				   xfs_health.o \
 				   xfs_icache.o \
 				   xfs_ioctl.o \
 				   xfs_iomap.o \
@@ -142,6 +143,8 @@ xfs-y				+= $(addprefix scrub/, \
 				   common.o \
 				   dabtree.o \
 				   dir.o \
+				   fscounters.o \
+				   health.o \
 				   ialloc.o \
 				   inode.o \
 				   parent.o \
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1ef8acf35e7d..b0c89f54d1bb 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -19,6 +19,8 @@
 #include "xfs_ialloc.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+#include "xfs_health.h"
 
 static struct xfs_buf *
 xfs_get_aghdr_buf(
@@ -461,3 +463,55 @@ xfs_ag_extend_space(
 				len, &XFS_RMAP_OINFO_SKIP_UPDATE,
 				XFS_AG_RESV_NONE);
 }
+
+/* Retrieve AG geometry. */
+int
+xfs_ag_get_geometry(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	struct xfs_ag_geometry	*ageo)
+{
+	struct xfs_buf		*agi_bp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_agi		*agi;
+	struct xfs_agf		*agf;
+	struct xfs_perag	*pag;
+	unsigned int		freeblks;
+	int			error;
+
+	if (agno >= mp->m_sb.sb_agcount)
+		return -EINVAL;
+
+	/* Lock the AG headers. */
+	error = xfs_ialloc_read_agi(mp, NULL, agno, &agi_bp);
+	if (error)
+		return error;
+	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp);
+	if (error)
+		goto out_agi;
+	pag = xfs_perag_get(mp, agno);
+
+	/* Fill out form. */
+	memset(ageo, 0, sizeof(*ageo));
+	ageo->ag_number = agno;
+
+	agi = XFS_BUF_TO_AGI(agi_bp);
+	ageo->ag_icount = be32_to_cpu(agi->agi_count);
+	ageo->ag_ifree = be32_to_cpu(agi->agi_freecount);
+
+	agf = XFS_BUF_TO_AGF(agf_bp);
+	ageo->ag_length = be32_to_cpu(agf->agf_length);
+	freeblks = pag->pagf_freeblks +
+		   pag->pagf_flcount +
+		   pag->pagf_btreeblks -
+		   xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE);
+	ageo->ag_freeblks = freeblks;
+	xfs_ag_geom_health(pag, ageo);
+
+	/* Release resources. */
+	xfs_perag_put(pag);
+	xfs_buf_relse(agf_bp);
+out_agi:
+	xfs_buf_relse(agi_bp);
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 412702e23f61..5166322807e7 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -26,5 +26,7 @@ struct aghdr_init_data {
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
 int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
 			struct aghdr_init_data *id, xfs_extlen_t len);
+int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno,
+			struct xfs_ag_geometry *ageo);
 
 #endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index bc3367b8b7bb..a9ff3cf82cce 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2042,6 +2042,7 @@ xfs_alloc_space_available(
 	xfs_extlen_t		alloc_len, longest;
 	xfs_extlen_t		reservation; /* blocks that are still reserved */
 	int			available;
+	xfs_extlen_t		agflcount;
 
 	if (flags & XFS_ALLOC_FLAG_FREEING)
 		return true;
@@ -2054,8 +2055,13 @@ xfs_alloc_space_available(
 	if (longest < alloc_len)
 		return false;
 
-	/* do we have enough free space remaining for the allocation? */
-	available = (int)(pag->pagf_freeblks + pag->pagf_flcount -
+	/*
+	 * Do we have enough free space remaining for the allocation? Don't
+	 * account extra agfl blocks because we are about to defer free them,
+	 * making them unavailable until the current transaction commits.
+	 */
+	agflcount = min_t(xfs_extlen_t, pag->pagf_flcount, min_free);
+	available = (int)(pag->pagf_freeblks + agflcount -
 			  reservation - min_free - args->minleft);
 	if (available < (int)max(args->total, alloc_len))
 		return false;
@@ -2237,6 +2243,9 @@ xfs_alloc_fix_freelist(
 	xfs_extlen_t		need;	/* total blocks needed in freelist */
 	int			error = 0;
 
+	/* deferred ops (AGFL block frees) require permanent transactions */
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
 	if (!pag->pagf_init) {
 		error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 2dd9ee2a2e08..c441f41f14e8 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -224,10 +224,10 @@ xfs_attr_try_sf_addname(
  */
 int
 xfs_attr_set_args(
-	struct xfs_da_args	*args,
-	struct xfs_buf          **leaf_bp)
+	struct xfs_da_args	*args)
 {
 	struct xfs_inode	*dp = args->dp;
+	struct xfs_buf          *leaf_bp = NULL;
 	int			error;
 
 	/*
@@ -255,7 +255,7 @@ xfs_attr_set_args(
 		 * It won't fit in the shortform, transform to a leaf block.
 		 * GROT: another possible req'mt for a double-split btree op.
 		 */
-		error = xfs_attr_shortform_to_leaf(args, leaf_bp);
+		error = xfs_attr_shortform_to_leaf(args, &leaf_bp);
 		if (error)
 			return error;
 
@@ -263,23 +263,16 @@ xfs_attr_set_args(
 		 * Prevent the leaf buffer from being unlocked so that a
 		 * concurrent AIL push cannot grab the half-baked leaf
 		 * buffer and run into problems with the write verifier.
+		 * Once we're done rolling the transaction we can release
+		 * the hold and add the attr to the leaf.
 		 */
-		xfs_trans_bhold(args->trans, *leaf_bp);
-
+		xfs_trans_bhold(args->trans, leaf_bp);
 		error = xfs_defer_finish(&args->trans);
-		if (error)
-			return error;
-
-		/*
-		 * Commit the leaf transformation.  We'll need another
-		 * (linked) transaction to add the new attribute to the
-		 * leaf.
-		 */
-		error = xfs_trans_roll_inode(&args->trans, dp);
-		if (error)
+		xfs_trans_bhold_release(args->trans, leaf_bp);
+		if (error) {
+			xfs_trans_brelse(args->trans, leaf_bp);
 			return error;
-		xfs_trans_bjoin(args->trans, *leaf_bp);
-		*leaf_bp = NULL;
+		}
 	}
 
 	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
@@ -322,7 +315,6 @@ xfs_attr_set(
 	int			flags)
 {
 	struct xfs_mount	*mp = dp->i_mount;
-	struct xfs_buf		*leaf_bp = NULL;
 	struct xfs_da_args	args;
 	struct xfs_trans_res	tres;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
@@ -381,9 +373,9 @@ xfs_attr_set(
 		goto out_trans_cancel;
 
 	xfs_trans_ijoin(args.trans, dp, 0);
-	error = xfs_attr_set_args(&args, &leaf_bp);
+	error = xfs_attr_set_args(&args);
 	if (error)
-		goto out_release_leaf;
+		goto out_trans_cancel;
 	if (!args.trans) {
 		/* shortform attribute has already been committed */
 		goto out_unlock;
@@ -408,9 +400,6 @@ out_unlock:
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 	return error;
 
-out_release_leaf:
-	if (leaf_bp)
-		xfs_trans_brelse(args.trans, leaf_bp);
 out_trans_cancel:
 	if (args.trans)
 		xfs_trans_cancel(args.trans);
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 2297d8467666..3b0dce06e454 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -140,7 +140,7 @@ int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
 		 unsigned char *value, int *valuelenp, int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 		 unsigned char *value, int valuelen, int flags);
-int xfs_attr_set_args(struct xfs_da_args *args, struct xfs_buf **leaf_bp);
+int xfs_attr_set_args(struct xfs_da_args *args);
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_remove_args(struct xfs_da_args *args);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4637ae1ae91c..356ebd1cbe82 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2009,6 +2009,9 @@ xfs_bmap_add_extent_delay_real(
 			goto done;
 	}
 
+	if (da_new != da_old)
+		xfs_mod_delalloc(mp, (int64_t)da_new - da_old);
+
 	if (bma->cur) {
 		da_new += bma->cur->bc_private.b.allocated;
 		bma->cur->bc_private.b.allocated = 0;
@@ -2640,6 +2643,7 @@ xfs_bmap_add_extent_hole_delay(
 		/*
 		 * Nothing to do for disk quota accounting here.
 		 */
+		xfs_mod_delalloc(ip->i_mount, (int64_t)newlen - oldlen);
 	}
 }
 
@@ -3352,8 +3356,10 @@ xfs_bmap_btalloc_accounting(
 		 * already have quota reservation and there's nothing to do
 		 * yet.
 		 */
-		if (ap->wasdel)
+		if (ap->wasdel) {
+			xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
 			return;
+		}
 
 		/*
 		 * Otherwise, we've allocated blocks in a hole. The transaction
@@ -3372,8 +3378,10 @@ xfs_bmap_btalloc_accounting(
 	/* data/attr fork only */
 	ap->ip->i_d.di_nblocks += args->len;
 	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
-	if (ap->wasdel)
+	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= args->len;
+		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+	}
 	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
 		args->len);
@@ -3969,6 +3977,7 @@ xfs_bmapi_reserve_delalloc(
 
 
 	ip->i_delayed_blks += alen;
+	xfs_mod_delalloc(ip->i_mount, alen + indlen);
 
 	got->br_startoff = aoff;
 	got->br_startblock = nullstartblock(indlen);
@@ -4840,8 +4849,10 @@ xfs_bmap_del_extent_delay(
 	da_diff = da_old - da_new;
 	if (!isrt)
 		da_diff += del->br_blockcount;
-	if (da_diff)
+	if (da_diff) {
 		xfs_mod_fdblocks(mp, da_diff, false);
+		xfs_mod_delalloc(mp, -da_diff);
+	}
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 94f00427de98..1c6bf2105939 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -274,13 +274,15 @@ xfs_defer_trans_roll(
 
 	trace_xfs_defer_trans_roll(tp, _RET_IP_);
 
-	/* Roll the transaction. */
+	/*
+	 * Roll the transaction.  Rolling always given a new transaction (even
+	 * if committing the old one fails!) to hand back to the caller, so we
+	 * join the held resources to the new transaction so that we always
+	 * return with the held resources joined to @tpp, no matter what
+	 * happened.
+	 */
 	error = xfs_trans_roll(tpp);
 	tp = *tpp;
-	if (error) {
-		trace_xfs_defer_trans_roll_error(tp, error);
-		return error;
-	}
 
 	/* Rejoin the joined inodes. */
 	for (i = 0; i < ipcount; i++)
@@ -292,6 +294,8 @@ xfs_defer_trans_roll(
 		xfs_trans_bhold(tp, bplist[i]);
 	}
 
+	if (error)
+		trace_xfs_defer_trans_roll_error(tp, error);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index fb5bd9a804f6..88fa11071f9f 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -110,7 +110,7 @@ xfs_dqblk_verify(
 /*
  * Do some primitive error checking on ondisk dquot data structures.
  */
-int
+void
 xfs_dqblk_repair(
 	struct xfs_mount	*mp,
 	struct xfs_dqblk	*dqb,
@@ -133,8 +133,6 @@ xfs_dqblk_repair(
 		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
 	}
-
-	return 0;
 }
 
 STATIC bool
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index f3aa59302fef..e7382c780ed7 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -124,7 +124,7 @@ typedef struct xfs_flock64 {
 /*
  * Output for XFS_IOC_FSGEOMETRY_V1
  */
-typedef struct xfs_fsop_geom_v1 {
+struct xfs_fsop_geom_v1 {
 	__u32		blocksize;	/* filesystem (data) block size */
 	__u32		rtextsize;	/* realtime extent size		*/
 	__u32		agblocks;	/* fsblocks in an AG		*/
@@ -145,12 +145,39 @@ typedef struct xfs_fsop_geom_v1 {
 	__u32		logsectsize;	/* log sector size, bytes	*/
 	__u32		rtsectsize;	/* realtime sector size, bytes	*/
 	__u32		dirblocksize;	/* directory block size, bytes	*/
-} xfs_fsop_geom_v1_t;
+};
+
+/*
+ * Output for XFS_IOC_FSGEOMETRY_V4
+ */
+struct xfs_fsop_geom_v4 {
+	__u32		blocksize;	/* filesystem (data) block size */
+	__u32		rtextsize;	/* realtime extent size		*/
+	__u32		agblocks;	/* fsblocks in an AG		*/
+	__u32		agcount;	/* number of allocation groups	*/
+	__u32		logblocks;	/* fsblocks in the log		*/
+	__u32		sectsize;	/* (data) sector size, bytes	*/
+	__u32		inodesize;	/* inode size in bytes		*/
+	__u32		imaxpct;	/* max allowed inode space(%)	*/
+	__u64		datablocks;	/* fsblocks in data subvolume	*/
+	__u64		rtblocks;	/* fsblocks in realtime subvol	*/
+	__u64		rtextents;	/* rt extents in realtime subvol*/
+	__u64		logstart;	/* starting fsblock of the log	*/
+	unsigned char	uuid[16];	/* unique id of the filesystem	*/
+	__u32		sunit;		/* stripe unit, fsblocks	*/
+	__u32		swidth;		/* stripe width, fsblocks	*/
+	__s32		version;	/* structure version		*/
+	__u32		flags;		/* superblock version flags	*/
+	__u32		logsectsize;	/* log sector size, bytes	*/
+	__u32		rtsectsize;	/* realtime sector size, bytes	*/
+	__u32		dirblocksize;	/* directory block size, bytes	*/
+	__u32		logsunit;	/* log stripe unit, bytes	*/
+};
 
 /*
  * Output for XFS_IOC_FSGEOMETRY
  */
-typedef struct xfs_fsop_geom {
+struct xfs_fsop_geom {
 	__u32		blocksize;	/* filesystem (data) block size */
 	__u32		rtextsize;	/* realtime extent size		*/
 	__u32		agblocks;	/* fsblocks in an AG		*/
@@ -171,8 +198,18 @@ typedef struct xfs_fsop_geom {
 	__u32		logsectsize;	/* log sector size, bytes	*/
 	__u32		rtsectsize;	/* realtime sector size, bytes	*/
 	__u32		dirblocksize;	/* directory block size, bytes	*/
-	__u32		logsunit;	/* log stripe unit, bytes */
-} xfs_fsop_geom_t;
+	__u32		logsunit;	/* log stripe unit, bytes	*/
+	uint32_t	sick;		/* o: unhealthy fs & rt metadata */
+	uint32_t	checked;	/* o: checked fs & rt metadata	*/
+	__u64		reserved[17];	/* reserved space		*/
+};
+
+#define XFS_FSOP_GEOM_SICK_COUNTERS	(1 << 0)  /* summary counters */
+#define XFS_FSOP_GEOM_SICK_UQUOTA	(1 << 1)  /* user quota */
+#define XFS_FSOP_GEOM_SICK_GQUOTA	(1 << 2)  /* group quota */
+#define XFS_FSOP_GEOM_SICK_PQUOTA	(1 << 3)  /* project quota */
+#define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
+#define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
@@ -188,28 +225,30 @@ typedef struct xfs_fsop_resblks {
 	__u64  resblks_avail;
 } xfs_fsop_resblks_t;
 
-#define XFS_FSOP_GEOM_VERSION	0
-
-#define XFS_FSOP_GEOM_FLAGS_ATTR	0x0001	/* attributes in use	*/
-#define XFS_FSOP_GEOM_FLAGS_NLINK	0x0002	/* 32-bit nlink values	*/
-#define XFS_FSOP_GEOM_FLAGS_QUOTA	0x0004	/* quotas enabled	*/
-#define XFS_FSOP_GEOM_FLAGS_IALIGN	0x0008	/* inode alignment	*/
-#define XFS_FSOP_GEOM_FLAGS_DALIGN	0x0010	/* large data alignment */
-#define XFS_FSOP_GEOM_FLAGS_SHARED	0x0020	/* read-only shared	*/
-#define XFS_FSOP_GEOM_FLAGS_EXTFLG	0x0040	/* special extent flag	*/
-#define XFS_FSOP_GEOM_FLAGS_DIRV2	0x0080	/* directory version 2	*/
-#define XFS_FSOP_GEOM_FLAGS_LOGV2	0x0100	/* log format version 2	*/
-#define XFS_FSOP_GEOM_FLAGS_SECTOR	0x0200	/* sector sizes >1BB	*/
-#define XFS_FSOP_GEOM_FLAGS_ATTR2	0x0400	/* inline attributes rework */
-#define XFS_FSOP_GEOM_FLAGS_PROJID32	0x0800	/* 32-bit project IDs	*/
-#define XFS_FSOP_GEOM_FLAGS_DIRV2CI	0x1000	/* ASCII only CI names	*/
-#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 */
-#define XFS_FSOP_GEOM_FLAGS_SPINODES	0x40000	/* sparse inode chunks	*/
-#define XFS_FSOP_GEOM_FLAGS_RMAPBT	0x80000	/* reverse mapping btree */
-#define XFS_FSOP_GEOM_FLAGS_REFLINK	0x100000 /* files can share blocks */
+#define XFS_FSOP_GEOM_VERSION		0
+#define XFS_FSOP_GEOM_VERSION_V5	5
+
+#define XFS_FSOP_GEOM_FLAGS_ATTR	(1 << 0)  /* attributes in use	   */
+#define XFS_FSOP_GEOM_FLAGS_NLINK	(1 << 1)  /* 32-bit nlink values   */
+#define XFS_FSOP_GEOM_FLAGS_QUOTA	(1 << 2)  /* quotas enabled	   */
+#define XFS_FSOP_GEOM_FLAGS_IALIGN	(1 << 3)  /* inode alignment	   */
+#define XFS_FSOP_GEOM_FLAGS_DALIGN	(1 << 4)  /* large data alignment  */
+#define XFS_FSOP_GEOM_FLAGS_SHARED	(1 << 5)  /* read-only shared	   */
+#define XFS_FSOP_GEOM_FLAGS_EXTFLG	(1 << 6)  /* special extent flag   */
+#define XFS_FSOP_GEOM_FLAGS_DIRV2	(1 << 7)  /* directory version 2   */
+#define XFS_FSOP_GEOM_FLAGS_LOGV2	(1 << 8)  /* log format version 2  */
+#define XFS_FSOP_GEOM_FLAGS_SECTOR	(1 << 9)  /* sector sizes >1BB	   */
+#define XFS_FSOP_GEOM_FLAGS_ATTR2	(1 << 10) /* inline attributes rework */
+#define XFS_FSOP_GEOM_FLAGS_PROJID32	(1 << 11) /* 32-bit project IDs	   */
+#define XFS_FSOP_GEOM_FLAGS_DIRV2CI	(1 << 12) /* ASCII only CI names   */
+	/*  -- Do not use --		(1 << 13)    SGI parent pointers   */
+#define XFS_FSOP_GEOM_FLAGS_LAZYSB	(1 << 14) /* lazy superblock counters */
+#define XFS_FSOP_GEOM_FLAGS_V5SB	(1 << 15) /* version 5 superblock  */
+#define XFS_FSOP_GEOM_FLAGS_FTYPE	(1 << 16) /* inode directory types */
+#define XFS_FSOP_GEOM_FLAGS_FINOBT	(1 << 17) /* free inode btree	   */
+#define XFS_FSOP_GEOM_FLAGS_SPINODES	(1 << 18) /* sparse inode chunks   */
+#define XFS_FSOP_GEOM_FLAGS_RMAPBT	(1 << 19) /* reverse mapping btree */
+#define XFS_FSOP_GEOM_FLAGS_REFLINK	(1 << 20) /* files can share blocks */
 
 /*
  * Minimum and maximum sizes need for growth checks.
@@ -238,6 +277,31 @@ typedef struct xfs_fsop_resblks {
 			 (s)->sb_agblocks + XFS_MIN_AG_BLOCKS)
 
 /*
+ * Output for XFS_IOC_AG_GEOMETRY
+ */
+struct xfs_ag_geometry {
+	uint32_t	ag_number;	/* i/o: AG number */
+	uint32_t	ag_length;	/* o: length in blocks */
+	uint32_t	ag_freeblks;	/* o: free space */
+	uint32_t	ag_icount;	/* o: inodes allocated */
+	uint32_t	ag_ifree;	/* o: inodes free */
+	uint32_t	ag_sick;	/* o: sick things in ag */
+	uint32_t	ag_checked;	/* o: checked metadata in ag */
+	uint32_t	ag_reserved32;	/* o: zero */
+	uint64_t	ag_reserved[12];/* o: zero */
+};
+#define XFS_AG_GEOM_SICK_SB	(1 << 0)  /* superblock */
+#define XFS_AG_GEOM_SICK_AGF	(1 << 1)  /* AGF header */
+#define XFS_AG_GEOM_SICK_AGFL	(1 << 2)  /* AGFL header */
+#define XFS_AG_GEOM_SICK_AGI	(1 << 3)  /* AGI header */
+#define XFS_AG_GEOM_SICK_BNOBT	(1 << 4)  /* free space by block */
+#define XFS_AG_GEOM_SICK_CNTBT	(1 << 5)  /* free space by length */
+#define XFS_AG_GEOM_SICK_INOBT	(1 << 6)  /* inode index */
+#define XFS_AG_GEOM_SICK_FINOBT	(1 << 7)  /* free inode index */
+#define XFS_AG_GEOM_SICK_RMAPBT	(1 << 8)  /* reverse mappings */
+#define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9)  /* reference counts */
+
+/*
  * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT
  */
 typedef struct xfs_growfs_data {
@@ -285,13 +349,25 @@ typedef struct xfs_bstat {
 #define	bs_projid	bs_projid_lo	/* (previously just bs_projid)	*/
 	__u16		bs_forkoff;	/* inode fork offset in bytes	*/
 	__u16		bs_projid_hi;	/* higher part of project id	*/
-	unsigned char	bs_pad[6];	/* pad space, unused		*/
+	uint16_t	bs_sick;	/* sick inode metadata		*/
+	uint16_t	bs_checked;	/* checked inode metadata	*/
+	unsigned char	bs_pad[2];	/* pad space, unused		*/
 	__u32		bs_cowextsize;	/* cow extent size		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
 } xfs_bstat_t;
 
+/* bs_sick flags */
+#define XFS_BS_SICK_INODE	(1 << 0)  /* inode core */
+#define XFS_BS_SICK_BMBTD	(1 << 1)  /* data fork */
+#define XFS_BS_SICK_BMBTA	(1 << 2)  /* attr fork */
+#define XFS_BS_SICK_BMBTC	(1 << 3)  /* cow fork */