[XFS] Lazy Superblock Counters

When we have a couple of hundred transactions on the fly at once, they all
typically modify the on disk superblock in some way.
create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify
free block counts.

When these counts are modified in a transaction, they must eventually lock
the superblock buffer and apply the mods. The buffer then remains locked
until the transaction is committed into the incore log buffer. The result
of this is that with enough transactions on the fly the incore superblock
buffer becomes a bottleneck.

The result of contention on the incore superblock buffer is that
transaction rates fall - the more pressure that is put on the superblock
buffer, the slower things go.

The key to removing the contention is to not require the superblock fields
in question to be locked. We do that by not marking the superblock dirty
in the transaction. IOWs, we modify the incore superblock but do not
modify the cached superblock buffer. In short, we do not log superblock
modifications to critical fields in the superblock on every transaction.
In fact we only do it just before we write the superblock to disk every
sync period or just before unmount.

This creates an interesting problem - if we don't log or write out the
fields in every transaction, then how do the values get recovered after a
crash? the answer is simple - we keep enough duplicate, logged information
in other structures that we can reconstruct the correct count after log
recovery has been performed.

It is the AGF and AGI structures that contain the duplicate information;
after recovery, we walk every AGI and AGF and sum their individual
counters to get the correct value, and we do a transaction into the log to
correct them. An optimisation of this is that if we have a clean unmount
record, we know the value in the superblock is correct, so we can avoid
the summation walk under normal conditions and so mount/recovery times do
not change under normal operation.

One wrinkle that was discovered during development was that the blocks
used in the freespace btrees are never accounted for in the AGF counters.
This was once a valid optimisation to make; when the filesystem is full,
the free space btrees are empty and consume no space. Hence when it
matters, the "accounting" is correct. But that means the when we do the
AGF summations, we would not have a correct count and xfs_check would
complain. Hence a new counter was added to track the number of blocks used
by the free space btrees. This is an *on-disk format change*.

As a result of this, lazy superblock counters are a mkfs option and at the
moment on linux there is no way to convert an old filesystem. This is
possible - xfs_db can be used to twiddle the right bits and then
xfs_repair will do the format conversion for you. Similarly, you can
convert backwards as well. At some point we'll add functionality to
xfs_admin to do the bit twiddling easily....

SGI-PV: 964999
SGI-Modid: xfs-linux-melb:xfs-kern:28652a

Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Tim Shimmin <tes@sgi.com>

18 files changed, 337 insertions, 54 deletions

diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index bf9a9d5909b..05f188ed120 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -547,7 +547,8 @@ vfs_sync_worker(
 
 	if (!(vfsp->vfs_flag & VFS_RDONLY))
 		error = bhv_vfs_sync(vfsp, SYNC_FSDATA | SYNC_BDFLUSH | \
-					SYNC_ATTR | SYNC_REFCACHE, NULL);
+					SYNC_ATTR | SYNC_REFCACHE | SYNC_SUPER,
+					NULL);
 	vfsp->vfs_sync_seq++;
 	wake_up(&vfsp->vfs_wait_single_sync_task);
 }
diff --git a/fs/xfs/linux-2.6/xfs_vfs.h b/fs/xfs/linux-2.6/xfs_vfs.h
index e2c2ce98ab5..cb7b0d62fb9 100644
--- a/fs/xfs/linux-2.6/xfs_vfs.h
+++ b/fs/xfs/linux-2.6/xfs_vfs.h
@@ -92,6 +92,7 @@ typedef enum {
 #define SYNC_REFCACHE		0x0040  /* prune some of the nfs ref cache */
 #define SYNC_REMOUNT		0x0080  /* remount readonly, no dummy LRs */
 #define SYNC_IOWAIT		0x0100  /* wait for all I/O to complete */
+#define SYNC_SUPER		0x0200  /* flush superblock to disk */
 
 #define SHUTDOWN_META_IO_ERROR	0x0001	/* write attempt to metadata failed */
 #define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 9ece7f87ec5..b1dd0029c60 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -68,6 +68,7 @@ typedef struct xfs_agf {
 	__be32		agf_flcount;	/* count of blocks in freelist */
 	__be32		agf_freeblks;	/* total free blocks */
 	__be32		agf_longest;	/* longest free space */
+	__be32		agf_btreeblks;	/* # of blocks held in AGF btrees */
 } xfs_agf_t;
 
 #define	XFS_AGF_MAGICNUM	0x00000001
@@ -81,7 +82,8 @@ typedef struct xfs_agf {
 #define	XFS_AGF_FLCOUNT		0x00000100
 #define	XFS_AGF_FREEBLKS	0x00000200
 #define	XFS_AGF_LONGEST		0x00000400
-#define	XFS_AGF_NUM_BITS	11
+#define	XFS_AGF_BTREEBLKS	0x00000800
+#define	XFS_AGF_NUM_BITS	12
 #define	XFS_AGF_ALL_BITS	((1 << XFS_AGF_NUM_BITS) - 1)
 
 /* disk block (xfs_daddr_t) in the AG */
@@ -186,11 +188,13 @@ typedef struct xfs_perag
 	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
+	__uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
 	xfs_agino_t	pagi_freecount;	/* number of free inodes */
+	xfs_agino_t	pagi_count;	/* number of allocated inodes */
+	int		pagb_count;	/* pagb slots in use */
 #ifdef __KERNEL__
 	lock_t		pagb_lock;	/* lock for pagb_list */
 #endif
-	int		pagb_count;	/* pagb slots in use */
 	xfs_perag_busy_t *pagb_list;	/* unstable blocks */
 } xfs_perag_t;
 
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 8e9a40aa0cd..98f95d4c4bc 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1447,7 +1447,8 @@ xfs_alloc_ag_vextent_small(
 	else if (args->minlen == 1 && args->alignment == 1 && !args->isfl &&
 		 (be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_flcount)
 		  > args->minleft)) {
-		if ((error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno)))
+		error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0);
+		if (error)
 			goto error0;
 		if (fbno != NULLAGBLOCK) {
 			if (args->userdata) {
@@ -1923,7 +1924,8 @@ xfs_alloc_fix_freelist(
 	while (be32_to_cpu(agf->agf_flcount) > need) {
 		xfs_buf_t	*bp;
 
-		if ((error = xfs_alloc_get_freelist(tp, agbp, &bno)))
+		error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);
+		if (error)
 			return error;
 		if ((error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1, 1)))
 			return error;
@@ -1973,8 +1975,9 @@ xfs_alloc_fix_freelist(
 		 * Put each allocated block on the list.
 		 */
 		for (bno = targs.agbno; bno < targs.agbno + targs.len; bno++) {
-			if ((error = xfs_alloc_put_freelist(tp, agbp, agflbp,
-					bno)))
+			error = xfs_alloc_put_freelist(tp, agbp,
+							agflbp, bno, 0);
+			if (error)
 				return error;
 		}
 	}
@@ -1991,13 +1994,15 @@ int				/* error */
 xfs_alloc_get_freelist(
 	xfs_trans_t	*tp,	/* transaction pointer */
 	xfs_buf_t	*agbp,	/* buffer containing the agf structure */
-	xfs_agblock_t	*bnop)	/* block address retrieved from freelist */
+	xfs_agblock_t	*bnop,	/* block address retrieved from freelist */
+	int		btreeblk) /* destination is a AGF btree */
 {
 	xfs_agf_t	*agf;	/* a.g. freespace structure */
 	xfs_agfl_t	*agfl;	/* a.g. freelist structure */
 	xfs_buf_t	*agflbp;/* buffer for a.g. freelist structure */
 	xfs_agblock_t	bno;	/* block number returned */
 	int		error;
+	int		logflags;
 #ifdef XFS_ALLOC_TRACE
 	static char	fname[] = "xfs_alloc_get_freelist";
 #endif
@@ -2032,8 +2037,16 @@ xfs_alloc_get_freelist(
 	be32_add(&agf->agf_flcount, -1);
 	xfs_trans_agflist_delta(tp, -1);
 	pag->pagf_flcount--;
-	TRACE_MODAGF(NULL, agf, XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT);
-	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT);
+
+	logflags = XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT;
+	if (btreeblk) {
+		be32_add(&agf->agf_btreeblks, 1);
+		pag->pagf_btreeblks++;
+		logflags |= XFS_AGF_BTREEBLKS;
+	}
+
+	TRACE_MODAGF(NULL, agf, logflags);
+	xfs_alloc_log_agf(tp, agbp, logflags);
 	*bnop = bno;
 
 	/*
@@ -2071,6 +2084,7 @@ xfs_alloc_log_agf(
 		offsetof(xfs_agf_t, agf_flcount),
 		offsetof(xfs_agf_t, agf_freeblks),
 		offsetof(xfs_agf_t, agf_longest),
+		offsetof(xfs_agf_t, agf_btreeblks),
 		sizeof(xfs_agf_t)
 	};
 
@@ -2106,12 +2120,14 @@ xfs_alloc_put_freelist(
 	xfs_trans_t		*tp,	/* transaction pointer */
 	xfs_buf_t		*agbp,	/* buffer for a.g. freelist header */
 	xfs_buf_t		*agflbp,/* buffer for a.g. free block array */
-	xfs_agblock_t		bno)	/* block being freed */
+	xfs_agblock_t		bno,	/* block being freed */
+	int			btreeblk) /* block came from a AGF btree */
 {
 	xfs_agf_t		*agf;	/* a.g. freespace structure */
 	xfs_agfl_t		*agfl;	/* a.g. free block array */
 	__be32			*blockp;/* pointer to array entry */
 	int			error;
+	int			logflags;
 #ifdef XFS_ALLOC_TRACE
 	static char		fname[] = "xfs_alloc_put_freelist";
 #endif
@@ -2132,11 +2148,22 @@ xfs_alloc_put_freelist(
 	be32_add(&agf->agf_flcount, 1);
 	xfs_trans_agflist_delta(tp, 1);
 	pag->pagf_flcount++;
+
+	logflags = XFS_AGF_FLLAST | XFS_AGF_FLCOUNT;
+	if (btreeblk) {
+		be32_add(&agf->agf_btreeblks, -1);
+		pag->pagf_btreeblks--;
+		logflags |= XFS_AGF_BTREEBLKS;
+	}
+
+	TRACE_MODAGF(NULL, agf, logflags);
+	xfs_alloc_log_agf(tp, agbp, logflags);
+
 	ASSERT(be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp));
 	blockp = &agfl->agfl_bno[be32_to_cpu(agf->agf_fllast)];
 	*blockp = cpu_to_be32(bno);
-	TRACE_MODAGF(NULL, agf, XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
-	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
+	TRACE_MODAGF(NULL, agf, logflags);
+	xfs_alloc_log_agf(tp, agbp, logflags);
 	xfs_trans_log_buf(tp, agflbp,
 		(int)((xfs_caddr_t)blockp - (xfs_caddr_t)agfl),
 		(int)((xfs_caddr_t)blockp - (xfs_caddr_t)agfl +
@@ -2196,6 +2223,7 @@ xfs_alloc_read_agf(
 	pag = &mp->m_perag[agno];
 	if (!pag->pagf_init) {
 		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
+		pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
 		pag->pagf_flcount = be32_to_cpu(agf->agf_flcount);
 		pag->pagf_longest = be32_to_cpu(agf->agf_longest);
 		pag->pagf_levels[XFS_BTNUM_BNOi] =
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 5a4256120cc..5aec15d0651 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -136,7 +136,8 @@ int				/* error */
 xfs_alloc_get_freelist(
 	struct xfs_trans *tp,	/* transaction pointer */
 	struct xfs_buf	*agbp,	/* buffer containing the agf structure */
-	xfs_agblock_t	*bnop);	/* block address retrieved from freelist */
+	xfs_agblock_t	*bnop,	/* block address retrieved from freelist */
+	int		btreeblk); /* destination is a AGF btree */
 
 /*
  * Log the given fields from the agf structure.
@@ -165,7 +166,8 @@ xfs_alloc_put_freelist(
 	struct xfs_trans *tp,	/* transaction pointer */
 	struct xfs_buf	*agbp,	/* buffer for a.g. freelist header */
 	struct xfs_buf	*agflbp,/* buffer for a.g. free block array */
-	xfs_agblock_t	bno);	/* block being freed */
+	xfs_agblock_t	bno,	/* block being freed */
+	int		btreeblk); /* owner was a AGF btree */
 
 /*
  * Read in the allocation group header (free/alloc section).
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 74cadf95d4e..1603ce59585 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -226,8 +226,9 @@ xfs_alloc_delrec(
 			/*
 			 * Put this buffer/block on the ag's freelist.
 			 */
-			if ((error = xfs_alloc_put_freelist(cur->bc_tp,
-					cur->bc_private.a.agbp, NULL, bno)))
+			error = xfs_alloc_put_freelist(cur->bc_tp,
+					cur->bc_private.a.agbp, NULL, bno, 1);
+			if (error)
 				return error;
 			/*
 			 * Since blocks move to the free list without the
@@ -549,8 +550,9 @@ xfs_alloc_delrec(
 	/*
 	 * Free the deleting block by putting it on the freelist.
 	 */
-	if ((error = xfs_alloc_put_freelist(cur->bc_tp, cur->bc_private.a.agbp,
-			NULL, rbno)))
+	error = xfs_alloc_put_freelist(cur->bc_tp,
+					 cur->bc_private.a.agbp, NULL, rbno, 1);
+	if (error)
 		return error;
 	/*
 	 * Since blocks move to the free list without the coordination
@@ -1320,8 +1322,9 @@ xfs_alloc_newroot(
 	/*
 	 * Get a buffer from the freelist blocks, for the new root.
 	 */
-	if ((error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_private.a.agbp,
-			&nbno)))
+	error = xfs_alloc_get_freelist(cur->bc_tp,
+					cur->bc_private.a.agbp, &nbno, 1);
+	if (error)
 		return error;
 	/*
 	 * None available, we fail.
@@ -1604,8 +1607,9 @@ xfs_alloc_split(
 	 * Allocate the new block from the freelist.
 	 * If we can't do it, we're toast.  Give up.
 	 */
-	if ((error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_private.a.agbp,
-			&rbno)))
+	error = xfs_alloc_get_freelist(cur->bc_tp,
+					 cur->bc_private.a.agbp, &rbno, 1);
+	if (error)
 		return error;
 	if (rbno == NULLAGBLOCK) {
 		*stat = 0;
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 1335449841c..1b60cfc28be 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -238,6 +238,7 @@ typedef struct xfs_fsop_resblks {
 #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_LAZYSB	0x4000	/* lazy superblock counters */
 
 
 /*
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 25e5eae8a97..27d01afe846 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -94,6 +94,8 @@ xfs_fs_geometry(
 				XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) |
 			(XFS_SB_VERSION_HASSECTOR(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_SECTOR : 0) |
+			(xfs_sb_version_haslazysbcount(&mp->m_sb) ?
+				XFS_FSOP_GEOM_FLAGS_LAZYSB : 0) |
 			(XFS_SB_VERSION_HASATTR2(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_ATTR2 : 0);
 		geo->logsectsize = XFS_SB_VERSION_HASSECTOR(&mp->m_sb) ?
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index b5feb3e7711..f943368c9b9 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -123,6 +123,7 @@ xfs_ialloc_ag_alloc(
 	int		blks_per_cluster;  /* fs blocks per inode cluster */
 	xfs_btree_cur_t	*cur;		/* inode btree cursor */
 	xfs_daddr_t	d;		/* disk addr of buffer */
+	xfs_agnumber_t	agno;
 	int		error;
 	xfs_buf_t	*fbuf;		/* new free inodes' buffer */
 	xfs_dinode_t	*free;		/* new free inode structure */
@@ -302,15 +303,15 @@ xfs_ialloc_ag_alloc(
 	}
 	be32_add(&agi->agi_count, newlen);
 	be32_add(&agi->agi_freecount, newlen);
+	agno = be32_to_cpu(agi->agi_seqno);
 	down_read(&args.mp->m_peraglock);
-	args.mp->m_perag[be32_to_cpu(agi->agi_seqno)].pagi_freecount += newlen;
+	args.mp->m_perag[agno].pagi_freecount += newlen;
 	up_read(&args.mp->m_peraglock);
 	agi->agi_newino = cpu_to_be32(newino);
 	/*
 	 * Insert records describing the new inode chunk into the btree.
 	 */
-	cur = xfs_btree_init_cursor(args.mp, tp, agbp,
-			be32_to_cpu(agi->agi_seqno),
+	cur = xfs_btree_init_cursor(args.mp, tp, agbp, agno,
 			XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
 	for (thisino = newino;
 	     thisino < newino + newlen;
@@ -1387,6 +1388,7 @@ xfs_ialloc_read_agi(
 	pag = &mp->m_perag[agno];
 	if (!pag->pagi_init) {
 		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
+		pag->pagi_count = be32_to_cpu(agi->agi_count);
 		pag->pagi_init = 1;
 	} else {
 		/*
@@ -1410,3 +1412,23 @@ xfs_ialloc_read_agi(
 	*bpp = bp;
 	return 0;
 }
+
+/*
+ * Read in the agi to initialise the per-ag data in the mount structure
+ */
+int
+xfs_ialloc_pagi_init(
+	xfs_mount_t	*mp,		/* file system mount structure */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	xfs_agnumber_t	agno)		/* allocation group number */
+{
+	xfs_buf_t	*bp = NULL;
+	int		error;
+
+	error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
+	if (error)
+		return error;
+	if (bp)
+		xfs_trans_brelse(tp, bp);
+	return 0;
+}
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 7f5debe1acb..97f4040931c 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -149,6 +149,16 @@ xfs_ialloc_read_agi(
 	xfs_agnumber_t	agno,		/* allocation group number */
 	struct xfs_buf	**bpp);		/* allocation group hdr buf */
 
+/*
+ * Read in the allocation group header to initialise the per-ag data
+ * in the mount structure
+ */
+int
+xfs_ialloc_pagi_init(
+	struct xfs_mount *mp,		/* file system mount structure */
+	struct xfs_trans *tp,		/* transaction pointer */
+        xfs_agnumber_t  agno);		/* allocation group number */
+
 #endif	/* __KERNEL__ */
 
 #endif	/* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index fb50fd400e5..9d4c4fbeb3e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -817,10 +817,8 @@ xfs_log_need_covered(xfs_mount_t *mp)
 	SPLDECL(s);
 	int		needed = 0, gen;
 	xlog_t		*log = mp->m_log;
-	bhv_vfs_t	*vfsp = XFS_MTOVFS(mp);
 
-	if (vfs_test_for_freeze(vfsp) || XFS_FORCED_SHUTDOWN(mp) ||
-	    (vfsp->vfs_flag & VFS_RDONLY))
+	if (!xfs_fs_writable(mp))
 		return 0;
 
 	s = LOG_LOCK(log);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 080fabf61c9..fddbb091a86 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -927,6 +927,14 @@ xlog_find_tail(
 			ASSIGN_ANY_LSN_HOST(log->l_last_sync_lsn, log->l_curr_cycle,
 					after_umount_blk);
 			*tail_blk = after_umount_blk;
+
+			/*
+			 * Note that the unmount was clean. If the unmount
+			 * was not clean, we need to know this to rebuild the
+			 * superblock counters from the perag headers if we
+			 * have a filesystem using non-persistent counters.
+			 */
+			log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
 		}
 	}
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 5de1f392e63..f6fe47d8c4d 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -643,6 +643,64 @@ xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
 					sbp->sb_inopblock);
 	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
 }
+
+/*
+ * xfs_initialize_perag_data
+ *
+ * Read in each per-ag structure so we can count up the number of
+ * allocated inodes, free inodes and used filesystem blocks as this
+ * information is no longer persistent in the superblock. Once we have
+ * this information, write it into the in-core superblock structure.
+ */
+STATIC int
+xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
+{
+	xfs_agnumber_t	index;
+	xfs_perag_t	*pag;
+	xfs_sb_t	*sbp = &mp->m_sb;
+	uint64_t	ifree = 0;
+	uint64_t	ialloc = 0;
+	uint64_t	bfree = 0;
+	uint64_t	bfreelst = 0;
+	uint64_t	btree = 0;
+	int		error;
+	int		s;
+
+	for (index = 0; index < agcount; index++) {
+		/*
+		 * read the agf, then the agi. This gets us
+		 * all the inforamtion we need and populates the
+		 * per-ag structures for us.
+		 */
+		error = xfs_alloc_pagf_init(mp, NULL, index, 0);
+		if (error)
+			return error;
+
+		error = xfs_ialloc_pagi_init(mp, NULL, index);
+		if (error)
+			return error;
+		pag = &mp->m_perag[index];
+		ifree += pag->pagi_freecount;
+		ialloc += pag->pagi_count;
+		bfree += pag->pagf_freeblks;
+		bfreelst += pag->pagf_flcount;
+		btree += pag->pagf_btreeblks;
+	}
+	/*
+	 * Overwrite incore superblock counters with just-read data
+	 */
+	s = XFS_SB_LOCK(mp);
+	sbp->sb_ifree = ifree;
+	sbp->sb_icount = ialloc;
+	sbp->sb_fdblocks = bfree + bfreelst + btree;
+	XFS_SB_UNLOCK(mp, s);
+
+	/* Fixup the per-cpu counters as well. */
+	xfs_icsb_reinit_counters(mp);
+
+	return 0;
+}
+
 /*
  * xfs_mountfs
  *
@@ -987,6 +1045,34 @@ xfs_mountfs(
 	}
 
 	/*
+	 * Now the log is mounted, we know if it was an unclean shutdown or
+	 * not. If it was, with the first phase of recovery has completed, we
+	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
+	 * but they are recovered transactionally in the second recovery phase
+	 * later.
+	 *
+	 * Hence we can safely re-initialise incore superblock counters from
+	 * the per-ag data. These may not be correct if the filesystem was not
+	 * cleanly unmounted, so we need to wait for recovery to finish before
+	 * doing this.
+	 *
+	 * If the filesystem was cleanly unmounted, then we can trust the
+	 * values in the superblock to be correct and we don't need to do
+	 * anything here.
+	 *
+	 * If we are currently making the filesystem, the initialisation will
+	 * fail as the perag data is in an undefined state.
+	 */
+
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
+	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+	     !mp->m_sb.sb_inprogress) {
+		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
+		if (error) {
+			goto error2;
+		}
+	}
+	/*
 	 * Get and sanity-check the root inode.
 	 * Save the pointer to it in the mount structure.
 	 */
@@ -1049,6 +1135,7 @@ xfs_mountfs(
 		goto error4;
 	}
 
+
 	/*
 	 * Complete the quota initialisation, post-log-replay component.
 	 */
@@ -1111,10 +1198,9 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
 		xfs_binval(mp->m_rtdev_targp);
 	}
 
+	xfs_log_sbcount(mp, 1);
 	xfs_unmountfs_writesb(mp);
-
 	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
-
 	xfs_log_unmount(mp);			/* Done! No more fs ops. */
 
 	xfs_freesb(mp);
@@ -1161,6 +1247,62 @@ xfs_unmountfs_wait(xfs_mount_t *mp)
 }
 
 int
+xfs_fs_writable(xfs_mount_t *mp)
+{
+	bhv_vfs_t	*vfsp = XFS_MTOVFS(mp);
+
+	return !(vfs_test_for_freeze(vfsp) || XFS_FORCED_SHUTDOWN(mp) ||
+		(vfsp->vfs_flag & VFS_RDONLY));
+}
+
+/*
+ * xfs_log_sbcount
+ *
+ * Called either periodically to keep the on disk superblock values
+ * roughly up to date or from unmount to make sure the values are
+ * correct on a clean unmount.
+ *
+ * Note this code can be called during the process of freezing, so
+ * we may need to use the transaction allocator which does not not
+ * block when the transaction subsystem is in its frozen state.
+ */
+int
+xfs_log_sbcount(
+	xfs_mount_t	*mp,
+	uint		sync)
+{
+	xfs_trans_t	*tp;
+	int		error;
+
+	if (!xfs_fs_writable(mp))
+		return 0;
+
+	xfs_icsb_sync_counters(mp);
+
+	/*
+	 * we don't need to do this if we are updating the superblock
+	 * counters on every modification.
+	 */
+	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+		return 0;
+
+	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
+	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
+					XFS_DEFAULT_LOG_COUNT);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
+	if (sync)
+		xfs_trans_set_sync(tp);
+	xfs_trans_commit(tp, 0);
+
+	return 0;
+}
+
+int
 xfs_unmountfs_writesb(xfs_mount_t *mp)
 {
 	xfs_buf_t	*sbp;
@@ -1171,16 +1313,15 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 	 * skip superblock write if fs is read-only, or
 	 * if we are doing a forced umount.
 	 */
-	sbp = xfs_getsb(mp, 0);
 	if (!(XFS_MTOVFS(mp)->vfs_flag & VFS_RDONLY ||
 		XFS_FORCED_SHUTDOWN(mp))) {
 
-		xfs_icsb_sync_counters(mp);
+		sbp = xfs_getsb(mp, 0);
+ 		sb = XFS_BUF_TO_SBP(sbp);
 
 		/*
 		 * mark shared-readonly if desired
 		 */
-		sb = XFS_BUF_TO_SBP(sbp);
 		if (mp->m_mk_sharedro) {
 			if (!(sb->sb_flags & XFS_SBF_READONLY))
 				sb->sb_flags |= XFS_SBF_READONLY;
@@ -1189,6 +1330,7 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 			xfs_fs_cmn_err(CE_NOTE, mp,
 				"Unmounting, marking shared read-only");
 		}
+
 		XFS_BUF_UNDONE(sbp);
 		XFS_BUF_UNREAD(sbp);
 		XFS_BUF_UNDELAYWRITE(sbp);
@@ -1203,8 +1345,8 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 					  mp, sbp, XFS_BUF_ADDR(sbp));
 		if (error && mp->m_mk_sharedro)
 			xfs_fs_cmn_err(CE_ALERT, mp, "Superblock write error detected while unmounting.  Filesystem may not be marked shared readonly");
+		xfs_buf_relse(sbp);
 	}
-	xfs_buf_relse(sbp);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 871a5bfd861..0bca2d42271 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -429,12 +429,12 @@ typedef struct xfs_mount {
 /*
  * Flags for m_flags.
  */
-#define	XFS_MOUNT_WSYNC		(1ULL << 0)	/* for nfs - all metadata ops
+#define XFS_MOUNT_WSYNC		(1ULL << 0)	/* for nfs - all metadata ops
 						   must be synchronous except
 						   for space allocations */
-#define	XFS_MOUNT_INO64		(1ULL << 1)
+#define XFS_MOUNT_INO64		(1ULL << 1)
 			     /* (1ULL << 2)	-- currently unused */
-			     /* (1ULL << 3)	-- currently unused */
+#define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
 						   operations, typically for
 						   disk errors in metadata */
@@ -511,6 +511,8 @@ xfs_preferred_iosize(xfs_mount_t *mp)
 
 #define XFS_MAXIOFFSET(mp)	((mp)->m_maxioffset)
 
+#define XFS_LAST_UNMOUNT_WAS_CLEAN(mp)	\
+				((mp)->m_flags & XFS_MOUNT_WAS_CLEAN)
 #define XFS_FORCED_SHUTDOWN(mp)	((mp)->m_flags & XFS_MOUNT_FS_SHUTDOWN)
 #define xfs_force_shutdown(m,f)	\
 	bhv_vfs_force_shutdown((XFS_MTOVFS(m)), f, __FILE__, __LINE__)
@@ -602,6 +604,7 @@ typedef struct xfs_mod_sb {
 
 extern xfs_mount_t *xfs_mount_init(void);
 extern void	xfs_mod_sb(xfs_trans_t *, __int64_t);
+extern int	xfs_log_sbcount(xfs_mount_t *, uint);
 extern void	xfs_mount_free(xfs_mount_t *mp, int remove_bhv);
 extern int	xfs_mountfs(struct bhv_vfs *, xfs_mount_t *mp, int);
 extern void	xfs_mountfs_check_barriers(xfs_mount_t *mp);
@@ -618,6 +621,7 @@ extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
+extern int	xfs_fs_writable(xfs_mount_t *);
 extern void	xfs_do_force_shutdown(bhv_desc_t *, int, char *, int);
 extern int	xfs_syncsub(xfs_mount_t *, int, int *);
 extern int	xfs_sync_inodes(xfs_mount_t *, int, int *);
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index 467854b45c8..ef42537a607 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -74,12 +74,13 @@ struct xfs_mount;
  */
 #define XFS_SB_VERSION2_REALFBITS	0x00ffffff	/* Mask: features */
 #define XFS_SB_VERSION2_RESERVED1BIT	0x00000001
-#define XFS_SB_VERSION2_RESERVED2BIT	0x00000002
+#define XFS_SB_VERSION2_LAZYSBCOUNTBIT	0x00000002	/* Superblk counters */
 #define XFS_SB_VERSION2_RESERVED4BIT	0x00000004
 #define XFS_SB_VERSION2_ATTR2BIT	0x00000008	/* Inline attr rework */
 
 #define	XFS_SB_VERSION2_OKREALFBITS	\
-	(XFS_SB_VERSION2_ATTR2BIT)
+	(XFS_SB_VERSION2_LAZYSBCOUNTBIT	| \
+	 XFS_SB_VERSION2_ATTR2BIT)
 #define	XFS_SB_VERSION2_OKSASHFBITS	\
 	(0)
 #define XFS_SB_VERSION2_OKREALBITS	\
@@ -181,6 +182,9 @@ typedef enum {
 #define XFS_SB_SHARED_VN	XFS_SB_MVAL(SHARED_VN)
 #define XFS_SB_UNIT		XFS_SB_MVAL(UNIT)
 #define XFS_SB_WIDTH		XFS_SB_MVAL(WIDTH)
+#define XFS_SB_ICOUNT		XFS_SB_MVAL(ICOUNT)
+#define XFS_SB_IFREE		XFS_SB_MVAL(IFREE)
+#define XFS_SB_FDBLOCKS		XFS_SB_MVAL(FDBLOCKS)
 #define XFS_SB_FEATURES2	XFS_SB_MVAL(FEATURES2)
 #define	XFS_SB_NUM_BITS		((int)XFS_SBS_FIELDCOUNT)
 #define	XFS_SB_ALL_BITS		((1LL << XFS_SB_NUM_BITS) - 1)
@@ -188,7 +192,7 @@ typedef enum {
 	(XFS_SB_UUID | XFS_SB_ROOTINO | XFS_SB_RBMINO | XFS_SB_RSUMINO | \
 	 XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \
 	 XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \
-	 XFS_SB_FEATURES2)
+	 XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2)
 
 
 /*
@@ -414,6 +418,12 @@ static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
  *	 ((sbp)->sb_features2 & XFS_SB_VERSION2_FUNBIT)
  */
 
+static inline int xfs_sb_version_haslazysbcount(xfs_sb_t *sbp)
+{
+	return (XFS_SB_VERSION_HASMOREBITS(sbp) &&	\
+		((sbp)->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT));
+}
+
 #define XFS_SB_VERSION_HASATTR2(sbp)	xfs_sb_version_hasattr2(sbp)
 static inline int xfs_sb_version_hasattr2(xfs_sb_t *sbp)
 {
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index cc2d60951e2..7133fd9ab86 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -427,6 +427,14 @@ undo_blocks:
  *
  * Mark the transaction structure to indicate that the superblock
  * needs to be updated before committing.
+ *
+ * Because we may not be keeping track of allocated/free inodes and
+ * used filesystem blocks in the superblock, we do not mark the
+ * superblock dirty in this transaction if we modify these fields.
+ * We still need to update the transaction deltas so that they get
+ * applied to the incore superblock, but we don't want them to
+ * cause the superblock to get locked and logged if these are the
+ * only fields in the superblock that the transaction modifies.
  */
 void
 xfs_trans_mod_sb(
@@ -434,13 +442,19 @@ xfs_trans_mod_sb(
 	uint		field,
 	int64_t		delta)
 {
+	uint32_t	flags = (XFS_TRANS_DIRTY|XFS_TRANS_SB_DIRTY);
+	xfs_mount_t	*mp = tp->t_mountp;
 
 	switch (field) {
 	case XFS_TRANS_SB_ICOUNT:
 		tp->t_icount_delta += delta;
+		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_IFREE:
 		tp->t_ifree_delta += delta;
+		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_FDBLOCKS:
 		/*
@@ -453,6 +467,8 @@ xfs_trans_mod_sb(
 			ASSERT(tp->t_blk_res_used <= tp->t_blk_res);
 		}
 		tp->t_fdblocks_delta += delta;
+		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_RES_FDBLOCKS:
 		/*
@@ -462,6 +478,8 @@ xfs_trans_mod_sb(
 		 */
 		ASSERT(delta < 0);
 		tp->t_res_fdblocks_delta += delta;
+		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_FREXTENTS:
 		/*
@@ -544,18 +562,23 @@ xfs_trans_apply_sb_deltas(
 	       (tp->t_ag_freeblks_delta + tp->t_ag_flist_delta +
 		tp->t_ag_btree_delta));
 
-	if (tp->t_icount_delta != 0) {
-		INT_MOD(sbp->sb_icount, ARCH_CONVERT, tp->t_icount_delta);
-	}
-	if (tp->t_ifree_delta != 0) {
-		INT_MOD(sbp->sb_ifree, ARCH_CONVERT, tp->t_ifree_delta);
-	}
+	/*
+	 * Only update the superblock counters if we are logging them
+	 */
+	if (!xfs_sb_version_haslazysbcount(&(tp->t_mountp->m_sb))) {
+		if (tp->t_icount_delta != 0) {
+			INT_MOD(sbp->sb_icount, ARCH_CONVERT, tp->t_icount_delta);
+		}
+		if (tp->t_ifree_delta != 0) {
+			INT_MOD(sbp->sb_ifree, ARCH_CONVERT, tp->t_ifree_delta);
+		}
 
-	if (tp->t_fdblocks_delta != 0) {
-		INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_fdblocks_delta);
-	}
-	if (tp->t_res_fdblocks_delta != 0) {
-		INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_res_fdblocks_delta);
+		if (tp->t_fdblocks_delta != 0) {
+			INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_fdblocks_delta);
+		}
+		if (tp->t_res_fdblocks_delta != 0) {
+			INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_res_fdblocks_delta);
+		}
 	}
 
 	if (tp->t_frextents_delta != 0) {
@@ -627,6 +650,7 @@ xfs_trans_unreserve_and_mod_sb(
 {
 	xfs_mod_sb_t	msb[14];	/* If you add cases, add entries */
 	xfs_mod_sb_t	*msbp;
+	xfs_mount_t	*mp = tp->t_mountp;
 	/* REFERENCED */
 	int		error;
 	int		rsvd;
@@ -659,8 +683,15 @@ xfs_trans_unreserve_and_mod_sb(
 	 * The t_res_fdblocks_delta and t_res_frextents_delta fields are
 	 * explicitly NOT applied to the in-core superblock.
 	 * The idea is that that has already been done.
+	 *
+	 * If we are not logging superblock counters, then the inode
+	 * allocated/free and used block counts are not updated in the
+	 * on disk superblock. In this case, XFS_TRANS_SB_DIRTY will
+	 * not be set when the transaction is updated but we still need
+	 * to update the incore superblock with the changes.
 	 */
-	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+	     (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
 		if (tp->t_icount_delta != 0) {
 			msbp->msb_field = XFS_SBS_ICOUNT;
 			msbp->msb_delta = tp->t_icount_delta;
@@ -676,6 +707,9 @@ xfs_trans_unreserve_and_mod_sb(
 			msbp->msb_delta = tp->t_fdblocks_delta;
 			msbp++;
 		}
+	}
+
+	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
 		if (tp->t_frextents_delta != 0) {
 			msbp->msb_field = XFS_SBS_FREXTENTS;
 			msbp->msb_delta = tp->t_frextents_delta;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7dfcc450366..0e26e729023 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -94,7 +94,8 @@ typedef struct xfs_trans_header {
 #define	XFS_TRANS_GROWFSRT_ZERO		38
 #define	XFS_TRANS_GROWFSRT_FREE		39
 #define	XFS_TRANS_SWAPEXT		40
-#define	XFS_TRANS_TYPE_MAX		40
+#define	XFS_TRANS_SB_COUNT		41
+#define	XFS_TRANS_TYPE_MAX		41
 /* new transaction types need to be reflected in xfs_logprint(8) */
 
 
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 92c1425d06c..3a647339f40 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -672,6 +672,7 @@ xfs_mntupdate(
 	} else if (!(vfsp->vfs_flag & VFS_RDONLY)) {	/* rw -> ro */
 		bhv_vfs_sync(vfsp, SYNC_FSDATA|SYNC_BDFLUSH|SYNC_ATTR, NULL);
 		xfs_quiesce_fs(mp);
+		xfs_log_sbcount(mp, 1);
 		xfs_log_unmount_write(mp);
 		xfs_unmountfs_writesb(mp);
 		vfsp->vfs_flag |= VFS_RDONLY;
@@ -1497,6 +1498,15 @@ xfs_syncsub(
 	}
 
 	/*
+	 * If asked, update the disk superblock with incore counter values if we
+	 * are using non-persistent counters so that they don't get too far out
+	 * of sync if we crash or get a forced shutdown. We don't want to force
+	 * this to disk, just get a transaction into the iclogs....
+	 */
+	if (flags & SYNC_SUPER)
+		xfs_log_sbcount(mp, 0);
+
+	/*
 	 * Now check to see if the log needs a "dummy" transaction.
 	 */
 
@@ -1962,6 +1972,7 @@ xfs_freeze(
 	ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
 
 	/* Push the superblock and write an unmount record */
+	xfs_log_sbcount(mp, 1);
 	xfs_log_unmount_write(mp);
 	xfs_unmountfs_writesb(mp);
 	xfs_fs_log_dummy(mp);