Merge git://oss.sgi.com:8090/xfs/xfs-2.6

* git://oss.sgi.com:8090/xfs/xfs-2.6: (33 commits)
  [XFS] Don't use kmap in xfs_iozero.
  [XFS] Remove a bunch of unused functions from XFS.
  [XFS] Remove unused arguments from the XFS_BTREE_*_ADDR macros.
  [XFS] Remove unused header files for MAC and CAP checking functionality.
  [XFS] Make freeze code a little cleaner.
  [XFS] Remove unused argument to xfs_bmap_finish
  [XFS] Clean up use of VFS attr flags
  [XFS] Remove useless memory barrier
  [XFS] XFS sysctl cleanups
  [XFS] Fix assertion in xfs_attr_shortform_remove().
  [XFS] Fix callers of xfs_iozero() to zero the correct range.
  [XFS] Ensure a frozen filesystem has a clean log before writing the dummy
  [XFS] Fix sub-block zeroing for buffered writes into unwritten extents.
  [XFS] Re-initialize the per-cpu superblock counters after recovery.
  [XFS] Fix block reservation changes for non-SMP systems.
  [XFS] Fix block reservation mechanism.
  [XFS] Make growfs work for amounts greater than 2TB
  [XFS] Fix inode log item use-after-free on forced shutdown
  [XFS] Fix attr2 corruption with btree data extents
  [XFS] Workaround log space issue by increasing XFS_TRANS_PUSH_AIL_RESTARTS
  ...

63 files changed, 885 insertions, 1189 deletions

diff --git a/fs/xfs/linux-2.6/mrlock.h b/fs/xfs/linux-2.6/mrlock.h
index 32e1ce0..af168a1 100644
--- a/fs/xfs/linux-2.6/mrlock.h
+++ b/fs/xfs/linux-2.6/mrlock.h
@@ -31,15 +31,13 @@ typedef struct {
 	do { (mrp)->mr_writer = 0; init_rwsem(&(mrp)->mr_lock); } while (0)
 #define mrlock_init(mrp, t,n,s)	mrinit(mrp, n)
 #define mrfree(mrp)		do { } while (0)
-#define mraccess(mrp)		mraccessf(mrp, 0)
-#define mrupdate(mrp)		mrupdatef(mrp, 0)
 
-static inline void mraccessf(mrlock_t *mrp, int flags)
+static inline void mraccess(mrlock_t *mrp)
 {
 	down_read(&mrp->mr_lock);
 }
 
-static inline void mrupdatef(mrlock_t *mrp, int flags)
+static inline void mrupdate(mrlock_t *mrp)
 {
 	down_write(&mrp->mr_lock);
 	mrp->mr_writer = 1;
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 7b54461..f3cc4ab 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -249,7 +249,7 @@ xfs_map_blocks(
 	return -error;
 }
 
-STATIC inline int
+STATIC_INLINE int
 xfs_iomap_valid(
 	xfs_iomap_t		*iomapp,
 	loff_t			offset)
@@ -1283,13 +1283,18 @@ __xfs_get_blocks(
 	bh_result->b_bdev = iomap.iomap_target->bt_bdev;
 
 	/*
-	 * If we previously allocated a block out beyond eof and we are
-	 * now coming back to use it then we will need to flag it as new
-	 * even if it has a disk address.
+	 * If we previously allocated a block out beyond eof and we are now
+	 * coming back to use it then we will need to flag it as new even if it
+	 * has a disk address.
+	 *
+	 * With sub-block writes into unwritten extents we also need to mark
+	 * the buffer as new so that the unwritten parts of the buffer gets
+	 * correctly zeroed.
 	 */
 	if (create &&
 	    ((!buffer_mapped(bh_result) && !buffer_uptodate(bh_result)) ||
-	     (offset >= i_size_read(inode)) || (iomap.iomap_flags & IOMAP_NEW)))
+	     (offset >= i_size_read(inode)) ||
+	     (iomap.iomap_flags & (IOMAP_NEW|IOMAP_UNWRITTEN))))
 		set_buffer_new(bh_result);
 
 	if (iomap.iomap_flags & IOMAP_DELAY) {
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 4fb01ff..e2bea6a 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -34,13 +34,13 @@
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
 
-STATIC kmem_zone_t *xfs_buf_zone;
-STATIC kmem_shaker_t xfs_buf_shake;
+static kmem_zone_t *xfs_buf_zone;
+static kmem_shaker_t xfs_buf_shake;
 STATIC int xfsbufd(void *);
 STATIC int xfsbufd_wakeup(int, gfp_t);
 STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int);
 
-STATIC struct workqueue_struct *xfslogd_workqueue;
+static struct workqueue_struct *xfslogd_workqueue;
 struct workqueue_struct *xfsdatad_workqueue;
 
 #ifdef XFS_BUF_TRACE
@@ -139,7 +139,7 @@ page_region_mask(
 	return mask;
 }
 
-STATIC inline void
+STATIC_INLINE void
 set_page_region(
 	struct page	*page,
 	size_t		offset,
@@ -151,7 +151,7 @@ set_page_region(
 		SetPageUptodate(page);
 }
 
-STATIC inline int
+STATIC_INLINE int
 test_page_region(
 	struct page	*page,
 	size_t		offset,
@@ -171,9 +171,9 @@ typedef struct a_list {
 	struct a_list	*next;
 } a_list_t;
 
-STATIC a_list_t		*as_free_head;
-STATIC int		as_list_len;
-STATIC DEFINE_SPINLOCK(as_lock);
+static a_list_t		*as_free_head;
+static int		as_list_len;
+static DEFINE_SPINLOCK(as_lock);
 
 /*
  *	Try to batch vunmaps because they are costly.
@@ -1085,7 +1085,7 @@ xfs_buf_iostart(
 	return status;
 }
 
-STATIC __inline__ int
+STATIC_INLINE int
 _xfs_buf_iolocked(
 	xfs_buf_t		*bp)
 {
@@ -1095,7 +1095,7 @@ _xfs_buf_iolocked(
 	return 0;
 }
 
-STATIC __inline__ void
+STATIC_INLINE void
 _xfs_buf_ioend(
 	xfs_buf_t		*bp,
 	int			schedule)
@@ -1426,8 +1426,8 @@ xfs_free_bufhash(
 /*
  *	buftarg list for delwrite queue processing
  */
-STATIC LIST_HEAD(xfs_buftarg_list);
-STATIC DEFINE_SPINLOCK(xfs_buftarg_lock);
+LIST_HEAD(xfs_buftarg_list);
+static DEFINE_SPINLOCK(xfs_buftarg_lock);
 
 STATIC void
 xfs_register_buftarg(
@@ -1679,21 +1679,60 @@ xfsbufd_wakeup(
 	return 0;
 }
 
+/*
+ * Move as many buffers as specified to the supplied list
+ * idicating if we skipped any buffers to prevent deadlocks.
+ */
+STATIC int
+xfs_buf_delwri_split(
+	xfs_buftarg_t	*target,
+	struct list_head *list,
+	unsigned long	age)
+{
+	xfs_buf_t	*bp, *n;
+	struct list_head *dwq = &target->bt_delwrite_queue;
+	spinlock_t	*dwlk = &target->bt_delwrite_lock;
+	int		skipped = 0;
+	int		force;
+
+	force = test_and_clear_bit(XBT_FORCE_FLUSH, &target->bt_flags);
+	INIT_LIST_HEAD(list);
+	spin_lock(dwlk);
+	list_for_each_entry_safe(bp, n, dwq, b_list) {
+		XB_TRACE(bp, "walkq1", (long)xfs_buf_ispin(bp));
+		ASSERT(bp->b_flags & XBF_DELWRI);
+
+		if (!xfs_buf_ispin(bp) && !xfs_buf_cond_lock(bp)) {
+			if (!force &&
+			    time_before(jiffies, bp->b_queuetime + age)) {
+				xfs_buf_unlock(bp);
+				break;
+			}
+
+			bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q|
+					 _XBF_RUN_QUEUES);
+			bp->b_flags |= XBF_WRITE;
+			list_move_tail(&bp->b_list, list);
+		} else
+			skipped++;
+	}
+	spin_unlock(dwlk);
+
+	return skipped;
+
+}
+
 STATIC int
 xfsbufd(
-	void			*data)
+	void		*data)
 {
-	struct list_head	tmp;
-	unsigned long		age;
-	xfs_buftarg_t		*target = (xfs_buftarg_t *)data;
-	xfs_buf_t		*bp, *n;
-	struct list_head	*dwq = &target->bt_delwrite_queue;
-	spinlock_t		*dwlk = &target->bt_delwrite_lock;
-	int			count;
+	struct list_head tmp;
+	xfs_buftarg_t	*target = (xfs_buftarg_t *)data;
+	int		count;
+	xfs_buf_t	*bp;
 
 	current->flags |= PF_MEMALLOC;
 
-	INIT_LIST_HEAD(&tmp);
 	do {
 		if (unlikely(freezing(current))) {
 			set_bit(XBT_FORCE_SLEEP, &target->bt_flags);
@@ -1705,37 +1744,17 @@ xfsbufd(
 		schedule_timeout_interruptible(
 			xfs_buf_timer_centisecs * msecs_to_jiffies(10));
 
-		count = 0;
-		age = xfs_buf_age_centisecs * msecs_to_jiffies(10);
-		spin_lock(dwlk);
-		list_for_each_entry_safe(bp, n, dwq, b_list) {
-			XB_TRACE(bp, "walkq1", (long)xfs_buf_ispin(bp));
-			ASSERT(bp->b_flags & XBF_DELWRI);
-
-			if (!xfs_buf_ispin(bp) && !xfs_buf_cond_lock(bp)) {
-				if (!test_bit(XBT_FORCE_FLUSH,
-						&target->bt_flags) &&
-				    time_before(jiffies,
-						bp->b_queuetime + age)) {
-					xfs_buf_unlock(bp);
-					break;
-				}
-
-				bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q|
-						 _XBF_RUN_QUEUES);
-				bp->b_flags |= XBF_WRITE;
-				list_move_tail(&bp->b_list, &tmp);
-				count++;
-			}
-		}
-		spin_unlock(dwlk);
+		xfs_buf_delwri_split(target, &tmp,
+				xfs_buf_age_centisecs * msecs_to_jiffies(10));
 
+		count = 0;
 		while (!list_empty(&tmp)) {
 			bp = list_entry(tmp.next, xfs_buf_t, b_list);
 			ASSERT(target == bp->b_target);
 
 			list_del_init(&bp->b_list);
 			xfs_buf_iostrategy(bp);
+			count++;
 		}
 
 		if (as_list_len > 0)
@@ -1743,7 +1762,6 @@ xfsbufd(
 		if (count)
 			blk_run_address_space(target->bt_mapping);
 
-		clear_bit(XBT_FORCE_FLUSH, &target->bt_flags);
 	} while (!kthread_should_stop());
 
 	return 0;
@@ -1756,40 +1774,24 @@ xfsbufd(
  */
 int
 xfs_flush_buftarg(
-	xfs_buftarg_t		*target,
-	int			wait)
+	xfs_buftarg_t	*target,
+	int		wait)
 {
-	struct list_head	tmp;
-	xfs_buf_t		*bp, *n;
-	int			pincount = 0;
-	struct list_head	*dwq = &target->bt_delwrite_queue;
-	spinlock_t		*dwlk = &target->bt_delwrite_lock;
+	struct list_head tmp;
+	xfs_buf_t	*bp, *n;
+	int		pincount = 0;
 
 	xfs_buf_runall_queues(xfsdatad_workqueue);
 	xfs_buf_runall_queues(xfslogd_workqueue);
 
-	INIT_LIST_HEAD(&tmp);
-	spin_lock(dwlk);
-	list_for_each_entry_safe(bp, n, dwq, b_list) {
-		ASSERT(bp->b_target == target);
-		ASSERT(bp->b_flags & (XBF_DELWRI | _XBF_DELWRI_Q));
-		XB_TRACE(bp, "walkq2", (long)xfs_buf_ispin(bp));
-		if (xfs_buf_ispin(bp)) {
-			pincount++;
-			continue;
-		}
-
-		list_move_tail(&bp->b_list, &tmp);
-	}
-	spin_unlock(dwlk);
+	set_bit(XBT_FORCE_FLUSH, &target->bt_flags);
+	pincount = xfs_buf_delwri_split(target, &tmp, 0);
 
 	/*
 	 * Dropped the delayed write list lock, now walk the temporary list
 	 */
 	list_for_each_entry_safe(bp, n, &tmp, b_list) {
-		xfs_buf_lock(bp);
-		bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q|_XBF_RUN_QUEUES);
-		bp->b_flags |= XBF_WRITE;
+		ASSERT(target == bp->b_target);
 		if (wait)
 			bp->b_flags &= ~XBF_ASYNC;
 		else
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 9dd235c..9e8ef8f 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -69,8 +69,8 @@ typedef enum {
 } xfs_buf_flags_t;
 
 typedef enum {
-	XBT_FORCE_SLEEP = (0 << 1),
-	XBT_FORCE_FLUSH = (1 << 1),
+	XBT_FORCE_SLEEP = 0,
+	XBT_FORCE_FLUSH = 1,
 } xfs_buftarg_flags_t;
 
 typedef struct xfs_bufhash {
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 5fb75d9..e3a5fed 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -24,7 +24,7 @@
 #include "xfs_mount.h"
 #include "xfs_export.h"
 
-STATIC struct dentry dotdot = { .d_name.name = "..", .d_name.len = 2, };
+static struct dentry dotdot = { .d_name.name = "..", .d_name.len = 2, };
 
 /*
  * XFS encodes and decodes the fileid portion of NFS filehandles
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index d26f5cd..cb51dc9 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -46,7 +46,7 @@ static struct vm_operations_struct xfs_file_vm_ops;
 static struct vm_operations_struct xfs_dmapi_file_vm_ops;
 #endif
 
-STATIC inline ssize_t
+STATIC_INLINE ssize_t
 __xfs_file_read(
 	struct kiocb		*iocb,
 	const struct iovec	*iov,
@@ -84,7 +84,7 @@ xfs_file_aio_read_invis(
 	return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos);
 }
 
-STATIC inline ssize_t
+STATIC_INLINE ssize_t
 __xfs_file_write(
 	struct kiocb		*iocb,
 	const struct iovec	*iov,
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index f011c9c..ff5c41f 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -41,8 +41,6 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_bmap.h"
 #include "xfs_buf_item.h"
@@ -355,7 +353,6 @@ STATIC int
 xfs_readlink_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
-	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -388,7 +385,7 @@ xfs_readlink_by_handle(
 	aiov.iov_len	= olen;
 	aiov.iov_base	= hreq.ohandle;
 
-	auio.uio_iov	= &aiov;
+	auio.uio_iov	= (struct kvec *)&aiov;
 	auio.uio_iovcnt	= 1;
 	auio.uio_offset	= 0;
 	auio.uio_segflg	= UIO_USERSPACE;
@@ -406,7 +403,6 @@ STATIC int
 xfs_fssetdm_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
-	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -448,7 +444,6 @@ STATIC int
 xfs_attrlist_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
-	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -569,7 +564,6 @@ STATIC int
 xfs_attrmulti_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
-	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -689,7 +683,6 @@ xfs_ioc_xattr(
 STATIC int
 xfs_ioc_getbmap(
 	bhv_desc_t		*bdp,
-	struct file		*filp,
 	int			flags,
 	unsigned int		cmd,
 	void			__user *arg);
@@ -788,7 +781,7 @@ xfs_ioctl(
 
 	case XFS_IOC_GETBMAP:
 	case XFS_IOC_GETBMAPA:
-		return xfs_ioc_getbmap(bdp, filp, ioflags, cmd, arg);
+		return xfs_ioc_getbmap(bdp, ioflags, cmd, arg);
 
 	case XFS_IOC_GETBMAPX:
 		return xfs_ioc_getbmapx(bdp, arg);
@@ -802,16 +795,16 @@ xfs_ioctl(
 		return xfs_open_by_handle(mp, arg, filp, inode);
 
 	case XFS_IOC_FSSETDM_BY_HANDLE:
-		return xfs_fssetdm_by_handle(mp, arg, filp, inode);
+		return xfs_fssetdm_by_handle(mp, arg, inode);
 
 	case XFS_IOC_READLINK_BY_HANDLE:
-		return xfs_readlink_by_handle(mp, arg, filp, inode);
+		return xfs_readlink_by_handle(mp, arg, inode);
 
 	case XFS_IOC_ATTRLIST_BY_HANDLE:
-		return xfs_attrlist_by_handle(mp, arg, filp, inode);
+		return xfs_attrlist_by_handle(mp, arg, inode);
 
 	case XFS_IOC_ATTRMULTI_BY_HANDLE:
-		return xfs_attrmulti_by_handle(mp, arg, filp, inode);
+		return xfs_attrmulti_by_handle(mp, arg, inode);
 
 	case XFS_IOC_SWAPEXT: {
 		error = xfs_swapext((struct xfs_swapext __user *)arg);
@@ -1095,11 +1088,6 @@ xfs_ioc_fsgeometry(
 /*
  * Linux extended inode flags interface.
  */
-#define LINUX_XFLAG_SYNC	0x00000008 /* Synchronous updates */
-#define LINUX_XFLAG_IMMUTABLE	0x00000010 /* Immutable file */
-#define LINUX_XFLAG_APPEND	0x00000020 /* writes to file may only append */
-#define LINUX_XFLAG_NODUMP	0x00000040 /* do not dump file */
-#define LINUX_XFLAG_NOATIME	0x00000080 /* do not update atime */
 
 STATIC unsigned int
 xfs_merge_ioc_xflags(
@@ -1108,23 +1096,23 @@ xfs_merge_ioc_xflags(
 {
 	unsigned int	xflags = start;
 
-	if (flags & LINUX_XFLAG_IMMUTABLE)
+	if (flags & FS_IMMUTABLE_FL)
 		xflags |= XFS_XFLAG_IMMUTABLE;
 	else
 		xflags &= ~XFS_XFLAG_IMMUTABLE;
-	if (flags & LINUX_XFLAG_APPEND)
+	if (flags & FS_APPEND_FL)
 		xflags |= XFS_XFLAG_APPEND;
 	else
 		xflags &= ~XFS_XFLAG_APPEND;
-	if (flags & LINUX_XFLAG_SYNC)
+	if (flags & FS_SYNC_FL)
 		xflags |= XFS_XFLAG_SYNC;
 	else
 		xflags &= ~XFS_XFLAG_SYNC;
-	if (flags & LINUX_XFLAG_NOATIME)
+	if (flags & FS_NOATIME_FL)
 		xflags |= XFS_XFLAG_NOATIME;
 	else
 		xflags &= ~XFS_XFLAG_NOATIME;
-	if (flags & LINUX_XFLAG_NODUMP)
+	if (flags & FS_NODUMP_FL)
 		xflags |= XFS_XFLAG_NODUMP;
 	else
 		xflags &= ~XFS_XFLAG_NODUMP;
@@ -1139,15 +1127,15 @@ xfs_di2lxflags(
 	unsigned int	flags = 0;
 
 	if (di_flags & XFS_DIFLAG_IMMUTABLE)
-		flags |= LINUX_XFLAG_IMMUTABLE;
+		flags |= FS_IMMUTABLE_FL;
 	if (di_flags & XFS_DIFLAG_APPEND)
-		flags |= LINUX_XFLAG_APPEND;
+		flags |= FS_APPEND_FL;
 	if (di_flags & XFS_DIFLAG_SYNC)
-		flags |= LINUX_XFLAG_SYNC;
+		flags |= FS_SYNC_FL;
 	if (di_flags & XFS_DIFLAG_NOATIME)
-		flags |= LINUX_XFLAG_NOATIME;
+		flags |= FS_NOATIME_FL;
 	if (di_flags & XFS_DIFLAG_NODUMP)
-		flags |= LINUX_XFLAG_NODUMP;
+		flags |= FS_NODUMP_FL;
 	return flags;
 }
 
@@ -1247,9 +1235,9 @@ xfs_ioc_xattr(
 			break;
 		}
 
-		if (flags & ~(LINUX_XFLAG_IMMUTABLE | LINUX_XFLAG_APPEND | \
-			      LINUX_XFLAG_NOATIME | LINUX_XFLAG_NODUMP | \
-			      LINUX_XFLAG_SYNC)) {
+		if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
+			      FS_NOATIME_FL | FS_NODUMP_FL | \
+			      FS_SYNC_FL)) {
 			error = -EOPNOTSUPP;
 			break;
 		}
@@ -1281,7 +1269,6 @@ xfs_ioc_xattr(
 STATIC int
 xfs_ioc_getbmap(
 	bhv_desc_t		*bdp,
-	struct file		*filp,
 	int			ioflags,
 	unsigned int		cmd,
 	void			__user *arg)
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 3ba814a..aa4c3b8 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
@@ -250,13 +248,13 @@ xfs_init_security(
  *
  * XXX(hch):  nfsd is broken, better fix it instead.
  */
-STATIC inline int
+STATIC_INLINE int
 xfs_has_fs_struct(struct task_struct *task)
 {
 	return (task->fs != init_task.fs);
 }
 
-STATIC inline void
+STATIC void
 xfs_cleanup_inode(
 	bhv_vnode_t	*dvp,
 	bhv_vnode_t	*vp,
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 65e79b4..ff8d64e 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_inode_item.h"
 #include "xfs_buf_item.h"
@@ -134,13 +132,11 @@ STATIC int
 xfs_iozero(
 	struct inode		*ip,	/* inode			*/
 	loff_t			pos,	/* offset in file		*/
-	size_t			count,	/* size of data to zero		*/
-	loff_t			end_size)	/* max file size to set */
+	size_t			count)	/* size of data to zero		*/
 {
 	unsigned		bytes;
 	struct page		*page;
 	struct address_space	*mapping;
-	char			*kaddr;
 	int			status;
 
 	mapping = ip->i_mapping;
@@ -158,26 +154,21 @@ xfs_iozero(
 		if (!page)
 			break;
 
-		kaddr = kmap(page);
 		status = mapping->a_ops->prepare_write(NULL, page, offset,
 							offset + bytes);
-		if (status) {
+		if (status)
 			goto unlock;
-		}
 
-		memset((void *) (kaddr + offset), 0, bytes);
-		flush_dcache_page(page);
+		memclear_highpage_flush(page, offset, bytes);
+
 		status = mapping->a_ops->commit_write(NULL, page, offset,
 							offset + bytes);
 		if (!status) {
 			pos += bytes;
 			count -= bytes;
-			if (pos > i_size_read(ip))
-				i_size_write(ip, pos < end_size ? pos : end_size);
 		}
 
 unlock:
-		kunmap(page);
 		unlock_page(page);
 		page_cache_release(page);
 		if (status)
@@ -449,8 +440,8 @@ STATIC int				/* error (positive) */
 xfs_zero_last_block(
 	struct inode	*ip,
 	xfs_iocore_t	*io,
-	xfs_fsize_t	isize,
-	xfs_fsize_t	end_size)
+	xfs_fsize_t	offset,
+	xfs_fsize_t	isize)
 {
 	xfs_fileoff_t	last_fsb;
 	xfs_mount_t	*mp = io->io_mount;
@@ -459,7 +450,6 @@ xfs_zero_last_block(
 	int		zero_len;
 	int		error = 0;
 	xfs_bmbt_irec_t	imap;
-	loff_t		loff;
 
 	ASSERT(ismrlocked(io->io_lock, MR_UPDATE) != 0);
 
@@ -494,9 +484,10 @@ xfs_zero_last_block(
 	 */
 	XFS_IUNLOCK(mp, io, XFS_ILOCK_EXCL| XFS_EXTSIZE_RD);
 
-	loff = XFS_FSB_TO_B(mp, last_fsb);
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
-	error = xfs_iozero(ip, loff + zero_offset, zero_len, end_size);
+	if (isize + zero_len > offset)
+		zero_len = offset - isize;
+	error = xfs_iozero(ip, isize, zero_len);
 
 	XFS_ILOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
 	ASSERT(error >= 0);
@@ -519,14 +510,15 @@ xfs_zero_eof(
 	bhv_vnode_t	*vp,
 	xfs_iocore_t	*io,
 	xfs_off_t	offset,		/* starting I/O offset */
-	xfs_fsize_t	isize,		/* current inode size */
-	xfs_fsize_t	end_size)	/* terminal inode size */
+	xfs_fsize_t	isize)		/* current inode size */
 {
 	struct inode	*ip = vn_to_inode(vp);
 	xfs_fileoff_t	start_zero_fsb;
 	xfs_fileoff_t	end_zero_fsb;
 	xfs_fileoff_t	zero_count_fsb;
 	xfs_fileoff_t	last_fsb;
+	xfs_fileoff_t	zero_off;
+	xfs_fsize_t	zero_len;
 	xfs_mount_t	*mp = io->io_mount;
 	int		nimaps;
 	int		error = 0;
@@ -540,7 +532,7 @@ xfs_zero_eof(
 	 * First handle zeroing the block on which isize resides.
 	 * We only zero a part of that block so it is handled specially.
 	 */
-	error = xfs_zero_last_block(ip, io, isize, end_size);
+	error = xfs_zero_last_block(ip, io, offset, isize);
 	if (error) {
 		ASSERT(ismrlocked(io->io_lock, MR_UPDATE));
 		ASSERT(ismrlocked(io->io_iolock, MR_UPDATE));
@@ -601,10 +593,13 @@ xfs_zero_eof(
 		 */
 		XFS_IUNLOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
 
-		error = xfs_iozero(ip,
-				   XFS_FSB_TO_B(mp, start_zero_fsb),
-				   XFS_FSB_TO_B(mp, imap.br_blockcount),
-				   end_size);
+		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
+		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
+
+		if ((zero_off + zero_len) > offset)
+			zero_len = offset - zero_off;
+
+		error = xfs_iozero(ip, zero_off, zero_len);
 		if (error) {
 			goto out_lock;
 		}
@@ -783,8 +778,7 @@ start:
 	 */
 
 	if (pos > isize) {
-		error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos,
-					isize, pos + count);
+		error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos, isize);
 		if (error) {
 			xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
 			goto out_unlock_mutex;
diff --git a/fs/xfs/linux-2.6/xfs_lrw.h b/fs/xfs/linux-2.6/xfs_lrw.h
index c77e62e..7ac51b1 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.h
+++ b/fs/xfs/linux-2.6/xfs_lrw.h
@@ -83,7 +83,7 @@ extern int xfs_bdstrat_cb(struct xfs_buf *);
 extern int xfs_dev_is_read_only(struct xfs_mount *, char *);
 
 extern int xfs_zero_eof(struct bhv_vnode *, struct xfs_iocore *, xfs_off_t,
-				xfs_fsize_t, xfs_fsize_t);
+				xfs_fsize_t);
 extern ssize_t xfs_read(struct bhv_desc *, struct kiocb *,
 				const struct iovec *, unsigned int,
 				loff_t *, int, struct cred *);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index b93265b..1a4103c 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
@@ -58,10 +56,10 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 
-STATIC struct quotactl_ops xfs_quotactl_operations;
-STATIC struct super_operations xfs_super_operations;
-STATIC kmem_zone_t *xfs_vnode_zone;
-STATIC kmem_zone_t *xfs_ioend_zone;
+static struct quotactl_ops xfs_quotactl_operations;
+static struct super_operations xfs_super_operations;
+static kmem_zone_t *xfs_vnode_zone;
+static kmem_zone_t *xfs_ioend_zone;
 mempool_t *xfs_ioend_pool;
 
 STATIC struct xfs_mount_args *
@@ -121,7 +119,7 @@ xfs_max_file_offset(
 	return (((__uint64_t)pagefactor) << bitshift) - 1;
 }
 
-STATIC __inline__ void
+STATIC_INLINE void
 xfs_set_inodeops(
 	struct inode		*inode)
 {
@@ -147,7 +145,7 @@ xfs_set_inodeops(
 	}
 }
 
-STATIC __inline__ void
+STATIC_INLINE void
 xfs_revalidate_inode(
 	xfs_mount_t		*mp,
 	bhv_vnode_t		*vp,
@@ -553,7 +551,6 @@ vfs_sync_worker(
 		error = bhv_vfs_sync(vfsp, SYNC_FSDATA | SYNC_BDFLUSH | \
 					SYNC_ATTR | SYNC_REFCACHE, NULL);
 	vfsp->vfs_sync_seq++;
-	wmb();
 	wake_up(&vfsp->vfs_wait_single_sync_task);
 }
 
@@ -659,9 +656,17 @@ xfs_fs_sync_super(
 	int			error;
 	int			flags;
 
-	if (unlikely(sb->s_frozen == SB_FREEZE_WRITE))
-		flags = SYNC_QUIESCE;
-	else
+	if (unlikely(sb->s_frozen == SB_FREEZE_WRITE)) {
+		/*
+		 * First stage of freeze - no more writers will make progress
+		 * now we are here, so we flush delwri and delalloc buffers
+		 * here, then wait for all I/O to complete.  Data is frozen at
+		 * that point. Metadata is not frozen, transactions can still
+		 * occur here so don't bother flushing the buftarg (i.e
+		 * SYNC_QUIESCE) because it'll just get dirty again.
+		 */
+		flags = SYNC_FSDATA | SYNC_DELWRI | SYNC_WAIT | SYNC_IOWAIT;
+	} else
 		flags = SYNC_FSDATA | (wait ? SYNC_WAIT : 0);
 
 	error = bhv_vfs_sync(vfsp, flags, NULL);
@@ -873,7 +878,7 @@ xfs_fs_get_sb(
 			   mnt);
 }
 
-STATIC struct super_operations xfs_super_operations = {
+static struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
 	.write_inode		= xfs_fs_write_inode,
@@ -887,7 +892,7 @@ STATIC struct super_operations xfs_super_operations = {
 	.show_options		= xfs_fs_show_options,
 };
 
-STATIC struct quotactl_ops xfs_quotactl_operations = {
+static struct quotactl_ops xfs_quotactl_operations = {
 	.quota_sync		= xfs_fs_quotasync,
 	.get_xstate		= xfs_fs_getxstate,
 	.set_xstate		= xfs_fs_setxstate,
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index af24653..5c46c35 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -54,102 +54,204 @@ xfs_stats_clear_proc_handler(
 }
 #endif /* CONFIG_PROC_FS */
 
-STATIC ctl_table xfs_table[] = {
-	{XFS_RESTRICT_CHOWN, "restrict_chown", &xfs_params.restrict_chown.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.restrict_chown.min, &xfs_params.restrict_chown.max},
-
-	{XFS_SGID_INHERIT, "irix_sgid_inherit", &xfs_params.sgid_inherit.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.sgid_inherit.min, &xfs_params.sgid_inherit.max},
-
-	{XFS_SYMLINK_MODE, "irix_symlink_mode", &xfs_params.symlink_mode.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.symlink_mode.min, &xfs_params.symlink_mode.max},
-
-	{XFS_PANIC_MASK, "panic_mask", &xfs_params.panic_mask.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.panic_mask.min, &xfs_params.panic_mask.max},
-
-	{XFS_ERRLEVEL, "error_level", &xfs_params.error_level.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.error_level.min, &xfs_params.error_level.max},
-
-	{XFS_SYNCD_TIMER, "xfssyncd_centisecs", &xfs_params.syncd_timer.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.syncd_timer.min, &xfs_params.syncd_timer.max},
-
-	{XFS_INHERIT_SYNC, "inherit_sync", &xfs_params.inherit_sync.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.inherit_sync.min, &xfs_params.inherit_sync.max},
-
-	{XFS_INHERIT_NODUMP, "inherit_nodump", &xfs_params.inherit_nodump.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.inherit_nodump.min, &xfs_params.inherit_nodump.max},
-
-	{XFS_INHERIT_NOATIME, "inherit_noatime", &xfs_params.inherit_noatim.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.inherit_noatim.min, &xfs_params.inherit_noatim.max},
-
-	{XFS_BUF_TIMER, "xfsbufd_centisecs", &xfs_params.xfs_buf_timer.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.xfs_buf_timer.min, &xfs_params.xfs_buf_timer.max},
-
-	{XFS_BUF_AGE, "age_buffer_centisecs", &xfs_params.xfs_buf_age.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.xfs_buf_age.min, &xfs_params.xfs_buf_age.max},
-
-	{XFS_INHERIT_NOSYM, "inherit_nosymlinks", &xfs_params.inherit_nosym.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.inherit_nosym.min, &xfs_params.inherit_nosym.max},
-
-	{XFS_ROTORSTEP, "rotorstep", &xfs_params.rotorstep.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.rotorstep.min, &xfs_params.rotorstep.max},
-
-	{XFS_INHERIT_NODFRG, "inherit_nodefrag", &xfs_params.inherit_nodfrg.val,
-	sizeof(int), 0644, NULL, &proc_dointvec_minmax,
-	&sysctl_intvec, NULL,
-	&xfs_params.inherit_nodfrg.min, &xfs_params.inherit_nodfrg.max},
+static ctl_table xfs_table[] = {
+	{
+		.ctl_name	= XFS_RESTRICT_CHOWN,
+		.procname	= "restrict_chown",
+		.data		= &xfs_params.restrict_chown.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.restrict_chown.min,
+		.extra2		= &xfs_params.restrict_chown.max
+	},
+	{
+		.ctl_name	= XFS_SGID_INHERIT,
+		.procname	= "irix_sgid_inherit",
+		.data		= &xfs_params.sgid_inherit.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.sgid_inherit.min,
+		.extra2		= &xfs_params.sgid_inherit.max
+	},
+	{
+		.ctl_name	= XFS_SYMLINK_MODE,
+		.procname	= "irix_symlink_mode",
+		.data		= &xfs_params.symlink_mode.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.symlink_mode.min,
+		.extra2		= &xfs_params.symlink_mode.max
+	},
+	{
+		.ctl_name	= XFS_PANIC_MASK,
+		.procname	= "panic_mask",
+		.data		= &xfs_params.panic_mask.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.panic_mask.min,
+		.extra2		= &xfs_params.panic_mask.max
+	},
 
+	{
+		.ctl_name	= XFS_ERRLEVEL,
+		.procname	= "error_level",
+		.data		= &xfs_params.error_level.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.error_level.min,
+		.extra2		= &xfs_params.error_level.max
+	},
+	{
+		.ctl_name	= XFS_SYNCD_TIMER,
+		.procname	= "xfssyncd_centisecs",
+		.data		= &xfs_params.syncd_timer.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.syncd_timer.min,
+		.extra2		= &xfs_params.syncd_timer.max
+	},
+	{
+		.ctl_name	= XFS_INHERIT_SYNC,
+		.procname	= "inherit_sync",
+		.data		= &xfs_params.inherit_sync.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.inherit_sync.min,
+		.extra2		= &xfs_params.inherit_sync.max
+	},
+	{
+		.ctl_name	= XFS_INHERIT_NODUMP,
+		.procname	= "inherit_nodump",
+		.data		= &xfs_params.inherit_nodump.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.inherit_nodump.min,
+		.extra2		= &xfs_params.inherit_nodump.max
+	},
+	{
+		.ctl_name	= XFS_INHERIT_NOATIME,
+		.procname	= "inherit_noatime",
+		.data		= &xfs_params.inherit_noatim.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.inherit_noatim.min,
+		.extra2		= &xfs_params.inherit_noatim.max
+	},
+	{
+		.ctl_name	= XFS_BUF_TIMER,
+		.procname	= "xfsbufd_centisecs",
+		.data		= &xfs_params.xfs_buf_timer.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.xfs_buf_timer.min,
+		.extra2		= &xfs_params.xfs_buf_timer.max
+	},
+	{
+		.ctl_name	= XFS_BUF_AGE,
+		.procname	= "age_buffer_centisecs",
+		.data		= &xfs_params.xfs_buf_age.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.xfs_buf_age.min,
+		.extra2		= &xfs_params.xfs_buf_age.max
+	},
+	{
+		.ctl_name	= XFS_INHERIT_NOSYM,
+		.procname	= "inherit_nosymlinks",
+		.data		= &xfs_params.inherit_nosym.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.inherit_nosym.min,
+		.extra2		= &xfs_params.inherit_nosym.max
+	},
+	{
+		.ctl_name	= XFS_ROTORSTEP,
+		.procname	= "rotorstep",
+		.data		= &xfs_params.rotorstep.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.rotorstep.min,
+		.extra2		= &xfs_params.rotorstep.max
+	},
+	{
+		.ctl_name	= XFS_INHERIT_NODFRG,
+		.procname	= "inherit_nodefrag",
+		.data		= &xfs_params.inherit_nodfrg.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.inherit_nodfrg.min,
+		.extra2		= &xfs_params.inherit_nodfrg.max
+	},
 	/* please keep this the last entry */
 #ifdef CONFIG_PROC_FS
-	{XFS_STATS_CLEAR, "stats_clear", &xfs_params.stats_clear.val,
-	sizeof(int), 0644, NULL, &xfs_stats_clear_proc_handler,
-	&sysctl_intvec, NULL,
-	&xfs_params.stats_clear.min, &xfs_params.stats_clear.max},
+	{
+		.ctl_name	= XFS_STATS_CLEAR,
+		.procname	= "stats_clear",
+		.data		= &xfs_params.stats_clear.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &xfs_stats_clear_proc_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &xfs_params.stats_clear.min,
+		.extra2		= &xfs_params.stats_clear.max
+	},
 #endif /* CONFIG_PROC_FS */
 
-	{0}
+	{}
 };
 
-STATIC ctl_table xfs_dir_table[] = {
-	{FS_XFS, "xfs", NULL, 0, 0555, xfs_table},
-	{0}
+static ctl_table xfs_dir_table[] = {
+	{
+		.ctl_name	= FS_XFS,
+		.procname	= "xfs",
+		.mode		= 0555,
+		.child		= xfs_table
+	},
+	{}
 };
 
-STATIC ctl_table xfs_root_table[] = {
-	{CTL_FS, "fs",  NULL, 0, 0555, xfs_dir_table},
-	{0}
+static ctl_table xfs_root_table[] = {
+	{
+		.ctl_name	= CTL_FS,
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= xfs_dir_table
+	},
+	{}
 };
 
 void
 xfs_sysctl_register(void)
 {
-	xfs_table_header = register_sysctl_table(xfs_root_table, 1);
+	xfs_table_header = register_sysctl_table(xfs_root_table, 0);
 }
 
 void
diff --git a/fs/xfs/linux-2.6/xfs_vfs.h b/fs/xfs/linux-2.6/xfs_vfs.h
index da255bd..e2c2ce9 100644
--- a/fs/xfs/linux-2.6/xfs_vfs.h
+++ b/fs/xfs/linux-2.6/xfs_vfs.h
@@ -91,7 +91,7 @@ typedef enum {
 #define SYNC_FSDATA		0x0020	/* flush fs data (e.g. superblocks) */
 #define SYNC_REFCACHE		0x0040  /* prune some of the nfs ref cache */
 #define SYNC_REMOUNT		0x0080  /* remount readonly, no dummy LRs */
-#define SYNC_QUIESCE		0x0100  /* quiesce fileystem for a snapshot */
+#define SYNC_IOWAIT		0x0100  /* wait for all I/O to complete */
 
 #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/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c
index 553fa73..ada24ba 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.c
+++ b/fs/xfs/linux-2.6/xfs_vnode.c
@@ -26,7 +26,7 @@ DEFINE_SPINLOCK(vnumber_lock);
  */
 #define NVSYNC                  37
 #define vptosync(v)             (&vsync[((unsigned long)v) % NVSYNC])
-STATIC wait_queue_head_t vsync[NVSYNC];
+static wait_queue_head_t vsync[NVSYNC];
 
 void
 vn_init(void)
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 515f5fd..b76118c 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -489,14 +489,14 @@ static inline struct bhv_vnode *vn_grab(struct bhv_vnode *vp)
 #define VN_LOCK(vp)		mutex_spinlock(&(vp)->v_lock)
 #define VN_UNLOCK(vp, s)	mutex_spinunlock(&(vp)->v_lock, s)
 
-static __inline__ void vn_flagset(struct bhv_vnode *vp, uint flag)
+STATIC_INLINE void vn_flagset(struct bhv_vnode *vp, uint flag)
 {
 	spin_lock(&vp->v_lock);
 	vp->v_flag |= flag;
 	spin_unlock(&vp->v_lock);
 }
 
-static __inline__ uint vn_flagclr(struct bhv_vnode *vp, uint flag)
+STATIC_INLINE uint vn_flagclr(struct bhv_vnode *vp, uint flag)
 {
 	uint	cleared;
 
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index 3aa7715..4adaf13 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_space.h"
@@ -484,7 +482,7 @@ xfs_qm_dqalloc(
 
 	xfs_trans_bhold(tp, bp);
 
-	if ((error = xfs_bmap_finish(tpp, &flist, firstblock, &committed))) {
+	if ((error = xfs_bmap_finish(tpp, &flist, &committed))) {
 		goto error1;
 	}
 
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index 33ad5af..ddb61fe 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
@@ -399,7 +397,7 @@ xfs_qm_dquot_logitem_committing(
 /*
  * This is the ops vector for dquots
  */
-STATIC struct xfs_item_ops xfs_dquot_item_ops = {
+static struct xfs_item_ops xfs_dquot_item_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_qm_dquot_logitem_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_qm_dquot_logitem_format,
@@ -606,7 +604,7 @@ xfs_qm_qoffend_logitem_committing(xfs_qoff_logitem_t *qip, xfs_lsn_t commit_lsn)
 	return;
 }
 
-STATIC struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
+static struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_qm_qoff_logitem_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_qm_qoff_logitem_format,
@@ -628,7 +626,7 @@ STATIC struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
 /*
  * This is the ops vector shared by all quotaoff-start log items.
  */
-STATIC struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
+static struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_qm_qoff_logitem_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_qm_qoff_logitem_format,
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 7c6a3a5..1de2acd 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -44,8 +44,6 @@
 #include "xfs_bmap.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_space.h"
@@ -64,10 +62,10 @@ uint		ndquot;
 
 kmem_zone_t	*qm_dqzone;
 kmem_zone_t	*qm_dqtrxzone;
-STATIC kmem_shaker_t	xfs_qm_shaker;
+static kmem_shaker_t	xfs_qm_shaker;
 
-STATIC cred_t	xfs_zerocr;
-STATIC xfs_inode_t	xfs_zeroino;
+static cred_t	xfs_zerocr;
+static xfs_inode_t	xfs_zeroino;
 
 STATIC void	xfs_qm_list_init(xfs_dqlist_t *, char *, int);
 STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index db8872b..d2cdb8a 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -44,8 +44,6 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_qm.h"
@@ -384,7 +382,7 @@ xfs_qm_dqrele_null(
 }
 
 
-STATIC struct xfs_qmops xfs_qmcore_xfs = {
+static struct xfs_qmops xfs_qmcore_xfs = {
 	.xfs_qminit		= xfs_qm_newmount,
 	.xfs_qmdone		= xfs_qm_unmount_quotadestroy,
 	.xfs_qmmount		= xfs_qm_endmount,
diff --git a/fs/xfs/quota/xfs_qm_stats.c b/fs/xfs/quota/xfs_qm_stats.c
index 6f858fb..709f5f5 100644
--- a/fs/xfs/quota/xfs_qm_stats.c
+++ b/fs/xfs/quota/xfs_qm_stats.c
@@ -43,8 +43,6 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_qm.h"
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index ed620c4..716f562 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -46,8 +46,6 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
@@ -134,7 +132,7 @@ xfs_qm_quotactl(
 		break;
 
 	case Q_XQUOTASYNC:
-		return (xfs_sync_inodes(mp, SYNC_DELWRI, 0, NULL));
+		return (xfs_sync_inodes(mp, SYNC_DELWRI, NULL));
 
 	default:
 		break;
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/quota/xfs_trans_dquot.c
index 0242e96..d7491e7 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/quota/xfs_trans_dquot.c
@@ -43,8 +43,6 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_priv.h"
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
index 4363512..08bbd3c 100644
--- a/fs/xfs/support/debug.c
+++ b/fs/xfs/support/debug.c
@@ -19,7 +19,7 @@
 #include "debug.h"
 #include "spin.h"
 
-static char		message[256];	/* keep it off the stack */
+static char		message[1024];	/* keep it off the stack */
 static DEFINE_SPINLOCK(xfs_err_lock);
 
 /* Translate from CE_FOO to KERN_FOO, err_level(CE_FOO) == KERN_FOO */
@@ -44,13 +44,14 @@ cmn_err(register int level, char *fmt, ...)
 	spin_lock_irqsave(&xfs_err_lock,flags);
 	va_start(ap, fmt);
 	if (*fmt == '!') fp++;
-	len = vsprintf(message, fp, ap);
-	if (level != CE_DEBUG && message[len-1] != '\n')
-		strcat(message, "\n");
-	printk("%s%s", err_level[level], message);
+	len = vsnprintf(message, sizeof(message), fp, ap);
+	if (len >= sizeof(message))
+		len = sizeof(message) - 1;
+	if (message[len-1] == '\n')
+		message[len-1] = 0;
+	printk("%s%s\n", err_level[level], message);
 	va_end(ap);
 	spin_unlock_irqrestore(&xfs_err_lock,flags);
-
 	BUG_ON(level == CE_PANIC);
 }
 
@@ -64,11 +65,13 @@ icmn_err(register int level, char *fmt, va_list ap)
 	if(level > XFS_MAX_ERR_LEVEL)
 		level = XFS_MAX_ERR_LEVEL;
 	spin_lock_irqsave(&xfs_err_lock,flags);
-	len = vsprintf(message, fmt, ap);
-	if (level != CE_DEBUG && message[len-1] != '\n')
-		strcat(message, "\n");
+	len = vsnprintf(message, sizeof(message), fmt, ap);
+	if (len >= sizeof(message))
+		len = sizeof(message) - 1;
+	if (message[len-1] == '\n')
+		message[len-1] = 0;
+	printk("%s%s\n", err_level[level], message);
 	spin_unlock_irqrestore(&xfs_err_lock,flags);
-	printk("%s%s", err_level[level], message);
 	BUG_ON(level == CE_PANIC);
 }
 
diff --git a/fs/xfs/support/debug.h b/fs/xfs/support/debug.h
index 4f54dca..2a70cc6 100644
--- a/fs/xfs/support/debug.h
+++ b/fs/xfs/support/debug.h
@@ -38,13 +38,37 @@ extern void assfail(char *expr, char *f, int l);
 
 #ifndef DEBUG
 # define ASSERT(expr)	((void)0)
-#else
+
+#ifndef STATIC
+# define STATIC static noinline
+#endif
+
+#ifndef STATIC_INLINE
+# define STATIC_INLINE static inline
+#endif
+
+#else /* DEBUG */
+
 # define ASSERT(expr)	ASSERT_ALWAYS(expr)
 extern unsigned long random(void);
-#endif
 
 #ifndef STATIC
-# define STATIC static
+# define STATIC noinline
 #endif
 
+/*
+ * We stop inlining of inline functions in debug mode.
+ * Unfortunately, this means static inline in header files
+ * get multiple definitions, so they need to remain static.
+ * This then gives tonnes of warnings about unused but defined
+ * functions, so we need to add the unused attribute to prevent
+ * these spurious warnings.
+ */
+#ifndef STATIC_INLINE
+# define STATIC_INLINE static __attribute__ ((unused)) noinline
+#endif
+
+#endif /* DEBUG */
+
+
 #endif  /* __XFS_SUPPORT_DEBUG_H__ */
diff --git a/fs/xfs/support/move.h b/fs/xfs/support/move.h
index 977879c..324e413 100644
--- a/fs/xfs/support/move.h
+++ b/fs/xfs/support/move.h
@@ -55,7 +55,7 @@ enum uio_seg {
 };
 
 struct uio {
-	struct iovec	*uio_iov;   /* pointer to array of iovecs */
+	struct kvec	*uio_iov;   /* pointer to array of iovecs */
 	int		uio_iovcnt; /* number of iovecs in array */
 	xfs_off_t	uio_offset; /* offset in file this uio corresponds to */
 	int		uio_resid;  /* residual i/o count */
@@ -63,7 +63,7 @@ struct uio {
 };
 
 typedef struct uio uio_t;
-typedef struct iovec iovec_t;
+typedef struct kvec iovec_t;
 
 extern int	xfs_uio_read (caddr_t, size_t, uio_t *);
 
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 4b0cb47..4ca4beb 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -31,7 +31,6 @@
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_acl.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 
 #include <linux/capability.h>
diff --git a/fs/xfs/xfs_alloc_btree.h b/fs/xfs/xfs_alloc_btree.h
index bce81c7..5bd1a2c 100644
--- a/fs/xfs/xfs_alloc_btree.h
+++ b/fs/xfs/xfs_alloc_btree.h
@@ -58,7 +58,6 @@ typedef	struct xfs_btree_sblock xfs_alloc_block_t;
 /*
  * Real block structures have a size equal to the disk block size.
  */
-#define	XFS_ALLOC_BLOCK_SIZE(lev,cur)	(1 << (cur)->bc_blocklog)
 #define	XFS_ALLOC_BLOCK_MAXRECS(lev,cur) ((cur)->bc_mp->m_alloc_mxr[lev != 0])
 #define	XFS_ALLOC_BLOCK_MINRECS(lev,cur) ((cur)->bc_mp->m_alloc_mnr[lev != 0])
 
@@ -87,16 +86,13 @@ typedef	struct xfs_btree_sblock xfs_alloc_block_t;
  * Record, key, and pointer address macros for btree blocks.
  */
 #define	XFS_ALLOC_REC_ADDR(bb,i,cur)	\
-	XFS_BTREE_REC_ADDR(XFS_ALLOC_BLOCK_SIZE(0,cur), xfs_alloc, \
-				bb, i, XFS_ALLOC_BLOCK_MAXRECS(0, cur))
+	XFS_BTREE_REC_ADDR(xfs_alloc, bb, i)
 
 #define	XFS_ALLOC_KEY_ADDR(bb,i,cur)	\
-	XFS_BTREE_KEY_ADDR(XFS_ALLOC_BLOCK_SIZE(1,cur), xfs_alloc, \
-				bb, i, XFS_ALLOC_BLOCK_MAXRECS(1, cur))
+	XFS_BTREE_KEY_ADDR(xfs_alloc, bb, i)
 
 #define	XFS_ALLOC_PTR_ADDR(bb,i,cur)	\
-	XFS_BTREE_PTR_ADDR(XFS_ALLOC_BLOCK_SIZE(1,cur), xfs_alloc, \
-				bb, i, XFS_ALLOC_BLOCK_MAXRECS(1, cur))
+	XFS_BTREE_PTR_ADDR(xfs_alloc, bb, i, XFS_ALLOC_BLOCK_MAXRECS(1, cur))
 
 /*
  * Decrement cursor by one record at the level.
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 9ada7bd..9d358ff 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -57,9 +57,9 @@
  */
 
 #define ATTR_SYSCOUNT	2
-STATIC struct attrnames posix_acl_access;
-STATIC struct attrnames posix_acl_default;
-STATIC struct attrnames *attr_system_names[ATTR_SYSCOUNT];
+static struct attrnames posix_acl_access;
+static struct attrnames posix_acl_default;
+static struct attrnames *attr_system_names[ATTR_SYSCOUNT];
 
 /*========================================================================
  * Function prototypes for the kernel.
@@ -199,18 +199,14 @@ xfs_attr_set_int(xfs_inode_t *dp, const char *name, int namelen,
 		return (error);
 
 	/*
-	 * Determine space new attribute will use, and if it would be
-	 * "local" or "remote" (note: local != inline).
-	 */
-	size = xfs_attr_leaf_newentsize(namelen, valuelen,
-					mp->m_sb.sb_blocksize, &local);
-
-	/*
 	 * If the inode doesn't have an attribute fork, add one.
 	 * (inode must not be locked when we call this routine)
 	 */
 	if (XFS_IFORK_Q(dp) == 0) {
-		if ((error = xfs_bmap_add_attrfork(dp, size, rsvd)))
+		int sf_size = sizeof(xfs_attr_sf_hdr_t) +
+			      XFS_ATTR_SF_ENTSIZE_BYNAME(namelen, valuelen);
+
+		if ((error = xfs_bmap_add_attrfork(dp, sf_size, rsvd)))
 			return(error);
 	}
 
@@ -231,6 +227,13 @@ xfs_attr_set_int(xfs_inode_t *dp, const char *name, int namelen,
 	args.addname = 1;
 	args.oknoent = 1;
 
+	/*
+	 * Determine space new attribute will use, and if it would be
+	 * "local" or "remote" (note: local != inline).
+	 */
+	size = xfs_attr_leaf_newentsize(namelen, valuelen,
+					mp->m_sb.sb_blocksize, &local);
+
 	nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
 	if (local) {
 		if (size > (mp->m_sb.sb_blocksize >> 1)) {
@@ -346,7 +349,7 @@ xfs_attr_set_int(xfs_inode_t *dp, const char *name, int namelen,
 		error = xfs_attr_shortform_to_leaf(&args);
 		if (!error) {
 			error = xfs_bmap_finish(&args.trans, args.flist,
-						*args.firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -973,7 +976,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		error = xfs_attr_leaf_to_node(args);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -1074,7 +1077,6 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			if (!error) {
 				error = xfs_bmap_finish(&args->trans,
 							args->flist,
-							*args->firstblock,
 							&committed);
 			}
 			if (error) {
@@ -1152,7 +1154,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -1307,7 +1309,6 @@ restart:
 			if (!error) {
 				error = xfs_bmap_finish(&args->trans,
 							args->flist,
-							*args->firstblock,
 							&committed);
 			}
 			if (error) {
@@ -1347,7 +1348,7 @@ restart:
 		error = xfs_da_split(state);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -1459,7 +1460,6 @@ restart:
 			if (!error) {
 				error = xfs_bmap_finish(&args->trans,
 							args->flist,
-							*args->firstblock,
 							&committed);
 			}
 			if (error) {
@@ -1594,7 +1594,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 		error = xfs_da_join(state);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -1646,7 +1646,6 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			if (!error) {
 				error = xfs_bmap_finish(&args->trans,
 							args->flist,
-							*args->firstblock,
 							&committed);
 			}
 			if (error) {
@@ -2090,7 +2089,7 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 				  args->flist, NULL);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -2246,7 +2245,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args)
 				    NULL, &done);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						*args->firstblock, &committed);
+						&committed);
 		}
 		if (error) {
 			ASSERT(committed);
@@ -2477,7 +2476,7 @@ posix_acl_default_exists(
 	return xfs_acl_vhasacl_default(vp);
 }
 
-STATIC struct attrnames posix_acl_access = {
+static struct attrnames posix_acl_access = {
 	.attr_name	= "posix_acl_access",
 	.attr_namelen	= sizeof("posix_acl_access") - 1,
 	.attr_get	= posix_acl_access_get,
@@ -2486,7 +2485,7 @@ STATIC struct attrnames posix_acl_access = {
 	.attr_exists	= posix_acl_access_exists,
 };
 
-STATIC struct attrnames posix_acl_default = {
+static struct attrnames posix_acl_default = {
 	.attr_name	= "posix_acl_default",
 	.attr_namelen	= sizeof("posix_acl_default") - 1,
 	.attr_get	= posix_acl_default_get,
@@ -2495,7 +2494,7 @@ STATIC struct attrnames posix_acl_default = {
 	.attr_exists	= posix_acl_default_exists,
 };
 
-STATIC struct attrnames *attr_system_names[] =
+static struct attrnames *attr_system_names[] =
 	{ &posix_acl_access, &posix_acl_default };
 
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 9719bbe..8eab73e 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -94,7 +94,7 @@ STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
  * Namespace helper routines
  *========================================================================*/
 
-STATIC inline attrnames_t *
+STATIC_INLINE attrnames_t *
 xfs_attr_flags_namesp(int flags)
 {
 	return ((flags & XFS_ATTR_SECURE) ? &attr_secure:
@@ -105,7 +105,7 @@ xfs_attr_flags_namesp(int flags)
  * If namespace bits don't match return 0.
  * If all match then return 1.
  */
-STATIC inline int
+STATIC_INLINE int
 xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
 {
 	return XFS_ATTR_NSP_ONDISK(ondisk_flags) == XFS_ATTR_NSP_ARGS_TO_ONDISK(arg_flags);
@@ -116,7 +116,7 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
  * then return 0.
  * If all match or are overridable then return 1.
  */
-STATIC inline int
+STATIC_INLINE int
 xfs_attr_namesp_match_overrides(int arg_flags, int ondisk_flags)
 {
 	if (((arg_flags & ATTR_SECURE) == 0) !=
@@ -150,6 +150,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	int offset;
 	int minforkoff;	/* lower limit on valid forkoff locations */
 	int maxforkoff;	/* upper limit on valid forkoff locations */
+	int dsize;	
 	xfs_mount_t *mp = dp->i_mount;
 
 	offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
@@ -169,8 +170,43 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 		return 0;
 	}
 
-	/* data fork btree root can have at least this many key/ptr pairs */
-	minforkoff = MAX(dp->i_df.if_bytes, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
+	dsize = dp->i_df.if_bytes;
+	
+	switch (dp->i_d.di_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		/* 
+		 * If there is no attr fork and the data fork is extents, 
+		 * determine if creating the default attr fork will result 
+		 * in the extents form migrating to btree. If so, the 
+		 * minimum offset only needs to be the space required for 
+		 * the btree root.
+		 */ 
+		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes > mp->m_attroffset)
+			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
+		break;
+		
+	case XFS_DINODE_FMT_BTREE:
+		/*
+		 * If have data btree then keep forkoff if we have one,
+		 * otherwise we are adding a new attr, so then we set 
+		 * minforkoff to where the btree root can finish so we have 
+		 * plenty of room for attrs
+		 */
+		if (dp->i_d.di_forkoff) {
+			if (offset < dp->i_d.di_forkoff) 
+				return 0;
+			else 
+				return dp->i_d.di_forkoff;
+		} else
+			dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+		break;
+	}
+	
+	/* 
+	 * A data fork btree root must have space for at least 
+	 * MINDBTPTRS key/ptr pairs if the data fork is small or empty.
+	 */
+	minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
 	minforkoff = roundup(minforkoff, 8) >> 3;
 
 	/* attr fork btree root can have at least this many key/ptr pairs */
@@ -336,7 +372,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 	 */
 	totsize -= size;
 	if (totsize == sizeof(xfs_attr_sf_hdr_t) && !args->addname &&
-	    (mp->m_flags & XFS_MOUNT_ATTR2)) {
+	    (mp->m_flags & XFS_MOUNT_ATTR2) && 
+	    (dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) {
 		/*
 		 * Last attribute now removed, revert to original
 		 * inode format making all literal area available
@@ -355,7 +392,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 		dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
 		ASSERT(dp->i_d.di_forkoff);
 		ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || args->addname ||
-			!(mp->m_flags & XFS_MOUNT_ATTR2));
+			!(mp->m_flags & XFS_MOUNT_ATTR2) ||
+			dp->i_d.di_format == XFS_DINODE_FMT_BTREE);
 		dp->i_afp->if_ext_max =
 			XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
 		dp->i_df.if_ext_max =
@@ -748,6 +786,7 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
 				+ be16_to_cpu(name_loc->valuelen);
 	}
 	if ((dp->i_mount->m_flags & XFS_MOUNT_ATTR2) &&
+	    (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
 	    (bytes == sizeof(struct xfs_attr_sf_hdr)))
 		return(-1);
 	return(xfs_attr_shortform_bytesfit(dp, bytes));
@@ -786,6 +825,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 
 	if (forkoff == -1) {
 		ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
+		ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
 
 		/*
 		 * Last attribute was removed, revert to original
diff --git a/fs/xfs/xfs_bit.c b/fs/xfs/xfs_bit.c
index 43be6a7..1afe07f 100644
--- a/fs/xfs/xfs_bit.c
+++ b/fs/xfs/xfs_bit.c
@@ -29,7 +29,7 @@
 /*
  * Index of high bit number in byte, -1 for none set, 0..7 otherwise.
  */
-STATIC const char xfs_highbit[256] = {
+static const char xfs_highbit[256] = {
        -1, 0, 1, 1, 2, 2, 2, 2,			/* 00 .. 07 */
 	3, 3, 3, 3, 3, 3, 3, 3,			/* 08 .. 0f */
 	4, 4, 4, 4, 4, 4, 4, 4,			/* 10 .. 17 */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 498ad50d..8779518 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -185,16 +185,6 @@ xfs_bmap_btree_to_extents(
 	int			*logflagsp, /* inode logging flags */
 	int			whichfork); /* data or attr fork */
 
-#ifdef DEBUG
-/*
- * Check that the extents list for the inode ip is in the right order.
- */
-STATIC void
-xfs_bmap_check_extents(
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	int			whichfork);	/* data or attr fork */
-#endif
-
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
@@ -410,7 +400,6 @@ xfs_bmap_count_leaves(
 STATIC int
 xfs_bmap_disk_count_leaves(
 	xfs_ifork_t		*ifp,
-	xfs_mount_t		*mp,
 	xfs_extnum_t		idx,
 	xfs_bmbt_block_t	*block,
 	int			numrecs,
@@ -684,7 +673,7 @@ xfs_bmap_add_extent(
 		ASSERT(nblks <= da_old);
 		if (nblks < da_old)
 			xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS,
-				(int)(da_old - nblks), rsvd);
+				(int64_t)(da_old - nblks), rsvd);
 	}
 	/*
 	 * Clear out the allocated field, done with it now in any case.
@@ -1209,7 +1198,7 @@ xfs_bmap_add_extent_delay_real(
 		diff = (int)(temp + temp2 - STARTBLOCKVAL(PREV.br_startblock) -
 			(cur ? cur->bc_private.b.allocated : 0));
 		if (diff > 0 &&
-		    xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, -diff, rsvd)) {
+		    xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) {
 			/*
 			 * Ick gross gag me with a spoon.
 			 */
@@ -1220,7 +1209,7 @@ xfs_bmap_add_extent_delay_real(
 					diff--;
 					if (!diff ||
 					    !xfs_mod_incore_sb(ip->i_mount,
-						    XFS_SBS_FDBLOCKS, -diff, rsvd))
+						    XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd))
 						break;
 				}
 				if (temp2) {
@@ -1228,7 +1217,7 @@ xfs_bmap_add_extent_delay_real(
 					diff--;
 					if (!diff ||
 					    !xfs_mod_incore_sb(ip->i_mount,
-						    XFS_SBS_FDBLOCKS, -diff, rsvd))
+						    XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd))
 						break;
 				}
 			}
@@ -2015,7 +2004,7 @@ xfs_bmap_add_extent_hole_delay(
 	if (oldlen != newlen) {
 		ASSERT(oldlen > newlen);
 		xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS,
-			(int)(oldlen - newlen), rsvd);
+			(int64_t)(oldlen - newlen), rsvd);
 		/*
 		 * Nothing to do for disk quota accounting here.
 		 */
@@ -3359,7 +3348,7 @@ xfs_bmap_del_extent(
 	 */
 	ASSERT(da_old >= da_new);
 	if (da_old > da_new)
-		xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, (int)(da_old - da_new),
+		xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, (int64_t)(da_old - da_new),
 			rsvd);
 	if (delta) {
 		/* DELTA: report the original extent. */
@@ -3543,6 +3532,7 @@ xfs_bmap_forkoff_reset(
 	if (whichfork == XFS_ATTR_FORK &&
 	    (ip->i_d.di_format != XFS_DINODE_FMT_DEV) &&
 	    (ip->i_d.di_format != XFS_DINODE_FMT_UUID) &&
+	    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
 	    ((mp->m_attroffset >> 3) > ip->i_d.di_forkoff)) {
 		ip->i_d.di_forkoff = mp->m_attroffset >> 3;
 		ip->i_df.if_ext_max = XFS_IFORK_DSIZE(ip) /
@@ -4079,7 +4069,7 @@ xfs_bmap_add_attrfork(
 		} else
 			XFS_SB_UNLOCK(mp, s);
 	}
-	if ((error = xfs_bmap_finish(&tp, &flist, firstblock, &committed)))
+	if ((error = xfs_bmap_finish(&tp, &flist, &committed)))
 		goto error2;
 	error = xfs_trans_commit(tp, XFS_TRANS_PERM_LOG_RES, NULL);
 	ASSERT(ip->i_df.if_ext_max ==
@@ -4212,7 +4202,6 @@ int						/* error */
 xfs_bmap_finish(
 	xfs_trans_t		**tp,		/* transaction pointer addr */
 	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
-	xfs_fsblock_t		firstblock,	/* controlled ag for allocs */
 	int			*committed)	/* xact committed or not */
 {
 	xfs_efd_log_item_t	*efd;		/* extent free data */
@@ -4533,8 +4522,7 @@ xfs_bmap_read_extents(
 			error0);
 		if (level == 0)
 			break;
-		pp = XFS_BTREE_PTR_ADDR(mp->m_sb.sb_blocksize, xfs_bmbt, block,
-			1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
 		xfs_trans_brelse(tp, bp);
@@ -4577,8 +4565,7 @@ xfs_bmap_read_extents(
 		/*
 		 * Copy records into the extent records.
 		 */
-		frp = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize, xfs_bmbt,
-			block, 1, mp->m_bmap_dmxr[0]);
+		frp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, 1);
 		start = i;
 		for (j = 0; j < num_recs; j++, i++, frp++) {
 			trp = xfs_iext_get_ext(ifp, i);
@@ -4929,28 +4916,28 @@ xfs_bmapi(
 				if (rt) {
 					error = xfs_mod_incore_sb(mp,
 							XFS_SBS_FREXTENTS,
-							-(extsz), (flags &
+							-((int64_t)extsz), (flags &
 							XFS_BMAPI_RSVBLOCKS));
 				} else {
 					error = xfs_mod_incore_sb(mp,
 							XFS_SBS_FDBLOCKS,
-							-(alen), (flags &
+							-((int64_t)alen), (flags &
 							XFS_BMAPI_RSVBLOCKS));
 				}
 				if (!error) {
 					error = xfs_mod_incore_sb(mp,
 							XFS_SBS_FDBLOCKS,
-							-(indlen), (flags &
+							-((int64_t)indlen), (flags &
 							XFS_BMAPI_RSVBLOCKS));
 					if (error && rt)
 						xfs_mod_incore_sb(mp,
 							XFS_SBS_FREXTENTS,
-							extsz, (flags &
+							(int64_t)extsz, (flags &
 							XFS_BMAPI_RSVBLOCKS));
 					else if (error)
 						xfs_mod_incore_sb(mp,
 							XFS_SBS_FDBLOCKS,
-							alen, (flags &
+							(int64_t)alen, (flags &
 							XFS_BMAPI_RSVBLOCKS));
 				}
 
@@ -5616,13 +5603,13 @@ xfs_bunmapi(
 				rtexts = XFS_FSB_TO_B(mp, del.br_blockcount);
 				do_div(rtexts, mp->m_sb.sb_rextsize);
 				xfs_mod_incore_sb(mp, XFS_SBS_FREXTENTS,
-						(int)rtexts, rsvd);
+						(int64_t)rtexts, rsvd);
 				(void)XFS_TRANS_RESERVE_QUOTA_NBLKS(mp,
 					NULL, ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_RTBLKS);
 			} else {
 				xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS,
-						(int)del.br_blockcount, rsvd);
+						(int64_t)del.br_blockcount, rsvd);
 				(void)XFS_TRANS_RESERVE_QUOTA_NBLKS(mp,
 					NULL, ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_REGBLKS);
@@ -6048,32 +6035,6 @@ xfs_bmap_eof(
 }
 
 #ifdef DEBUG
-/*
- * Check that the extents list for the inode ip is in the right order.
- */
-STATIC void
-xfs_bmap_check_extents(
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	int			whichfork)	/* data or attr fork */
-{
-	xfs_bmbt_rec_t		*ep;		/* current extent entry */
-	xfs_extnum_t		idx;		/* extent record index */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
-	xfs_extnum_t		nextents;	/* number of extents in list */
-	xfs_bmbt_rec_t		*nextp;		/* next extent entry */
-
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
-	ep = xfs_iext_get_ext(ifp, 0);
-	for (idx = 0; idx < nextents - 1; idx++) {
-		nextp = xfs_iext_get_ext(ifp, idx + 1);
-		xfs_btree_check_rec(XFS_BTNUM_BMAP, (void *)ep,
-			(void *)(nextp));
-		ep = nextp;
-	}
-}
-
 STATIC
 xfs_buf_t *
 xfs_bmap_get_bp(
@@ -6156,8 +6117,7 @@ xfs_check_block(
 		if (root) {
 			keyp = XFS_BMAP_BROOT_KEY_ADDR(block, i, sz);
 		} else {
-			keyp = XFS_BTREE_KEY_ADDR(mp->m_sb.sb_blocksize,
-				xfs_bmbt, block, i, dmxr);
+			keyp = XFS_BTREE_KEY_ADDR(xfs_bmbt, block, i);
 		}
 
 		if (prevp) {
@@ -6172,15 +6132,14 @@ xfs_check_block(
 		if (root) {
 			pp = XFS_BMAP_BROOT_PTR_ADDR(block, i, sz);
 		} else {
-			pp = XFS_BTREE_PTR_ADDR(mp->m_sb.sb_blocksize,
-				xfs_bmbt, block, i, dmxr);
+			pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, i, dmxr);
 		}
 		for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
 			if (root) {
 				thispa = XFS_BMAP_BROOT_PTR_ADDR(block, j, sz);
 			} else {
-				thispa = XFS_BTREE_PTR_ADDR(mp->m_sb.sb_blocksize,
-					xfs_bmbt, block, j, dmxr);
+				thispa = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, j,
+							    dmxr);
 			}
 			if (*thispa == *pp) {
 				cmn_err(CE_WARN, "%s: thispa(%d) == pp(%d) %Ld",
@@ -6267,8 +6226,7 @@ xfs_bmap_check_leaf_extents(
 		 */
 
 		xfs_check_block(block, mp, 0, 0);
-		pp = XFS_BTREE_PTR_ADDR(mp->m_sb.sb_blocksize, xfs_bmbt, block,
-			1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
 		if (bp_release) {
@@ -6305,11 +6263,9 @@ xfs_bmap_check_leaf_extents(
 		 * conform with the first entry in this one.
 		 */
 
-		ep = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize, xfs_bmbt,
-			block, 1, mp->m_bmap_dmxr[0]);
+		ep = XFS_BTREE_REC_ADDR(xfs_bmbt, block, 1);
 		for (j = 1; j < num_recs; j++) {
-			nextp = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize, xfs_bmbt,
-				block, j + 1, mp->m_bmap_dmxr[0]);
+			nextp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, j + 1);
 			if (lastp) {
 				xfs_btree_check_rec(XFS_BTNUM_BMAP,
 					(void *)lastp, (void *)ep);
@@ -6454,8 +6410,7 @@ xfs_bmap_count_tree(
 		}
 
 		/* Dive to the next level */
-		pp = XFS_BTREE_PTR_ADDR(mp->m_sb.sb_blocksize,
-			xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		if (unlikely((error =
 		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
@@ -6470,7 +6425,7 @@ xfs_bmap_count_tree(
 		for (;;) {
 			nextbno = be64_to_cpu(block->bb_rightsib);
 			numrecs = be16_to_cpu(block->bb_numrecs);
-			if (unlikely(xfs_bmap_disk_count_leaves(ifp, mp,
+			if (unlikely(xfs_bmap_disk_count_leaves(ifp,
 					0, block, numrecs, count) < 0)) {
 				xfs_trans_brelse(tp, bp);
 				XFS_ERROR_REPORT("xfs_bmap_count_tree(2)",
@@ -6518,7 +6473,6 @@ xfs_bmap_count_leaves(
 int
 xfs_bmap_disk_count_leaves(
 	xfs_ifork_t		*ifp,
-	xfs_mount_t		*mp,
 	xfs_extnum_t		idx,
 	xfs_bmbt_block_t	*block,
 	int			numrecs,
@@ -6528,8 +6482,7 @@ xfs_bmap_disk_count_leaves(
 	xfs_bmbt_rec_t	*frp;
 
 	for (b = 1; b <= numrecs; b++) {
-		frp = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize,
-			xfs_bmbt, block, idx + b, mp->m_bmap_dmxr[0]);
+		frp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, idx + b);
 		*count += xfs_bmbt_disk_get_blockcount(frp);
 	}
 	return 0;
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 80e9340..4f24c7e 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -202,7 +202,6 @@ int						/* error */
 xfs_bmap_finish(
 	struct xfs_trans	**tp,		/* transaction pointer addr */
 	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
-	xfs_fsblock_t		firstblock,	/* controlled a.g. for allocs */
 	int			*committed);	/* xact committed or not */
 
 /*
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index a7b835b..0bf192f 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -678,47 +678,6 @@ error0:
 	return error;
 }
 
-#ifdef DEBUG
-/*
- * Get the data from the pointed-to record.
- */
-int
-xfs_bmbt_get_rec(
-	xfs_btree_cur_t		*cur,
-	xfs_fileoff_t		*off,
-	xfs_fsblock_t		*bno,
-	xfs_filblks_t		*len,
-	xfs_exntst_t		*state,
-	int			*stat)
-{
-	xfs_bmbt_block_t	*block;
-	xfs_buf_t		*bp;
-#ifdef DEBUG
-	int			error;
-#endif
-	int			ptr;
-	xfs_bmbt_rec_t		*rp;
-
-	block = xfs_bmbt_get_block(cur, 0, &bp);
-	ptr = cur->bc_ptrs[0];
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, 0, bp)))
-		return error;
-#endif
-	if (ptr > be16_to_cpu(block->bb_numrecs) || ptr <= 0) {
-		*stat = 0;
-		return 0;
-	}
-	rp = XFS_BMAP_REC_IADDR(block, ptr, cur);
-	*off = xfs_bmbt_disk_get_startoff(rp);
-	*bno = xfs_bmbt_disk_get_startblock(rp);
-	*len = xfs_bmbt_disk_get_blockcount(rp);
-	*state = xfs_bmbt_disk_get_state(rp);
-	*stat = 1;
-	return 0;
-}
-#endif
-
 /*
  * Insert one record/level.  Return information to the caller
  * allowing the next level up to proceed if necessary.
@@ -1731,9 +1690,9 @@ xfs_bmdr_to_bmbt(
 	rblock->bb_leftsib = cpu_to_be64(NULLDFSBNO);
 	rblock->bb_rightsib = cpu_to_be64(NULLDFSBNO);
 	dmxr = (int)XFS_BTREE_BLOCK_MAXRECS(dblocklen, xfs_bmdr, 0);
-	fkp = XFS_BTREE_KEY_ADDR(dblocklen, xfs_bmdr, dblock, 1, dmxr);
+	fkp = XFS_BTREE_KEY_ADDR(xfs_bmdr, dblock, 1);
 	tkp = XFS_BMAP_BROOT_KEY_ADDR(rblock, 1, rblocklen);
-	fpp = XFS_BTREE_PTR_ADDR(dblocklen, xfs_bmdr, dblock, 1, dmxr);
+	fpp = XFS_BTREE_PTR_ADDR(xfs_bmdr, dblock, 1, dmxr);
 	tpp = XFS_BMAP_BROOT_PTR_ADDR(rblock, 1, rblocklen);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
@@ -1862,7 +1821,7 @@ xfs_bmbt_delete(
  * xfs_bmbt_get_startblock, xfs_bmbt_get_blockcount and xfs_bmbt_get_state.
  */
 
-STATIC __inline__ void
+STATIC_INLINE void
 __xfs_bmbt_get_all(
 		__uint64_t l0,
 		__uint64_t l1,
@@ -2016,30 +1975,6 @@ xfs_bmbt_disk_get_blockcount(
 }
 
 /*
- * Extract the startblock field from an on disk bmap extent record.
- */
-xfs_fsblock_t
-xfs_bmbt_disk_get_startblock(
-	xfs_bmbt_rec_t	*r)
-{
-#if XFS_BIG_BLKNOS
-	return (((xfs_fsblock_t)INT_GET(r->l0, ARCH_CONVERT) & XFS_MASK64LO(9)) << 43) |
-	       (((xfs_fsblock_t)INT_GET(r->l1, ARCH_CONVERT)) >> 21);
-#else
-#ifdef DEBUG
-	xfs_dfsbno_t	b;
-
-	b = (((xfs_dfsbno_t)INT_GET(r->l0, ARCH_CONVERT) & XFS_MASK64LO(9)) << 43) |
-	    (((xfs_dfsbno_t)INT_GET(r->l1, ARCH_CONVERT)) >> 21);
-	ASSERT((b >> 32) == 0 || ISNULLDSTARTBLOCK(b));
-	return (xfs_fsblock_t)b;
-#else	/* !DEBUG */
-	return (xfs_fsblock_t)(((xfs_dfsbno_t)INT_GET(r->l1, ARCH_CONVERT)) >> 21);
-#endif	/* DEBUG */
-#endif	/* XFS_BIG_BLKNOS */
-}
-
-/*
  * Extract the startoff field from a disk format bmap extent record.
  */
 xfs_fileoff_t
@@ -2049,17 +1984,6 @@ xfs_bmbt_disk_get_startoff(
 	return ((xfs_fileoff_t)INT_GET(r->l0, ARCH_CONVERT) &
 		 XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
 }
-
-xfs_exntst_t
-xfs_bmbt_disk_get_state(
-	xfs_bmbt_rec_t  *r)
-{
-	int	ext_flag;
-
-	ext_flag = (int)((INT_GET(r->l0, ARCH_CONVERT)) >> (64 - BMBT_EXNTFLAG_BITLEN));
-	return xfs_extent_state(xfs_bmbt_disk_get_blockcount(r),
-				ext_flag);
-}
 #endif /* XFS_NATIVE_HOST */
 
 
@@ -2684,9 +2608,9 @@ xfs_bmbt_to_bmdr(
 	dblock->bb_numrecs = rblock->bb_numrecs;
 	dmxr = (int)XFS_BTREE_BLOCK_MAXRECS(dblocklen, xfs_bmdr, 0);
 	fkp = XFS_BMAP_BROOT_KEY_ADDR(rblock, 1, rblocklen);
-	tkp = XFS_BTREE_KEY_ADDR(dblocklen, xfs_bmdr, dblock, 1, dmxr);
+	tkp = XFS_BTREE_KEY_ADDR(xfs_bmdr, dblock, 1);
 	fpp = XFS_BMAP_BROOT_PTR_ADDR(rblock, 1, rblocklen);
-	tpp = XFS_BTREE_PTR_ADDR(dblocklen, xfs_bmdr, dblock, 1, dmxr);
+	tpp = XFS_BTREE_PTR_ADDR(xfs_bmdr, dblock, 1, dmxr);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index 49539de..a77b1b7 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -175,19 +175,11 @@ typedef struct xfs_btree_lblock xfs_bmbt_block_t;
 
 #define XFS_BUF_TO_BMBT_BLOCK(bp)	((xfs_bmbt_block_t *)XFS_BUF_PTR(bp))
 
-#define XFS_BMAP_IBLOCK_SIZE(lev,cur)	(1 << (cur)->bc_blocklog)
 #define XFS_BMAP_RBLOCK_DSIZE(lev,cur)	((cur)->bc_private.b.forksize)
 #define XFS_BMAP_RBLOCK_ISIZE(lev,cur)	\
 	((int)XFS_IFORK_PTR((cur)->bc_private.b.ip, \
 		    (cur)->bc_private.b.whichfork)->if_broot_bytes)
 
-#define XFS_BMAP_BLOCK_DSIZE(lev,cur)	\
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-		XFS_BMAP_RBLOCK_DSIZE(lev,cur) : XFS_BMAP_IBLOCK_SIZE(lev,cur)))
-#define XFS_BMAP_BLOCK_ISIZE(lev,cur)	\
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-		XFS_BMAP_RBLOCK_ISIZE(lev,cur) : XFS_BMAP_IBLOCK_SIZE(lev,cur)))
-
 #define XFS_BMAP_BLOCK_DMAXRECS(lev,cur) \
 	(((lev) == (cur)->bc_nlevels - 1 ? \
 		XFS_BTREE_BLOCK_MAXRECS(XFS_BMAP_RBLOCK_DSIZE(lev,cur), \
@@ -210,37 +202,21 @@ typedef struct xfs_btree_lblock xfs_bmbt_block_t;
 				xfs_bmbt, (lev) == 0) : \
 			((cur)->bc_mp->m_bmap_dmnr[(lev) != 0])))
 
-#define XFS_BMAP_REC_DADDR(bb,i,cur)	\
-	(XFS_BTREE_REC_ADDR(XFS_BMAP_BLOCK_DSIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_DMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
-#define XFS_BMAP_REC_IADDR(bb,i,cur)	\
-	(XFS_BTREE_REC_ADDR(XFS_BMAP_BLOCK_ISIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_IMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
+#define XFS_BMAP_REC_DADDR(bb,i,cur)	(XFS_BTREE_REC_ADDR(xfs_bmbt, bb, i))
+
+#define XFS_BMAP_REC_IADDR(bb,i,cur)	(XFS_BTREE_REC_ADDR(xfs_bmbt, bb, i))
 
 #define XFS_BMAP_KEY_DADDR(bb,i,cur)	\
-	(XFS_BTREE_KEY_ADDR(XFS_BMAP_BLOCK_DSIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_DMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
+	(XFS_BTREE_KEY_ADDR(xfs_bmbt, bb, i))
+
 #define XFS_BMAP_KEY_IADDR(bb,i,cur)	\
-	(XFS_BTREE_KEY_ADDR(XFS_BMAP_BLOCK_ISIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_IMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
+	(XFS_BTREE_KEY_ADDR(xfs_bmbt, bb, i))
 
 #define XFS_BMAP_PTR_DADDR(bb,i,cur)	\
-	(XFS_BTREE_PTR_ADDR(XFS_BMAP_BLOCK_DSIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_DMAXRECS(	\
+	(XFS_BTREE_PTR_ADDR(xfs_bmbt, bb, i, XFS_BMAP_BLOCK_DMAXRECS(	\
 				be16_to_cpu((bb)->bb_level), cur)))
 #define XFS_BMAP_PTR_IADDR(bb,i,cur)	\
-	(XFS_BTREE_PTR_ADDR(XFS_BMAP_BLOCK_ISIZE(			\
-			be16_to_cpu((bb)->bb_level), cur),		\
-			xfs_bmbt, bb, i, XFS_BMAP_BLOCK_IMAXRECS(	\
+	(XFS_BTREE_PTR_ADDR(xfs_bmbt, bb, i, XFS_BMAP_BLOCK_IMAXRECS(	\
 				be16_to_cpu((bb)->bb_level), cur)))
 
 /*
@@ -248,11 +224,11 @@ typedef struct xfs_btree_lblock xfs_bmbt_block_t;
  * we don't have a cursor.
  */
 #define XFS_BMAP_BROOT_REC_ADDR(bb,i,sz) \
-	(XFS_BTREE_REC_ADDR(sz,xfs_bmbt,bb,i,XFS_BMAP_BROOT_MAXRECS(sz)))
+	(XFS_BTREE_REC_ADDR(xfs_bmbt,bb,i))
 #define XFS_BMAP_BROOT_KEY_ADDR(bb,i,sz) \
-	(XFS_BTREE_KEY_ADDR(sz,xfs_bmbt,bb,i,XFS_BMAP_BROOT_MAXRECS(sz)))
+	(XFS_BTREE_KEY_ADDR(xfs_bmbt,bb,i))
 #define XFS_BMAP_BROOT_PTR_ADDR(bb,i,sz) \
-	(XFS_BTREE_PTR_ADDR(sz,xfs_bmbt,bb,i,XFS_BMAP_BROOT_MAXRECS(sz)))
+	(XFS_BTREE_PTR_ADDR(xfs_bmbt,bb,i,XFS_BMAP_BROOT_MAXRECS(sz)))
 
 #define XFS_BMAP_BROOT_NUMRECS(bb)	be16_to_cpu((bb)->bb_numrecs)
 #define XFS_BMAP_BROOT_MAXRECS(sz)	XFS_BTREE_BLOCK_MAXRECS(sz,xfs_bmbt,0)
@@ -315,15 +291,11 @@ extern xfs_exntst_t xfs_bmbt_get_state(xfs_bmbt_rec_t *r);
 
 #ifndef XFS_NATIVE_HOST
 extern void xfs_bmbt_disk_get_all(xfs_bmbt_rec_t *r, xfs_bmbt_irec_t *s);
-extern xfs_exntst_t xfs_bmbt_disk_get_state(xfs_bmbt_rec_t *r);
 extern xfs_filblks_t xfs_bmbt_disk_get_blockcount(xfs_bmbt_rec_t *r);
-extern xfs_fsblock_t xfs_bmbt_disk_get_startblock(xfs_bmbt_rec_t *r);
 extern xfs_fileoff_t xfs_bmbt_disk_get_startoff(xfs_bmbt_rec_t *r);
 #else
 #define xfs_bmbt_disk_get_all(r, s)	xfs_bmbt_get_all(r, s)
-#define xfs_bmbt_disk_get_state(r)	xfs_bmbt_get_state(r)
 #define xfs_bmbt_disk_get_blockcount(r)	xfs_bmbt_get_blockcount(r)
-#define xfs_bmbt_disk_get_startblock(r)	xfs_bmbt_get_blockcount(r)
 #define xfs_bmbt_disk_get_startoff(r)	xfs_bmbt_get_startoff(r)
 #endif /* XFS_NATIVE_HOST */
 
@@ -364,15 +336,6 @@ extern void xfs_bmbt_to_bmdr(xfs_bmbt_block_t *, int, xfs_bmdr_block_t *, int);
 extern int xfs_bmbt_update(struct xfs_btree_cur *, xfs_fileoff_t,
 				xfs_fsblock_t, xfs_filblks_t, xfs_exntst_t);
 
-#ifdef DEBUG
-/*
- * Get the data from the pointed-to record.
- */
-extern int xfs_bmbt_get_rec(struct xfs_btree_cur *, xfs_fileoff_t *,
-				xfs_fsblock_t *, xfs_filblks_t *,
-				xfs_exntst_t *, int *);
-#endif
-
 #endif	/* __KERNEL__ */
 
 #endif	/* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 892b06c..4e27d55 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -122,13 +122,13 @@ extern const __uint32_t	xfs_magics[];
  * Given block size, type prefix, block pointer, and index of requested entry
  * (first entry numbered 1).
  */
-#define	XFS_BTREE_REC_ADDR(bsz,t,bb,i,mxr)	\
+#define	XFS_BTREE_REC_ADDR(t,bb,i)	\
 	((t ## _rec_t *)((char *)(bb) + sizeof(t ## _block_t) + \
 	 ((i) - 1) * sizeof(t ## _rec_t)))
-#define	XFS_BTREE_KEY_ADDR(bsz,t,bb,i,mxr)	\
+#define	XFS_BTREE_KEY_ADDR(t,bb,i)	\
 	((t ## _key_t *)((char *)(bb) + sizeof(t ## _block_t) + \
 	 ((i) - 1) * sizeof(t ## _key_t)))
-#define	XFS_BTREE_PTR_ADDR(bsz,t,bb,i,mxr)	\
+#define	XFS_BTREE_PTR_ADDR(t,bb,i,mxr)	\
 	((t ## _ptr_t *)((char *)(bb) + sizeof(t ## _block_t) + \
 	 (mxr) * sizeof(t ## _key_t) + ((i) - 1) * sizeof(t ## _ptr_t)))
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 7a55c24..6c1bddc 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -660,7 +660,7 @@ xfs_buf_item_committing(xfs_buf_log_item_t *bip, xfs_lsn_t commit_lsn)
 /*
  * This is the ops vector shared by all buf log items.
  */
-STATIC struct xfs_item_ops xfs_buf_item_ops = {
+static struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_buf_item_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_buf_item_format,
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 07c708c..d7e1361 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -21,23 +21,7 @@
 /*
  * This is the structure used to lay out a buf log item in the
  * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.  This structure works only on buffers that
- * reside up to the first TB in the filesystem.  These buffers are
- * generated only by pre-6.2 systems and are known as XFS_LI_6_1_BUF.
- */
-typedef struct xfs_buf_log_format_v1 {
-	unsigned short	blf_type;	/* buf log item type indicator */
-	unsigned short	blf_size;	/* size of this item */
-	__int32_t	blf_blkno;	/* starting blkno of this buf */
-	ushort		blf_flags;	/* misc state */
-	ushort		blf_len;	/* number of blocks in this buf */
-	unsigned int	blf_map_size;	/* size of data bitmap in words */
-	unsigned int	blf_data_map[1];/* variable size bitmap of */
-					/*   regions of buffer in this item */
-} xfs_buf_log_format_v1_t;
-
-/*
- * This is a form of the above structure with a 64 bit blkno field.
+ * have been logged.
  * For 6.2 and beyond, this is XFS_LI_BUF.  We use this to log everything.
  */
 typedef struct xfs_buf_log_format_t {
diff --git a/fs/xfs/xfs_cap.h b/fs/xfs/xfs_cap.h
deleted file mode 100644
index 7a0e482..0000000
--- a/fs/xfs/xfs_cap.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_CAP_H__
-#define __XFS_CAP_H__
-
-/*
- * Capabilities
- */
-typedef __uint64_t xfs_cap_value_t;
-
-typedef struct xfs_cap_set {
-	xfs_cap_value_t	cap_effective;	/* use in capability checks */
-	xfs_cap_value_t	cap_permitted;	/* combined with file attrs */
-	xfs_cap_value_t	cap_inheritable;/* pass through exec */
-} xfs_cap_set_t;
-
-/* On-disk XFS extended attribute names */
-#define SGI_CAP_FILE	"SGI_CAP_FILE"
-#define SGI_CAP_FILE_SIZE	(sizeof(SGI_CAP_FILE)-1)
-#define SGI_CAP_LINUX	"SGI_CAP_LINUX"
-#define SGI_CAP_LINUX_SIZE	(sizeof(SGI_CAP_LINUX)-1)
-
-/*
- * For Linux, we take the bitfields directly from capability.h
- * and no longer attempt to keep this attribute ondisk compatible
- * with IRIX.  Since this attribute is only set on executables,
- * it just doesn't make much sense to try.  We do use a different
- * named attribute though, to avoid confusion.
- */
-
-#ifdef __KERNEL__
-
-#ifdef CONFIG_FS_POSIX_CAP
-
-#include <linux/posix_cap_xattr.h>
-
-struct bhv_vnode;
-
-extern int xfs_cap_vhascap(struct bhv_vnode *);
-extern int xfs_cap_vset(struct bhv_vnode *, void *, size_t);
-extern int xfs_cap_vget(struct bhv_vnode *, void *, size_t);
-extern int xfs_cap_vremove(struct bhv_vnode *);
-
-#define _CAP_EXISTS		xfs_cap_vhascap
-
-#else
-#define xfs_cap_vset(v,p,sz)	(-EOPNOTSUPP)
-#define xfs_cap_vget(v,p,sz)	(-EOPNOTSUPP)
-#define xfs_cap_vremove(v)	(-EOPNOTSUPP)
-#define _CAP_EXISTS		(NULL)
-#endif
-
-#endif	/* __KERNEL__ */
-
-#endif  /* __XFS_CAP_H__ */
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index a68bc1f..aea37df 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1090,8 +1090,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
 		if (blk->magic == XFS_DA_NODE_MAGIC) {
 			node = blk->bp->data;
 			max = be16_to_cpu(node->hdr.count);
-			btreehashval = node->btree[max-1].hashval;
-			blk->hashval = be32_to_cpu(btreehashval);
+			blk->hashval = be32_to_cpu(node->btree[max-1].hashval);
 
 			/*
 			 * Binary search.  (note: small blocks will skip loop)
@@ -2166,21 +2165,6 @@ xfs_da_reada_buf(
 		return rval;
 }
 
-/*
- * Calculate the number of bits needed to hold i different values.
- */
-uint
-xfs_da_log2_roundup(uint i)
-{
-	uint rval;
-
-	for (rval = 0; rval < NBBY * sizeof(i); rval++) {
-		if ((1 << rval) >= i)
-			break;
-	}
-	return(rval);
-}
-
 kmem_zone_t *xfs_da_state_zone;	/* anchor for state struct zone */
 kmem_zone_t *xfs_dabuf_zone;		/* dabuf zone */
 
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 4ab865e..44dabf0 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -249,7 +249,6 @@ int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  xfs_dabuf_t *dead_buf);
 
 uint xfs_da_hashname(const uchar_t *name_string, int name_length);
-uint xfs_da_log2_roundup(uint i);
 xfs_da_state_t *xfs_da_state_alloc(void);
 void xfs_da_state_free(xfs_da_state_t *state);
 
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 50d0fae..b847e6a 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -41,7 +41,6 @@
 #include "xfs_itable.h"
 #include "xfs_dfrag.h"
 #include "xfs_error.h"
-#include "xfs_mac.h"
 #include "xfs_rw.h"
 
 /*
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index b95681b..b1af544 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -132,32 +132,6 @@ xfs_errortag_add(int error_tag, xfs_mount_t *mp)
 }
 
 int
-xfs_errortag_clear(int error_tag, xfs_mount_t *mp)
-{
-	int i;
-	int64_t fsid;
-
-	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
-
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
-		if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
-			xfs_etest[i] = 0;
-			xfs_etest_fsid[i] = 0LL;
-			kmem_free(xfs_etest_fsname[i],
-				  strlen(xfs_etest_fsname[i]) + 1);
-			xfs_etest_fsname[i] = NULL;
-			cmn_err(CE_WARN, "Cleared XFS error tag #%d",
-				error_tag);
-			return 0;
-		}
-	}
-
-	cmn_err(CE_WARN, "XFS error tag %d not on", error_tag);
-
-	return 1;
-}
-
-int
 xfs_errortag_clearall_umount(int64_t fsid, char *fsname, int loud)
 {
 	int i;
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 0893e16..5599ada 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -144,7 +144,6 @@ extern void xfs_error_test_init(void);
 #endif /* __ANSI_CPP__ */
 
 extern int xfs_errortag_add(int error_tag, xfs_mount_t *mp);
-extern int xfs_errortag_clear(int error_tag, xfs_mount_t *mp);
 extern int xfs_errortag_clearall(xfs_mount_t *mp);
 extern int xfs_errortag_clearall_umount(int64_t fsid, char *fsname, int loud);
 #else
@@ -180,6 +179,6 @@ extern void xfs_fs_cmn_err(int level, struct xfs_mount *mp, char *fmt, ...);
 	xfs_fs_cmn_err(level, mp, fmt "  Unmount and run xfs_repair.", ## args)
 
 #define xfs_fs_mount_cmn_err(f, fmt, args...) \
-	((f & XFS_MFSI_QUIET)? cmn_err(CE_WARN, "XFS: " fmt, ## args) : (void)0)
+	((f & XFS_MFSI_QUIET)? (void)0 : cmn_err(CE_WARN, "XFS: " fmt, ## args))
 
 #endif	/* __XFS_ERROR_H__ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 6dba781..3b14427 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -227,7 +227,7 @@ xfs_efi_item_committing(xfs_efi_log_item_t *efip, xfs_lsn_t lsn)
 /*
  * This is the ops vector shared by all efi log items.
  */
-STATIC struct xfs_item_ops xfs_efi_item_ops = {
+static struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_efi_item_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_efi_item_format,
@@ -525,7 +525,7 @@ xfs_efd_item_committing(xfs_efd_log_item_t *efip, xfs_lsn_t lsn)
 /*
  * This is the ops vector shared by all efd log items.
  */
-STATIC struct xfs_item_ops xfs_efd_item_ops = {
+static struct xfs_item_ops xfs_efd_item_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_efd_item_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_efd_item_format,
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index c064e72..32c37c1 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -250,8 +250,7 @@ xfs_growfs_data_private(
 		block->bb_numrecs = cpu_to_be16(1);
 		block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
 		block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize, xfs_alloc,
-			block, 1, mp->m_alloc_mxr[0]);
+		arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
@@ -272,8 +271,7 @@ xfs_growfs_data_private(
 		block->bb_numrecs = cpu_to_be16(1);
 		block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
 		block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_BTREE_REC_ADDR(mp->m_sb.sb_blocksize, xfs_alloc,
-			block, 1, mp->m_alloc_mxr[0]);
+		arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
@@ -460,7 +458,7 @@ xfs_fs_counts(
 {
 	unsigned long	s;
 
-	xfs_icsb_sync_counters_lazy(mp);
+	xfs_icsb_sync_counters_flags(mp, XFS_ICSB_LAZY_COUNT);
 	s = XFS_SB_LOCK(mp);
 	cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 	cnt->freertx = mp->m_sb.sb_frextents;
@@ -491,7 +489,7 @@ xfs_reserve_blocks(
 	__uint64_t              *inval,
 	xfs_fsop_resblks_t      *outval)
 {
-	__int64_t		lcounter, delta;
+	__int64_t		lcounter, delta, fdblks_delta;
 	__uint64_t		request;
 	unsigned long		s;
 
@@ -504,17 +502,35 @@ xfs_reserve_blocks(
 	}
 
 	request = *inval;
+
+	/*
+	 * With per-cpu counters, this becomes an interesting
+	 * problem. we needto work out if we are freeing or allocation
+	 * blocks first, then we can do the modification as necessary.
+	 *
+	 * We do this under the XFS_SB_LOCK so that if we are near
+	 * ENOSPC, we will hold out any changes while we work out
+	 * what to do. This means that the amount of free space can
+	 * change while we do this, so we need to retry if we end up
+	 * trying to reserve more space than is available.
+	 *
+	 * We also use the xfs_mod_incore_sb() interface so that we
+	 * don't have to care about whether per cpu counter are
+	 * enabled, disabled or even compiled in....
+	 */
+retry:
 	s = XFS_SB_LOCK(mp);
+	xfs_icsb_sync_counters_flags(mp, XFS_ICSB_SB_LOCKED);
 
 	/*
 	 * If our previous reservation was larger than the current value,
 	 * then move any unused blocks back to the free pool.
 	 */
-
+	fdblks_delta = 0;
 	if (mp->m_resblks > request) {
 		lcounter = mp->m_resblks_avail - request;
 		if (lcounter  > 0) {		/* release unused blocks */
-			mp->m_sb.sb_fdblocks += lcounter;
+			fdblks_delta = lcounter;
 			mp->m_resblks_avail -= lcounter;
 		}
 		mp->m_resblks = request;
@@ -522,24 +538,50 @@ xfs_reserve_blocks(
 		__int64_t	free;
 
 		free =  mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
+		if (!free)
+			goto out; /* ENOSPC and fdblks_delta = 0 */
+
 		delta = request - mp->m_resblks;
 		lcounter = free - delta;
 		if (lcounter < 0) {
 			/* We can't satisfy the request, just get what we can */
 			mp->m_resblks += free;
 			mp->m_resblks_avail += free;
+			fdblks_delta = -free;
 			mp->m_sb.sb_fdblocks = XFS_ALLOC_SET_ASIDE(mp);
 		} else {
+			fdblks_delta = -delta;
 			mp->m_sb.sb_fdblocks =
 				lcounter + XFS_ALLOC_SET_ASIDE(mp);
 			mp->m_resblks = request;
 			mp->m_resblks_avail += delta;
 		}
 	}
-
+out:
 	outval->resblks = mp->m_resblks;
 	outval->resblks_avail = mp->m_resblks_avail;
 	XFS_SB_UNLOCK(mp, s);
+
+	if (fdblks_delta) {
+		/*
+		 * If we are putting blocks back here, m_resblks_avail is
+		 * already at it's max so this will put it in the free pool.
+		 *
+		 * If we need space, we'll either succeed in getting it
+		 * from the free block count or we'll get an enospc. If
+		 * we get a ENOSPC, it means things changed while we were
+		 * calculating fdblks_delta and so we should try again to
+		 * see if there is anything left to reserve.
+		 *
+		 * Don't set the reserved flag here - we don't want to reserve
+		 * the extra reserve blocks from the reserve.....
+		 */
+		int error;
+		error = xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, fdblks_delta, 0);
+		if (error == ENOSPC)
+			goto retry;
+	}
+
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index a446e5a..b5feb3e 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -342,7 +342,7 @@ xfs_ialloc_ag_alloc(
 	return 0;
 }
 
-STATIC __inline xfs_agnumber_t
+STATIC_INLINE xfs_agnumber_t
 xfs_ialloc_next_ag(
 	xfs_mount_t	*mp)
 {
diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h
index 2c0e498..bf8e9af 100644
--- a/fs/xfs/xfs_ialloc_btree.h
+++ b/fs/xfs/xfs_ialloc_btree.h
@@ -89,7 +89,6 @@ typedef	struct xfs_btree_sblock xfs_inobt_block_t;
 /*
  * Real block structures have a size equal to the disk block size.
  */
-#define	XFS_INOBT_BLOCK_SIZE(lev,cur)	(1 << (cur)->bc_blocklog)
 #define	XFS_INOBT_BLOCK_MAXRECS(lev,cur) ((cur)->bc_mp->m_inobt_mxr[lev != 0])
 #define	XFS_INOBT_BLOCK_MINRECS(lev,cur) ((cur)->bc_mp->m_inobt_mnr[lev != 0])
 #define	XFS_INOBT_IS_LAST_REC(cur)	\
@@ -110,14 +109,13 @@ typedef	struct xfs_btree_sblock xfs_inobt_block_t;
  * Record, key, and pointer address macros for btree blocks.
  */
 #define XFS_INOBT_REC_ADDR(bb,i,cur) \
-	(XFS_BTREE_REC_ADDR(XFS_INOBT_BLOCK_SIZE(0,cur), xfs_inobt, bb, \
-				i, XFS_INOBT_BLOCK_MAXRECS(0, cur)))
+	(XFS_BTREE_REC_ADDR(xfs_inobt, bb, i))
+
 #define	XFS_INOBT_KEY_ADDR(bb,i,cur) \
-	(XFS_BTREE_KEY_ADDR(XFS_INOBT_BLOCK_SIZE(1,cur), xfs_inobt, bb, \
-				i, XFS_INOBT_BLOCK_MAXRECS(1, cur)))
+	(XFS_BTREE_KEY_ADDR(xfs_inobt, bb, i))
 
 #define	XFS_INOBT_PTR_ADDR(bb,i,cur) \
-	(XFS_BTREE_PTR_ADDR(XFS_INOBT_BLOCK_SIZE(1,cur), xfs_inobt, bb, \
+	(XFS_BTREE_PTR_ADDR(xfs_inobt, bb, \
 				i, XFS_INOBT_BLOCK_MAXRECS(1, cur)))
 
 /*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 44dfac5..3da9829 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -47,7 +47,6 @@
 #include "xfs_utils.h"
 #include "xfs_dir2_trace.h"
 #include "xfs_quota.h"
-#include "xfs_mac.h"
 #include "xfs_acl.h"
 
 
@@ -1699,8 +1698,7 @@ xfs_itruncate_finish(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		error = xfs_bmap_finish(tp, &free_list, first_block,
-					&committed);
+		error = xfs_bmap_finish(tp, &free_list, &committed);
 		ntp = *tp;
 		if (error) {
 			/*
@@ -1810,7 +1808,7 @@ xfs_igrow_start(
 	 * and any blocks between the old and new file sizes.
 	 */
 	error = xfs_zero_eof(XFS_ITOV(ip), &ip->i_iocore, new_size,
-			     ip->i_d.di_size, new_size);
+			     ip->i_d.di_size);
 	return error;
 }
 
@@ -2125,7 +2123,7 @@ xfs_iunlink_remove(
 	return 0;
 }
 
-static __inline__ int xfs_inode_clean(xfs_inode_t *ip)
+STATIC_INLINE int xfs_inode_clean(xfs_inode_t *ip)
 {
 	return (((ip->i_itemp == NULL) ||
 		!(ip->i_itemp->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
@@ -2707,10 +2705,24 @@ xfs_idestroy(
 	ktrace_free(ip->i_dir_trace);
 #endif
 	if (ip->i_itemp) {
-		/* XXXdpd should be able to assert this but shutdown
-		 * is leaving the AIL behind. */
-		ASSERT(((ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL) == 0) ||
-		       XFS_FORCED_SHUTDOWN(ip->i_mount));
+		/*
+		 * Only if we are shutting down the fs will we see an
+		 * inode still in the AIL. If it is there, we should remove
+		 * it to prevent a use-after-free from occurring.
+		 */
+		xfs_mount_t	*mp = ip->i_mount;
+		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
+		int		s;
+
+		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
+				       XFS_FORCED_SHUTDOWN(ip->i_mount));
+		if (lip->li_flags & XFS_LI_IN_AIL) {
+			AIL_LOCK(mp, s);
+			if (lip->li_flags & XFS_LI_IN_AIL)
+				xfs_trans_delete_ail(mp, lip, s);
+			else
+				AIL_UNLOCK(mp, s);
+		}
 		xfs_inode_item_destroy(ip);
 	}
 	kmem_zone_free(xfs_inode_zone, ip);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index a7a9225..565d470 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -887,7 +887,7 @@ xfs_inode_item_committing(
 /*
  * This is the ops vector shared by all buf log items.
  */
-STATIC struct xfs_item_ops xfs_inode_item_ops = {
+static struct xfs_item_ops xfs_inode_item_ops = {
 	.iop_size	= (uint(*)(xfs_log_item_t*))xfs_inode_item_size,
 	.iop_format	= (void(*)(xfs_log_item_t*, xfs_log_iovec_t*))
 					xfs_inode_item_format,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1965512..cc6a7b5 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -43,8 +43,6 @@
 #include "xfs_itable.h"
 #include "xfs_rw.h"
 #include "xfs_acl.h"
-#include "xfs_cap.h"
-#include "xfs_mac.h"
 #include "xfs_attr.h"
 #include "xfs_buf_item.h"
 #include "xfs_trans_space.h"
@@ -542,7 +540,7 @@ xfs_iomap_write_direct(
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_bmap_finish(&tp, &free_list, firstfsb, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error)
 		goto error0;
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
@@ -838,8 +836,7 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto trans_cancel;
 
-			error = xfs_bmap_finish(&tp, &free_list,
-					first_block, &committed);
+			error = xfs_bmap_finish(&tp, &free_list, &committed);
 			if (error)
 				goto trans_cancel;
 
@@ -947,8 +944,7 @@ xfs_iomap_write_unwritten(
 		if (error)
 			goto error_on_bmapi_transaction;
 
-		error = xfs_bmap_finish(&(tp), &(free_list),
-				firstfsb, &committed);
+		error = xfs_bmap_finish(&(tp), &(free_list), &committed);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 3cb678e..ca74d3f 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1514,7 +1514,6 @@ xlog_recover_reorder_trans(
 {
 	xlog_recover_item_t	*first_item, *itemq, *itemq_next;
 	xfs_buf_log_format_t	*buf_f;
-	xfs_buf_log_format_v1_t	*obuf_f;
 	ushort			flags = 0;
 
 	first_item = itemq = trans->r_itemq;
@@ -1522,29 +1521,16 @@ xlog_recover_reorder_trans(
 	do {
 		itemq_next = itemq->ri_next;
 		buf_f = (xfs_buf_log_format_t *)itemq->ri_buf[0].i_addr;
-		switch (ITEM_TYPE(itemq)) {
-		case XFS_LI_BUF:
-			flags = buf_f->blf_flags;
-			break;
-		case XFS_LI_6_1_BUF:
-		case XFS_LI_5_3_BUF:
-			obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-			flags = obuf_f->blf_flags;
-			break;
-		}
 
 		switch (ITEM_TYPE(itemq)) {
 		case XFS_LI_BUF:
-		case XFS_LI_6_1_BUF:
-		case XFS_LI_5_3_BUF:
+			flags = buf_f->blf_flags;
 			if (!(flags & XFS_BLI_CANCEL)) {
 				xlog_recover_insert_item_frontq(&trans->r_itemq,
 								itemq);
 				break;
 			}
 		case XFS_LI_INODE:
-		case XFS_LI_6_1_INODE:
-		case XFS_LI_5_3_INODE:
 		case XFS_LI_DQUOT:
 		case XFS_LI_QUOTAOFF:
 		case XFS_LI_EFD:
@@ -1583,7 +1569,6 @@ xlog_recover_do_buffer_pass1(
 	xfs_buf_cancel_t	*nextp;
 	xfs_buf_cancel_t	*prevp;
 	xfs_buf_cancel_t	**bucket;
-	xfs_buf_log_format_v1_t	*obuf_f;
 	xfs_daddr_t		blkno = 0;
 	uint			len = 0;
 	ushort			flags = 0;
@@ -1594,13 +1579,6 @@ xlog_recover_do_buffer_pass1(
 		len = buf_f->blf_len;
 		flags = buf_f->blf_flags;
 		break;
-	case XFS_LI_6_1_BUF:
-	case XFS_LI_5_3_BUF:
-		obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-		blkno = (xfs_daddr_t) obuf_f->blf_blkno;
-		len = obuf_f->blf_len;
-		flags = obuf_f->blf_flags;
-		break;
 	}
 
 	/*
@@ -1746,7 +1724,6 @@ xlog_recover_do_buffer_pass2(
 	xlog_t			*log,
 	xfs_buf_log_format_t	*buf_f)
 {
-	xfs_buf_log_format_v1_t	*obuf_f;
 	xfs_daddr_t		blkno = 0;
 	ushort			flags = 0;
 	uint			len = 0;
@@ -1757,13 +1734,6 @@ xlog_recover_do_buffer_pass2(
 		flags = buf_f->blf_flags;
 		len = buf_f->blf_len;
 		break;
-	case XFS_LI_6_1_BUF:
-	case XFS_LI_5_3_BUF:
-		obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-		blkno = (xfs_daddr_t) obuf_f->blf_blkno;
-		flags = obuf_f->blf_flags;
-		len = (xfs_daddr_t) obuf_f->blf_len;
-		break;
 	}
 
 	return xlog_check_buffer_cancelled(log, blkno, len, flags);
@@ -1799,7 +1769,6 @@ xlog_recover_do_inode_buffer(
 	int			inodes_per_buf;
 	xfs_agino_t		*logged_nextp;
 	xfs_agino_t		*buffer_nextp;
-	xfs_buf_log_format_v1_t	*obuf_f;
 	unsigned int		*data_map = NULL;
 	unsigned int		map_size = 0;
 
@@ -1808,12 +1777,6 @@ xlog_recover_do_inode_buffer(
 		data_map = buf_f->blf_data_map;
 		map_size = buf_f->blf_map_size;
 		break;
-	case XFS_LI_6_1_BUF:
-	case XFS_LI_5_3_BUF:
-		obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-		data_map = obuf_f->blf_data_map;
-		map_size = obuf_f->blf_map_size;
-		break;
 	}
 	/*
 	 * Set the variables corresponding to the current region to
@@ -1912,7 +1875,6 @@ xlog_recover_do_reg_buffer(
 	int			i;
 	int			bit;
 	int			nbits;
-	xfs_buf_log_format_v1_t	*obuf_f;
 	unsigned int		*data_map = NULL;
 	unsigned int		map_size = 0;
 	int                     error;
@@ -1922,12 +1884,6 @@ xlog_recover_do_reg_buffer(
 		data_map = buf_f->blf_data_map;
 		map_size = buf_f->blf_map_size;
 		break;
-	case XFS_LI_6_1_BUF:
-	case XFS_LI_5_3_BUF:
-		obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-		data_map = obuf_f->blf_data_map;
-		map_size = obuf_f->blf_map_size;
-		break;
 	}
 	bit = 0;
 	i = 1;  /* 0 is the buf format structure */
@@ -2160,7 +2116,6 @@ xlog_recover_do_buffer_trans(
 	int			pass)
 {
 	xfs_buf_log_format_t	*buf_f;
-	xfs_buf_log_format_v1_t	*obuf_f;
 	xfs_mount_t		*mp;
 	xfs_buf_t		*bp;
 	int			error;
@@ -2197,13 +2152,6 @@ xlog_recover_do_buffer_trans(
 		len = buf_f->blf_len;
 		flags = buf_f->blf_flags;
 		break;
-	case XFS_LI_6_1_BUF:
-	case XFS_LI_5_3_BUF:
-		obuf_f = (xfs_buf_log_format_v1_t*)buf_f;
-		blkno = obuf_f->blf_blkno;
-		len = obuf_f->blf_len;
-		flags = obuf_f->blf_flags;
-		break;
 	default:
 		xfs_fs_cmn_err(CE_ALERT, log->l_mp,
 			"xfs_log_recover: unknown buffer type 0x%x, logdev %s",
@@ -2830,9 +2778,7 @@ xlog_recover_do_trans(
 		 * where xfs_daddr_t is 32-bits but mount will warn us
 		 * off a > 1 TB filesystem before we get here.
 		 */
-		if ((ITEM_TYPE(item) == XFS_LI_BUF) ||
-		    (ITEM_TYPE(item) == XFS_LI_6_1_BUF) ||
-		    (ITEM_TYPE(item) == XFS_LI_5_3_BUF)) {
+		if ((ITEM_TYPE(item) == XFS_LI_BUF)) {
 			if  ((error = xlog_recover_do_buffer_trans(log, item,
 								 pass)))
 				break;
@@ -3902,6 +3848,9 @@ xlog_do_recover(
 	ASSERT(XFS_SB_GOOD_VERSION(sbp));
 	xfs_buf_relse(bp);
 
+	/* We've re-read the superblock so re-initialize per-cpu counters */
+	xfs_icsb_reinit_counters(log->l_mp);
+
 	xlog_recover_check_summary(log);
 
 	/* Normal transactions can now occur */
diff --git a/fs/xfs/xfs_mac.h b/fs/xfs/xfs_mac.h
deleted file mode 100644
index 18e0e98..0000000
--- a/fs/xfs/xfs_mac.h
+++ /dev/null
@@ -1,106 +0,0 @@
-/*
- * Copyright (c) 2001-2002,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_MAC_H__
-#define __XFS_MAC_H__
-
-/*
- * Mandatory Access Control
- *
- * Layout of a composite MAC label:
- * ml_list contains the list of categories (MSEN) followed by the list of
- * divisions (MINT). This is actually a header for the data structure which
- * will have an ml_list with more than one element.
- *
- *      -------------------------------
- *      | ml_msen_type | ml_mint_type |
- *      -------------------------------
- *      | ml_level     | ml_grade     |
- *      -------------------------------
- *      | ml_catcount                 |
- *      -------------------------------
- *      | ml_divcount                 |
- *      -------------------------------
- *      | category 1                  |
- *      | . . .                       |
- *      | category N                  | (where N = ml_catcount)
- *      -------------------------------
- *      | division 1                  |
- *      | . . .                       |
- *      | division M                  | (where M = ml_divcount)
- *      -------------------------------
- */
-#define XFS_MAC_MAX_SETS	250
-typedef struct xfs_mac_label {
-	__uint8_t	ml_msen_type;	/* MSEN label type */
-	__uint8_t	ml_mint_type;	/* MINT label type */
-	__uint8_t	ml_level;	/* Hierarchical level */
-	__uint8_t	ml_grade;	/* Hierarchical grade */
-	__uint16_t	ml_catcount;	/* Category count */
-	__uint16_t	ml_divcount;	/* Division count */
-					/* Category set, then Division set */
-	__uint16_t	ml_list[XFS_MAC_MAX_SETS];
-} xfs_mac_label_t;
-
-/* MSEN label type names. Choose an upper case ASCII character.  */
-#define XFS_MSEN_ADMIN_LABEL	'A'	/* Admin: low<admin != tcsec<high */
-#define XFS_MSEN_EQUAL_LABEL	'E'	/* Wildcard - always equal */
-#define XFS_MSEN_HIGH_LABEL	'H'	/* System High - always dominates */
-#define XFS_MSEN_MLD_HIGH_LABEL	'I'	/* System High, multi-level dir */
-#define XFS_MSEN_LOW_LABEL	'L'	/* System Low - always dominated */
-#define XFS_MSEN_MLD_LABEL	'M'	/* TCSEC label on a multi-level dir */
-#define XFS_MSEN_MLD_LOW_LABEL	'N'	/* System Low, multi-level dir */
-#define XFS_MSEN_TCSEC_LABEL	'T'	/* TCSEC label */
-#define XFS_MSEN_UNKNOWN_LABEL	'U'	/* unknown label */
-
-/* MINT label type names. Choose a lower case ASCII character.  */
-#define XFS_MINT_BIBA_LABEL	'b'	/* Dual of a TCSEC label */
-#define XFS_MINT_EQUAL_LABEL	'e'	/* Wildcard - always equal */
-#define XFS_MINT_HIGH_LABEL	'h'	/* High Grade - always dominates */
-#define XFS_MINT_LOW_LABEL	'l'	/* Low Grade - always dominated */
-
-/* On-disk XFS extended attribute names */
-#define SGI_MAC_FILE	"SGI_MAC_FILE"
-#define SGI_MAC_FILE_SIZE	(sizeof(SGI_MAC_FILE)-1)
-
-
-#ifdef __KERNEL__
-
-#ifdef CONFIG_FS_POSIX_MAC
-
-/* NOT YET IMPLEMENTED */
-
-#define MACEXEC		00100
-#define MACWRITE	00200
-#define MACREAD		00400
-
-struct xfs_inode;
-extern int  xfs_mac_iaccess(struct xfs_inode *, mode_t, cred_t *);
-
-#define _MAC_XFS_IACCESS(i,m,c) (xfs_mac_iaccess(i,m,c))
-#define _MAC_VACCESS(v,c,m)	(xfs_mac_vaccess(v,c,m))
-#define _MAC_EXISTS		xfs_mac_vhaslabel
-
-#else
-#define _MAC_XFS_IACCESS(i,m,c)	(0)
-#define _MAC_VACCESS(v,c,m)	(0)
-#define _MAC_EXISTS		(NULL)
-#endif
-
-#endif	/* __KERNEL__ */
-
-#endif	/* __XFS_MAC_H__ */
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 9dfae18..3bed0cf 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -52,21 +52,19 @@ STATIC void	xfs_unmountfs_wait(xfs_mount_t *);
 
 #ifdef HAVE_PERCPU_SB
 STATIC void	xfs_icsb_destroy_counters(xfs_mount_t *);
-STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t, int);
+STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
+						int, int);
 STATIC void	xfs_icsb_sync_counters(xfs_mount_t *);
 STATIC int	xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t,
-						int, int);
-STATIC int	xfs_icsb_modify_counters_locked(xfs_mount_t *, xfs_sb_field_t,
-						int, int);
+						int64_t, int);
 STATIC int	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
 
 #else
 
 #define xfs_icsb_destroy_counters(mp)			do { } while (0)
-#define xfs_icsb_balance_counter(mp, a, b)		do { } while (0)
+#define xfs_icsb_balance_counter(mp, a, b, c)		do { } while (0)
 #define xfs_icsb_sync_counters(mp)			do { } while (0)
 #define xfs_icsb_modify_counters(mp, a, b, c)		do { } while (0)
-#define xfs_icsb_modify_counters_locked(mp, a, b, c)	do { } while (0)
 
 #endif
 
@@ -545,9 +543,8 @@ xfs_readsb(xfs_mount_t *mp, int flags)
 		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
 	}
 
-	xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
-	xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
-	xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
+	/* Initialize per-cpu counters */
+	xfs_icsb_reinit_counters(mp);
 
 	mp->m_sb_bp = bp;
 	xfs_buf_relse(bp);
@@ -1254,8 +1251,11 @@ xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
  * The SB_LOCK must be held when this routine is called.
  */
 int
-xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
-			int delta, int rsvd)
+xfs_mod_incore_sb_unlocked(
+	xfs_mount_t	*mp,
+	xfs_sb_field_t	field,
+	int64_t		delta,
+	int		rsvd)
 {
 	int		scounter;	/* short counter for 32 bit fields */
 	long long	lcounter;	/* long counter for 64 bit fields */
@@ -1287,7 +1287,6 @@ xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
 		mp->m_sb.sb_ifree = lcounter;
 		return 0;
 	case XFS_SBS_FDBLOCKS:
-
 		lcounter = (long long)
 			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
@@ -1418,7 +1417,11 @@ xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
  * routine to do the work.
  */
 int
-xfs_mod_incore_sb(xfs_mount_t *mp, xfs_sb_field_t field, int delta, int rsvd)
+xfs_mod_incore_sb(
+	xfs_mount_t	*mp,
+	xfs_sb_field_t	field,
+	int64_t		delta,
+	int		rsvd)
 {
 	unsigned long	s;
 	int	status;
@@ -1485,9 +1488,11 @@ xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd)
 		case XFS_SBS_IFREE:
 		case XFS_SBS_FDBLOCKS:
 			if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
-				status = xfs_icsb_modify_counters_locked(mp,
+				XFS_SB_UNLOCK(mp, s);
+				status = xfs_icsb_modify_counters(mp,
 							msbp->msb_field,
 							msbp->msb_delta, rsvd);
+				s = XFS_SB_LOCK(mp);
 				break;
 			}
 			/* FALLTHROUGH */
@@ -1521,11 +1526,12 @@ xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd)
 			case XFS_SBS_IFREE:
 			case XFS_SBS_FDBLOCKS:
 				if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
-					status =
-					    xfs_icsb_modify_counters_locked(mp,
+					XFS_SB_UNLOCK(mp, s);
+					status = xfs_icsb_modify_counters(mp,
 							msbp->msb_field,
 							-(msbp->msb_delta),
 							rsvd);
+					s = XFS_SB_LOCK(mp);
 					break;
 				}
 				/* FALLTHROUGH */
@@ -1733,14 +1739,17 @@ xfs_icsb_cpu_notify(
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
 		break;
 	case CPU_ONLINE:
-		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
-		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
-		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
+		xfs_icsb_lock(mp);
+		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0, 0);
+		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0, 0);
+		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0, 0);
+		xfs_icsb_unlock(mp);
 		break;
 	case CPU_DEAD:
 		/* Disable all the counters, then fold the dead cpu's
 		 * count into the total on the global superblock and
 		 * re-enable the counters. */
+		xfs_icsb_lock(mp);
 		s = XFS_SB_LOCK(mp);
 		xfs_icsb_disable_counter(mp, XFS_SBS_ICOUNT);
 		xfs_icsb_disable_counter(mp, XFS_SBS_IFREE);
@@ -1752,10 +1761,14 @@ xfs_icsb_cpu_notify(
 
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
 
-		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, XFS_ICSB_SB_LOCKED);
-		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, XFS_ICSB_SB_LOCKED);
-		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, XFS_ICSB_SB_LOCKED);
+		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT,
+					 XFS_ICSB_SB_LOCKED, 0);
+		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE,
+					 XFS_ICSB_SB_LOCKED, 0);
+		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS,
+					 XFS_ICSB_SB_LOCKED, 0);
 		XFS_SB_UNLOCK(mp, s);
+		xfs_icsb_unlock(mp);
 		break;
 	}
 
@@ -1784,6 +1797,9 @@ xfs_icsb_init_counters(
 		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
 	}
+
+	mutex_init(&mp->m_icsb_mutex);
+
 	/*
 	 * start with all counters disabled so that the
 	 * initial balance kicks us off correctly
@@ -1792,6 +1808,22 @@ xfs_icsb_init_counters(
 	return 0;
 }
 
+void
+xfs_icsb_reinit_counters(
+	xfs_mount_t	*mp)
+{
+	xfs_icsb_lock(mp);
+	/*
+	 * start with all counters disabled so that the
+	 * initial balance kicks us off correctly
+	 */
+	mp->m_icsb_counters = -1;
+	xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0, 0);
+	xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0, 0);
+	xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0, 0);
+	xfs_icsb_unlock(mp);
+}
+
 STATIC void
 xfs_icsb_destroy_counters(
 	xfs_mount_t	*mp)
@@ -1800,9 +1832,10 @@ xfs_icsb_destroy_counters(
 		unregister_hotcpu_notifier(&mp->m_icsb_notifier);
 		free_percpu(mp->m_sb_cnts);
 	}
+	mutex_destroy(&mp->m_icsb_mutex);
 }
 
-STATIC inline void
+STATIC_INLINE void
 xfs_icsb_lock_cntr(
 	xfs_icsb_cnts_t	*icsbp)
 {
@@ -1811,7 +1844,7 @@ xfs_icsb_lock_cntr(
 	}
 }
 
-STATIC inline void
+STATIC_INLINE void
 xfs_icsb_unlock_cntr(
 	xfs_icsb_cnts_t	*icsbp)
 {
@@ -1819,7 +1852,7 @@ xfs_icsb_unlock_cntr(
 }
 
 
-STATIC inline void
+STATIC_INLINE void
 xfs_icsb_lock_all_counters(
 	xfs_mount_t	*mp)
 {
@@ -1832,7 +1865,7 @@ xfs_icsb_lock_all_counters(
 	}
 }
 
-STATIC inline void
+STATIC_INLINE void
 xfs_icsb_unlock_all_counters(
 	xfs_mount_t	*mp)
 {
@@ -1888,6 +1921,17 @@ xfs_icsb_disable_counter(
 
 	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
 
+	/*
+	 * If we are already disabled, then there is nothing to do
+	 * here. We check before locking all the counters to avoid
+	 * the expensive lock operation when being called in the
+	 * slow path and the counter is already disabled. This is
+	 * safe because the only time we set or clear this state is under
+	 * the m_icsb_mutex.
+	 */
+	if (xfs_icsb_counter_disabled(mp, field))
+		return 0;
+
 	xfs_icsb_lock_all_counters(mp);
 	if (!test_and_set_bit(field, &mp->m_icsb_counters)) {
 		/* drain back to superblock */
@@ -1948,8 +1992,8 @@ xfs_icsb_enable_counter(
 	xfs_icsb_unlock_all_counters(mp);
 }
 
-STATIC void
-xfs_icsb_sync_counters_int(
+void
+xfs_icsb_sync_counters_flags(
 	xfs_mount_t	*mp,
 	int		flags)
 {
@@ -1981,40 +2025,39 @@ STATIC void
 xfs_icsb_sync_counters(
 	xfs_mount_t	*mp)
 {
-	xfs_icsb_sync_counters_int(mp, 0);
-}
-
-/*
- * lazy addition used for things like df, background sb syncs, etc
- */
-void
-xfs_icsb_sync_counters_lazy(
-	xfs_mount_t	*mp)
-{
-	xfs_icsb_sync_counters_int(mp, XFS_ICSB_LAZY_COUNT);
+	xfs_icsb_sync_counters_flags(mp, 0);
 }
 
 /*
  * Balance and enable/disable counters as necessary.
  *
- * Thresholds for re-enabling counters are somewhat magic.
- * inode counts are chosen to be the same number as single
- * on disk allocation chunk per CPU, and free blocks is
- * something far enough zero that we aren't going thrash
- * when we get near ENOSPC.
+ * Thresholds for re-enabling counters are somewhat magic.  inode counts are
+ * chosen to be the same number as single on disk allocation chunk per CPU, and
+ * free blocks is something far enough zero that we aren't going thrash when we
+ * get near ENOSPC. We also need to supply a minimum we require per cpu to
+ * prevent looping endlessly when xfs_alloc_space asks for more than will
+ * be distributed to a single CPU but each CPU has enough blocks to be
+ * reenabled.
+ *
+ * Note that we can be called when counters are already disabled.
+ * xfs_icsb_disable_counter() optimises the counter locking in this case to
+ * prevent locking every per-cpu counter needlessly.
  */
-#define XFS_ICSB_INO_CNTR_REENABLE	64
+
+#define XFS_ICSB_INO_CNTR_REENABLE	(uint64_t)64
 #define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \
-		(512 + XFS_ALLOC_SET_ASIDE(mp))
+		(uint64_t)(512 + XFS_ALLOC_SET_ASIDE(mp))
 STATIC void
 xfs_icsb_balance_counter(
 	xfs_mount_t	*mp,
 	xfs_sb_field_t  field,
-	int		flags)
+	int		flags,
+	int		min_per_cpu)
 {
 	uint64_t	count, resid;
 	int		weight = num_online_cpus();
 	int		s;
+	uint64_t	min = (uint64_t)min_per_cpu;
 
 	if (!(flags & XFS_ICSB_SB_LOCKED))
 		s = XFS_SB_LOCK(mp);
@@ -2027,19 +2070,19 @@ xfs_icsb_balance_counter(
 	case XFS_SBS_ICOUNT:
 		count = mp->m_sb.sb_icount;
 		resid = do_div(count, weight);
-		if (count < XFS_ICSB_INO_CNTR_REENABLE)
+		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
 			goto out;
 		break;
 	case XFS_SBS_IFREE:
 		count = mp->m_sb.sb_ifree;
 		resid = do_div(count, weight);
-		if (count < XFS_ICSB_INO_CNTR_REENABLE)
+		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
 			goto out;
 		break;
 	case XFS_SBS_FDBLOCKS:
 		count = mp->m_sb.sb_fdblocks;
 		resid = do_div(count, weight);
-		if (count < XFS_ICSB_FDBLK_CNTR_REENABLE(mp))
+		if (count < max(min, XFS_ICSB_FDBLK_CNTR_REENABLE(mp)))
 			goto out;
 		break;
 	default:
@@ -2054,32 +2097,39 @@ out:
 		XFS_SB_UNLOCK(mp, s);
 }
 
-STATIC int
-xfs_icsb_modify_counters_int(
+int
+xfs_icsb_modify_counters(
 	xfs_mount_t	*mp,
 	xfs_sb_field_t	field,
-	int		delta,
-	int		rsvd,
-	int		flags)
+	int64_t		delta,
+	int		rsvd)
 {
 	xfs_icsb_cnts_t	*icsbp;
 	long long	lcounter;	/* long counter for 64 bit fields */
-	int		cpu, s, locked = 0;
-	int		ret = 0, balance_done = 0;
+	int		cpu, ret = 0, s;
 
+	might_sleep();
 again:
 	cpu = get_cpu();
-	icsbp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, cpu),
-	xfs_icsb_lock_cntr(icsbp);
+	icsbp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, cpu);
+
+	/*
+	 * if the counter is disabled, go to slow path
+	 */
 	if (unlikely(xfs_icsb_counter_disabled(mp, field)))
 		goto slow_path;
+	xfs_icsb_lock_cntr(icsbp);
+	if (unlikely(xfs_icsb_counter_disabled(mp, field))) {
+		xfs_icsb_unlock_cntr(icsbp);
+		goto slow_path;
+	}
 
 	switch (field) {
 	case XFS_SBS_ICOUNT:
 		lcounter = icsbp->icsb_icount;
 		lcounter += delta;
 		if (unlikely(lcounter < 0))
-			goto slow_path;
+			goto balance_counter;
 		icsbp->icsb_icount = lcounter;
 		break;
 
@@ -2087,7 +2137,7 @@ again:
 		lcounter = icsbp->icsb_ifree;
 		lcounter += delta;
 		if (unlikely(lcounter < 0))
-			goto slow_path;
+			goto balance_counter;
 		icsbp->icsb_ifree = lcounter;
 		break;
 
@@ -2097,7 +2147,7 @@ again:
 		lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 		lcounter += delta;
 		if (unlikely(lcounter < 0))
-			goto slow_path;
+			goto balance_counter;
 		icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
 		break;
 	default:
@@ -2106,72 +2156,78 @@ again:
 	}
 	xfs_icsb_unlock_cntr(icsbp);
 	put_cpu();
-	if (locked)
-		XFS_SB_UNLOCK(mp, s);
 	return 0;
 
-	/*
-	 * The slow path needs to be run with the SBLOCK
-	 * held so that we prevent other threads from
-	 * attempting to run this path at the same time.
-	 * this provides exclusion for the balancing code,
-	 * and exclusive fallback if the balance does not
-	 * provide enough resources to continue in an unlocked
-	 * manner.
-	 */
 slow_path:
-	xfs_icsb_unlock_cntr(icsbp);
 	put_cpu();
 
-	/* need to hold superblock incase we need
-	 * to disable a counter */
-	if (!(flags & XFS_ICSB_SB_LOCKED)) {
-		s = XFS_SB_LOCK(mp);
-		locked = 1;
-		flags |= XFS_ICSB_SB_LOCKED;
-	}
-	if (!balance_done) {
-		xfs_icsb_balance_counter(mp, field, flags);
-		balance_done = 1;
+	/*
+	 * serialise with a mutex so we don't burn lots of cpu on
+	 * the superblock lock. We still need to hold the superblock
+	 * lock, however, when we modify the global structures.
+	 */
+	xfs_icsb_lock(mp);
+
+	/*
+	 * Now running atomically.
+	 *
+	 * If the counter is enabled, someone has beaten us to rebalancing.
+	 * Drop the lock and try again in the fast path....
+	 */
+	if (!(xfs_icsb_counter_disabled(mp, field))) {
+		xfs_icsb_unlock(mp);
 		goto again;
-	} else {
-		/*
-		 * we might not have enough on this local
-		 * cpu to allocate for a bulk request.
-		 * We need to drain this field from all CPUs
-		 * and disable the counter fastpath
-		 */
-		xfs_icsb_disable_counter(mp, field);
 	}
 
+	/*
+	 * The counter is currently disabled. Because we are
+	 * running atomically here, we know a rebalance cannot
+	 * be in progress. Hence we can go straight to operating
+	 * on the global superblock. We do not call xfs_mod_incore_sb()
+	 * here even though we need to get the SB_LOCK. Doing so
+	 * will cause us to re-enter this function and deadlock.
+	 * Hence we get the SB_LOCK ourselves and then call
+	 * xfs_mod_incore_sb_unlocked() as the unlocked path operates
+	 * directly on the global counters.
+	 */
+	s = XFS_SB_LOCK(mp);
 	ret = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
+	XFS_SB_UNLOCK(mp, s);
 
-	if (locked)
-		XFS_SB_UNLOCK(mp, s);
+	/*
+	 * Now that we've modified the global superblock, we
+	 * may be able to re-enable the distributed counters
+	 * (e.g. lots of space just got freed). After that
+	 * we are done.
+	 */
+	if (ret != ENOSPC)
+		xfs_icsb_balance_counter(mp, field, 0, 0);
+	xfs_icsb_unlock(mp);
 	return ret;
-}
 
-STATIC int
-xfs_icsb_modify_counters(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	int		delta,
-	int		rsvd)
-{
-	return xfs_icsb_modify_counters_int(mp, field, delta, rsvd, 0);
-}
+balance_counter:
+	xfs_icsb_unlock_cntr(icsbp);
+	put_cpu();
 
-/*
- * Called when superblock is already locked
- */
-STATIC int
-xfs_icsb_modify_counters_locked(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	int		delta,
-	int		rsvd)
-{
-	return xfs_icsb_modify_counters_int(mp, field, delta,
-						rsvd, XFS_ICSB_SB_LOCKED);
+	/*
+	 * We may have multiple threads here if multiple per-cpu
+	 * counters run dry at the same time. This will mean we can
+	 * do more balances than strictly necessary but it is not
+	 * the common slowpath case.
+	 */
+	xfs_icsb_lock(mp);
+
+	/*
+	 * running atomically.
+	 *
+	 * This will leave the counter in the correct state for future
+	 * accesses. After the rebalance, we simply try again and our retry
+	 * will either succeed through the fast path or slow path without
+	 * another balance operation being required.
+	 */
+	xfs_icsb_balance_counter(mp, field, 0, delta);
+	xfs_icsb_unlock(mp);
+	goto again;
 }
+
 #endif
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e5f396f..82304b9 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -18,6 +18,7 @@
 #ifndef __XFS_MOUNT_H__
 #define	__XFS_MOUNT_H__
 
+
 typedef struct xfs_trans_reservations {
 	uint	tr_write;	/* extent alloc trans */
 	uint	tr_itruncate;	/* truncate trans */
@@ -306,11 +307,13 @@ typedef struct xfs_icsb_cnts {
 #define XFS_ICSB_LAZY_COUNT	(1 << 1)	/* accuracy not needed */
 
 extern int	xfs_icsb_init_counters(struct xfs_mount *);
-extern void	xfs_icsb_sync_counters_lazy(struct xfs_mount *);
+extern void	xfs_icsb_reinit_counters(struct xfs_mount *);
+extern void	xfs_icsb_sync_counters_flags(struct xfs_mount *, int);
 
 #else
 #define xfs_icsb_init_counters(mp)	(0)
-#define xfs_icsb_sync_counters_lazy(mp)	do { } while (0)
+#define xfs_icsb_reinit_counters(mp)	do { } while (0)
+#define xfs_icsb_sync_counters_flags(mp, flags)	do { } while (0)
 #endif
 
 typedef struct xfs_mount {
@@ -419,6 +422,7 @@ typedef struct xfs_mount {
 	xfs_icsb_cnts_t		*m_sb_cnts;	/* per-cpu superblock counters */
 	unsigned long		m_icsb_counters; /* disabled per-cpu counters */
 	struct notifier_block	m_icsb_notifier; /* hotplug cpu notifier */
+	struct mutex		m_icsb_mutex;	/* balancer sync lock */
 #endif
 } xfs_mount_t;
 
@@ -563,11 +567,32 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 }
 
 /*
+ * Per-cpu superblock locking functions
+ */
+#ifdef HAVE_PERCPU_SB
+STATIC_INLINE void
+xfs_icsb_lock(xfs_mount_t *mp)
+{
+	mutex_lock(&mp->m_icsb_mutex);
+}
+
+STATIC_INLINE void
+xfs_icsb_unlock(xfs_mount_t *mp)
+{
+	mutex_unlock(&mp->m_icsb_mutex);
+}
+#else
+#define xfs_icsb_lock(mp)
+#define xfs_icsb_unlock(mp)
+#endif
+
+/*
  * This structure is for use by the xfs_mod_incore_sb_batch() routine.
+ * xfs_growfs can specify a few fields which are more than int limit
  */
 typedef struct xfs_mod_sb {
 	xfs_sb_field_t	msb_field;	/* Field to modify, see below */
-	int		msb_delta;	/* Change to make to specified field */
+	int64_t		msb_delta;	/* Change to make to specified field */
 } xfs_mod_sb_t;
 
 #define	XFS_MOUNT_ILOCK(mp)	mutex_lock(&((mp)->m_ilock))
@@ -585,17 +610,17 @@ extern int	xfs_unmountfs(xfs_mount_t *, struct cred *);
 extern void	xfs_unmountfs_close(xfs_mount_t *, struct cred *);
 extern int	xfs_unmountfs_writesb(xfs_mount_t *);
 extern int	xfs_unmount_flush(xfs_mount_t *, int);
-extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int, int);
+extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_unlocked(xfs_mount_t *, xfs_sb_field_t,
-			int, int);
+			int64_t, int);
 extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 			uint, int);
 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 void	xfs_do_force_shutdown(bhv_desc_t *, int, char *, int);
-extern int	xfs_syncsub(xfs_mount_t *, int, int, int *);
-extern int	xfs_sync_inodes(xfs_mount_t *, int, int, int *);
+extern int	xfs_syncsub(xfs_mount_t *, int, int *);
+extern int	xfs_sync_inodes(xfs_mount_t *, int, int *);
 extern xfs_agnumber_t	xfs_initialize_perag(struct bhv_vfs *, xfs_mount_t *,
 						xfs_agnumber_t);
 extern void	xfs_xlatesb(void *, struct xfs_sb *, int, __int64_t);
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index d98171d..4c6573d 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -565,7 +565,7 @@ xfs_rename(
 		IHOLD(target_ip);
 	IHOLD(src_ip);
 
-	error = xfs_bmap_finish(&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
 		xfs_bmap_cancel(&free_list);
 		xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES |
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 880c732..6fff19d 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -147,7 +147,7 @@ xfs_growfs_rt_alloc(
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_bmap_finish(&tp, &flist, firstblock, &committed);
+		error = xfs_bmap_finish(&tp, &flist, &committed);
 		if (error)
 			goto error_exit;
 		xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
@@ -913,57 +913,6 @@ xfs_rtcheck_alloc_range(
 }
 #endif
 
-#ifdef DEBUG
-/*
- * Check whether the given block in the bitmap has the given value.
- */
-STATIC int				/* 1 for matches, 0 for not */
-xfs_rtcheck_bit(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* bit (block) to check */
-	int		val)		/* 1 for free, 0 for allocated */
-{
-	int		bit;		/* bit number in the word */
-	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
-	xfs_rtword_t	*bufp;		/* pointer into the buffer */
-	/* REFERENCED */
-	int		error;		/* error value */
-	xfs_rtword_t	wdiff;		/* difference between bit & expected */
-	int		word;		/* word number in the buffer */
-	xfs_rtword_t	wval;		/* word value from buffer */
-
-	block = XFS_BITTOBLOCK(mp, start);
-	error = xfs_rtbuf_get(mp, tp, block, 0, &bp);
-	bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
-	word = XFS_BITTOWORD(mp, start);
-	bit = (int)(start & (XFS_NBWORD - 1));
-	wval = bufp[word];
-	xfs_trans_brelse(tp, bp);
-	wdiff = (wval ^ -val) & ((xfs_rtword_t)1 << bit);
-	return !wdiff;
-}
-#endif	/* DEBUG */
-
-#if 0
-/*
- * Check that the given extent (block range) is free already.
- */
-STATIC int				/* error */
-xfs_rtcheck_free_range(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	bno,		/* starting block number of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		*stat)		/* out: 1 for free, 0 for not */
-{
-	xfs_rtblock_t	new;		/* dummy for xfs_rtcheck_range */
-
-	return xfs_rtcheck_range(mp, tp, bno, len, 1, &new, stat);
-}
-#endif
-
 /*
  * Check that the given range is either all allocated (val = 0) or
  * all free (val = 1).
@@ -2382,60 +2331,3 @@ xfs_rtpick_extent(
 	*pick = b;
 	return 0;
 }
-
-#ifdef DEBUG
-/*
- * Debug code: print out the value of a range in the bitmap.
- */
-void
-xfs_rtprint_range(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_rtblock_t	start,		/* starting block to print */
-	xfs_extlen_t	len)		/* length to print */
-{
-	xfs_extlen_t	i;		/* block number in the extent */
-
-	cmn_err(CE_DEBUG, "%Ld: ", (long long)start);
-	for (i = 0; i < len; i++)
-		cmn_err(CE_DEBUG, "%d", xfs_rtcheck_bit(mp, tp, start + i, 1));
-	cmn_err(CE_DEBUG, "\n");
-}
-
-/*
- * Debug code: print the summary file.
- */
-void
-xfs_rtprint_summary(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp)		/* transaction pointer */
-{
-	xfs_suminfo_t	c;		/* summary data */
-	xfs_rtblock_t	i;		/* bitmap block number */
-	int		l;		/* summary information level */
-	int		p;		/* flag for printed anything */
-	xfs_fsblock_t	sb;		/* summary block number */
-	xfs_buf_t	*sumbp;		/* summary block buffer */
-
-	sumbp = NULL;
-	for (l = 0; l < mp->m_rsumlevels; l++) {
-		for (p = 0, i = 0; i < mp->m_sb.sb_rbmblocks; i++) {
-			(void)xfs_rtget_summary(mp, tp, l, i, &sumbp, &sb, &c);
-			if (c) {
-				if (!p) {
-					cmn_err(CE_DEBUG, "%Ld-%Ld:", 1LL << l,
-						XFS_RTMIN((1LL << l) +
-							  ((1LL << l) - 1LL),
-							 mp->m_sb.sb_rextents));
-					p = 1;
-				}
-				cmn_err(CE_DEBUG, " %Ld:%d", (long long)i, c);
-			}
-		}
-		if (p)
-			cmn_err(CE_DEBUG, "\n");
-	}
-	if (sumbp)
-		xfs_trans_brelse(tp, sumbp);
-}
-#endif	/* DEBUG */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 0e0b4d2..799c1f8 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -134,24 +134,6 @@ xfs_rtpick_extent(
 	xfs_rtblock_t		*pick);	/* result rt extent */
 
 /*
- * Debug code: print out the value of a range in the bitmap.
- */
-void
-xfs_rtprint_range(
-	struct xfs_mount	*mp,	/* file system mount structure */
-	struct xfs_trans	*tp,	/* transaction pointer */
-	xfs_rtblock_t		start,	/* starting block to print */
-	xfs_extlen_t		len);	/* length to print */
-
-/*
- * Debug code: print the summary file.
- */
-void
-xfs_rtprint_summary(
-	struct xfs_mount	*mp,	/* file system mount structure */
-	struct xfs_trans	*tp);	/* transaction pointer */
-
-/*
  * Grow the realtime area of the filesystem.
  */
 int
diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c
index defb2fe..1ea7c0c 100644
--- a/fs/xfs/xfs_rw.c
+++ b/fs/xfs/xfs_rw.c
@@ -42,7 +42,6 @@
 #include "xfs_attr.h"
 #include "xfs_bmap.h"
 #include "xfs_acl.h"
-#include "xfs_mac.h"
 #include "xfs_error.h"
 #include "xfs_buf_item.h"
 #include "xfs_rw.h"
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index ee2721e..301ff94 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -339,7 +339,7 @@ xfs_trans_reserve(
 	 */
 	if (blocks > 0) {
 		error = xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS,
-					  -blocks, rsvd);
+					  -((int64_t)blocks), rsvd);
 		if (error != 0) {
 			current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
 			return (XFS_ERROR(ENOSPC));
@@ -380,7 +380,7 @@ xfs_trans_reserve(
 	 */
 	if (rtextents > 0) {
 		error = xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FREXTENTS,
-					  -rtextents, rsvd);
+					  -((int64_t)rtextents), rsvd);
 		if (error) {
 			error = XFS_ERROR(ENOSPC);
 			goto undo_log;
@@ -410,7 +410,7 @@ undo_log:
 undo_blocks:
 	if (blocks > 0) {
 		(void) xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS,
-					 blocks, rsvd);
+					 (int64_t)blocks, rsvd);
 		tp->t_blk_res = 0;
 	}
 
@@ -432,7 +432,7 @@ void
 xfs_trans_mod_sb(
 	xfs_trans_t	*tp,
 	uint		field,
-	long		delta)
+	int64_t		delta)
 {
 
 	switch (field) {
@@ -663,62 +663,62 @@ xfs_trans_unreserve_and_mod_sb(
 	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
 		if (tp->t_icount_delta != 0) {
 			msbp->msb_field = XFS_SBS_ICOUNT;
-			msbp->msb_delta = (int)tp->t_icount_delta;
+			msbp->msb_delta = tp->t_icount_delta;
 			msbp++;
 		}
 		if (tp->t_ifree_delta != 0) {
 			msbp->msb_field = XFS_SBS_IFREE;
-			msbp->msb_delta = (int)tp->t_ifree_delta;
+			msbp->msb_delta = tp->t_ifree_delta;
 			msbp++;
 		}
 		if (tp->t_fdblocks_delta != 0) {
 			msbp->msb_field = XFS_SBS_FDBLOCKS;
-			msbp->msb_delta = (int)tp->t_fdblocks_delta;
+			msbp->msb_delta = tp->t_fdblocks_delta;
 			msbp++;
 		}
 		if (tp->t_frextents_delta != 0) {
 			msbp->msb_field = XFS_SBS_FREXTENTS;
-			msbp->msb_delta = (int)tp->t_frextents_delta;
+			msbp->msb_delta = tp->t_frextents_delta;
 			msbp++;
 		}
 		if (tp->t_dblocks_delta != 0) {
 			msbp->msb_field = XFS_SBS_DBLOCKS;
-			msbp->msb_delta = (int)tp->t_dblocks_delta;
+			msbp->msb_delta = tp->t_dblocks_delta;
 			msbp++;
 		}
 		if (tp->t_agcount_delta != 0) {
 			msbp->msb_field = XFS_SBS_AGCOUNT;
-			msbp->msb_delta = (int)tp->t_agcount_delta;
+			msbp->msb_delta = tp->t_agcount_delta;
 			msbp++;
 		}
 		if (tp->t_imaxpct_delta != 0) {
 			msbp->msb_field = XFS_SBS_IMAX_PCT;
-			msbp->msb_delta = (int)tp->t_imaxpct_delta;
+			msbp->msb_delta = tp->t_imaxpct_delta;
 			msbp++;
 		}
 		if (tp->t_rextsize_delta != 0) {
 			msbp->msb_field = XFS_SBS_REXTSIZE;
-			msbp->msb_delta = (int)tp->t_rextsize_delta;
+			msbp->msb_delta = tp->t_rextsize_delta;
 			msbp++;
 		}
 		if (tp->t_rbmblocks_delta != 0) {
 			msbp->msb_field = XFS_SBS_RBMBLOCKS;
-			msbp->msb_delta = (int)tp->t_rbmblocks_delta;
+			msbp->msb_delta = tp->t_rbmblocks_delta;
 			msbp++;
 		}
 		if (tp->t_rblocks_delta != 0) {
 			msbp->msb_field = XFS_SBS_RBLOCKS;
-			msbp->msb_delta = (int)tp->t_rblocks_delta;
+			msbp->msb_delta = tp->t_rblocks_delta;
 			msbp++;
 		}
 		if (tp->t_rextents_delta != 0) {
 			msbp->msb_field = XFS_SBS_REXTENTS;
-			msbp->msb_delta = (int)tp->t_rextents_delta;
+			msbp->msb_delta = tp->t_rextents_delta;
 			msbp++;
 		}
 		if (tp->t_rextslog_delta != 0) {
 			msbp->msb_field = XFS_SBS_REXTSLOG;
-			msbp->msb_delta = (int)tp->t_rextslog_delta;
+			msbp->msb_delta = tp->t_rextslog_delta;
 			msbp++;
 		}
 	}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index c68e001..f1d7ab2 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -39,13 +39,9 @@ typedef struct xfs_trans_header {
 /*
  * Log item types.
  */
-#define	XFS_LI_5_3_BUF		0x1234	/* v1 bufs, 1-block inode buffers */
-#define	XFS_LI_5_3_INODE	0x1235	/* 1-block inode buffers */
 #define	XFS_LI_EFI		0x1236
 #define	XFS_LI_EFD		0x1237
 #define	XFS_LI_IUNLINK		0x1238
-#define	XFS_LI_6_1_INODE	0x1239	/* 4K non-aligned inode bufs */
-#define	XFS_LI_6_1_BUF		0x123a	/* v1, 4K inode buffers */
 #define	XFS_LI_INODE		0x123b	/* aligned ino chunks, var-size ibufs */
 #define	XFS_LI_BUF		0x123c	/* v2 bufs, variable sized inode bufs */
 #define	XFS_LI_DQUOT		0x123d
@@ -354,25 +350,25 @@ typedef struct xfs_trans {
 	xfs_trans_callback_t	t_callback;	/* transaction callback */
 	void			*t_callarg;	/* callback arg */
 	unsigned int		t_flags;	/* misc flags */
-	long			t_icount_delta;	/* superblock icount change */
-	long			t_ifree_delta;	/* superblock ifree change */
-	long			t_fdblocks_delta; /* superblock fdblocks chg */
-	long			t_res_fdblocks_delta; /* on-disk only chg */
-	long			t_frextents_delta;/* superblock freextents chg*/
-	long			t_res_frextents_delta; /* on-disk only chg */
+	int64_t			t_icount_delta;	/* superblock icount change */
+	int64_t			t_ifree_delta;	/* superblock ifree change */
+	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
+	int64_t			t_res_fdblocks_delta; /* on-disk only chg */
+	int64_t			t_frextents_delta;/* superblock freextents chg*/
+	int64_t			t_res_frextents_delta; /* on-disk only chg */
 #ifdef DEBUG
-	long			t_ag_freeblks_delta; /* debugging counter */
-	long			t_ag_flist_delta; /* debugging counter */
-	long			t_ag_btree_delta; /* debugging counter */
+	int64_t			t_ag_freeblks_delta; /* debugging counter */
+	int64_t			t_ag_flist_delta; /* debugging counter */
+	int64_t			t_ag_btree_delta; /* debugging counter */
 #endif
-	long			t_dblocks_delta;/* superblock dblocks change */
-	long			t_agcount_delta;/* superblock agcount change */
-	long			t_imaxpct_delta;/* superblock imaxpct change */
-	long			t_rextsize_delta;/* superblock rextsize chg */
-	long			t_rbmblocks_delta;/* superblock rbmblocks chg */
-	long			t_rblocks_delta;/* superblock rblocks change */
-	long			t_rextents_delta;/* superblocks rextents chg */
-	long			t_rextslog_delta;/* superblocks rextslog chg */
+	int64_t			t_dblocks_delta;/* superblock dblocks change */
+	int64_t			t_agcount_delta;/* superblock agcount change */
+	int64_t			t_imaxpct_delta;/* superblock imaxpct change */
+	int64_t			t_rextsize_delta;/* superblock rextsize chg */
+	int64_t			t_rbmblocks_delta;/* superblock rbmblocks chg */
+	int64_t			t_rblocks_delta;/* superblock rblocks change */
+	int64_t			t_rextents_delta;/* superblocks rextents chg */
+	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
 	unsigned int		t_items_free;	/* log item descs free */
 	xfs_log_item_chunk_t	t_items;	/* first log item desc chunk */
 	xfs_trans_header_t	t_header;	/* header for in-log trans */
@@ -936,9 +932,9 @@ typedef struct xfs_trans {
 #define	xfs_trans_set_sync(tp)		((tp)->t_flags |= XFS_TRANS_SYNC)
 
 #ifdef DEBUG
-#define	xfs_trans_agblocks_delta(tp, d)	((tp)->t_ag_freeblks_delta += (long)d)
-#define	xfs_trans_agflist_delta(tp, d)	((tp)->t_ag_flist_delta += (long)d)
-#define	xfs_trans_agbtree_delta(tp, d)	((tp)->t_ag_btree_delta += (long)d)
+#define	xfs_trans_agblocks_delta(tp, d)	((tp)->t_ag_freeblks_delta += (int64_t)d)
+#define	xfs_trans_agflist_delta(tp, d)	((tp)->t_ag_flist_delta += (int64_t)d)
+#define	xfs_trans_agbtree_delta(tp, d)	((tp)->t_ag_btree_delta += (int64_t)d)
 #else
 #define	xfs_trans_agblocks_delta(tp, d)
 #define	xfs_trans_agflist_delta(tp, d)
@@ -954,7 +950,7 @@ xfs_trans_t	*_xfs_trans_alloc(struct xfs_mount *, uint);
 xfs_trans_t	*xfs_trans_dup(xfs_trans_t *);
 int		xfs_trans_reserve(xfs_trans_t *, uint, uint, uint,
 				  uint, uint);
-void		xfs_trans_mod_sb(xfs_trans_t *, uint, long);
+void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
 struct xfs_buf	*xfs_trans_get_buf(xfs_trans_t *, struct xfs_buftarg *, xfs_daddr_t,
 				   int, uint);
 int		xfs_trans_read_buf(struct xfs_mount *, xfs_trans_t *,
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index fc39b16..ceb4f6e 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -90,7 +90,7 @@ xfs_trans_push_ail(
 	int			flush_log;
 	SPLDECL(s);
 
-#define	XFS_TRANS_PUSH_AIL_RESTARTS	10
+#define	XFS_TRANS_PUSH_AIL_RESTARTS	1000
 
 	AIL_LOCK(mp,s);
 	lip = xfs_trans_first_ail(mp, &gen);
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 62336a4..29f72f6 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -640,7 +640,7 @@ xfs_quiesce_fs(
 	 * we can write the unmount record.
 	 */
 	do {
-		xfs_syncsub(mp, SYNC_REMOUNT|SYNC_ATTR|SYNC_WAIT, 0, NULL);
+		xfs_syncsub(mp, SYNC_REMOUNT|SYNC_ATTR|SYNC_WAIT, NULL);
 		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
 		if (!pincount) {
 			delay(50);
@@ -806,7 +806,7 @@ xfs_statvfs(
 
 	statp->f_type = XFS_SB_MAGIC;
 
-	xfs_icsb_sync_counters_lazy(mp);
+	xfs_icsb_sync_counters_flags(mp, XFS_ICSB_LAZY_COUNT);
 	s = XFS_SB_LOCK(mp);
 	statp->f_bsize = sbp->sb_blocksize;
 	lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
@@ -872,6 +872,10 @@ xfs_statvfs(
  *		       this by simply making sure the log gets flushed
  *		       if SYNC_BDFLUSH is set, and by actually writing it
  *		       out otherwise.
+ *	SYNC_IOWAIT  - The caller wants us to wait for all data I/O to complete
+ *		       before we return (including direct I/O). Forms the drain
+ *		       side of the write barrier needed to safely quiesce the
+ *		       filesystem.
  *
  */
 /*ARGSUSED*/
@@ -883,27 +887,20 @@ xfs_sync(
 {
 	xfs_mount_t	*mp = XFS_BHVTOM(bdp);
 
-	if (unlikely(flags == SYNC_QUIESCE))
-		return xfs_quiesce_fs(mp);
-	else
-		return xfs_syncsub(mp, flags, 0, NULL);
+	return xfs_syncsub(mp, flags, NULL);
 }
 
 /*
  * xfs sync routine for internal use
  *
  * This routine supports all of the flags defined for the generic vfs_sync
- * interface as explained above under xfs_sync.  In the interests of not
- * changing interfaces within the 6.5 family, additional internally-
- * required functions are specified within a separate xflags parameter,
- * only available by calling this routine.
+ * interface as explained above under xfs_sync.
  *
  */
 int
 xfs_sync_inodes(
 	xfs_mount_t	*mp,
 	int		flags,
-	int             xflags,
 	int             *bypassed)
 {
 	xfs_inode_t	*ip = NULL;
@@ -1176,6 +1173,13 @@ xfs_sync_inodes(
 			}
 
 		}
+		/*
+		 * When freezing, we need to wait ensure all I/O (including direct
+		 * I/O) is complete to ensure no further data modification can take
+		 * place after this point
+		 */
+		if (flags & SYNC_IOWAIT)
+			vn_iowait(vp);
 
 		if (flags & SYNC_BDFLUSH) {
 			if ((flags & SYNC_ATTR) &&
@@ -1412,17 +1416,13 @@ xfs_sync_inodes(
  * xfs sync routine for internal use
  *
  * This routine supports all of the flags defined for the generic vfs_sync
- * interface as explained above under xfs_sync.  In the interests of not
- * changing interfaces within the 6.5 family, additional internally-
- * required functions are specified within a separate xflags parameter,
- * only available by calling this routine.
+ * interface as explained above under xfs_sync.
  *
  */
 int
 xfs_syncsub(
 	xfs_mount_t	*mp,
 	int		flags,
-	int             xflags,
 	int             *bypassed)
 {
 	int		error = 0;
@@ -1444,7 +1444,7 @@ xfs_syncsub(
 		if (flags & SYNC_BDFLUSH)
 			xfs_finish_reclaim_all(mp, 1);
 		else
-			error = xfs_sync_inodes(mp, flags, xflags, bypassed);
+			error = xfs_sync_inodes(mp, flags, bypassed);
 	}
 
 	/*
@@ -1958,15 +1958,26 @@ xfs_showargs(
 	return 0;
 }
 
+/*
+ * Second stage of a freeze. The data is already frozen, now we have to take
+ * care of the metadata. New transactions are already blocked, so we need to
+ * wait for any remaining transactions to drain out before proceding.
+ */
 STATIC void
 xfs_freeze(
 	bhv_desc_t	*bdp)
 {
 	xfs_mount_t	*mp = XFS_BHVTOM(bdp);
 
+	/* wait for all modifications to complete */
 	while (atomic_read(&mp->m_active_trans) > 0)
 		delay(100);
 
+	/* flush inodes and push all remaining buffers out to disk */
+	xfs_quiesce_fs(mp);
+
+	ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
+
 	/* Push the superblock and write an unmount record */
 	xfs_log_unmount_write(mp);
 	xfs_unmountfs_writesb(mp);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index bda774a..52c4171 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -51,7 +51,6 @@
 #include "xfs_refcache.h"
 #include "xfs_trans_space.h"
 #include "xfs_log_priv.h"
-#include "xfs_mac.h"
 
 STATIC int
 xfs_open(
@@ -1381,7 +1380,7 @@ xfs_inactive_symlink_rmt(
 	/*
 	 * Commit the first transaction.  This logs the EFI and the inode.
 	 */
-	if ((error = xfs_bmap_finish(&tp, &free_list, first_block, &committed)))
+	if ((error = xfs_bmap_finish(&tp, &free_list, &committed)))
 		goto error1;
 	/*
 	 * The transaction must have been committed, since there were
@@ -1790,8 +1789,7 @@ xfs_inactive(
 		 * Just ignore errors at this point.  There is
 		 * nothing we can do except to try to keep going.
 		 */
-		(void) xfs_bmap_finish(&tp,  &free_list, first_block,
-				       &committed);
+		(void) xfs_bmap_finish(&tp,  &free_list, &committed);
 		(void) xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
 	}
 	/*
@@ -2022,7 +2020,7 @@ xfs_create(
 	IHOLD(ip);
 	vp = XFS_ITOV(ip);
 
-	error = xfs_bmap_finish(&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
 		xfs_bmap_cancel(&free_list);
 		goto abort_rele;
@@ -2507,7 +2505,7 @@ xfs_remove(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_bmap_finish(&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
 		REMOVE_DEBUG_TRACE(__LINE__);
 		goto error_rele;
@@ -2715,7 +2713,7 @@ xfs_link(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_bmap_finish (&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish (&tp, &free_list, &committed);
 	if (error) {
 		xfs_bmap_cancel(&free_list);
 		goto abort_return;
@@ -2932,7 +2930,7 @@ xfs_mkdir(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_bmap_finish(&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
 		IRELE(cdp);
 		goto error2;
@@ -3183,7 +3181,7 @@ xfs_rmdir(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_bmap_finish (&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish (&tp, &free_list, &committed);
 	if (error) {
 		xfs_bmap_cancel(&free_list);
 		xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES |
@@ -3533,7 +3531,7 @@ xfs_symlink(
 	 */
 	IHOLD(ip);
 
-	error = xfs_bmap_finish(&tp, &free_list, first_block, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
 		goto error2;
 	}
@@ -4145,7 +4143,7 @@ retry:
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_bmap_finish(&tp, &free_list, firstfsb, &committed);
+		error = xfs_bmap_finish(&tp, &free_list, &committed);
 		if (error) {
 			goto error0;
 		}
@@ -4452,7 +4450,7 @@ xfs_free_file_space(
 		/*
 		 * complete the transaction
 		 */
-		error = xfs_bmap_finish(&tp, &free_list, firstfsb, &committed);
+		error = xfs_bmap_finish(&tp, &free_list, &committed);
 		if (error) {
 			goto error0;
 		}