Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs: (49 commits)
  xfs: add size update tracepoint to IO completion
  xfs: convert AIL cursors to use struct list_head
  xfs: remove confusing ail cursor wrapper
  xfs: use a cursor for bulk AIL insertion
  xfs: failure mapping nfs fh to inode should return ESTALE
  xfs: Remove the second parameter to xfs_sb_count()
  xfs: remove the dead XFS_DABUF_DEBUG code
  xfs: remove leftovers of the old btree tracing code
  xfs: remove the dead QUOTADEBUG code
  xfs: remove the unused xfs_buf_delwri_sort function
  xfs: remove wrappers around b_iodone
  xfs: remove wrappers around b_fspriv
  xfs: add a proper transaction pointer to struct xfs_buf
  xfs: factor out xfs_da_grow_inode_int
  xfs: factor out xfs_dir2_leaf_find_stale
  xfs: cleanup struct xfs_dir2_free
  xfs: reshuffle dir2 headers
  xfs: start periodic workers later
  Revert "xfs: fix filesystsem freeze race in xfs_trans_alloc"
  xfs: remove variables that serve no purpose in xfs_alloc_ag_vextent_exact()
  ...

67 files changed, 2796 insertions, 4654 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 284a7c89697e..75bb316529dd 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -88,8 +88,6 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_vnodeops.o \
 				   xfs_rw.o
 
-xfs-$(CONFIG_XFS_TRACE)		+= xfs_btree_trace.o
-
 # Objects in linux/
 xfs-y				+= $(addprefix $(XFS_LINUX)/, \
 				   kmem.o \
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 39f4f809bb68..115ac6919533 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -264,7 +264,7 @@ xfs_set_mode(struct inode *inode, mode_t mode)
 		iattr.ia_mode = mode;
 		iattr.ia_ctime = current_fs_time(inode->i_sb);
 
-		error = -xfs_setattr(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
+		error = -xfs_setattr_nonsize(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
 	}
 
 	return error;
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 79ce38be15a1..26384fe3f26d 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -181,6 +181,7 @@ xfs_setfilesize(
 
 	isize = xfs_ioend_new_eof(ioend);
 	if (isize) {
+		trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
 		ip->i_d.di_size = isize;
 		xfs_mark_inode_dirty(ip);
 	}
@@ -894,11 +895,6 @@ out_invalidate:
  * For unwritten space on the page we need to start the conversion to
  * regular allocated space.
  * For any other dirty buffer heads on the page we should flush them.
- *
- * If we detect that a transaction would be required to flush the page, we
- * have to check the process flags first, if we are already in a transaction
- * or disk I/O during allocations is off, we need to fail the writepage and
- * redirty the page.
  */
 STATIC int
 xfs_vm_writepage(
@@ -906,7 +902,6 @@ xfs_vm_writepage(
 	struct writeback_control *wbc)
 {
 	struct inode		*inode = page->mapping->host;
-	int			delalloc, unwritten;
 	struct buffer_head	*bh, *head;
 	struct xfs_bmbt_irec	imap;
 	xfs_ioend_t		*ioend = NULL, *iohead = NULL;
@@ -938,15 +933,10 @@ xfs_vm_writepage(
 		goto redirty;
 
 	/*
-	 * We need a transaction if there are delalloc or unwritten buffers
-	 * on the page.
-	 *
-	 * If we need a transaction and the process flags say we are already
-	 * in a transaction, or no IO is allowed then mark the page dirty
-	 * again and leave the page as is.
+	 * Given that we do not allow direct reclaim to call us, we should
+	 * never be called while in a filesystem transaction.
 	 */
-	xfs_count_page_state(page, &delalloc, &unwritten);
-	if ((current->flags & PF_FSTRANS) && (delalloc || unwritten))
+	if (WARN_ON(current->flags & PF_FSTRANS))
 		goto redirty;
 
 	/* Is this page beyond the end of the file? */
@@ -970,7 +960,7 @@ xfs_vm_writepage(
 	offset = page_offset(page);
 	type = IO_OVERWRITE;
 
-	if (wbc->sync_mode == WB_SYNC_NONE && wbc->nonblocking)
+	if (wbc->sync_mode == WB_SYNC_NONE)
 		nonblocking = 1;
 
 	do {
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 5e68099db2a5..b2b411985591 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -499,16 +499,14 @@ found:
 	spin_unlock(&pag->pag_buf_lock);
 	xfs_perag_put(pag);
 
-	if (xfs_buf_cond_lock(bp)) {
-		/* failed, so wait for the lock if requested. */
-		if (!(flags & XBF_TRYLOCK)) {
-			xfs_buf_lock(bp);
-			XFS_STATS_INC(xb_get_locked_waited);
-		} else {
+	if (!xfs_buf_trylock(bp)) {
+		if (flags & XBF_TRYLOCK) {
 			xfs_buf_rele(bp);
 			XFS_STATS_INC(xb_busy_locked);
 			return NULL;
 		}
+		xfs_buf_lock(bp);
+		XFS_STATS_INC(xb_get_locked_waited);
 	}
 
 	/*
@@ -594,10 +592,8 @@ _xfs_buf_read(
 	ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE)));
 	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
 
-	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | \
-			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
-	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | \
-			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
+	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD);
+	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
 	status = xfs_buf_iorequest(bp);
 	if (status || XFS_BUF_ISERROR(bp) || (flags & XBF_ASYNC))
@@ -681,7 +677,6 @@ xfs_buf_read_uncached(
 		return NULL;
 
 	/* set up the buffer for a read IO */
-	xfs_buf_lock(bp);
 	XFS_BUF_SET_ADDR(bp, daddr);
 	XFS_BUF_READ(bp);
 	XFS_BUF_BUSY(bp);
@@ -816,8 +811,6 @@ xfs_buf_get_uncached(
 		goto fail_free_mem;
 	}
 
-	xfs_buf_unlock(bp);
-
 	trace_xfs_buf_get_uncached(bp, _RET_IP_);
 	return bp;
 
@@ -896,8 +889,8 @@ xfs_buf_rele(
  *	to push on stale inode buffers.
  */
 int
-xfs_buf_cond_lock(
-	xfs_buf_t		*bp)
+xfs_buf_trylock(
+	struct xfs_buf		*bp)
 {
 	int			locked;
 
@@ -907,15 +900,8 @@ xfs_buf_cond_lock(
 	else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
 		xfs_log_force(bp->b_target->bt_mount, 0);
 
-	trace_xfs_buf_cond_lock(bp, _RET_IP_);
-	return locked ? 0 : -EBUSY;
-}
-
-int
-xfs_buf_lock_value(
-	xfs_buf_t		*bp)
-{
-	return bp->b_sema.count;
+	trace_xfs_buf_trylock(bp, _RET_IP_);
+	return locked;
 }
 
 /*
@@ -929,7 +915,7 @@ xfs_buf_lock_value(
  */
 void
 xfs_buf_lock(
-	xfs_buf_t		*bp)
+	struct xfs_buf		*bp)
 {
 	trace_xfs_buf_lock(bp, _RET_IP_);
 
@@ -950,7 +936,7 @@ xfs_buf_lock(
  */
 void
 xfs_buf_unlock(
-	xfs_buf_t		*bp)
+	struct xfs_buf		*bp)
 {
 	if ((bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)) == XBF_DELWRI) {
 		atomic_inc(&bp->b_hold);
@@ -1121,7 +1107,7 @@ xfs_bioerror_relse(
 	XFS_BUF_UNDELAYWRITE(bp);
 	XFS_BUF_DONE(bp);
 	XFS_BUF_STALE(bp);
-	XFS_BUF_CLR_IODONE_FUNC(bp);
+	bp->b_iodone = NULL;
 	if (!(fl & XBF_ASYNC)) {
 		/*
 		 * Mark b_error and B_ERROR _both_.
@@ -1223,23 +1209,21 @@ _xfs_buf_ioapply(
 	total_nr_pages = bp->b_page_count;
 	map_i = 0;
 
-	if (bp->b_flags & XBF_ORDERED) {
-		ASSERT(!(bp->b_flags & XBF_READ));
-		rw = WRITE_FLUSH_FUA;
-	} else if (bp->b_flags & XBF_LOG_BUFFER) {
-		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
-		bp->b_flags &= ~_XBF_RUN_QUEUES;
-		rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC;
-	} else if (bp->b_flags & _XBF_RUN_QUEUES) {
-		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
-		bp->b_flags &= ~_XBF_RUN_QUEUES;
-		rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META;
+	if (bp->b_flags & XBF_WRITE) {
+		if (bp->b_flags & XBF_SYNCIO)
+			rw = WRITE_SYNC;
+		else
+			rw = WRITE;
+		if (bp->b_flags & XBF_FUA)
+			rw |= REQ_FUA;
+		if (bp->b_flags & XBF_FLUSH)
+			rw |= REQ_FLUSH;
+	} else if (bp->b_flags & XBF_READ_AHEAD) {
+		rw = READA;
 	} else {
-		rw = (bp->b_flags & XBF_WRITE) ? WRITE :
-		     (bp->b_flags & XBF_READ_AHEAD) ? READA : READ;
+		rw = READ;
 	}
 
-
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
 	nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT);
@@ -1694,15 +1678,14 @@ xfs_buf_delwri_split(
 	list_for_each_entry_safe(bp, n, dwq, b_list) {
 		ASSERT(bp->b_flags & XBF_DELWRI);
 
-		if (!XFS_BUF_ISPINNED(bp) && !xfs_buf_cond_lock(bp)) {
+		if (!XFS_BUF_ISPINNED(bp) && xfs_buf_trylock(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_DELWRI | _XBF_DELWRI_Q);
 			bp->b_flags |= XBF_WRITE;
 			list_move_tail(&bp->b_list, list);
 			trace_xfs_buf_delwri_split(bp, _RET_IP_);
@@ -1738,14 +1721,6 @@ xfs_buf_cmp(
 	return 0;
 }
 
-void
-xfs_buf_delwri_sort(
-	xfs_buftarg_t	*target,
-	struct list_head *list)
-{
-	list_sort(NULL, list, xfs_buf_cmp);
-}
-
 STATIC int
 xfsbufd(
 	void		*data)
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 50a7d5fb3b73..6a83b46b4bcf 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -46,43 +46,46 @@ typedef enum {
 
 #define XBF_READ	(1 << 0) /* buffer intended for reading from device */
 #define XBF_WRITE	(1 << 1) /* buffer intended for writing to device */
-#define XBF_MAPPED	(1 << 2) /* buffer mapped (b_addr valid) */
+#define XBF_READ_AHEAD	(1 << 2) /* asynchronous read-ahead */
+#define XBF_MAPPED	(1 << 3) /* buffer mapped (b_addr valid) */
 #define XBF_ASYNC	(1 << 4) /* initiator will not wait for completion */
 #define XBF_DONE	(1 << 5) /* all pages in the buffer uptodate */
 #define XBF_DELWRI	(1 << 6) /* buffer has dirty pages */
 #define XBF_STALE	(1 << 7) /* buffer has been staled, do not find it */
-#define XBF_ORDERED	(1 << 11)/* use ordered writes */
-#define XBF_READ_AHEAD	(1 << 12)/* asynchronous read-ahead */
-#define XBF_LOG_BUFFER	(1 << 13)/* this is a buffer used for the log */
+
+/* I/O hints for the BIO layer */
+#define XBF_SYNCIO	(1 << 10)/* treat this buffer as synchronous I/O */
+#define XBF_FUA		(1 << 11)/* force cache write through mode */
+#define XBF_FLUSH	(1 << 12)/* flush the disk cache before a write */
 
 /* flags used only as arguments to access routines */
-#define XBF_LOCK	(1 << 14)/* lock requested */
-#define XBF_TRYLOCK	(1 << 15)/* lock requested, but do not wait */
-#define XBF_DONT_BLOCK	(1 << 16)/* do not block in current thread */
+#define XBF_LOCK	(1 << 15)/* lock requested */
+#define XBF_TRYLOCK	(1 << 16)/* lock requested, but do not wait */
+#define XBF_DONT_BLOCK	(1 << 17)/* do not block in current thread */
 
 /* flags used only internally */
-#define _XBF_PAGES	(1 << 18)/* backed by refcounted pages */
-#define	_XBF_RUN_QUEUES	(1 << 19)/* run block device task queue	*/
-#define	_XBF_KMEM	(1 << 20)/* backed by heap memory */
-#define _XBF_DELWRI_Q	(1 << 21)/* buffer on delwri queue */
+#define _XBF_PAGES	(1 << 20)/* backed by refcounted pages */
+#define _XBF_KMEM	(1 << 21)/* backed by heap memory */
+#define _XBF_DELWRI_Q	(1 << 22)/* buffer on delwri queue */
 
 typedef unsigned int xfs_buf_flags_t;
 
 #define XFS_BUF_FLAGS \
 	{ XBF_READ,		"READ" }, \
 	{ XBF_WRITE,		"WRITE" }, \
+	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
 	{ XBF_MAPPED,		"MAPPED" }, \
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_DELWRI,		"DELWRI" }, \
 	{ XBF_STALE,		"STALE" }, \
-	{ XBF_ORDERED,		"ORDERED" }, \
-	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
+	{ XBF_SYNCIO,		"SYNCIO" }, \
+	{ XBF_FUA,		"FUA" }, \
+	{ XBF_FLUSH,		"FLUSH" }, \
 	{ XBF_LOCK,		"LOCK" },  	/* should never be set */\
 	{ XBF_TRYLOCK,		"TRYLOCK" }, 	/* ditto */\
 	{ XBF_DONT_BLOCK,	"DONT_BLOCK" },	/* ditto */\
 	{ _XBF_PAGES,		"PAGES" }, \
-	{ _XBF_RUN_QUEUES,	"RUN_QUEUES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
 
@@ -91,11 +94,6 @@ typedef enum {
 	XBT_FORCE_FLUSH = 1,
 } xfs_buftarg_flags_t;
 
-typedef struct xfs_bufhash {
-	struct list_head	bh_list;
-	spinlock_t		bh_lock;
-} xfs_bufhash_t;
-
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
@@ -151,7 +149,7 @@ typedef struct xfs_buf {
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	void			*b_fspriv;
-	void			*b_fspriv2;
+	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
 	unsigned long		b_queuetime;	/* time buffer was queued */
@@ -192,10 +190,11 @@ extern void xfs_buf_free(xfs_buf_t *);
 extern void xfs_buf_rele(xfs_buf_t *);
 
 /* Locking and Unlocking Buffers */
-extern int xfs_buf_cond_lock(xfs_buf_t *);
-extern int xfs_buf_lock_value(xfs_buf_t *);
+extern int xfs_buf_trylock(xfs_buf_t *);
 extern void xfs_buf_lock(xfs_buf_t *);
 extern void xfs_buf_unlock(xfs_buf_t *);
+#define xfs_buf_islocked(bp) \
+	((bp)->b_sema.count <= 0)
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_mount *mp, struct xfs_buf *bp);
@@ -234,8 +233,9 @@ extern void xfs_buf_terminate(void);
 
 
 #define XFS_BUF_BFLAGS(bp)	((bp)->b_flags)
-#define XFS_BUF_ZEROFLAGS(bp)	((bp)->b_flags &= \
-		~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI|XBF_ORDERED))
+#define XFS_BUF_ZEROFLAGS(bp) \
+	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \
+			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
 
 void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_STALE(bp)	xfs_buf_stale(bp);
@@ -267,10 +267,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNASYNC(bp)	((bp)->b_flags &= ~XBF_ASYNC)
 #define XFS_BUF_ISASYNC(bp)	((bp)->b_flags & XBF_ASYNC)
 
-#define XFS_BUF_ORDERED(bp)	((bp)->b_flags |= XBF_ORDERED)
-#define XFS_BUF_UNORDERED(bp)	((bp)->b_flags &= ~XBF_ORDERED)
-#define XFS_BUF_ISORDERED(bp)	((bp)->b_flags & XBF_ORDERED)
-
 #define XFS_BUF_HOLD(bp)	xfs_buf_hold(bp)
 #define XFS_BUF_READ(bp)	((bp)->b_flags |= XBF_READ)
 #define XFS_BUF_UNREAD(bp)	((bp)->b_flags &= ~XBF_READ)
@@ -280,14 +276,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
 #define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
 
-#define XFS_BUF_IODONE_FUNC(bp)			((bp)->b_iodone)
-#define XFS_BUF_SET_IODONE_FUNC(bp, func)	((bp)->b_iodone = (func))
-#define XFS_BUF_CLR_IODONE_FUNC(bp)		((bp)->b_iodone = NULL)
-
-#define XFS_BUF_FSPRIVATE(bp, type)		((type)(bp)->b_fspriv)
-#define XFS_BUF_SET_FSPRIVATE(bp, val)		((bp)->b_fspriv = (void*)(val))
-#define XFS_BUF_FSPRIVATE2(bp, type)		((type)(bp)->b_fspriv2)
-#define XFS_BUF_SET_FSPRIVATE2(bp, val)		((bp)->b_fspriv2 = (void*)(val))
 #define XFS_BUF_SET_START(bp)			do { } while (0)
 
 #define XFS_BUF_PTR(bp)			(xfs_caddr_t)((bp)->b_addr)
@@ -313,10 +301,6 @@ xfs_buf_set_ref(
 
 #define XFS_BUF_ISPINNED(bp)	atomic_read(&((bp)->b_pin_count))
 
-#define XFS_BUF_VALUSEMA(bp)	xfs_buf_lock_value(bp)
-#define XFS_BUF_CPSEMA(bp)	(xfs_buf_cond_lock(bp) == 0)
-#define XFS_BUF_VSEMA(bp)	xfs_buf_unlock(bp)
-#define XFS_BUF_PSEMA(bp,x)	xfs_buf_lock(bp)
 #define XFS_BUF_FINISH_IOWAIT(bp)	complete(&bp->b_iowait);
 
 #define XFS_BUF_SET_TARGET(bp, target)	((bp)->b_target = (target))
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index f4f878fc0083..75e5d322e48f 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -151,14 +151,14 @@ xfs_nfs_get_inode(
 		 * We don't use ESTALE directly down the chain to not
 		 * confuse applications using bulkstat that expect EINVAL.
 		 */
-		if (error == EINVAL)
+		if (error == EINVAL || error == ENOENT)
 			error = ESTALE;
 		return ERR_PTR(-error);
 	}
 
 	if (ip->i_d.di_gen != generation) {
 		IRELE(ip);
-		return ERR_PTR(-ENOENT);
+		return ERR_PTR(-ESTALE);
 	}
 
 	return VFS_I(ip);
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 7f782af286bf..8073f61efb8e 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -944,7 +944,7 @@ xfs_file_fallocate(
 
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = new_size;
-		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
+		error = -xfs_setattr_size(ip, &iattr, XFS_ATTR_NOLOCK);
 	}
 
 out_unlock:
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index d44d92cd12b1..501e4f630548 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -39,6 +39,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
 #include "xfs_vnodeops.h"
+#include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
 #include <linux/capability.h>
@@ -497,12 +498,442 @@ xfs_vn_getattr(
 	return 0;
 }
 
+int
+xfs_setattr_nonsize(
+	struct xfs_inode	*ip,
+	struct iattr		*iattr,
+	int			flags)
+{
+	xfs_mount_t		*mp = ip->i_mount;
+	struct inode		*inode = VFS_I(ip);
+	int			mask = iattr->ia_valid;
+	xfs_trans_t		*tp;
+	int			error;
+	uid_t			uid = 0, iuid = 0;
+	gid_t			gid = 0, igid = 0;
+	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
+	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;
+
+	trace_xfs_setattr(ip);
+
+	if (mp->m_flags & XFS_MOUNT_RDONLY)
+		return XFS_ERROR(EROFS);
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return XFS_ERROR(EIO);
+
+	error = -inode_change_ok(inode, iattr);
+	if (error)
+		return XFS_ERROR(error);
+
+	ASSERT((mask & ATTR_SIZE) == 0);
+
+	/*
+	 * If disk quotas is on, we make sure that the dquots do exist on disk,
+	 * before we start any other transactions. Trying to do this later
+	 * is messy. We don't care to take a readlock to look at the ids
+	 * in inode here, because we can't hold it across the trans_reserve.
+	 * If the IDs do change before we take the ilock, we're covered
+	 * because the i_*dquot fields will get updated anyway.
+	 */
+	if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
+		uint	qflags = 0;
+
+		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
+			uid = iattr->ia_uid;
+			qflags |= XFS_QMOPT_UQUOTA;
+		} else {
+			uid = ip->i_d.di_uid;
+		}
+		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
+			gid = iattr->ia_gid;
+			qflags |= XFS_QMOPT_GQUOTA;
+		}  else {
+			gid = ip->i_d.di_gid;
+		}
+
+		/*
+		 * We take a reference when we initialize udqp and gdqp,
+		 * so it is important that we never blindly double trip on
+		 * the same variable. See xfs_create() for an example.
+		 */
+		ASSERT(udqp == NULL);
+		ASSERT(gdqp == NULL);
+		error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
+					 qflags, &udqp, &gdqp);
+		if (error)
+			return error;
+	}
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
+	if (error)
+		goto out_dqrele;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	/*
+	 * Change file ownership.  Must be the owner or privileged.
+	 */
+	if (mask & (ATTR_UID|ATTR_GID)) {
+		/*
+		 * These IDs could have changed since we last looked at them.
+		 * But, we're assured that if the ownership did change
+		 * while we didn't have the inode locked, inode's dquot(s)
+		 * would have changed also.
+		 */
+		iuid = ip->