Merge branch 'for-linus' of git://oss.sgi.com:8090/xfs/xfs-2.6

* 'for-linus' of git://oss.sgi.com:8090/xfs/xfs-2.6: (62 commits)
  [XFS] add __init/__exit mark to specific init/cleanup functions
  [XFS] Fix oops in xfs_file_readdir()
  [XFS] kill xfs_root
  [XFS] keep i_nlink updated and use proper accessors
  [XFS] stop updating inode->i_blocks
  [XFS] Make xfs_ail_check check less by default
  [XFS] Move AIL pushing into it's own thread
  [XFS] use generic_permission
  [XFS] stop re-checking permissions in xfs_swapext
  [XFS] clean up xfs_swapext
  [XFS] remove permission check from xfs_change_file_space
  [XFS] prevent panic during log recovery due to bogus op_hdr length
  [XFS] Cleanup various fid related bits:
  [XFS] Fix xfs_lowbit64
  [XFS] Remove CFORK macros and use code directly in IFORK and DFORK macros.
  [XFS] kill superflous buffer locking (2nd attempt)
  [XFS] Use kernel-supplied "roundup_pow_of_two" for simplicity
  [XFS] Remove the BPCSHIFT and NB* based macros from XFS.
  [XFS] Remove bogus assert
  [XFS] optimize XFS_IS_REALTIME_INODE w/o realtime config
  ...

85 files changed, 2303 insertions, 3184 deletions

diff --git a/fs/xfs/Makefile-linux-2.6 b/fs/xfs/Makefile-linux-2.6
index d1491aa7a0e..97316451fc6 100644
--- a/fs/xfs/Makefile-linux-2.6
+++ b/fs/xfs/Makefile-linux-2.6
@@ -70,7 +70,6 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_iget.o \
 				   xfs_inode.o \
 				   xfs_inode_item.o \
-				   xfs_iocore.o \
 				   xfs_iomap.o \
 				   xfs_itable.o \
 				   xfs_dfrag.o \
diff --git a/fs/xfs/linux-2.6/spin.h b/fs/xfs/linux-2.6/spin.h
deleted file mode 100644
index 50a6191178f..00000000000
--- a/fs/xfs/linux-2.6/spin.h
+++ /dev/null
@@ -1,45 +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_SUPPORT_SPIN_H__
-#define __XFS_SUPPORT_SPIN_H__
-
-#include <linux/sched.h>	/* preempt needs this */
-#include <linux/spinlock.h>
-
-/*
- * Map lock_t from IRIX to Linux spinlocks.
- *
- * We do not make use of lock_t from interrupt context, so we do not
- * have to worry about disabling interrupts at all (unlike IRIX).
- */
-
-typedef spinlock_t lock_t;
-
-#define SPLDECL(s)			unsigned long s
-#ifndef DEFINE_SPINLOCK
-#define DEFINE_SPINLOCK(s)		spinlock_t s = SPIN_LOCK_UNLOCKED
-#endif
-
-#define spinlock_init(lock, name)	spin_lock_init(lock)
-#define	spinlock_destroy(lock)
-#define mutex_spinlock(lock)		({ spin_lock(lock); 0; })
-#define mutex_spinunlock(lock, s)	do { spin_unlock(lock); (void)s; } while (0)
-#define nested_spinlock(lock)		spin_lock(lock)
-#define nested_spinunlock(lock)		spin_unlock(lock)
-
-#endif /* __XFS_SUPPORT_SPIN_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 2e34b104107..e0519529c26 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -107,6 +107,18 @@ xfs_page_trace(
 #define xfs_page_trace(tag, inode, page, pgoff)
 #endif
 
+STATIC struct block_device *
+xfs_find_bdev_for_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (XFS_IS_REALTIME_INODE(ip))
+		return mp->m_rtdev_targp->bt_bdev;
+	else
+		return mp->m_ddev_targp->bt_bdev;
+}
+
 /*
  * Schedule IO completion handling on a xfsdatad if this was
  * the final hold on this ioend. If we are asked to wait,
@@ -151,7 +163,7 @@ xfs_destroy_ioend(
 /*
  * Update on-disk file size now that data has been written to disk.
  * The current in-memory file size is i_size.  If a write is beyond
- * eof io_new_size will be the intended file size until i_size is
+ * eof i_new_size will be the intended file size until i_size is
  * updated.  If this write does not extend all the way to the valid
  * file size then restrict this update to the end of the write.
  */
@@ -173,7 +185,7 @@ xfs_setfilesize(
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
-	isize = MAX(ip->i_size, ip->i_iocore.io_new_size);
+	isize = MAX(ip->i_size, ip->i_new_size);
 	isize = MIN(isize, bsize);
 
 	if (ip->i_d.di_size < isize) {
@@ -226,12 +238,13 @@ xfs_end_bio_unwritten(
 {
 	xfs_ioend_t		*ioend =
 		container_of(work, xfs_ioend_t, io_work);
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	xfs_off_t		offset = ioend->io_offset;
 	size_t			size = ioend->io_size;
 
 	if (likely(!ioend->io_error)) {
-		xfs_bmap(XFS_I(ioend->io_inode), offset, size,
-				BMAPI_UNWRITTEN, NULL, NULL);
+		if (!XFS_FORCED_SHUTDOWN(ip->i_mount))
+			xfs_iomap_write_unwritten(ip, offset, size);
 		xfs_setfilesize(ioend);
 	}
 	xfs_destroy_ioend(ioend);
@@ -304,7 +317,7 @@ xfs_map_blocks(
 	xfs_inode_t		*ip = XFS_I(inode);
 	int			error, nmaps = 1;
 
-	error = xfs_bmap(ip, offset, count,
+	error = xfs_iomap(ip, offset, count,
 				flags, mapp, &nmaps);
 	if (!error && (flags & (BMAPI_WRITE|BMAPI_ALLOCATE)))
 		xfs_iflags_set(ip, XFS_IMODIFIED);
@@ -1323,7 +1336,7 @@ __xfs_get_blocks(
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
 	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
 	size = bh_result->b_size;
-	error = xfs_bmap(XFS_I(inode), offset, size,
+	error = xfs_iomap(XFS_I(inode), offset, size,
 			     create ? flags : BMAPI_READ, &iomap, &niomap);
 	if (error)
 		return -error;
@@ -1471,28 +1484,21 @@ xfs_vm_direct_IO(
 {
 	struct file	*file = iocb->ki_filp;
 	struct inode	*inode = file->f_mapping->host;
-	xfs_iomap_t	iomap;
-	int		maps = 1;
-	int		error;
+	struct block_device *bdev;
 	ssize_t		ret;
 
-	error = xfs_bmap(XFS_I(inode), offset, 0,
-				BMAPI_DEVICE, &iomap, &maps);
-	if (error)
-		return -error;
+	bdev = xfs_find_bdev_for_inode(XFS_I(inode));
 
 	if (rw == WRITE) {
 		iocb->private = xfs_alloc_ioend(inode, IOMAP_UNWRITTEN);
 		ret = blockdev_direct_IO_own_locking(rw, iocb, inode,
-			iomap.iomap_target->bt_bdev,
-			iov, offset, nr_segs,
+			bdev, iov, offset, nr_segs,
 			xfs_get_blocks_direct,
 			xfs_end_io_direct);
 	} else {
 		iocb->private = xfs_alloc_ioend(inode, IOMAP_READ);
 		ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
-			iomap.iomap_target->bt_bdev,
-			iov, offset, nr_segs,
+			bdev, iov, offset, nr_segs,
 			xfs_get_blocks_direct,
 			xfs_end_io_direct);
 	}
@@ -1525,8 +1531,7 @@ xfs_vm_bmap(
 	struct inode		*inode = (struct inode *)mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 
-	vn_trace_entry(XFS_I(inode), __FUNCTION__,
-			(inst_t *)__return_address);
+	xfs_itrace_entry(XFS_I(inode));
 	xfs_rwlock(ip, VRWLOCK_READ);
 	xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
 	xfs_rwunlock(ip, VRWLOCK_READ);
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 0382c19d652..e347bfd47c9 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -387,8 +387,6 @@ _xfs_buf_lookup_pages(
 		if (unlikely(page == NULL)) {
 			if (flags & XBF_READ_AHEAD) {
 				bp->b_page_count = i;
-				for (i = 0; i < bp->b_page_count; i++)
-					unlock_page(bp->b_pages[i]);
 				return -ENOMEM;
 			}
 
@@ -418,24 +416,17 @@ _xfs_buf_lookup_pages(
 		ASSERT(!PagePrivate(page));
 		if (!PageUptodate(page)) {
 			page_count--;
-			if (blocksize >= PAGE_CACHE_SIZE) {
-				if (flags & XBF_READ)
-					bp->b_locked = 1;
-			} else if (!PagePrivate(page)) {
+			if (blocksize < PAGE_CACHE_SIZE && !PagePrivate(page)) {
 				if (test_page_region(page, offset, nbytes))
 					page_count++;
 			}
 		}
 
+		unlock_page(page);
 		bp->b_pages[i] = page;
 		offset = 0;
 	}
 
-	if (!bp->b_locked) {
-		for (i = 0; i < bp->b_page_count; i++)
-			unlock_page(bp->b_pages[i]);
-	}
-
 	if (page_count == bp->b_page_count)
 		bp->b_flags |= XBF_DONE;
 
@@ -751,7 +742,6 @@ xfs_buf_associate_memory(
 		bp->b_pages[i] = mem_to_page((void *)pageaddr);
 		pageaddr += PAGE_CACHE_SIZE;
 	}
-	bp->b_locked = 0;
 
 	bp->b_count_desired = len;
 	bp->b_buffer_length = buflen;
@@ -1098,25 +1088,13 @@ xfs_buf_iostart(
 	return status;
 }
 
-STATIC_INLINE int
-_xfs_buf_iolocked(
-	xfs_buf_t		*bp)
-{
-	ASSERT(bp->b_flags & (XBF_READ | XBF_WRITE));
-	if (bp->b_flags & XBF_READ)
-		return bp->b_locked;
-	return 0;
-}
-
 STATIC_INLINE void
 _xfs_buf_ioend(
 	xfs_buf_t		*bp,
 	int			schedule)
 {
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
-		bp->b_locked = 0;
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
 		xfs_buf_ioend(bp, schedule);
-	}
 }
 
 STATIC void
@@ -1147,10 +1125,6 @@ xfs_buf_bio_end_io(
 
 		if (--bvec >= bio->bi_io_vec)
 			prefetchw(&bvec->bv_page->flags);
-
-		if (_xfs_buf_iolocked(bp)) {
-			unlock_page(page);
-		}
 	} while (bvec >= bio->bi_io_vec);
 
 	_xfs_buf_ioend(bp, 1);
@@ -1161,13 +1135,12 @@ STATIC void
 _xfs_buf_ioapply(
 	xfs_buf_t		*bp)
 {
-	int			i, rw, map_i, total_nr_pages, nr_pages;
+	int			rw, map_i, total_nr_pages, nr_pages;
 	struct bio		*bio;
 	int			offset = bp->b_offset;
 	int			size = bp->b_count_desired;
 	sector_t		sector = bp->b_bn;
 	unsigned int		blocksize = bp->b_target->bt_bsize;
-	int			locking = _xfs_buf_iolocked(bp);
 
 	total_nr_pages = bp->b_page_count;
 	map_i = 0;
@@ -1190,7 +1163,7 @@ _xfs_buf_ioapply(
 	 * filesystem block size is not smaller than the page size.
 	 */
 	if ((bp->b_buffer_length < PAGE_CACHE_SIZE) &&
-	    (bp->b_flags & XBF_READ) && locking &&
+	    (bp->b_flags & XBF_READ) &&
 	    (blocksize >= PAGE_CACHE_SIZE)) {
 		bio = bio_alloc(GFP_NOIO, 1);
 
@@ -1207,24 +1180,6 @@ _xfs_buf_ioapply(
 		goto submit_io;
 	}
 
-	/* Lock down the pages which we need to for the request */
-	if (locking && (bp->b_flags & XBF_WRITE) && (bp->b_locked == 0)) {
-		for (i = 0; size; i++) {
-			int		nbytes = PAGE_CACHE_SIZE - offset;
-			struct page	*page = bp->b_pages[i];
-
-			if (nbytes > size)
-				nbytes = size;
-
-			lock_page(page);
-
-			size -= nbytes;
-			offset = 0;
-		}
-		offset = bp->b_offset;
-		size = bp->b_count_desired;
-	}
-
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
 	nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT);
@@ -1571,7 +1526,7 @@ xfs_alloc_delwrite_queue(
 
 	INIT_LIST_HEAD(&btp->bt_list);
 	INIT_LIST_HEAD(&btp->bt_delwrite_queue);
-	spinlock_init(&btp->bt_delwrite_lock, "delwri_lock");
+	spin_lock_init(&btp->bt_delwrite_lock);
 	btp->bt_flags = 0;
 	btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd");
 	if (IS_ERR(btp->bt_task)) {
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index b5908a34b15..a3d207de48b 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -143,7 +143,6 @@ typedef struct xfs_buf {
 	void			*b_fspriv2;
 	void			*b_fspriv3;
 	unsigned short		b_error;	/* error code on I/O */
-	unsigned short		b_locked;	/* page array is locked */
 	unsigned int		b_page_count;	/* size of page array */
 	unsigned int		b_offset;	/* page offset in first page */
 	struct page		**b_pages;	/* array of page pointers */
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 15bd4948832..ca4f66c4de1 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -118,20 +118,29 @@ xfs_nfs_get_inode(
 	u64			ino,
 	u32			generation)
  {
-	xfs_fid_t		xfid;
-	bhv_vnode_t		*vp;
+ 	xfs_mount_t		*mp = XFS_M(sb);
+	xfs_inode_t		*ip;
 	int			error;
 
-	xfid.fid_len = sizeof(xfs_fid_t) - sizeof(xfid.fid_len);
-	xfid.fid_pad = 0;
-	xfid.fid_ino = ino;
-	xfid.fid_gen = generation;
+	/*
+	 * NFS can sometimes send requests for ino 0.  Fail them gracefully.
+	 */
+	if (ino == 0)
+		return ERR_PTR(-ESTALE);
 
-	error = xfs_vget(XFS_M(sb), &vp, &xfid);
+	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0);
 	if (error)
 		return ERR_PTR(-error);
+	if (!ip)
+		return ERR_PTR(-EIO);
+
+	if (!ip->i_d.di_mode || ip->i_d.di_gen != generation) {
+		xfs_iput_new(ip, XFS_ILOCK_SHARED);
+		return ERR_PTR(-ENOENT);
+	}
 
-	return vp ? vn_to_inode(vp) : NULL;
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return ip->i_vnode;
 }
 
 STATIC struct dentry *
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 21a1c2b1c5f..edab1ffbb16 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -350,8 +350,8 @@ xfs_file_readdir(
 
 		size = buf.used;
 		de = (struct hack_dirent *)buf.dirent;
-		curr_offset = de->offset /* & 0x7fffffff */;
 		while (size > 0) {
+			curr_offset = de->offset /* & 0x7fffffff */;
 			if (filldir(dirent, de->name, de->namlen,
 					curr_offset & 0x7fffffff,
 					de->ino, de->d_type)) {
@@ -362,7 +362,6 @@ xfs_file_readdir(
 				       sizeof(u64));
 			size -= reclen;
 			de = (struct hack_dirent *)((char *)de + reclen);
-			curr_offset = de->offset /* & 0x7fffffff */;
 		}
 	}
 
diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/linux-2.6/xfs_globals.c
index 9febf9dc999..ef90e64641e 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/