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: (59 commits)
  [XFS] eagerly remove vmap mappings to avoid upsetting Xen
  [XFS] simplify validata_fields
  [XFS] no longer using io_vnode, as was remaining from 23 cherrypick
  [XFS] Remove STATIC which was missing from prior manual merge
  [XFS] Put back the QUEUE_ORDERED_NONE test in the barrier check.
  [XFS] Turn off XBF_ASYNC flag before re-reading superblock.
  [XFS] avoid race in sync_inodes() that can fail to write out all dirty data
  [XFS] This fix prevents bulkstat from spinning in an infinite loop.
  [XFS] simplify xfs_create/mknod/symlink prototype
  [XFS] avoid xfs_getattr in XFS_IOC_FSGETXATTR ioctl
  [XFS] get_bulkall() could return incorrect inode state
  [XFS] Kill unused IOMAP_EOF flag
  [XFS] fix when DMAPI mount option processing happens
  [XFS] ensure file size is logged on synchronous writes
  [XFS] growlock should be a mutex
  [XFS] replace some large xfs_log_priv.h macros by proper functions
  [XFS] kill struct bhv_vfs
  [XFS] move syncing related members from struct bhv_vfs to struct xfs_mount
  [XFS] kill the vfs_flags member in struct bhv_vfs
  [XFS] kill the vfs_fsid and vfs_altfsid members in struct bhv_vfs
  ...

90 files changed, 2762 insertions, 4739 deletions

diff --git a/fs/xfs/Makefile-linux-2.6 b/fs/xfs/Makefile-linux-2.6
index e7a9a83f008..d1491aa7a0e 100644
--- a/fs/xfs/Makefile-linux-2.6
+++ b/fs/xfs/Makefile-linux-2.6
@@ -49,7 +49,6 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_alloc_btree.o \
 				   xfs_attr.o \
 				   xfs_attr_leaf.o \
-				   xfs_behavior.o \
 				   xfs_bit.o \
 				   xfs_bmap.o \
 				   xfs_bmap_btree.o \
@@ -108,13 +107,11 @@ xfs-y				+= $(addprefix $(XFS_LINUX)/, \
 				   xfs_iops.o \
 				   xfs_lrw.o \
 				   xfs_super.o \
-				   xfs_vfs.o \
 				   xfs_vnode.o)
 
 # Objects in support/
 xfs-y				+= $(addprefix support/, \
 				   debug.o \
-				   move.o \
 				   uuid.o)
 
 xfs-$(CONFIG_XFS_TRACE)		+= support/ktrace.o
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 52bd08c0a27..2e34b104107 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -37,6 +37,7 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_iomap.h"
+#include "xfs_vnodeops.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
@@ -139,9 +140,11 @@ xfs_destroy_ioend(
 		next = bh->b_private;
 		bh->b_end_io(bh, !ioend->io_error);
 	}
-	if (unlikely(ioend->io_error))
-		vn_ioerror(ioend->io_vnode, ioend->io_error, __FILE__,__LINE__);
-	vn_iowake(ioend->io_vnode);
+	if (unlikely(ioend->io_error)) {
+		vn_ioerror(XFS_I(ioend->io_inode), ioend->io_error,
+				__FILE__,__LINE__);
+	}
+	vn_iowake(XFS_I(ioend->io_inode));
 	mempool_free(ioend, xfs_ioend_pool);
 }
 
@@ -156,14 +159,10 @@ STATIC void
 xfs_setfilesize(
 	xfs_ioend_t		*ioend)
 {
-	xfs_inode_t		*ip;
+	xfs_inode_t		*ip = XFS_I(ioend->io_inode);
 	xfs_fsize_t		isize;
 	xfs_fsize_t		bsize;
 
-	ip = xfs_vtoi(ioend->io_vnode);
-	if (!ip)
-		return;
-
 	ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
 	ASSERT(ioend->io_type != IOMAP_READ);
 
@@ -181,7 +180,7 @@ xfs_setfilesize(
 		ip->i_d.di_size = isize;
 		ip->i_update_core = 1;
 		ip->i_update_size = 1;
-		mark_inode_dirty_sync(vn_to_inode(ioend->io_vnode));
+		mark_inode_dirty_sync(ioend->io_inode);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -227,12 +226,12 @@ xfs_end_bio_unwritten(
 {
 	xfs_ioend_t		*ioend =
 		container_of(work, xfs_ioend_t, io_work);
-	bhv_vnode_t		*vp = ioend->io_vnode;
 	xfs_off_t		offset = ioend->io_offset;
 	size_t			size = ioend->io_size;
 
 	if (likely(!ioend->io_error)) {
-		bhv_vop_bmap(vp, offset, size, BMAPI_UNWRITTEN, NULL, NULL);
+		xfs_bmap(XFS_I(ioend->io_inode), offset, size,
+				BMAPI_UNWRITTEN, NULL, NULL);
 		xfs_setfilesize(ioend);
 	}
 	xfs_destroy_ioend(ioend);
@@ -275,10 +274,10 @@ xfs_alloc_ioend(
 	ioend->io_error = 0;
 	ioend->io_list = NULL;
 	ioend->io_type = type;
-	ioend->io_vnode = vn_from_inode(inode);
+	ioend->io_inode = inode;
 	ioend->io_buffer_head = NULL;
 	ioend->io_buffer_tail = NULL;
-	atomic_inc(&ioend->io_vnode->v_iocount);
+	atomic_inc(&XFS_I(ioend->io_inode)->i_iocount);
 	ioend->io_offset = 0;
 	ioend->io_size = 0;
 
@@ -302,12 +301,13 @@ xfs_map_blocks(
 	xfs_iomap_t		*mapp,
 	int			flags)
 {
-	bhv_vnode_t		*vp = vn_from_inode(inode);
+	xfs_inode_t		*ip = XFS_I(inode);
 	int			error, nmaps = 1;
 
-	error = bhv_vop_bmap(vp, offset, count, flags, mapp, &nmaps);
+	error = xfs_bmap(ip, offset, count,
+				flags, mapp, &nmaps);
 	if (!error && (flags & (BMAPI_WRITE|BMAPI_ALLOCATE)))
-		VMODIFY(vp);
+		xfs_iflags_set(ip, XFS_IMODIFIED);
 	return -error;
 }
 
@@ -497,7 +497,7 @@ xfs_cancel_ioend(
 			unlock_buffer(bh);
 		} while ((bh = next_bh) != NULL);
 
-		vn_iowake(ioend->io_vnode);
+		vn_iowake(XFS_I(ioend->io_inode));
 		mempool_free(ioend, xfs_ioend_pool);
 	} while ((ioend = next) != NULL);
 }
@@ -1237,10 +1237,7 @@ xfs_vm_writepages(
 	struct address_space	*mapping,
 	struct writeback_control *wbc)
 {
-	struct bhv_vnode	*vp = vn_from_inode(mapping->host);
-
-	if (VN_TRUNC(vp))
-		VUNTRUNCATE(vp);
+	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
 	return generic_writepages(mapping, wbc);
 }
 
@@ -1317,7 +1314,6 @@ __xfs_get_blocks(
 	int			direct,
 	bmapi_flags_t		flags)
 {
-	bhv_vnode_t		*vp = vn_from_inode(inode);
 	xfs_iomap_t		iomap;
 	xfs_off_t		offset;
 	ssize_t			size;
@@ -1327,7 +1323,7 @@ __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 = bhv_vop_bmap(vp, offset, size,
+	error = xfs_bmap(XFS_I(inode), offset, size,
 			     create ? flags : BMAPI_READ, &iomap, &niomap);
 	if (error)
 		return -error;
@@ -1475,13 +1471,13 @@ xfs_vm_direct_IO(
 {
 	struct file	*file = iocb->ki_filp;
 	struct inode	*inode = file->f_mapping->host;
-	bhv_vnode_t	*vp = vn_from_inode(inode);
 	xfs_iomap_t	iomap;
 	int		maps = 1;
 	int		error;
 	ssize_t		ret;
 
-	error = bhv_vop_bmap(vp, offset, 0, BMAPI_DEVICE, &iomap, &maps);
+	error = xfs_bmap(XFS_I(inode), offset, 0,
+				BMAPI_DEVICE, &iomap, &maps);
 	if (error)
 		return -error;
 
@@ -1527,12 +1523,13 @@ xfs_vm_bmap(
 	sector_t		block)
 {
 	struct inode		*inode = (struct inode *)mapping->host;
-	bhv_vnode_t		*vp = vn_from_inode(inode);
+	struct xfs_inode	*ip = XFS_I(inode);
 
-	vn_trace_entry(vp, __FUNCTION__, (inst_t *)__return_address);
-	bhv_vop_rwlock(vp, VRWLOCK_READ);
-	bhv_vop_flush_pages(vp, (xfs_off_t)0, -1, 0, FI_REMAPF);
-	bhv_vop_rwunlock(vp, VRWLOCK_READ);
+	vn_trace_entry(XFS_I(inode), __FUNCTION__,
+			(inst_t *)__return_address);
+	xfs_rwlock(ip, VRWLOCK_READ);
+	xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
+	xfs_rwunlock(ip, VRWLOCK_READ);
 	return generic_block_bmap(mapping, block, xfs_get_blocks);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 2244e516b66..3ba0631a381 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -32,7 +32,7 @@ typedef struct xfs_ioend {
 	unsigned int		io_type;	/* delalloc / unwritten */
 	int			io_error;	/* I/O error code */
 	atomic_t		io_remaining;	/* hold count */
-	struct bhv_vnode	*io_vnode;	/* file being written to */
+	struct inode		*io_inode;	/* file being written to */
 	struct buffer_head	*io_buffer_head;/* buffer linked list head */
 	struct buffer_head	*io_buffer_tail;/* buffer linked list tail */
 	size_t			io_size;	/* size of the extent */
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 39f44ee572e..b9c8589e05c 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -187,6 +187,19 @@ free_address(
 {
 	a_list_t	*aentry;
 
+#ifdef CONFIG_XEN
+	/*
+	 * Xen needs to be able to make sure it can get an exclusive
+	 * RO mapping of pages it wants to turn into a pagetable.  If
+	 * a newly allocated page is also still being vmap()ed by xfs,
+	 * it will cause pagetable construction to fail.  This is a
+	 * quick workaround to always eagerly unmap pages so that Xen
+	 * is happy.
+	 */
+	vunmap(addr);
+	return;
+#endif
+
 	aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT);
 	if (likely(aentry)) {
 		spin_lock(&as_lock);
@@ -997,7 +1010,18 @@ xfs_buf_iodone_work(
 	xfs_buf_t		*bp =
 		container_of(work, xfs_buf_t, b_iodone_work);
 
-	if (bp->b_iodone)
+	/*
+	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
+	 * ordered flag and reissue them.  Because we can't tell the higher
+	 * layers directly that they should not issue ordered I/O anymore, they
+	 * need to check if the ordered flag was cleared during I/O completion.
+	 */
+	if ((bp->b_error == EOPNOTSUPP) &&
+	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
+		XB_TRACE(bp, "ordered_retry", bp->b_iodone);
+		bp->b_flags &= ~XBF_ORDERED;
+		xfs_buf_iorequest(bp);
+	} else if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index e3a5fedac1b..726449d4fd2 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -17,12 +17,18 @@
  */
 #include "xfs.h"
 #include "xfs_types.h"
-#include "xfs_dmapi.h"
+#include "xfs_inum.h"
 #include "xfs_log.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_dmapi.h"
 #include "xfs_mount.h"
 #include "xfs_export.h"
+#include "xfs_vnodeops.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_vfsops.h"
 
 static struct dentry dotdot = { .d_name.name = "..", .d_name.len = 2, };
 
@@ -96,9 +102,7 @@ xfs_fs_encode_fh(
 	int			len;
 	int			is64 = 0;
 #if XFS_BIG_INUMS
-	bhv_vfs_t		*vfs = vfs_from_sb(inode->i_sb);
-
-	if (!(vfs->vfs_flag & VFS_32BITINODES)) {
+	if (!(XFS_M(inode->i_sb)->m_flags & XFS_MOUNT_SMALL_INUMS)) {
 		/* filesystem may contain 64bit inode numbers */
 		is64 = XFS_FILEID_TYPE_64FLAG;
 	}
@@ -138,10 +142,9 @@ xfs_fs_get_dentry(
 	bhv_vnode_t		*vp;
 	struct inode		*inode;
 	struct dentry		*result;
-	bhv_vfs_t		*vfsp = vfs_from_sb(sb);
 	int			error;
 
-	error = bhv_vfs_vget(vfsp, &vp, (fid_t *)data);
+	error = xfs_vget(XFS_M(sb), &vp, (fid_t *)data);
 	if (error || vp == NULL)
 		return ERR_PTR(-ESTALE) ;
 
@@ -159,12 +162,11 @@ xfs_fs_get_parent(
 	struct dentry		*child)
 {
 	int			error;
-	bhv_vnode_t		*vp, *cvp;
+	bhv_vnode_t		*cvp;
 	struct dentry		*parent;
 
 	cvp = NULL;
-	vp = vn_from_inode(child->d_inode);
-	error = bhv_vop_lookup(vp, &dotdot, &cvp, 0, NULL, NULL);
+	error = xfs_lookup(XFS_I(child->d_inode), &dotdot, &cvp);
 	if (unlikely(error))
 		return ERR_PTR(-error);
 
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 0d4001eafd1..fb8dd34041e 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -37,6 +37,7 @@
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_ioctl32.h"
+#include "xfs_vnodeops.h"
 
 #include <linux/dcache.h>
 #include <linux/smp_lock.h>
@@ -55,13 +56,12 @@ __xfs_file_read(
 	loff_t			pos)
 {
 	struct file		*file = iocb->ki_filp;
-	bhv_vnode_t		*vp = vn_from_inode(file->f_path.dentry->d_inode);
 
 	BUG_ON(iocb->ki_pos != pos);
 	if (unlikely(file->f_flags & O_DIRECT))
 		ioflags |= IO_ISDIRECT;
-	return bhv_vop_read(vp, iocb, iov, nr_segs, &iocb->ki_pos,
-				ioflags, NULL);
+	return xfs_read(XFS_I(file->f_path.dentry->d_inode), iocb, iov,
+				nr_segs, &iocb->ki_pos, ioflags);
 }
 
 STATIC ssize_t
@@ -93,14 +93,12 @@ __xfs_file_write(
 	loff_t			pos)
 {
 	struct file	*file = iocb->ki_filp;
-	struct inode	*inode = file->f_mapping->host;
-	bhv_vnode_t	*vp = vn_from_inode(inode);
 
 	BUG_ON(iocb->ki_pos != pos);
 	if (unlikely(file->f_flags & O_DIRECT))
 		ioflags |= IO_ISDIRECT;
-	return bhv_vop_write(vp, iocb, iov, nr_segs, &iocb->ki_pos,
-				ioflags, NULL);
+	return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
+				&iocb->ki_pos, ioflags);
 }
 
 STATIC ssize_t
@@ -131,8 +129,8 @@ xfs_file_splice_read(
 	size_t			len,
 	unsigned int		flags)
 {
-	return bhv_vop_splice_read(vn_from_inode(infilp->f_path.dentry->d_inode),
-				   infilp, ppos, pipe, len, flags, 0, NULL);
+	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
+				   infilp, ppos, pipe, len, flags, 0);