[Cluster-devel] GFS2: Pre-pull patch posting

[Cluster-devel] GFS2: Pre-pull patch posting

[Steven Whitehouse]

Hi,

As the merge window is more or less upon us, here is the content
of the GFS2 -nmw tree. There is nothing too startling this time
as the focus has very much been bug fixes and clean up.

We have a new mount option, commit= which does exactly the same
thing as the ext3 equivalent option. We have a long term plan to
make all the tunable parameters available as mount options and
thus to be able to eventually drop the sysfs interface to these
parameters.

Another long term plan is to get rid of the files named
ops_somethingorother and to either merge them into other
files, or rename them to not have the ops_ prefix. This
patch series makes a start on that, and does all the easy
ones. As a result some functions with only one caller are
moved to the same file as their caller and made static.

The docs are also updated to reflect the fact that the
lock_dlm interface module no longer exists and that interface is
now built into GFS2.

Steve.

[Cluster-devel] [PATCH 01/24] GFS2: Update the rw flags

[Steven Whitehouse]

After Jens recent updates:
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=a1f242524c3c1f5d40f1c9c343427e34d1aadd6e
et al. this is a patch to bring gfs2 uptodate with the core
code. Also I've managed to squash another call to ll_rw_block()
along the way.

There is still one part of the GFS2 I/O paths which are not correctly
annotated and that is due to the sharing of the writeback code between
the data and metadata address spaces. I would like to change that too,
but this patch is still worth doing on its own, I think.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 98918a7..aa62cf5 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -120,7 +120,7 @@ __acquires(&sdp->sd_log_lock)
 			lock_buffer(bh);
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
-				submit_bh(WRITE, bh);
+				submit_bh(WRITE_SYNC_PLUG, bh);
 			} else {
 				unlock_buffer(bh);
 				brelse(bh);
@@ -604,7 +604,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
 		goto skip_barrier;
 	get_bh(bh);
-	submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
+	submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh);
 	wait_on_buffer(bh);
 	if (buffer_eopnotsupp(bh)) {
 		clear_buffer_eopnotsupp(bh);
@@ -664,7 +664,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 		lock_buffer(bh);
 		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
 			bh->b_end_io = end_buffer_write_sync;
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 		} else {
 			unlock_buffer(bh);
 			brelse(bh);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 80e4f5f..00315f5 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -13,6 +13,8 @@
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -189,7 +191,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 		}
 
 		gfs2_log_unlock(sdp);
-		submit_bh(WRITE, bh);
+		submit_bh(WRITE_SYNC_PLUG, bh);
 		gfs2_log_lock(sdp);
 
 		n = 0;
@@ -199,7 +201,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 			gfs2_log_unlock(sdp);
 			lock_buffer(bd2->bd_bh);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
@@ -341,7 +343,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 
 			bh = gfs2_log_get_buf(sdp);
 			mh = (struct gfs2_meta_header *)bh->b_data;
@@ -358,7 +360,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	}
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 
-	submit_bh(WRITE, bh);
+	submit_bh(WRITE_SYNC_PLUG, bh);
 }
 
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -560,7 +562,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	ptr = bh_log_ptr(bh);
 	
 	get_bh(bh);
-	submit_bh(WRITE, bh);
+	submit_bh(WRITE_SYNC_PLUG, bh);
 	gfs2_log_lock(sdp);
 	while(!list_empty(list)) {
 		bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
@@ -586,7 +588,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 		} else {
 			bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
 		}
-		submit_bh(WRITE, bh1);
+		submit_bh(WRITE_SYNC_PLUG, bh1);
 		gfs2_log_lock(sdp);
 		ptr += 2;
 	}
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 8d6f132..75b2aec 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -201,16 +201,32 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		   struct buffer_head **bhp)
 {
-	*bhp = gfs2_getbuf(gl, blkno, CREATE);
-	if (!buffer_uptodate(*bhp)) {
-		ll_rw_block(READ_META, 1, bhp);
-		if (flags & DIO_WAIT) {
-			int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
-			if (error) {
-				brelse(*bhp);
-				return error;
-			}
-		}
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *bh;
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);
+
+	lock_buffer(bh);
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+	bh->b_end_io = end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(READ_SYNC | (1 << BIO_RW_META), bh);
+	if (!(flags & DIO_WAIT))
+		return 0;
+
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh))) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		brelse(bh);
+		return -EIO;
 	}
 
 	return 0;
@@ -404,7 +420,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(READ_META, 1, &first_bh);
+		ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh);
 
 	dblock++;
 	extlen--;
-- 
1.6.0.6

[Cluster-devel] [PATCH 02/24] GFS2: Optimise writepage for metadata

[Steven Whitehouse]

This adds a GFS2 specific writepage for metadata, rather than
continuing to use the VFS function. As a result we now tag all
our metadata I/O with the correct flag so that blktraces will
now be less confusing.

Also, the generic function was checking for a number of corner
cases which cannot happen on the metadata address spaces so that
this should be faster too.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 75b2aec..78a5f43 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -33,17 +33,65 @@
 #include "util.h"
 #include "ops_address.h"
 
-static int aspace_get_block(struct inode *inode, sector_t lblock,
-			    struct buffer_head *bh_result, int create)
+static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
 {
-	gfs2_assert_warn(inode->i_sb->s_fs_info, 0);
-	return -EOPNOTSUPP;
-}
+	int err;
+	struct buffer_head *bh, *head;
+	int nr_underway = 0;
+	int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ?
+			WRITE_SYNC_PLUG : WRITE));
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!page_has_buffers(page));
+
+	head = page_buffers(page);
+	bh = head;
+
+	do {
+		if (!buffer_mapped(bh))
+			continue;
+		/*
+		 * If it's a fully non-blocking write attempt and we cannot
+		 * lock the buffer then redirty the page.  Note that this can
+		 * potentially cause a busy-wait loop from pdflush and kswapd
+		 * activity, but those code paths have their own higher-level
+		 * throttling.
+		 */
+		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
+			lock_buffer(bh);
+		} else if (!trylock_buffer(bh)) {
+			redirty_page_for_writepage(wbc, page);
+			continue;
+		}
+		if (test_clear_buffer_dirty(bh)) {
+			mark_buffer_async_write(bh);
+		} else {
+			unlock_buffer(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+	/*
+	 * The page and its buffers are protected by PageWriteback(), so we can
+	 * drop the bh refcounts early.
+	 */
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			submit_bh(write_op, bh);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
 
-static int gfs2_aspace_writepage(struct page *page,
-				 struct writeback_control *wbc)
-{
-	return block_write_full_page(page, aspace_get_block, wbc);
+	err = 0;
+	if (nr_underway == 0)
+		end_page_writeback(page);
+
+	return err;
 }
 
 static const struct address_space_operations aspace_aops = {
-- 
1.6.0.6

[Cluster-devel] [PATCH 03/24] GFS2: Something nonlinear this way comes!

[Steven Whitehouse]

For some reason GFS2 has been missing support for non-linear
mappings. This patch fixes that, and also avoids taking any
locks for mmap in the O_NOATIME case. In fact we don't actually need
to take the lock here at all - just doing file_accessed() would be
enough, but we have to take the lock eventually and this helps
it hit disk (and thus be seen by other nodes) faster.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 5d82e91..0ee7bd2 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -425,33 +425,36 @@ static struct vm_operations_struct gfs2_vm_ops = {
 	.page_mkwrite = gfs2_page_mkwrite,
 };
 
-
 /**
  * gfs2_mmap -
  * @file: The file to map
  * @vma: The VMA which described the mapping
  *
- * Returns: 0 or error code
+ * There is no need to get a lock here unless we should be updating
+ * atime. We ignore any locking errors since the only consequence is
+ * a missed atime update (which will just be deferred until later).
+ *
+ * Returns: 0
  */
 
 static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_holder i_gh;
-	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
-	error = gfs2_glock_nq(&i_gh);
-	if (error) {
-		gfs2_holder_uninit(&i_gh);
-		return error;
-	}
+	if (!(file->f_flags & O_NOATIME)) {
+		struct gfs2_holder i_gh;
+		int error;
 
+		gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+		error = gfs2_glock_nq(&i_gh);
+		file_accessed(file);
+		if (error == 0)
+			gfs2_glock_dq_uninit(&i_gh);
+	}
 	vma->vm_ops = &gfs2_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
 
-	gfs2_glock_dq_uninit(&i_gh);
-
-	return error;
+	return 0;
 }
 
 /**
-- 
1.6.0.6

[Cluster-devel] [PATCH 04/24] GFS2: Fix timestamps on write

[Steven Whitehouse]

From: Abhijith Das <adas@redhat.com>

This patch copies the timestamps from the vfs inode into gfs2 and syncs
it to the disk inode during writes.

Signed-off-by: Abhijith Das <adas@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index a6dde17..e566421 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -781,10 +781,12 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	unlock_page(page);
 	page_cache_release(page);
 
-	if (inode->i_size < to) {
-		i_size_write(inode, to);
-		ip->i_disksize = inode->i_size;
-		di->di_size = cpu_to_be64(inode->i_size);
+	if (copied) {
+		if (inode->i_size < to) {
+			i_size_write(inode, to);
+			ip->i_disksize = inode->i_size;
+		}
+		gfs2_dinode_out(ip, di);
 		mark_inode_dirty(inode);
 	}
 
@@ -824,7 +826,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *dibh;
 	struct gfs2_alloc *al = ip->i_alloc;
-	struct gfs2_dinode *di;
 	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
 	unsigned int to = from + len;
 	int ret;
@@ -847,11 +848,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 		gfs2_page_add_databufs(ip, page, from, to);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	if (likely(ret >= 0) && (inode->i_size > ip->i_disksize)) {
-		di = (struct gfs2_dinode *)dibh->b_data;
-		ip->i_disksize = inode->i_size;
-		di->di_size = cpu_to_be64(inode->i_size);
+	if (ret > 0) {
+		if (inode->i_size > ip->i_disksize)
+			ip->i_disksize = inode->i_size;
+		gfs2_dinode_out(ip, dibh->b_data);
 		mark_inode_dirty(inode);
 	}
 
-- 
1.6.0.6

[Cluster-devel] [PATCH 05/24] GFS2: Move journal live test at transaction start

[Steven Whitehouse]

There seems little point grabbing the transaction glock
only to have to release it again if the journal isn't
live. This moves the test earlier to avoid grabbing the lock
when we don't need it in the first place.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 053752d..4ef0e9f 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -33,6 +33,9 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	BUG_ON(current->journal_info);
 	BUG_ON(blocks == 0 && revokes == 0);
 
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
 	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
 	if (!tr)
 		return -ENOMEM;
@@ -54,12 +57,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (error)
 		goto fail_holder_uninit;
 
-	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		tr->tr_t_gh.gh_flags |= GL_NOCACHE;
-		error = -EROFS;
-		goto fail_gunlock;
-	}
-
 	error = gfs2_log_reserve(sdp, tr->tr_reserved);
 	if (error)
 		goto fail_gunlock;
-- 
1.6.0.6

[Cluster-devel] [PATCH 06/24] GFS2: Add commit= mount option

[Steven Whitehouse]

It has always been possible to adjust the gfs2 log commit
interval, but only from the sysfs interface. This adds a
mount option, commit=<nn>, which will be familar to ext3
users.

The sysfs interface continues to be available as well, although
this might be removed in the future.

Also this patch cleans up some duplicated structures in the GFS2
sysfs code.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 399d1b9..65f438e 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -418,6 +418,7 @@ struct gfs2_args {
 	unsigned int ar_data:2;			/* ordered/writeback */
 	unsigned int ar_meta:1;			/* mount metafs */
 	unsigned int ar_discard:1;		/* discard requests */
+	int ar_commit;				/* Commit interval */
 };
 
 struct gfs2_tune {
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index f7e8527..947af15 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -45,6 +45,7 @@ enum {
 	Opt_meta,
 	Opt_discard,
 	Opt_nodiscard,
+	Opt_commit,
 	Opt_err,
 };
 
@@ -73,6 +74,7 @@ static const match_table_t tokens = {
 	{Opt_meta, "meta"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
+	{Opt_commit, "commit=%d"},
 	{Opt_err, NULL}
 };
 
@@ -89,6 +91,7 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
 	char *o;
 	int token;
 	substring_t tmp[MAX_OPT_ARGS];
+	int rv;
 
 	/* Split the options into tokens with the "," character and
 	   process them */
@@ -173,6 +176,13 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
 		case Opt_nodiscard:
 			args->ar_discard = 0;
 			break;
+		case Opt_commit:
+			rv = match_int(&tmp[0], &args->ar_commit);
+			if (rv || args->ar_commit <= 0) {
+				fs_info(sdp, "commit mount option requires a positive numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
 		case Opt_err:
 		default:
 			fs_info(sdp, "invalid mount option: %s\n", o);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1ff9473..7981fbc 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -55,7 +55,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 	spin_lock_init(&gt->gt_spin);
 
 	gt->gt_incore_log_blocks = 1024;
-	gt->gt_log_flush_secs = 60;
 	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quota_simul_sync = 64;
@@ -1165,6 +1164,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 
 	sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT;
 	sdp->sd_args.ar_data = GFS2_DATA_DEFAULT;
+	sdp->sd_args.ar_commit = 60;
 
 	error = gfs2_mount_args(sdp, &sdp->sd_args, data);
 	if (error) {
@@ -1191,6 +1191,8 @@ static int fill_super(struct super_block *sb, void *data, int silent)
                                GFS2_BASIC_BLOCK_SHIFT;
 	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
 
+	sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit;
+
 	error = init_names(sdp, silent);
 	if (error)
 		goto fail;
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index 4580195..0677a83 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -436,8 +436,12 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
+	struct gfs2_tune *gt = &sdp->sd_tune;
 	int error;
 
+	spin_lock(&gt->gt_spin);
+	args.ar_commit = gt->gt_log_flush_secs;
+	spin_unlock(&gt->gt_spin);
 	error = gfs2_mount_args(sdp, &args, data);
 	if (error)
 		return error;
@@ -473,6 +477,10 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 		sb->s_flags |= MS_POSIXACL;
 	else
 		sb->s_flags &= ~MS_POSIXACL;
+	spin_lock(&gt->gt_spin);
+	gt->gt_log_flush_secs = args.ar_commit;
+	spin_unlock(&gt->gt_spin);
+
 	return 0;
 }
 
@@ -550,6 +558,7 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 {
 	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
 	struct gfs2_args *args = &sdp->sd_args;
+	int lfsecs;
 
 	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
 		seq_printf(s, ",meta");
@@ -610,7 +619,9 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	}
 	if (args->ar_discard)
 		seq_printf(s, ",discard");
-
+	lfsecs = sdp->sd_tune.gt_log_flush_secs;
+	if (lfsecs != 60)
+		seq_printf(s, ",commit=%d", lfsecs);
 	return 0;
 }
 
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 7655f50..d53b22e 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -26,6 +26,36 @@
 #include "util.h"
 #include "glops.h"
 
+struct gfs2_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->show ? a->show(sdp, buf) : 0;
+}
+
+static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->store ? a->store(sdp, buf, len) : len;
+}
+
+static struct sysfs_ops gfs2_attr_ops = {
+	.show  = gfs2_attr_show,
+	.store = gfs2_attr_store,
+};
+
+
+static struct kset *gfs2_kset;
+
 static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%u:%u\n",
@@ -212,11 +242,6 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
 	return len;
 }
 
-struct gfs2_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
-};
 
 #define GFS2_ATTR(name, mode, show, store) \
 static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)
@@ -246,49 +271,21 @@ static struct attribute *gfs2_attrs[] = {
 	NULL,
 };
 
-static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
-			      char *buf)
-{
-	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
-	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
-	return a->show ? a->show(sdp, buf) : 0;
-}
-
-static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
-			       const char *buf, size_t len)
-{
-	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
-	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
-	return a->store ? a->store(sdp, buf, len) : len;
-}
-
-static struct sysfs_ops gfs2_attr_ops = {
-	.show  = gfs2_attr_show,
-	.store = gfs2_attr_store,
-};
-
 static struct kobj_type gfs2_ktype = {
 	.default_attrs = gfs2_attrs,
 	.sysfs_ops     = &gfs2_attr_ops,
 };
 
-static struct kset *gfs2_kset;
-
 /*
  * display struct lm_lockstruct fields
  */
 
-struct lockstruct_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-};
-
 #define LOCKSTRUCT_ATTR(name, fmt)                                          \
 static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
 {                                                                           \
 	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \
 }                                                                           \
-static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name)
+static struct gfs2_attr lockstruct_attr_##name = __ATTR_RO(name)
 
 LOCKSTRUCT_ATTR(jid,      "%u\n");
 LOCKSTRUCT_ATTR(first,    "%u\n");
@@ -401,14 +398,8 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
 	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
 }
 
-struct gdlm_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *sdp, char *);
-	ssize_t (*store)(struct gfs2_sbd *sdp, const char *, size_t);
-};
-
 #define GDLM_ATTR(_name,_mode,_show,_store) \
-static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
+static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
 GDLM_ATTR(proto_name,     0444, proto_name_show,     NULL);
 GDLM_ATTR(block,          0644, block_show,          block_store);
@@ -434,21 +425,12 @@ static struct attribute *lock_module_attrs[] = {
 	NULL,
 };
 
-/*
- * display struct gfs2_args fields
- */
-
-struct args_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-};
-
 #define ARGS_ATTR(name, fmt)                                                \
 static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
 {                                                                           \
 	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name);       \
 }                                                                           \
-static struct args_attr args_attr_##name = __ATTR_RO(name)
+static struct gfs2_attr args_attr_##name = __ATTR_RO(name)
 
 ARGS_ATTR(lockproto,       "%s\n");
 ARGS_ATTR(locktable,       "%s\n");
@@ -531,14 +513,8 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
 	return len;
 }
 
-struct tune_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
-};
-
 #define TUNE_ATTR_3(name, show, store)                                        \
-static struct tune_attr tune_attr_##name = __ATTR(name, 0644, show, store)
+static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store)
 
 #define TUNE_ATTR_2(name, store)                                              \
 static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
-- 
1.6.0.6

[Cluster-devel] [PATCH 07/24] GFS2: Remove a couple of unused sysfs entries

[Steven Whitehouse]

These two tunables are pointless and would never need to be
changed anyway. There is also a race between them and umount
as the deamons which they refer to might have gone away. The
easiest way to fix the race is to remove the interface.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index d53b22e..894bf77 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -530,15 +530,6 @@ static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
 }                                                                             \
 TUNE_ATTR_2(name, name##_store)
 
-#define TUNE_ATTR_DAEMON(name, process)                                       \
-static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
-{                                                                             \
-	ssize_t r = tune_set(sdp, &sdp->sd_tune.gt_##name, 1, buf, len);      \
-	wake_up_process(sdp->sd_##process);                                   \
-	return r;                                                             \
-}                                                                             \
-TUNE_ATTR_2(name, name##_store)
-
 TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
@@ -550,8 +541,6 @@ TUNE_ATTR(new_files_jdata, 0);
 TUNE_ATTR(quota_simul_sync, 1);
 TUNE_ATTR(stall_secs, 1);
 TUNE_ATTR(statfs_quantum, 1);
-TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process);
-TUNE_ATTR_DAEMON(logd_secs, logd_process);
 TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
 
 static struct attribute *tune_attrs[] = {
@@ -565,8 +554,6 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_quota_simul_sync.attr,
 	&tune_attr_stall_secs.attr,
 	&tune_attr_statfs_quantum.attr,
-	&tune_attr_recoverd_secs.attr,
-	&tune_attr_logd_secs.attr,
 	&tune_attr_quota_scale.attr,
 	&tune_attr_new_files_jdata.attr,
 	NULL,
-- 
1.6.0.6

[Cluster-devel] [PATCH 08/24] GFS2: Umount recovery race fix

[Steven Whitehouse]

This patch fixes a race condition where we can receive recovery
requests part way through processing a umount. This was causing
problems since the recovery thread had already gone away.

Looking in more detail at the recovery code, it was really trying
to implement a slight variation on a work queue, and that happens to
align nicely with the recently introduced slow-work subsystem. As a
result I've updated the code to use slow-work, rather than its own home
grown variety of work queue.

When using the wait_on_bit() function, I noticed that the wait function
that was supplied as an argument was appearing in the WCHAN field, so
I've updated the function names in order to produce more meaningful
output.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index 3a981b7..cad957c 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -7,6 +7,7 @@ config GFS2_FS
 	select IP_SCTP if DLM_SCTP
 	select FS_POSIX_ACL
 	select CRC32
+	select SLOW_WORK
 	help
 	  A cluster filesystem.
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ff49810..2bf62bc 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -796,22 +796,37 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
 	gh->gh_ip = 0;
 }
 
-static int just_schedule(void *word)
+/**
+ * gfs2_glock_holder_wait
+ * @word: unused
+ *
+ * This function and gfs2_glock_demote_wait both show up in the WCHAN
+ * field. Thus I've separated these otherwise identical functions in
+ * order to be more informative to the user.
+ */
+
+static int gfs2_glock_holder_wait(void *word)
 {
         schedule();
         return 0;
 }
 
+static int gfs2_glock_demote_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
 static void wait_on_holder(struct gfs2_holder *gh)
 {
 	might_sleep();
-	wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
 }
 
 static void wait_on_demote(struct gfs2_glock *gl)
 {
 	might_sleep();
-	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
 }
 
 /**
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 65f438e..0060e95 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -12,6 +12,7 @@
 
 #include <linux/fs.h>
 #include <linux/workqueue.h>
+#include <linux/slow-work.h>
 #include <linux/dlm.h>
 #include <linux/buffer_head.h>
 
@@ -376,11 +377,11 @@ struct gfs2_journal_extent {
 struct gfs2_jdesc {
 	struct list_head jd_list;
 	struct list_head extent_list;
-
+	struct slow_work jd_work;
 	struct inode *jd_inode;
+	unsigned long jd_flags;
+#define JDF_RECOVERY 1
 	unsigned int jd_jid;
-	int jd_dirty;
-
 	unsigned int jd_blocks;
 };
 
@@ -390,9 +391,6 @@ struct gfs2_statfs_change_host {
 	s64 sc_dinodes;
 };
 
-#define GFS2_GLOCKD_DEFAULT	1
-#define GFS2_GLOCKD_MAX		16
-
 #define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
 #define GFS2_QUOTA_OFF		0
 #define GFS2_QUOTA_ACCOUNT	1
@@ -427,7 +425,6 @@ struct gfs2_tune {
 	unsigned int gt_incore_log_blocks;
 	unsigned int gt_log_flush_secs;
 
-	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
 
 	unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
@@ -448,6 +445,7 @@ enum {
 	SDF_JOURNAL_LIVE	= 1,
 	SDF_SHUTDOWN		= 2,
 	SDF_NOBARRIERS		= 3,
+	SDF_NORECOVERY		= 4,
 };
 
 #define GFS2_FSNAME_LEN		256
@@ -494,7 +492,6 @@ struct lm_lockstruct {
 	unsigned long ls_flags;
 	dlm_lockspace_t *ls_dlm;
 
-	int ls_recover_jid;
 	int ls_recover_jid_done;
 	int ls_recover_jid_status;
 };
@@ -583,7 +580,6 @@ struct gfs2_sbd {
 
 	/* Daemon stuff */
 
-	struct task_struct *sd_recoverd_process;
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;
 
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index a6892ed..eacd78a 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/gfs2_ondisk.h>
 #include <asm/atomic.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -113,12 +114,18 @@ static int __init init_gfs2_fs(void)
 	if (error)
 		goto fail_unregister;
 
+	error = slow_work_register_user();
+	if (error)
+		goto fail_slow;
+
 	gfs2_register_debugfs();
 
 	printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
 
 	return 0;
 
+fail_slow:
+	unregister_filesystem(&gfs2meta_fs_type);
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
 fail:
@@ -156,6 +163,7 @@ static void __exit exit_gfs2_fs(void)
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
+	slow_work_unregister_user();
 
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 7981fbc..2cd1164 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -17,6 +17,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -55,7 +56,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 	spin_lock_init(&gt->gt_spin);
 
 	gt->gt_incore_log_blocks = 1024;
-	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quota_simul_sync = 64;
 	gt->gt_quota_warn_period = 10;
@@ -675,6 +675,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 			break;
 
 		INIT_LIST_HEAD(&jd->extent_list);
+		slow_work_init(&jd->jd_work, &gfs2_recover_ops);
 		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
 		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
 			if (!jd->jd_inode)
@@ -700,14 +701,13 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
 	struct inode *master = sdp->sd_master_dir->d_inode;
 	struct gfs2_holder ji_gh;
-	struct task_struct *p;
 	struct gfs2_inode *ip;
 	int jindex = 1;
 	int error = 0;
 
 	if (undo) {
 		jindex = 0;
-		goto fail_recoverd;
+		goto fail_jinode_gh;
 	}
 
 	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
@@ -800,18 +800,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 	gfs2_glock_dq_uninit(&ji_gh);
 	jindex = 0;
 
-	p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start recoverd thread: %d\n", error);
-		goto fail_jinode_gh;
-	}
-	sdp->sd_recoverd_process = p;
-
 	return 0;
 
-fail_recoverd:
-	kthread_stop(sdp->sd_recoverd_process);
 fail_jinode_gh:
 	if (!sdp->sd_args.ar_spectator)
 		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
@@ -1172,8 +1162,10 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 	}
 
-	if (sdp->sd_args.ar_spectator)
+	if (sdp->sd_args.ar_spectator) {
                 sb->s_flags |= MS_RDONLY;
+		set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	}
 	if (sdp->sd_args.ar_posix_acl)
 		sb->s_flags |= MS_POSIXACL;
 
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index 0677a83..a3c2272 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -121,6 +121,12 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	return error;
 }
 
+static int gfs2_umount_recovery_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
 /**
  * gfs2_put_super - Unmount the filesystem
  * @sb: The VFS superblock
@@ -131,6 +137,7 @@ static void gfs2_put_super(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int error;
+	struct gfs2_jdesc *jd;
 
 	/*  Unfreeze the filesystem, if we need to  */
 
@@ -139,9 +146,25 @@ static void gfs2_put_super(struct super_block *sb)
 		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
 	mutex_unlock(&sdp->sd_freeze_lock);
 
+	/* No more recovery requests */
+	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	smp_mb();
+
+	/* Wait on outstanding recovery */
+restart:
+	spin_lock(&sdp->sd_jindex_spin);
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
+			continue;
+		spin_unlock(&sdp->sd_jindex_spin);
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
+			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
+		goto restart;
+	}
+	spin_unlock(&sdp->sd_jindex_spin);
+
 	kthread_stop(sdp->sd_quotad_process);
 	kthread_stop(sdp->sd_logd_process);
-	kthread_stop(sdp->sd_recoverd_process);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		error = gfs2_make_fs_ro(sdp);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 247e8f7..59d2695 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -13,8 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -441,18 +440,25 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
         kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
 }
 
-/**
- * gfs2_recover_journal - recover a given journal
- * @jd: the struct gfs2_jdesc describing the journal
- *
- * Acquire the journal's lock, check to see if the journal is clean, and
- * do recovery if necessary.
- *
- * Returns: errno
- */
+static int gfs2_recover_get_ref(struct slow_work *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+		return -EBUSY;
+	return 0;
+}
 
-int gfs2_recover_journal(struct gfs2_jdesc *jd)
+static void gfs2_recover_put_ref(struct slow_work *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	clear_bit(JDF_RECOVERY, &jd->jd_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
+}
+
+static void gfs2_recover_work(struct slow_work *work)
 {
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
 	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 	struct gfs2_log_header_host head;
@@ -569,7 +575,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 		gfs2_glock_dq_uninit(&j_gh);
 
 	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
-	return 0;
+	return;
 
 fail_gunlock_tr:
 	gfs2_glock_dq_uninit(&t_gh);
@@ -584,70 +590,28 @@ fail_gunlock_j:
 
 fail:
 	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
-	return error;
 }
 
-static struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp)
-{
-	struct gfs2_jdesc *jd;
-	int found = 0;
-
-	spin_lock(&sdp->sd_jindex_spin);
+struct slow_work_ops gfs2_recover_ops = {
+	.get_ref = gfs2_recover_get_ref,
+	.put_ref = gfs2_recover_put_ref,
+	.execute = gfs2_recover_work,
+};
 
-	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
-		if (jd->jd_dirty) {
-			jd->jd_dirty = 0;
-			found = 1;
-			break;
-		}
-	}
-	spin_unlock(&sdp->sd_jindex_spin);
-
-	if (!found)
-		jd = NULL;
 
-	return jd;
-}
-
-/**
- * gfs2_check_journals - Recover any dirty journals
- * @sdp: the filesystem
- *
- */
-
-static void gfs2_check_journals(struct gfs2_sbd *sdp)
+static int gfs2_recovery_wait(void *word)
 {
-	struct gfs2_jdesc *jd;
-
-	for (;;) {
-		jd = gfs2_jdesc_find_dirty(sdp);
-		if (!jd)
-			break;
-
-		if (jd != sdp->sd_jdesc)
-			gfs2_recover_journal(jd);
-	}
+	schedule();
+	return 0;
 }
 
-/**
- * gfs2_recoverd - Recover dead machine's journals
- * @sdp: Pointer to GFS2 superblock
- *
- */
-
-int gfs2_recoverd(void *data)
+int gfs2_recover_journal(struct gfs2_jdesc *jd)
 {
-	struct gfs2_sbd *sdp = data;
-	unsigned long t;
-
-	while (!kthread_should_stop()) {
-		gfs2_check_journals(sdp);
-		t = gfs2_tune_get(sdp,  gt_recoverd_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
+	int rv;
+	rv = slow_work_enqueue(&jd->jd_work);
+	if (rv)
+		return rv;
+	wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE);
 	return 0;
 }
 
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index a8218ea..1616ac2 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -28,7 +28,7 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp);
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 		    struct gfs2_log_header_host *head);
 extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd);
-extern int gfs2_recoverd(void *data);
+extern struct slow_work_ops gfs2_recover_ops;
 
 #endif /* __RECOVERY_DOT_H__ */
 
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 894bf77..9f6d48b 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -356,34 +356,33 @@ static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
 	return sprintf(buf, "%d\n", ls->ls_first_done);
 }
 
-static ssize_t recover_show(struct gfs2_sbd *sdp, char *buf)
-{
-	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	return sprintf(buf, "%d\n", ls->ls_recover_jid);
-}
-
-static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid)
+static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 {
+	unsigned jid;
 	struct gfs2_jdesc *jd;
+	int rv;
+
+	rv = sscanf(buf, "%u", &jid);
+	if (rv != 1)
+		return -EINVAL;
 
+	rv = -ESHUTDOWN;
 	spin_lock(&sdp->sd_jindex_spin);
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+		goto out;
+	rv = -EBUSY;
+	if (sdp->sd_jdesc->jd_jid == jid)
+		goto out;
+	rv = -ENOENT;
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		if (jd->jd_jid != jid)
 			continue;
-		jd->jd_dirty = 1;
+		rv = slow_work_enqueue(&jd->jd_work);
 		break;
 	}
+out:
 	spin_unlock(&sdp->sd_jindex_spin);
-}
-
-static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
-{
-	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	ls->ls_recover_jid = simple_strtol(buf, NULL, 0);
-	gfs2_jdesc_make_dirty(sdp, ls->ls_recover_jid);
-	if (sdp->sd_recoverd_process)
-		wake_up_process(sdp->sd_recoverd_process);
-	return len;
+	return rv ? rv : len;
 }
 
 static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf)
@@ -401,15 +400,15 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
 #define GDLM_ATTR(_name,_mode,_show,_store) \
 static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-GDLM_ATTR(proto_name,     0444, proto_name_show,     NULL);
-GDLM_ATTR(block,          0644, block_show,          block_store);
-GDLM_ATTR(withdraw,       0644, withdraw_show,       withdraw_store);
-GDLM_ATTR(id,             0444, lkid_show,           NULL);
-GDLM_ATTR(first,          0444, lkfirst_show,        NULL);
-GDLM_ATTR(first_done,     0444, first_done_show,     NULL);
-GDLM_ATTR(recover,        0644, recover_show,        recover_store);
-GDLM_ATTR(recover_done,   0444, recover_done_show,   NULL);
-GDLM_ATTR(recover_status, 0444, recover_status_show, NULL);
+GDLM_ATTR(proto_name,     0444, proto_name_show,	NULL);
+GDLM_ATTR(block,          0644, block_show,		block_store);
+GDLM_ATTR(withdraw,       0644, withdraw_show,		withdraw_store);
+GDLM_ATTR(id,             0444, lkid_show,		NULL);
+GDLM_ATTR(first,          0444, lkfirst_show,		NULL);
+GDLM_ATTR(first_done,     0444, first_done_show,	NULL);
+GDLM_ATTR(recover,        0200, NULL,			recover_store);
+GDLM_ATTR(recover_done,   0444, recover_done_show,	NULL);
+GDLM_ATTR(recover_status, 0444, recover_status_show,	NULL);
 
 static struct attribute *lock_module_attrs[] = {
 	&gdlm_attr_proto_name.attr,
-- 
1.6.0.6

[Cluster-devel] [PATCH 09/24] GFS2: Update docs

[Steven Whitehouse]

Update a few things which were out of date, and fix a typo.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
index 4dae9a3..0494f78 100644
--- a/Documentation/filesystems/gfs2-glocks.txt
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -60,7 +60,7 @@ go_lock          | Called for the first local holder of a lock
 go_unlock        | Called on the final local unlock of a lock
 go_dump          | Called to print content of object for debugfs file, or on
                  | error to dump glock to the log.
-go_type;         | The type of the glock, LM_TYPE_.....
+go_type          | The type of the glock, LM_TYPE_.....
 go_min_hold_time | The minimum hold time
 
 The minimum hold time for each lock is the time after a remote lock
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 593004b..5e3ab8f 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -11,18 +11,15 @@ their I/O so file system consistency is maintained.  One of the nifty
 features of GFS is perfect consistency -- changes made to the file system
 on one machine show up immediately on all other machines in the cluster.
 
-GFS uses interchangable inter-node locking mechanisms.  Different lock
-modules can plug into GFS and each file system selects the appropriate
-lock module at mount time.  Lock modules include:
+GFS uses interchangable inter-node locking mechanisms, the currently
+supported mechanisms are:
 
   lock_nolock -- allows gfs to be used as a local file system
 
   lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
   The dlm is found at linux/fs/dlm/
 
-In addition to interfacing with an external locking manager, a gfs lock
-module is responsible for interacting with external cluster management
-systems.  Lock_dlm depends on user space cluster management systems found
+Lock_dlm depends on user space cluster management systems found
 at the URL above.
 
 To use gfs as a local file system, no external clustering systems are
@@ -31,13 +28,19 @@ needed, simply:
   $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
   $ mount -t gfs2 /dev/block_device /dir
 
-GFS2 is not on-disk compatible with previous versions of GFS.
+If you are using Fedora, you need to install the gfs2-utils package
+and, for lock_dlm, you will also need to install the cman package
+and write a cluster.conf as per the documentation.
+
+GFS2 is not on-disk compatible with previous versions of GFS, but it
+is pretty close.
 
 The following man pages can be found at the URL above:
-  gfs2_fsck	to repair a filesystem
+  fsck.gfs2	to repair a filesystem
   gfs2_grow	to expand a filesystem online
   gfs2_jadd	to add journals to a filesystem online
   gfs2_tool	to manipulate, examine and tune a filesystem
   gfs2_quota	to examine and change quota values in a filesystem
+  gfs2_convert	to convert a gfs filesystem to gfs2 in-place
   mount.gfs2	to help mount(8) mount a filesystem
   mkfs.gfs2	to make a filesystem
-- 
1.6.0.6

[Cluster-devel] [PATCH 10/24] GFS2: Don't warn when delete inode fails on ro filesystem

[Steven Whitehouse]

If the filesystem is read-only, then we expect that delete inode
will fail, so there is no need to warn about it.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index a3c2272..2fd1dcb 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -714,7 +714,7 @@ out_unlock:
 		gfs2_glock_dq(&ip->i_iopen_gh);
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
-	if (error && error != GLR_TRYFAILED)
+	if (error && error != GLR_TRYFAILED && error != -EROFS)
 		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
 out:
 	truncate_inode_pages(&inode->i_data, 0);
-- 
1.6.0.6

[Cluster-devel] [PATCH 11/24] GFS2: Improve resource group error handling

[Steven Whitehouse]

This patch improves the error handling in the case where we
discover that the summary information in the resource group
doesn't match the bitmap information while in the process of
allocating blocks. Originally this resulted in a kernel bug,
but this patch changes that so that we return -EIO and print
some messages explaining what went wrong, and how to fix it.

We also remember locally not to try and allocate from the
same rgrp again, so that a subsequent allocation in a
different rgrp should succeed.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 3a5d3f8..253e1a3 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -136,7 +136,9 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
 		   and write it out to disk */
 
 		unsigned int n = 1;
-		block = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &block, &n);
+		if (error)
+			goto out_brelse;
 		if (isdir) {
 			gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
 			error = gfs2_dir_get_new_buffer(ip, block, &bh);
@@ -476,8 +478,11 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 	blks = dblks + iblks;
 	i = sheight;
 	do {
+		int error;
 		n = blks - alloced;
-		bn = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &bn, &n);
+		if (error)
+			return error;
 		alloced += n;
 		if (state != ALLOC_DATA || gfs2_is_jdata(ip))
 			gfs2_trans_add_unrevoke(sdp, bn, n);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index aef4d0c..297d7e5 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -803,13 +803,20 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	unsigned int n = 1;
-	u64 bn = gfs2_alloc_block(ip, &n);
-	struct buffer_head *bh = gfs2_meta_new(ip->i_gl, bn);
+	u64 bn;
+	int error;
+	struct buffer_head *bh;
 	struct gfs2_leaf *leaf;
 	struct gfs2_dirent *dent;
 	struct qstr name = { .name = "", .len = 0, .hash = 0 };
+
+	error = gfs2_alloc_block(ip, &bn, &n);
+	if (error)
+		return NULL;
+	bh = gfs2_meta_new(ip->i_gl, bn);
 	if (!bh)
 		return NULL;
+
 	gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
 	gfs2_trans_add_bh(ip->i_gl, bh, 1);
 	gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c
index 899763a..07ea952 100644
--- a/fs/gfs2/eattr.c
+++ b/fs/gfs2/eattr.c
@@ -582,8 +582,11 @@ static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp)
 	struct gfs2_ea_header *ea;
 	unsigned int n = 1;
 	u64 block;
+	int error;
 
-	block = gfs2_alloc_block(ip, &n);
+	error = gfs2_alloc_block(ip, &block, &n);
+	if (error)
+		return error;
 	gfs2_trans_add_unrevoke(sdp, block, 1);
 	*bhp = gfs2_meta_new(ip->i_gl, block);
 	gfs2_trans_add_bh(ip->i_gl, *bhp, 1);
@@ -617,6 +620,7 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 		    struct gfs2_ea_request *er)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int error;
 
 	ea->ea_data_len = cpu_to_be32(er->er_data_len);
 	ea->ea_name_len = er->er_name_len;
@@ -642,7 +646,9 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 			int mh_size = sizeof(struct gfs2_meta_header);
 			unsigned int n = 1;
 
-			block = gfs2_alloc_block(ip, &n);
+			error = gfs2_alloc_block(ip, &block, &n);
+			if (error)
+				return error;
 			gfs2_trans_add_unrevoke(sdp, block, 1);
 			bh = gfs2_meta_new(ip->i_gl, block);
 			gfs2_trans_add_bh(ip->i_gl, bh, 1);
@@ -963,7 +969,9 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 	} else {
 		u64 blk;
 		unsigned int n = 1;
-		blk = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &blk, &n);
+		if (error)
+			return error;
 		gfs2_trans_add_unrevoke(sdp, blk, 1);
 		indbh = gfs2_meta_new(ip->i_gl, blk);
 		gfs2_trans_add_bh(ip->i_gl, indbh, 1);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 70f87f4..d5e4ab1 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -310,24 +310,6 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
 }
 
 /**
- * rgrp_go_dump - print out an rgrp
- * @seq: The iterator
- * @gl: The glock in question
- *
- */
-
-static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
-{
-	const struct gfs2_rgrpd *rgd = gl->gl_object;
-	if (rgd == NULL)
-		return 0;
-	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
-		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
-		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
-	return 0;
-}
-
-/**
  * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
  * @state: the requested state
@@ -410,7 +392,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_demote_ok = rgrp_go_demote_ok,
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
-	.go_dump = rgrp_go_dump,
+	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
 	.go_min_hold_time = HZ / 5,
 };
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 0060e95..de50d86 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -92,9 +92,10 @@ struct gfs2_rgrpd {
 	unsigned int rd_bh_count;
 	u32 rd_last_alloc;
 	unsigned char rd_flags;
-#define GFS2_RDF_CHECK        0x01      /* Need to check for unlinked inodes */
-#define GFS2_RDF_NOALLOC      0x02      /* rg prohibits allocation */
-#define GFS2_RDF_UPTODATE     0x04      /* rg is up to date */
+#define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
+#define GFS2_RDF_UPTODATE	0x20000000 /* rg is up to date */
+#define GFS2_RDF_ERROR		0x40000000 /* error in rg */
+#define GFS2_RDF_MASK		0xf0000000 /* mask for internal flags */
 };
 
 enum gfs2_state_bits {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 5650382..fbacf09 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -701,10 +701,7 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 	u32 rg_flags;
 
 	rg_flags = be32_to_cpu(str->rg_flags);
-	if (rg_flags & GFS2_RGF_NOALLOC)
-		rgd->rd_flags |= GFS2_RDF_NOALLOC;
-	else
-		rgd->rd_flags &= ~GFS2_RDF_NOALLOC;
+	rg_flags &= ~GFS2_RDF_MASK;
 	rgd->rd_free = be32_to_cpu(str->rg_free);
 	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
 	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
@@ -713,11 +710,8 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 {
 	struct gfs2_rgrp *str = buf;
-	u32 rg_flags = 0;
 
-	if (rgd->rd_flags & GFS2_RDF_NOALLOC)
-		rg_flags |= GFS2_RGF_NOALLOC;
-	str->rg_flags = cpu_to_be32(rg_flags);
+	str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
 	str->rg_free = cpu_to_be32(rgd->rd_free);
 	str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
 	str->__pad = cpu_to_be32(0);
@@ -942,7 +936,7 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
 	int ret = 0;
 
-	if (rgd->rd_flags & GFS2_RDF_NOALLOC)
+	if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
 		return 0;
 
 	spin_lock(&sdp->sd_rindex_spin);
@@ -1435,13 +1429,33 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
 }
 
 /**
- * gfs2_alloc_block - Allocate a block
+ * gfs2_rgrp_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_rgrpd *rgd = gl->gl_object;
+	if (rgd == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
+		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
+		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
+	return 0;
+}
+
+/**
+ * gfs2_alloc_block - Allocate one or more blocks
  * @ip: the inode to allocate the block for
+ * @bn: Used to return the starting block number
+ * @n: requested number of blocks/extent length (value/result)
  *
- * Returns: the allocated block
+ * Returns: 0 or error
  */
 
-u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
+int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct buffer_head *dibh;
@@ -1457,7 +1471,10 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 		goal = rgd->rd_last_alloc;
 
 	blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n);
-	BUG_ON(blk == BFITNOENT);
+
+	/* Since all blocks are reserved in advance, this shouldn't happen */
+	if (blk == BFITNOENT)
+		goto rgrp_error;
 
 	rgd->rd_last_alloc = blk;
 	block = rgd->rd_data0 + blk;
@@ -1469,7 +1486,9 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 		di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal);
 		brelse(dibh);
 	}
-	gfs2_assert_withdraw(sdp, rgd->rd_free >= *n);
+	if (rgd->rd_free < *n)
+		goto rgrp_error;
+
 	rgd->rd_free -= *n;
 
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
@@ -1484,7 +1503,16 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 	rgd->rd_free_clone -= *n;
 	spin_unlock(&sdp->sd_rindex_spin);
 
-	return block;
+	*bn = block;
+	return 0;
+
+rgrp_error:
+	fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
+	        (unsigned long long)rgd->rd_addr);
+	fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
+	gfs2_rgrp_dump(NULL, rgd->rd_gl);
+	rgd->rd_flags |= GFS2_RDF_ERROR;
+	return -EIO;
 }
 
 /**
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 3181c7e..1e76ff0 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -14,22 +14,22 @@ struct gfs2_rgrpd;
 struct gfs2_sbd;
 struct gfs2_holder;
 
-void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
 
 struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
 struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
 struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
 
-void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
-int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
+extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
+extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
 
-int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
-void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
-void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
+extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
 
-void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
 
-struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
+extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
 static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 {
 	BUG_ON(ip->i_alloc == NULL);
@@ -37,22 +37,22 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 	ip->i_alloc = NULL;
 }
 
-int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
-			 char *file, unsigned int line);
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file,
+				  unsigned int line);
 #define gfs2_inplace_reserve(ip) \
 gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
 
-void gfs2_inplace_release(struct gfs2_inode *ip);
+extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
-unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
+extern unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
 
-u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n);
-u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
+extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
+extern u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
 
-void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
-void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
-void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
-void gfs2_unlink_di(struct inode *inode);
+extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
+extern void gfs2_unlink_di(struct inode *inode);
 
 struct gfs2_rgrp_list {
 	unsigned int rl_rgrps;
@@ -61,10 +61,11 @@ struct gfs2_rgrp_list {
 	struct gfs2_holder *rl_ghs;
 };
 
-void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
-		    u64 block);
-void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
-void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
-u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+			   u64 block);
+extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
+extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
+extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
 
 #endif /* __RGRP_DOT_H__ */
-- 
1.6.0.6

[Cluster-devel] [PATCH 12/24] GFS2: Add a rgrp bitmap full flag

[Steven Whitehouse]

During block allocation, it is useful to know if sections of disk
are full on a finer grained basis than a single resource group.
This can make a performance difference when resource groups have
larger numbers of bitmap blocks, since we no longer have to search
them all block by block in each individual bitmap.

The full flag is set on a per-bitmap basis when it has been
searched and found to have no free space. It is then skipped in
subsequent searches until the flag is reset. The resetting
occurs if we have to drop the glock on the resource group for any
reason, or if we deallocate some blocks within that resource
group and thus free up some space.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index de50d86..dd87379 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -64,9 +64,12 @@ struct gfs2_log_element {
 	const struct gfs2_log_operations *le_ops;
 };
 
+#define GBF_FULL 1
+
 struct gfs2_bitmap {
 	struct buffer_head *bi_bh;
 	char *bi_clone;
+	unsigned long bi_flags;
 	u32 bi_offset;
 	u32 bi_start;
 	u32 bi_len;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index fbacf09..23637b9 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -442,6 +442,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd)
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
 
+		bi->bi_flags = 0;
 		/* small rgrp; bitmap stored completely in header block */
 		if (length == 1) {
 			bytes = bytes_left;
@@ -769,6 +770,8 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 	}
 
 	if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
+		for (x = 0; x < length; x++)
+			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
 		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
 		rgd->rd_flags |= GFS2_RDF_UPTODATE;
 	}
@@ -897,6 +900,7 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
 			continue;
 		if (sdp->sd_args.ar_discard)
 			gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi);
+		clear_bit(GBF_FULL, &bi->bi_flags);
 		memcpy(bi->bi_clone + bi->bi_offset,
 		       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
 	}
@@ -1309,30 +1313,37 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 {
 	struct gfs2_bitmap *bi = NULL;
 	const u32 length = rgd->rd_length;
-	u32 blk = 0;
+	u32 blk = BFITNOENT;
 	unsigned int buf, x;
 	const unsigned int elen = *n;
-	const u8 *buffer;
+	const u8 *buffer = NULL;
 
 	*n = 0;
 	/* Find bitmap block that contains bits for goal block */
 	for (buf = 0; buf < length; buf++) {
 		bi = rgd->rd_bits + buf;
-		if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY)
-			break;
+		/* Convert scope of "goal" from rgrp-wide to within found bit block */
+		if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) {
+			goal -= bi->bi_start * GFS2_NBBY;
+			goto do_search;
+		}
 	}
+	buf = 0;
+	goal = 0;
 
-	gfs2_assert(rgd->rd_sbd, buf < length);
-
-	/* Convert scope of "goal" from rgrp-wide to within found bit block */
-	goal -= bi->bi_start * GFS2_NBBY;
-
+do_search:
 	/* Search (up to entire) bitmap in this rgrp for allocatable block.
 	   "x <= length", instead of "x < length", because we typically start
 	   the search in the middle of a bit block, but if we can't find an
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
+		bi = rgd->rd_bits + buf;
+
+		if (test_bit(GBF_FULL, &bi->bi_flags) &&
+		    (old_state == GFS2_BLKST_FREE))
+			goto skip;
+
 		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
 		   bitmaps, so we must search the originals for that. */
 		buffer = bi->bi_bh->b_data + bi->bi_offset;
@@ -1343,33 +1354,39 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 		if (blk != BFITNOENT)
 			break;
 
+		if ((goal == 0) && (old_state == GFS2_BLKST_FREE))
+			set_bit(GBF_FULL, &bi->bi_flags);
+
 		/* Try next bitmap block (wrap back to rgrp header if at end) */
-		buf = (buf + 1) % length;
-		bi = rgd->rd_bits + buf;
+skip:
+		buf++;
+		buf %= length;
 		goal = 0;
 	}
 
-	if (blk != BFITNOENT && old_state != new_state) {
-		*n = 1;
-		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+	if (blk == BFITNOENT)
+		return blk;
+	*n = 1;
+	if (old_state == new_state)
+		goto out;
+
+	gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+	gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+		    bi->bi_len, blk, new_state);
+	goal = blk;
+	while (*n < elen) {
+		goal++;
+		if (goal >= (bi->bi_len * GFS2_NBBY))
+			break;
+		if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
+		    GFS2_BLKST_FREE)
+			break;
 		gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
-			    bi->bi_len, blk, new_state);
-		goal = blk;
-		while (*n < elen) {
-			goal++;
-			if (goal >= (bi->bi_len * GFS2_NBBY))
-				break;
-			if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
-			    GFS2_BLKST_FREE)
-				break;
-			gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone,
-				    bi->bi_offset, bi->bi_len, goal,
-				    new_state);
-			(*n)++;
-		}
+			    bi->bi_len, goal, new_state);
+		(*n)++;
 	}
-
-	return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk;
+out:
+	return (bi->bi_start * GFS2_NBBY) + blk;
 }
 
 /**
-- 
1.6.0.6

[Cluster-devel] [PATCH 13/24] GFS2: Be more aggressive in reclaiming unlinked inodes

[Steven Whitehouse]

This patch increases the frequency with which gfs2 looks
for unlinked, but still allocated inodes. Its the equivalent
operation to ext3's orphan list, but done with bitmaps in
the resource groups.

This also fixes a bug where a field in the rgrp was too small.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index dd87379..225347f 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -94,7 +94,7 @@ struct gfs2_rgrpd {
 	struct gfs2_sbd *rd_sbd;
 	unsigned int rd_bh_count;
 	u32 rd_last_alloc;
-	unsigned char rd_flags;
+	u32 rd_flags;
 #define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
 #define GFS2_RDF_UPTODATE	0x20000000 /* rg is up to date */
 #define GFS2_RDF_ERROR		0x40000000 /* error in rg */
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 23637b9..ee3d5c1 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -581,7 +581,6 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 
 	rgd->rd_gl->gl_object = rgd;
 	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
-	rgd->rd_flags |= GFS2_RDF_CHECK;
 	return error;
 }
 
@@ -703,6 +702,8 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 
 	rg_flags = be32_to_cpu(str->rg_flags);
 	rg_flags &= ~GFS2_RDF_MASK;
+	rgd->rd_flags &= GFS2_RDF_MASK;
+	rgd->rd_flags |= rg_flags;
 	rgd->rd_free = be32_to_cpu(str->rg_free);
 	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
 	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
@@ -773,7 +774,7 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 		for (x = 0; x < length; x++)
 			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
 		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
-		rgd->rd_flags |= GFS2_RDF_UPTODATE;
+		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
 	}
 
 	spin_lock(&sdp->sd_rindex_spin);
-- 
1.6.0.6

[Cluster-devel] [PATCH 14/24] GFS2: Clean up some file names

[Steven Whitehouse]

This patch renames the ops_*.c files which have no counterpart
without the ops_ prefix in order to shorten the name and make
it more readable. In addition, ops_address.h (which was very
small) is moved into inode.h and inode.h is cleaned up by
adding extern where required.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index a851ea4..4f7332c 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,7 +1,7 @@
 obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
 	glops.o inode.o log.o lops.o main.o meta_io.o \
-	mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
+	mount.o aops.o dentry.o export.o file.o \
 	ops_fstype.o ops_inode.o ops_super.o quota.o \
 	recovery.o rgrp.o super.o sys.o trans.o util.o
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
new file mode 100644
index 0000000..03ebb43
--- /dev/null
+++ b/fs/gfs2/aops.c
@@ -0,0 +1,1145 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/fs.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/backing-dev.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "trans.h"
+#include "rgrp.h"
+#include "super.h"
+#include "util.h"
+#include "glops.h"
+
+
+static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to)
+{
+	struct buffer_head *head = page_buffers(page);
+	unsigned int bsize = head->b_size;
+	struct buffer_head *bh;
+	unsigned int start, end;
+
+	for (bh = head, start = 0; bh != head || !start;
+	     bh = bh->b_this_page, start = end) {
+		end = start + bsize;
+		if (end <= from || start >= to)
+			continue;
+		if (gfs2_is_jdata(ip))
+			set_buffer_uptodate(bh);
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+	}
+}
+
+/**
+ * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
+				  struct buffer_head *bh_result, int create)
+{
+	int error;
+
+	error = gfs2_block_map(inode, lblock, bh_result, 0);
+	if (error)
+		return error;
+	if (!buffer_mapped(bh_result))
+		return -EIO;
+	return 0;
+}
+
+static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
+				 struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, bh_result, 0);
+}
+
+/**
+ * gfs2_writepage_common - Common bits of writepage
+ * @page: The page to be written
+ * @wbc: The writeback control
+ *
+ * Returns: 1 if writepage is ok, otherwise an error code or zero if no error.
+ */
+
+static int gfs2_writepage_common(struct page *page,
+				 struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
+		goto out;
+	if (current->journal_info)
+		goto redirty;
+	/* Is the page fully outside i_size? (truncate in progress) */
+	offset = i_size & (PAGE_CACHE_SIZE-1);
+	if (page->index > end_index || (page->index == end_index && !offset)) {
+		page->mapping->a_ops->invalidatepage(page, 0);
+		goto out;
+	}
+	return 1;
+redirty:
+	redirty_page_for_writepage(wbc, page);
+out:
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writeback_writepage - Write page for writeback mappings
+ * @page: The page
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_writeback_writepage(struct page *page,
+				    struct writeback_control *wbc)
+{
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
+	if (ret == -EAGAIN)
+		ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	return ret;
+}
+
+/**
+ * gfs2_ordered_writepage - Write page for ordered data files
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_ordered_writepage(struct page *page,
+				  struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	if (!page_has_buffers(page)) {
+		create_empty_buffers(page, inode->i_sb->s_blocksize,
+				     (1 << BH_Dirty)|(1 << BH_Uptodate));
+	}
+	gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1);
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * __gfs2_jdata_writepage - The core of jdata writepage
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ * This is shared between writepage and writepages and implements the
+ * core of the writepage operation. If a transaction is required then
+ * PageChecked will have been set and the transaction will have
+ * already been started before this is called.
+ */
+
+static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	if (PageChecked(page)) {
+		ClearPageChecked(page);
+		if (!page_has_buffers(page)) {
+			create_empty_buffers(page, inode->i_sb->s_blocksize,
+					     (1 << BH_Dirty)|(1 << BH_Uptodate));
+		}
+		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
+	}
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * gfs2_jdata_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ */
+
+static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int ret;
+	int done_trans = 0;
+
+	if (PageChecked(page)) {
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			goto out_ignore;
+		ret = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+		if (ret)
+			goto out_ignore;
+		done_trans = 1;
+	}
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret > 0)
+		ret = __gfs2_jdata_writepage(page, wbc);
+	if (done_trans)
+		gfs2_trans_end(sdp);
+	return ret;
+
+out_ignore:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: Write-back control
+ *
+ * For the data=writeback case we can already ignore buffer heads
+ * and write whole extents at once. This is a big reduction in the
+ * number of I/O requests we send and the bmap calls we make in this case.
+ */
+static int gfs2_writeback_writepages(struct address_space *mapping,
+				     struct writeback_control *wbc)
+{
+	return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+}
+
+/**
+ * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages
+ * @mapping: The mapping
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call for each page
+ * @pvec: The vector of pages
+ * @nr_pages: The number of pages to write
+ *
+ * Returns: non-zero if loop should terminate, zero otherwise
+ */
+
+static int gfs2_write_jdata_pagevec(struct address_space *mapping,
+				    struct writeback_control *wbc,
+				    struct pagevec *pvec,
+				    int nr_pages, pgoff_t end)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
+	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int i;
+	int ret;
+
+	ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
+	if (ret < 0)
+		return ret;
+
+	for(i = 0; i < nr_pages; i++) {
+		struct page *page = pvec->pages[i];
+
+		lock_page(page);
+
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			continue;
+		}
+
+		if (!wbc->range_cyclic && page->index > end) {
+			ret = 1;
+			unlock_page(page);
+			continue;
+		}
+
+		if (wbc->sync_mode != WB_SYNC_NONE)
+			wait_on_page_writeback(page);
+
+		if (PageWriteback(page) ||
+		    !clear_page_dirty_for_io(page)) {
+			unlock_page(page);
+			continue;
+		}
+
+		/* Is the page fully outside i_size? (truncate in progress) */
+		if (page->index > end_index || (page->index == end_index && !offset)) {
+			page->mapping->a_ops->invalidatepage(page, 0);
+			unlock_page(page);
+			continue;
+		}
+
+		ret = __gfs2_jdata_writepage(page, wbc);
+
+		if (ret || (--(wbc->nr_to_write) <= 0))
+			ret = 1;
+		if (wbc->nonblocking && bdi_write_congested(bdi)) {
+			wbc->encountered_congestion = 1;
+			ret = 1;
+		}
+
+	}
+	gfs2_trans_end(sdp);
+	return ret;
+}
+
+/**
+ * gfs2_write_cache_jdata - Like write_cache_pages but different
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call
+ * @data: The data to pass to writepage
+ *
+ * The reason that we use our own function here is that we need to
+ * start transactions before we grab page locks. This allows us
+ * to get the ordering right.
+ */
+
+static int gfs2_write_cache_jdata(struct address_space *mapping,
+				  struct writeback_control *wbc)
+{
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int ret = 0;
+	int done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;
+	int scanned = 0;
+	int range_whole = 0;
+
+	if (wbc->nonblocking && bdi_write_congested(bdi)) {
+		wbc->encountered_congestion = 1;
+		return 0;
+	}
+
+	pagevec_init(&pvec, 0);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* Start from prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
+		scanned = 1;
+	}
+
+retry:
+	 while (!done && (index <= end) &&
+		(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					       PAGECACHE_TAG_DIRTY,
+					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+		scanned = 1;
+		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+		if (ret)
+			done = 1;
+		if (ret > 0)
+			ret = 0;
+
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+
+	if (!scanned && !done) {
+		/*
+		 * We hit the last page and there is more work to be done: wrap
+		 * back to the start of the file
+		 */
+		scanned = 1;
+		index = 0;
+		goto retry;
+	}
+
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = index;
+	return ret;
+}
+
+
+/**
+ * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * 
+ */
+
+static int gfs2_jdata_writepages(struct address_space *mapping,
+				 struct writeback_control *wbc)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	int ret;
+
+	ret = gfs2_write_cache_jdata(mapping, wbc);
+	if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
+		gfs2_log_flush(sdp, ip->i_gl);
+		ret = gfs2_write_cache_jdata(mapping, wbc);
+	}
+	return ret;
+}
+
+/**
+ * stuffed_readpage - Fill in a Linux page with stuffed file data
+ * @ip: the inode
+ * @page: the page
+ *
+ * Returns: errno
+ */
+
+static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+{
+	struct buffer_head *dibh;
+	void *kaddr;
+	int error;
+
+	/*
+	 * Due to the order of unstuffing files and ->fault(), we can be
+	 * asked for a zero page in the case of a stuffed file being extended,
+	 * so we need to supply one here. It doesn't happen often.
+	 */
+	if (unlikely(page->index)) {
+		zero_user(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
+		return 0;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
+	       ip->i_disksize);
+	memset(kaddr + ip->i_disksize, 0, PAGE_CACHE_SIZE - ip->i_disksize);
+	kunmap_atomic(kaddr, KM_USER0);
+	flush_dcache_page(page);
+	brelse(dibh);
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+
+/**
+ * __gfs2_readpage - readpage
+ * @file: The file to read a page for
+ * @page: The page to read
+ *
+ * This is the core of gfs2's readpage. Its used by the internal file
+ * reading code as in that case we already hold the glock. Also its
+ * called by gfs2_readpage() once the required lock has been granted.
+ *
+ */
+
+static int __gfs2_readpage(void *file, struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	int error;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = stuffed_readpage(ip, page);
+		unlock_page(page);
+	} else {
+		error = mpage_readpage(page, gfs2_block_map);
+	}
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return error;
+}
+
+/**
+ * gfs2_readpage - read a page of a file
+ * @file: The file to read
+ * @page: The page of the file
+ *
+ * This deals with the locking required. We have to unlock and
+ * relock the page in order to get the locking in the right
+ * order.
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder gh;
+	int error;
+
+	unlock_page(page);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
+	if (unlikely(error))
+		goto out;
+	error = AOP_TRUNCATED_PAGE;
+	lock_page(page);
+	if (page->mapping == mapping && !PageUptodate(page))
+		error = __gfs2_readpage(file, page);
+	else
+		unlock_page(page);
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	if (error && error != AOP_TRUNCATED_PAGE)
+		lock_page(page);
+	return error;
+}
+
+/**
+ * gfs2_internal_read - read an internal file
+ * @ip: The gfs2 inode
+ * @ra_state: The readahead state (or NULL for no readahead)
+ * @buf: The buffer to fill
+ * @pos: The file position
+ * @size: The amount to read
+ *
+ */
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+                       char *buf, loff_t *pos, unsigned size)
+{
+	struct address_space *mapping = ip->i_inode.i_mapping;
+	unsigned long index = *pos / PAGE_CACHE_SIZE;
+	unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
+	unsigned copied = 0;
+	unsigned amt;
+	struct page *page;
+	void *p;
+
+	do {
+		amt = size - copied;
+		if (offset + size > PAGE_CACHE_SIZE)
+			amt = PAGE_CACHE_SIZE - offset;
+		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+		p = kmap_atomic(page, KM_USER0);
+		memcpy(buf + copied, p + offset, amt);
+		kunmap_atomic(p, KM_USER0);
+		mark_page_accessed(page);
+		page_cache_release(page);
+		copied += amt;
+		index++;
+		offset = 0;
+	} while(copied < size);
+	(*pos) += size;
+	return size;
+}
+
+/**
+ * gfs2_readpages - Read a bunch of pages at once
+ *
+ * Some notes:
+ * 1. This is only for readahead, so we can simply ignore any things
+ *    which are slightly inconvenient (such as locking conflicts between
+ *    the page lock and the glock) and return having done no I/O. Its
+ *    obviously not something we'd want to do on too regular a basis.
+ *    Any I/O we ignore@this time will be done via readpage later.
+ * 2. We don't handle stuffed files here we let readpage do the honours.
+ * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
+ */
+
+static int gfs2_readpages(struct file *file, struct address_space *mapping,
+			  struct list_head *pages, unsigned nr_pages)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (unlikely(ret))
+		goto out_uninit;
+	if (!gfs2_is_stuffed(ip))
+		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = -EIO;
+	return ret;
+}
+
+/**
+ * gfs2_write_begin - Begin to write to a file
+ * @file: The file to write to
+ * @mapping: The mapping in which to write
+ * @pos: The file offset at which to start writing
+ * @len: Length of the write
+ * @flags: Various flags
+ * @pagep: Pointer to return the page
+ * @fsdata: Pointer to return fs data (unused by GFS2)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_begin(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	int alloc_required;
+	int error = 0;
+	struct gfs2_alloc *al;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned to = from + len;
+	struct page *page;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (unlikely(error))
+		goto out_uninit;
+
+	error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
+	if (error)
+		goto out_unlock;
+
+	if (alloc_required || gfs2_is_jdata(ip))
+		gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
+
+	if (alloc_required) {
+		al = gfs2_alloc_get(ip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_unlock;
+		}
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto out_alloc_put;
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto out_qunlock;
+	}
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+
+	error = gfs2_trans_begin(sdp, rblocks,
+				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+	if (error)
+		goto out_trans_fail;
+
+	error = -ENOMEM;
+	flags |= AOP_FLAG_NOFS;
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	*pagep = page;
+	if (unlikely(!page))
+		goto out_endtrans;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = 0;
+		if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
+			error = gfs2_unstuff_dinode(ip, page);
+			if (error == 0)
+				goto prepare_write;
+		} else if (!PageUptodate(page)) {
+			error = stuffed_readpage(ip, page);
+		}
+		goto out;
+	}
+
+prepare_write:
+	error = block_prepare_write(page, from, to, gfs2_block_map);
+out:
+	if (error == 0)
+		return 0;
+
+	page_cache_release(page);
+	if (pos + len > ip->i_inode.i_size)
+		vmtruncate(&ip->i_inode, ip->i_inode.i_size);
+out_endtrans:
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	if (alloc_required) {
+		gfs2_inplace_release(ip);
+out_qunlock:
+		gfs2_quota_unlock(ip);
+out_alloc_put:
+		gfs2_alloc_put(ip);
+	}
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
+/**
+ * adjust_fs_space - Adjusts the free space available due to gfs2_grow
+ * @inode: the rindex inode
+ */
+static void adjust_fs_space(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	u64 fs_total, new_free;
+
+	/* Total up the file system space, according to the latest rindex. */
+	fs_total = gfs2_ri_total(sdp);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	if (fs_total > (m_sc->sc_total + l_sc->sc_total))
+		new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
+	else
+		new_free = 0;
+	spin_unlock(&sdp->sd_statfs_spin);
+	fs_warn(sdp, "File system extended by %llu blocks.\n",
+		(unsigned long long)new_free);
+	gfs2_statfs_change(sdp, new_free, new_free, 0);
+}
+
+/**
+ * gfs2_stuffed_write_end - Write end for stuffed files
+ * @inode: The inode
+ * @dibh: The buffer_head containing the on-disk inode
+ * @pos: The file position
+ * @len: The length of the write
+ * @copied: How much was actually copied by the VFS
+ * @page: The page
+ *
+ * This copies the data from the page into the inode block after
+ * the inode data structure itself.
+ *
+ * Returns: errno
+ */
+static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	u64 to = pos + copied;
+	void *kaddr;
+	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
+	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+
+	BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(buf + pos, kaddr + pos, copied);
+	memset(kaddr + pos + copied, 0, len - copied);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (copied) {
+		if (inode->i_size < to) {
+			i_size_write(inode, to);
+			ip->i_disksize = inode->i_size;
+		}
+		gfs2_dinode_out(ip, di);
+		mark_inode_dirty(inode);
+	}
+
+	if (inode == sdp->sd_rindex)
+		adjust_fs_space(inode);
+
+	brelse(dibh);
+	gfs2_trans_end(sdp);
+	gfs2_glock_dq(&ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return copied;
+}
+
+/**
+ * gfs2_write_end
+ * @file: The file to write to
+ * @mapping: The address space to write to
+ * @pos: The file position
+ * @len: The length of the data
+ * @copied:
+ * @page: The page that has been written
+ * @fsdata: The fsdata (unused in GFS2)
+ *
+ * The main write_end function for GFS2. We have a separate one for
+ * stuffed files as they are slightly different, otherwise we just
+ * put our locking around the VFS provided functions.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = ip->i_alloc;
+	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned int to = from + len;
+	int ret;
+
+	BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
+
+	ret = gfs2_meta_inode_buffer(ip, &dibh);
+	if (unlikely(ret)) {
+		unlock_page(page);
+		page_cache_release(page);
+		goto failed;
+	}
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip))
+		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
+
+	if (!gfs2_is_writeback(ip))
+		gfs2_page_add_databufs(ip, page, from, to);
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	if (ret > 0) {
+		if (inode->i_size > ip->i_disksize)
+			ip->i_disksize = inode->i_size;
+		gfs2_dinode_out(ip, dibh->b_data);
+		mark_inode_dirty(inode);
+	}
+
+	if (inode == sdp->sd_rindex)
+		adjust_fs_space(inode);
+
+	brelse(dibh);
+	gfs2_trans_end(sdp);
+failed:
+	if (al) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	gfs2_glock_dq(&ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return ret;
+}
+
+/**
+ * gfs2_set_page_dirty - Page dirtying function
+ * @page: The page to dirty
+ *
+ * Returns: 1 if it dirtyed the page, or 0 otherwise
+ */
+ 
+static int gfs2_set_page_dirty(struct page *page)
+{
+	SetPageChecked(page);
+	return __set_page_dirty_buffers(page);
+}
+
+/**
+ * gfs2_bmap - Block map function
+ * @mapping: Address space info
+ * @lblock: The block to map
+ *
+ * Returns: The disk address for the block or 0 on hole or error
+ */
+
+static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder i_gh;
+	sector_t dblock = 0;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return 0;
+
+	if (!gfs2_is_stuffed(ip))
+		dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return dblock;
+}
+
+static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	lock_buffer(bh);
+	gfs2_log_lock(sdp);
+	clear_buffer_dirty(bh);
+	bd = bh->b_private;
+	if (bd) {
+		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+			list_del_init(&bd->bd_le.le_list);
+		else
+			gfs2_remove_from_journal(bh, current->journal_info, 0);
+	}
+	bh->b_bdev = NULL;
+	clear_buffer_mapped(bh);
+	clear_buffer_req(bh);
+	clear_buffer_new(bh);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
+}
+
+static void gfs2_invalidatepage(struct page *page, unsigned long offset)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	struct buffer_head *bh, *head;
+	unsigned long pos = 0;
+
+	BUG_ON(!PageLocked(page));
+	if (offset == 0)
+		ClearPageChecked(page);
+	if (!page_has_buffers(page))
+		goto out;
+
+	bh = head = page_buffers(page);
+	do {
+		if (offset <= pos)
+			gfs2_discard(sdp, bh);
+		pos += bh->b_size;
+		bh = bh->b_this_page;
+	} while (bh != head);
+out:
+	if (offset == 0)
+		try_to_release_page(page, 0);
+}
+
+/**
+ * gfs2_ok_for_dio - check that dio is valid on this file
+ * @ip: The inode
+ * @rw: READ or WRITE
+ * @offset: The offset at which we are reading or writing
+ *
+ * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
+ *          1 (to accept the i/o request)
+ */
+static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
+{
+	/*
+	 * Should we return an error here? I can't see that O_DIRECT for
+	 * a stuffed file makes any sense. For now we'll silently fall
+	 * back to buffered I/O
+	 */
+	if (gfs2_is_stuffed(ip))
+		return 0;
+
+	if (offset >= i_size_read(&ip->i_inode))
+		return 0;
+	return 1;
+}
+
+
+
+static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int rv;
+
+	/*
+	 * Deferred lock, even if its a write, since we do no allocation
+	 * on this path. All we need change is atime, and this lock mode
+	 * ensures that other nodes have flushed their buffered read caches
+	 * (i.e. their page cache entries for this inode). We do not,
+	 * unfortunately have the option of only flushing a range like
+	 * the VFS does.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	rv = gfs2_glock_nq(&gh);
+	if (rv)
+		return rv;
+	rv = gfs2_ok_for_dio(ip, rw, offset);
+	if (rv != 1)
+		goto out; /* dio not valid, fall back to buffered i/o */
+
+	rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
+					   iov, offset, nr_segs,
+					   gfs2_get_block_direct, NULL);
+out:
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	return rv;
+}
+
+/**
+ * gfs2_releasepage - free the metadata associated with a page
+ * @page: the page that's being released
+ * @gfp_mask: passed from Linux VFS, ignored by us
+ *
+ * Call try_to_free_buffers() if the buffers in this page can be
+ * released.
+ *
+ * Returns: 0
+ */
+
+int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	struct inode *aspace = page->mapping->host;
+	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
+	struct buffer_head *bh, *head;
+	struct gfs2_bufdata *bd;
+
+	if (!page_has_buffers(page))
+		return 0;
+
+	gfs2_log_lock(sdp);
+	head = bh = page_buffers(page);
+	do {
+		if (atomic_read(&bh->b_count))
+			goto cannot_release;
+		bd = bh->b_private;
+		if (bd && bd->bd_ail)
+			goto cannot_release;
+		gfs2_assert_warn(sdp, !buffer_pinned(bh));
+		gfs2_assert_warn(sdp, !buffer_dirty(bh));
+		bh = bh->b_this_page;
+	} while(bh != head);
+	gfs2_log_unlock(sdp);
+
+	head = bh = page_buffers(page);
+	do {
+		gfs2_log_lock(sdp);
+		bd = bh->b_private;
+		if (bd) {
+			gfs2_assert_warn(sdp, bd->bd_bh == bh);
+			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
+			if (!list_empty(&bd->bd_le.le_list)) {
+				if (!buffer_pinned(bh))
+					list_del_init(&bd->bd_le.le_list);
+				else
+					bd = NULL;
+			}
+			if (bd)
+				bd->bd_bh = NULL;
+			bh->b_private = NULL;
+		}
+		gfs2_log_unlock(sdp);
+		if (bd)
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	return try_to_free_buffers(page);
+cannot_release:
+	gfs2_log_unlock(sdp);
+	return 0;
+}
+
+static const struct address_space_operations gfs2_writeback_aops = {
+	.writepage = gfs2_writeback_writepage,
+	.writepages = gfs2_writeback_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
+};
+
+static const struct address_space_operations gfs2_ordered_aops = {
+	.writepage = gfs2_ordered_writepage,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.set_page_dirty = gfs2_set_page_dirty,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
+};
+
+static const struct address_space_operations gfs2_jdata_aops = {
+	.writepage = gfs2_jdata_writepage,
+	.writepages = gfs2_jdata_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.set_page_dirty = gfs2_set_page_dirty,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.is_partially_uptodate = block_is_partially_uptodate,
+};
+
+void gfs2_set_aops(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (gfs2_is_writeback(ip))
+		inode->i_mapping->a_ops = &gfs2_writeback_aops;
+	else if (gfs2_is_ordered(ip))
+		inode->i_mapping->a_ops = &gfs2_ordered_aops;
+	else if (gfs2_is_jdata(ip))
+		inode->i_mapping->a_ops = &gfs2_jdata_aops;
+	else
+		BUG();
+}
+
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 253e1a3..1153a07 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -25,7 +25,6 @@
 #include "trans.h"
 #include "dir.h"
 #include "util.h"
-#include "ops_address.h"
 
 /* This doesn't need to be that large as max 64 bit pointers in a 4k
  * block is 512, so __u16 is fine for that. It saves stack space to
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
new file mode 100644
index 0000000..022c66c
--- /dev/null
+++ b/fs/gfs2/dentry.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "super.h"
+#include "util.h"
+#include "inode.h"
+
+/**
+ * gfs2_drevalidate - Check directory lookup consistency
+ * @dentry: the mapping to check
+ * @nd:
+ *
+ * Check to make sure the lookup necessary to arrive at this inode from its
+ * parent is still good.
+ *
+ * Returns: 1 if the dentry is ok, 0 if it isn't
+ */
+
+static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *parent = dget_parent(dentry);
+	struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
+	struct gfs2_inode *dip = GFS2_I(parent->d_inode);
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_holder d_gh;
+	struct gfs2_inode *ip = NULL;
+	int error;
+	int had_lock = 0;
+
+	if (inode) {
+		if (is_bad_inode(inode))
+			goto invalid;
+		ip = GFS2_I(inode);
+	}
+
+	if (sdp->sd_args.ar_localcaching)
+		goto valid;
+
+	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
+	if (!had_lock) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		if (error)
+			goto fail;
+	} 
+
+	error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip);
+	switch (error) {
+	case 0:
+		if (!inode)
+			goto invalid_gunlock;
+		break;
+	case -ENOENT:
+		if (!inode)
+			goto valid_gunlock;
+		goto invalid_gunlock;
+	default:
+		goto fail_gunlock;
+	}
+
+valid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+valid:
+	dput(parent);
+	return 1;
+
+invalid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+invalid:
+	if (inode && S_ISDIR(inode->i_mode)) {
+		if (have_submounts(dentry))
+			goto valid;
+		shrink_dcache_parent(dentry);
+	}
+	d_drop(dentry);
+	dput(parent);
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+fail:
+	dput(parent);
+	return 0;
+}
+
+static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
+{
+	str->hash = gfs2_disk_hash(str->name, str->len);
+	return 0;
+}
+
+const struct dentry_operations gfs2_dops = {
+	.d_revalidate = gfs2_drevalidate,
+	.d_hash = gfs2_dhash,
+};
+
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
new file mode 100644
index 0000000..9200ef2
--- /dev/null
+++ b/fs/gfs2/export.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "super.h"
+#include "rgrp.h"
+#include "util.h"
+
+#define GFS2_SMALL_FH_SIZE 4
+#define GFS2_LARGE_FH_SIZE 8
+#define GFS2_OLD_FH_SIZE 10
+
+static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
+			  int connectable)
+{
+	__be32 *fh = (__force __be32 *)p;
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (*len < GFS2_SMALL_FH_SIZE ||
+	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+		return 255;
+
+	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[2] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_SMALL_FH_SIZE;
+
+	if (!connectable || inode == sb->s_root->d_inode)
+		return *len;
+
+	spin_lock(&dentry->d_lock);
+	inode = dentry->d_parent->d_inode;
+	ip = GFS2_I(inode);
+	igrab(inode);
+	spin_unlock(&dentry->d_lock);
+
+	fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[6] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_LARGE_FH_SIZE;
+
+	iput(inode);
+
+	return *len;
+}
+
+struct get_name_filldir {
+	struct gfs2_inum_host inum;
+	char *name;
+};
+
+static int get_name_filldir(void *opaque, const char *name, int length,
+			    loff_t offset, u64 inum, unsigned int type)
+{
+	struct get_name_filldir *gnfd = opaque;
+
+	if (inum != gnfd->inum.no_addr)
+		return 0;
+
+	memcpy(gnfd->name, name, length);
+	gnfd->name[length] = 0;
+
+	return 1;
+}
+
+static int gfs2_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct inode *dir = parent->d_inode;
+	struct inode *inode = child->d_inode;
+	struct gfs2_inode *dip, *ip;
+	struct get_name_filldir gnfd;
+	struct gfs2_holder gh;
+	u64 offset = 0;
+	int error;
+
+	if (!dir)
+		return -EINVAL;
+
+	if (!S_ISDIR(dir->i_mode) || !inode)
+		return -EINVAL;
+
+	dip = GFS2_I(dir);
+	ip = GFS2_I(inode);
+
+	*name = 0;
+	gnfd.inum.no_addr = ip->i_no_addr;
+	gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
+	gnfd.name = name;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (error)
+		return error;
+
+	error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
+
+	gfs2_glock_dq_uninit(&gh);
+
+	if (!error && !*name)
+		error = -ENOENT;
+
+	return error;
+}
+
+static struct dentry *gfs2_get_parent(struct dentry *child)
+{
+	struct qstr dotdot;
+	struct dentry *dentry;
+
+	/*
+	 * XXX(hch): it would be a good idea to keep this around as a
+	 *	     static variable.
+	 */
+	gfs2_str2qstr(&dotdot, "..");
+
+	dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &dotdot, 1));
+	if (!IS_ERR(dentry))
+		dentry->d_op = &gfs2_dops;
+	return dentry;
+}
+
+static struct dentry *gfs2_get_dentry(struct super_block *sb,
+		struct gfs2_inum_host *inum)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_holder i_gh, ri_gh, rgd_gh;
+	struct gfs2_rgrpd *rgd;
+	struct inode *inode;
+	struct dentry *dentry;
+	int error;
+
+	/* System files? */
+
+	inode = gfs2_ilookup(sb, inum->no_addr);
+	if (inode) {
+		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		goto out_inode;
+	}
+
+	error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
+				  LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return ERR_PTR(error);
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto fail;
+
+	error = -EINVAL;
+	rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
+	if (!rgd)
+		goto fail_rindex;
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
+	if (error)
+		goto fail_rindex;
+
+	error = -ESTALE;
+	if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
+		goto fail_rgd;
+
+	gfs2_glock_dq_uninit(&rgd_gh);
+	gfs2_glock_dq_uninit(&ri_gh);
+
+	inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
+					inum->no_addr,
+					0, 0);
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		goto fail;
+	}
+
+	error = gfs2_inode_refresh(GFS2_I(inode));
+	if (error) {
+		iput(inode);
+		goto fail;
+	}
+
+	/* Pick up the works we bypass in gfs2_inode_lookup */
+	if (inode->i_state & I_NEW) 
+		gfs2_set_iop(inode);
+
+	if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
+		iput(inode);
+		goto fail;
+	}
+
+	error = -EIO;
+	if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM) {
+		iput(inode);
+		goto fail;
+	}
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+out_inode:
+	dentry = d_obtain_alias(inode);
+	if (!IS_ERR(dentry))
+		dentry->d_op = &gfs2_dops;
+	return dentry;
+
+fail_rgd:
+	gfs2_glock_dq_uninit(&rgd_gh);
+
+fail_rindex:
+	gfs2_glock_dq_uninit(&ri_gh);
+
+fail:
+	gfs2_glock_dq_uninit(&i_gh);
+	return ERR_PTR(error);
+}
+
+static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host this;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_SMALL_FH_SIZE:
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
+		this.no_formal_ino |= be32_to_cpu(fh[1]);
+		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
+		this.no_addr |= be32_to_cpu(fh[3]);
+		return gfs2_get_dentry(sb, &this);
+	default:
+		return NULL;
+	}
+}
+
+static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host parent;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
+		parent.no_formal_ino |= be32_to_cpu(fh[5]);
+		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
+		parent.no_addr |= be32_to_cpu(fh[7]);
+		return gfs2_get_dentry(sb, &parent);
+	default:
+		return NULL;
+	}
+}
+
+const struct export_operations gfs2_export_ops = {
+	.encode_fh = gfs2_encode_fh,
+	.fh_to_dentry = gfs2_fh_to_dentry,
+	.fh_to_parent = gfs2_fh_to_parent,
+	.get_name = gfs2_get_name,
+	.get_parent = gfs2_get_parent,
+};
+
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
new file mode 100644
index 0000000..73b6f55
--- /dev/null
+++ b/fs/gfs2/file.c
@@ -0,0 +1,765 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/ext2_fs.h>
+#include <linux/crc32.h>
+#include <linux/writeback.h>
+#include <asm/uaccess.h>
+#include <linux/dlm.h>
+#include <linux/dlm_plock.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "eaops.h"
+
+/**
+ * gfs2_llseek - seek to a location in a file
+ * @file: the file
+ * @offset: the offset
+ * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
+ *
+ * SEEK_END requires the glock for the file because it references the
+ * file's size.
+ *
+ * Returns: The new offset, or errno
+ */
+
+static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	loff_t error;
+
+	if (origin == 2) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (!error) {
+			error = generic_file_llseek_unlocked(file, offset, origin);
+			gfs2_glock_dq_uninit(&i_gh);
+		}
+	} else
+		error = generic_file_llseek_unlocked(file, offset, origin);
+
+	return error;
+}
+
+/**
+ * gfs2_readdir - Read directory entries from a directory
+ * @file: The directory to read from
+ * @dirent: Buffer for dirents
+ * @filldir: Function used to do the copying
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct inode *dir = file->f_mapping->host;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_holder d_gh;
+	u64 offset = file->f_pos;
+	int error;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+	error = gfs2_glock_nq(&d_gh);
+	if (error) {
+		gfs2_holder_uninit(&d_gh);
+		return error;
+	}
+
+	error = gfs2_dir_read(dir, &offset, dirent, filldir);
+
+	gfs2_glock_dq_uninit(&d_gh);
+
+	file->f_pos = offset;
+
+	return error;
+}
+
+/**
+ * fsflags_cvt
+ * @table: A table of 32 u32 flags
+ * @val: a 32 bit value to convert
+ *
+ * This function can be used to convert between fsflags values and
+ * GFS2's own flags values.
+ *
+ * Returns: the converted flags
+ */
+static u32 fsflags_cvt(const u32 *table, u32 val)
+{
+	u32 res = 0;
+	while(val) {
+		if (val & 1)
+			res |= *table;
+		table++;
+		val >>= 1;
+	}
+	return res;
+}
+
+static const u32 fsflags_to_gfs2[32] = {
+	[3] = GFS2_DIF_SYNC,
+	[4] = GFS2_DIF_IMMUTABLE,
+	[5] = GFS2_DIF_APPENDONLY,
+	[7] = GFS2_DIF_NOATIME,
+	[12] = GFS2_DIF_EXHASH,
+	[14] = GFS2_DIF_INHERIT_JDATA,
+};
+
+static const u32 gfs2_to_fsflags[32] = {
+	[gfs2fl_Sync] = FS_SYNC_FL,
+	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
+	[gfs2fl_AppendOnly] = FS_APPEND_FL,
+	[gfs2fl_NoAtime] = FS_NOATIME_FL,
+	[gfs2fl_ExHash] = FS_INDEX_FL,
+	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
+};
+
+static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+	u32 fsflags;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
+	if (error)
+		return error;
+
+	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
+	if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
+		fsflags |= FS_JOURNAL_DATA_FL;
+	if (put_user(fsflags, ptr))
+		error = -EFAULT;
+
+	gfs2_glock_dq(&gh);
+	gfs2_holder_uninit(&gh);
+	return error;
+}
+
+void gfs2_set_inode_flags(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int flags = inode->i_flags;
+
+	flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	if (ip->i_diskflags & GFS2_DIF_IMMUTABLE)
+		flags |= S_IMMUTABLE;
+	if (ip->i_diskflags & GFS2_DIF_APPENDONLY)
+		flags |= S_APPEND;
+	if (ip->i_diskflags & GFS2_DIF_NOATIME)
+		flags |= S_NOATIME;
+	if (ip->i_diskflags & GFS2_DIF_SYNC)
+		flags |= S_SYNC;
+	inode->i_flags = flags;
+}
+
+/* Flags that can be set by user space */
+#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
+			     GFS2_DIF_IMMUTABLE|		\
+			     GFS2_DIF_APPENDONLY|		\
+			     GFS2_DIF_NOATIME|			\
+			     GFS2_DIF_SYNC|			\
+			     GFS2_DIF_SYSTEM|			\
+			     GFS2_DIF_INHERIT_JDATA)
+
+/**
+ * gfs2_set_flags - set flags on an inode
+ * @inode: The inode
+ * @flags: The flags to set
+ * @mask: Indicates which flags are valid
+ *
+ */
+static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder gh;
+	int error;
+	u32 new_flags, flags;
+
+	error = mnt_want_write(filp->f_path.mnt);
+	if (error)
+		return error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (error)
+		goto out_drop_write;
+
+	flags = ip->i_diskflags;
+	new_flags = (flags & ~mask) | (reqflags & mask);
+	if ((new_flags ^ flags) == 0)
+		goto out;
+
+	error = -EINVAL;
+	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
+		goto out;
+
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
+		goto out;
+	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
+		goto out;
+	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		goto out;
+	if (!IS_IMMUTABLE(inode)) {
+		error = gfs2_permission(inode, MAY_WRITE);
+		if (error)
+			goto out;
+	}
+	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
+		if (flags & GFS2_DIF_JDATA)
+			gfs2_log_flush(sdp, ip->i_gl);
+		error = filemap_fdatawrite(inode->i_mapping);
+		if (error)
+			goto out;
+		error = filemap_fdatawait(inode->i_mapping);
+		if (error)
+			goto out;
+	}
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		goto out;
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		goto out_trans_end;
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	ip->i_diskflags = new_flags;
+	gfs2_dinode_out(ip, bh->b_data);
+	brelse(bh);
+	gfs2_set_inode_flags(inode);
+	gfs2_set_aops(inode);
+out_trans_end:
+	gfs2_trans_end(sdp);
+out:
+	gfs2_glock_dq_uninit(&gh);
+out_drop_write:
+	mnt_drop_write(filp->f_path.mnt);
+	return error;
+}
+
+static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	u32 fsflags, gfsflags;
+	if (get_user(fsflags, ptr))
+		return -EFAULT;
+	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
+	if (!S_ISDIR(inode->i_mode)) {
+		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
+			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
+		return do_gfs2_set_flags(filp, gfsflags, ~0);
+	}
+	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
+}
+
+static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch(cmd) {
+	case FS_IOC_GETFLAGS:
+		return gfs2_get_flags(filp, (u32 __user *)arg);
+	case FS_IOC_SETFLAGS:
+		return gfs2_set_flags(filp, (u32 __user *)arg);
+	}
+	return -ENOTTY;
+}
+
+/**
+ * gfs2_allocate_page_backing - Use bmap to allocate blocks
+ * @page: The (locked) page to allocate backing for
+ *
+ * We try to allocate all the blocks required for the page in
+ * one go. This might fail for various reasons, so we keep
+ * trying until all the blocks to back this page are allocated.
+ * If some of the blocks are already allocated, thats ok too.
+ */
+
+static int gfs2_allocate_page_backing(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct buffer_head bh;
+	unsigned long size = PAGE_CACHE_SIZE;
+	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	do {
+		bh.b_state = 0;
+		bh.b_size = size;
+		gfs2_block_map(inode, lblock, &bh, 1);
+		if (!buffer_mapped(&bh))
+			return -EIO;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> inode->i_blkbits);
+	} while(size > 0);
+	return 0;
+}
+
+/**
+ * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
+ * @vma: The virtual memory area
+ * @page: The page which is about to become writable
+ *
+ * When the page becomes writable, we need to ensure that we have
+ * blocks allocated on disk to back that page.
+ */
+
+static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned long last_index;
+	u64 pos = page->index << PAGE_CACHE_SHIFT;
+	unsigned int data_blocks, ind_blocks, rblocks;
+	int alloc_required = 0;
+	struct gfs2_holder gh;
+	struct gfs2_alloc *al;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out;
+
+	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
+	set_bit(GIF_SW_PAGED, &ip->i_flags);
+
+	ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
+	if (ret || !alloc_required)
+		goto out_unlock;
+	ret = -ENOMEM;
+	al = gfs2_alloc_get(ip);
+	if (al == NULL)
+		goto out_unlock;
+
+	ret = gfs2_quota_lock_check(ip);
+	if (ret)
+		goto out_alloc_put;
+	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+	al->al_requested = data_blocks + ind_blocks;
+	ret = gfs2_inplace_reserve(ip);
+	if (ret)
+		goto out_quota_unlock;
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+	ret = gfs2_trans_begin(sdp, rblocks, 0);
+	if (ret)
+		goto out_trans_fail;
+
+	lock_page(page);
+	ret = -EINVAL;
+	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
+	if (page->index > last_index)
+		goto out_unlock_page;
+	ret = 0;
+	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
+		goto out_unlock_page;
+	if (gfs2_is_stuffed(ip)) {
+		ret = gfs2_unstuff_dinode(ip, page);
+		if (ret)
+			goto out_unlock_page;
+	}
+	ret = gfs2_allocate_page_backing(page);
+
+out_unlock_page:
+	unlock_page(page);
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_quota_unlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	if (ret == -ENOMEM)
+		ret = VM_FAULT_OOM;
+	else if (ret)
+		ret = VM_FAULT_SIGBUS;
+	return ret;
+}
+
+static struct vm_operations_struct gfs2_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = gfs2_page_mkwrite,
+};
+
+/**
+ * gfs2_mmap -
+ * @file: The file to map
+ * @vma: The VMA which described the mapping
+ *
+ * There is no need to get a lock here unless we should be updating
+ * atime. We ignore any locking errors since the only consequence is
+ * a missed atime update (which will just be deferred until later).
+ *
+ * Returns: 0
+ */
+
+static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+
+	if (!(file->f_flags & O_NOATIME)) {
+		struct gfs2_holder i_gh;
+		int error;
+
+		gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+		error = gfs2_glock_nq(&i_gh);
+		file_accessed(file);
+		if (error == 0)
+			gfs2_glock_dq_uninit(&i_gh);
+	}
+	vma->vm_ops = &gfs2_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
+
+	return 0;
+}
+
+/**
+ * gfs2_open - open a file
+ * @inode: the inode to open
+ * @file: the struct file for this opening
+ *
+ * Returns: errno
+ */
+
+static int gfs2_open(struct inode *inode, struct file *file)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	struct gfs2_file *fp;
+	int error;
+
+	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	mutex_init(&fp->f_fl_mutex);
+
+	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
+	file->private_data = fp;
+
+	if (S_ISREG(ip->i_inode.i_mode)) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (error)
+			goto fail;
+
+		if (!(file->f_flags & O_LARGEFILE) &&
+		    ip->i_disksize > MAX_NON_LFS) {
+			error = -EOVERFLOW;
+			goto fail_gunlock;
+		}
+
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+fail:
+	file->private_data = NULL;
+	kfree(fp);
+	return error;
+}
+
+/**
+ * gfs2_close - called to close a struct file
+ * @inode: the inode the struct file belongs to
+ * @file: the struct file being closed
+ *
+ * Returns: errno
+ */
+
+static int gfs2_close(struct inode *inode, struct file *file)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_file *fp;
+
+	fp = file->private_data;
+	file->private_data = NULL;
+
+	if (gfs2_assert_warn(sdp, fp))
+		return -EIO;
+
+	kfree(fp);
+
+	return 0;
+}
+
+/**
+ * gfs2_fsync - sync the dirty data for a file (across the cluster)
+ * @file: the file that points to the dentry (we ignore this)
+ * @dentry: the dentry that points to the inode to sync
+ *
+ * The VFS will flush "normal" data for us. We only need to worry
+ * about metadata here. For journaled data, we just do a log flush
+ * as we can't avoid it. Otherwise we can just bale out if datasync
+ * is set. For stuffed inodes we must flush the log in order to
+ * ensure that all data is on disk.
+ *
+ * The call to write_inode_now() is there to write back metadata and
+ * the inode itself. It does also try and write the data, but thats
+ * (hopefully) a no-op due to the VFS having already called filemap_fdatawrite()
+ * for us.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
+	int ret = 0;
+
+	if (gfs2_is_jdata(GFS2_I(inode))) {
+		gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
+		return 0;
+	}
+
+	if (sync_state != 0) {
+		if (!datasync)
+			ret = write_inode_now(inode, 0);
+
+		if (gfs2_is_stuffed(GFS2_I(inode)))
+			gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+
+/**
+ * gfs2_setlease - acquire/release a file lease
+ * @file: the file pointer
+ * @arg: lease type
+ * @fl: file lock
+ *
+ * We don't currently have a way to enforce a lease across the whole
+ * cluster; until we do, disable leases (by just returning -EINVAL),
+ * unless the administrator has requested purely local locking.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
+{
+	return -EINVAL;
+}
+
+/**
+ * gfs2_lock - acquire/release a posix lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+
+	if (!(fl->fl_flags & FL_POSIX))
+		return -ENOLCK;
+	if (__mandatory_lock(&ip->i_inode))
+		return -ENOLCK;
+
+	if (cmd == F_CANCELLK) {
+		/* Hack: */
+		cmd = F_SETLK;
+		fl->fl_type = F_UNLCK;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+	if (IS_GETLK(cmd))
+		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
+	else if (fl->fl_type == F_UNLCK)
+		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
+	else
+		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
+}
+
+static int do_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+	struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
+	struct gfs2_glock *gl;
+	unsigned int state;
+	int flags;
+	int error = 0;
+
+	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+
+	mutex_lock(&fp->f_fl_mutex);
+
+	gl = fl_gh->gh_gl;
+	if (gl) {
+		if (fl_gh->gh_state == state)
+			goto out;
+		flock_lock_file_wait(file,
+				     &(struct file_lock){.fl_type = F_UNLCK});
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_reinit(state, flags, fl_gh);
+	} else {
+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
+				       &gfs2_flock_glops, CREATE, &gl);
+		if (error)
+			goto out;
+		gfs2_holder_init(gl, state, flags, fl_gh);
+		gfs2_glock_put(gl);
+	}
+	error = gfs2_glock_nq(fl_gh);
+	if (error) {
+		gfs2_holder_uninit(fl_gh);
+		if (error == GLR_TRYFAILED)
+			error = -EAGAIN;
+	} else {
+		error = flock_lock_file_wait(file, fl);
+		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
+	}
+
+out:
+	mutex_unlock(&fp->f_fl_mutex);
+	return error;
+}
+
+static void do_unflock(struct file *file, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+
+	mutex_lock(&fp->f_fl_mutex);
+	flock_lock_file_wait(file, fl);
+	if (fl_gh->gh_gl)
+		gfs2_glock_dq_uninit(fl_gh);
+	mutex_unlock(&fp->f_fl_mutex);
+}
+
+/**
+ * gfs2_flock - acquire/release a flock lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		return -ENOLCK;
+	if (__mandatory_lock(&ip->i_inode))
+		return -ENOLCK;
+
+	if (fl->fl_type == F_UNLCK) {
+		do_unflock(file, fl);
+		return 0;
+	} else {
+		return do_flock(file, cmd, fl);
+	}
+}
+
+const struct file_operations gfs2_file_fops = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.setlease	= gfs2_setlease,
+};
+
+const struct file_operations gfs2_dir_fops = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+};
+
+#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
+
+const struct file_operations gfs2_file_fops_nolock = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.setlease	= generic_setlease,
+};
+
+const struct file_operations gfs2_dir_fops_nolock = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+};
+
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 5a31d42..c03a1a3 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -30,7 +30,6 @@
 #include "inode.h"
 #include "log.h"
 #include "meta_io.h"
-#include "ops_address.h"
 #include "quota.h"
 #include "rgrp.h"
 #include "trans.h"
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index c30be2b..2c3ec07 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -11,8 +11,16 @@
 #define __INODE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
 #include "util.h"
 
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_set_aops(struct inode *inode);
+
 static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
 {
 	return !ip->i_height;
@@ -73,30 +81,31 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
 }
 
 
-void gfs2_set_iop(struct inode *inode);
-struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				u64 no_addr, u64 no_formal_ino,
-				int skip_freeing);
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
-
-int gfs2_inode_refresh(struct gfs2_inode *ip);
-
-int gfs2_dinode_dealloc(struct gfs2_inode *inode);
-int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
-struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
-			   int is_root);
-struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
-			   unsigned int mode, dev_t dev);
-int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
-		struct gfs2_inode *ip);
-int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
-		   const struct gfs2_inode *ip);
-int gfs2_permission(struct inode *inode, int mask);
-int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
-int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
-struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
-void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
-void gfs2_dinode_print(const struct gfs2_inode *ip);
+extern void gfs2_set_iop(struct inode *inode);
+extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
+				       u64 no_addr, u64 no_formal_ino,
+				       int skip_freeing);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
+
+extern int gfs2_inode_refresh(struct gfs2_inode *ip);
+
+extern int gfs2_dinode_dealloc(struct gfs2_inode *inode);
+extern int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
+extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+				  int is_root);
+extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
+				  const struct qstr *name,
+				  unsigned int mode, dev_t dev);
+extern int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
+		       struct gfs2_inode *ip);
+extern int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+			  const struct gfs2_inode *ip);
+extern int gfs2_permission(struct inode *inode, int mask);
+extern int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
+extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
+extern void gfs2_dinode_print(const struct gfs2_inode *ip);
 
 extern const struct inode_operations gfs2_file_iops;
 extern const struct inode_operations gfs2_dir_iops;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 78a5f43..cb8d7a9 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -31,7 +31,6 @@
 #include "rgrp.h"
 #include "trans.h"
 #include "util.h"
-#include "ops_address.h"
 
 static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
 {
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
deleted file mode 100644
index e566421..0000000
--- a/fs/gfs2/ops_address.c
+++ /dev/null
@@ -1,1146 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/pagemap.h>
-#include <linux/pagevec.h>
-#include <linux/mpage.h>
-#include <linux/fs.h>
-#include <linux/writeback.h>
-#include <linux/swap.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/backing-dev.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "bmap.h"
-#include "glock.h"
-#include "inode.h"
-#include "log.h"
-#include "meta_io.h"
-#include "ops_address.h"
-#include "quota.h"
-#include "trans.h"
-#include "rgrp.h"
-#include "super.h"
-#include "util.h"
-#include "glops.h"
-
-
-static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-				   unsigned int from, unsigned int to)
-{
-	struct buffer_head *head = page_buffers(page);
-	unsigned int bsize = head->b_size;
-	struct buffer_head *bh;
-	unsigned int start, end;
-
-	for (bh = head, start = 0; bh != head || !start;
-	     bh = bh->b_this_page, start = end) {
-		end = start + bsize;
-		if (end <= from || start >= to)
-			continue;
-		if (gfs2_is_jdata(ip))
-			set_buffer_uptodate(bh);
-		gfs2_trans_add_bh(ip->i_gl, bh, 0);
-	}
-}
-
-/**
- * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
- * @inode: The inode
- * @lblock: The block number to look up
- * @bh_result: The buffer head to return the result in
- * @create: Non-zero if we may add block to the file
- *
- * Returns: errno
- */
-
-static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
-				  struct buffer_head *bh_result, int create)
-{
-	int error;
-
-	error = gfs2_block_map(inode, lblock, bh_result, 0);
-	if (error)
-		return error;
-	if (!buffer_mapped(bh_result))
-		return -EIO;
-	return 0;
-}
-
-static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
-				 struct buffer_head *bh_result, int create)
-{
-	return gfs2_block_map(inode, lblock, bh_result, 0);
-}
-
-/**
- * gfs2_writepage_common - Common bits of writepage
- * @page: The page to be written
- * @wbc: The writeback control
- *
- * Returns: 1 if writepage is ok, otherwise an error code or zero if no error.
- */
-
-static int gfs2_writepage_common(struct page *page,
-				 struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-	unsigned offset;
-
-	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
-		goto out;
-	if (current->journal_info)
-		goto redirty;
-	/* Is the page fully outside i_size? (truncate in progress) */
-	offset = i_size & (PAGE_CACHE_SIZE-1);
-	if (page->index > end_index || (page->index == end_index && !offset)) {
-		page->mapping->a_ops->invalidatepage(page, 0);
-		goto out;
-	}
-	return 1;
-redirty:
-	redirty_page_for_writepage(wbc, page);
-out:
-	unlock_page(page);
-	return 0;
-}
-
-/**
- * gfs2_writeback_writepage - Write page for writeback mappings
- * @page: The page
- * @wbc: The writeback control
- *
- */
-
-static int gfs2_writeback_writepage(struct page *page,
-				    struct writeback_control *wbc)
-{
-	int ret;
-
-	ret = gfs2_writepage_common(page, wbc);
-	if (ret <= 0)
-		return ret;
-
-	ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
-	if (ret == -EAGAIN)
-		ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
-	return ret;
-}
-
-/**
- * gfs2_ordered_writepage - Write page for ordered data files
- * @page: The page to write
- * @wbc: The writeback control
- *
- */
-
-static int gfs2_ordered_writepage(struct page *page,
-				  struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	int ret;
-
-	ret = gfs2_writepage_common(page, wbc);
-	if (ret <= 0)
-		return ret;
-
-	if (!page_has_buffers(page)) {
-		create_empty_buffers(page, inode->i_sb->s_blocksize,
-				     (1 << BH_Dirty)|(1 << BH_Uptodate));
-	}
-	gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1);
-	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
-}
-
-/**
- * __gfs2_jdata_writepage - The core of jdata writepage
- * @page: The page to write
- * @wbc: The writeback control
- *
- * This is shared between writepage and writepages and implements the
- * core of the writepage operation. If a transaction is required then
- * PageChecked will have been set and the transaction will have
- * already been started before this is called.
- */
-
-static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-
-	if (PageChecked(page)) {
-		ClearPageChecked(page);
-		if (!page_has_buffers(page)) {
-			create_empty_buffers(page, inode->i_sb->s_blocksize,
-					     (1 << BH_Dirty)|(1 << BH_Uptodate));
-		}
-		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
-	}
-	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
-}
-
-/**
- * gfs2_jdata_writepage - Write complete page
- * @page: Page to write
- *
- * Returns: errno
- *
- */
-
-static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int ret;
-	int done_trans = 0;
-
-	if (PageChecked(page)) {
-		if (wbc->sync_mode != WB_SYNC_ALL)
-			goto out_ignore;
-		ret = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
-		if (ret)
-			goto out_ignore;
-		done_trans = 1;
-	}
-	ret = gfs2_writepage_common(page, wbc);
-	if (ret > 0)
-		ret = __gfs2_jdata_writepage(page, wbc);
-	if (done_trans)
-		gfs2_trans_end(sdp);
-	return ret;
-
-out_ignore:
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
-
-/**
- * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
- * @mapping: The mapping to write
- * @wbc: Write-back control
- *
- * For the data=writeback case we can already ignore buffer heads
- * and write whole extents at once. This is a big reduction in the
- * number of I/O requests we send and the bmap calls we make in this case.
- */
-static int gfs2_writeback_writepages(struct address_space *mapping,
-				     struct writeback_control *wbc)
-{
-	return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
-}
-
-/**
- * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages
- * @mapping: The mapping
- * @wbc: The writeback control
- * @writepage: The writepage function to call for each page
- * @pvec: The vector of pages
- * @nr_pages: The number of pages to write
- *
- * Returns: non-zero if loop should terminate, zero otherwise
- */
-
-static int gfs2_write_jdata_pagevec(struct address_space *mapping,
-				    struct writeback_control *wbc,
-				    struct pagevec *pvec,
-				    int nr_pages, pgoff_t end)
-{
-	struct inode *inode = mapping->host;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-	unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
-	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
-	int i;
-	int ret;
-
-	ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
-	if (ret < 0)
-		return ret;
-
-	for(i = 0; i < nr_pages; i++) {
-		struct page *page = pvec->pages[i];
-
-		lock_page(page);
-
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			continue;
-		}
-
-		if (!wbc->range_cyclic && page->index > end) {
-			ret = 1;
-			unlock_page(page);
-			continue;
-		}
-
-		if (wbc->sync_mode != WB_SYNC_NONE)
-			wait_on_page_writeback(page);
-
-		if (PageWriteback(page) ||
-		    !clear_page_dirty_for_io(page)) {
-			unlock_page(page);
-			continue;
-		}
-
-		/* Is the page fully outside i_size? (truncate in progress) */
-		if (page->index > end_index || (page->index == end_index && !offset)) {
-			page->mapping->a_ops->invalidatepage(page, 0);
-			unlock_page(page);
-			continue;
-		}
-
-		ret = __gfs2_jdata_writepage(page, wbc);
-
-		if (ret || (--(wbc->nr_to_write) <= 0))
-			ret = 1;
-		if (wbc->nonblocking && bdi_write_congested(bdi)) {
-			wbc->encountered_congestion = 1;
-			ret = 1;
-		}
-
-	}
-	gfs2_trans_end(sdp);
-	return ret;
-}
-
-/**
- * gfs2_write_cache_jdata - Like write_cache_pages but different
- * @mapping: The mapping to write
- * @wbc: The writeback control
- * @writepage: The writepage function to call
- * @data: The data to pass to writepage
- *
- * The reason that we use our own function here is that we need to
- * start transactions before we grab page locks. This allows us
- * to get the ordering right.
- */
-
-static int gfs2_write_cache_jdata(struct address_space *mapping,
-				  struct writeback_control *wbc)
-{
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
-	int ret = 0;
-	int done = 0;
-	struct pagevec pvec;
-	int nr_pages;
-	pgoff_t index;
-	pgoff_t end;
-	int scanned = 0;
-	int range_whole = 0;
-
-	if (wbc->nonblocking && bdi_write_congested(bdi)) {
-		wbc->encountered_congestion = 1;
-		return 0;
-	}
-
-	pagevec_init(&pvec, 0);
-	if (wbc->range_cyclic) {
-		index = mapping->writeback_index; /* Start from prev offset */
-		end = -1;
-	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
-		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
-			range_whole = 1;
-		scanned = 1;
-	}
-
-retry:
-	 while (!done && (index <= end) &&
-		(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-					       PAGECACHE_TAG_DIRTY,
-					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
-		scanned = 1;
-		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
-		if (ret)
-			done = 1;
-		if (ret > 0)
-			ret = 0;
-
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-
-	if (!scanned && !done) {
-		/*
-		 * We hit the last page and there is more work to be done: wrap
-		 * back to the start of the file
-		 */
-		scanned = 1;
-		index = 0;
-		goto retry;
-	}
-
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
-	return ret;
-}
-
-
-/**
- * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
- * @mapping: The mapping to write
- * @wbc: The writeback control
- * 
- */
-
-static int gfs2_jdata_writepages(struct address_space *mapping,
-				 struct writeback_control *wbc)
-{
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
-	int ret;
-
-	ret = gfs2_write_cache_jdata(mapping, wbc);
-	if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
-		gfs2_log_flush(sdp, ip->i_gl);
-		ret = gfs2_write_cache_jdata(mapping, wbc);
-	}
-	return ret;
-}
-
-/**
- * stuffed_readpage - Fill in a Linux page with stuffed file data
- * @ip: the inode
- * @page: the page
- *
- * Returns: errno
- */
-
-static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
-{
-	struct buffer_head *dibh;
-	void *kaddr;
-	int error;
-
-	/*
-	 * Due to the order of unstuffing files and ->fault(), we can be
-	 * asked for a zero page in the case of a stuffed file being extended,
-	 * so we need to supply one here. It doesn't happen often.
-	 */
-	if (unlikely(page->index)) {
-		zero_user(page, 0, PAGE_CACHE_SIZE);
-		SetPageUptodate(page);
-		return 0;
-	}
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		return error;
-
-	kaddr = kmap_atomic(page, KM_USER0);
-	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
-	       ip->i_disksize);
-	memset(kaddr + ip->i_disksize, 0, PAGE_CACHE_SIZE - ip->i_disksize);
-	kunmap_atomic(kaddr, KM_USER0);
-	flush_dcache_page(page);
-	brelse(dibh);
-	SetPageUptodate(page);
-
-	return 0;
-}
-
-
-/**
- * __gfs2_readpage - readpage
- * @file: The file to read a page for
- * @page: The page to read
- *
- * This is the core of gfs2's readpage. Its used by the internal file
- * reading code as in that case we already hold the glock. Also its
- * called by gfs2_readpage() once the required lock has been granted.
- *
- */
-
-static int __gfs2_readpage(void *file, struct page *page)
-{
-	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-	int error;
-
-	if (gfs2_is_stuffed(ip)) {
-		error = stuffed_readpage(ip, page);
-		unlock_page(page);
-	} else {
-		error = mpage_readpage(page, gfs2_block_map);
-	}
-
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-		return -EIO;
-
-	return error;
-}
-
-/**
- * gfs2_readpage - read a page of a file
- * @file: The file to read
- * @page: The page of the file
- *
- * This deals with the locking required. We have to unlock and
- * relock the page in order to get the locking in the right
- * order.
- */
-
-static int gfs2_readpage(struct file *file, struct page *page)
-{
-	struct address_space *mapping = page->mapping;
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_holder gh;
-	int error;
-
-	unlock_page(page);
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	error = gfs2_glock_nq(&gh);
-	if (unlikely(error))
-		goto out;
-	error = AOP_TRUNCATED_PAGE;
-	lock_page(page);
-	if (page->mapping == mapping && !PageUptodate(page))
-		error = __gfs2_readpage(file, page);
-	else
-		unlock_page(page);
-	gfs2_glock_dq(&gh);
-out:
-	gfs2_holder_uninit(&gh);
-	if (error && error != AOP_TRUNCATED_PAGE)
-		lock_page(page);
-	return error;
-}
-
-/**
- * gfs2_internal_read - read an internal file
- * @ip: The gfs2 inode
- * @ra_state: The readahead state (or NULL for no readahead)
- * @buf: The buffer to fill
- * @pos: The file position
- * @size: The amount to read
- *
- */
-
-int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
-                       char *buf, loff_t *pos, unsigned size)
-{
-	struct address_space *mapping = ip->i_inode.i_mapping;
-	unsigned long index = *pos / PAGE_CACHE_SIZE;
-	unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
-	unsigned copied = 0;
-	unsigned amt;
-	struct page *page;
-	void *p;
-
-	do {
-		amt = size - copied;
-		if (offset + size > PAGE_CACHE_SIZE)
-			amt = PAGE_CACHE_SIZE - offset;
-		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
-		if (IS_ERR(page))
-			return PTR_ERR(page);
-		p = kmap_atomic(page, KM_USER0);
-		memcpy(buf + copied, p + offset, amt);
-		kunmap_atomic(p, KM_USER0);
-		mark_page_accessed(page);
-		page_cache_release(page);
-		copied += amt;
-		index++;
-		offset = 0;
-	} while(copied < size);
-	(*pos) += size;
-	return size;
-}
-
-/**
- * gfs2_readpages - Read a bunch of pages at once
- *
- * Some notes:
- * 1. This is only for readahead, so we can simply ignore any things
- *    which are slightly inconvenient (such as locking conflicts between
- *    the page lock and the glock) and return having done no I/O. Its
- *    obviously not something we'd want to do on too regular a basis.
- *    Any I/O we ignore@this time will be done via readpage later.
- * 2. We don't handle stuffed files here we let readpage do the honours.
- * 3. mpage_readpages() does most of the heavy lifting in the common case.
- * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
- */
-
-static int gfs2_readpages(struct file *file, struct address_space *mapping,
-			  struct list_head *pages, unsigned nr_pages)
-{
-	struct inode *inode = mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_holder gh;
-	int ret;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	ret = gfs2_glock_nq(&gh);
-	if (unlikely(ret))
-		goto out_uninit;
-	if (!gfs2_is_stuffed(ip))
-		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
-	gfs2_glock_dq(&gh);
-out_uninit:
-	gfs2_holder_uninit(&gh);
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-		ret = -EIO;
-	return ret;
-}
-
-/**
- * gfs2_write_begin - Begin to write to a file
- * @file: The file to write to
- * @mapping: The mapping in which to write
- * @pos: The file offset at which to start writing
- * @len: Length of the write
- * @flags: Various flags
- * @pagep: Pointer to return the page
- * @fsdata: Pointer to return fs data (unused by GFS2)
- *
- * Returns: errno
- */
-
-static int gfs2_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned flags,
-			    struct page **pagep, void **fsdata)
-{
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
-	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
-	int alloc_required;
-	int error = 0;
-	struct gfs2_alloc *al;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
-	unsigned to = from + len;
-	struct page *page;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
-	if (unlikely(error))
-		goto out_uninit;
-
-	error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
-	if (error)
-		goto out_unlock;
-
-	if (alloc_required || gfs2_is_jdata(ip))
-		gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
-
-	if (alloc_required) {
-		al = gfs2_alloc_get(ip);
-		if (!al) {
-			error = -ENOMEM;
-			goto out_unlock;
-		}
-
-		error = gfs2_quota_lock_check(ip);
-		if (error)
-			goto out_alloc_put;
-
-		al->al_requested = data_blocks + ind_blocks;
-		error = gfs2_inplace_reserve(ip);
-		if (error)
-			goto out_qunlock;
-	}
-
-	rblocks = RES_DINODE + ind_blocks;
-	if (gfs2_is_jdata(ip))
-		rblocks += data_blocks ? data_blocks : 1;
-	if (ind_blocks || data_blocks)
-		rblocks += RES_STATFS + RES_QUOTA;
-
-	error = gfs2_trans_begin(sdp, rblocks,
-				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
-	if (error)
-		goto out_trans_fail;
-
-	error = -ENOMEM;
-	flags |= AOP_FLAG_NOFS;
-	page = grab_cache_page_write_begin(mapping, index, flags);
-	*pagep = page;
-	if (unlikely(!page))
-		goto out_endtrans;
-
-	if (gfs2_is_stuffed(ip)) {
-		error = 0;
-		if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
-			error = gfs2_unstuff_dinode(ip, page);
-			if (error == 0)
-				goto prepare_write;
-		} else if (!PageUptodate(page)) {
-			error = stuffed_readpage(ip, page);
-		}
-		goto out;
-	}
-
-prepare_write:
-	error = block_prepare_write(page, from, to, gfs2_block_map);
-out:
-	if (error == 0)
-		return 0;
-
-	page_cache_release(page);
-	if (pos + len > ip->i_inode.i_size)
-		vmtruncate(&ip->i_inode, ip->i_inode.i_size);
-out_endtrans:
-	gfs2_trans_end(sdp);
-out_trans_fail:
-	if (alloc_required) {
-		gfs2_inplace_release(ip);
-out_qunlock:
-		gfs2_quota_unlock(ip);
-out_alloc_put:
-		gfs2_alloc_put(ip);
-	}
-out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
-out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
-	return error;
-}
-
-/**
- * adjust_fs_space - Adjusts the free space available due to gfs2_grow
- * @inode: the rindex inode
- */
-static void adjust_fs_space(struct inode *inode)
-{
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
-	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
-	u64 fs_total, new_free;
-
-	/* Total up the file system space, according to the latest rindex. */
-	fs_total = gfs2_ri_total(sdp);
-
-	spin_lock(&sdp->sd_statfs_spin);
-	if (fs_total > (m_sc->sc_total + l_sc->sc_total))
-		new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
-	else
-		new_free = 0;
-	spin_unlock(&sdp->sd_statfs_spin);
-	fs_warn(sdp, "File system extended by %llu blocks.\n",
-		(unsigned long long)new_free);
-	gfs2_statfs_change(sdp, new_free, new_free, 0);
-}
-
-/**
- * gfs2_stuffed_write_end - Write end for stuffed files
- * @inode: The inode
- * @dibh: The buffer_head containing the on-disk inode
- * @pos: The file position
- * @len: The length of the write
- * @copied: How much was actually copied by the VFS
- * @page: The page
- *
- * This copies the data from the page into the inode block after
- * the inode data structure itself.
- *
- * Returns: errno
- */
-static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
-				  loff_t pos, unsigned len, unsigned copied,
-				  struct page *page)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	u64 to = pos + copied;
-	void *kaddr;
-	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
-	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
-
-	BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
-	kaddr = kmap_atomic(page, KM_USER0);
-	memcpy(buf + pos, kaddr + pos, copied);
-	memset(kaddr + pos + copied, 0, len - copied);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
-
-	if (!PageUptodate(page))
-		SetPageUptodate(page);
-	unlock_page(page);
-	page_cache_release(page);
-
-	if (copied) {
-		if (inode->i_size < to) {
-			i_size_write(inode, to);
-			ip->i_disksize = inode->i_size;
-		}
-		gfs2_dinode_out(ip, di);
-		mark_inode_dirty(inode);
-	}
-
-	if (inode == sdp->sd_rindex)
-		adjust_fs_space(inode);
-
-	brelse(dibh);
-	gfs2_trans_end(sdp);
-	gfs2_glock_dq(&ip->i_gh);
-	gfs2_holder_uninit(&ip->i_gh);
-	return copied;
-}
-
-/**
- * gfs2_write_end
- * @file: The file to write to
- * @mapping: The address space to write to
- * @pos: The file position
- * @len: The length of the data
- * @copied:
- * @page: The page that has been written
- * @fsdata: The fsdata (unused in GFS2)
- *
- * The main write_end function for GFS2. We have a separate one for
- * stuffed files as they are slightly different, otherwise we just
- * put our locking around the VFS provided functions.
- *
- * Returns: errno
- */
-
-static int gfs2_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *page, void *fsdata)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct buffer_head *dibh;
-	struct gfs2_alloc *al = ip->i_alloc;
-	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
-	unsigned int to = from + len;
-	int ret;
-
-	BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
-
-	ret = gfs2_meta_inode_buffer(ip, &dibh);
-	if (unlikely(ret)) {
-		unlock_page(page);
-		page_cache_release(page);
-		goto failed;
-	}
-
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-
-	if (gfs2_is_stuffed(ip))
-		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
-
-	if (!gfs2_is_writeback(ip))
-		gfs2_page_add_databufs(ip, page, from, to);
-
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (ret > 0) {
-		if (inode->i_size > ip->i_disksize)
-			ip->i_disksize = inode->i_size;
-		gfs2_dinode_out(ip, dibh->b_data);
-		mark_inode_dirty(inode);
-	}
-
-	if (inode == sdp->sd_rindex)
-		adjust_fs_space(inode);
-
-	brelse(dibh);
-	gfs2_trans_end(sdp);
-failed:
-	if (al) {
-		gfs2_inplace_release(ip);
-		gfs2_quota_unlock(ip);
-		gfs2_alloc_put(ip);
-	}
-	gfs2_glock_dq(&ip->i_gh);
-	gfs2_holder_uninit(&ip->i_gh);
-	return ret;
-}
-
-/**
- * gfs2_set_page_dirty - Page dirtying function
- * @page: The page to dirty
- *
- * Returns: 1 if it dirtyed the page, or 0 otherwise
- */
- 
-static int gfs2_set_page_dirty(struct page *page)
-{
-	SetPageChecked(page);
-	return __set_page_dirty_buffers(page);
-}
-
-/**
- * gfs2_bmap - Block map function
- * @mapping: Address space info
- * @lblock: The block to map
- *
- * Returns: The disk address for the block or 0 on hole or error
- */
-
-static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
-{
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_holder i_gh;
-	sector_t dblock = 0;
-	int error;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
-	if (error)
-		return 0;
-
-	if (!gfs2_is_stuffed(ip))
-		dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
-
-	gfs2_glock_dq_uninit(&i_gh);
-
-	return dblock;
-}
-
-static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
-{
-	struct gfs2_bufdata *bd;
-
-	lock_buffer(bh);
-	gfs2_log_lock(sdp);
-	clear_buffer_dirty(bh);
-	bd = bh->b_private;
-	if (bd) {
-		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
-			list_del_init(&bd->bd_le.le_list);
-		else
-			gfs2_remove_from_journal(bh, current->journal_info, 0);
-	}
-	bh->b_bdev = NULL;
-	clear_buffer_mapped(bh);
-	clear_buffer_req(bh);
-	clear_buffer_new(bh);
-	gfs2_log_unlock(sdp);
-	unlock_buffer(bh);
-}
-
-static void gfs2_invalidatepage(struct page *page, unsigned long offset)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-	struct buffer_head *bh, *head;
-	unsigned long pos = 0;
-
-	BUG_ON(!PageLocked(page));
-	if (offset == 0)
-		ClearPageChecked(page);
-	if (!page_has_buffers(page))
-		goto out;
-
-	bh = head = page_buffers(page);
-	do {
-		if (offset <= pos)
-			gfs2_discard(sdp, bh);
-		pos += bh->b_size;
-		bh = bh->b_this_page;
-	} while (bh != head);
-out:
-	if (offset == 0)
-		try_to_release_page(page, 0);
-}
-
-/**
- * gfs2_ok_for_dio - check that dio is valid on this file
- * @ip: The inode
- * @rw: READ or WRITE
- * @offset: The offset at which we are reading or writing
- *
- * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
- *          1 (to accept the i/o request)
- */
-static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
-{
-	/*
-	 * Should we return an error here? I can't see that O_DIRECT for
-	 * a stuffed file makes any sense. For now we'll silently fall
-	 * back to buffered I/O
-	 */
-	if (gfs2_is_stuffed(ip))
-		return 0;
-
-	if (offset >= i_size_read(&ip->i_inode))
-		return 0;
-	return 1;
-}
-
-
-
-static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
-			      const struct iovec *iov, loff_t offset,
-			      unsigned long nr_segs)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
-	int rv;
-
-	/*
-	 * Deferred lock, even if its a write, since we do no allocation
-	 * on this path. All we need change is atime, and this lock mode
-	 * ensures that other nodes have flushed their buffered read caches
-	 * (i.e. their page cache entries for this inode). We do not,
-	 * unfortunately have the option of only flushing a range like
-	 * the VFS does.
-	 */
-	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
-	rv = gfs2_glock_nq(&gh);
-	if (rv)
-		return rv;
-	rv = gfs2_ok_for_dio(ip, rw, offset);
-	if (rv != 1)
-		goto out; /* dio not valid, fall back to buffered i/o */
-
-	rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
-					   iov, offset, nr_segs,
-					   gfs2_get_block_direct, NULL);
-out:
-	gfs2_glock_dq_m(1, &gh);
-	gfs2_holder_uninit(&gh);
-	return rv;
-}
-
-/**
- * gfs2_releasepage - free the metadata associated with a page
- * @page: the page that's being released
- * @gfp_mask: passed from Linux VFS, ignored by us
- *
- * Call try_to_free_buffers() if the buffers in this page can be
- * released.
- *
- * Returns: 0
- */
-
-int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
-{
-	struct inode *aspace = page->mapping->host;
-	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
-	struct buffer_head *bh, *head;
-	struct gfs2_bufdata *bd;
-
-	if (!page_has_buffers(page))
-		return 0;
-
-	gfs2_log_lock(sdp);
-	head = bh = page_buffers(page);
-	do {
-		if (atomic_read(&bh->b_count))
-			goto cannot_release;
-		bd = bh->b_private;
-		if (bd && bd->bd_ail)
-			goto cannot_release;
-		gfs2_assert_warn(sdp, !buffer_pinned(bh));
-		gfs2_assert_warn(sdp, !buffer_dirty(bh));
-		bh = bh->b_this_page;
-	} while(bh != head);
-	gfs2_log_unlock(sdp);
-
-	head = bh = page_buffers(page);
-	do {
-		gfs2_log_lock(sdp);
-		bd = bh->b_private;
-		if (bd) {
-			gfs2_assert_warn(sdp, bd->bd_bh == bh);
-			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
-			if (!list_empty(&bd->bd_le.le_list)) {
-				if (!buffer_pinned(bh))
-					list_del_init(&bd->bd_le.le_list);
-				else
-					bd = NULL;
-			}
-			if (bd)
-				bd->bd_bh = NULL;
-			bh->b_private = NULL;
-		}
-		gfs2_log_unlock(sdp);
-		if (bd)
-			kmem_cache_free(gfs2_bufdata_cachep, bd);
-
-		bh = bh->b_this_page;
-	} while (bh != head);
-
-	return try_to_free_buffers(page);
-cannot_release:
-	gfs2_log_unlock(sdp);
-	return 0;
-}
-
-static const struct address_space_operations gfs2_writeback_aops = {
-	.writepage = gfs2_writeback_writepage,
-	.writepages = gfs2_writeback_writepages,
-	.readpage = gfs2_readpage,
-	.readpages = gfs2_readpages,
-	.sync_page = block_sync_page,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
-	.bmap = gfs2_bmap,
-	.invalidatepage = gfs2_invalidatepage,
-	.releasepage = gfs2_releasepage,
-	.direct_IO = gfs2_direct_IO,
-	.migratepage = buffer_migrate_page,
-	.is_partially_uptodate = block_is_partially_uptodate,
-};
-
-static const struct address_space_operations gfs2_ordered_aops = {
-	.writepage = gfs2_ordered_writepage,
-	.readpage = gfs2_readpage,
-	.readpages = gfs2_readpages,
-	.sync_page = block_sync_page,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
-	.set_page_dirty = gfs2_set_page_dirty,
-	.bmap = gfs2_bmap,
-	.invalidatepage = gfs2_invalidatepage,
-	.releasepage = gfs2_releasepage,
-	.direct_IO = gfs2_direct_IO,
-	.migratepage = buffer_migrate_page,
-	.is_partially_uptodate = block_is_partially_uptodate,
-};
-
-static const struct address_space_operations gfs2_jdata_aops = {
-	.writepage = gfs2_jdata_writepage,
-	.writepages = gfs2_jdata_writepages,
-	.readpage = gfs2_readpage,
-	.readpages = gfs2_readpages,
-	.sync_page = block_sync_page,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
-	.set_page_dirty = gfs2_set_page_dirty,
-	.bmap = gfs2_bmap,
-	.invalidatepage = gfs2_invalidatepage,
-	.releasepage = gfs2_releasepage,
-	.is_partially_uptodate = block_is_partially_uptodate,
-};
-
-void gfs2_set_aops(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	if (gfs2_is_writeback(ip))
-		inode->i_mapping->a_ops = &gfs2_writeback_aops;
-	else if (gfs2_is_ordered(ip))
-		inode->i_mapping->a_ops = &gfs2_ordered_aops;
-	else if (gfs2_is_jdata(ip))
-		inode->i_mapping->a_ops = &gfs2_jdata_aops;
-	else
-		BUG();
-}
-
diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h
deleted file mode 100644
index 5da2128..0000000
--- a/fs/gfs2/ops_address.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#ifndef __OPS_ADDRESS_DOT_H__
-#define __OPS_ADDRESS_DOT_H__
-
-#include <linux/fs.h>
-#include <linux/buffer_head.h>
-#include <linux/mm.h>
-
-extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
-extern int gfs2_internal_read(struct gfs2_inode *ip,
-			      struct file_ra_state *ra_state,
-			      char *buf, loff_t *pos, unsigned size);
-extern void gfs2_set_aops(struct inode *inode);
-
-#endif /* __OPS_ADDRESS_DOT_H__ */
diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/ops_dentry.c
deleted file mode 100644
index 022c66c..0000000
--- a/fs/gfs2/ops_dentry.c
+++ /dev/null
@@ -1,114 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/crc32.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "dir.h"
-#include "glock.h"
-#include "super.h"
-#include "util.h"
-#include "inode.h"
-
-/**
- * gfs2_drevalidate - Check directory lookup consistency
- * @dentry: the mapping to check
- * @nd:
- *
- * Check to make sure the lookup necessary to arrive at this inode from its
- * parent is still good.
- *
- * Returns: 1 if the dentry is ok, 0 if it isn't
- */
-
-static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
-{
-	struct dentry *parent = dget_parent(dentry);
-	struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
-	struct gfs2_inode *dip = GFS2_I(parent->d_inode);
-	struct inode *inode = dentry->d_inode;
-	struct gfs2_holder d_gh;
-	struct gfs2_inode *ip = NULL;
-	int error;
-	int had_lock = 0;
-
-	if (inode) {
-		if (is_bad_inode(inode))
-			goto invalid;
-		ip = GFS2_I(inode);
-	}
-
-	if (sdp->sd_args.ar_localcaching)
-		goto valid;
-
-	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
-	if (!had_lock) {
-		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
-		if (error)
-			goto fail;
-	} 
-
-	error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip);
-	switch (error) {
-	case 0:
-		if (!inode)
-			goto invalid_gunlock;
-		break;
-	case -ENOENT:
-		if (!inode)
-			goto valid_gunlock;
-		goto invalid_gunlock;
-	default:
-		goto fail_gunlock;
-	}
-
-valid_gunlock:
-	if (!had_lock)
-		gfs2_glock_dq_uninit(&d_gh);
-valid:
-	dput(parent);
-	return 1;
-
-invalid_gunlock:
-	if (!had_lock)
-		gfs2_glock_dq_uninit(&d_gh);
-invalid:
-	if (inode && S_ISDIR(inode->i_mode)) {
-		if (have_submounts(dentry))
-			goto valid;
-		shrink_dcache_parent(dentry);
-	}
-	d_drop(dentry);
-	dput(parent);
-	return 0;
-
-fail_gunlock:
-	gfs2_glock_dq_uninit(&d_gh);
-fail:
-	dput(parent);
-	return 0;
-}
-
-static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
-{
-	str->hash = gfs2_disk_hash(str->name, str->len);
-	return 0;
-}
-
-const struct dentry_operations gfs2_dops = {
-	.d_revalidate = gfs2_drevalidate,
-	.d_hash = gfs2_dhash,
-};
-
diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c
deleted file mode 100644
index 9200ef2..0000000
--- a/fs/gfs2/ops_export.c
+++ /dev/null
@@ -1,285 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/exportfs.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/crc32.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "dir.h"
-#include "glock.h"
-#include "glops.h"
-#include "inode.h"
-#include "super.h"
-#include "rgrp.h"
-#include "util.h"
-
-#define GFS2_SMALL_FH_SIZE 4
-#define GFS2_LARGE_FH_SIZE 8
-#define GFS2_OLD_FH_SIZE 10
-
-static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
-			  int connectable)
-{
-	__be32 *fh = (__force __be32 *)p;
-	struct inode *inode = dentry->d_inode;
-	struct super_block *sb = inode->i_sb;
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	if (*len < GFS2_SMALL_FH_SIZE ||
-	    (connectable && *len < GFS2_LARGE_FH_SIZE))
-		return 255;
-
-	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
-	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
-	fh[2] = cpu_to_be32(ip->i_no_addr >> 32);
-	fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
-	*len = GFS2_SMALL_FH_SIZE;
-
-	if (!connectable || inode == sb->s_root->d_inode)
-		return *len;
-
-	spin_lock(&dentry->d_lock);
-	inode = dentry->d_parent->d_inode;
-	ip = GFS2_I(inode);
-	igrab(inode);
-	spin_unlock(&dentry->d_lock);
-
-	fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32);
-	fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
-	fh[6] = cpu_to_be32(ip->i_no_addr >> 32);
-	fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
-	*len = GFS2_LARGE_FH_SIZE;
-
-	iput(inode);
-
-	return *len;
-}
-
-struct get_name_filldir {
-	struct gfs2_inum_host inum;
-	char *name;
-};
-
-static int get_name_filldir(void *opaque, const char *name, int length,
-			    loff_t offset, u64 inum, unsigned int type)
-{
-	struct get_name_filldir *gnfd = opaque;
-
-	if (inum != gnfd->inum.no_addr)
-		return 0;
-
-	memcpy(gnfd->name, name, length);
-	gnfd->name[length] = 0;
-
-	return 1;
-}
-
-static int gfs2_get_name(struct dentry *parent, char *name,
-			 struct dentry *child)
-{
-	struct inode *dir = parent->d_inode;
-	struct inode *inode = child->d_inode;
-	struct gfs2_inode *dip, *ip;
-	struct get_name_filldir gnfd;
-	struct gfs2_holder gh;
-	u64 offset = 0;
-	int error;
-
-	if (!dir)
-		return -EINVAL;
-
-	if (!S_ISDIR(dir->i_mode) || !inode)
-		return -EINVAL;
-
-	dip = GFS2_I(dir);
-	ip = GFS2_I(inode);
-
-	*name = 0;
-	gnfd.inum.no_addr = ip->i_no_addr;
-	gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
-	gnfd.name = name;
-
-	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
-	if (error)
-		return error;
-
-	error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
-
-	gfs2_glock_dq_uninit(&gh);
-
-	if (!error && !*name)
-		error = -ENOENT;
-
-	return error;
-}
-
-static struct dentry *gfs2_get_parent(struct dentry *child)
-{
-	struct qstr dotdot;
-	struct dentry *dentry;
-
-	/*
-	 * XXX(hch): it would be a good idea to keep this around as a
-	 *	     static variable.
-	 */
-	gfs2_str2qstr(&dotdot, "..");
-
-	dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &dotdot, 1));
-	if (!IS_ERR(dentry))
-		dentry->d_op = &gfs2_dops;
-	return dentry;
-}
-
-static struct dentry *gfs2_get_dentry(struct super_block *sb,
-		struct gfs2_inum_host *inum)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_holder i_gh, ri_gh, rgd_gh;
-	struct gfs2_rgrpd *rgd;
-	struct inode *inode;
-	struct dentry *dentry;
-	int error;
-
-	/* System files? */
-
-	inode = gfs2_ilookup(sb, inum->no_addr);
-	if (inode) {
-		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
-			iput(inode);
-			return ERR_PTR(-ESTALE);
-		}
-		goto out_inode;
-	}
-
-	error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
-				  LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
-	if (error)
-		return ERR_PTR(error);
-
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto fail;
-
-	error = -EINVAL;
-	rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
-	if (!rgd)
-		goto fail_rindex;
-
-	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
-	if (error)
-		goto fail_rindex;
-
-	error = -ESTALE;
-	if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
-		goto fail_rgd;
-
-	gfs2_glock_dq_uninit(&rgd_gh);
-	gfs2_glock_dq_uninit(&ri_gh);
-
-	inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
-					inum->no_addr,
-					0, 0);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		goto fail;
-	}
-
-	error = gfs2_inode_refresh(GFS2_I(inode));
-	if (error) {
-		iput(inode);
-		goto fail;
-	}
-
-	/* Pick up the works we bypass in gfs2_inode_lookup */
-	if (inode->i_state & I_NEW) 
-		gfs2_set_iop(inode);
-
-	if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
-		iput(inode);
-		goto fail;
-	}
-
-	error = -EIO;
-	if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM) {
-		iput(inode);
-		goto fail;
-	}
-
-	gfs2_glock_dq_uninit(&i_gh);
-
-out_inode:
-	dentry = d_obtain_alias(inode);
-	if (!IS_ERR(dentry))
-		dentry->d_op = &gfs2_dops;
-	return dentry;
-
-fail_rgd:
-	gfs2_glock_dq_uninit(&rgd_gh);
-
-fail_rindex:
-	gfs2_glock_dq_uninit(&ri_gh);
-
-fail:
-	gfs2_glock_dq_uninit(&i_gh);
-	return ERR_PTR(error);
-}
-
-static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	struct gfs2_inum_host this;
-	__be32 *fh = (__force __be32 *)fid->raw;
-
-	switch (fh_type) {
-	case GFS2_SMALL_FH_SIZE:
-	case GFS2_LARGE_FH_SIZE:
-	case GFS2_OLD_FH_SIZE:
-		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
-		this.no_formal_ino |= be32_to_cpu(fh[1]);
-		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
-		this.no_addr |= be32_to_cpu(fh[3]);
-		return gfs2_get_dentry(sb, &this);
-	default:
-		return NULL;
-	}
-}
-
-static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	struct gfs2_inum_host parent;
-	__be32 *fh = (__force __be32 *)fid->raw;
-
-	switch (fh_type) {
-	case GFS2_LARGE_FH_SIZE:
-	case GFS2_OLD_FH_SIZE:
-		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
-		parent.no_formal_ino |= be32_to_cpu(fh[5]);
-		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
-		parent.no_addr |= be32_to_cpu(fh[7]);
-		return gfs2_get_dentry(sb, &parent);
-	default:
-		return NULL;
-	}
-}
-
-const struct export_operations gfs2_export_ops = {
-	.encode_fh = gfs2_encode_fh,
-	.fh_to_dentry = gfs2_fh_to_dentry,
-	.fh_to_parent = gfs2_fh_to_parent,
-	.get_name = gfs2_get_name,
-	.get_parent = gfs2_get_parent,
-};
-
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
deleted file mode 100644
index 0ee7bd2..0000000
--- a/fs/gfs2/ops_file.c
+++ /dev/null
@@ -1,766 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/pagemap.h>
-#include <linux/uio.h>
-#include <linux/blkdev.h>
-#include <linux/mm.h>
-#include <linux/mount.h>
-#include <linux/fs.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/ext2_fs.h>
-#include <linux/crc32.h>
-#include <linux/writeback.h>
-#include <asm/uaccess.h>
-#include <linux/dlm.h>
-#include <linux/dlm_plock.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "bmap.h"
-#include "dir.h"
-#include "glock.h"
-#include "glops.h"
-#include "inode.h"
-#include "log.h"
-#include "meta_io.h"
-#include "quota.h"
-#include "rgrp.h"
-#include "trans.h"
-#include "util.h"
-#include "eaops.h"
-#include "ops_address.h"
-
-/**
- * gfs2_llseek - seek to a location in a file
- * @file: the file
- * @offset: the offset
- * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
- *
- * SEEK_END requires the glock for the file because it references the
- * file's size.
- *
- * Returns: The new offset, or errno
- */
-
-static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
-{
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_holder i_gh;
-	loff_t error;
-
-	if (origin == 2) {
-		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
-					   &i_gh);
-		if (!error) {
-			error = generic_file_llseek_unlocked(file, offset, origin);
-			gfs2_glock_dq_uninit(&i_gh);
-		}
-	} else
-		error = generic_file_llseek_unlocked(file, offset, origin);
-
-	return error;
-}
-
-/**
- * gfs2_readdir - Read directory entries from a directory
- * @file: The directory to read from
- * @dirent: Buffer for dirents
- * @filldir: Function used to do the copying
- *
- * Returns: errno
- */
-
-static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
-{
-	struct inode *dir = file->f_mapping->host;
-	struct gfs2_inode *dip = GFS2_I(dir);
-	struct gfs2_holder d_gh;
-	u64 offset = file->f_pos;
-	int error;
-
-	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
-	error = gfs2_glock_nq(&d_gh);
-	if (error) {
-		gfs2_holder_uninit(&d_gh);
-		return error;
-	}
-
-	error = gfs2_dir_read(dir, &offset, dirent, filldir);
-
-	gfs2_glock_dq_uninit(&d_gh);
-
-	file->f_pos = offset;
-
-	return error;
-}
-
-/**
- * fsflags_cvt
- * @table: A table of 32 u32 flags
- * @val: a 32 bit value to convert
- *
- * This function can be used to convert between fsflags values and
- * GFS2's own flags values.
- *
- * Returns: the converted flags
- */
-static u32 fsflags_cvt(const u32 *table, u32 val)
-{
-	u32 res = 0;
-	while(val) {
-		if (val & 1)
-			res |= *table;
-		table++;
-		val >>= 1;
-	}
-	return res;
-}
-
-static const u32 fsflags_to_gfs2[32] = {
-	[3] = GFS2_DIF_SYNC,
-	[4] = GFS2_DIF_IMMUTABLE,
-	[5] = GFS2_DIF_APPENDONLY,
-	[7] = GFS2_DIF_NOATIME,
-	[12] = GFS2_DIF_EXHASH,
-	[14] = GFS2_DIF_INHERIT_JDATA,
-};
-
-static const u32 gfs2_to_fsflags[32] = {
-	[gfs2fl_Sync] = FS_SYNC_FL,
-	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
-	[gfs2fl_AppendOnly] = FS_APPEND_FL,
-	[gfs2fl_NoAtime] = FS_NOATIME_FL,
-	[gfs2fl_ExHash] = FS_INDEX_FL,
-	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
-};
-
-static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
-{
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
-	int error;
-	u32 fsflags;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	error = gfs2_glock_nq(&gh);
-	if (error)
-		return error;
-
-	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
-	if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
-		fsflags |= FS_JOURNAL_DATA_FL;
-	if (put_user(fsflags, ptr))
-		error = -EFAULT;
-
-	gfs2_glock_dq(&gh);
-	gfs2_holder_uninit(&gh);
-	return error;
-}
-
-void gfs2_set_inode_flags(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	unsigned int flags = inode->i_flags;
-
-	flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
-	if (ip->i_diskflags & GFS2_DIF_IMMUTABLE)
-		flags |= S_IMMUTABLE;
-	if (ip->i_diskflags & GFS2_DIF_APPENDONLY)
-		flags |= S_APPEND;
-	if (ip->i_diskflags & GFS2_DIF_NOATIME)
-		flags |= S_NOATIME;
-	if (ip->i_diskflags & GFS2_DIF_SYNC)
-		flags |= S_SYNC;
-	inode->i_flags = flags;
-}
-
-/* Flags that can be set by user space */
-#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
-			     GFS2_DIF_IMMUTABLE|		\
-			     GFS2_DIF_APPENDONLY|		\
-			     GFS2_DIF_NOATIME|			\
-			     GFS2_DIF_SYNC|			\
-			     GFS2_DIF_SYSTEM|			\
-			     GFS2_DIF_INHERIT_JDATA)
-
-/**
- * gfs2_set_flags - set flags on an inode
- * @inode: The inode
- * @flags: The flags to set
- * @mask: Indicates which flags are valid
- *
- */
-static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
-{
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct buffer_head *bh;
-	struct gfs2_holder gh;
-	int error;
-	u32 new_flags, flags;
-
-	error = mnt_want_write(filp->f_path.mnt);
-	if (error)
-		return error;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (error)
-		goto out_drop_write;
-
-	flags = ip->i_diskflags;
-	new_flags = (flags & ~mask) | (reqflags & mask);
-	if ((new_flags ^ flags) == 0)
-		goto out;
-
-	error = -EINVAL;
-	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
-		goto out;
-
-	error = -EPERM;
-	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
-		goto out;
-	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
-		goto out;
-	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
-	    !capable(CAP_LINUX_IMMUTABLE))
-		goto out;
-	if (!IS_IMMUTABLE(inode)) {
-		error = gfs2_permission(inode, MAY_WRITE);
-		if (error)
-			goto out;
-	}
-	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
-		if (flags & GFS2_DIF_JDATA)
-			gfs2_log_flush(sdp, ip->i_gl);
-		error = filemap_fdatawrite(inode->i_mapping);
-		if (error)
-			goto out;
-		error = filemap_fdatawait(inode->i_mapping);
-		if (error)
-			goto out;
-	}
-	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (error)
-		goto out;
-	error = gfs2_meta_inode_buffer(ip, &bh);
-	if (error)
-		goto out_trans_end;
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
-	ip->i_diskflags = new_flags;
-	gfs2_dinode_out(ip, bh->b_data);
-	brelse(bh);
-	gfs2_set_inode_flags(inode);
-	gfs2_set_aops(inode);
-out_trans_end:
-	gfs2_trans_end(sdp);
-out:
-	gfs2_glock_dq_uninit(&gh);
-out_drop_write:
-	mnt_drop_write(filp->f_path.mnt);
-	return error;
-}
-
-static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
-{
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	u32 fsflags, gfsflags;
-	if (get_user(fsflags, ptr))
-		return -EFAULT;
-	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
-	if (!S_ISDIR(inode->i_mode)) {
-		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
-			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
-		return do_gfs2_set_flags(filp, gfsflags, ~0);
-	}
-	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
-}
-
-static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
-	switch(cmd) {
-	case FS_IOC_GETFLAGS:
-		return gfs2_get_flags(filp, (u32 __user *)arg);
-	case FS_IOC_SETFLAGS:
-		return gfs2_set_flags(filp, (u32 __user *)arg);
-	}
-	return -ENOTTY;
-}
-
-/**
- * gfs2_allocate_page_backing - Use bmap to allocate blocks
- * @page: The (locked) page to allocate backing for
- *
- * We try to allocate all the blocks required for the page in
- * one go. This might fail for various reasons, so we keep
- * trying until all the blocks to back this page are allocated.
- * If some of the blocks are already allocated, thats ok too.
- */
-
-static int gfs2_allocate_page_backing(struct page *page)
-{
-	struct inode *inode = page->mapping->host;
-	struct buffer_head bh;
-	unsigned long size = PAGE_CACHE_SIZE;
-	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
-	do {
-		bh.b_state = 0;
-		bh.b_size = size;
-		gfs2_block_map(inode, lblock, &bh, 1);
-		if (!buffer_mapped(&bh))
-			return -EIO;
-		size -= bh.b_size;
-		lblock += (bh.b_size >> inode->i_blkbits);
-	} while(size > 0);
-	return 0;
-}
-
-/**
- * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
- * @vma: The virtual memory area
- * @page: The page which is about to become writable
- *
- * When the page becomes writable, we need to ensure that we have
- * blocks allocated on disk to back that page.
- */
-
-static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *page = vmf->page;
-	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	unsigned long last_index;
-	u64 pos = page->index << PAGE_CACHE_SHIFT;
-	unsigned int data_blocks, ind_blocks, rblocks;
-	int alloc_required = 0;
-	struct gfs2_holder gh;
-	struct gfs2_alloc *al;
-	int ret;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	ret = gfs2_glock_nq(&gh);
-	if (ret)
-		goto out;
-
-	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
-	set_bit(GIF_SW_PAGED, &ip->i_flags);
-
-	ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
-	if (ret || !alloc_required)
-		goto out_unlock;
-	ret = -ENOMEM;
-	al = gfs2_alloc_get(ip);
-	if (al == NULL)
-		goto out_unlock;
-
-	ret = gfs2_quota_lock_check(ip);
-	if (ret)
-		goto out_alloc_put;
-	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
-	al->al_requested = data_blocks + ind_blocks;
-	ret = gfs2_inplace_reserve(ip);
-	if (ret)
-		goto out_quota_unlock;
-
-	rblocks = RES_DINODE + ind_blocks;
-	if (gfs2_is_jdata(ip))
-		rblocks += data_blocks ? data_blocks : 1;
-	if (ind_blocks || data_blocks)
-		rblocks += RES_STATFS + RES_QUOTA;
-	ret = gfs2_trans_begin(sdp, rblocks, 0);
-	if (ret)
-		goto out_trans_fail;
-
-	lock_page(page);
-	ret = -EINVAL;
-	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
-	if (page->index > last_index)
-		goto out_unlock_page;
-	ret = 0;
-	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
-		goto out_unlock_page;
-	if (gfs2_is_stuffed(ip)) {
-		ret = gfs2_unstuff_dinode(ip, page);
-		if (ret)
-			goto out_unlock_page;
-	}
-	ret = gfs2_allocate_page_backing(page);
-
-out_unlock_page:
-	unlock_page(page);
-	gfs2_trans_end(sdp);
-out_trans_fail:
-	gfs2_inplace_release(ip);
-out_quota_unlock:
-	gfs2_quota_unlock(ip);
-out_alloc_put:
-	gfs2_alloc_put(ip);
-out_unlock:
-	gfs2_glock_dq(&gh);
-out:
-	gfs2_holder_uninit(&gh);
-	if (ret == -ENOMEM)
-		ret = VM_FAULT_OOM;
-	else if (ret)
-		ret = VM_FAULT_SIGBUS;
-	return ret;
-}
-
-static struct vm_operations_struct gfs2_vm_ops = {
-	.fault = filemap_fault,
-	.page_mkwrite = gfs2_page_mkwrite,
-};
-
-/**
- * gfs2_mmap -
- * @file: The file to map
- * @vma: The VMA which described the mapping
- *
- * There is no need to get a lock here unless we should be updating
- * atime. We ignore any locking errors since the only consequence is
- * a missed atime update (which will just be deferred until later).
- *
- * Returns: 0
- */
-
-static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-
-	if (!(file->f_flags & O_NOATIME)) {
-		struct gfs2_holder i_gh;
-		int error;
-
-		gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
-		error = gfs2_glock_nq(&i_gh);
-		file_accessed(file);
-		if (error == 0)
-			gfs2_glock_dq_uninit(&i_gh);
-	}
-	vma->vm_ops = &gfs2_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
-
-	return 0;
-}
-
-/**
- * gfs2_open - open a file
- * @inode: the inode to open
- * @file: the struct file for this opening
- *
- * Returns: errno
- */
-
-static int gfs2_open(struct inode *inode, struct file *file)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder i_gh;
-	struct gfs2_file *fp;
-	int error;
-
-	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
-	if (!fp)
-		return -ENOMEM;
-
-	mutex_init(&fp->f_fl_mutex);
-
-	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
-	file->private_data = fp;
-
-	if (S_ISREG(ip->i_inode.i_mode)) {
-		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
-					   &i_gh);
-		if (error)
-			goto fail;
-
-		if (!(file->f_flags & O_LARGEFILE) &&
-		    ip->i_disksize > MAX_NON_LFS) {
-			error = -EOVERFLOW;
-			goto fail_gunlock;
-		}
-
-		gfs2_glock_dq_uninit(&i_gh);
-	}
-
-	return 0;
-
-fail_gunlock:
-	gfs2_glock_dq_uninit(&i_gh);
-fail:
-	file->private_data = NULL;
-	kfree(fp);
-	return error;
-}
-
-/**
- * gfs2_close - called to close a struct file
- * @inode: the inode the struct file belongs to
- * @file: the struct file being closed
- *
- * Returns: errno
- */
-
-static int gfs2_close(struct inode *inode, struct file *file)
-{
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_file *fp;
-
-	fp = file->private_data;
-	file->private_data = NULL;
-
-	if (gfs2_assert_warn(sdp, fp))
-		return -EIO;
-
-	kfree(fp);
-
-	return 0;
-}
-
-/**
- * gfs2_fsync - sync the dirty data for a file (across the cluster)
- * @file: the file that points to the dentry (we ignore this)
- * @dentry: the dentry that points to the inode to sync
- *
- * The VFS will flush "normal" data for us. We only need to worry
- * about metadata here. For journaled data, we just do a log flush
- * as we can't avoid it. Otherwise we can just bale out if datasync
- * is set. For stuffed inodes we must flush the log in order to
- * ensure that all data is on disk.
- *
- * The call to write_inode_now() is there to write back metadata and
- * the inode itself. It does also try and write the data, but thats
- * (hopefully) a no-op due to the VFS having already called filemap_fdatawrite()
- * for us.
- *
- * Returns: errno
- */
-
-static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
-	int ret = 0;
-
-	if (gfs2_is_jdata(GFS2_I(inode))) {
-		gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
-		return 0;
-	}
-
-	if (sync_state != 0) {
-		if (!datasync)
-			ret = write_inode_now(inode, 0);
-
-		if (gfs2_is_stuffed(GFS2_I(inode)))
-			gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
-	}
-
-	return ret;
-}
-
-#ifdef CONFIG_GFS2_FS_LOCKING_DLM
-
-/**
- * gfs2_setlease - acquire/release a file lease
- * @file: the file pointer
- * @arg: lease type
- * @fl: file lock
- *
- * We don't currently have a way to enforce a lease across the whole
- * cluster; until we do, disable leases (by just returning -EINVAL),
- * unless the administrator has requested purely local locking.
- *
- * Returns: errno
- */
-
-static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	return -EINVAL;
-}
-
-/**
- * gfs2_lock - acquire/release a posix lock on a file
- * @file: the file pointer
- * @cmd: either modify or retrieve lock state, possibly wait
- * @fl: type and range of lock
- *
- * Returns: errno
- */
-
-static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
-{
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
-	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-
-	if (!(fl->fl_flags & FL_POSIX))
-		return -ENOLCK;
-	if (__mandatory_lock(&ip->i_inode))
-		return -ENOLCK;
-
-	if (cmd == F_CANCELLK) {
-		/* Hack: */
-		cmd = F_SETLK;
-		fl->fl_type = F_UNLCK;
-	}
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-		return -EIO;
-	if (IS_GETLK(cmd))
-		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
-	else if (fl->fl_type == F_UNLCK)
-		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
-	else
-		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
-}
-
-static int do_flock(struct file *file, int cmd, struct file_lock *fl)
-{
-	struct gfs2_file *fp = file->private_data;
-	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
-	struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
-	struct gfs2_glock *gl;
-	unsigned int state;
-	int flags;
-	int error = 0;
-
-	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
-
-	mutex_lock(&fp->f_fl_mutex);
-
-	gl = fl_gh->gh_gl;
-	if (gl) {
-		if (fl_gh->gh_state == state)
-			goto out;
-		flock_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_wait(fl_gh);
-		gfs2_holder_reinit(state, flags, fl_gh);
-	} else {
-		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
-				       &gfs2_flock_glops, CREATE, &gl);
-		if (error)
-			goto out;
-		gfs2_holder_init(gl, state, flags, fl_gh);
-		gfs2_glock_put(gl);
-	}
-	error = gfs2_glock_nq(fl_gh);
-	if (error) {
-		gfs2_holder_uninit(fl_gh);
-		if (error == GLR_TRYFAILED)
-			error = -EAGAIN;
-	} else {
-		error = flock_lock_file_wait(file, fl);
-		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
-	}
-
-out:
-	mutex_unlock(&fp->f_fl_mutex);
-	return error;
-}
-
-static void do_unflock(struct file *file, struct file_lock *fl)
-{
-	struct gfs2_file *fp = file->private_data;
-	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
-
-	mutex_lock(&fp->f_fl_mutex);
-	flock_lock_file_wait(file, fl);
-	if (fl_gh->gh_gl)
-		gfs2_glock_dq_uninit(fl_gh);
-	mutex_unlock(&fp->f_fl_mutex);
-}
-
-/**
- * gfs2_flock - acquire/release a flock lock on a file
- * @file: the file pointer
- * @cmd: either modify or retrieve lock state, possibly wait
- * @fl: type and range of lock
- *
- * Returns: errno
- */
-
-static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
-{
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-
-	if (!(fl->fl_flags & FL_FLOCK))
-		return -ENOLCK;
-	if (__mandatory_lock(&ip->i_inode))
-		return -ENOLCK;
-
-	if (fl->fl_type == F_UNLCK) {
-		do_unflock(file, fl);
-		return 0;
-	} else {
-		return do_flock(file, cmd, fl);
-	}
-}
-
-const struct file_operations gfs2_file_fops = {
-	.llseek		= gfs2_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
-	.unlocked_ioctl	= gfs2_ioctl,
-	.mmap		= gfs2_mmap,
-	.open		= gfs2_open,
-	.release	= gfs2_close,
-	.fsync		= gfs2_fsync,
-	.lock		= gfs2_lock,
-	.flock		= gfs2_flock,
-	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
-	.setlease	= gfs2_setlease,
-};
-
-const struct file_operations gfs2_dir_fops = {
-	.readdir	= gfs2_readdir,
-	.unlocked_ioctl	= gfs2_ioctl,
-	.open		= gfs2_open,
-	.release	= gfs2_close,
-	.fsync		= gfs2_fsync,
-	.lock		= gfs2_lock,
-	.flock		= gfs2_flock,
-};
-
-#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
-
-const struct file_operations gfs2_file_fops_nolock = {
-	.llseek		= gfs2_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
-	.unlocked_ioctl	= gfs2_ioctl,
-	.mmap		= gfs2_mmap,
-	.open		= gfs2_open,
-	.release	= gfs2_close,
-	.fsync		= gfs2_fsync,
-	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
-	.setlease	= generic_setlease,
-};
-
-const struct file_operations gfs2_dir_fops_nolock = {
-	.readdir	= gfs2_readdir,
-	.unlocked_ioctl	= gfs2_ioctl,
-	.open		= gfs2_open,
-	.release	= gfs2_close,
-	.fsync		= gfs2_fsync,
-};
-
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 152e6c4..2e9b932 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -60,7 +60,6 @@
 #include "super.h"
 #include "trans.h"
 #include "inode.h"
-#include "ops_address.h"
 #include "util.h"
 
 #define QUOTA_USER 1
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ee3d5c1..6122c7e 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -29,7 +29,6 @@
 #include "util.h"
 #include "log.h"
 #include "inode.h"
-#include "ops_address.h"
 
 #define BFITNOENT ((u32)~0)
 #define NO_BLOCK ((u64)~0)
-- 
1.6.0.6

[Cluster-devel] [PATCH 15/24] GFS2: Merge mount.c and ops_super.c into super.c

[Steven Whitehouse]

mount.c only contained a single function, so is not really
worth retaining on its own. All of the super related code
is now either in super.c or ops_fstype.c

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index 4f7332c..d53a9be 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
 	glops.o inode.o log.o lops.o main.o meta_io.o \
-	mount.o aops.o dentry.o export.o file.o \
-	ops_fstype.o ops_inode.o ops_super.o quota.o \
+	aops.o dentry.o export.o file.o \
+	ops_fstype.o ops_inode.o quota.o \
 	recovery.o rgrp.o super.o sys.o trans.o util.o
 
 gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
deleted file mode 100644
index 947af15..0000000
--- a/fs/gfs2/mount.c
+++ /dev/null
@@ -1,195 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/parser.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "super.h"
-#include "sys.h"
-#include "util.h"
-
-enum {
-	Opt_lockproto,
-	Opt_locktable,
-	Opt_hostdata,
-	Opt_spectator,
-	Opt_ignore_local_fs,
-	Opt_localflocks,
-	Opt_localcaching,
-	Opt_debug,
-	Opt_nodebug,
-	Opt_upgrade,
-	Opt_acl,
-	Opt_noacl,
-	Opt_quota_off,
-	Opt_quota_account,
-	Opt_quota_on,
-	Opt_quota,
-	Opt_noquota,
-	Opt_suiddir,
-	Opt_nosuiddir,
-	Opt_data_writeback,
-	Opt_data_ordered,
-	Opt_meta,
-	Opt_discard,
-	Opt_nodiscard,
-	Opt_commit,
-	Opt_err,
-};
-
-static const match_table_t tokens = {
-	{Opt_lockproto, "lockproto=%s"},
-	{Opt_locktable, "locktable=%s"},
-	{Opt_hostdata, "hostdata=%s"},
-	{Opt_spectator, "spectator"},
-	{Opt_ignore_local_fs, "ignore_local_fs"},
-	{Opt_localflocks, "localflocks"},
-	{Opt_localcaching, "localcaching"},
-	{Opt_debug, "debug"},
-	{Opt_nodebug, "nodebug"},
-	{Opt_upgrade, "upgrade"},
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_quota_off, "quota=off"},
-	{Opt_quota_account, "quota=account"},
-	{Opt_quota_on, "quota=on"},
-	{Opt_quota, "quota"},
-	{Opt_noquota, "noquota"},
-	{Opt_suiddir, "suiddir"},
-	{Opt_nosuiddir, "nosuiddir"},
-	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"},
-	{Opt_meta, "meta"},
-	{Opt_discard, "discard"},
-	{Opt_nodiscard, "nodiscard"},
-	{Opt_commit, "commit=%d"},
-	{Opt_err, NULL}
-};
-
-/**
- * gfs2_mount_args - Parse mount options
- * @sdp:
- * @data:
- *
- * Return: errno
- */
-
-int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
-{
-	char *o;
-	int token;
-	substring_t tmp[MAX_OPT_ARGS];
-	int rv;
-
-	/* Split the options into tokens with the "," character and
-	   process them */
-
-	while (1) {
-		o = strsep(&options, ",");
-		if (o == NULL)
-			break;
-		if (*o == '\0')
-			continue;
-
-		token = match_token(o, tokens, tmp);
-		switch (token) {
-		case Opt_lockproto:
-			match_strlcpy(args->ar_lockproto, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_locktable:
-			match_strlcpy(args->ar_locktable, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_hostdata:
-			match_strlcpy(args->ar_hostdata, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_spectator:
-			args->ar_spectator = 1;
-			break;
-		case Opt_ignore_local_fs:
-			args->ar_ignore_local_fs = 1;
-			break;
-		case Opt_localflocks:
-			args->ar_localflocks = 1;
-			break;
-		case Opt_localcaching:
-			args->ar_localcaching = 1;
-			break;
-		case Opt_debug:
-			args->ar_debug = 1;
-			break;
-		case Opt_nodebug:
-			args->ar_debug = 0;
-			break;
-		case Opt_upgrade:
-			args->ar_upgrade = 1;
-			break;
-		case Opt_acl:
-			args->ar_posix_acl = 1;
-			break;
-		case Opt_noacl:
-			args->ar_posix_acl = 0;
-			break;
-		case Opt_quota_off:
-		case Opt_noquota:
-			args->ar_quota = GFS2_QUOTA_OFF;
-			break;
-		case Opt_quota_account:
-			args->ar_quota = GFS2_QUOTA_ACCOUNT;
-			break;
-		case Opt_quota_on:
-		case Opt_quota:
-			args->ar_quota = GFS2_QUOTA_ON;
-			break;
-		case Opt_suiddir:
-			args->ar_suiddir = 1;
-			break;
-		case Opt_nosuiddir:
-			args->ar_suiddir = 0;
-			break;
-		case Opt_data_writeback:
-			args->ar_data = GFS2_DATA_WRITEBACK;
-			break;
-		case Opt_data_ordered:
-			args->ar_data = GFS2_DATA_ORDERED;
-			break;
-		case Opt_meta:
-			args->ar_meta = 1;
-			break;
-		case Opt_discard:
-			args->ar_discard = 1;
-			break;
-		case Opt_nodiscard:
-			args->ar_discard = 0;
-			break;
-		case Opt_commit:
-			rv = match_int(&tmp[0], &args->ar_commit);
-			if (rv || args->ar_commit <= 0) {
-				fs_info(sdp, "commit mount option requires a positive numeric argument\n");
-				return rv ? rv : -EINVAL;
-			}
-			break;
-		case Opt_err:
-		default:
-			fs_info(sdp, "invalid mount option: %s\n", o);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
deleted file mode 100644
index 2fd1dcb..0000000
--- a/fs/gfs2/ops_super.c
+++ /dev/null
@@ -1,757 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/statfs.h>
-#include <linux/seq_file.h>
-#include <linux/mount.h>
-#include <linux/kthread.h>
-#include <linux/delay.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/crc32.h>
-#include <linux/time.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "glock.h"
-#include "inode.h"
-#include "log.h"
-#include "quota.h"
-#include "recovery.h"
-#include "rgrp.h"
-#include "super.h"
-#include "sys.h"
-#include "util.h"
-#include "trans.h"
-#include "dir.h"
-#include "eattr.h"
-#include "bmap.h"
-#include "meta_io.h"
-
-#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
-
-/**
- * gfs2_write_inode - Make sure the inode is stable on the disk
- * @inode: The inode
- * @sync: synchronous write flag
- *
- * Returns: errno
- */
-
-static int gfs2_write_inode(struct inode *inode, int sync)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_holder gh;
-	struct buffer_head *bh;
-	struct timespec atime;
-	struct gfs2_dinode *di;
-	int ret = 0;
-
-	/* Check this is a "normal" inode, etc */
-	if (!test_bit(GIF_USER, &ip->i_flags) ||
-	    (current->flags & PF_MEMALLOC))
-		return 0;
-	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (ret)
-		goto do_flush;
-	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (ret)
-		goto do_unlock;
-	ret = gfs2_meta_inode_buffer(ip, &bh);
-	if (ret == 0) {
-		di = (struct gfs2_dinode *)bh->b_data;
-		atime.tv_sec = be64_to_cpu(di->di_atime);
-		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
-		if (timespec_compare(&inode->i_atime, &atime) > 0) {
-			gfs2_trans_add_bh(ip->i_gl, bh, 1);
-			gfs2_dinode_out(ip, bh->b_data);
-		}
-		brelse(bh);
-	}
-	gfs2_trans_end(sdp);
-do_unlock:
-	gfs2_glock_dq_uninit(&gh);
-do_flush:
-	if (sync != 0)
-		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
-	return ret;
-}
-
-/**
- * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
- * @sdp: the filesystem
- *
- * Returns: errno
- */
-
-static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
-{
-	struct gfs2_holder t_gh;
-	int error;
-
-	gfs2_quota_sync(sdp);
-	gfs2_statfs_sync(sdp);
-
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
-				   &t_gh);
-	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return error;
-
-	gfs2_meta_syncfs(sdp);
-	gfs2_log_shutdown(sdp);
-
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-
-	if (t_gh.gh_gl)
-		gfs2_glock_dq_uninit(&t_gh);
-
-	gfs2_quota_cleanup(sdp);
-
-	return error;
-}
-
-static int gfs2_umount_recovery_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
-/**
- * gfs2_put_super - Unmount the filesystem
- * @sb: The VFS superblock
- *
- */
-
-static void gfs2_put_super(struct super_block *sb)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error;
-	struct gfs2_jdesc *jd;
-
-	/*  Unfreeze the filesystem, if we need to  */
-
-	mutex_lock(&sdp->sd_freeze_lock);
-	if (sdp->sd_freeze_count)
-		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
-	mutex_unlock(&sdp->sd_freeze_lock);
-
-	/* No more recovery requests */
-	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
-	smp_mb();
-
-	/* Wait on outstanding recovery */
-restart:
-	spin_lock(&sdp->sd_jindex_spin);
-	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
-		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
-			continue;
-		spin_unlock(&sdp->sd_jindex_spin);
-		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
-			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
-		goto restart;
-	}
-	spin_unlock(&sdp->sd_jindex_spin);
-
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
-
-	if (!(sb->s_flags & MS_RDONLY)) {
-		error = gfs2_make_fs_ro(sdp);
-		if (error)
-			gfs2_io_error(sdp);
-	}
-	/*  At this point, we're through modifying the disk  */
-
-	/*  Release stuff  */
-
-	iput(sdp->sd_jindex);
-	iput(sdp->sd_inum_inode);
-	iput(sdp->sd_statfs_inode);
-	iput(sdp->sd_rindex);
-	iput(sdp->sd_quota_inode);
-
-	gfs2_glock_put(sdp->sd_rename_gl);
-	gfs2_glock_put(sdp->sd_trans_gl);
-
-	if (!sdp->sd_args.ar_spectator) {
-		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
-		iput(sdp->sd_ir_inode);
-		iput(sdp->sd_sc_inode);
-		iput(sdp->sd_qc_inode);
-	}
-
-	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
-	gfs2_clear_rgrpd(sdp);
-	gfs2_jindex_free(sdp);
-	/*  Take apart glock structures and buffer lists  */
-	gfs2_gl_hash_clear(sdp);
-	/*  Unmount the locking protocol  */
-	gfs2_lm_unmount(sdp);
-
-	/*  At this point, we're through participating in the lockspace  */
-	gfs2_sys_fs_del(sdp);
-}
-
-/**
- * gfs2_write_super
- * @sb: the superblock
- *
- */
-
-static void gfs2_write_super(struct super_block *sb)
-{
-	sb->s_dirt = 0;
-}
-
-/**
- * gfs2_sync_fs - sync the filesystem
- * @sb: the superblock
- *
- * Flushes the log to disk.
- */
-
-static int gfs2_sync_fs(struct super_block *sb, int wait)
-{
-	sb->s_dirt = 0;
-	if (wait && sb->s_fs_info)
-		gfs2_log_flush(sb->s_fs_info, NULL);
-	return 0;
-}
-
-/**
- * gfs2_freeze - prevent further writes to the filesystem
- * @sb: the VFS structure for the filesystem
- *
- */
-
-static int gfs2_freeze(struct super_block *sb)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error;
-
-	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return -EINVAL;
-
-	for (;;) {
-		error = gfs2_freeze_fs(sdp);
-		if (!error)
-			break;
-
-		switch (error) {
-		case -EBUSY:
-			fs_err(sdp, "waiting for recovery before freeze\n");
-			break;
-
-		default:
-			fs_err(sdp, "error freezing FS: %d\n", error);
-			break;
-		}
-
-		fs_err(sdp, "retrying...\n");
-		msleep(1000);
-	}
-	return 0;
-}
-
-/**
- * gfs2_unfreeze - reallow writes to the filesystem
- * @sb: the VFS structure for the filesystem
- *
- */
-
-static int gfs2_unfreeze(struct super_block *sb)
-{
-	gfs2_unfreeze_fs(sb->s_fs_info);
-	return 0;
-}
-
-/**
- * statfs_fill - fill in the sg for a given RG
- * @rgd: the RG
- * @sc: the sc structure
- *
- * Returns: 0 on success, -ESTALE if the LVB is invalid
- */
-
-static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
-			    struct gfs2_statfs_change_host *sc)
-{
-	gfs2_rgrp_verify(rgd);
-	sc->sc_total += rgd->rd_data;
-	sc->sc_free += rgd->rd_free;
-	sc->sc_dinodes += rgd->rd_dinodes;
-	return 0;
-}
-
-/**
- * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
- * @sdp: the filesystem
- * @sc: the sc info that will be returned
- *
- * Any error (other than a signal) will cause this routine to fall back
- * to the synchronous version.
- *
- * FIXME: This really shouldn't busy wait like this.
- *
- * Returns: errno
- */
-
-static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
-{
-	struct gfs2_holder ri_gh;
-	struct gfs2_rgrpd *rgd_next;
-	struct gfs2_holder *gha, *gh;
-	unsigned int slots = 64;
-	unsigned int x;
-	int done;
-	int error = 0, err;
-
-	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
-	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
-	if (!gha)
-		return -ENOMEM;
-
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto out;
-
-	rgd_next = gfs2_rgrpd_get_first(sdp);
-
-	for (;;) {
-		done = 1;
-
-		for (x = 0; x < slots; x++) {
-			gh = gha + x;
-
-			if (gh->gh_gl && gfs2_glock_poll(gh)) {
-				err = gfs2_glock_wait(gh);
-				if (err) {
-					gfs2_holder_uninit(gh);
-					error = err;
-				} else {
-					if (!error)
-						error = statfs_slow_fill(
-							gh->gh_gl->gl_object, sc);
-					gfs2_glock_dq_uninit(gh);
-				}
-			}
-
-			if (gh->gh_gl)
-				done = 0;
-			else if (rgd_next && !error) {
-				error = gfs2_glock_nq_init(rgd_next->rd_gl,
-							   LM_ST_SHARED,
-							   GL_ASYNC,
-							   gh);
-				rgd_next = gfs2_rgrpd_get_next(rgd_next);
-				done = 0;
-			}
-
-			if (signal_pending(current))
-				error = -ERESTARTSYS;
-		}
-
-		if (done)
-			break;
-
-		yield();
-	}
-
-	gfs2_glock_dq_uninit(&ri_gh);
-
-out:
-	kfree(gha);
-	return error;
-}
-
-/**
- * gfs2_statfs_i - Do a statfs
- * @sdp: the filesystem
- * @sg: the sg structure
- *
- * Returns: errno
- */
-
-static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
-{
-	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
-	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
-
-	spin_lock(&sdp->sd_statfs_spin);
-
-	*sc = *m_sc;
-	sc->sc_total += l_sc->sc_total;
-	sc->sc_free += l_sc->sc_free;
-	sc->sc_dinodes += l_sc->sc_dinodes;
-
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	if (sc->sc_free < 0)
-		sc->sc_free = 0;
-	if (sc->sc_free > sc->sc_total)
-		sc->sc_free = sc->sc_total;
-	if (sc->sc_dinodes < 0)
-		sc->sc_dinodes = 0;
-
-	return 0;
-}
-
-/**
- * gfs2_statfs - Gather and return stats about the filesystem
- * @sb: The superblock
- * @statfsbuf: The buffer
- *
- * Returns: 0 on success or error code
- */
-
-static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
-{
-	struct super_block *sb = dentry->d_inode->i_sb;
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_statfs_change_host sc;
-	int error;
-
-	if (gfs2_tune_get(sdp, gt_statfs_slow))
-		error = gfs2_statfs_slow(sdp, &sc);
-	else
-		error = gfs2_statfs_i(sdp, &sc);
-
-	if (error)
-		return error;
-
-	buf->f_type = GFS2_MAGIC;
-	buf->f_bsize = sdp->sd_sb.sb_bsize;
-	buf->f_blocks = sc.sc_total;
-	buf->f_bfree = sc.sc_free;
-	buf->f_bavail = sc.sc_free;
-	buf->f_files = sc.sc_dinodes + sc.sc_free;
-	buf->f_ffree = sc.sc_free;
-	buf->f_namelen = GFS2_FNAMESIZE;
-
-	return 0;
-}
-
-/**
- * gfs2_remount_fs - called when the FS is remounted
- * @sb:  the filesystem
- * @flags:  the remount flags
- * @data:  extra data passed in (not used right now)
- *
- * Returns: errno
- */
-
-static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
-	struct gfs2_tune *gt = &sdp->sd_tune;
-	int error;
-
-	spin_lock(&gt->gt_spin);
-	args.ar_commit = gt->gt_log_flush_secs;
-	spin_unlock(&gt->gt_spin);
-	error = gfs2_mount_args(sdp, &args, data);
-	if (error)
-		return error;
-
-	/* Not allowed to change locking details */
-	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
-	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
-	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
-		return -EINVAL;
-
-	/* Some flags must not be changed */
-	if (args_neq(&args, &sdp->sd_args, spectator) ||
-	    args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
-	    args_neq(&args, &sdp->sd_args, localflocks) ||
-	    args_neq(&args, &sdp->sd_args, localcaching) ||
-	    args_neq(&args, &sdp->sd_args, meta))
-		return -EINVAL;
-
-	if (sdp->sd_args.ar_spectator)
-		*flags |= MS_RDONLY;
-
-	if ((sb->s_flags ^ *flags) & MS_RDONLY) {
-		if (*flags & MS_RDONLY)
-			error = gfs2_make_fs_ro(sdp);
-		else
-			error = gfs2_make_fs_rw(sdp);
-		if (error)
-			return error;
-	}
-
-	sdp->sd_args = args;
-	if (sdp->sd_args.ar_posix_acl)
-		sb->s_flags |= MS_POSIXACL;
-	else
-		sb->s_flags &= ~MS_POSIXACL;
-	spin_lock(&gt->gt_spin);
-	gt->gt_log_flush_secs = args.ar_commit;
-	spin_unlock(&gt->gt_spin);
-
-	return 0;
-}
-
-/**
- * gfs2_drop_inode - Drop an inode (test for remote unlink)
- * @inode: The inode to drop
- *
- * If we've received a callback on an iopen lock then its because a
- * remote node tried to deallocate the inode but failed due to this node
- * still having the inode open. Here we mark the link count zero
- * since we know that it must have reached zero if the GLF_DEMOTE flag
- * is set on the iopen glock. If we didn't do a disk read since the
- * remote node removed the final link then we might otherwise miss
- * this event. This check ensures that this node will deallocate the
- * inode's blocks, or alternatively pass the baton on to another
- * node for later deallocation.
- */
-
-static void gfs2_drop_inode(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) {
-		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
-		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
-			clear_nlink(inode);
-	}
-	generic_drop_inode(inode);
-}
-
-/**
- * gfs2_clear_inode - Deallocate an inode when VFS is done with it
- * @inode: The VFS inode
- *
- */
-
-static void gfs2_clear_inode(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	/* This tells us its a "real" inode and not one which only
-	 * serves to contain an address space (see rgrp.c, meta_io.c)
-	 * which therefore doesn't have its own glocks.
-	 */
-	if (test_bit(GIF_USER, &ip->i_flags)) {
-		ip->i_gl->gl_object = NULL;
-		gfs2_glock_put(ip->i_gl);
-		ip->i_gl = NULL;
-		if (ip->i_iopen_gh.gh_gl) {
-			ip->i_iopen_gh.gh_gl->gl_object = NULL;
-			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		}
-	}
-}
-
-static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
-{
-	do {
-		if (d1 == d2)
-			return 1;
-		d1 = d1->d_parent;
-	} while (!IS_ROOT(d1));
-	return 0;
-}
-
-/**
- * gfs2_show_options - Show mount options for /proc/mounts
- * @s: seq_file structure
- * @mnt: vfsmount
- *
- * Returns: 0 on success or error code
- */
-
-static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
-{
-	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
-	struct gfs2_args *args = &sdp->sd_args;
-	int lfsecs;
-
-	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
-		seq_printf(s, ",meta");
-	if (args->ar_lockproto[0])
-		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
-	if (args->ar_locktable[0])
-		seq_printf(s, ",locktable=%s", args->ar_locktable);
-	if (args->ar_hostdata[0])
-		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
-	if (args->ar_spectator)
-		seq_printf(s, ",spectator");
-	if (args->ar_ignore_local_fs)
-		seq_printf(s, ",ignore_local_fs");
-	if (args->ar_localflocks)
-		seq_printf(s, ",localflocks");
-	if (args->ar_localcaching)
-		seq_printf(s, ",localcaching");
-	if (args->ar_debug)
-		seq_printf(s, ",debug");
-	if (args->ar_upgrade)
-		seq_printf(s, ",upgrade");
-	if (args->ar_posix_acl)
-		seq_printf(s, ",acl");
-	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
-		char *state;
-		switch (args->ar_quota) {
-		case GFS2_QUOTA_OFF:
-			state = "off";
-			break;
-		case GFS2_QUOTA_ACCOUNT:
-			state = "account";
-			break;
-		case GFS2_QUOTA_ON:
-			state = "on";
-			break;
-		default:
-			state = "unknown";
-			break;
-		}
-		seq_printf(s, ",quota=%s", state);
-	}
-	if (args->ar_suiddir)
-		seq_printf(s, ",suiddir");
-	if (args->ar_data != GFS2_DATA_DEFAULT) {
-		char *state;
-		switch (args->ar_data) {
-		case GFS2_DATA_WRITEBACK:
-			state = "writeback";
-			break;
-		case GFS2_DATA_ORDERED:
-			state = "ordered";
-			break;
-		default:
-			state = "unknown";
-			break;
-		}
-		seq_printf(s, ",data=%s", state);
-	}
-	if (args->ar_discard)
-		seq_printf(s, ",discard");
-	lfsecs = sdp->sd_tune.gt_log_flush_secs;
-	if (lfsecs != 60)
-		seq_printf(s, ",commit=%d", lfsecs);
-	return 0;
-}
-
-/*
- * We have to (at the moment) hold the inodes main lock to cover
- * the gap between unlocking the shared lock on the iopen lock and
- * taking the exclusive lock. I'd rather do a shared -> exclusive
- * conversion on the iopen lock, but we can change that later. This
- * is safe, just less efficient.
- */
-
-static void gfs2_delete_inode(struct inode *inode)
-{
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
-	int error;
-
-	if (!test_bit(GIF_USER, &ip->i_flags))
-		goto out;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (unlikely(error)) {
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		goto out;
-	}
-
-	gfs2_glock_dq_wait(&ip->i_iopen_gh);
-	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
-	error = gfs2_glock_nq(&ip->i_iopen_gh);
-	if (error)
-		goto out_truncate;
-
-	if (S_ISDIR(inode->i_mode) &&
-	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
-		error = gfs2_dir_exhash_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (ip->i_eattr) {
-		error = gfs2_ea_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (!gfs2_is_stuffed(ip)) {
-		error = gfs2_file_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	error = gfs2_dinode_dealloc(ip);
-	if (error)
-		goto out_unlock;
-
-out_truncate:
-	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-	if (error)
-		goto out_unlock;
-	/* Needs to be done before glock release & also in a transaction */
-	truncate_inode_pages(&inode->i_data, 0);
-	gfs2_trans_end(sdp);
-
-out_unlock:
-	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
-		gfs2_glock_dq(&ip->i_iopen_gh);
-	gfs2_holder_uninit(&ip->i_iopen_gh);
-	gfs2_glock_dq_uninit(&gh);
-	if (error && error != GLR_TRYFAILED && error != -EROFS)
-		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
-out:
-	truncate_inode_pages(&inode->i_data, 0);
-	clear_inode(inode);
-}
-
-static struct inode *gfs2_alloc_inode(struct super_block *sb)
-{
-	struct gfs2_inode *ip;
-
-	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
-	if (ip) {
-		ip->i_flags = 0;
-		ip->i_gl = NULL;
-	}
-	return &ip->i_inode;
-}
-
-static void gfs2_destroy_inode(struct inode *inode)
-{
-	kmem_cache_free(gfs2_inode_cachep, inode);
-}
-
-const struct super_operations gfs2_super_ops = {
-	.alloc_inode		= gfs2_alloc_inode,
-	.destroy_inode		= gfs2_destroy_inode,
-	.write_inode		= gfs2_write_inode,
-	.delete_inode		= gfs2_delete_inode,
-	.put_super		= gfs2_put_super,
-	.write_super		= gfs2_write_super,
-	.sync_fs		= gfs2_sync_fs,
-	.freeze_fs 		= gfs2_freeze,
-	.unfreeze_fs		= gfs2_unfreeze,
-	.statfs			= gfs2_statfs,
-	.remount_fs		= gfs2_remount_fs,
-	.clear_inode		= gfs2_clear_inode,
-	.drop_inode		= gfs2_drop_inode,
-	.show_options		= gfs2_show_options,
-};
-
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 601913e..40bcc37 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -7,14 +7,20 @@
  * of the GNU General Public License version 2.
  */
 
+#include <linux/bio.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
-#include <linux/crc32.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/bio.h>
+#include <linux/crc32.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -31,6 +37,183 @@
 #include "super.h"
 #include "trans.h"
 #include "util.h"
+#include "sys.h"
+#include "eattr.h"
+
+#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
+
+enum {
+	Opt_lockproto,
+	Opt_locktable,
+	Opt_hostdata,
+	Opt_spectator,
+	Opt_ignore_local_fs,
+	Opt_localflocks,
+	Opt_localcaching,
+	Opt_debug,
+	Opt_nodebug,
+	Opt_upgrade,
+	Opt_acl,
+	Opt_noacl,
+	Opt_quota_off,
+	Opt_quota_account,
+	Opt_quota_on,
+	Opt_quota,
+	Opt_noquota,
+	Opt_suiddir,
+	Opt_nosuiddir,
+	Opt_data_writeback,
+	Opt_data_ordered,
+	Opt_meta,
+	Opt_discard,
+	Opt_nodiscard,
+	Opt_commit,
+	Opt_error,
+};
+
+static const match_table_t tokens = {
+	{Opt_lockproto, "lockproto=%s"},
+	{Opt_locktable, "locktable=%s"},
+	{Opt_hostdata, "hostdata=%s"},
+	{Opt_spectator, "spectator"},
+	{Opt_ignore_local_fs, "ignore_local_fs"},
+	{Opt_localflocks, "localflocks"},
+	{Opt_localcaching, "localcaching"},
+	{Opt_debug, "debug"},
+	{Opt_nodebug, "nodebug"},
+	{Opt_upgrade, "upgrade"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_quota_off, "quota=off"},
+	{Opt_quota_account, "quota=account"},
+	{Opt_quota_on, "quota=on"},
+	{Opt_quota, "quota"},
+	{Opt_noquota, "noquota"},
+	{Opt_suiddir, "suiddir"},
+	{Opt_nosuiddir, "nosuiddir"},
+	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_meta, "meta"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
+	{Opt_commit, "commit=%d"},
+	{Opt_error, NULL}
+};
+
+/**
+ * gfs2_mount_args - Parse mount options
+ * @sdp:
+ * @data:
+ *
+ * Return: errno
+ */
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
+{
+	char *o;
+	int token;
+	substring_t tmp[MAX_OPT_ARGS];
+	int rv;
+
+	/* Split the options into tokens with the "," character and
+	   process them */
+
+	while (1) {
+		o = strsep(&options, ",");
+		if (o == NULL)
+			break;
+		if (*o == '\0')
+			continue;
+
+		token = match_token(o, tokens, tmp);
+		switch (token) {
+		case Opt_lockproto:
+			match_strlcpy(args->ar_lockproto, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_locktable:
+			match_strlcpy(args->ar_locktable, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_hostdata:
+			match_strlcpy(args->ar_hostdata, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_spectator:
+			args->ar_spectator = 1;
+			break;
+		case Opt_ignore_local_fs:
+			args->ar_ignore_local_fs = 1;
+			break;
+		case Opt_localflocks:
+			args->ar_localflocks = 1;
+			break;
+		case Opt_localcaching:
+			args->ar_localcaching = 1;
+			break;
+		case Opt_debug:
+			args->ar_debug = 1;
+			break;
+		case Opt_nodebug:
+			args->ar_debug = 0;
+			break;
+		case Opt_upgrade:
+			args->ar_upgrade = 1;
+			break;
+		case Opt_acl:
+			args->ar_posix_acl = 1;
+			break;
+		case Opt_noacl:
+			args->ar_posix_acl = 0;
+			break;
+		case Opt_quota_off:
+		case Opt_noquota:
+			args->ar_quota = GFS2_QUOTA_OFF;
+			break;
+		case Opt_quota_account:
+			args->ar_quota = GFS2_QUOTA_ACCOUNT;
+			break;
+		case Opt_quota_on:
+		case Opt_quota:
+			args->ar_quota = GFS2_QUOTA_ON;
+			break;
+		case Opt_suiddir:
+			args->ar_suiddir = 1;
+			break;
+		case Opt_nosuiddir:
+			args->ar_suiddir = 0;
+			break;
+		case Opt_data_writeback:
+			args->ar_data = GFS2_DATA_WRITEBACK;
+			break;
+		case Opt_data_ordered:
+			args->ar_data = GFS2_DATA_ORDERED;
+			break;
+		case Opt_meta:
+			args->ar_meta = 1;
+			break;
+		case Opt_discard:
+			args->ar_discard = 1;
+			break;
+		case Opt_nodiscard:
+			args->ar_discard = 0;
+			break;
+		case Opt_commit:
+			rv = match_int(&tmp[0], &args->ar_commit);
+			if (rv || args->ar_commit <= 0) {
+				fs_info(sdp, "commit mount option requires a positive numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_error:
+		default:
+			fs_info(sdp, "invalid mount option: %s\n", o);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
 
 /**
  * gfs2_jindex_free - Clear all the journal index information
@@ -436,3 +619,719 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
 	mutex_unlock(&sdp->sd_freeze_lock);
 }
 
+
+/**
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @sync: synchronous write flag
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_inode(struct inode *inode, int sync)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	struct buffer_head *bh;
+	struct timespec atime;
+	struct gfs2_dinode *di;
+	int ret = 0;
+
+	/* Check this is a "normal" inode, etc */
+	if (!test_bit(GIF_USER, &ip->i_flags) ||
+	    (current->flags & PF_MEMALLOC))
+		return 0;
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (ret)
+		goto do_flush;
+	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (ret)
+		goto do_unlock;
+	ret = gfs2_meta_inode_buffer(ip, &bh);
+	if (ret == 0) {
+		di = (struct gfs2_dinode *)bh->b_data;
+		atime.tv_sec = be64_to_cpu(di->di_atime);
+		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
+		if (timespec_compare(&inode->i_atime, &atime) > 0) {
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			gfs2_dinode_out(ip, bh->b_data);
+		}
+		brelse(bh);
+	}
+	gfs2_trans_end(sdp);
+do_unlock:
+	gfs2_glock_dq_uninit(&gh);
+do_flush:
+	if (sync != 0)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	return ret;
+}
+
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+	struct gfs2_holder t_gh;
+	int error;
+
+	gfs2_quota_sync(sdp);
+	gfs2_statfs_sync(sdp);
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &t_gh);
+	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return error;
+
+	gfs2_meta_syncfs(sdp);
+	gfs2_log_shutdown(sdp);
+
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	if (t_gh.gh_gl)
+		gfs2_glock_dq_uninit(&t_gh);
+
+	gfs2_quota_cleanup(sdp);
+
+	return error;
+}
+
+static int gfs2_umount_recovery_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * gfs2_put_super - Unmount the filesystem
+ * @sb: The VFS superblock
+ *
+ */
+
+static void gfs2_put_super(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+	struct gfs2_jdesc *jd;
+
+	/*  Unfreeze the filesystem, if we need to  */
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	if (sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	/* No more recovery requests */
+	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	smp_mb();
+
+	/* Wait on outstanding recovery */
+restart:
+	spin_lock(&sdp->sd_jindex_spin);
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
+			continue;
+		spin_unlock(&sdp->sd_jindex_spin);
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
+			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
+		goto restart;
+	}
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_ro(sdp);
+		if (error)
+			gfs2_io_error(sdp);
+	}
+	/*  At this point, we're through modifying the disk  */
+
+	/*  Release stuff  */
+
+	iput(sdp->sd_jindex);
+	iput(sdp->sd_inum_inode);
+	iput(sdp->sd_statfs_inode);
+	iput(sdp->sd_rindex);
+	iput(sdp->sd_quota_inode);
+
+	gfs2_glock_put(sdp->sd_rename_gl);
+	gfs2_glock_put(sdp->sd_trans_gl);
+
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+		iput(sdp->sd_ir_inode);
+		iput(sdp->sd_sc_inode);
+		iput(sdp->sd_qc_inode);
+	}
+
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+	gfs2_clear_rgrpd(sdp);
+	gfs2_jindex_free(sdp);
+	/*  Take apart glock structures and buffer lists  */
+	gfs2_gl_hash_clear(sdp);
+	/*  Unmount the locking protocol  */
+	gfs2_lm_unmount(sdp);
+
+	/*  At this point, we're through participating in the lockspace  */
+	gfs2_sys_fs_del(sdp);
+}
+
+/**
+ * gfs2_write_super
+ * @sb: the superblock
+ *
+ */
+
+static void gfs2_write_super(struct super_block *sb)
+{
+	sb->s_dirt = 0;
+}
+
+/**
+ * gfs2_sync_fs - sync the filesystem
+ * @sb: the superblock
+ *
+ * Flushes the log to disk.
+ */
+
+static int gfs2_sync_fs(struct super_block *sb, int wait)
+{
+	sb->s_dirt = 0;
+	if (wait && sb->s_fs_info)
+		gfs2_log_flush(sb->s_fs_info, NULL);
+	return 0;
+}
+
+/**
+ * gfs2_freeze - prevent further writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_freeze(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return -EINVAL;
+
+	for (;;) {
+		error = gfs2_freeze_fs(sdp);
+		if (!error)
+			break;
+
+		switch (error) {
+		case -EBUSY:
+			fs_err(sdp, "waiting for recovery before freeze\n");
+			break;
+
+		default:
+			fs_err(sdp, "error freezing FS: %d\n", error);
+			break;
+		}
+
+		fs_err(sdp, "retrying...\n");
+		msleep(1000);
+	}
+	return 0;
+}
+
+/**
+ * gfs2_unfreeze - reallow writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_unfreeze(struct super_block *sb)
+{
+	gfs2_unfreeze_fs(sb->s_fs_info);
+	return 0;
+}
+
+/**
+ * statfs_fill - fill in the sg for a given RG
+ * @rgd: the RG
+ * @sc: the sc structure
+ *
+ * Returns: 0 on success, -ESTALE if the LVB is invalid
+ */
+
+static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
+			    struct gfs2_statfs_change_host *sc)
+{
+	gfs2_rgrp_verify(rgd);
+	sc->sc_total += rgd->rd_data;
+	sc->sc_free += rgd->rd_free;
+	sc->sc_dinodes += rgd->rd_dinodes;
+	return 0;
+}
+
+/**
+ * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
+ * @sdp: the filesystem
+ * @sc: the sc info that will be returned
+ *
+ * Any error (other than a signal) will cause this routine to fall back
+ * to the synchronous version.
+ *
+ * FIXME: This really shouldn't busy wait like this.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_holder ri_gh;
+	struct gfs2_rgrpd *rgd_next;
+	struct gfs2_holder *gha, *gh;
+	unsigned int slots = 64;
+	unsigned int x;
+	int done;
+	int error = 0, err;
+
+	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
+	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
+	if (!gha)
+		return -ENOMEM;
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto out;
+
+	rgd_next = gfs2_rgrpd_get_first(sdp);
+
+	for (;;) {
+		done = 1;
+
+		for (x = 0; x < slots; x++) {
+			gh = gha + x;
+
+			if (gh->gh_gl && gfs2_glock_poll(gh)) {
+				err = gfs2_glock_wait(gh);
+				if (err) {
+					gfs2_holder_uninit(gh);
+					error = err;
+				} else {
+					if (!error)
+						error = statfs_slow_fill(
+							gh->gh_gl->gl_object, sc);
+					gfs2_glock_dq_uninit(gh);
+				}
+			}
+
+			if (gh->gh_gl)
+				done = 0;
+			else if (rgd_next && !error) {
+				error = gfs2_glock_nq_init(rgd_next->rd_gl,
+							   LM_ST_SHARED,
+							   GL_ASYNC,
+							   gh);
+				rgd_next = gfs2_rgrpd_get_next(rgd_next);
+				done = 0;
+			}
+
+			if (signal_pending(current))
+				error = -ERESTARTSYS;
+		}
+
+		if (done)
+			break;
+
+		yield();
+	}
+
+	gfs2_glock_dq_uninit(&ri_gh);
+
+out:
+	kfree(gha);
+	return error;
+}
+
+/**
+ * gfs2_statfs_i - Do a statfs
+ * @sdp: the filesystem
+ * @sg: the sg structure
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	spin_lock(&sdp->sd_statfs_spin);
+
+	*sc = *m_sc;
+	sc->sc_total += l_sc->sc_total;
+	sc->sc_free += l_sc->sc_free;
+	sc->sc_dinodes += l_sc->sc_dinodes;
+
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	if (sc->sc_free < 0)
+		sc->sc_free = 0;
+	if (sc->sc_free > sc->sc_total)
+		sc->sc_free = sc->sc_total;
+	if (sc->sc_dinodes < 0)
+		sc->sc_dinodes = 0;
+
+	return 0;
+}
+
+/**
+ * gfs2_statfs - Gather and return stats about the filesystem
+ * @sb: The superblock
+ * @statfsbuf: The buffer
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_statfs_change_host sc;
+	int error;
+
+	if (gfs2_tune_get(sdp, gt_statfs_slow))
+		error = gfs2_statfs_slow(sdp, &sc);
+	else
+		error = gfs2_statfs_i(sdp, &sc);
+
+	if (error)
+		return error;
+
+	buf->f_type = GFS2_MAGIC;
+	buf->f_bsize = sdp->sd_sb.sb_bsize;
+	buf->f_blocks = sc.sc_total;
+	buf->f_bfree = sc.sc_free;
+	buf->f_bavail = sc.sc_free;
+	buf->f_files = sc.sc_dinodes + sc.sc_free;
+	buf->f_ffree = sc.sc_free;
+	buf->f_namelen = GFS2_FNAMESIZE;
+
+	return 0;
+}
+
+/**
+ * gfs2_remount_fs - called when the FS is remounted
+ * @sb:  the filesystem
+ * @flags:  the remount flags
+ * @data:  extra data passed in (not used right now)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	int error;
+
+	spin_lock(&gt->gt_spin);
+	args.ar_commit = gt->gt_log_flush_secs;
+	spin_unlock(&gt->gt_spin);
+	error = gfs2_mount_args(sdp, &args, data);
+	if (error)
+		return error;
+
+	/* Not allowed to change locking details */
+	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
+	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
+	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
+		return -EINVAL;
+
+	/* Some flags must not be changed */
+	if (args_neq(&args, &sdp->sd_args, spectator) ||
+	    args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
+	    args_neq(&args, &sdp->sd_args, localflocks) ||
+	    args_neq(&args, &sdp->sd_args, localcaching) ||
+	    args_neq(&args, &sdp->sd_args, meta))
+		return -EINVAL;
+
+	if (sdp->sd_args.ar_spectator)
+		*flags |= MS_RDONLY;
+
+	if ((sb->s_flags ^ *flags) & MS_RDONLY) {
+		if (*flags & MS_RDONLY)
+			error = gfs2_make_fs_ro(sdp);
+		else
+			error = gfs2_make_fs_rw(sdp);
+		if (error)
+			return error;
+	}
+
+	sdp->sd_args = args;
+	if (sdp->sd_args.ar_posix_acl)
+		sb->s_flags |= MS_POSIXACL;
+	else
+		sb->s_flags &= ~MS_POSIXACL;
+	spin_lock(&gt->gt_spin);
+	gt->gt_log_flush_secs = args.ar_commit;
+	spin_unlock(&gt->gt_spin);
+
+	return 0;
+}
+
+/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+
+static void gfs2_drop_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) {
+		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+			clear_nlink(inode);
+	}
+	generic_drop_inode(inode);
+}
+
+/**
+ * gfs2_clear_inode - Deallocate an inode when VFS is done with it
+ * @inode: The VFS inode
+ *
+ */
+
+static void gfs2_clear_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	/* This tells us its a "real" inode and not one which only
+	 * serves to contain an address space (see rgrp.c, meta_io.c)
+	 * which therefore doesn't have its own glocks.
+	 */
+	if (test_bit(GIF_USER, &ip->i_flags)) {
+		ip->i_gl->gl_object = NULL;
+		gfs2_glock_put(ip->i_gl);
+		ip->i_gl = NULL;
+		if (ip->i_iopen_gh.gh_gl) {
+			ip->i_iopen_gh.gh_gl->gl_object = NULL;
+			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		}
+	}
+}
+
+static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
+{
+	do {
+		if (d1 == d2)
+			return 1;
+		d1 = d1->d_parent;
+	} while (!IS_ROOT(d1));
+	return 0;
+}
+
+/**
+ * gfs2_show_options - Show mount options for /proc/mounts
+ * @s: seq_file structure
+ * @mnt: vfsmount
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_args *args = &sdp->sd_args;
+	int lfsecs;
+
+	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+		seq_printf(s, ",meta");
+	if (args->ar_lockproto[0])
+		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
+	if (args->ar_locktable[0])
+		seq_printf(s, ",locktable=%s", args->ar_locktable);
+	if (args->ar_hostdata[0])
+		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
+	if (args->ar_spectator)
+		seq_printf(s, ",spectator");
+	if (args->ar_ignore_local_fs)
+		seq_printf(s, ",ignore_local_fs");
+	if (args->ar_localflocks)
+		seq_printf(s, ",localflocks");
+	if (args->ar_localcaching)
+		seq_printf(s, ",localcaching");
+	if (args->ar_debug)
+		seq_printf(s, ",debug");
+	if (args->ar_upgrade)
+		seq_printf(s, ",upgrade");
+	if (args->ar_posix_acl)
+		seq_printf(s, ",acl");
+	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
+		char *state;
+		switch (args->ar_quota) {
+		case GFS2_QUOTA_OFF:
+			state = "off";
+			break;
+		case GFS2_QUOTA_ACCOUNT:
+			state = "account";
+			break;
+		case GFS2_QUOTA_ON:
+			state = "on";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",quota=%s", state);
+	}
+	if (args->ar_suiddir)
+		seq_printf(s, ",suiddir");
+	if (args->ar_data != GFS2_DATA_DEFAULT) {
+		char *state;
+		switch (args->ar_data) {
+		case GFS2_DATA_WRITEBACK:
+			state = "writeback";
+			break;
+		case GFS2_DATA_ORDERED:
+			state = "ordered";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",data=%s", state);
+	}
+	if (args->ar_discard)
+		seq_printf(s, ",discard");
+	lfsecs = sdp->sd_tune.gt_log_flush_secs;
+	if (lfsecs != 60)
+		seq_printf(s, ",commit=%d", lfsecs);
+	return 0;
+}
+
+/*
+ * We have to (at the moment) hold the inodes main lock to cover
+ * the gap between unlocking the shared lock on the iopen lock and
+ * taking the exclusive lock. I'd rather do a shared -> exclusive
+ * conversion on the iopen lock, but we can change that later. This
+ * is safe, just less efficient.
+ */
+
+static void gfs2_delete_inode(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+
+	if (!test_bit(GIF_USER, &ip->i_flags))
+		goto out;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (unlikely(error)) {
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		goto out;
+	}
+
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
+	error = gfs2_glock_nq(&ip->i_iopen_gh);
+	if (error)
+		goto out_truncate;
+
+	if (S_ISDIR(inode->i_mode) &&
+	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
+		error = gfs2_dir_exhash_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (ip->i_eattr) {
+		error = gfs2_ea_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		error = gfs2_file_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = gfs2_dinode_dealloc(ip);
+	if (error)
+		goto out_unlock;
+
+out_truncate:
+	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_unlock;
+	/* Needs to be done before glock release & also in a transaction */
+	truncate_inode_pages(&inode->i_data, 0);
+	gfs2_trans_end(sdp);
+
+out_unlock:
+	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
+		gfs2_glock_dq(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_uninit(&gh);
+	if (error && error != GLR_TRYFAILED && error != -EROFS)
+		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+out:
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+}
+
+static struct inode *gfs2_alloc_inode(struct super_block *sb)
+{
+	struct gfs2_inode *ip;
+
+	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
+	if (ip) {
+		ip->i_flags = 0;
+		ip->i_gl = NULL;
+	}
+	return &ip->i_inode;
+}
+
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(gfs2_inode_cachep, inode);
+}
+
+const struct super_operations gfs2_super_ops = {
+	.alloc_inode		= gfs2_alloc_inode,
+	.destroy_inode		= gfs2_destroy_inode,
+	.write_inode		= gfs2_write_inode,
+	.delete_inode		= gfs2_delete_inode,
+	.put_super		= gfs2_put_super,
+	.write_super		= gfs2_write_super,
+	.sync_fs		= gfs2_sync_fs,
+	.freeze_fs 		= gfs2_freeze,
+	.unfreeze_fs		= gfs2_unfreeze,
+	.statfs			= gfs2_statfs,
+	.remount_fs		= gfs2_remount_fs,
+	.clear_inode		= gfs2_clear_inode,
+	.drop_inode		= gfs2_drop_inode,
+	.show_options		= gfs2_show_options,
+};
+
-- 
1.6.0.6

[Cluster-devel] [PATCH 16/24] GFS2: Move gfs2_rmdiri into ops_inode.c

[Steven Whitehouse]

Move gfs2_rmdiri() into ops_inode.c and make it static.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index c03a1a3..9b17447 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1046,58 +1046,6 @@ fail:
 	return ERR_PTR(error);
 }
 
-/**
- * gfs2_rmdiri - Remove a directory
- * @dip: The parent directory of the directory to be removed
- * @name: The name of the directory to be removed
- * @ip: The GFS2 inode of the directory to be removed
- *
- * Assumes Glocks on dip and ip are held
- *
- * Returns: errno
- */
-
-int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
-		struct gfs2_inode *ip)
-{
-	struct qstr dotname;
-	int error;
-
-	if (ip->i_entries != 2) {
-		if (gfs2_consist_inode(ip))
-			gfs2_dinode_print(ip);
-		return -EIO;
-	}
-
-	error = gfs2_dir_del(dip, name);
-	if (error)
-		return error;
-
-	error = gfs2_change_nlink(dip, -1);
-	if (error)
-		return error;
-
-	gfs2_str2qstr(&dotname, ".");
-	error = gfs2_dir_del(ip, &dotname);
-	if (error)
-		return error;
-
-	gfs2_str2qstr(&dotname, "..");
-	error = gfs2_dir_del(ip, &dotname);
-	if (error)
-		return error;
-
-	/* It looks odd, but it really should be done twice */
-	error = gfs2_change_nlink(ip, -1);
-	if (error)
-		return error;
-
-	error = gfs2_change_nlink(ip, -1);
-	if (error)
-		return error;
-
-	return error;
-}
 
 /*
  * gfs2_unlink_ok - check to see that a inode is still in a directory
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 2c3ec07..6cd3928 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -96,8 +96,6 @@ extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
 				  const struct qstr *name,
 				  unsigned int mode, dev_t dev);
-extern int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
-		       struct gfs2_inode *ip);
 extern int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 			  const struct gfs2_inode *ip);
 extern int gfs2_permission(struct inode *inode, int mask);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1c70fa5..5dacd64 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -473,6 +473,59 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 }
 
 /**
+ * gfs2_rmdiri - Remove a directory
+ * @dip: The parent directory of the directory to be removed
+ * @name: The name of the directory to be removed
+ * @ip: The GFS2 inode of the directory to be removed
+ *
+ * Assumes Glocks on dip and ip are held
+ *
+ * Returns: errno
+ */
+
+static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
+		       struct gfs2_inode *ip)
+{
+	struct qstr dotname;
+	int error;
+
+	if (ip->i_entries != 2) {
+		if (gfs2_consist_inode(ip))
+			gfs2_dinode_print(ip);
+		return -EIO;
+	}
+
+	error = gfs2_dir_del(dip, name);
+	if (error)
+		return error;
+
+	error = gfs2_change_nlink(dip, -1);
+	if (error)
+		return error;
+
+	gfs2_str2qstr(&dotname, ".");
+	error = gfs2_dir_del(ip, &dotname);
+	if (error)
+		return error;
+
+	gfs2_str2qstr(&dotname, "..");
+	error = gfs2_dir_del(ip, &dotname);
+	if (error)
+		return error;
+
+	/* It looks odd, but it really should be done twice */
+	error = gfs2_change_nlink(ip, -1);
+	if (error)
+		return error;
+
+	error = gfs2_change_nlink(ip, -1);
+	if (error)
+		return error;
+
+	return error;
+}
+
+/**
  * gfs2_rmdir - Remove a directory
  * @dir: The parent directory of the directory to be removed
  * @dentry: The dentry of the directory to remove
-- 
1.6.0.6

[Cluster-devel] [PATCH 17/24] GFS2: Move gfs2_readlinki into ops_inode.c

[Steven Whitehouse]

Move gfs2_readlinki into ops_inode.c and make it static

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 9b17447..676e750 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1085,63 +1085,7 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 	return 0;
 }
 
-/**
- * gfs2_readlinki - return the contents of a symlink
- * @ip: the symlink's inode
- * @buf: a pointer to the buffer to be filled
- * @len: a pointer to the length of @buf
- *
- * If @buf is too small, a piece of memory is kmalloc()ed and needs
- * to be freed by the caller.
- *
- * Returns: errno
- */
-
-int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
-{
-	struct gfs2_holder i_gh;
-	struct buffer_head *dibh;
-	unsigned int x;
-	int error;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
-	error = gfs2_glock_nq(&i_gh);
-	if (error) {
-		gfs2_holder_uninit(&i_gh);
-		return error;
-	}
-
-	if (!ip->i_disksize) {
-		gfs2_consist_inode(ip);
-		error = -EIO;
-		goto out;
-	}
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		goto out;
-
-	x = ip->i_disksize + 1;
-	if (x > *len) {
-		*buf = kmalloc(x, GFP_NOFS);
-		if (!*buf) {
-			error = -ENOMEM;
-			goto out_brelse;
-		}
-	}
-
-	memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
-	*len = x;
-
-out_brelse:
-	brelse(dibh);
-out:
-	gfs2_glock_dq_uninit(&i_gh);
-	return error;
-}
-
-static int
-__gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
 	struct buffer_head *dibh;
 	int error;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 6cd3928..fc9a08f 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -99,7 +99,6 @@ extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
 extern int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 			  const struct gfs2_inode *ip);
 extern int gfs2_permission(struct inode *inode, int mask);
-extern int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
 extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 5dacd64..f607f09 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -938,6 +938,61 @@ out:
 }
 
 /**
+ * gfs2_readlinki - return the contents of a symlink
+ * @ip: the symlink's inode
+ * @buf: a pointer to the buffer to be filled
+ * @len: a pointer to the length of @buf
+ *
+ * If @buf is too small, a piece of memory is kmalloc()ed and needs
+ * to be freed by the caller.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
+{
+	struct gfs2_holder i_gh;
+	struct buffer_head *dibh;
+	unsigned int x;
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+	error = gfs2_glock_nq(&i_gh);
+	if (error) {
+		gfs2_holder_uninit(&i_gh);
+		return error;
+	}
+
+	if (!ip->i_disksize) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+		goto out;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+
+	x = ip->i_disksize + 1;
+	if (x > *len) {
+		*buf = kmalloc(x, GFP_NOFS);
+		if (!*buf) {
+			error = -ENOMEM;
+			goto out_brelse;
+		}
+	}
+
+	memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
+	*len = x;
+
+out_brelse:
+	brelse(dibh);
+out:
+	gfs2_glock_dq_uninit(&i_gh);
+	return error;
+}
+
+/**
  * gfs2_readlink - Read the value of a symlink
  * @dentry: the symlink
  * @buf: the buffer to read the symlink data into
-- 
1.6.0.6

[Cluster-devel] [PATCH 18/24] GFS2: Move gfs2_unlink_ok into ops_inode.c

[Steven Whitehouse]

Another function which is only called from one ops_inode.c so
we move it and make it static.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 676e750..2f94bd7 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1046,45 +1046,6 @@ fail:
 	return ERR_PTR(error);
 }
 
-
-/*
- * gfs2_unlink_ok - check to see that a inode is still in a directory
- * @dip: the directory
- * @name: the name of the file
- * @ip: the inode
- *
- * Assumes that the lock on (at least) @dip is held.
- *
- * Returns: 0 if the parent/child relationship is correct, errno if it isn't
- */
-
-int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
-		   const struct gfs2_inode *ip)
-{
-	int error;
-
-	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
-		return -EPERM;
-
-	if ((dip->i_inode.i_mode & S_ISVTX) &&
-	    dip->i_inode.i_uid != current_fsuid() &&
-	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
-		return -EPERM;
-
-	if (IS_APPEND(&dip->i_inode))
-		return -EPERM;
-
-	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
-	if (error)
-		return error;
-
-	error = gfs2_dir_check(&dip->i_inode, name, ip);
-	if (error)
-		return error;
-
-	return 0;
-}
-
 static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
 	struct buffer_head *dibh;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index fc9a08f..c341aaf 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -96,8 +96,6 @@ extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
 				  const struct qstr *name,
 				  unsigned int mode, dev_t dev);
-extern int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
-			  const struct gfs2_inode *ip);
 extern int gfs2_permission(struct inode *inode, int mask);
 extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index f607f09..f8bd20b 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -262,6 +262,44 @@ out_parent:
 	return error;
 }
 
+/*
+ * gfs2_unlink_ok - check to see that a inode is still in a directory
+ * @dip: the directory
+ * @name: the name of the file
+ * @ip: the inode
+ *
+ * Assumes that the lock on (at least) @dip is held.
+ *
+ * Returns: 0 if the parent/child relationship is correct, errno if it isn't
+ */
+
+static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+			  const struct gfs2_inode *ip)
+{
+	int error;
+
+	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
+		return -EPERM;
+
+	if ((dip->i_inode.i_mode & S_ISVTX) &&
+	    dip->i_inode.i_uid != current_fsuid() &&
+	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
+		return -EPERM;
+
+	if (IS_APPEND(&dip->i_inode))
+		return -EPERM;
+
+	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+	if (error)
+		return error;
+
+	error = gfs2_dir_check(&dip->i_inode, name, ip);
+	if (error)
+		return error;
+
+	return 0;
+}
+
 /**
  * gfs2_unlink - Unlink a file
  * @dir: The inode of the directory containing the file to unlink
-- 
1.6.0.6

[Cluster-devel] [PATCH 19/24] GFS2: Remove lockstruct subdir from gfs2 sysfs files

[Steven Whitehouse]

The lockstruct sub directory contained two entries, both of
which are duplicated elsewhere in the gfs2 sysfs files as
well as being available via /proc/mounts. There is no userland program
using either of them, so this patch removes them.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 9f6d48b..94bd59e 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -276,25 +276,6 @@ static struct kobj_type gfs2_ktype = {
 	.sysfs_ops     = &gfs2_attr_ops,
 };
 
-/*
- * display struct lm_lockstruct fields
- */
-
-#define LOCKSTRUCT_ATTR(name, fmt)                                          \
-static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
-{                                                                           \
-	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \
-}                                                                           \
-static struct gfs2_attr lockstruct_attr_##name = __ATTR_RO(name)
-
-LOCKSTRUCT_ATTR(jid,      "%u\n");
-LOCKSTRUCT_ATTR(first,    "%u\n");
-
-static struct attribute *lockstruct_attrs[] = {
-	&lockstruct_attr_jid.attr,
-	&lockstruct_attr_first.attr,
-	NULL,
-};
 
 /*
  * lock_module. Originally from lock_dlm
@@ -397,6 +378,11 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
 	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
 }
 
+static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid);
+}
+
 #define GDLM_ATTR(_name,_mode,_show,_store) \
 static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
@@ -404,6 +390,7 @@ GDLM_ATTR(proto_name,     0444, proto_name_show,	NULL);
 GDLM_ATTR(block,          0644, block_show,		block_store);
 GDLM_ATTR(withdraw,       0644, withdraw_show,		withdraw_store);
 GDLM_ATTR(id,             0444, lkid_show,		NULL);
+GDLM_ATTR(jid,		  0444, jid_show,		NULL);
 GDLM_ATTR(first,          0444, lkfirst_show,		NULL);
 GDLM_ATTR(first_done,     0444, first_done_show,	NULL);
 GDLM_ATTR(recover,        0200, NULL,			recover_store);
@@ -415,7 +402,7 @@ static struct attribute *lock_module_attrs[] = {
 	&gdlm_attr_block.attr,
 	&gdlm_attr_withdraw.attr,
 	&gdlm_attr_id.attr,
-	&lockstruct_attr_jid.attr,
+	&gdlm_attr_jid.attr,
 	&gdlm_attr_first.attr,
 	&gdlm_attr_first_done.attr,
 	&gdlm_attr_recover.attr,
@@ -558,11 +545,6 @@ static struct attribute *tune_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group lockstruct_group = {
-	.name = "lockstruct",
-	.attrs = lockstruct_attrs,
-};
-
 static struct attribute_group args_group = {
 	.name = "args",
 	.attrs = args_attrs,
@@ -588,13 +570,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
 	if (error)
 		goto fail;
 
-	error = sysfs_create_group(&sdp->sd_kobj, &lockstruct_group);
-	if (error)
-		goto fail_reg;
-
 	error = sysfs_create_group(&sdp->sd_kobj, &args_group);
 	if (error)
-		goto fail_lockstruct;
+		goto fail_reg;
 
 	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
 	if (error)
@@ -611,8 +589,6 @@ fail_tune:
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
 fail_args:
 	sysfs_remove_group(&sdp->sd_kobj, &args_group);
-fail_lockstruct:
-	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
 fail_reg:
 	kobject_put(&sdp->sd_kobj);
 fail:
@@ -624,7 +600,6 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
 {
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
 	sysfs_remove_group(&sdp->sd_kobj, &args_group);
-	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
 	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
 	kobject_put(&sdp->sd_kobj);
 }
-- 
1.6.0.6

[Cluster-devel] [PATCH 20/24] GFS2: Remove args subdir from gfs2 sysfs files

[Steven Whitehouse]

Since we can cat /proc/mounts there is no need to have this
subdirectory in the gfs2 sysfs files. In fact this does not
reflect the full range of possible mount argumenmts, where
as /proc/mounts does.

There was only one userland user of this set of sysfs files
and it will function perfectly well without these files
being present (in fact that subcommand of gfs2_tool is
obsolete anyway).

The tune/* subdirectory is also considered mostly obsolete,
but there are a few uses of this until mount arguments can
be added for the last few functions for which there are no
equivalents currently. However the tune/* directory is still
in my sights and new code should avoid using it. Only the gfs2_quota
and gfs2_tool programs are know to use tune/* at the moment.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 94bd59e..23419dc 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -411,44 +411,6 @@ static struct attribute *lock_module_attrs[] = {
 	NULL,
 };
 
-#define ARGS_ATTR(name, fmt)                                                \
-static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
-{                                                                           \
-	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name);       \
-}                                                                           \
-static struct gfs2_attr args_attr_##name = __ATTR_RO(name)
-
-ARGS_ATTR(lockproto,       "%s\n");
-ARGS_ATTR(locktable,       "%s\n");
-ARGS_ATTR(hostdata,        "%s\n");
-ARGS_ATTR(spectator,       "%d\n");
-ARGS_ATTR(ignore_local_fs, "%d\n");
-ARGS_ATTR(localcaching,    "%d\n");
-ARGS_ATTR(localflocks,     "%d\n");
-ARGS_ATTR(debug,           "%d\n");
-ARGS_ATTR(upgrade,         "%d\n");
-ARGS_ATTR(posix_acl,       "%d\n");
-ARGS_ATTR(quota,           "%u\n");
-ARGS_ATTR(suiddir,         "%d\n");
-ARGS_ATTR(data,            "%d\n");
-
-static struct attribute *args_attrs[] = {
-	&args_attr_lockproto.attr,
-	&args_attr_locktable.attr,
-	&args_attr_hostdata.attr,
-	&args_attr_spectator.attr,
-	&args_attr_ignore_local_fs.attr,
-	&args_attr_localcaching.attr,
-	&args_attr_localflocks.attr,
-	&args_attr_debug.attr,
-	&args_attr_upgrade.attr,
-	&args_attr_posix_acl.attr,
-	&args_attr_quota.attr,
-	&args_attr_suiddir.attr,
-	&args_attr_data.attr,
-	NULL,
-};
-
 /*
  * get and set struct gfs2_tune fields
  */
@@ -545,11 +507,6 @@ static struct attribute *tune_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group args_group = {
-	.name = "args",
-	.attrs = args_attrs,
-};
-
 static struct attribute_group tune_group = {
 	.name = "tune",
 	.attrs = tune_attrs,
@@ -570,13 +527,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
 	if (error)
 		goto fail;
 
-	error = sysfs_create_group(&sdp->sd_kobj, &args_group);
-	if (error)
-		goto fail_reg;
-
 	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
 	if (error)
-		goto fail_args;
+		goto fail_reg;
 
 	error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group);
 	if (error)
@@ -587,8 +540,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
 
 fail_tune:
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
-fail_args:
-	sysfs_remove_group(&sdp->sd_kobj, &args_group);
 fail_reg:
 	kobject_put(&sdp->sd_kobj);
 fail:
@@ -599,7 +550,6 @@ fail:
 void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
 {
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
-	sysfs_remove_group(&sdp->sd_kobj, &args_group);
 	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
 	kobject_put(&sdp->sd_kobj);
 }
-- 
1.6.0.6

[Cluster-devel] [PATCH 21/24] GFS2: smbd proccess hangs with flock() call.

[Steven Whitehouse]

From: Abhijith Das <adas@redhat.com>

GFS2 currently does not support mandatory flocks. An flock() call with
LOCK_MAND triggers unexpected behavior because gfs2 is not checking for
this lock type. This patch corrects that.

Signed-off-by: Abhi Das <adas@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 73b6f55..841ddc9 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -698,8 +698,8 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
-	if (__mandatory_lock(&ip->i_inode))
-		return -ENOLCK;
+	if (fl->fl_type & LOCK_MAND)
+		return -EOPNOTSUPP;
 
 	if (fl->fl_type == F_UNLCK) {
 		do_unflock(file, fl);
-- 
1.6.0.6

[Cluster-devel] [PATCH 22/24] GFS2: Remove unused variable

[Steven Whitehouse]

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 841ddc9..73318a3 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -694,8 +694,6 @@ static void do_unflock(struct file *file, struct file_lock *fl)
 
 static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 {
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 	if (fl->fl_type & LOCK_MAND)
-- 
1.6.0.6

[Cluster-devel] [PATCH 23/24] GFS2: Fix locking issue mounting gfs2meta fs

[Steven Whitehouse]

This patch uses sget() to get a reference to the
existing gfs2 sb when mouting the gfs2meta filesystem
(in fact thats just another mount of the gfs2
filesystem with a different root and this interface
is for backward compatibility).

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Reported-by: Benjamin Marzinski <bmarzins@redhat.com>
Tested-by: Benjamin Marzinski <bmarzins@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 2cd1164..9da161c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1273,9 +1273,20 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
 	return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
 }
 
+static int test_meta_super(struct super_block *s, void *ptr)
+{
+	struct block_device *bdev = ptr;
+	return (bdev == s->s_bdev);
+}
+
+static int set_meta_super(struct super_block *s, void *ptr)
+{
+	return -EINVAL;
+}
+
 static struct super_block *get_gfs2_sb(const char *dev_name)
 {
-	struct super_block *sb;
+	struct super_block *s;
 	struct path path;
 	int error;
 
@@ -1283,30 +1294,27 @@ static struct super_block *get_gfs2_sb(const char *dev_name)
 	if (error) {
 		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
 		       dev_name, error);
-		return NULL;
+		return ERR_PTR(-ENOENT);
 	}
-	sb = path.dentry->d_inode->i_sb;
-	if (sb && (sb->s_type == &gfs2_fs_type))
-		atomic_inc(&sb->s_active);
-	else
-		sb = NULL;
+	s = sget(&gfs2_fs_type, test_meta_super, set_meta_super,
+		 path.dentry->d_inode->i_sb->s_bdev);
 	path_put(&path);
-	return sb;
+	return s;
 }
 
 static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 			    const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	struct super_block *sb = NULL;
+	struct super_block *s;
 	struct gfs2_sbd *sdp;
 
-	sb = get_gfs2_sb(dev_name);
-	if (!sb) {
+	s = get_gfs2_sb(dev_name);
+	if (IS_ERR(s)) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-		return -ENOENT;
+		return PTR_ERR(s);
 	}
-	sdp = sb->s_fs_info;
-	mnt->mnt_sb = sb;
+	sdp = s->s_fs_info;
+	mnt->mnt_sb = s;
 	mnt->mnt_root = dget(sdp->sd_master_dir);
 	return 0;
 }
-- 
1.6.0.6

[Cluster-devel] [PATCH 24/24] GFS2: Fix cache coherency between truncate and O_DIRECT read

[Steven Whitehouse]

If a page was partially zeroed as the result of a truncate, then it was
not being correctly marked dirty. This resulted in the deleted data
reappearing if the file was read back via direct I/O.

Reported-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 1153a07..3297635 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1012,7 +1012,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping)
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 
 	zero_user(page, offset, length);
-
+	mark_buffer_dirty(bh);
 unlock:
 	unlock_page(page);
 	page_cache_release(page);
-- 
1.6.0.6

[Cluster-devel] Re: [PATCH 23/24] GFS2: Fix locking issue mounting gfs2meta fs

[Christoph Hellwig]

On Wed, Jun 10, 2009 at 09:31:04AM +0100, Steven Whitehouse wrote:
>  static struct super_block *get_gfs2_sb(const char *dev_name)
>  {
> -	struct super_block *sb;

Any reason you don't merge get_gfs2_sb into gfs2_get_sb_meta?  That's
how most other get_sb callbacks are structured, and would also get rid
of the rather confusing get_gfs2_sb name.

[Cluster-devel] Re: [PATCH 23/24] GFS2: Fix locking issue mounting gfs2meta fs

[Steven Whitehouse]

Hi,

On Wed, 2009-06-10 at 05:53 -0400, Christoph Hellwig wrote:
> On Wed, Jun 10, 2009 at 09:31:04AM +0100, Steven Whitehouse wrote:
> >  static struct super_block *get_gfs2_sb(const char *dev_name)
> >  {
> > -	struct super_block *sb;
> 
> Any reason you don't merge get_gfs2_sb into gfs2_get_sb_meta?  That's
> how most other get_sb callbacks are structured, and would also get rid
> of the rather confusing get_gfs2_sb name.
> 

Well originally I was expecting to share that code with the
gfs2_get_sb() but since that patch has been dropped now, I guess there
is no reason not to merge them,

Steve.

[Cluster-devel] GFS2: Merge gfs2_get_sb into gfs2_get_sb_meta

[Steven Whitehouse]

From 003dec8913d6bebb4ecc989ec04a235cf38f5ea9 Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Wed, 10 Jun 2009 10:31:45 +0100
Subject: [PATCH] GFS2: Merge gfs2_get_sb into gfs2_get_sb_meta

These don't need to be separate functions.

Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 9da161c..f234aba 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1284,9 +1284,11 @@ static int set_meta_super(struct super_block *s, void *ptr)
 	return -EINVAL;
 }
 
-static struct super_block *get_gfs2_sb(const char *dev_name)
+static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
+			    const char *dev_name, void *data, struct vfsmount *mnt)
 {
 	struct super_block *s;
+	struct gfs2_sbd *sdp;
 	struct path path;
 	int error;
 
@@ -1294,21 +1296,11 @@ static struct super_block *get_gfs2_sb(const char *dev_name)
 	if (error) {
 		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
 		       dev_name, error);
-		return ERR_PTR(-ENOENT);
+		return error;
 	}
 	s = sget(&gfs2_fs_type, test_meta_super, set_meta_super,
 		 path.dentry->d_inode->i_sb->s_bdev);
 	path_put(&path);
-	return s;
-}
-
-static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
-			    const char *dev_name, void *data, struct vfsmount *mnt)
-{
-	struct super_block *s;
-	struct gfs2_sbd *sdp;
-
-	s = get_gfs2_sb(dev_name);
 	if (IS_ERR(s)) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
 		return PTR_ERR(s);
-- 
1.6.0.6

[Cluster-devel] Re: [PATCH 10/24] GFS2: Don't warn when delete inode fails on ro filesystem

[Christoph Hellwig]

On Wed, Jun 10, 2009 at 09:30:51AM +0100, Steven Whitehouse wrote:
> If the filesystem is read-only, then we expect that delete inode
> will fail, so there is no need to warn about it.

Umm, ->delete_inode should never be called on a read-only filesystem
by the VFS.

[Cluster-devel] Re: [PATCH 10/24] GFS2: Don't warn when delete inode fails on ro filesystem

[Steven Whitehouse]

Hi,

On Wed, 2009-06-10 at 05:49 -0400, Christoph Hellwig wrote:
> On Wed, Jun 10, 2009 at 09:30:51AM +0100, Steven Whitehouse wrote:
> > If the filesystem is read-only, then we expect that delete inode
> > will fail, so there is no need to warn about it.
> 
> Umm, ->delete_inode should never be called on a read-only filesystem
> by the VFS.
> 

On a single node, thats true. With multiple nodes, some mounted ro and
some mounted rw, sometimes the ro node gets the baton passed to it, if
it happens to have a process holding open an inode thats been unlinked
on the rw node. In that case it has to ignore it and one of the rw nodes
will deal with the deallocation later,

Steve.