X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fgfs2%2Fops_fstype.c;h=c1309ed1c4969e355cade447a6422f46ba9f0aa1;hb=2e531fa0d0868f5114c2b3a782ab02eb9d6f914d;hp=cf5aa50505488d95a62719f9728660e742728575;hpb=bb9bcf061660661c57ddcf31337529f82414b937;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index cf5aa50..c1309ed 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -17,28 +17,56 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/lm_interface.h>
+#include <linux/slow-work.h>
+#include <linux/quotaops.h>
 
 #include "gfs2.h"
 #include "incore.h"
-#include "daemon.h"
+#include "bmap.h"
 #include "glock.h"
 #include "glops.h"
 #include "inode.h"
-#include "lm.h"
-#include "mount.h"
-#include "ops_fstype.h"
-#include "ops_super.h"
 #include "recovery.h"
 #include "rgrp.h"
 #include "super.h"
 #include "sys.h"
 #include "util.h"
+#include "log.h"
+#include "quota.h"
+#include "dir.h"
+#include "trace_gfs2.h"
 
 #define DO 0
 #define UNDO 1
 
-extern struct dentry_operations gfs2_dops;
+static const u32 gfs2_old_fs_formats[] = {
+        0
+};
+
+static const u32 gfs2_old_multihost_formats[] = {
+        0
+};
+
+/**
+ * gfs2_tune_init - Fill a gfs2_tune structure with default values
+ * @gt: tune
+ *
+ */
+
+static void gfs2_tune_init(struct gfs2_tune *gt)
+{
+	spin_lock_init(&gt->gt_spin);
+
+	gt->gt_incore_log_blocks = 1024;
+	gt->gt_logd_secs = 1;
+	gt->gt_quota_simul_sync = 64;
+	gt->gt_quota_warn_period = 10;
+	gt->gt_quota_scale_num = 1;
+	gt->gt_quota_scale_den = 1;
+	gt->gt_new_files_jdata = 0;
+	gt->gt_max_readahead = 1 << 18;
+	gt->gt_complain_secs = 10;
+}
 
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
@@ -53,42 +81,40 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	gfs2_tune_init(&sdp->sd_tune);
 
-	INIT_LIST_HEAD(&sdp->sd_reclaim_list);
-	spin_lock_init(&sdp->sd_reclaim_lock);
-	init_waitqueue_head(&sdp->sd_reclaim_wq);
-
-	mutex_init(&sdp->sd_inum_mutex);
+	init_waitqueue_head(&sdp->sd_glock_wait);
+	atomic_set(&sdp->sd_glock_disposal, 0);
 	spin_lock_init(&sdp->sd_statfs_spin);
-	mutex_init(&sdp->sd_statfs_mutex);
 
 	spin_lock_init(&sdp->sd_rindex_spin);
 	mutex_init(&sdp->sd_rindex_mutex);
 	INIT_LIST_HEAD(&sdp->sd_rindex_list);
 	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
-	INIT_LIST_HEAD(&sdp->sd_rindex_recent_list);
 
 	INIT_LIST_HEAD(&sdp->sd_jindex_list);
 	spin_lock_init(&sdp->sd_jindex_spin);
 	mutex_init(&sdp->sd_jindex_mutex);
 
 	INIT_LIST_HEAD(&sdp->sd_quota_list);
-	spin_lock_init(&sdp->sd_quota_spin);
 	mutex_init(&sdp->sd_quota_mutex);
+	init_waitqueue_head(&sdp->sd_quota_wait);
+	INIT_LIST_HEAD(&sdp->sd_trunc_list);
+	spin_lock_init(&sdp->sd_trunc_lock);
 
 	spin_lock_init(&sdp->sd_log_lock);
 
-	INIT_LIST_HEAD(&sdp->sd_log_le_gl);
 	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
 	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
 	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
 	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
 
 	mutex_init(&sdp->sd_log_reserve_mutex);
 	INIT_LIST_HEAD(&sdp->sd_ail1_list);
 	INIT_LIST_HEAD(&sdp->sd_ail2_list);
 
 	init_rwsem(&sdp->sd_log_flush_lock);
-	INIT_LIST_HEAD(&sdp->sd_log_flush_list);
+	atomic_set(&sdp->sd_log_in_flight, 0);
+	init_waitqueue_head(&sdp->sd_log_flush_wait);
 
 	INIT_LIST_HEAD(&sdp->sd_revoke_list);
 
@@ -97,21 +123,267 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	return sdp;
 }
 
-static void init_vfs(struct super_block *sb, unsigned noatime)
+
+/**
+ * gfs2_check_sb - Check superblock
+ * @sdp: the filesystem
+ * @sb: The superblock
+ * @silent: Don't print a message if the check fails
+ *
+ * Checks the version code of the FS is one that we understand how to
+ * read and that the sizes of the various on-disk structures have not
+ * changed.
+ */
+
+static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 {
-	struct gfs2_sbd *sdp = sb->s_fs_info;
+	unsigned int x;
 
-	sb->s_magic = GFS2_MAGIC;
-	sb->s_op = &gfs2_super_ops;
-	sb->s_export_op = &gfs2_export_ops;
-	sb->s_time_gran = 1;
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	if (sb->sb_magic != GFS2_MAGIC ||
+	    sb->sb_type != GFS2_METATYPE_SB) {
+		if (!silent)
+			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+		return -EINVAL;
+	}
+
+	/*  If format numbers match exactly, we're done.  */
+
+	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
+	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
+		return 0;
+
+	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
+		for (x = 0; gfs2_old_fs_formats[x]; x++)
+			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
+				break;
+
+		if (!gfs2_old_fs_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
+		for (x = 0; gfs2_old_multihost_formats[x]; x++)
+			if (gfs2_old_multihost_formats[x] ==
+			    sb->sb_multihost_format)
+				break;
+
+		if (!gfs2_old_multihost_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!sdp->sd_args.ar_upgrade) {
+		printk(KERN_WARNING
+		       "GFS2: code version (%u, %u) is incompatible "
+		       "with ondisk format (%u, %u)\n",
+		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+		       sb->sb_fs_format, sb->sb_multihost_format);
+		printk(KERN_INFO
+		       "GFS2: Use the \"upgrade\" mount option to upgrade "
+		       "the FS\n");
+		printk(KERN_INFO "GFS2: See the manual for more details\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void end_bio_io_page(struct bio *bio, int error)
+{
+	struct page *page = bio->bi_private;
+
+	if (!error)
+		SetPageUptodate(page);
+	else
+		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
+	unlock_page(page);
+}
+
+static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
+{
+	const struct gfs2_sb *str = buf;
+
+	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
+	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
+	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
+	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
+	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
+	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
+	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
+
+	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_uuid, str->sb_uuid, 16);
+}
+
+/**
+ * gfs2_read_super - Read the gfs2 super block from disk
+ * @sdp: The GFS2 super block
+ * @sector: The location of the super block
+ * @error: The error code to return
+ *
+ * This uses the bio functions to read the super block from disk
+ * because we want to be 100% sure that we never read cached data.
+ * A super block is read twice only during each GFS2 mount and is
+ * never written to by the filesystem. The first time its read no
+ * locks are held, and the only details which are looked at are those
+ * relating to the locking protocol. Once locking is up and working,
+ * the sb is read again under the lock to establish the location of
+ * the master directory (contains pointers to journals etc) and the
+ * root directory.
+ *
+ * Returns: 0 on success or error
+ */
+
+static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_sb *p;
+	struct page *page;
+	struct bio *bio;
+
+	page = alloc_page(GFP_NOFS);
+	if (unlikely(!page))
+		return -ENOBUFS;
+
+	ClearPageUptodate(page);
+	ClearPageDirty(page);
+	lock_page(page);
+
+	bio = bio_alloc(GFP_NOFS, 1);
+	bio->bi_sector = sector * (sb->s_blocksize >> 9);
+	bio->bi_bdev = sb->s_bdev;
+	bio_add_page(bio, page, PAGE_SIZE, 0);
+
+	bio->bi_end_io = end_bio_io_page;
+	bio->bi_private = page;
+	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
+	wait_on_page_locked(page);
+	bio_put(bio);
+	if (!PageUptodate(page)) {
+		__free_page(page);
+		return -EIO;
+	}
+	p = kmap(page);
+	gfs2_sb_in(&sdp->sd_sb, p);
+	kunmap(page);
+	__free_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_read_sb - Read super block
+ * @sdp: The GFS2 superblock
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
+{
+	u32 hash_blocks, ind_blocks, leaf_blocks;
+	u32 tmp_blocks;
+	unsigned int x;
+	int error;
+
+	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+	if (error) {
+		if (!silent)
+			fs_err(sdp, "can't read superblock\n");
+		return error;
+	}
+
+	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+	if (error)
+		return error;
+
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+			       GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_dinode)) / sizeof(u64);
+	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
+	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
+	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
+	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
+	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_meta_header)) /
+			        sizeof(struct gfs2_quota_change);
+
+	/* Compute maximum reservation required to add a entry to a directory */
+
+	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+			     sdp->sd_jbsize);
+
+	ind_blocks = 0;
+	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
+		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
+		ind_blocks += tmp_blocks;
+	}
+
+	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
 
-	if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
-		set_bit(noatime, &sdp->sd_flags);
+	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
 
-	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
-	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_dinode);
+	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_heightsize[x - 1] || m)
+			break;
+		sdp->sd_heightsize[x] = space;
+	}
+	sdp->sd_max_height = x;
+	sdp->sd_heightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
+
+	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
+				 sizeof(struct gfs2_dinode);
+	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_jheightsize[x - 1] || m)
+			break;
+		sdp->sd_jheightsize[x] = space;
+	}
+	sdp->sd_max_jheight = x;
+	sdp->sd_jheightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
+
+	return 0;
 }
 
 static int init_names(struct gfs2_sbd *sdp, int silent)
@@ -142,10 +414,11 @@ static int init_names(struct gfs2_sbd *sdp, int silent)
 	if (!table[0])
 		table = sdp->sd_vfs->s_id;
 
-	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
-	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
+	strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN);
+	strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN);
 
-	while ((table = strchr(sdp->sd_table_name, '/')))
+	table = sdp->sd_table_name;
+	while ((table = strchr(table, '/')))
 		*table = '_';
 
 out:
@@ -155,32 +428,11 @@ out:
 static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
 			int undo)
 {
-	struct task_struct *p;
 	int error = 0;
 
 	if (undo)
 		goto fail_trans;
 
-	p = kthread_run(gfs2_scand, sdp, "gfs2_scand");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start scand thread: %d\n", error);
-		return error;
-	}
-	sdp->sd_scand_process = p;
-
-	for (sdp->sd_glockd_num = 0;
-	     sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
-	     sdp->sd_glockd_num++) {
-		p = kthread_run(gfs2_glockd, sdp, "gfs2_glockd");
-		error = IS_ERR(p);
-		if (error) {
-			fs_err(sdp, "can't start glockd thread: %d\n", error);
-			goto fail;
-		}
-		sdp->sd_glockd_process[sdp->sd_glockd_num] = p;
-	}
-
 	error = gfs2_glock_nq_num(sdp,
 				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
 				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
@@ -213,7 +465,6 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
 		fs_err(sdp, "can't create transaction glock: %d\n", error);
 		goto fail_rename;
 	}
-	set_bit(GLF_STICKY, &sdp->sd_trans_gl->gl_flags);
 
 	return 0;
 
@@ -226,58 +477,62 @@ fail_live:
 fail_mount:
 	gfs2_glock_dq_uninit(mount_gh);
 fail:
-	while (sdp->sd_glockd_num--)
-		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
-
-	kthread_stop(sdp->sd_scand_process);
 	return error;
 }
 
-static inline struct inode *gfs2_lookup_root(struct super_block *sb,
-					     u64 no_addr)
+static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
+			    u64 no_addr, const char *name)
 {
-	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct dentry *dentry;
+	struct inode *inode;
+
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	if (IS_ERR(inode)) {
+		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
+		return PTR_ERR(inode);
+	}
+	dentry = d_alloc_root(inode);
+	if (!dentry) {
+		fs_err(sdp, "can't alloc %s dentry\n", name);
+		iput(inode);
+		return -ENOMEM;
+	}
+	dentry->d_op = &gfs2_dops;
+	*dptr = dentry;
+	return 0;
 }
 
-static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
+static int init_sb(struct gfs2_sbd *sdp, int silent)
 {
 	struct super_block *sb = sdp->sd_vfs;
 	struct gfs2_holder sb_gh;
 	u64 no_addr;
-	struct inode *inode;
-	int error = 0;
+	int ret;
 
-	if (undo) {
-		if (sb->s_root) {
-			dput(sb->s_root);
-			sb->s_root = NULL;
-		}
-		return 0;
+	ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+				LM_ST_SHARED, 0, &sb_gh);
+	if (ret) {
+		fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
+		return ret;
 	}
 
-	error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
-				 LM_ST_SHARED, 0, &sb_gh);
-	if (error) {
-		fs_err(sdp, "can't acquire superblock glock: %d\n", error);
-		return error;
-	}
-
-	error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
-	if (error) {
-		fs_err(sdp, "can't read superblock: %d\n", error);
+	ret = gfs2_read_sb(sdp, silent);
+	if (ret) {
+		fs_err(sdp, "can't read superblock: %d\n", ret);
 		goto out;
 	}
 
 	/* Set up the buffer cache and SB for real */
-	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
-		error = -EINVAL;
+	if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) {
+		ret = -EINVAL;
 		fs_err(sdp, "FS block size (%u) is too small for device "
 		       "block size (%u)\n",
-		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
+		       sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev));
 		goto out;
 	}
 	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
-		error = -EINVAL;
+		ret = -EINVAL;
 		fs_err(sdp, "FS block size (%u) is too big for machine "
 		       "page size (%u)\n",
 		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
@@ -287,47 +542,179 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
 
 	/* Get the root inode */
 	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
-	if (sb->s_type == &gfs2meta_fs_type)
-		no_addr = sdp->sd_sb.sb_master_dir.no_addr;
-	inode = gfs2_lookup_root(sb, no_addr);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		fs_err(sdp, "can't read in root inode: %d\n", error);
+	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
+	if (ret)
 		goto out;
-	}
 
-	sb->s_root = d_alloc_root(inode);
-	if (!sb->s_root) {
-		fs_err(sdp, "can't get root dentry\n");
-		error = -ENOMEM;
-		iput(inode);
+	/* Get the master inode */
+	no_addr = sdp->sd_sb.sb_master_dir.no_addr;
+	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
+	if (ret) {
+		dput(sdp->sd_root_dir);
+		goto out;
 	}
-	sb->s_root->d_op = &gfs2_dops;
+	sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
+	return ret;
+}
+
+/**
+ * map_journal_extents - create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal.  This will save
+ * us time when writing journal blocks.  Most journals will have only one
+ * extent that maps all their logical blocks.  That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential.  Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out.  But it's still possible.  These journals might have
+ * several extents.
+ *
+ * TODO: This should be done in bigger chunks rather than one block at a time,
+ *       but since it's only done at mount time, I'm not worried about the
+ *       time it takes.
+ */
+static int map_journal_extents(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd = sdp->sd_jdesc;
+	unsigned int lb;
+	u64 db, prev_db; /* logical block, disk block, prev disk block */
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_journal_extent *jext = NULL;
+	struct buffer_head bh;
+	int rc = 0;
+
+	prev_db = 0;
+
+	for (lb = 0; lb < ip->i_disksize >> sdp->sd_sb.sb_bsize_shift; lb++) {
+		bh.b_state = 0;
+		bh.b_blocknr = 0;
+		bh.b_size = 1 << ip->i_inode.i_blkbits;
+		rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
+		db = bh.b_blocknr;
+		if (rc || !db) {
+			printk(KERN_INFO "GFS2 journal mapping error %d: lb="
+			       "%u db=%llu\n", rc, lb, (unsigned long long)db);
+			break;
+		}
+		if (!prev_db || db != prev_db + 1) {
+			jext = kzalloc(sizeof(struct gfs2_journal_extent),
+				       GFP_KERNEL);
+			if (!jext) {
+				printk(KERN_INFO "GFS2 error: out of memory "
+				       "mapping journal extents.\n");
+				rc = -ENOMEM;
+				break;
+			}
+			jext->dblock = db;
+			jext->lblock = lb;
+			jext->blocks = 1;
+			list_add_tail(&jext->extent_list, &jd->extent_list);
+		} else {
+			jext->blocks++;
+		}
+		prev_db = db;
+	}
+	return rc;
+}
+
+static void gfs2_others_may_mount(struct gfs2_sbd *sdp)
+{
+	char *message = "FIRSTMOUNT=Done";
+	char *envp[] = { message, NULL };
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ls->ls_first_done = 1;
+	kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
+}
+
+/**
+ * gfs2_jindex_hold - Grab a lock on the jindex
+ * @sdp: The GFS2 superblock
+ * @ji_gh: the holder for the jindex glock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
+{
+	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
+	struct qstr name;
+	char buf[20];
+	struct gfs2_jdesc *jd;
+	int error;
+
+	name.name = buf;
+
+	mutex_lock(&sdp->sd_jindex_mutex);
+
+	for (;;) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
+		if (error)
+			break;
+
+		name.len = sprintf(buf, "journal%u", sdp->sd_journals);
+		name.hash = gfs2_disk_hash(name.name, name.len);
+
+		error = gfs2_dir_check(sdp->sd_jindex, &name, NULL);
+		if (error == -ENOENT) {
+			error = 0;
+			break;
+		}
+
+		gfs2_glock_dq_uninit(ji_gh);
+
+		if (error)
+			break;
+
+		error = -ENOMEM;
+		jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
+		if (!jd)
+			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)
+				error = -ENOENT;
+			else
+				error = PTR_ERR(jd->jd_inode);
+			kfree(jd);
+			break;
+		}
+
+		spin_lock(&sdp->sd_jindex_spin);
+		jd->jd_jid = sdp->sd_journals++;
+		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
+		spin_unlock(&sdp->sd_jindex_spin);
+	}
+
+	mutex_unlock(&sdp->sd_jindex_mutex);
+
 	return error;
 }
 
 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(sdp->sd_master_dir, "jindex");
+	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
 	if (IS_ERR(sdp->sd_jindex)) {
 		fs_err(sdp, "can't lookup journal index: %d\n", error);
 		return PTR_ERR(sdp->sd_jindex);
 	}
 	ip = GFS2_I(sdp->sd_jindex);
-	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
 
 	/* Load in the journal index special file */
 
@@ -337,7 +724,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail;
 	}
 
-	error = -EINVAL;
+	error = -EUSERS;
 	if (!gfs2_jindex_size(sdp)) {
 		fs_err(sdp, "no journals!\n");
 		goto fail_jindex;
@@ -345,7 +732,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 	if (sdp->sd_args.ar_spectator) {
 		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
-		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
 	} else {
 		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
 			fs_err(sdp, "can't mount journal #%u\n",
@@ -368,7 +755,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | GL_EXACT,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal inode glock: %d\n",
@@ -382,8 +769,12 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 			       sdp->sd_jdesc->jd_jid, error);
 			goto fail_jinode_gh;
 		}
-		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+
+		/* Map the extents for this journal's blocks */
+		map_journal_extents(sdp);
 	}
+	trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
 
 	if (sdp->sd_lockstruct.ls_first) {
 		unsigned int x;
@@ -396,7 +787,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 			}
 		}
 
-		gfs2_lm_others_may_mount(sdp);
+		gfs2_others_may_mount(sdp);
 	} else if (!sdp->sd_args.ar_spectator) {
 		error = gfs2_recover_journal(sdp->sd_jdesc);
 		if (error) {
@@ -409,18 +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);
@@ -441,53 +822,35 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 {
 	int error = 0;
 	struct gfs2_inode *ip;
-	struct inode *inode;
+	struct inode *master = sdp->sd_master_dir->d_inode;
 
 	if (undo)
 		goto fail_qinode;
 
-	inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		fs_err(sdp, "can't read in master directory: %d\n", error);
-		goto fail;
-	}
-	sdp->sd_master_dir = inode;
-
 	error = init_journal(sdp, undo);
 	if (error)
-		goto fail_master;
-
-	/* Read in the master inode number inode */
-	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
-	if (IS_ERR(sdp->sd_inum_inode)) {
-		error = PTR_ERR(sdp->sd_inum_inode);
-		fs_err(sdp, "can't read in inum inode: %d\n", error);
-		goto fail_journal;
-	}
-
+		goto fail;
 
 	/* Read in the master statfs inode */
-	sdp->sd_statfs_inode = gfs2_lookup_simple(sdp->sd_master_dir, "statfs");
+	sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
 	if (IS_ERR(sdp->sd_statfs_inode)) {
 		error = PTR_ERR(sdp->sd_statfs_inode);
 		fs_err(sdp, "can't read in statfs inode: %d\n", error);
-		goto fail_inum;
+		goto fail_journal;
 	}
 
 	/* Read in the resource index inode */
-	sdp->sd_rindex = gfs2_lookup_simple(sdp->sd_master_dir, "rindex");
+	sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
 	if (IS_ERR(sdp->sd_rindex)) {
 		error = PTR_ERR(sdp->sd_rindex);
 		fs_err(sdp, "can't get resource index inode: %d\n", error);
 		goto fail_statfs;
 	}
 	ip = GFS2_I(sdp->sd_rindex);
-	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
-	sdp->sd_rindex_vn = ip->i_gl->gl_vn - 1;
+	sdp->sd_rindex_uptodate = 0;
 
 	/* Read in the quota inode */
-	sdp->sd_quota_inode = gfs2_lookup_simple(sdp->sd_master_dir, "quota");
+	sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
 	if (IS_ERR(sdp->sd_quota_inode)) {
 		error = PTR_ERR(sdp->sd_quota_inode);
 		fs_err(sdp, "can't get quota file inode: %d\n", error);
@@ -502,12 +865,8 @@ fail_rindex:
 	iput(sdp->sd_rindex);
 fail_statfs:
 	iput(sdp->sd_statfs_inode);
-fail_inum:
-	iput(sdp->sd_inum_inode);
 fail_journal:
 	init_journal(sdp, UNDO);
-fail_master:
-	iput(sdp->sd_master_dir);
 fail:
 	return error;
 }
@@ -518,6 +877,7 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 	char buf[30];
 	int error = 0;
 	struct gfs2_inode *ip;
+	struct inode *master = sdp->sd_master_dir->d_inode;
 
 	if (sdp->sd_args.ar_spectator)
 		return 0;
@@ -525,27 +885,19 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 	if (undo)
 		goto fail_qc_gh;
 
-	pn = gfs2_lookup_simple(sdp->sd_master_dir, "per_node");
+	pn = gfs2_lookup_simple(master, "per_node");
 	if (IS_ERR(pn)) {
 		error = PTR_ERR(pn);
 		fs_err(sdp, "can't find per_node directory: %d\n", error);
 		return error;
 	}
 
-	sprintf(buf, "inum_range%u", sdp->sd_jdesc->jd_jid);
-	sdp->sd_ir_inode = gfs2_lookup_simple(pn, buf);
-	if (IS_ERR(sdp->sd_ir_inode)) {
-		error = PTR_ERR(sdp->sd_ir_inode);
-		fs_err(sdp, "can't find local \"ir\" file: %d\n", error);
-		goto fail;
-	}
-
 	sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
 	sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
 	if (IS_ERR(sdp->sd_sc_inode)) {
 		error = PTR_ERR(sdp->sd_sc_inode);
 		fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
-		goto fail_ir_i;
+		goto fail;
 	}
 
 	sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
@@ -559,27 +911,16 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 	iput(pn);
 	pn = NULL;
 
-	ip = GFS2_I(sdp->sd_ir_inode);
-	error = gfs2_glock_nq_init(ip->i_gl,
-				   LM_ST_EXCLUSIVE, 0,
-				   &sdp->sd_ir_gh);
-	if (error) {
-		fs_err(sdp, "can't lock local \"ir\" file: %d\n", error);
-		goto fail_qc_i;
-	}
-
 	ip = GFS2_I(sdp->sd_sc_inode);
-	error = gfs2_glock_nq_init(ip->i_gl,
-				   LM_ST_EXCLUSIVE, 0,
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
 				   &sdp->sd_sc_gh);
 	if (error) {
 		fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
-		goto fail_ir_gh;
+		goto fail_qc_i;
 	}
 
 	ip = GFS2_I(sdp->sd_qc_inode);
-	error = gfs2_glock_nq_init(ip->i_gl,
-				   LM_ST_EXCLUSIVE, 0,
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
 				   &sdp->sd_qc_gh);
 	if (error) {
 		fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
@@ -592,14 +933,10 @@ fail_qc_gh:
 	gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
 fail_ut_gh:
 	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
-fail_ir_gh:
-	gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
 fail_qc_i:
 	iput(sdp->sd_qc_inode);
 fail_ut_i:
 	iput(sdp->sd_sc_inode);
-fail_ir_i:
-	iput(sdp->sd_ir_inode);
 fail:
 	if (pn)
 		iput(pn);
@@ -615,7 +952,6 @@ static int init_threads(struct gfs2_sbd *sdp, int undo)
 		goto fail_quotad;
 
 	sdp->sd_log_flush_time = jiffies;
-	sdp->sd_jindex_refresh_time = jiffies;
 
 	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
 	error = IS_ERR(p);
@@ -625,9 +961,6 @@ static int init_threads(struct gfs2_sbd *sdp, int undo)
 	}
 	sdp->sd_logd_process = p;
 
-	sdp->sd_statfs_sync_time = jiffies;
-	sdp->sd_quota_sync_time = jiffies;
-
 	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
 	error = IS_ERR(p);
 	if (error) {
@@ -646,6 +979,139 @@ fail:
 	return error;
 }
 
+static const match_table_t nolock_tokens = {
+	{ Opt_jid, "jid=%d\n", },
+	{ Opt_err, NULL },
+};
+
+static void nolock_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	kmem_cache_free(cachep, gl);
+	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+		wake_up(&sdp->sd_glock_wait);
+}
+
+static const struct lm_lockops nolock_ops = {
+	.lm_proto_name = "lock_nolock",
+	.lm_put_lock = nolock_put_lock,
+	.lm_tokens = &nolock_tokens,
+};
+
+/**
+ * gfs2_lm_mount - mount a locking protocol
+ * @sdp: the filesystem
+ * @args: mount arguments
+ * @silent: if 1, don't complain if the FS isn't a GFS2 fs
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
+{
+	const struct lm_lockops *lm;
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	struct gfs2_args *args = &sdp->sd_args;
+	const char *proto = sdp->sd_proto_name;
+	const char *table = sdp->sd_table_name;
+	const char *fsname;
+	char *o, *options;
+	int ret;
+
+	if (!strcmp("lock_nolock", proto)) {
+		lm = &nolock_ops;
+		sdp->sd_args.ar_localflocks = 1;
+		sdp->sd_args.ar_localcaching = 1;
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+	} else if (!strcmp("lock_dlm", proto)) {
+		lm = &gfs2_dlm_ops;
+#endif
+	} else {
+		printk(KERN_INFO "GFS2: can't find protocol %s\n", proto);
+		return -ENOENT;
+	}
+
+	fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table);
+
+	ls->ls_ops = lm;
+	ls->ls_first = 1;
+
+	for (options = args->ar_hostdata; (o = strsep(&options, ":")); ) {
+		substring_t tmp[MAX_OPT_ARGS];
+		int token, option;
+
+		if (!o || !*o)
+			continue;
+
+		token = match_token(o, *lm->lm_tokens, tmp);
+		switch (token) {
+		case Opt_jid:
+			ret = match_int(&tmp[0], &option);
+			if (ret || option < 0) 
+				goto hostdata_error;
+			ls->ls_jid = option;
+			break;
+		case Opt_id:
+			/* Obsolete, but left for backward compat purposes */
+			break;
+		case Opt_first:
+			ret = match_int(&tmp[0], &option);
+			if (ret || (option != 0 && option != 1))
+				goto hostdata_error;
+			ls->ls_first = option;
+			break;
+		case Opt_nodir:
+			ret = match_int(&tmp[0], &option);
+			if (ret || (option != 0 && option != 1))
+				goto hostdata_error;
+			ls->ls_nodir = option;
+			break;
+		case Opt_err:
+		default:
+hostdata_error:
+			fs_info(sdp, "unknown hostdata (%s)\n", o);
+			return -EINVAL;
+		}
+	}
+
+	if (sdp->sd_args.ar_spectator)
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", table);
+	else
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table,
+			 sdp->sd_lockstruct.ls_jid);
+
+	fsname = strchr(table, ':');
+	if (fsname)
+		fsname++;
+	if (lm->lm_mount == NULL) {
+		fs_info(sdp, "Now mounting FS...\n");
+		return 0;
+	}
+	ret = lm->lm_mount(sdp, fsname);
+	if (ret == 0)
+		fs_info(sdp, "Joined cluster. Now mounting FS...\n");
+	return ret;
+}
+
+void gfs2_lm_unmount(struct gfs2_sbd *sdp)
+{
+	const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
+	    lm->lm_unmount)
+		lm->lm_unmount(sdp);
+}
+
+void gfs2_online_uevent(struct gfs2_sbd *sdp)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	char ro[20];
+	char spectator[20];
+	char *envp[] = { ro, spectator, NULL };
+	sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
+	sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
+	kobject_uevent_env(&sdp->sd_kobj, KOBJ_ONLINE, envp);
+}
+
 /**
  * fill_super - Read in superblock
  * @sb: The VFS superblock
@@ -655,7 +1121,7 @@ fail:
  * Returns: errno
  */
 
-static int fill_super(struct super_block *sb, void *data, int silent)
+static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent)
 {
 	struct gfs2_sbd *sdp;
 	struct gfs2_holder mount_gh;
@@ -666,14 +1132,25 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 		printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
 		return -ENOMEM;
 	}
+	sdp->sd_args = *args;
 
-	error = gfs2_mount_args(sdp, (char *)data, 0);
-	if (error) {
-		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
-		goto fail;
+	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;
+	if (sdp->sd_args.ar_nobarrier)
+		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
 
-	init_vfs(sb, SDF_NOATIME);
+	sb->s_magic = GFS2_MAGIC;
+	sb->s_op = &gfs2_super_ops;
+	sb->s_export_op = &gfs2_export_ops;
+	sb->s_xattr = gfs2_xattr_handlers;
+	sb->s_qcop = &gfs2_quotactl_ops;
+	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+	sb->s_time_gran = 1;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
 
 	/* Set up the buffer cache and fill in some fake block size values
 	   to allow us to read-in the on-disk superblock. */
@@ -683,6 +1160,17 @@ 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;
+	sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum;
+	if (sdp->sd_args.ar_statfs_quantum) {
+		sdp->sd_tune.gt_statfs_slow = 0;
+		sdp->sd_tune.gt_statfs_quantum = sdp->sd_args.ar_statfs_quantum;
+	}
+	else {
+		sdp->sd_tune.gt_statfs_slow = 1;
+		sdp->sd_tune.gt_statfs_quantum = 30;
+	}
+
 	error = init_names(sdp, silent);
 	if (error)
 		goto fail;
@@ -701,7 +1189,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 	if (error)
 		goto fail_lm;
 
-	error = init_sb(sdp, silent, DO);
+	error = init_sb(sdp, silent);
 	if (error)
 		goto fail_locking;
 
@@ -732,7 +1220,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	gfs2_glock_dq_uninit(&mount_gh);
-
+	gfs2_online_uevent(sdp);
 	return 0;
 
 fail_threads:
@@ -742,14 +1230,19 @@ fail_per_node:
 fail_inodes:
 	init_inodes(sdp, UNDO);
 fail_sb:
-	init_sb(sdp, 0, UNDO);
+	if (sdp->sd_root_dir)
+		dput(sdp->sd_root_dir);
+	if (sdp->sd_master_dir)
+		dput(sdp->sd_master_dir);
+	if (sb->s_root)
+		dput(sb->s_root);
+	sb->s_root = NULL;
 fail_locking:
 	init_locking(sdp, &mount_gh, UNDO);
 fail_lm:
-	gfs2_gl_hash_clear(sdp, WAIT);
+	invalidate_inodes(sb);
+	gfs2_gl_hash_clear(sdp);
 	gfs2_lm_unmount(sdp);
-	while (invalidate_inodes(sb))
-		yield();
 fail_sys:
 	gfs2_sys_fs_del(sdp);
 fail:
@@ -759,153 +1252,181 @@ fail:
 	return error;
 }
 
-static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data, struct vfsmount *mnt)
-{
-	struct super_block *sb;
-	struct gfs2_sbd *sdp;
-	int error = get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
-	if (error)
-		goto out;
-	sb = mnt->mnt_sb;
-	sdp = sb->s_fs_info;
-	sdp->sd_gfs2mnt = mnt;
-out:
-	return error;
-}
-
-static int fill_super_meta(struct super_block *sb, struct super_block *new,
-			   void *data, int silent)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct inode *inode;
-	int error = 0;
-
-	new->s_fs_info = sdp;
-	sdp->sd_vfs_meta = sb;
-
-	init_vfs(new, SDF_NOATIME);
-
-        /* Get the master inode */
-	inode = igrab(sdp->sd_master_dir);
-
-	new->s_root = d_alloc_root(inode);
-	if (!new->s_root) {
-		fs_err(sdp, "can't get root dentry\n");
-		error = -ENOMEM;
-		iput(inode);
-	} else
-		new->s_root->d_op = &gfs2_dops;
-
-	return error;
-}
-
-static int set_bdev_super(struct super_block *s, void *data)
+static int set_gfs2_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
+
+	/*
+	 * We set the bdi here to the queue backing, file systems can
+	 * overwrite this in ->fill_super()
+	 */
+	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
-static int test_bdev_super(struct super_block *s, void *data)
+static int test_gfs2_super(struct super_block *s, void *ptr)
 {
-	return s->s_bdev == data;
+	struct block_device *bdev = ptr;
+	return (bdev == s->s_bdev);
 }
 
-static struct super_block* get_gfs2_sb(const char *dev_name)
+/**
+ * gfs2_get_sb - Get the GFS2 superblock
+ * @fs_type: The GFS2 filesystem type
+ * @flags: Mount flags
+ * @dev_name: The name of the device
+ * @data: The mount arguments
+ * @mnt: The vfsmnt for this mount
+ *
+ * Q. Why not use get_sb_bdev() ?
+ * A. We need to select one of two root directories to mount, independent
+ *    of whether this is the initial, or subsequent, mount of this sb
+ *
+ * Returns: 0 or -ve on error
+ */
+
+static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	struct kstat stat;
-	struct nameidata nd;
-	struct file_system_type *fstype;
-	struct super_block *sb = NULL, *s;
-	struct list_head *l;
+	struct block_device *bdev;
+	struct super_block *s;
+	fmode_t mode = FMODE_READ;
 	int error;
+	struct gfs2_args args;
+	struct gfs2_sbd *sdp;
 
-	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
+	if (!(flags & MS_RDONLY))
+		mode |= FMODE_WRITE;
+
+	bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+
+	/*
+	 * once the super is inserted into the list by sget, s_umount
+	 * will protect the lockfs code from trying to start a snapshot
+	 * while we are mounting
+	 */
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (bdev->bd_fsfreeze_count > 0) {
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		error = -EBUSY;
+		goto error_bdev;
+	}
+	s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev);
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	error = PTR_ERR(s);
+	if (IS_ERR(s))
+		goto error_bdev;
+
+	memset(&args, 0, sizeof(args));
+	args.ar_quota = GFS2_QUOTA_DEFAULT;
+	args.ar_data = GFS2_DATA_DEFAULT;
+	args.ar_commit = 60;
+	args.ar_statfs_quantum = 30;
+	args.ar_quota_quantum = 60;
+	args.ar_errors = GFS2_ERRORS_DEFAULT;
+
+	error = gfs2_mount_args(&args, data);
 	if (error) {
-		printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
-		       dev_name);
-		goto out;
+		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
+		if (s->s_root)
+			goto error_super;
+		deactivate_locked_super(s);
+		return error;
 	}
-	error = vfs_getattr(nd.mnt, nd.dentry, &stat);
 
-	fstype = get_fs_type("gfs2");
-	list_for_each(l, &fstype->fs_supers) {
-		s = list_entry(l, struct super_block, s_instances);
-		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
-		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
-			sb = s;
-			goto free_nd;
+	if (s->s_root) {
+		error = -EBUSY;
+		if ((flags ^ s->s_flags) & MS_RDONLY)
+			goto error_super;
+		close_bdev_exclusive(bdev, mode);
+	} else {
+		char b[BDEVNAME_SIZE];
+
+		s->s_flags = flags;
+		s->s_mode = mode;
+		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		sb_set_blocksize(s, block_size(bdev));
+		error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
+		if (error) {
+			deactivate_locked_super(s);
+			return error;
 		}
+		s->s_flags |= MS_ACTIVE;
+		bdev->bd_super = s;
 	}
 
-	printk(KERN_WARNING "GFS2: Unrecognized block device or "
-	       "mount point %s\n", dev_name);
+	sdp = s->s_fs_info;
+	mnt->mnt_sb = s;
+	if (args.ar_meta)
+		mnt->mnt_root = dget(sdp->sd_master_dir);
+	else
+		mnt->mnt_root = dget(sdp->sd_root_dir);
+	return 0;
 
-free_nd:
-	path_release(&nd);
-out:
-	return sb;
+error_super:
+	deactivate_locked_super(s);
+error_bdev:
+	close_bdev_exclusive(bdev, mode);
+	return error;
+}
+
+static int set_meta_super(struct super_block *s, void *ptr)
+{
+	return -EINVAL;
 }
 
 static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 			    const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	int error = 0;
-	struct super_block *sb = NULL, *new;
+	struct super_block *s;
 	struct gfs2_sbd *sdp;
+	struct path path;
+	int error;
 
-	sb = get_gfs2_sb(dev_name);
-	if (!sb) {
+	error = kern_path(dev_name, LOOKUP_FOLLOW, &path);
+	if (error) {
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
+		       dev_name, error);
+		return error;
+	}
+	s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super,
+		 path.dentry->d_inode->i_sb->s_bdev);
+	path_put(&path);
+	if (IS_ERR(s)) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-		error = -ENOENT;
-		goto error;
+		return PTR_ERR(s);
 	}
-	sdp = (struct gfs2_sbd*) sb->s_fs_info;
-	if (sdp->sd_vfs_meta) {
-		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
-		error = -EBUSY;
-		goto error;
-	}
-	down(&sb->s_bdev->bd_mount_sem);
-	new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
-	up(&sb->s_bdev->bd_mount_sem);
-	if (IS_ERR(new)) {
-		error = PTR_ERR(new);
-		goto error;
-	}
-	module_put(fs_type->owner);
-	new->s_flags = flags;
-	strlcpy(new->s_id, sb->s_id, sizeof(new->s_id));
-	sb_set_blocksize(new, sb->s_blocksize);
-	error = fill_super_meta(sb, new, data, flags & MS_SILENT ? 1 : 0);
-	if (error) {
-		up_write(&new->s_umount);
-		deactivate_super(new);
-		goto error;
+	if ((flags ^ s->s_flags) & MS_RDONLY) {
+		deactivate_locked_super(s);
+		return -EBUSY;
 	}
-
-	new->s_flags |= MS_ACTIVE;
-
-	/* Grab a reference to the gfs2 mount point */
-	atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
-	return simple_set_mnt(mnt, new);
-error:
-	return error;
+	sdp = s->s_fs_info;
+	mnt->mnt_sb = s;
+	mnt->mnt_root = dget(sdp->sd_master_dir);
+	return 0;
 }
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	gfs2_delete_debugfs_file(sb->s_fs_info);
-	kill_block_super(sb);
-}
-
-static void gfs2_kill_sb_meta(struct super_block *sb)
-{
 	struct gfs2_sbd *sdp = sb->s_fs_info;
-	generic_shutdown_super(sb);
-	sdp->sd_vfs_meta = NULL;
-	atomic_dec(&sdp->sd_gfs2mnt->mnt_count);
+
+	if (sdp == NULL) {
+		kill_block_super(sb);
+		return;
+	}
+
+	gfs2_meta_syncfs(sdp);
+	dput(sdp->sd_root_dir);
+	dput(sdp->sd_master_dir);
+	sdp->sd_root_dir = NULL;
+	sdp->sd_master_dir = NULL;
+	shrink_dcache_sb(sb);
+	kill_block_super(sb);
+	gfs2_delete_debugfs_file(sdp);
+	kfree(sdp);
 }
 
 struct file_system_type gfs2_fs_type = {
@@ -920,7 +1441,6 @@ struct file_system_type gfs2meta_fs_type = {
 	.name = "gfs2meta",
 	.fs_flags = FS_REQUIRES_DEV,
 	.get_sb = gfs2_get_sb_meta,
-	.kill_sb = gfs2_kill_sb_meta,
 	.owner = THIS_MODULE,
 };