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

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

[Steven Whitehouse]

I'm guessing that the merge window opening might not be too far
away now, and in any case, I won't have quite my normal internet
access next week. So I'm pushing out the current GFS2 tree so
that (I hope) there will be time to fix any issues.

Again, there are fewer patches here. A lot of them are fairly small
too. The most noteable item deals with the meta filesystem which
was in response to Al Viro's suggestions concerning a better way
to structure that code. It certainly results in a much cleaner
implementation, so thanks go to Al for pointing that out.

A couple of new features: I/O barrier support (needs no user
configuration, see the patch for details) and UUID support
(no code changes, its all userland but we reserve space in
the super block, again details in the patch itself).

I know that I hardly need say, but please let me know if you have any
comments :-)

Steve.

[Cluster-devel] [PATCH 01/12] GFS2: Fix debugfs glock file iterator

[Steven Whitehouse]

Due to an incorrect iterator, some glocks were being missed from the
glock dumps obtained via debugfs. This patch fixes the problem and
ensures that we don't miss any glocks in future.

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

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 13391e5..4cbb695 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1816,15 +1816,17 @@ restart:
 	if (gl) {
 		gi->gl = hlist_entry(gl->gl_list.next,
 				     struct gfs2_glock, gl_list);
-		if (gi->gl)
-			gfs2_glock_hold(gi->gl);
+	} else {
+		gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+				     struct gfs2_glock, gl_list);
 	}
+	if (gi->gl)
+		gfs2_glock_hold(gi->gl);
 	read_unlock(gl_lock_addr(gi->hash));
 	if (gl)
 		gfs2_glock_put(gl);
-	if (gl && gi->gl == NULL)
-		gi->hash++;
 	while (gi->gl == NULL) {
+		gi->hash++;
 		if (gi->hash >= GFS2_GL_HASH_SIZE)
 			return 1;
 		read_lock(gl_lock_addr(gi->hash));
@@ -1833,7 +1835,6 @@ restart:
 		if (gi->gl)
 			gfs2_glock_hold(gi->gl);
 		read_unlock(gl_lock_addr(gi->hash));
-		gi->hash++;
 	}
 
 	if (gi->sdp != gi->gl->gl_sbd)
-- 
1.5.5.1

[Cluster-devel] [PATCH 02/12] GFS2: Fix metafs mounts

[Steven Whitehouse]

This patch is intended to fix the issues reported in bz #457798. Instead
of having the metafs as a separate filesystem, it becomes a second root
of gfs2. As a result it will appear as type gfs2 in /proc/mounts, but it
is still possible (for backwards compatibility purposes) to mount it as
type gfs2meta. A new mount flag "meta" is introduced so that its possible
to tell the two cases apart in /proc/mounts.

As a result it becomes possible to mount type gfs2 with -o meta and
get the same result as mounting type gfs2meta. So it is possible to
mount just the metafs on its own. Currently if you do this, its then
impossible to mount the "normal" root of the gfs2 filesystem without
first unmounting the metafs root. I'm not sure if thats a feature or
a bug :-)

Either way, this is a great improvement on the previous scheme and I've
verified that it works ok with bind mounts on both the "normal" root
and the metafs root in various combinations.

There were also a bunch of functions in super.c which didn't belong there,
so this moves them into ops_fstype.c where they can be static. Hopefully
the mount/umount sequence is now more obvious as a result.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Alexander Viro <aviro@redhat.com>

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 448697a..a1777a1 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -400,6 +400,7 @@ struct gfs2_args {
 	int ar_quota; /* off/account/on */
 	int ar_suiddir; /* suiddir support */
 	int ar_data; /* ordered/writeback */
+	int ar_meta; /* mount metafs */
 };
 
 struct gfs2_tune {
@@ -461,7 +462,6 @@ struct gfs2_sb_host {
 
 struct gfs2_sbd {
 	struct super_block *sd_vfs;
-	struct super_block *sd_vfs_meta;
 	struct kobject sd_kobj;
 	unsigned long sd_flags;	/* SDF_... */
 	struct gfs2_sb_host sd_sb;
@@ -499,7 +499,9 @@ struct gfs2_sbd {
 
 	/* Inode Stuff */
 
-	struct inode *sd_master_dir;
+	struct dentry *sd_master_dir;
+	struct dentry *sd_root_dir;
+
 	struct inode *sd_jindex;
 	struct inode *sd_inum_inode;
 	struct inode *sd_statfs_inode;
@@ -634,7 +636,6 @@ struct gfs2_sbd {
 	/* Debugging crud */
 
 	unsigned long sd_last_warning;
-	struct vfsmount *sd_gfs2mnt;
 	struct dentry *debugfs_dir;    /* debugfs directory */
 	struct dentry *debugfs_dentry_glocks; /* for debugfs */
 };
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index b941f9f..df48333 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -42,6 +42,7 @@ enum {
 	Opt_nosuiddir,
 	Opt_data_writeback,
 	Opt_data_ordered,
+	Opt_meta,
 	Opt_err,
 };
 
@@ -66,6 +67,7 @@ static match_table_t tokens = {
 	{Opt_nosuiddir, "nosuiddir"},
 	{Opt_data_writeback, "data=writeback"},
 	{Opt_data_ordered, "data=ordered"},
+	{Opt_meta, "meta"},
 	{Opt_err, NULL}
 };
 
@@ -239,6 +241,11 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
 			break;
+		case Opt_meta:
+			if (remount && args->ar_meta != 1)
+				goto cant_remount;
+			args->ar_meta = 1;
+			break;
 		case Opt_err:
 		default:
 			fs_info(sdp, "unknown option: %s\n", o);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b4d1d64..a6225cc 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -40,6 +40,45 @@
 #define DO 0
 #define UNDO 1
 
+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_demote_secs = 300;
+	gt->gt_incore_log_blocks = 1024;
+	gt->gt_log_flush_secs = 60;
+	gt->gt_recoverd_secs = 60;
+	gt->gt_logd_secs = 1;
+	gt->gt_quotad_secs = 5;
+	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_quota_cache_secs = 300;
+	gt->gt_quota_quantum = 60;
+	gt->gt_atime_quantum = 3600;
+	gt->gt_new_files_jdata = 0;
+	gt->gt_max_readahead = 1 << 18;
+	gt->gt_stall_secs = 600;
+	gt->gt_complain_secs = 10;
+	gt->gt_statfs_quantum = 30;
+	gt->gt_statfs_slow = 0;
+}
+
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp;
@@ -113,6 +152,272 @@ static void init_vfs(struct super_block *sb, unsigned noatime)
 	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
 }
 
+/**
+ * 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)
+{
+	unsigned int x;
+
+	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);
+}
+
+/**
+ * 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);
+	if (unlikely(!bio)) {
+		__free_page(page);
+		return -ENOBUFS;
+	}
+
+	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
+ * @gl: the glock for the superblock (assumed to be held)
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+static int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, 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;
+
+	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
+
+	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)
 {
 	char *proto, *table;
@@ -224,51 +529,59 @@ fail:
 	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, 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, sb_gh.gh_gl, 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;
+		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));
 		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);
@@ -278,26 +591,21 @@ 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);
-	} else
-		sb->s_root->d_op = &gfs2_dops;
-	
+	/* 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 = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
-	return error;
+	return ret;
 }
 
 /**
@@ -372,6 +680,7 @@ static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
 
 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;
@@ -383,7 +692,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail_recoverd;
 	}
 
-	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);
@@ -506,25 +815,17 @@ 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;
+		goto fail;
 
 	/* Read in the master inode number inode */
-	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
+	sdp->sd_inum_inode = gfs2_lookup_simple(master, "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);
@@ -533,7 +834,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 
 
 	/* 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);
@@ -541,7 +842,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 	}
 
 	/* 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);
@@ -552,7 +853,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 	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);
@@ -571,8 +872,6 @@ fail_inum:
 	iput(sdp->sd_inum_inode);
 fail_journal:
 	init_journal(sdp, UNDO);
-fail_master:
-	iput(sdp->sd_master_dir);
 fail:
 	return error;
 }
@@ -583,6 +882,7 @@ 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;
@@ -590,7 +890,7 @@ 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);
@@ -828,7 +1128,7 @@ 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;
 
@@ -869,7 +1169,11 @@ 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);
+	sb->s_root = NULL;
 fail_locking:
 	init_locking(sdp, &mount_gh, UNDO);
 fail_lm:
@@ -887,151 +1191,60 @@ fail:
 }
 
 static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data, struct vfsmount *mnt)
+		       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;
+	return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
 }
 
-static int fill_super_meta(struct super_block *sb, struct super_block *new,
-			   void *data, int silent)
+static struct super_block *get_gfs2_sb(const char *dev_name)
 {
-	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)
-{
-	s->s_bdev = data;
-	s->s_dev = s->s_bdev->bd_dev;
-	return 0;
-}
-
-static int test_bdev_super(struct super_block *s, void *data)
-{
-	return s->s_bdev == data;
-}
-
-static struct super_block* get_gfs2_sb(const char *dev_name)
-{
-	struct kstat stat;
+	struct super_block *sb;
 	struct nameidata nd;
-	struct super_block *sb = NULL, *s;
 	int error;
 
 	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
 	if (error) {
-		printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
-		       dev_name);
-		goto out;
-	}
-	error = vfs_getattr(nd.path.mnt, nd.path.dentry, &stat);
-
-	list_for_each_entry(s, &gfs2_fs_type.fs_supers, s_instances) {
-		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
-		    (S_ISDIR(stat.mode) &&
-		     s == nd.path.dentry->d_inode->i_sb)) {
-			sb = s;
-			goto free_nd;
-		}
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
+		       dev_name, error);
+		return NULL;
 	}
-
-	printk(KERN_WARNING "GFS2: Unrecognized block device or "
-	       "mount point %s\n", dev_name);
-
-free_nd:
+	sb = nd.path.dentry->d_inode->i_sb;
+	if (sb && (sb->s_type == &gfs2_fs_type))
+		atomic_inc(&sb->s_active);
+	else
+		sb = NULL;
 	path_put(&nd.path);
-out:
 	return sb;
 }
 
 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 *sb = NULL;
 	struct gfs2_sbd *sdp;
 
 	sb = get_gfs2_sb(dev_name);
 	if (!sb) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-		error = -ENOENT;
-		goto error;
+		return -ENOENT;
 	}
 	sdp = 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;
-	}
-	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;
-	}
-
-	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;
+	mnt->mnt_sb = sb;
+	mnt->mnt_root = dget(sdp->sd_master_dir);
+	return 0;
 }
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	if (sb->s_fs_info) {
-		gfs2_delete_debugfs_file(sb->s_fs_info);
-		gfs2_meta_syncfs(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);
+	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);
 }
 
 struct file_system_type gfs2_fs_type = {
@@ -1046,7 +1259,6 @@ 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,
 };
 
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index f66ea0f..8f332d2 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -63,6 +63,39 @@ static int gfs2_write_inode(struct inode *inode, int sync)
 }
 
 /**
+ * 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;
+}
+
+/**
  * gfs2_put_super - Unmount the filesystem
  * @sb: The VFS superblock
  *
@@ -73,12 +106,6 @@ static void gfs2_put_super(struct super_block *sb)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int error;
 
-	if (!sdp)
-		return;
-
-	if (!strncmp(sb->s_type->name, "gfs2meta", 8))
-		return; /* Nothing to do */
-
 	/*  Unfreeze the filesystem, if we need to  */
 
 	mutex_lock(&sdp->sd_freeze_lock);
@@ -101,7 +128,6 @@ static void gfs2_put_super(struct super_block *sb)
 
 	/*  Release stuff  */
 
-	iput(sdp->sd_master_dir);
 	iput(sdp->sd_jindex);
 	iput(sdp->sd_inum_inode);
 	iput(sdp->sd_statfs_inode);
@@ -152,6 +178,7 @@ static void gfs2_write_super(struct super_block *sb)
  *
  * Flushes the log to disk.
  */
+
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
 	sb->s_dirt = 0;
@@ -295,6 +322,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
  * 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);
@@ -333,6 +361,16 @@ static void gfs2_clear_inode(struct inode *inode)
 	}
 }
 
+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
@@ -346,6 +384,8 @@ 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;
 
+	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])
@@ -414,6 +454,7 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
  * 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;
@@ -478,8 +519,6 @@ out:
 	clear_inode(inode);
 }
 
-
-
 static struct inode *gfs2_alloc_inode(struct super_block *sb)
 {
 	struct gfs2_inode *ip;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ca83199..c3ba3d9 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -33,313 +33,6 @@
 #include "trans.h"
 #include "util.h"
 
-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
- *
- */
-
-void gfs2_tune_init(struct gfs2_tune *gt)
-{
-	spin_lock_init(&gt->gt_spin);
-
-	gt->gt_demote_secs = 300;
-	gt->gt_incore_log_blocks = 1024;
-	gt->gt_log_flush_secs = 60;
-	gt->gt_recoverd_secs = 60;
-	gt->gt_logd_secs = 1;
-	gt->gt_quotad_secs = 5;
-	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_quota_cache_secs = 300;
-	gt->gt_quota_quantum = 60;
-	gt->gt_atime_quantum = 3600;
-	gt->gt_new_files_jdata = 0;
-	gt->gt_max_readahead = 1 << 18;
-	gt->gt_stall_secs = 600;
-	gt->gt_complain_secs = 10;
-	gt->gt_statfs_quantum = 30;
-	gt->gt_statfs_slow = 0;
-}
-
-/**
- * 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.
- */
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
-{
-	unsigned int x;
-
-	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);
-}
-
-/**
- * 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
- */
-
-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);
-	if (unlikely(!bio)) {
-		__free_page(page);
-		return -ENOBUFS;
-	}
-
-	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
- * @gl: the glock for the superblock (assumed to be held)
- * @silent: Don't print message if mount fails
- *
- */
-
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, 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;
-
-	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
-
-	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;
-}
-
 /**
  * gfs2_jindex_hold - Grab a lock on the jindex
  * @sdp: The GFS2 superblock
@@ -581,39 +274,6 @@ fail:
 	return error;
 }
 
-/**
- * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
- * @sdp: the filesystem
- *
- * Returns: errno
- */
-
-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 void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
 {
 	const struct gfs2_statfs_change *str = buf;
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 44361ec..50a4c9b 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -12,11 +12,6 @@
 
 #include "incore.h"
 
-void gfs2_tune_init(struct gfs2_tune *gt);
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent);
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent);
-int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector);
 void gfs2_lm_unmount(struct gfs2_sbd *sdp);
 
 static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
@@ -40,7 +35,6 @@ int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
 			      struct gfs2_inode **ipp);
 
 int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
 
 int gfs2_statfs_init(struct gfs2_sbd *sdp);
 void gfs2_statfs_change(struct gfs2_sbd *sdp,
-- 
1.5.5.1

[Cluster-devel] [PATCH 03/12] GFS2: rm on multiple nodes causes panic

[Steven Whitehouse]

From: Bob Peterson <rpeterso@redhat.com>

This patch fixes a problem whereby simultaneous unlink, rmdir,
rename and link operations (e.g. rm -fR *) from multiple nodes
on the same GFS2 file system can cause kernel panics, hangs,
and/or memory corruption.  It also gets rid of all the non-rgrp
calls to gfs2_glock_nq_m.

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

diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index e2c62f7..35f6f03 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -159,9 +159,13 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
 
-	error = gfs2_glock_nq_m(2, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
 
 	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
 	if (error)
@@ -245,8 +249,10 @@ out_alloc:
 	if (alloc_required)
 		gfs2_alloc_put(dip);
 out_gunlock:
-	gfs2_glock_dq_m(2, ghs);
-out:
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_glock_dq(ghs);
+out_parent:
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
 	if (!error) {
@@ -302,7 +308,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
-		goto out_rgrp;
+		goto out_gunlock;
 
 	error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
 	if (error)
@@ -316,6 +322,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 out_end_trans:
 	gfs2_trans_end(sdp);
+out_gunlock:
 	gfs2_glock_dq(ghs + 2);
 out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
@@ -485,7 +492,6 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	struct gfs2_holder ri_gh;
 	int error;
 
-
 	error = gfs2_rindex_hold(sdp, &ri_gh);
 	if (error)
 		return error;
@@ -495,9 +501,17 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
 	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
-	error = gfs2_glock_nq_m(3, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
@@ -523,11 +537,15 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
 	gfs2_trans_end(sdp);
 
 out_gunlock:
-	gfs2_glock_dq_m(3, ghs);
-out:
-	gfs2_holder_uninit(ghs);
-	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
 	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
@@ -639,9 +657,11 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
 	}
 
-	error = gfs2_glock_nq_m(num_gh, ghs);
-	if (error)
-		goto out_uninit;
+	for (x = 0; x < num_gh; x++) {
+		error = gfs2_glock_nq(ghs + x);
+		if (error)
+			goto out_gunlock;
+	}
 
 	/* Check out the old directory */
 
@@ -804,10 +824,10 @@ out_alloc:
 	if (alloc_required)
 		gfs2_alloc_put(ndip);
 out_gunlock:
-	gfs2_glock_dq_m(num_gh, ghs);
-out_uninit:
-	for (x = 0; x < num_gh; x++)
+	while (x--) {
+		gfs2_glock_dq(ghs + x);
 		gfs2_holder_uninit(ghs + x);
+	}
 out_gunlock_r:
 	if (dir_rename)
 		gfs2_glock_dq_uninit(&r_gh);
-- 
1.5.5.1

[Cluster-devel] [PATCH 04/12] GFS2: Fix & clean up GFS2 rename

[Steven Whitehouse]

This patch fixes a locking issue in the rename code by ensuring that we hold
the per sb rename lock over both directory and "other" renames which involve
different parent directories.

At the same time, this moved the (only called from one place) function
gfs2_ok_to_move into the file that its called from, so we can mark it
static. This should make a code a bit easier to follow.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Peter Staubach <staubach@redhat.com>

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8b0806a..8752552 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1140,54 +1140,6 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 	return 0;
 }
 
-/*
- * gfs2_ok_to_move - check if it's ok to move a directory to another directory
- * @this: move this
- * @to: to here
- *
- * Follow @to back to the root and make sure we don't encounter @this
- * Assumes we already hold the rename lock.
- *
- * Returns: errno
- */
-
-int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
-{
-	struct inode *dir = &to->i_inode;
-	struct super_block *sb = dir->i_sb;
-	struct inode *tmp;
-	struct qstr dotdot;
-	int error = 0;
-
-	gfs2_str2qstr(&dotdot, "..");
-
-	igrab(dir);
-
-	for (;;) {
-		if (dir == &this->i_inode) {
-			error = -EINVAL;
-			break;
-		}
-		if (dir == sb->s_root->d_inode) {
-			error = 0;
-			break;
-		}
-
-		tmp = gfs2_lookupi(dir, &dotdot, 1);
-		if (IS_ERR(tmp)) {
-			error = PTR_ERR(tmp);
-			break;
-		}
-
-		iput(dir);
-		dir = tmp;
-	}
-
-	iput(dir);
-
-	return error;
-}
-
 /**
  * gfs2_readlinki - return the contents of a symlink
  * @ip: the symlink's inode
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 58f9607..bfd2afc 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -91,7 +91,6 @@ int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
 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_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
 int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
 int gfs2_glock_nq_atime(struct gfs2_holder *gh);
 int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 35f6f03..534e1e2 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -589,6 +589,54 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
 	return 0;
 }
 
+/*
+ * gfs2_ok_to_move - check if it's ok to move a directory to another directory
+ * @this: move this
+ * @to: to here
+ *
+ * Follow @to back to the root and make sure we don't encounter @this
+ * Assumes we already hold the rename lock.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
+{
+	struct inode *dir = &to->i_inode;
+	struct super_block *sb = dir->i_sb;
+	struct inode *tmp;
+	struct qstr dotdot;
+	int error = 0;
+
+	gfs2_str2qstr(&dotdot, "..");
+
+	igrab(dir);
+
+	for (;;) {
+		if (dir == &this->i_inode) {
+			error = -EINVAL;
+			break;
+		}
+		if (dir == sb->s_root->d_inode) {
+			error = 0;
+			break;
+		}
+
+		tmp = gfs2_lookupi(dir, &dotdot, 1);
+		if (IS_ERR(tmp)) {
+			error = PTR_ERR(tmp);
+			break;
+		}
+
+		iput(dir);
+		dir = tmp;
+	}
+
+	iput(dir);
+
+	return error;
+}
+
 /**
  * gfs2_rename - Rename a file
  * @odir: Parent directory of old file name
@@ -607,7 +655,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
 	struct gfs2_inode *nip = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(odir);
-	struct gfs2_holder ghs[5], r_gh;
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
@@ -621,19 +669,20 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			return 0;
 	}
 
-	/* Make sure we aren't trying to move a dirctory into it's subdir */
 
-	if (S_ISDIR(ip->i_inode.i_mode) && odip != ndip) {
-		dir_rename = 1;
-
-		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE, 0,
-					   &r_gh);
+	if (odip != ndip) {
+		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
+					   0, &r_gh);
 		if (error)
 			goto out;
 
-		error = gfs2_ok_to_move(ip, ndip);
-		if (error)
-			goto out_gunlock_r;
+		if (S_ISDIR(ip->i_inode.i_mode)) {
+			dir_rename = 1;
+			/* don't move a dirctory into it's subdir */
+			error = gfs2_ok_to_move(ip, ndip);
+			if (error)
+				goto out_gunlock_r;
+		}
 	}
 
 	num_gh = 1;
@@ -829,7 +878,7 @@ out_gunlock:
 		gfs2_holder_uninit(ghs + x);
 	}
 out_gunlock_r:
-	if (dir_rename)
+	if (r_gh.gh_gl)
 		gfs2_glock_dq_uninit(&r_gh);
 out:
 	return error;
-- 
1.5.5.1

[Cluster-devel] [PATCH 05/12] GFS2: Fix race relating to glock min-hold time

[Steven Whitehouse]

In the case that a request for a glock arrives right after the
grant reply has arrived, it sometimes means that the gl_tstamp
field hasn't been updated recently enough. The net result is that
the min-hold time for the glock is ignored. If this happens
often enough, it leads to poor performance.

This patch adds an additional test, so that if the reply pending
bit is set on a glock, then it will select the maximum length of
time for the min-hold time, rather than looking at gl_tstamp.

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

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 4cbb695..806e1eb 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1265,6 +1265,8 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
 	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
 	if (time_before(now, holdtime))
 		delay = holdtime - now;
+	if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
 
 	spin_lock(&gl->gl_spin);
 	handle_callback(gl, state, 1, delay);
-- 
1.5.5.1

[Cluster-devel] [PATCH 06/12] GFS2: Use an IS_ERR test rather than a NULL test

[Steven Whitehouse]

From: Julien Brunel <brunel@diku.dk>

In case of error, the function gfs2_inode_lookup returns an
ERR pointer, but never returns a NULL pointer. So a NULL test that
necessarily comes after an IS_ERR test should be deleted, and a NULL
test that may come after a call to this function should be
strengthened by an IS_ERR test.

The semantic match that finds this problem is as follows:
(http://www.emn.fr/x-info/coccinelle/)

// <smpl>
@match_bad_null_test@
expression x, E;
statement S1,S2;
@@
x = gfs2_inode_lookup(...)
... when != x = E
* if (x != NULL)
S1 else S2
// </smpl>

Signed-off-by:  Julien Brunel <brunel@diku.dk>
Signed-off-by:  Julia Lawall <julia@diku.dk>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8752552..c8a959c 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1033,13 +1033,11 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 
 	if (bh)
 		brelse(bh);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
 	return inode;
 
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
-	if (inode)
+	if (inode && !IS_ERR(inode))
 		iput(inode);
 fail_gunlock:
 	gfs2_glock_dq(ghs);
-- 
1.5.5.1

[Cluster-devel] [PATCH 07/12] GFS2: Direct IO write at end of file error

[Steven Whitehouse]

From: Bob Peterson <rpeterso@redhat.com>

This patch fixes a problem whereby a direct_io write doesn't fall
back to buffered write properly at end of file.

Signed-off-by: Bob Peterson <rpeterso@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 e64a1b0..ae7126a 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -975,7 +975,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
 	if (gfs2_is_stuffed(ip))
 		return 0;
 
-	if (offset > i_size_read(&ip->i_inode))
+	if (offset >= i_size_read(&ip->i_inode))
 		return 0;
 	return 1;
 }
-- 
1.5.5.1

[Cluster-devel] [PATCH 08/12] GFS2: GFS2 will panic if you misspell any mount options

[Steven Whitehouse]

From: Abhijith Das <adas@redhat.com>

The gfs2 superblock pointer is NULL after a failed mount. When control
eventually goes to gfs2_kill_sb, we dereference this NULL pointer. This
patch ensures that the gfs2 superblock pointer is not NULL before being
dereferenced in gfs2_kill_sb.

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

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index a6225cc..ae35f09 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1237,14 +1237,17 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 static void gfs2_kill_sb(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
-	gfs2_meta_syncfs(sdp);
-	dput(sdp->sd_root_dir);
-	dput(sdp->sd_master_dir);
-	sdp->sd_root_dir = NULL;
-	sdp->sd_master_dir = NULL;
+	if (sdp) {
+		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);
+	if (sdp)
+		gfs2_delete_debugfs_file(sdp);
 }
 
 struct file_system_type gfs2_fs_type = {
-- 
1.5.5.1

[Cluster-devel] [PATCH 09/12] GFS2: The war on bloat

[Steven Whitehouse]

The following patch shrinks the gfs2_args structure which is embedded in
every GFS2 superblock. It cuts down the size of the options to a single
unsigned int (the 13 bits of bitfields will be rounded up to that size
by the compiler) from the current 11 unsigned ints. So on x86 thats 44
bytes shrinking to 4 bytes, in each and every GFS2 superblock.

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

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a1777a1..b2c5784 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -386,21 +386,21 @@ struct gfs2_statfs_change_host {
 #define GFS2_DATA_ORDERED	2
 
 struct gfs2_args {
-	char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
-	char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
-	char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */
-	int ar_spectator; /* Don't get a journal because we're always RO */
-	int ar_ignore_local_fs; /* Don't optimize even if local_fs is 1 */
-	int ar_localflocks; /* Let the VFS do flock|fcntl locks for us */
-	int ar_localcaching; /* Local-style caching (dangerous on multihost) */
-	int ar_debug; /* Oops on errors instead of trying to be graceful */
-	int ar_upgrade; /* Upgrade ondisk/multihost format */
-	unsigned int ar_num_glockd; /* Number of glockd threads */
-	int ar_posix_acl; /* Enable posix acls */
-	int ar_quota; /* off/account/on */
-	int ar_suiddir; /* suiddir support */
-	int ar_data; /* ordered/writeback */
-	int ar_meta; /* mount metafs */
+	char ar_lockproto[GFS2_LOCKNAME_LEN];	/* Name of the Lock Protocol */
+	char ar_locktable[GFS2_LOCKNAME_LEN];	/* Name of the Lock Table */
+	char ar_hostdata[GFS2_LOCKNAME_LEN];	/* Host specific data */
+	unsigned int ar_spectator:1;		/* Don't get a journal */
+	unsigned int ar_ignore_local_fs:1;	/* Ignore optimisations */
+	unsigned int ar_localflocks:1;		/* Let the VFS do flock|fcntl */
+	unsigned int ar_localcaching:1;		/* Local caching */
+	unsigned int ar_debug:1;		/* Oops on errors */
+	unsigned int ar_upgrade:1;		/* Upgrade ondisk format */
+	unsigned int ar_posix_acl:1;		/* Enable posix acls */
+	unsigned int ar_quota:2;		/* off/account/on */
+	unsigned int ar_suiddir:1;		/* suiddir support */
+	unsigned int ar_data:2;			/* ordered/writeback */
+	unsigned int ar_meta:1;			/* mount metafs */
+	unsigned int ar_num_glockd;		/* Number of glockd threads */
 };
 
 struct gfs2_tune {
-- 
1.5.5.1

[Cluster-devel] [PATCH 10/12] GFS2: high time to take some time over atime

[Steven Whitehouse]

Until now, we've used the same scheme as GFS1 for atime. This has failed
since atime is a per vfsmnt flag, not a per fs flag and as such the
"noatime" flag was not getting passed down to the filesystems. This
patch removes all the "special casing" around atime updates and we
simply use the VFS's atime code.

The net result is that GFS2 will now support all the same atime related
mount options of any other filesystem on a per-vfsmnt basis. We do lose
the "lazy atime" updates, but we gain "relatime". We could add lazy
atime to the VFS at a later date, if there is a requirement for that
variant still - I suspect relatime will be enough.

Also we lose about 100 lines of code after this patch has been applied,
and I have a suspicion that it will speed things up a bit, even when
atime is "on". So it seems like a nice clean up as well.

From a user perspective, everything stays the same except the loss of
the per-fs atime quantum tweekable (ought to be per-vfsmnt at the very
least, and to be honest I don't think anybody ever used it) and that a
number of options which were ignored before now work correctly.

Please let me know if you've got any comments. I'm pushing this out
early so that you can all see what my plans are.

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

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 806e1eb..c962283 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1580,8 +1580,6 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
 		*p++ = 'a';
 	if (flags & GL_EXACT)
 		*p++ = 'E';
-	if (flags & GL_ATIME)
-		*p++ = 'a';
 	if (flags & GL_NOCACHE)
 		*p++ = 'c';
 	if (test_bit(HIF_HOLDER, &iflags))
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 971d92a..695c6b1 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -24,7 +24,6 @@
 #define GL_ASYNC		0x00000040
 #define GL_EXACT		0x00000080
 #define GL_SKIP			0x00000100
-#define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
 
 #define GLR_TRYFAILED		13
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index b2c5784..f1ed3a1 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -420,7 +420,6 @@ struct gfs2_tune {
 	unsigned int gt_quota_scale_den; /* Denominator */
 	unsigned int gt_quota_cache_secs;
 	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
-	unsigned int gt_atime_quantum; /* Min secs between atime updates */
 	unsigned int gt_new_files_jdata;
 	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
 	unsigned int gt_stall_secs; /* Detects trouble! */
@@ -433,7 +432,6 @@ enum {
 	SDF_JOURNAL_CHECKED	= 0,
 	SDF_JOURNAL_LIVE	= 1,
 	SDF_SHUTDOWN		= 2,
-	SDF_NOATIME		= 3,
 };
 
 #define GFS2_FSNAME_LEN		256
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index c8a959c..7cee695 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -18,6 +18,7 @@
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
 #include <linux/security.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -249,6 +250,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 {
 	struct gfs2_dinode_host *di = &ip->i_di;
 	const struct gfs2_dinode *str = buf;
+	struct timespec atime;
 	u16 height, depth;
 
 	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
@@ -275,8 +277,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	di->di_size = be64_to_cpu(str->di_size);
 	i_size_write(&ip->i_inode, di->di_size);
 	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
-	ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime);
-	ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	atime.tv_sec = be64_to_cpu(str->di_atime);
+	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+		ip->i_inode.i_atime = atime;
 	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
 	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
 	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
@@ -1157,8 +1161,8 @@ int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
 	unsigned int x;
 	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-	error = gfs2_glock_nq_atime(&i_gh);
+	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;
@@ -1193,101 +1197,6 @@ out:
 	return error;
 }
 
-/**
- * gfs2_glock_nq_atime - Acquire a hold on an inode's glock, and
- *       conditionally update the inode's atime
- * @gh: the holder to acquire
- *
- * Tests atime (access time) for gfs2_read, gfs2_readdir and gfs2_mmap
- * Update if the difference between the current time and the inode's current
- * atime is greater than an interval specified at mount.
- *
- * Returns: errno
- */
-
-int gfs2_glock_nq_atime(struct gfs2_holder *gh)
-{
-	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
-	struct gfs2_inode *ip = gl->gl_object;
-	s64 quantum = gfs2_tune_get(sdp, gt_atime_quantum);
-	unsigned int state;
-	int flags;
-	int error;
-	struct timespec tv = CURRENT_TIME;
-
-	if (gfs2_assert_warn(sdp, gh->gh_flags & GL_ATIME) ||
-	    gfs2_assert_warn(sdp, !(gh->gh_flags & GL_ASYNC)) ||
-	    gfs2_assert_warn(sdp, gl->gl_ops == &gfs2_inode_glops))
-		return -EINVAL;
-
-	state = gh->gh_state;
-	flags = gh->gh_flags;
-
-	error = gfs2_glock_nq(gh);
-	if (error)
-		return error;
-
-	if (test_bit(SDF_NOATIME, &sdp->sd_flags) ||
-	    (sdp->sd_vfs->s_flags & MS_RDONLY))
-		return 0;
-
-	if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-		gfs2_glock_dq(gh);
-		gfs2_holder_reinit(LM_ST_EXCLUSIVE, gh->gh_flags & ~LM_FLAG_ANY,
-				   gh);
-		error = gfs2_glock_nq(gh);
-		if (error)
-			return error;
-
-		/* Verify that atime hasn't been updated while we were
-		   trying to get exclusive lock. */
-
-		tv = CURRENT_TIME;
-		if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-			struct buffer_head *dibh;
-			struct gfs2_dinode *di;
-
-			error = gfs2_trans_begin(sdp, RES_DINODE, 0);
-			if (error == -EROFS)
-				return 0;
-			if (error)
-				goto fail;
-
-			error = gfs2_meta_inode_buffer(ip, &dibh);
-			if (error)
-				goto fail_end_trans;
-
-			ip->i_inode.i_atime = tv;
-
-			gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-			di = (struct gfs2_dinode *)dibh->b_data;
-			di->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
-			di->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
-			brelse(dibh);
-
-			gfs2_trans_end(sdp);
-		}
-
-		/* If someone else has asked for the glock,
-		   unlock and let them have it. Then reacquire
-		   in the original state. */
-		if (gfs2_glock_is_blocking(gl)) {
-			gfs2_glock_dq(gh);
-			gfs2_holder_reinit(state, flags, gh);
-			return gfs2_glock_nq(gh);
-		}
-	}
-
-	return 0;
-
-fail_end_trans:
-	gfs2_trans_end(sdp);
-fail:
-	gfs2_glock_dq(gh);
-	return error;
-}
-
 static int
 __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index bfd2afc..2d43f69 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -92,7 +92,6 @@ 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_glock_nq_atime(struct gfs2_holder *gh);
 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);
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index ae7126a..2756381 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -512,8 +512,8 @@ static int gfs2_readpage(struct file *file, struct page *page)
 	int error;
 
 	unlock_page(page);
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	error = gfs2_glock_nq_atime(&gh);
+	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;
@@ -594,8 +594,8 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 	struct gfs2_holder gh;
 	int ret;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	ret = gfs2_glock_nq_atime(&gh);
+	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))
@@ -636,8 +636,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	unsigned to = from + len;
 	struct page *page;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &ip->i_gh);
-	error = gfs2_glock_nq_atime(&ip->i_gh);
+	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;
 
@@ -1000,8 +1000,8 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	 * unfortunately have the option of only flushing a range like
 	 * the VFS does.
 	 */
-	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
-	rv = gfs2_glock_nq_atime(&gh);
+	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);
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index e9a366d..3a747f8 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -89,8 +89,8 @@ static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
 	u64 offset = file->f_pos;
 	int error;
 
-	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
-	error = gfs2_glock_nq_atime(&d_gh);
+	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;
@@ -153,8 +153,8 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
 	int error;
 	u32 fsflags;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-	error = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
 	if (error)
 		return error;
 
@@ -351,8 +351,8 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 	struct gfs2_alloc *al;
 	int ret;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &gh);
-	ret = gfs2_glock_nq_atime(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
 	if (ret)
 		goto out;
 
@@ -434,8 +434,8 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 	struct gfs2_holder i_gh;
 	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-	error = gfs2_glock_nq_atime(&i_gh);
+	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;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index ae35f09..b117fcf 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -70,7 +70,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 	gt->gt_quota_scale_den = 1;
 	gt->gt_quota_cache_secs = 300;
 	gt->gt_quota_quantum = 60;
-	gt->gt_atime_quantum = 3600;
 	gt->gt_new_files_jdata = 0;
 	gt->gt_max_readahead = 1 << 18;
 	gt->gt_stall_secs = 600;
@@ -135,22 +134,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	return sdp;
 }
 
-static void init_vfs(struct super_block *sb, unsigned noatime)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-
-	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->s_flags & (MS_NOATIME | MS_NODIRATIME))
-		set_bit(noatime, &sdp->sd_flags);
-
-	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
-	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
-}
 
 /**
  * gfs2_check_sb - Check superblock
@@ -1100,7 +1083,11 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 	}
 
-	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_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. */
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index 8f332d2..d5355d9 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -20,6 +20,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -38,6 +39,7 @@
 #include "dir.h"
 #include "eattr.h"
 #include "bmap.h"
+#include "meta_io.h"
 
 /**
  * gfs2_write_inode - Make sure the inode is stable on the disk
@@ -50,16 +52,41 @@
 static int gfs2_write_inode(struct inode *inode, int sync)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-
-	/* Check this is a "normal" inode */
-	if (test_bit(GIF_USER, &ip->i_flags)) {
-		if (current->flags & PF_MEMALLOC)
-			return 0;
-		if (sync)
-			gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	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);
 	}
-
-	return 0;
+	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;
 }
 
 /**
@@ -297,14 +324,6 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
-	if (*flags & (MS_NOATIME | MS_NODIRATIME))
-		set_bit(SDF_NOATIME, &sdp->sd_flags);
-	else
-		clear_bit(SDF_NOATIME, &sdp->sd_flags);
-
-	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
-	*flags |= MS_NOATIME | MS_NODIRATIME;
-
 	return error;
 }
 
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 7484655..7e1879f 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -269,14 +269,6 @@ ARGS_ATTR(quota,           "%u\n");
 ARGS_ATTR(suiddir,         "%d\n");
 ARGS_ATTR(data,            "%d\n");
 
-/* one oddball doesn't fit the macro mold */
-static ssize_t noatime_show(struct gfs2_sbd *sdp, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-			!!test_bit(SDF_NOATIME, &sdp->sd_flags));
-}
-static struct args_attr args_attr_noatime = __ATTR_RO(noatime);
-
 static struct attribute *args_attrs[] = {
 	&args_attr_lockproto.attr,
 	&args_attr_locktable.attr,
@@ -292,7 +284,6 @@ static struct attribute *args_attrs[] = {
 	&args_attr_quota.attr,
 	&args_attr_suiddir.attr,
 	&args_attr_data.attr,
-	&args_attr_noatime.attr,
 	NULL,
 };
 
@@ -407,7 +398,6 @@ TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
 TUNE_ATTR(quota_quantum, 0);
-TUNE_ATTR(atime_quantum, 0);
 TUNE_ATTR(max_readahead, 0);
 TUNE_ATTR(complain_secs, 0);
 TUNE_ATTR(statfs_slow, 0);
@@ -427,7 +417,6 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_log_flush_secs.attr,
 	&tune_attr_quota_warn_period.attr,
 	&tune_attr_quota_quantum.attr,
-	&tune_attr_atime_quantum.attr,
 	&tune_attr_max_readahead.attr,
 	&tune_attr_complain_secs.attr,
 	&tune_attr_statfs_slow.attr,
-- 
1.5.5.1

[Cluster-devel] [PATCH 11/12] GFS2: Add UUID to GFS2 sb

[Steven Whitehouse]

This patch adds a UUID to the GFS2 sb structure. This field is not
actually referenced from kernel space at all, but is added for
completeness and due to the userland tools which get their on-disk
structure information from the gfs2_ondisk.h header file.

Since we have to be backwards compatible, we will assume that any GFS2
sb for which the UUID is all 0 does not have a UUID as such.

We should then be (after some userland changes) able to support the -U
mount option. This addresses Fedora bugzilla #242689

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

diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h
index c3c19f9..14d0df0 100644
--- a/include/linux/gfs2_ondisk.h
+++ b/include/linux/gfs2_ondisk.h
@@ -118,7 +118,11 @@ struct gfs2_sb {
 
 	char sb_lockproto[GFS2_LOCKNAME_LEN];
 	char sb_locktable[GFS2_LOCKNAME_LEN];
-	/* In gfs1, quota and license dinodes followed */
+
+	struct gfs2_inum __pad3; /* Was quota inode in gfs1 */
+	struct gfs2_inum __pad4; /* Was licence inode in gfs1 */
+#define GFS2_HAS_UUID 1
+	__u8 sb_uuid[16]; /* The UUID, maybe 0 for backwards compat */
 };
 
 /*
-- 
1.5.5.1

[Cluster-devel] [PATCH 12/12] GFS2: Support for I/O barriers

[Steven Whitehouse]

This patch adds barrier support to GFS2. There is not a lot of change
really... we just add the barrier flag when we write journal header
blocks. If the underlying device refuses to support them, we fall back
to the previous way of doing things (wait for the I/O and hope) since
there is nothing else we can do. There is no user configuration,
barriers will always be on unless the device refuses to support them.
This seems a reasonable solution to me since this is a correctness
issue.

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

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index f1ed3a1..f566ec1 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -432,6 +432,7 @@ enum {
 	SDF_JOURNAL_CHECKED	= 0,
 	SDF_JOURNAL_LIVE	= 1,
 	SDF_SHUTDOWN		= 2,
+	SDF_NOBARRIERS		= 3,
 };
 
 #define GFS2_FSNAME_LEN		256
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6c6af9f..ad30585 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/bio.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -584,7 +585,6 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	memset(bh->b_data, 0, bh->b_size);
 	set_buffer_uptodate(bh);
 	clear_buffer_dirty(bh);
-	unlock_buffer(bh);
 
 	gfs2_ail1_empty(sdp, 0);
 	tail = current_tail(sdp);
@@ -601,8 +601,23 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
 	lh->lh_hash = cpu_to_be32(hash);
 
-	set_buffer_dirty(bh);
-	if (sync_dirty_buffer(bh))
+	bh->b_end_io = end_buffer_write_sync;
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
+		goto skip_barrier;
+	get_bh(bh);
+	submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
+	wait_on_buffer(bh);
+	if (buffer_eopnotsupp(bh)) {
+		clear_buffer_eopnotsupp(bh);
+		set_buffer_uptodate(bh);
+		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+		lock_buffer(bh);
+skip_barrier:
+		get_bh(bh);
+		submit_bh(WRITE_SYNC | (1 << BIO_RW_META), bh);
+		wait_on_buffer(bh);
+	}
+	if (!buffer_uptodate(bh))
 		gfs2_io_error_bh(sdp, bh);
 	brelse(bh);
 
-- 
1.5.5.1