1 files changed, 363 insertions, 156 deletions

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 2b2c4997430..1319b5c4ec6 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bio.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -23,6 +25,7 @@
 #include <linux/time.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -77,6 +80,8 @@ enum {
 	Opt_quota_quantum,
 	Opt_barrier,
 	Opt_nobarrier,
+	Opt_rgrplvb,
+	Opt_norgrplvb,
 	Opt_error,
 };
 
@@ -114,6 +119,8 @@ static const match_table_t tokens = {
 	{Opt_quota_quantum, "quota_quantum=%d"},
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
+	{Opt_rgrplvb, "rgrplvb"},
+	{Opt_norgrplvb, "norgrplvb"},
 	{Opt_error, NULL}
 };
 
@@ -170,8 +177,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 			break;
 		case Opt_debug:
 			if (args->ar_errors == GFS2_ERRORS_PANIC) {
-				printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
-				       "are mutually exclusive.\n");
+				pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
 				return -EINVAL;
 			}
 			args->ar_debug = 1;
@@ -223,21 +229,21 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 		case Opt_commit:
 			rv = match_int(&tmp[0], &args->ar_commit);
 			if (rv || args->ar_commit <= 0) {
-				printk(KERN_WARNING "GFS2: commit mount option requires a positive numeric argument\n");
+				pr_warn("commit mount option requires a positive numeric argument\n");
 				return rv ? rv : -EINVAL;
 			}
 			break;
 		case Opt_statfs_quantum:
 			rv = match_int(&tmp[0], &args->ar_statfs_quantum);
 			if (rv || args->ar_statfs_quantum < 0) {
-				printk(KERN_WARNING "GFS2: statfs_quantum mount option requires a non-negative numeric argument\n");
+				pr_warn("statfs_quantum mount option requires a non-negative numeric argument\n");
 				return rv ? rv : -EINVAL;
 			}
 			break;
 		case Opt_quota_quantum:
 			rv = match_int(&tmp[0], &args->ar_quota_quantum);
 			if (rv || args->ar_quota_quantum <= 0) {
-				printk(KERN_WARNING "GFS2: quota_quantum mount option requires a positive numeric argument\n");
+				pr_warn("quota_quantum mount option requires a positive numeric argument\n");
 				return rv ? rv : -EINVAL;
 			}
 			break;
@@ -245,7 +251,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 			rv = match_int(&tmp[0], &args->ar_statfs_percent);
 			if (rv || args->ar_statfs_percent < 0 ||
 			    args->ar_statfs_percent > 100) {
-				printk(KERN_WARNING "statfs_percent mount option requires a numeric argument between 0 and 100\n");
+				pr_warn("statfs_percent mount option requires a numeric argument between 0 and 100\n");
 				return rv ? rv : -EINVAL;
 			}
 			break;
@@ -254,8 +260,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 			break;
 		case Opt_err_panic:
 			if (args->ar_debug) {
-				printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
-					"are mutually exclusive.\n");
+				pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
 				return -EINVAL;
 			}
 			args->ar_errors = GFS2_ERRORS_PANIC;
@@ -266,9 +271,15 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 		case Opt_nobarrier:
 			args->ar_nobarrier = 1;
 			break;
+		case Opt_rgrplvb:
+			args->ar_rgrplvb = 1;
+			break;
+		case Opt_norgrplvb:
+			args->ar_rgrplvb = 0;
+			break;
 		case Opt_error:
 		default:
-			printk(KERN_WARNING "GFS2: invalid mount option: %s\n", o);
+			pr_warn("invalid mount option: %s\n", o);
 			return -EINVAL;
 		}
 	}
@@ -284,9 +295,8 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 
 void gfs2_jindex_free(struct gfs2_sbd *sdp)
 {
-	struct list_head list, *head;
+	struct list_head list;
 	struct gfs2_jdesc *jd;
-	struct gfs2_journal_extent *jext;
 
 	spin_lock(&sdp->sd_jindex_spin);
 	list_add(&list, &sdp->sd_jindex_list);
@@ -296,14 +306,7 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp)
 
 	while (!list_empty(&list)) {
 		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
-		head = &jd->extent_list;
-		while (!list_empty(head)) {
-			jext = list_entry(head->next,
-					  struct gfs2_journal_extent,
-					  extent_list);
-			list_del(&jext->extent_list);
-			kfree(jext);
-		}
+		gfs2_free_journal_extents(jd);
 		list_del(&jd->jd_list);
 		iput(jd->jd_inode);
 		kfree(jd);
@@ -358,6 +361,33 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
 	return 0;
 }
 
+static int init_threads(struct gfs2_sbd *sdp)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	if (IS_ERR(p)) {
+		error = PTR_ERR(p);
+		fs_err(sdp, "can't start logd thread: %d\n", error);
+		return error;
+	}
+	sdp->sd_logd_process = p;
+
+	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	if (IS_ERR(p)) {
+		error = PTR_ERR(p);
+		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_quotad_process = p;
+	return 0;
+
+fail:
+	kthread_stop(sdp->sd_logd_process);
+	return error;
+}
+
 /**
  * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
  * @sdp: the filesystem
@@ -369,14 +399,19 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 	struct gfs2_glock *j_gl = ip->i_gl;
-	struct gfs2_holder t_gh;
+	struct gfs2_holder thaw_gh;
 	struct gfs2_log_header_host head;
 	int error;
 
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh);
+	error = init_threads(sdp);
 	if (error)
 		return error;
 
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
+				   &thaw_gh);
+	if (error)
+		goto fail_threads;
+
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 
 	error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -399,14 +434,16 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 
 	set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 
-	gfs2_glock_dq_uninit(&t_gh);
+	gfs2_glock_dq_uninit(&thaw_gh);
 
 	return 0;
 
 fail:
-	t_gh.gh_flags |= GL_NOCACHE;
-	gfs2_glock_dq_uninit(&t_gh);
-
+	thaw_gh.gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_uninit(&thaw_gh);
+fail_threads:
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
 	return error;
 }
 
@@ -489,7 +526,7 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
 	if (error)
 		return;
 
-	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+	gfs2_trans_add_meta(l_ip->i_gl, l_bh);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	l_sc->sc_total += total;
@@ -517,7 +554,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
 
-	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+	gfs2_trans_add_meta(l_ip->i_gl, l_bh);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	m_sc->sc_total += l_sc->sc_total;
@@ -528,7 +565,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	       0, sizeof(struct gfs2_statfs_change));
 	spin_unlock(&sdp->sd_statfs_spin);
 
-	gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
+	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
 }
 
@@ -599,15 +636,21 @@ struct lfcc {
  */
 
 static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
-				    struct gfs2_holder *t_gh)
+				    struct gfs2_holder *freeze_gh)
 {
 	struct gfs2_inode *ip;
 	struct gfs2_jdesc *jd;
 	struct lfcc *lfcc;
 	LIST_HEAD(list);
 	struct gfs2_log_header_host lh;
+	struct gfs2_inode *dip = GFS2_I(sdp->sd_root_dir->d_inode);
 	int error;
 
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0,
+				   &sdp->sd_freeze_root_gh);
+	if (error)
+		return error;
+	atomic_set(&sdp->sd_frozen_root, 1);
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
 		if (!lfcc) {
@@ -623,8 +666,8 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
 		list_add(&lfcc->list, &list);
 	}
 
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
-				   GL_NOCACHE, t_gh);
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
+				   GL_NOCACHE, freeze_gh);
 
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		error = gfs2_jdesc_check(jd);
@@ -640,7 +683,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
 	}
 
 	if (error)
-		gfs2_glock_dq_uninit(t_gh);
+		gfs2_glock_dq_uninit(freeze_gh);
 
 out:
 	while (!list_empty(&list)) {
@@ -649,103 +692,137 @@ out:
 		gfs2_glock_dq_uninit(&lfcc->gh);
 		kfree(lfcc);
 	}
+	if (error) {
+		atomic_dec(&sdp->sd_frozen_root);
+		wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0);
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh);
+	}
 	return error;
 }
 
-/**
- * gfs2_freeze_fs - freezes the file system
- * @sdp: the file system
- *
- * This function flushes data and meta data for all machines by
- * aquiring the transaction log exclusively.  All journals are
- * ensured to be in a clean state as well.
- *
- * Returns: errno
- */
-
-int gfs2_freeze_fs(struct gfs2_sbd *sdp)
+void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
 {
-	int error = 0;
-
-	mutex_lock(&sdp->sd_freeze_lock);
-
-	if (!sdp->sd_freeze_count++) {
-		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
-		if (error)
-			sdp->sd_freeze_count--;
-	}
-
-	mutex_unlock(&sdp->sd_freeze_lock);
-
-	return error;
+	struct gfs2_dinode *str = buf;
+
+	str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
+	str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
+	str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
+	str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+	str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
+	str->di_uid = cpu_to_be32(i_uid_read(&ip->i_inode));
+	str->di_gid = cpu_to_be32(i_gid_read(&ip->i_inode));
+	str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
+	str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
+	str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
+	str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
+	str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
+	str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
+
+	str->di_goal_meta = cpu_to_be64(ip->i_goal);
+	str->di_goal_data = cpu_to_be64(ip->i_goal);
+	str->di_generation = cpu_to_be64(ip->i_generation);
+
+	str->di_flags = cpu_to_be32(ip->i_diskflags);
+	str->di_height = cpu_to_be16(ip->i_height);
+	str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
+					     !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
+					     GFS2_FORMAT_DE : 0);
+	str->di_depth = cpu_to_be16(ip->i_depth);
+	str->di_entries = cpu_to_be32(ip->i_entries);
+
+	str->di_eattr = cpu_to_be64(ip->i_eattr);
+	str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
+	str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
+	str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
 }
 
 /**
- * gfs2_unfreeze_fs - unfreezes the file system
- * @sdp: the file system
- *
- * This function allows the file system to proceed by unlocking
- * the exclusively held transaction lock.  Other GFS2 nodes are
- * now free to acquire the lock shared and go on with their lives.
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @wbc: The writeback control structure
  *
+ * Returns: errno
  */
 
-void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
+static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	mutex_lock(&sdp->sd_freeze_lock);
-
-	if (sdp->sd_freeze_count && !--sdp->sd_freeze_count)
-		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
+	struct backing_dev_info *bdi = metamapping->backing_dev_info;
+	int ret = 0;
 
-	mutex_unlock(&sdp->sd_freeze_lock);
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
+	if (bdi->dirty_exceeded)
+		gfs2_ail1_flush(sdp, wbc);
+	else
+		filemap_fdatawrite(metamapping);
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		ret = filemap_fdatawait(metamapping);
+	if (ret)
+		mark_inode_dirty_sync(inode);
+	return ret;
 }
 
-
 /**
- * gfs2_write_inode - Make sure the inode is stable on the disk
- * @inode: The inode
- * @sync: synchronous write flag
+ * gfs2_dirty_inode - check for atime updates
+ * @inode: The inode in question
+ * @flags: The type of dirty
  *
- * Returns: errno
+ * Unfortunately it can be called under any combination of inode
+ * glock and transaction lock, so we have to check carefully.
+ *
+ * At the moment this deals only with atime - it should be possible
+ * to expand that role in future, once a review of the locking has
+ * been carried out.
  */
 
-static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
+static void gfs2_dirty_inode(struct inode *inode, int flags)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_holder gh;
 	struct buffer_head *bh;
-	struct timespec atime;
-	struct gfs2_dinode *di;
-	int ret = 0;
+	struct gfs2_holder gh;
+	int need_unlock = 0;
+	int need_endtrans = 0;
+	int ret;
+
+	if (!(flags & (I_DIRTY_DATASYNC|I_DIRTY_SYNC)))
+		return;
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		if (ret) {
+			fs_err(sdp, "dirty_inode: glock %d\n", ret);
+			return;
+		}
+		need_unlock = 1;
+	} else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE))
+		return;
+
+	if (current->journal_info == NULL) {
+		ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+		if (ret) {
+			fs_err(sdp, "dirty_inode: gfs2_trans_begin %d\n", ret);
+			goto out;
+		}
+		need_endtrans = 1;
+	}
 
-	/* Check this is a "normal" inode, etc */
-	if (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);
-		}
+		gfs2_trans_add_meta(ip->i_gl, bh);
+		gfs2_dinode_out(ip, bh->b_data);
 		brelse(bh);
 	}
-	gfs2_trans_end(sdp);
-do_unlock:
-	gfs2_glock_dq_uninit(&gh);
-do_flush:
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
-	return ret;
+
+	if (need_endtrans)
+		gfs2_trans_end(sdp);
+out:
+	if (need_unlock)
+		gfs2_glock_dq_uninit(&gh);
 }
 
 /**
@@ -757,25 +834,30 @@ do_flush:
 
 static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 {
-	struct gfs2_holder t_gh;
+	struct gfs2_holder thaw_gh;
 	int error;
 
-	flush_workqueue(gfs2_delete_workqueue);
-	gfs2_quota_sync(sdp->sd_vfs, 0, 1);
-	gfs2_statfs_sync(sdp->sd_vfs, 0);
-
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
-				   &t_gh);
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &thaw_gh);
 	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
 		return error;
 
-	gfs2_meta_syncfs(sdp);
-	gfs2_log_shutdown(sdp);
-
+	down_write(&sdp->sd_log_flush_lock);
 	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+	up_write(&sdp->sd_log_flush_lock);
 
-	if (t_gh.gh_gl)
-		gfs2_glock_dq_uninit(&t_gh);
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+
+	flush_workqueue(gfs2_delete_workqueue);
+	gfs2_quota_sync(sdp->sd_vfs, 0);
+	gfs2_statfs_sync(sdp->sd_vfs, 0);
+
+	gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH);
+	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
+
+	if (thaw_gh.gh_gl)
+		gfs2_glock_dq_uninit(&thaw_gh);
 
 	gfs2_quota_cleanup(sdp);
 
@@ -800,13 +882,6 @@ static void gfs2_put_super(struct super_block *sb)
 	int error;
 	struct gfs2_jdesc *jd;
 
-	/*  Unfreeze the filesystem, if we need to  */
-
-	mutex_lock(&sdp->sd_freeze_lock);
-	if (sdp->sd_freeze_count)
-		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
-	mutex_unlock(&sdp->sd_freeze_lock);
-
 	/* No more recovery requests */
 	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
 	smp_mb();
@@ -824,9 +899,6 @@ restart:
 	}
 	spin_unlock(&sdp->sd_jindex_spin);
 
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
-
 	if (!(sb->s_flags & MS_RDONLY)) {
 		error = gfs2_make_fs_ro(sdp);
 		if (error)
@@ -842,7 +914,7 @@ restart:
 	iput(sdp->sd_quota_inode);
 
 	gfs2_glock_put(sdp->sd_rename_gl);
-	gfs2_glock_put(sdp->sd_trans_gl);
+	gfs2_glock_put(sdp->sd_freeze_gl);
 
 	if (!sdp->sd_args.ar_spectator) {
 		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
@@ -874,8 +946,11 @@ restart:
 
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
-	if (wait && sb->s_fs_info)
-		gfs2_log_flush(sb->s_fs_info, NULL);
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	gfs2_quota_sync(sb, -1);
+	if (wait && sdp && !atomic_read(&sdp->sd_log_freeze))
+		gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
 	return 0;
 }
 
@@ -894,7 +969,7 @@ static int gfs2_freeze(struct super_block *sb)
 		return -EINVAL;
 
 	for (;;) {
-		error = gfs2_freeze_fs(sdp);
+		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
 		if (!error)
 			break;
 
@@ -922,7 +997,12 @@ static int gfs2_freeze(struct super_block *sb)
 
 static int gfs2_unfreeze(struct super_block *sb)
 {
-	gfs2_unfreeze_fs(sb->s_fs_info);
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	atomic_dec(&sdp->sd_frozen_root);
+	wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0);
+	gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh);
 	return 0;
 }
 
@@ -959,7 +1039,6 @@ static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
 
 static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
 {
-	struct gfs2_holder ri_gh;
 	struct gfs2_rgrpd *rgd_next;
 	struct gfs2_holder *gha, *gh;
 	unsigned int slots = 64;
@@ -972,10 +1051,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 	if (!gha)
 		return -ENOMEM;
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto out;
-
 	rgd_next = gfs2_rgrpd_get_first(sdp);
 
 	for (;;) {
@@ -1018,9 +1093,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 		yield();
 	}
 
-	gfs2_glock_dq_uninit(&ri_gh);
-
-out:
 	kfree(gha);
 	return error;
 }
@@ -1072,6 +1144,10 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct gfs2_statfs_change_host sc;
 	int error;
 
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		return error;
+
 	if (gfs2_tune_get(sdp, gt_statfs_slow))
 		error = gfs2_statfs_slow(sdp, &sc);
 	else
@@ -1108,6 +1184,8 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 	struct gfs2_tune *gt = &sdp->sd_tune;
 	int error;
 
+	sync_filesystem(sb);
+
 	spin_lock(&gt->gt_spin);
 	args.ar_commit = gt->gt_logd_secs;
 	args.ar_quota_quantum = gt->gt_quota_quantum;
@@ -1189,7 +1267,7 @@ static int gfs2_drop_inode(struct inode *inode)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	if (inode->i_nlink) {
+	if (!test_bit(GIF_FREE_VFS_INODE, &ip->i_flags) && inode->i_nlink) {
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
 			clear_nlink(inode);
@@ -1210,18 +1288,18 @@ static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
 /**
  * gfs2_show_options - Show mount options for /proc/mounts
  * @s: seq_file structure
- * @mnt: vfsmount
+ * @root: root of this (sub)tree
  *
  * Returns: 0 on success or error code
  */
 
-static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 {
-	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_sbd *sdp = root->d_sb->s_fs_info;
 	struct gfs2_args *args = &sdp->sd_args;
 	int val;
 
-	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+	if (is_ancestor(root, sdp->sd_master_dir))
 		seq_printf(s, ",meta");
 	if (args->ar_lockproto[0])
 		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
@@ -1280,6 +1358,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	val = sdp->sd_tune.gt_statfs_quantum;
 	if (val != 30)
 		seq_printf(s, ",statfs_quantum=%d", val);
+	else if (sdp->sd_tune.gt_statfs_slow)
+		seq_puts(s, ",statfs_quantum=0");
 	val = sdp->sd_tune.gt_quota_quantum;
 	if (val != 60)
 		seq_printf(s, ",quota_quantum=%d", val);
@@ -1305,10 +1385,88 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 		seq_printf(s, ",nobarrier");
 	if (test_bit(SDF_DEMOTE, &sdp->sd_flags))
 		seq_printf(s, ",demote_interface_used");
+	if (args->ar_rgrplvb)
+		seq_printf(s, ",rgrplvb");
 	return 0;
 }
 
-/*
+static void gfs2_final_release_pages(struct gfs2_inode *ip)
+{
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_glock *gl = ip->i_gl;
+
+	truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0);
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (atomic_read(&gl->gl_revokes) == 0) {
+		clear_bit(GLF_LFLUSH, &gl->gl_flags);
+		clear_bit(GLF_DIRTY, &gl->gl_flags);
+	}
+}
+
+static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_holder gh;
+	int error;
+
+	if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		return error;
+
+	error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
+	if (error)
+		return error;
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
+	if (!rgd) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+		goto out_qs;
+	}
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (error)
+		goto out_qs;
+
+	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
+				 sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_rg_gunlock;
+
+	gfs2_free_di(rgd, ip);
+
+	gfs2_final_release_pages(ip);
+
+	gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+	gfs2_glock_dq_uninit(&gh);
+out_qs:
+	gfs2_quota_unhold(ip);
+	return error;
+}
+
+/**
+ * gfs2_evict_inode - Remove an inode from cache
+ * @inode: The inode to evict
+ *
+ * There are three cases to consider:
+ * 1. i_nlink == 0, we are final opener (and must deallocate)
+ * 2. i_nlink == 0, we are not the final opener (and cannot deallocate)
+ * 3. i_nlink > 0
+ *
+ * If the fs is read only, then we have to treat all cases as per #3
+ * since we are unable to do any deallocation. The inode will be
+ * deallocated by the next read/write node to attempt an allocation
+ * in the same resource group
+ *
  * We have to (at the moment) hold the inodes main lock to cover
  * the gap between unlocking the shared lock on the iopen lock and
  * taking the exclusive lock. I'd rather do a shared -> exclusive
@@ -1318,30 +1476,49 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 
 static void gfs2_evict_inode(struct inode *inode)
 {
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int error;
 
-	if (inode->i_nlink)
+	if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
+		clear_inode(inode);
+		return;
+	}
+
+	if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
 		goto out;
 
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	/* Must not read inode block until block type has been verified */
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 		goto out;
 	}
 
-	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
-	if (error)
-		goto out_truncate;
+	if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
+		error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+		if (error)
+			goto out_truncate;
+	}
 
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			goto out_truncate;
+	}
+
+	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_wait(&ip->i_iopen_gh);
 	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
 	error = gfs2_glock_nq(&ip->i_iopen_gh);
 	if (error)
 		goto out_truncate;
 
+	/* Case 1 starts here */
+
 	if (S_ISDIR(inode->i_mode) &&
 	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
 		error = gfs2_dir_exhash_dealloc(ip);
@@ -1362,10 +1539,19 @@ static void gfs2_evict_inode(struct inode *inode)
 	}
 
 	error = gfs2_dinode_dealloc(ip);
-	if (error)
-		goto out_unlock;
+	goto out_unlock;
 
 out_truncate:
+	gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
+	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
+		struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
+		filemap_fdatawrite(metamapping);
+		filemap_fdatawait(metamapping);
+	}
+	write_inode_now(inode, 1);
+	gfs2_ail_flush(ip->i_gl, 0);
+
+	/* Case 2 starts here */
 	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
 	if (error)
 		goto out_unlock;
@@ -1374,21 +1560,33 @@ out_truncate:
 	gfs2_trans_end(sdp);
 
 out_unlock:
-	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
+	/* Error path for case 1 */
+	if (gfs2_rs_active(ip->i_res))
+		gfs2_rs_deltree(ip->i_res);
+
+	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq(&ip->i_iopen_gh);
+	}
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
 	if (error && error != GLR_TRYFAILED && error != -EROFS)
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
-	truncate_inode_pages(&inode->i_data, 0);
-	end_writeback(inode);
-
+	/* Case 3 starts here */
+	truncate_inode_pages_final(&inode->i_data);
+	gfs2_rs_delete(ip, NULL);
+	gfs2_ordered_del_inode(ip);
+	clear_inode(inode);
+	gfs2_dir_hash_inval(ip);
 	ip->i_gl->gl_object = NULL;
+	flush_delayed_work(&ip->i_gl->gl_work);
+	gfs2_glock_add_to_lru(ip->i_gl);
 	gfs2_glock_put(ip->i_gl);
 	ip->i_gl = NULL;
 	if (ip->i_iopen_gh.gh_gl) {
 		ip->i_iopen_gh.gh_gl->gl_object = NULL;
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 	}
 }
@@ -1401,19 +1599,28 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
+		ip->i_rgd = NULL;
+		ip->i_res = NULL;
 	}
 	return &ip->i_inode;
 }
 
-static void gfs2_destroy_inode(struct inode *inode)
+static void gfs2_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(gfs2_inode_cachep, inode);
 }
 
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, gfs2_i_callback);
+}
+
 const struct super_operations gfs2_super_ops = {
 	.alloc_inode		= gfs2_alloc_inode,
 	.destroy_inode		= gfs2_destroy_inode,
 	.write_inode		= gfs2_write_inode,
+	.dirty_inode		= gfs2_dirty_inode,
 	.evict_inode		= gfs2_evict_inode,
 	.put_super		= gfs2_put_super,
 	.sync_fs		= gfs2_sync_fs,