Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw

Pull gfs2 changes from Steven Whitehouse.

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw:
  GFS2: Change truncate page allocation to be GFP_NOFS
  GFS2: call gfs2_write_alloc_required for each chunk
  GFS2: Clean up log flush header writing
  GFS2: Remove a __GFP_NOFAIL allocation
  GFS2: Flush pending glock work when evicting an inode
  GFS2: make sure rgrps are up to date in func gfs2_blk2rgrpd
  GFS2: Eliminate sd_rindex_mutex
  GFS2: Unlock rindex mutex on glock error
  GFS2: Make bd_cmp() static
  GFS2: Sort the ordered write list
  GFS2: FITRIM ioctl support
  GFS2: Move two functions from log.c to lops.c
  GFS2: glock statistics gathering

19 files changed, 804 insertions, 245 deletions

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 14a704015970..197c5c47e577 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -60,7 +60,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 	int release = 0;
 
 	if (!page || page->index) {
-		page = grab_cache_page(inode->i_mapping, 0);
+		page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
 		if (!page)
 			return -ENOMEM;
 		release = 1;
@@ -930,7 +930,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 	struct page *page;
 	int err;
 
-	page = grab_cache_page(mapping, index);
+	page = find_or_create_page(mapping, index, GFP_NOFS);
 	if (!page)
 		return 0;
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index c5fb3597f696..76834587a8a4 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -313,6 +313,8 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return gfs2_get_flags(filp, (u32 __user *)arg);
 	case FS_IOC_SETFLAGS:
 		return gfs2_set_flags(filp, (u32 __user *)arg);
+	case FITRIM:
+		return gfs2_fitrim(filp, (void __user *)arg);
 	}
 	return -ENOTTY;
 }
@@ -674,6 +676,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct buffer_head *dibh;
 	int error;
+	loff_t size = len;
 	unsigned int nr_blks;
 	sector_t lblock = offset >> inode->i_blkbits;
 
@@ -707,8 +710,8 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 			goto out;
 		}
 	}
-	if (offset + len > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
-		i_size_write(inode, offset + len);
+	if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
+		i_size_write(inode, offset + size);
 
 	mark_inode_dirty(inode);
 
@@ -777,12 +780,14 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
 	if (unlikely(error))
 		goto out_uninit;
 
-	if (!gfs2_write_alloc_required(ip, offset, len))
-		goto out_unlock;
-
 	while (len > 0) {
 		if (len < bytes)
 			bytes = len;
+		if (!gfs2_write_alloc_required(ip, offset, bytes)) {
+			len -= bytes;
+			offset += bytes;
+			continue;
+		}
 		qa = gfs2_qadata_get(ip);
 		if (!qa) {
 			error = -ENOMEM;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 351a3e797789..dab2526071cc 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -29,6 +29,7 @@
 #include <linux/rcupdate.h>
 #include <linux/rculist_bl.h>
 #include <linux/bit_spinlock.h>
+#include <linux/percpu.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -543,6 +544,11 @@ __acquires(&gl->gl_spin)
 		do_error(gl, 0); /* Fail queued try locks */
 	}
 	gl->gl_req = target;
+	set_bit(GLF_BLOCKING, &gl->gl_flags);
+	if ((gl->gl_req == LM_ST_UNLOCKED) ||
+	    (gl->gl_state == LM_ST_EXCLUSIVE) ||
+	    (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
+		clear_bit(GLF_BLOCKING, &gl->gl_flags);
 	spin_unlock(&gl->gl_spin);
 	if (glops->go_xmote_th)
 		glops->go_xmote_th(gl);
@@ -744,6 +750,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		return -ENOMEM;
 
 	atomic_inc(&sdp->sd_glock_disposal);
+	gl->gl_sbd = sdp;
 	gl->gl_flags = 0;
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
@@ -752,12 +759,17 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
 	gl->gl_ops = glops;
-	snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number);
+	gl->gl_dstamp = ktime_set(0, 0);
+	preempt_disable();
+	/* We use the global stats to estimate the initial per-glock stats */
+	gl->gl_stats = this_cpu_ptr(sdp->sd_lkstats)->lkstats[glops->go_type];
+	preempt_enable();
+	gl->gl_stats.stats[GFS2_LKS_DCOUNT] = 0;
+	gl->gl_stats.stats[GFS2_LKS_QCOUNT] = 0;
 	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
 	gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
 	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;
-	gl->gl_sbd = sdp;
 	gl->gl_hold_time = GL_GLOCK_DFT_HOLD;
 	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 	INIT_WORK(&gl->gl_delete, delete_work_func);
@@ -999,6 +1011,8 @@ fail:
 	}
 	set_bit(GLF_QUEUED, &gl->gl_flags);
 	trace_gfs2_glock_queue(gh, 1);
+	gfs2_glstats_inc(gl, GFS2_LKS_QCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_QCOUNT);
 	if (likely(insert_pt == NULL)) {
 		list_add_tail(&gh->gh_list, &gl->gl_holders);
 		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
@@ -1658,6 +1672,8 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
 		*p++ = 'L';
 	if (gl->gl_object)
 		*p++ = 'o';
+	if (test_bit(GLF_BLOCKING, gflags))
+		*p++ = 'b';
 	*p = 0;
 	return buf;
 }
@@ -1714,8 +1730,78 @@ out:
 	return error;
 }
 
+static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+	struct gfs2_glock *gl = iter_ptr;
+
+	seq_printf(seq, "G: n:%u/%llx rtt:%lld/%lld rttb:%lld/%lld irt:%lld/%lld dcnt: %lld qcnt: %lld\n",
+		   gl->gl_name.ln_type,
+		   (unsigned long long)gl->gl_name.ln_number,
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTT],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVAR],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTB],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVARB],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRT],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRTVAR],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_DCOUNT],
+		   (long long)gl->gl_stats.stats[GFS2_LKS_QCOUNT]);
+	return 0;
+}
+
+static const char *gfs2_gltype[] = {
+	"type",
+	"reserved",
+	"nondisk",
+	"inode",
+	"rgrp",
+	"meta",
+	"iopen",
+	"flock",
+	"plock",
+	"quota",
+	"journal",
+};
+
+static const char *gfs2_stype[] = {
+	[GFS2_LKS_SRTT]		= "srtt",
+	[GFS2_LKS_SRTTVAR]	= "srttvar",
+	[GFS2_LKS_SRTTB]	= "srttb",
+	[GFS2_LKS_SRTTVARB]	= "srttvarb",
+	[GFS2_LKS_SIRT]		= "sirt",
+	[GFS2_LKS_SIRTVAR]	= "sirtvar",
+	[GFS2_LKS_DCOUNT]	= "dlm",
+	[GFS2_LKS_QCOUNT]	= "queue",
+};
+
+#define GFS2_NR_SBSTATS (ARRAY_SIZE(gfs2_gltype) * ARRAY_SIZE(gfs2_stype))
+
+static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+	struct gfs2_sbd *sdp = gi->sdp;
+	unsigned index = gi->hash >> 3;
+	unsigned subindex = gi->hash & 0x07;
+	s64 value;
+	int i;
+
+	if (index == 0 && subindex != 0)
+		return 0;
 
+	seq_printf(seq, "%-10s %8s:", gfs2_gltype[index],
+		   (index == 0) ? "cpu": gfs2_stype[subindex]);
 
+	for_each_possible_cpu(i) {
+                const struct gfs2_pcpu_lkstats *lkstats = per_cpu_ptr(sdp->sd_lkstats, i);
+		if (index == 0) {
+			value = i;
+		} else {
+			value = lkstats->lkstats[index - 1].stats[subindex];
+		}
+		seq_printf(seq, " %15lld", (long long)value);
+	}
+	seq_putc(seq, '\n');
+	return 0;
+}
 
 int __init gfs2_glock_init(void)
 {
@@ -1828,6 +1914,35 @@ static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
 	return dump_glock(seq, iter_ptr);
 }
 
+static void *gfs2_sbstats_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+
+	gi->hash = *pos;
+	if (*pos >= GFS2_NR_SBSTATS)
+		return NULL;
+	preempt_disable();
+	return SEQ_START_TOKEN;
+}
+
+static void *gfs2_sbstats_seq_next(struct seq_file *seq, void *iter_ptr,
+				   loff_t *pos)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+	(*pos)++;
+	gi->hash++;
+	if (gi->hash >= GFS2_NR_SBSTATS) {
+		preempt_enable();
+		return NULL;
+	}
+	return SEQ_START_TOKEN;
+}
+
+static void gfs2_sbstats_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+	preempt_enable();
+}
+
 static const struct seq_operations gfs2_glock_seq_ops = {
 	.start = gfs2_glock_seq_start,
 	.next  = gfs2_glock_seq_next,
@@ -1835,7 +1950,21 @@ static const struct seq_operations gfs2_glock_seq_ops = {
 	.show  = gfs2_glock_seq_show,
 };
 
-static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+static const struct seq_operations gfs2_glstats_seq_ops = {
+	.start = gfs2_glock_seq_start,
+	.next  = gfs2_glock_seq_next,
+	.stop  = gfs2_glock_seq_stop,
+	.show  = gfs2_glstats_seq_show,
+};
+
+static const struct seq_operations gfs2_sbstats_seq_ops = {
+	.start = gfs2_sbstats_seq_start,
+	.next  = gfs2_sbstats_seq_next,
+	.stop  = gfs2_sbstats_seq_stop,
+	.show  = gfs2_sbstats_seq_show,
+};
+
+static int gfs2_glocks_open(struct inode *inode, struct file *file)
 {
 	int ret = seq_open_private(file, &gfs2_glock_seq_ops,
 				   sizeof(struct gfs2_glock_iter));
@@ -1847,9 +1976,49 @@ static int gfs2_debugfs_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-static const struct file_operations gfs2_debug_fops = {
+static int gfs2_glstats_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
+				   sizeof(struct gfs2_glock_iter));
+	if (ret == 0) {
+		struct seq_file *seq = file->private_data;
+		struct gfs2_glock_iter *gi = seq->private;
+		gi->sdp = inode->i_private;
+	}
+	return ret;
+}
+
+static int gfs2_sbstats_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open_private(file, &gfs2_sbstats_seq_ops,
+				   sizeof(struct gfs2_glock_iter));
+	if (ret == 0) {
+		struct seq_file *seq = file->private_data;
+		struct gfs2_glock_iter *gi = seq->private;
+		gi->sdp = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations gfs2_glocks_fops = {
+	.owner   = THIS_MODULE,
+	.open    = gfs2_glocks_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private,
+};
+
+static const struct file_operations gfs2_glstats_fops = {
 	.owner   = THIS_MODULE,
-	.open    = gfs2_debugfs_open,
+	.open    = gfs2_glstats_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private,
+};
+
+static const struct file_operations gfs2_sbstats_fops = {
+	.owner   = THIS_MODULE,
+	.open	 = gfs2_sbstats_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
 	.release = seq_release_private,
@@ -1863,20 +2032,45 @@ int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
 	sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
 							 S_IFREG | S_IRUGO,
 							 sdp->debugfs_dir, sdp,
-							 &gfs2_debug_fops);
+							 &gfs2_glocks_fops);
 	if (!sdp->debugfs_dentry_glocks)
-		return -ENOMEM;
+		goto fail;
+
+	sdp->debugfs_dentry_glstats = debugfs_create_file("glstats",
+							S_IFREG | S_IRUGO,
+							sdp->debugfs_dir, sdp,
+							&gfs2_glstats_fops);
+	if (!sdp->debugfs_dentry_glstats)
+		goto fail;
+
+	sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats",
+							S_IFREG | S_IRUGO,
+							sdp->debugfs_dir, sdp,
+							&gfs2_sbstats_fops);
+	if (!sdp->debugfs_dentry_sbstats)
+		goto fail;
 
 	return 0;
+fail:
+	gfs2_delete_debugfs_file(sdp);
+	return -ENOMEM;
 }
 
 void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
 {
-	if (sdp && sdp->debugfs_dir) {
+	if (sdp->debugfs_dir) {
 		if (sdp->debugfs_dentry_glocks) {
 			debugfs_remove(sdp->debugfs_dentry_glocks);
 			sdp->debugfs_dentry_glocks = NULL;
 		}
+		if (sdp->debugfs_dentry_glstats) {
+			debugfs_remove(sdp->debugfs_dentry_glstats);
+			sdp->debugfs_dentry_glstats = NULL;
+		}
+		if (sdp->debugfs_dentry_sbstats) {
+			debugfs_remove(sdp->debugfs_dentry_sbstats);
+			sdp->debugfs_dentry_sbstats = NULL;
+		}
 		debugfs_remove(sdp->debugfs_dir);
 		sdp->debugfs_dir = NULL;
 	}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 97742a7ea9cc..47d0bda5ac2b 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -19,6 +19,8 @@
 #include <linux/rculist_bl.h>
 #include <linux/completion.h>
 #include <linux/rbtree.h>
+#include <linux/ktime.h>
+#include <linux/percpu.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -205,6 +207,22 @@ struct gfs2_glock_operations {
 };
 
 enum {
+	GFS2_LKS_SRTT = 0,	/* Non blocking smoothed round trip time */
+	GFS2_LKS_SRTTVAR = 1,	/* Non blocking smoothed variance */
+	GFS2_LKS_SRTTB = 2,	/* Blocking smoothed round trip time */
+	GFS2_LKS_SRTTVARB = 3,	/* Blocking smoothed variance */
+	GFS2_LKS_SIRT = 4,	/* Smoothed Inter-request time */
+	GFS2_LKS_SIRTVAR = 5,	/* Smoothed Inter-request variance */
+	GFS2_LKS_DCOUNT = 6,	/* Count of dlm requests */
+	GFS2_LKS_QCOUNT = 7,	/* Count of gfs2_holder queues */
+	GFS2_NR_LKSTATS
+};
+
+struct gfs2_lkstats {
+	s64 stats[GFS2_NR_LKSTATS];
+};
+
+enum {
 	/* States */
 	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
 	HIF_FIRST		= 7,
@@ -238,10 +256,12 @@ enum {
 	GLF_QUEUED			= 12,
 	GLF_LRU				= 13,
 	GLF_OBJECT			= 14, /* Used only for tracing */
+	GLF_BLOCKING			= 15,
 };
 
 struct gfs2_glock {
 	struct hlist_bl_node gl_list;
+	struct gfs2_sbd *gl_sbd;
 	unsigned long gl_flags;		/* GLF_... */
 	struct lm_lockname gl_name;
 	atomic_t gl_ref;
@@ -261,16 +281,14 @@ struct gfs2_glock {
 	struct list_head gl_holders;
 
 	const struct gfs2_glock_operations *gl_ops;
-	char gl_strname[GDLM_STRNAME_BYTES];
+	ktime_t gl_dstamp;
+	struct gfs2_lkstats gl_stats;
 	struct dlm_lksb gl_lksb;
 	char gl_lvb[32];
 	unsigned long gl_tchange;
 	void *gl_object;
 
 	struct list_head gl_lru;
-
-	struct gfs2_sbd *gl_sbd;
-
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
 	atomic_t gl_revokes;
@@ -560,8 +578,14 @@ struct lm_lockstruct {
 	uint32_t *ls_recover_result; /* result of last jid recovery */
 };
 
+struct gfs2_pcpu_lkstats {
+	/* One struct for each glock type */
+	struct gfs2_lkstats lkstats[10];
+};
+
 struct gfs2_sbd {
 	struct super_block *sd_vfs;
+	struct gfs2_pcpu_lkstats __percpu *sd_lkstats;
 	struct kobject sd_kobj;
 	unsigned long sd_flags;	/* SDF_... */
 	struct gfs2_sb_host sd_sb;
@@ -620,7 +644,6 @@ struct gfs2_sbd {
 
 	int sd_rindex_uptodate;
 	spinlock_t sd_rindex_spin;
-	struct mutex sd_rindex_mutex;
 	struct rb_root sd_rindex_tree;
 	unsigned int sd_rgrps;
 	unsigned int sd_max_rg_data;
@@ -725,8 +748,23 @@ struct gfs2_sbd {
 
 	unsigned long sd_last_warning;
 	struct dentry *debugfs_dir;    /* debugfs directory */
-	struct dentry *debugfs_dentry_glocks; /* for debugfs */
+	struct dentry *debugfs_dentry_glocks;
+	struct dentry *debugfs_dentry_glstats;
+	struct dentry *debugfs_dentry_sbstats;
 };
 
+static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
+{
+	gl->gl_stats.stats[which]++;
+}
+
+static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which)
+{
+	const struct gfs2_sbd *sdp = gl->gl_sbd;
+	preempt_disable();
+	this_cpu_ptr(sdp->sd_lkstats)->lkstats[gl->gl_name.ln_type].stats[which]++;
+	preempt_enable();
+}
+
 #endif /* __INCORE_DOT_H__ */
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 56987460cdae..c98a60ee6dfd 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1036,7 +1036,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	gfs2_holder_init(ip->i_gl,  LM_ST_EXCLUSIVE, 0, ghs + 1);
 
-	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
 	if (!rgd)
 		goto out_inodes;
 
@@ -1255,7 +1255,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 		 * this is the case of the target file already existing
 		 * so we unlink before doing the rename
 		 */
-		nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
+		nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr, 1);
 		if (nrgd)
 			gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
 	}
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8944d1e32ab5..f8411bd1b805 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -18,14 +18,106 @@
 #include "glock.h"
 #include "util.h"
 #include "sys.h"
+#include "trace_gfs2.h"
 
 extern struct workqueue_struct *gfs2_control_wq;
 
+/**
+ * gfs2_update_stats - Update time based stats
+ * @mv: Pointer to mean/variance structure to update
+ * @sample: New data to include
+ *
+ * @delta is the difference between the current rtt sample and the
+ * running average srtt. We add 1/8 of that to the srtt in order to
+ * update the current srtt estimate. The varience estimate is a bit
+ * more complicated. We subtract the abs value of the @delta from
+ * the current variance estimate and add 1/4 of that to the running
+ * total.
+ *
+ * Note that the index points at the array entry containing the smoothed
+ * mean value, and the variance is always in the following entry
+ *
+ * Reference: TCP/IP Illustrated, vol 2, p. 831,832
+ * All times are in units of integer nanoseconds. Unlike the TCP/IP case,
+ * they are not scaled fixed point.
+ */
+
+static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index,
+				     s64 sample)
+{
+	s64 delta = sample - s->stats[index];
+	s->stats[index] += (delta >> 3);
+	index++;
+	s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2);
+}
+
+/**
+ * gfs2_update_reply_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * This assumes that gl->gl_dstamp has been set earlier.
+ *
+ * The rtt (lock round trip time) is an estimate of the time
+ * taken to perform a dlm lock request. We update it on each
+ * reply from the dlm.
+ *
+ * The blocking flag is set on the glock for all dlm requests
+ * which may potentially block due to lock requests from other nodes.
+ * DLM requests where the current lock state is exclusive, the
+ * requested state is null (or unlocked) or where the TRY or
+ * TRY_1CB flags are set are classified as non-blocking. All
+ * other DLM requests are counted as (potentially) blocking.
+ */
+static inline void gfs2_update_reply_times(struct gfs2_glock *gl)
+{
+	struct gfs2_pcpu_lkstats *lks;
+	const unsigned gltype = gl->gl_name.ln_type;
+	unsigned index = test_bit(GLF_BLOCKING, &gl->gl_flags) ?
+			 GFS2_LKS_SRTTB : GFS2_LKS_SRTT;
+	s64 rtt;
+
+	preempt_disable();
+	rtt = ktime_to_ns(ktime_sub(ktime_get_real(), gl->gl_dstamp));
+	lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+	gfs2_update_stats(&gl->gl_stats, index, rtt);		/* Local */
+	gfs2_update_stats(&lks->lkstats[gltype], index, rtt);	/* Global */
+	preempt_enable();
+
+	trace_gfs2_glock_lock_time(gl, rtt);
+}
+
+/**
+ * gfs2_update_request_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * The irt (lock inter-request times) measures the average time
+ * between requests to the dlm. It is updated immediately before
+ * each dlm call.
+ */
+
+static inline void gfs2_update_request_times(struct gfs2_glock *gl)
+{
+	struct gfs2_pcpu_lkstats *lks;
+	const unsigned gltype = gl->gl_name.ln_type;
+	ktime_t dstamp;
+	s64 irt;
+
+	preempt_disable();
+	dstamp = gl->gl_dstamp;
+	gl->gl_dstamp = ktime_get_real();
+	irt = ktime_to_ns(ktime_sub(gl->gl_dstamp, dstamp));
+	lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+	gfs2_update_stats(&gl->gl_stats, GFS2_LKS_SIRT, irt);		/* Local */
+	gfs2_update_stats(&lks->lkstats[gltype], GFS2_LKS_SIRT, irt);	/* Global */
+	preempt_enable();
+}
+ 
 static void gdlm_ast(void *arg)
 {
 	struct gfs2_glock *gl = arg;
 	unsigned ret = gl->gl_state;
 
+	gfs2_update_reply_times(gl);
 	BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
 
 	if (gl->gl_lksb.sb_flags & DLM_SBF_VALNOTVALID)
@@ -111,7 +203,7 @@ static int make_mode(const unsigned int lmstate)
 static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
 		      const int req)
 {
-	u32 lkf = 0;
+	u32 lkf = DLM_LKF_VALBLK;
 
 	if (gfs_flags & LM_FLAG_TRY)
 		lkf |= DLM_LKF_NOQUEUE;
@@ -138,26 +230,43 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
 	if (lkid != 0) 
 		lkf |= DLM_LKF_CONVERT;
 
-	lkf |= DLM_LKF_VALBLK;
-
 	return lkf;
 }
 
+static void gfs2_reverse_hex(char *c, u64 value)
+{
+	while (value) {
+		*c-- = hex_asc[value & 0x0f];
+		value >>= 4;
+	}
+}
+
 static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
 		     unsigned int flags)
 {
 	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
 	int req;
 	u32 lkf;
+	char strname[GDLM_STRNAME_BYTES] = "";
 
 	req = make_mode(req_state);
 	lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
-
+	gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+	if (gl->gl_lksb.sb_lkid) {
+		gfs2_update_request_times(gl);
+	} else {
+		memset(strname, ' ', GDLM_STRNAME_BYTES - 1);
+		strname[GDLM_STRNAME_BYTES - 1] = '\0';
+		gfs2_reverse_hex(strname + 7, gl->gl_name.ln_type);
+		gfs2_reverse_hex(strname + 23, gl->gl_name.ln_number);
+		gl->gl_dstamp = ktime_get_real();
+	}
 	/*
 	 * Submit the actual lock request.
 	 */
 
-	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname,
 			GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
 }
 
@@ -172,6 +281,10 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
 		return;
 	}
 
+	clear_bit(GLF_BLOCKING, &gl->gl_flags);
+	gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_update_request_times(gl);
 	error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
 			   NULL, gl);
 	if (error) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 756fae9eaf8f..4752eadc7f6e 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -19,6 +19,7 @@
 #include <linux/freezer.h>
 #include <linux/bio.h>
 #include <linux/writeback.h>
+#include <linux/list_sort.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -358,7 +359,7 @@ retry:
 	return 0;
 }
 
-static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
 {
 	struct gfs2_journal_extent *je;
 
@@ -467,8 +468,8 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
 
 void gfs2_log_incr_head(struct gfs2_sbd *sdp)
 {
-	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
-		BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
+	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
+	       (sdp->sd_log_flush_head != sdp->sd_log_head));
 
 	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
 		sdp->sd_log_flush_head = 0;
@@ -476,99 +477,6 @@ void gfs2_log_incr_head(struct gfs2_sbd *sdp)
 	}
 }
 
-/**
- * gfs2_log_write_endio - End of I/O for a log buffer
- * @bh: The buffer head
- * @uptodate: I/O Status
- *
- */
-
-static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
-{
-	struct gfs2_sbd *sdp = bh->b_private;
-	bh->b_private = NULL;
-
-	end_buffer_write_sync(bh, uptodate);
-	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
-		wake_up(&sdp->sd_log_flush_wait);
-}
-
-/**
- * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
- * @sdp: The GFS2 superblock
- *
- * Returns: the buffer_head
- */
-
-struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
-{
-	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
-
-	bh = sb_getblk(sdp->sd_vfs, blkno);
-	lock_buffer(bh);
-	memset(bh->b_data, 0, bh->b_size);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-	gfs2_log_incr_head(sdp);
-	atomic_inc(&sdp->sd_log_in_flight);
-	bh->b_private = sdp;
-	bh->b_end_io = gfs2_log_write_endio;
-
-	return bh;
-}
-
-/**
- * gfs2_fake_write_endio - 
- * @bh: The buffer head
- * @uptodate: The I/O Status
- *
- */
-
-static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
-{
-	struct buffer_head *real_bh = bh->b_private;
-	struct gfs2_bufdata *bd = real_bh->b_private;
-	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
-
-	end_buffer_write_sync(bh, uptodate);
-	free_buffer_head(bh);
-	unlock_buffer(real_bh);
-	brelse(real_bh);
-	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
-		wake_up(&sdp->sd_log_flush_wait);
-}
-
-/**
- * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
- * @sdp: the filesystem
- * @data: the data the buffer_head should point to
- *
- * Returns: the log buffer descriptor
- */
-
-struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
-				      struct buffer_head *real)
-{
-	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
-
-	bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
-	atomic_set(&bh->b_count, 1);
-	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
-	set_bh_page(bh, real->b_page, bh_offset(real));
-	bh->b_blocknr = blkno;
-	bh->b_size = sdp->sd_sb.sb_bsize;
-	bh->b_bdev = sdp->sd_vfs->s_bdev;
-	bh->b_private = real;
-	bh->b_end_io = gfs2_fake_write_endio;
-
-	gfs2_log_incr_head(sdp);
-	atomic_inc(&sdp->sd_log_in_flight);
-
-	return bh;
-}
-
 static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 {
 	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
@@ -583,66 +491,8 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 	sdp->sd_log_tail = new_tail;
 }
 
-/**
- * log_write_header - Get and initialize a journal header buffer
- * @sdp: The GFS2 superblock
- *
- * Returns: the initialized log buffer descriptor
- */
 
-static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
-{
-	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
-	struct gfs2_log_header *lh;
-	unsigned int tail;
-	u32 hash;
-
-	bh = sb_getblk(sdp->sd_vfs, blkno);
-	lock_buffer(bh);
-	memset(bh->b_data, 0, bh->b_size);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-
-	gfs2_ail1_empty(sdp);
-	tail = current_tail(sdp);
-
-	lh = (struct gfs2_log_header *)bh->b_data;
-	memset(lh, 0, sizeof(struct gfs2_log_header));
-	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
-	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
-	lh->lh_header.__pad0 = cpu_to_be64(0);
-	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
-	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
-	lh->lh_flags = cpu_to_be32(flags);
-	lh->lh_tail = cpu_to_be32(tail);
-	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
-	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
-	lh->lh_hash = cpu_to_be32(hash);
-
-	bh->b_end_io = end_buffer_write_sync;
-	get_bh(bh);
-	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
-		submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
-	else
-		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
-	wait_on_buffer(bh);
-
-	if (!buffer_uptodate(bh))
-		gfs2_io_error_bh(sdp, bh);
-	brelse(bh);
-
-	if (sdp->sd_log_tail != tail)
-		log_pull_tail(sdp, tail);
-	else
-		gfs2_assert_withdraw(sdp, !pull);
-
-	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
-	gfs2_log_incr_head(sdp);
-}
-
-static void log_flush_commit(struct gfs2_sbd *sdp)
+static void log_flush_wait(struct gfs2_sbd *sdp)
 {
 	DEFINE_WAIT(wait);
 
@@ -655,8 +505,20 @@ static void log_flush_commit(struct gfs2_sbd *sdp)
 		} while(atomic_read(&sdp->sd_log_in_flight));
 		finish_wait(&sdp->sd_log_flush_wait, &wait);
 	}
+}
+
+static int bd_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct gfs2_bufdata *bda, *bdb;
 
-	log_write_header(sdp, 0, 0);
+	bda = list_entry(a, struct gfs2_bufdata, bd_le.le_list);
+	bdb = list_entry(b, struct gfs2_bufdata, bd_le.le_list);
+
+	if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
+		return -1;
+	if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
+		return 1;
+	return 0;
 }
 
 static void gfs2_ordered_write(struct gfs2_sbd *sdp)
@@ -666,6 +528,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 	LIST_HEAD(written);
 
 	gfs2_log_lock(sdp);
+	list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp);
 	while (!list_empty(&sdp->sd_log_le_ordered)) {
 		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
 		list_move(&bd->bd_le.le_list, &written);
@@ -711,6 +574,68 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 }
 
 /**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+{
+	u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+	struct gfs2_log_header *lh;
+	unsigned int tail;
+	u32 hash;
+
+	bh = sb_getblk(sdp->sd_vfs, blkno);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+
+	gfs2_ail1_empty(sdp);
+	tail = current_tail(sdp);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.__pad0 = cpu_to_be64(0);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	lh->l