X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fgfs2%2Fglock.c;h=80e09c50590a52ed1a6e77c47ea59459da4b1bde;hb=4c5680177012a2b5c0f3fdf58f4375dd84a1da67;hp=b348053c436351754200e7f39b825eb64d57013a;hpb=94610610f10749c0e17b4d2840ff8a7cb636c413;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index b348053..80e09c5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -15,13 +15,22 @@
 #include <linux/delay.h>
 #include <linux/sort.h>
 #include <linux/jhash.h>
-#include <linux/kref.h>
 #include <linux/kallsyms.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/list.h>
+#include <linux/lm_interface.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include <linux/rwsem.h>
 #include <asm/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
 
 #include "gfs2.h"
-#include "lm_interface.h"
 #include "incore.h"
 #include "glock.h"
 #include "glops.h"
@@ -33,31 +42,38 @@
 #include "super.h"
 #include "util.h"
 
-/*  Must be kept in sync with the beginning of struct gfs2_glock  */
-struct glock_plug {
-	struct list_head gl_list;
-	unsigned long gl_flags;
-};
-
-struct greedy {
-	struct gfs2_holder gr_gh;
-	struct work_struct gr_work;
+struct gfs2_gl_hash_bucket {
+        struct hlist_head hb_list;
 };
 
-struct gfs2_gl_hash_bucket {
-        struct list_head hb_list;
+struct glock_iter {
+	int hash;                     /* hash bucket index         */
+	struct gfs2_sbd *sdp;         /* incore superblock         */
+	struct gfs2_glock *gl;        /* current glock struct      */
+	struct seq_file *seq;         /* sequence file for debugfs */
+	char string[512];             /* scratch space             */
 };
 
 typedef void (*glock_examiner) (struct gfs2_glock * gl);
 
 static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
-static int dump_glock(struct gfs2_glock *gl);
-
-#define GFS2_GL_HASH_SHIFT      13
+static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
+static void gfs2_glock_drop_th(struct gfs2_glock *gl);
+static void run_queue(struct gfs2_glock *gl);
+
+static DECLARE_RWSEM(gfs2_umount_flush_sem);
+static struct dentry *gfs2_root;
+static struct task_struct *scand_process;
+static unsigned int scand_secs = 5;
+static struct workqueue_struct *glock_workqueue;
+
+#define GFS2_GL_HASH_SHIFT      15
 #define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
 #define GFS2_GL_HASH_MASK       (GFS2_GL_HASH_SIZE - 1)
 
 static struct gfs2_gl_hash_bucket gl_hash_table[GFS2_GL_HASH_SIZE];
+static struct dentry *gfs2_root;
 
 /*
  * Despite what you might think, the numbers below are not arbitrary :-)
@@ -101,7 +117,7 @@ static inline rwlock_t *gl_lock_addr(unsigned int x)
 	return &gl_hash_locks[x & (GL_HASH_LOCK_SZ-1)];
 }
 #else /* not SMP, so no spinlocks required */
-static inline rwlock_t *gl_lock_addr(x)
+static inline rwlock_t *gl_lock_addr(unsigned int x)
 {
 	return NULL;
 }
@@ -183,23 +199,7 @@ static void glock_free(struct gfs2_glock *gl)
 
 void gfs2_glock_hold(struct gfs2_glock *gl)
 {
-	kref_get(&gl->gl_ref);
-}
-
-/* All work is done after the return from kref_put() so we
-   can release the write_lock before the free. */
-
-static void kill_glock(struct kref *kref)
-{
-	struct gfs2_glock *gl = container_of(kref, struct gfs2_glock, gl_ref);
-	struct gfs2_sbd *sdp = gl->gl_sbd;
-
-	gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED);
-	gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
-	gfs2_assert(sdp, list_empty(&gl->gl_holders));
-	gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
-	gfs2_assert(sdp, list_empty(&gl->gl_waiters2));
-	gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
+	atomic_inc(&gl->gl_ref);
 }
 
 /**
@@ -211,12 +211,17 @@ static void kill_glock(struct kref *kref)
 int gfs2_glock_put(struct gfs2_glock *gl)
 {
 	int rv = 0;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
 
 	write_lock(gl_lock_addr(gl->gl_hash));
-	if (kref_put(&gl->gl_ref, kill_glock)) {
-		list_del_init(&gl_hash_table[gl->gl_hash].hb_list);
+	if (atomic_dec_and_test(&gl->gl_ref)) {
+		hlist_del(&gl->gl_list);
 		write_unlock(gl_lock_addr(gl->gl_hash));
-		BUG_ON(spin_is_locked(&gl->gl_spin));
+		gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED);
+		gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
+		gfs2_assert(sdp, list_empty(&gl->gl_holders));
+		gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
+		gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
 		glock_free(gl);
 		rv = 1;
 		goto out;
@@ -227,30 +232,6 @@ out:
 }
 
 /**
- * queue_empty - check to see if a glock's queue is empty
- * @gl: the glock
- * @head: the head of the queue to check
- *
- * This function protects the list in the event that a process already
- * has a holder on the list and is adding a second holder for itself.
- * The glmutex lock is what generally prevents processes from working
- * on the same glock at once, but the special case of adding a second
- * holder for yourself ("recursive" locking) doesn't involve locking
- * glmutex, making the spin lock necessary.
- *
- * Returns: 1 if the queue is empty
- */
-
-static inline int queue_empty(struct gfs2_glock *gl, struct list_head *head)
-{
-	int empty;
-	spin_lock(&gl->gl_spin);
-	empty = list_empty(head);
-	spin_unlock(&gl->gl_spin);
-	return empty;
-}
-
-/**
  * search_bucket() - Find struct gfs2_glock by lock number
  * @bucket: the bucket to search
  * @name: The lock name
@@ -263,16 +244,15 @@ static struct gfs2_glock *search_bucket(unsigned int hash,
 					const struct lm_lockname *name)
 {
 	struct gfs2_glock *gl;
+	struct hlist_node *h;
 
-	list_for_each_entry(gl, &gl_hash_table[hash].hb_list, gl_list) {
-		if (test_bit(GLF_PLUG, &gl->gl_flags))
-			continue;
+	hlist_for_each_entry(gl, h, &gl_hash_table[hash].hb_list, gl_list) {
 		if (!lm_name_equal(&gl->gl_name, name))
 			continue;
 		if (gl->gl_sbd != sdp)
 			continue;
 
-		kref_get(&gl->gl_ref);
+		atomic_inc(&gl->gl_ref);
 
 		return gl;
 	}
@@ -301,6 +281,18 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
 	return gl;
 }
 
+static void glock_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+
+	spin_lock(&gl->gl_spin);
+	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
+		set_bit(GLF_DEMOTE, &gl->gl_flags);
+	run_queue(gl);
+	spin_unlock(&gl->gl_spin);
+	gfs2_glock_put(gl);
+}
+
 /**
  * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
  * @sdp: The GFS2 superblock
@@ -338,20 +330,22 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 
 	gl->gl_flags = 0;
 	gl->gl_name = name;
-	kref_init(&gl->gl_ref);
+	atomic_set(&gl->gl_ref, 1);
 	gl->gl_state = LM_ST_UNLOCKED;
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
-	gl->gl_owner = NULL;
+	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;
 	gl->gl_ops = glops;
 	gl->gl_req_gh = NULL;
 	gl->gl_req_bh = NULL;
 	gl->gl_vn = 0;
 	gl->gl_stamp = jiffies;
+	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;
 	gl->gl_sbd = sdp;
 	gl->gl_aspace = NULL;
-	lops_init_le(&gl->gl_le, &gfs2_glock_lops);
+	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 
 	/* If this glock protects actual on-disk data or metadata blocks,
 	   create a VFS inode to manage the pages/buffers holding them. */
@@ -374,7 +368,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		glock_free(gl);
 		gl = tmp;
 	} else {
-		list_add_tail(&gl->gl_list, &gl_hash_table[hash].hb_list);
+		hlist_add_head(&gl->gl_list, &gl_hash_table[hash].hb_list);
 		write_unlock(gl_lock_addr(hash));
 	}
 
@@ -386,7 +380,7 @@ fail_aspace:
 	if (gl->gl_aspace)
 		gfs2_aspace_put(gl->gl_aspace);
 fail:
-	kmem_cache_free(gfs2_glock_cachep, gl);	
+	kmem_cache_free(gfs2_glock_cachep, gl);
 	return error;
 }
 
@@ -405,16 +399,11 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
 	INIT_LIST_HEAD(&gh->gh_list);
 	gh->gh_gl = gl;
 	gh->gh_ip = (unsigned long)__builtin_return_address(0);
-	gh->gh_owner = current;
+	gh->gh_owner_pid = current->pid;
 	gh->gh_state = state;
 	gh->gh_flags = flags;
 	gh->gh_error = 0;
 	gh->gh_iflags = 0;
-	init_completion(&gh->gh_wait);
-
-	if (gh->gh_state == LM_ST_EXCLUSIVE)
-		gh->gh_flags |= GL_LOCAL_EXCL;
-
 	gfs2_glock_hold(gl);
 }
 
@@ -432,10 +421,7 @@ void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *
 {
 	gh->gh_state = state;
 	gh->gh_flags = flags;
-	if (gh->gh_state == LM_ST_EXCLUSIVE)
-		gh->gh_flags |= GL_LOCAL_EXCL;
-
-	gh->gh_iflags &= 1 << HIF_ALLOCED;
+	gh->gh_iflags = 0;
 	gh->gh_ip = (unsigned long)__builtin_return_address(0);
 }
 
@@ -452,46 +438,37 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
 	gh->gh_ip = 0;
 }
 
-/**
- * gfs2_holder_get - get a struct gfs2_holder structure
- * @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gfp_flags:
- *
- * Figure out how big an impact this function has.  Either:
- * 1) Replace it with a cache of structures hanging off the struct gfs2_sbd
- * 2) Leave it like it is
- *
- * Returns: the holder structure, NULL on ENOMEM
- */
-
-static struct gfs2_holder *gfs2_holder_get(struct gfs2_glock *gl,
-					   unsigned int state,
-					   int flags, gfp_t gfp_flags)
+static void gfs2_holder_wake(struct gfs2_holder *gh)
 {
-	struct gfs2_holder *gh;
+	clear_bit(HIF_WAIT, &gh->gh_iflags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
+}
 
-	gh = kmalloc(sizeof(struct gfs2_holder), gfp_flags);
-	if (!gh)
-		return NULL;
+static int just_schedule(void *word)
+{
+        schedule();
+        return 0;
+}
 
-	gfs2_holder_init(gl, state, flags, gh);
-	set_bit(HIF_ALLOCED, &gh->gh_iflags);
-	gh->gh_ip = (unsigned long)__builtin_return_address(0);
-	return gh;
+static void wait_on_holder(struct gfs2_holder *gh)
+{
+	might_sleep();
+	wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
 }
 
-/**
- * gfs2_holder_put - get rid of a struct gfs2_holder structure
- * @gh: the holder structure
- *
- */
+static void gfs2_demote_wake(struct gfs2_glock *gl)
+{
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
+        clear_bit(GLF_DEMOTE, &gl->gl_flags);
+        smp_mb__after_clear_bit();
+        wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
+}
 
-static void gfs2_holder_put(struct gfs2_holder *gh)
+static void wait_on_demote(struct gfs2_glock *gl)
 {
-	gfs2_holder_uninit(gh);
-	kfree(gh);
+	might_sleep();
+	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE);
 }
 
 /**
@@ -508,7 +485,9 @@ static int rq_mutex(struct gfs2_holder *gh)
 	list_del_init(&gh->gh_list);
 	/*  gh->gh_error never examined.  */
 	set_bit(GLF_LOCK, &gl->gl_flags);
-	complete(&gh->gh_wait);
+	clear_bit(HIF_WAIT, &gh->gh_iflags);
+	smp_mb();
+	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
 
 	return 1;
 }
@@ -525,23 +504,13 @@ static int rq_mutex(struct gfs2_holder *gh)
 static int rq_promote(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
-	const struct gfs2_glock_operations *glops = gl->gl_ops;
 
 	if (!relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
 		if (list_empty(&gl->gl_holders)) {
 			gl->gl_req_gh = gh;
 			set_bit(GLF_LOCK, &gl->gl_flags);
 			spin_unlock(&gl->gl_spin);
-
-			if (atomic_read(&sdp->sd_reclaim_count) >
-			    gfs2_tune_get(sdp, gt_reclaim_limit) &&
-			    !(gh->gh_flags & LM_FLAG_PRIORITY)) {
-				gfs2_reclaim_glock(sdp);
-				gfs2_reclaim_glock(sdp);
-			}
-
-			glops->go_xmote_th(gl, gh->gh_state, gh->gh_flags);
+			gfs2_glock_xmote_th(gh->gh_gl, gh);
 			spin_lock(&gl->gl_spin);
 		}
 		return 1;
@@ -552,11 +521,11 @@ static int rq_promote(struct gfs2_holder *gh)
 		set_bit(GLF_LOCK, &gl->gl_flags);
 	} else {
 		struct gfs2_holder *next_gh;
-		if (gh->gh_flags & GL_LOCAL_EXCL)
+		if (gh->gh_state == LM_ST_EXCLUSIVE)
 			return 1;
 		next_gh = list_entry(gl->gl_holders.next, struct gfs2_holder,
 				     gh_list);
-		if (next_gh->gh_flags & GL_LOCAL_EXCL)
+		if (next_gh->gh_state == LM_ST_EXCLUSIVE)
 			 return 1;
 	}
 
@@ -564,7 +533,7 @@ static int rq_promote(struct gfs2_holder *gh)
 	gh->gh_error = 0;
 	set_bit(HIF_HOLDER, &gh->gh_iflags);
 
-	complete(&gh->gh_wait);
+	gfs2_holder_wake(gh);
 
 	return 0;
 }
@@ -576,60 +545,31 @@ static int rq_promote(struct gfs2_holder *gh)
  * Returns: 1 if the queue is blocked
  */
 
-static int rq_demote(struct gfs2_holder *gh)
+static int rq_demote(struct gfs2_glock *gl)
 {
-	struct gfs2_glock *gl = gh->gh_gl;
-	const struct gfs2_glock_operations *glops = gl->gl_ops;
-
 	if (!list_empty(&gl->gl_holders))
 		return 1;
 
-	if (gl->gl_state == gh->gh_state || gl->gl_state == LM_ST_UNLOCKED) {
-		list_del_init(&gh->gh_list);
-		gh->gh_error = 0;
+	if (gl->gl_state == gl->gl_demote_state ||
+	    gl->gl_state == LM_ST_UNLOCKED) {
+		gfs2_demote_wake(gl);
+		return 0;
+	}
+
+	set_bit(GLF_LOCK, &gl->gl_flags);
+	set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+
+	if (gl->gl_demote_state == LM_ST_UNLOCKED ||
+	    gl->gl_state != LM_ST_EXCLUSIVE) {
 		spin_unlock(&gl->gl_spin);
-		if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
-			gfs2_holder_put(gh);
-		else
-			complete(&gh->gh_wait);
-		spin_lock(&gl->gl_spin);
+		gfs2_glock_drop_th(gl);
 	} else {
-		gl->gl_req_gh = gh;
-		set_bit(GLF_LOCK, &gl->gl_flags);
 		spin_unlock(&gl->gl_spin);
-
-		if (gh->gh_state == LM_ST_UNLOCKED ||
-		    gl->gl_state != LM_ST_EXCLUSIVE)
-			glops->go_drop_th(gl);
-		else
-			glops->go_xmote_th(gl, gh->gh_state, gh->gh_flags);
-
-		spin_lock(&gl->gl_spin);
+		gfs2_glock_xmote_th(gl, NULL);
 	}
 
-	return 0;
-}
-
-/**
- * rq_greedy - process a queued request to drop greedy status
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_greedy(struct gfs2_holder *gh)
-{
-	struct gfs2_glock *gl = gh->gh_gl;
-
-	list_del_init(&gh->gh_list);
-	/*  gh->gh_error never examined.  */
-	clear_bit(GLF_GREEDY, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
-
-	gfs2_holder_uninit(gh);
-	kfree(container_of(gh, struct greedy, gr_gh));
-
-	spin_lock(&gl->gl_spin);		
+	spin_lock(&gl->gl_spin);
+	clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
 
 	return 0;
 }
@@ -651,33 +591,18 @@ static void run_queue(struct gfs2_glock *gl)
 		if (!list_empty(&gl->gl_waiters1)) {
 			gh = list_entry(gl->gl_waiters1.next,
 					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_MUTEX, &gh->gh_iflags))
-				blocked = rq_mutex(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
-		} else if (!list_empty(&gl->gl_waiters2) &&
-			   !test_bit(GLF_SKIP_WAITERS2, &gl->gl_flags)) {
-			gh = list_entry(gl->gl_waiters2.next,
-					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_DEMOTE, &gh->gh_iflags))
-				blocked = rq_demote(gh);
-			else if (test_bit(HIF_GREEDY, &gh->gh_iflags))
-				blocked = rq_greedy(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
+			blocked = rq_mutex(gh);
+		} else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+			blocked = rq_demote(gl);
+			if (gl->gl_waiters2 && !blocked) {
+				set_bit(GLF_DEMOTE, &gl->gl_flags);
+				gl->gl_demote_state = LM_ST_UNLOCKED;
+			}
+			gl->gl_waiters2 = 0;
 		} else if (!list_empty(&gl->gl_waiters3)) {
 			gh = list_entry(gl->gl_waiters3.next,
 					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_PROMOTE, &gh->gh_iflags))
-				blocked = rq_promote(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
+			blocked = rq_promote(gh);
 		} else
 			break;
 
@@ -695,23 +620,21 @@ static void run_queue(struct gfs2_glock *gl)
 
 static void gfs2_glmutex_lock(struct gfs2_glock *gl)
 {
-	struct gfs2_holder gh;
-
-	gfs2_holder_init(gl, 0, 0, &gh);
-	set_bit(HIF_MUTEX, &gh.gh_iflags);
-
 	spin_lock(&gl->gl_spin);
 	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+		struct gfs2_holder gh;
+
+		gfs2_holder_init(gl, 0, 0, &gh);
+		set_bit(HIF_WAIT, &gh.gh_iflags);
 		list_add_tail(&gh.gh_list, &gl->gl_waiters1);
+		spin_unlock(&gl->gl_spin);
+		wait_on_holder(&gh);
+		gfs2_holder_uninit(&gh);
 	} else {
-		gl->gl_owner = current;
+		gl->gl_owner_pid = current->pid;
 		gl->gl_ip = (unsigned long)__builtin_return_address(0);
-		complete(&gh.gh_wait);
+		spin_unlock(&gl->gl_spin);
 	}
-	spin_unlock(&gl->gl_spin);
-
-	wait_for_completion(&gh.gh_wait);
-	gfs2_holder_uninit(&gh);
 }
 
 /**
@@ -729,7 +652,7 @@ static int gfs2_glmutex_trylock(struct gfs2_glock *gl)
 	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
 		acquired = 0;
 	} else {
-		gl->gl_owner = current;
+		gl->gl_owner_pid = current->pid;
 		gl->gl_ip = (unsigned long)__builtin_return_address(0);
 	}
 	spin_unlock(&gl->gl_spin);
@@ -747,72 +670,45 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
 {
 	spin_lock(&gl->gl_spin);
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	gl->gl_owner = NULL;
+	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;
 	run_queue(gl);
-	BUG_ON(!spin_is_locked(&gl->gl_spin));
 	spin_unlock(&gl->gl_spin);
 }
 
 /**
- * handle_callback - add a demote request to a lock's queue
+ * handle_callback - process a demote request
  * @gl: the glock
  * @state: the state the caller wants us to change to
  *
- * Note: This may fail sliently if we are out of memory.
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
  */
 
-static void handle_callback(struct gfs2_glock *gl, unsigned int state)
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+			    int remote, unsigned long delay)
 {
-	struct gfs2_holder *gh, *new_gh = NULL;
+	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
 
-restart:
 	spin_lock(&gl->gl_spin);
-
-	list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
-		if (test_bit(HIF_DEMOTE, &gh->gh_iflags) &&
-		    gl->gl_req_gh != gh) {
-			if (gh->gh_state != state)
-				gh->gh_state = LM_ST_UNLOCKED;
-			goto out;
-		}
-	}
-
-	if (new_gh) {
-		list_add_tail(&new_gh->gh_list, &gl->gl_waiters2);
-		new_gh = NULL;
-	} else {
-		spin_unlock(&gl->gl_spin);
-
-		new_gh = gfs2_holder_get(gl, state, LM_FLAG_TRY, GFP_KERNEL);
-		if (!new_gh)
+	set_bit(bit, &gl->gl_flags);
+	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
+		gl->gl_demote_state = state;
+		gl->gl_demote_time = jiffies;
+		if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
+		    gl->gl_object) {
+			gfs2_glock_schedule_for_reclaim(gl);
+			spin_unlock(&gl->gl_spin);
 			return;
-		set_bit(HIF_DEMOTE, &new_gh->gh_iflags);
-		set_bit(HIF_DEALLOC, &new_gh->gh_iflags);
-
-		goto restart;
+		}
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+			gl->gl_demote_state != state) {
+		if (test_bit(GLF_DEMOTE_IN_PROGRESS,  &gl->gl_flags)) 
+			gl->gl_waiters2 = 1;
+		else 
+			gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
-
-out:
-	spin_unlock(&gl->gl_spin);
-
-	if (new_gh)
-		gfs2_holder_put(new_gh);
-}
-
-void gfs2_glock_inode_squish(struct inode *inode)
-{
-	struct gfs2_holder gh;
-	struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
-	gfs2_holder_init(gl, LM_ST_UNLOCKED, 0, &gh);
-	set_bit(HIF_DEMOTE, &gh.gh_iflags);
-	spin_lock(&gl->gl_spin);
-	gfs2_assert(inode->i_sb->s_fs_info, list_empty(&gl->gl_holders));
-	list_add_tail(&gh.gh_list, &gl->gl_waiters2);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
-	wait_for_completion(&gh.gh_wait);
-	gfs2_holder_uninit(&gh);
 }
 
 /**
@@ -837,6 +733,7 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 	}
 
 	gl->gl_state = new_state;
+	gl->gl_tchange = jiffies;
 }
 
 /**
@@ -855,73 +752,64 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
 	int op_done = 1;
 
 	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-	gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
+	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
 	gfs2_assert_warn(sdp, !(ret & LM_OUT_ASYNC));
 
 	state_change(gl, ret & LM_OUT_ST_MASK);
 
 	if (prev_state != LM_ST_UNLOCKED && !(ret & LM_OUT_CACHEABLE)) {
 		if (glops->go_inval)
-			glops->go_inval(gl, DIO_METADATA | DIO_DATA);
+			glops->go_inval(gl, DIO_METADATA);
 	} else if (gl->gl_state == LM_ST_DEFERRED) {
 		/* We might not want to do this here.
 		   Look at moving to the inode glops. */
 		if (glops->go_inval)
-			glops->go_inval(gl, DIO_DATA);
+			glops->go_inval(gl, 0);
 	}
 
 	/*  Deal with each possible exit condition  */
 
-	if (!gh)
+	if (!gh) {
 		gl->gl_stamp = jiffies;
-	else if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
-		gh->gh_error = -EIO;
-		spin_unlock(&gl->gl_spin);
-	} else if (test_bit(HIF_DEMOTE, &gh->gh_iflags)) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
-		if (gl->gl_state == gh->gh_state ||
-		    gl->gl_state == LM_ST_UNLOCKED) {
-			gh->gh_error = 0;
+		if (ret & LM_OUT_CANCELED) {
+			op_done = 0;
 		} else {
-			if (gfs2_assert_warn(sdp, gh->gh_flags &
-					(LM_FLAG_TRY | LM_FLAG_TRY_1CB)) == -1)
-				fs_warn(sdp, "ret = 0x%.8X\n", ret);
-			gh->gh_error = GLR_TRYFAILED;
+			spin_lock(&gl->gl_spin);
+			if (gl->gl_state != gl->gl_demote_state) {
+				gl->gl_req_bh = NULL;
+				spin_unlock(&gl->gl_spin);
+				gfs2_glock_drop_th(gl);
+				gfs2_glock_put(gl);
+				return;
+			}
+			gfs2_demote_wake(gl);
+			spin_unlock(&gl->gl_spin);
 		}
-		spin_unlock(&gl->gl_spin);
-
-		if (ret & LM_OUT_CANCELED)
-			handle_callback(gl, LM_ST_UNLOCKED);
-
-	} else if (ret & LM_OUT_CANCELED) {
+	} else {
 		spin_lock(&gl->gl_spin);
 		list_del_init(&gh->gh_list);
+		gh->gh_error = -EIO;
+		if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) 
+			goto out;
 		gh->gh_error = GLR_CANCELED;
-		spin_unlock(&gl->gl_spin);
-
-	} else if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
-		spin_lock(&gl->gl_spin);
-		list_move_tail(&gh->gh_list, &gl->gl_holders);
-		gh->gh_error = 0;
-		set_bit(HIF_HOLDER, &gh->gh_iflags);
-		spin_unlock(&gl->gl_spin);
-
-		set_bit(HIF_FIRST, &gh->gh_iflags);
-
-		op_done = 0;
-
-	} else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
+		if (ret & LM_OUT_CANCELED) 
+			goto out;
+		if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
+			list_add_tail(&gh->gh_list, &gl->gl_holders);
+			gh->gh_error = 0;
+			set_bit(HIF_HOLDER, &gh->gh_iflags);
+			set_bit(HIF_FIRST, &gh->gh_iflags);
+			op_done = 0;
+			goto out;
+		}
 		gh->gh_error = GLR_TRYFAILED;
-		spin_unlock(&gl->gl_spin);
-
-	} else {
+		if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+			goto out;
+		gh->gh_error = -EINVAL;
 		if (gfs2_assert_withdraw(sdp, 0) == -1)
 			fs_err(sdp, "ret = 0x%.8X\n", ret);
+out:
+		spin_unlock(&gl->gl_spin);
 	}
 
 	if (glops->go_xmote_bh)
@@ -932,18 +820,13 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
 		gl->gl_req_gh = NULL;
 		gl->gl_req_bh = NULL;
 		clear_bit(GLF_LOCK, &gl->gl_flags);
-		run_queue(gl);
 		spin_unlock(&gl->gl_spin);
 	}
 
 	gfs2_glock_put(gl);
 
-	if (gh) {
-		if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
-			gfs2_holder_put(gh);
-		else
-			complete(&gh->gh_wait);
-	}
+	if (gh)
+		gfs2_holder_wake(gh);
 }
 
 /**
@@ -954,23 +837,25 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
  *
  */
 
-void gfs2_glock_xmote_th(struct gfs2_glock *gl, unsigned int state, int flags)
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
+	int flags = gh ? gh->gh_flags : 0;
+	unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
 				 LM_FLAG_NOEXP | LM_FLAG_ANY |
 				 LM_FLAG_PRIORITY);
 	unsigned int lck_ret;
 
+	if (glops->go_xmote_th)
+		glops->go_xmote_th(gl);
+
 	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-	gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
+	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
 	gfs2_assert_warn(sdp, state != LM_ST_UNLOCKED);
 	gfs2_assert_warn(sdp, state != gl->gl_state);
 
-	if (gl->gl_state == LM_ST_EXCLUSIVE && glops->go_sync)
-		glops->go_sync(gl, DIO_METADATA | DIO_DATA | DIO_RELEASE);
-
 	gfs2_glock_hold(gl);
 	gl->gl_req_bh = xmote_bh;
 
@@ -1001,16 +886,14 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_holder *gh = gl->gl_req_gh;
 
-	clear_bit(GLF_PREFETCH, &gl->gl_flags);
-
 	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-	gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
+	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
 	gfs2_assert_warn(sdp, !ret);
 
 	state_change(gl, LM_ST_UNLOCKED);
 
 	if (glops->go_inval)
-		glops->go_inval(gl, DIO_METADATA | DIO_DATA);
+		glops->go_inval(gl, DIO_METADATA);
 
 	if (gh) {
 		spin_lock(&gl->gl_spin);
@@ -1019,24 +902,17 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 		spin_unlock(&gl->gl_spin);
 	}
 
-	if (glops->go_drop_bh)
-		glops->go_drop_bh(gl);
-
 	spin_lock(&gl->gl_spin);
+	gfs2_demote_wake(gl);
 	gl->gl_req_gh = NULL;
 	gl->gl_req_bh = NULL;
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
 
 	gfs2_glock_put(gl);
 
-	if (gh) {
-		if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
-			gfs2_holder_put(gh);
-		else
-			complete(&gh->gh_wait);
-	}
+	if (gh)
+		gfs2_holder_wake(gh);
 }
 
 /**
@@ -1045,19 +921,19 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
  *
  */
 
-void gfs2_glock_drop_th(struct gfs2_glock *gl)
+static void gfs2_glock_drop_th(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	unsigned int ret;
 
+	if (glops->go_xmote_th)
+		glops->go_xmote_th(gl);
+
 	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-	gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
+	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
 	gfs2_assert_warn(sdp, gl->gl_state != LM_ST_UNLOCKED);
 
-	if (gl->gl_state == LM_ST_EXCLUSIVE && glops->go_sync)
-		glops->go_sync(gl, DIO_METADATA | DIO_DATA | DIO_RELEASE);
-
 	gfs2_glock_hold(gl);
 	gl->gl_req_bh = drop_bh;
 
@@ -1137,8 +1013,7 @@ static int glock_wait_internal(struct gfs2_holder *gh)
 	if (gh->gh_flags & LM_FLAG_PRIORITY)
 		do_cancels(gh);
 
-	wait_for_completion(&gh->gh_wait);
-
+	wait_on_holder(gh);
 	if (gh->gh_error)
 		return gh->gh_error;
 
@@ -1170,18 +1045,32 @@ static int glock_wait_internal(struct gfs2_holder *gh)
 }
 
 static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct task_struct *owner)
+find_holder_by_owner(struct list_head *head, pid_t pid)
 {
 	struct gfs2_holder *gh;
 
 	list_for_each_entry(gh, head, gh_list) {
-		if (gh->gh_owner == owner)
+		if (gh->gh_owner_pid == pid)
 			return gh;
 	}
 
 	return NULL;
 }
 
+static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	if (gi) {
+		vsprintf(gi->string, fmt, args);
+		seq_printf(gi->seq, gi->string);
+	}
+	else
+		vprintk(fmt, args);
+	va_end(args);
+}
+
 /**
  * add_to_queue - Add a holder to the wait queue (but look for recursion)
  * @gh: the holder structure to add
@@ -1193,32 +1082,41 @@ static void add_to_queue(struct gfs2_holder *gh)
 	struct gfs2_glock *gl = gh->gh_gl;
 	struct gfs2_holder *existing;
 
-	BUG_ON(!gh->gh_owner);
-
-	existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		printk(KERN_INFO "pid : %d\n", existing->gh_owner->pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n", 
-				existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		printk(KERN_INFO "pid : %d\n", gh->gh_owner->pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n", 
-				gl->gl_name.ln_type, gl->gl_state);
+	BUG_ON(!gh->gh_owner_pid);
+	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
 		BUG();
-	}
 
-	existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		BUG();
+	if (!(gh->gh_flags & GL_FLOCK)) {
+		existing = find_holder_by_owner(&gl->gl_holders, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       existing->gh_gl->gl_name.ln_type, 
+			       existing->gh_gl->gl_state);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       gl->gl_name.ln_type, gl->gl_state);
+			BUG();
+		}
+		
+		existing = find_holder_by_owner(&gl->gl_waiters3, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			BUG();
+		}
 	}
 
 	if (gh->gh_flags & LM_FLAG_PRIORITY)
 		list_add(&gh->gh_list, &gl->gl_waiters3);
 	else
-		list_add_tail(&gh->gh_list, &gl->gl_waiters3);	
+		list_add_tail(&gh->gh_list, &gl->gl_waiters3);
 }
 
 /**
@@ -1242,8 +1140,6 @@ restart:
 		return -EIO;
 	}
 
-	set_bit(HIF_PROMOTE, &gh->gh_iflags);
-
 	spin_lock(&gl->gl_spin);
 	add_to_queue(gh);
 	run_queue(gl);
@@ -1257,11 +1153,6 @@ restart:
 		}
 	}
 
-	clear_bit(GLF_PREFETCH, &gl->gl_flags);
-
-	if (error == GLR_TRYFAILED && (gh->gh_flags & GL_DUMP))
-		dump_glock(gl);
-
 	return error;
 }
 
@@ -1328,9 +1219,10 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned delay = 0;
 
 	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED);
+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 
 	gfs2_glmutex_lock(gl);
 
@@ -1338,111 +1230,30 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	list_del_init(&gh->gh_list);
 
 	if (list_empty(&gl->gl_holders)) {
-		spin_unlock(&gl->gl_spin);
-
-		if (glops->go_unlock)
+		if (glops->go_unlock) {
+			spin_unlock(&gl->gl_spin);
 			glops->go_unlock(gh);
-
+			spin_lock(&gl->gl_spin);
+		}
 		gl->gl_stamp = jiffies;
-
-		spin_lock(&gl->gl_spin);
 	}
 
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
-}
-
-/**
- * gfs2_glock_prefetch - Try to prefetch a glock
- * @gl: the glock
- * @state: the state to prefetch in
- * @flags: flags passed to go_xmote_th()
- *
- */
-
-static void gfs2_glock_prefetch(struct gfs2_glock *gl, unsigned int state,
-				int flags)
-{
-	const struct gfs2_glock_operations *glops = gl->gl_ops;
-
-	spin_lock(&gl->gl_spin);
-
-	if (test_bit(GLF_LOCK, &gl->gl_flags) || !list_empty(&gl->gl_holders) ||
-	    !list_empty(&gl->gl_waiters1) || !list_empty(&gl->gl_waiters2) ||
-	    !list_empty(&gl->gl_waiters3) ||
-	    relaxed_state_ok(gl->gl_state, state, flags)) {
-		spin_unlock(&gl->gl_spin);
-		return;
-	}
 
-	set_bit(GLF_PREFETCH, &gl->gl_flags);
-	set_bit(GLF_LOCK, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
-
-	glops->go_xmote_th(gl, state, flags);
-}
-
-static void greedy_work(void *data)
-{
-	struct greedy *gr = data;
-	struct gfs2_holder *gh = &gr->gr_gh;
-	struct gfs2_glock *gl = gh->gh_gl;
-	const struct gfs2_glock_operations *glops = gl->gl_ops;
-
-	clear_bit(GLF_SKIP_WAITERS2, &gl->gl_flags);
-
-	if (glops->go_greedy)
-		glops->go_greedy(gl);
-
-	spin_lock(&gl->gl_spin);
-
-	if (list_empty(&gl->gl_waiters2)) {
-		clear_bit(GLF_GREEDY, &gl->gl_flags);
-		spin_unlock(&gl->gl_spin);
-		gfs2_holder_uninit(gh);
-		kfree(gr);
-	} else {
-		gfs2_glock_hold(gl);
-		list_add_tail(&gh->gh_list, &gl->gl_waiters2);
-		run_queue(gl);
-		spin_unlock(&gl->gl_spin);
+	gfs2_glock_hold(gl);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
 		gfs2_glock_put(gl);
-	}
 }
 
-/**
- * gfs2_glock_be_greedy -
- * @gl:
- * @time:
- *
- * Returns: 0 if go_greedy will be called, 1 otherwise
- */
-
-int gfs2_glock_be_greedy(struct gfs2_glock *gl, unsigned int time)
+void gfs2_glock_dq_wait(struct gfs2_holder *gh)
 {
-	struct greedy *gr;
-	struct gfs2_holder *gh;
-
-	if (!time || gl->gl_sbd->sd_args.ar_localcaching ||
-	    test_and_set_bit(GLF_GREEDY, &gl->gl_flags))
-		return 1;
-
-	gr = kmalloc(sizeof(struct greedy), GFP_KERNEL);
-	if (!gr) {
-		clear_bit(GLF_GREEDY, &gl->gl_flags);
-		return 1;
-	}
-	gh = &gr->gr_gh;
-
-	gfs2_holder_init(gl, 0, 0, gh);
-	set_bit(HIF_GREEDY, &gh->gh_iflags);
-	INIT_WORK(&gr->gr_work, greedy_work, gr);
-
-	set_bit(GLF_SKIP_WAITERS2, &gl->gl_flags);
-	schedule_delayed_work(&gr->gr_work, time);
-
-	return 0;
+	struct gfs2_glock *gl = gh->gh_gl;
+	gfs2_glock_dq(gh);
+	wait_on_demote(gl);
 }
 
 /**
@@ -1503,10 +1314,7 @@ static int glock_compare(const void *arg_a, const void *arg_b)
 		return 1;
 	if (a->ln_number < b->ln_number)
 		return -1;
-	if (gh_a->gh_state == LM_ST_SHARED && gh_b->gh_state == LM_ST_EXCLUSIVE)
-		return 1;
-	if (!(gh_a->gh_flags & GL_LOCAL_EXCL) && (gh_b->gh_flags & GL_LOCAL_EXCL))
-		return 1;
+	BUG_ON(gh_a->gh_gl->gl_ops->go_type == gh_b->gh_gl->gl_ops->go_type);
 	return 0;
 }
 
@@ -1549,10 +1357,6 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs,
  * @num_gh: the number of structures
  * @ghs: an array of struct gfs2_holder structures
  *
- * Figure out how big an impact this function has.  Either:
- * 1) Replace this code with code that calls gfs2_glock_prefetch()
- * 2) Forget async stuff and just call nq_m_sync()
- * 3) Leave it like it is
  *
  * Returns: 0 on success (all glocks acquired),
  *          errno on failure (no glocks acquired)
@@ -1560,62 +1364,28 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs,
 
 int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
 {
-	int *e;
-	unsigned int x;
-	int borked = 0, serious = 0;
+	struct gfs2_holder *tmp[4];
+	struct gfs2_holder **pph = tmp;
 	int error = 0;
 
-	if (!num_gh)
+	switch(num_gh) {
+	case 0:
 		return 0;
-
-	if (num_gh == 1) {
+	case 1:
 		ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
 		return gfs2_glock_nq(ghs);
-	}
-
-	e = kcalloc(num_gh, sizeof(struct gfs2_holder *), GFP_KERNEL);
-	if (!e)
-		return -ENOMEM;
-
-	for (x = 0; x < num_gh; x++) {
-		ghs[x].gh_flags |= LM_FLAG_TRY | GL_ASYNC;
-		error = gfs2_glock_nq(&ghs[x]);
-		if (error) {
-			borked = 1;
-			serious = error;
-			num_gh = x;
+	default:
+		if (num_gh <= 4)
 			break;
-		}
+		pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
+		if (!pph)
+			return -ENOMEM;
 	}
 
-	for (x = 0; x < num_gh; x++) {
-		error = e[x] = glock_wait_internal(&ghs[x]);
-		if (error) {
-			borked = 1;
-			if (error != GLR_TRYFAILED && error != GLR_CANCELED)
-				serious = error;
-		}
-	}
+	error = nq_m_sync(num_gh, ghs, pph);
 
-	if (!borked) {
-		kfree(e);
-		return 0;
-	}
-
-	for (x = 0; x < num_gh; x++)
-		if (!e[x])
-			gfs2_glock_dq(&ghs[x]);
-
-	if (serious)
-		error = serious;
-	else {
-		for (x = 0; x < num_gh; x++)
-			gfs2_holder_reinit(ghs[x].gh_state, ghs[x].gh_flags,
-					  &ghs[x]);
-		error = nq_m_sync(num_gh, ghs, (struct gfs2_holder **)e);
-	}
-
-	kfree(e);
+	if (pph != tmp)
+		kfree(pph);
 
 	return error;
 }
@@ -1651,34 +1421,6 @@ void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
 }
 
 /**
- * gfs2_glock_prefetch_num - prefetch a glock based on lock number
- * @sdp: the filesystem
- * @number: the lock number
- * @glops: the glock operations for the type of glock
- * @state: the state to acquire the glock in
- * @flags: modifier flags for the aquisition
- *
- * Returns: errno
- */
-
-void gfs2_glock_prefetch_num(struct gfs2_sbd *sdp, u64 number,
-			     const struct gfs2_glock_operations *glops,
-			     unsigned int state, int flags)
-{
-	struct gfs2_glock *gl;
-	int error;
-
-	if (atomic_read(&sdp->sd_reclaim_count) <
-	    gfs2_tune_get(sdp, gt_reclaim_limit)) {
-		error = gfs2_glock_get(sdp, number, glops, CREATE, &gl);
-		if (!error) {
-			gfs2_glock_prefetch(gl, state, flags);
-			gfs2_glock_put(gl);
-		}
-	}
-}
-
-/**
  * gfs2_lvb_hold - attach a LVB from a glock
  * @gl: The glock in question
  *
@@ -1731,20 +1473,21 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
 			unsigned int state)
 {
 	struct gfs2_glock *gl;
+	unsigned long delay = 0;
+	unsigned long holdtime;
+	unsigned long now = jiffies;
 
 	gl = gfs2_glock_find(sdp, name);
 	if (!gl)
 		return;
 
-	if (gl->gl_ops->go_callback)
-		gl->gl_ops->go_callback(gl, state);
-	handle_callback(gl, state);
-
-	spin_lock(&gl->gl_spin);
-	run_queue(gl);
-	spin_unlock(&gl->gl_spin);
+	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+	if (time_before(now, holdtime))
+		delay = holdtime - now;
 
-	gfs2_glock_put(gl);
+	handle_callback(gl, state, 1, delay);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 /**
@@ -1779,12 +1522,15 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
 		struct lm_async_cb *async = data;
 		struct gfs2_glock *gl;
 
+		down_read(&gfs2_umount_flush_sem);
 		gl = gfs2_glock_find(sdp, &async->lc_name);
 		if (gfs2_assert_warn(sdp, gl))
 			return;
 		if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
 			gl->gl_req_bh(gl, async->lc_ret);
-		gfs2_glock_put(gl);
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put(gl);
+		up_read(&gfs2_umount_flush_sem);
 		return;
 	}
 
@@ -1814,15 +1560,11 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
 
 static int demote_ok(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	int demote = 1;
 
 	if (test_bit(GLF_STICKY, &gl->gl_flags))
 		demote = 0;
-	else if (test_bit(GLF_PREFETCH, &gl->gl_flags))
-		demote = time_after_eq(jiffies, gl->gl_stamp +
-				    gfs2_tune_get(sdp, gt_prefetch_secs) * HZ);
 	else if (glops->go_demote_ok)
 		demote = glops->go_demote_ok(gl);
 
@@ -1878,9 +1620,9 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
 	atomic_inc(&sdp->sd_reclaimed);
 
 	if (gfs2_glmutex_trylock(gl)) {
-		if (queue_empty(gl, &gl->gl_holders) &&
+		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
-			handle_callback(gl, LM_ST_UNLOCKED);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 
@@ -1899,51 +1641,36 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
 static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
 			  unsigned int hash)
 {
-	struct glock_plug plug;
-	struct list_head *tmp;
-	struct gfs2_glock *gl;
-	int entries;
-
-	/* Add "plug" to end of bucket list, work back up list from there */
-	memset(&plug.gl_flags, 0, sizeof(unsigned long));
-	set_bit(GLF_PLUG, &plug.gl_flags);
-
-	write_lock(gl_lock_addr(hash));
-	list_add(&plug.gl_list, &gl_hash_table[hash].hb_list);
-	write_unlock(gl_lock_addr(hash));
-
-	for (;;) {
-		write_lock(gl_lock_addr(hash));
+	struct gfs2_glock *gl, *prev = NULL;
+	int has_entries = 0;
+	struct hlist_head *head = &gl_hash_table[hash].hb_list;
 
-		for (;;) {
-			tmp = plug.gl_list.next;
-
-			if (tmp == &gl_hash_table[hash].hb_list) {
-				list_del(&plug.gl_list);
-				entries = !list_empty(&gl_hash_table[hash].hb_list);
-				write_unlock(gl_lock_addr(hash));
-				return entries;
-			}
-			gl = list_entry(tmp, struct gfs2_glock, gl_list);
-
-			/* Move plug up list */
-			list_move(&plug.gl_list, &gl->gl_list);
-
-			if (test_bit(GLF_PLUG, &gl->gl_flags))
-				continue;
-			if (gl->gl_sbd != sdp)
-				continue;
-
-			/* examiner() must glock_put() */
+	read_lock(gl_lock_addr(hash));
+	/* Can't use hlist_for_each_entry - don't want prefetch here */
+	if (hlist_empty(head))
+		goto out;
+	gl = list_entry(head->first, struct gfs2_glock, gl_list);
+	while(1) {
+		if (!sdp || gl->gl_sbd == sdp) {
 			gfs2_glock_hold(gl);
-
-			break;
+			read_unlock(gl_lock_addr(hash));
+			if (prev)
+				gfs2_glock_put(prev);
+			prev = gl;
+			examiner(gl);
+			has_entries = 1;
+			read_lock(gl_lock_addr(hash));
 		}
-
-		write_unlock(gl_lock_addr(hash));
-
-		examiner(gl);
+		if (gl->gl_list.next == NULL)
+			break;
+		gl = list_entry(gl->gl_list.next, struct gfs2_glock, gl_list);
 	}
+out:
+	read_unlock(gl_lock_addr(hash));
+	if (prev)
+		gfs2_glock_put(prev);
+	cond_resched();
+	return has_entries;
 }
 
 /**
@@ -1954,38 +1681,20 @@ static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
 
 static void scan_glock(struct gfs2_glock *gl)
 {
-	if (gl->gl_ops == &gfs2_inode_glops)
-		goto out;
+	if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object)
+		return;
 
 	if (gfs2_glmutex_trylock(gl)) {
-		if (queue_empty(gl, &gl->gl_holders) &&
-		    gl->gl_state != LM_ST_UNLOCKED &&
-		    demote_ok(gl))
+		if (list_empty(&gl->gl_holders) &&
+		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
 			goto out_schedule;
 		gfs2_glmutex_unlock(gl);
 	}
-out:
-	gfs2_glock_put(gl);
 	return;
 
 out_schedule:
 	gfs2_glmutex_unlock(gl);
 	gfs2_glock_schedule_for_reclaim(gl);
-	gfs2_glock_put(gl);
-}
-
-/**
- * gfs2_scand_internal - Look for glocks and inodes to toss from memory
- * @sdp: the filesystem
- *
- */
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp)
-{
-	unsigned int x;
-
-	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
-		examine_bucket(scan_glock, sdp, x);
 }
 
 /**
@@ -2011,14 +1720,11 @@ static void clear_glock(struct gfs2_glock *gl)
 	}
 
 	if (gfs2_glmutex_trylock(gl)) {
-		if (queue_empty(gl, &gl->gl_holders) &&
+		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED)
-			handle_callback(gl, LM_ST_UNLOCKED);
-
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
-
-	gfs2_glock_put(gl);
 }
 
 /**
@@ -2040,10 +1746,10 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
 
 	for (;;) {
 		cont = 0;
-
-		for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+		for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
 			if (examine_bucket(clear_glock, sdp, x))
 				cont = 1;
+		}
 
 		if (!wait || !cont)
 			break;
@@ -2056,7 +1762,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
 			t = jiffies;
 		}
 
+		down_write(&gfs2_umount_flush_sem);
 		invalidate_inodes(sdp->sd_vfs);
+		up_write(&gfs2_umount_flush_sem);
 		msleep(10);
 	}
 }
@@ -2065,6 +1773,15 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
  *  Diagnostic routines to help debug distributed deadlock
  */
 
+static void gfs2_print_symbol(struct glock_iter *gi, const char *fmt,
+                              unsigned long address)
+{
+	char buffer[KSYM_SYMBOL_LEN];
+
+	sprint_symbol(buffer, address);
+	print_dbg(gi, fmt, buffer);
+}
+
 /**
  * dump_holder - print information about a glock holder
  * @str: a string naming the type of holder
@@ -2073,31 +1790,37 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
  * Returns: 0 on success, -ENOBUFS when we run out of space
  */
 
-static int dump_holder(char *str, struct gfs2_holder *gh)
+static int dump_holder(struct glock_iter *gi, char *str,
+		       struct gfs2_holder *gh)
 {
 	unsigned int x;
-	int error = -ENOBUFS;
-
-	printk(KERN_INFO "  %s\n", str);
-	printk(KERN_INFO "    owner = %ld\n",
-		   (gh->gh_owner) ? (long)gh->gh_owner->pid : -1);
-	printk(KERN_INFO "    gh_state = %u\n", gh->gh_state);
-	printk(KERN_INFO "    gh_flags =");
+	struct task_struct *gh_owner;
+
+	print_dbg(gi, "  %s\n", str);
+	if (gh->gh_owner_pid) {
+		print_dbg(gi, "    owner = %ld ", (long)gh->gh_owner_pid);
+		gh_owner = find_task_by_pid(gh->gh_owner_pid);
+		if (gh_owner)
+			print_dbg(gi, "(%s)\n", gh_owner->comm);
+		else
+			print_dbg(gi, "(ended)\n");
+	} else
+		print_dbg(gi, "    owner = -1\n");
+	print_dbg(gi, "    gh_state = %u\n", gh->gh_state);
+	print_dbg(gi, "    gh_flags =");
 	for (x = 0; x < 32; x++)
 		if (gh->gh_flags & (1 << x))
-			printk(" %u", x);
-	printk(" \n");
-	printk(KERN_INFO "    error = %d\n", gh->gh_error);
-	printk(KERN_INFO "    gh_iflags =");
+			print_dbg(gi, " %u", x);
+	print_dbg(gi, " \n");
+	print_dbg(gi, "    error = %d\n", gh->gh_error);
+	print_dbg(gi, "    gh_iflags =");
 	for (x = 0; x < 32; x++)
 		if (test_bit(x, &gh->gh_iflags))
-			printk(" %u", x);
-	printk(" \n");
-	print_symbol(KERN_INFO "    initialized at: %s\n", gh->gh_ip);
-
-	error = 0;
+			print_dbg(gi, " %u", x);
+	print_dbg(gi, " \n");
+        gfs2_print_symbol(gi, "    initialized at: %s\n", gh->gh_ip);
 
-	return error;
+	return 0;
 }
 
 /**
@@ -2107,25 +1830,21 @@ static int dump_holder(char *str, struct gfs2_holder *gh)
  * Returns: 0 on success, -ENOBUFS when we run out of space
  */
 
-static int dump_inode(struct gfs2_inode *ip)
+static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
 {
 	unsigned int x;
-	int error = -ENOBUFS;
 
-	printk(KERN_INFO "  Inode:\n");
-	printk(KERN_INFO "    num = %llu %llu\n",
-		    (unsigned long long)ip->i_num.no_formal_ino,
-		    (unsigned long long)ip->i_num.no_addr);
-	printk(KERN_INFO "    type = %u\n", IF2DT(ip->i_di.di_mode));
-	printk(KERN_INFO "    i_flags =");
+	print_dbg(gi, "  Inode:\n");
+	print_dbg(gi, "    num = %llu/%llu\n",
+		  (unsigned long long)ip->i_no_formal_ino,
+		  (unsigned long long)ip->i_no_addr);
+	print_dbg(gi, "    type = %u\n", IF2DT(ip->i_inode.i_mode));
+	print_dbg(gi, "    i_flags =");
 	for (x = 0; x < 32; x++)
 		if (test_bit(x, &ip->i_flags))
-			printk(" %u", x);
-	printk(" \n");
-
-	error = 0;
-
-	return error;
+			print_dbg(gi, " %u", x);
+	print_dbg(gi, " \n");
+	return 0;
 }
 
 /**
@@ -2136,74 +1855,84 @@ static int dump_inode(struct gfs2_inode *ip)
  * Returns: 0 on success, -ENOBUFS when we run out of space
  */
 
-static int dump_glock(struct gfs2_glock *gl)
+static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
 {
 	struct gfs2_holder *gh;
 	unsigned int x;
 	int error = -ENOBUFS;
+	struct task_struct *gl_owner;
 
 	spin_lock(&gl->gl_spin);
 
-	printk(KERN_INFO "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
-	       (unsigned long long)gl->gl_name.ln_number);
-	printk(KERN_INFO "  gl_flags =");
+	print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
+		   (unsigned long long)gl->gl_name.ln_number);
+	print_dbg(gi, "  gl_flags =");
 	for (x = 0; x < 32; x++) {
 		if (test_bit(x, &gl->gl_flags))
-			printk(" %u", x);
-	}
-	printk(" \n");
-	printk(KERN_INFO "  gl_ref = %d\n", atomic_read(&gl->gl_ref.refcount));
-	printk(KERN_INFO "  gl_state = %u\n", gl->gl_state);
-	printk(KERN_INFO "  gl_owner = %s\n", gl->gl_owner->comm);
-	print_symbol(KERN_INFO "  gl_ip = %s\n", gl->gl_ip);
-	printk(KERN_INFO "  req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
-	printk(KERN_INFO "  req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
-	printk(KERN_INFO "  lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
-	printk(KERN_INFO "  object = %s\n", (gl->gl_object) ? "yes" : "no");
-	printk(KERN_INFO "  le = %s\n",
-		   (list_empty(&gl->gl_le.le_list)) ? "no" : "yes");
-	printk(KERN_INFO "  reclaim = %s\n",
-		    (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
+			print_dbg(gi, " %u", x);
+	}
+	if (!test_bit(GLF_LOCK, &gl->gl_flags))
+		print_dbg(gi, " (unlocked)");
+	print_dbg(gi, " \n");
+	print_dbg(gi, "  gl_ref = %d\n", atomic_read(&gl->gl_ref));
+	print_dbg(gi, "  gl_state = %u\n", gl->gl_state);
+	if (gl->gl_owner_pid) {
+		gl_owner = find_task_by_pid(gl->gl_owner_pid);
+		if (gl_owner)
+			print_dbg(gi, "  gl_owner = pid %d (%s)\n",
+				  gl->gl_owner_pid, gl_owner->comm);
+		else
+			print_dbg(gi, "  gl_owner = %d (ended)\n",
+				  gl->gl_owner_pid);
+	} else
+		print_dbg(gi, "  gl_owner = -1\n");
+	print_dbg(gi, "  gl_ip = %lu\n", gl->gl_ip);
+	print_dbg(gi, "  req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
+	print_dbg(gi, "  req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
+	print_dbg(gi, "  lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
+	print_dbg(gi, "  object = %s\n", (gl->gl_object) ? "yes" : "no");
+	print_dbg(gi, "  reclaim = %s\n",
+		   (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
 	if (gl->gl_aspace)
-		printk(KERN_INFO "  aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
-		       gl->gl_aspace->i_mapping->nrpages);
+		print_dbg(gi, "  aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
+			   gl->gl_aspace->i_mapping->nrpages);
 	else
-		printk(KERN_INFO "  aspace = no\n");
-	printk(KERN_INFO "  ail = %d\n", atomic_read(&gl->gl_ail_count));
+		print_dbg(gi, "  aspace = no\n");
+	print_dbg(gi, "  ail = %d\n", atomic_read(&gl->gl_ail_count));
 	if (gl->gl_req_gh) {
-		error = dump_holder("Request", gl->gl_req_gh);
+		error = dump_holder(gi, "Request", gl->gl_req_gh);
 		if (error)
 			goto out;
 	}
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
-		error = dump_holder("Holder", gh);
+		error = dump_holder(gi, "Holder", gh);
 		if (error)
 			goto out;
 	}
 	list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
-		error = dump_holder("Waiter1", gh);
-		if (error)
-			goto out;
-	}
-	list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
-		error = dump_holder("Waiter2", gh);
+		error = dump_holder(gi, "Waiter1", gh);
 		if (error)
 			goto out;
 	}
 	list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
-		error = dump_holder("Waiter3", gh);
+		error = dump_holder(gi, "Waiter3", gh);
 		if (error)
 			goto out;
 	}
+	if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+		print_dbg(gi, "  Demotion req to state %u (%llu uS ago)\n",
+			  gl->gl_demote_state, (unsigned long long)
+			  (jiffies - gl->gl_demote_time)*(1000000/HZ));
+	}
 	if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
 		if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
-		    list_empty(&gl->gl_holders)) {
-			error = dump_inode(gl->gl_object);
+			list_empty(&gl->gl_holders)) {
+			error = dump_inode(gi, gl->gl_object);
 			if (error)
 				goto out;
 		} else {
 			error = -ENOBUFS;
-			printk(KERN_INFO "  Inode: busy\n");
+			print_dbg(gi, "  Inode: busy\n");
 		}
 	}
 
@@ -2226,6 +1955,7 @@ out:
 static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
+	struct hlist_node *h;
 	unsigned int x;
 	int error = 0;
 
@@ -2233,13 +1963,11 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
 
 		read_lock(gl_lock_addr(x));
 
-		list_for_each_entry(gl, &gl_hash_table[x].hb_list, gl_list) {
-			if (test_bit(GLF_PLUG, &gl->gl_flags))
-				continue;
+		hlist_for_each_entry(gl, h, &gl_hash_table[x].hb_list, gl_list) {
 			if (gl->gl_sbd != sdp)
 				continue;
 
-			error = dump_glock(gl);
+			error = dump_glock(NULL, gl);
 			if (error)
 				break;
 		}
@@ -2254,17 +1982,250 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
 	return error;
 }
 
+/**
+ * gfs2_scand - Look for cached glocks and inodes to toss from memory
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * One of these daemons runs, finding candidates to add to sd_reclaim_list.
+ * See gfs2_glockd()
+ */
+
+static int gfs2_scand(void *data)
+{
+	unsigned x;
+	unsigned delay;
+
+	while (!kthread_should_stop()) {
+		for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+			examine_bucket(scan_glock, NULL, x);
+		if (freezing(current))
+			refrigerator();
+		delay = scand_secs;
+		if (delay < 1)
+			delay = 1;
+		schedule_timeout_interruptible(delay * HZ);
+	}
+
+	return 0;
+}
+
+
+
 int __init gfs2_glock_init(void)
 {
 	unsigned i;
 	for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
-		INIT_LIST_HEAD(&gl_hash_table[i].hb_list);
+		INIT_HLIST_HEAD(&gl_hash_table[i].hb_list);
 	}
 #ifdef GL_HASH_LOCK_SZ
 	for(i = 0; i < GL_HASH_LOCK_SZ; i++) {
 		rwlock_init(&gl_hash_locks[i]);
 	}
 #endif
+
+	scand_process = kthread_run(gfs2_scand, NULL, "gfs2_scand");
+	if (IS_ERR(scand_process))
+		return PTR_ERR(scand_process);
+
+	glock_workqueue = create_workqueue("glock_workqueue");
+	if (IS_ERR(glock_workqueue)) {
+		kthread_stop(scand_process);
+		return PTR_ERR(glock_workqueue);
+	}
+
+	return 0;
+}
+
+void gfs2_glock_exit(void)
+{
+	destroy_workqueue(glock_workqueue);
+	kthread_stop(scand_process);
+}
+
+module_param(scand_secs, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs");
+
+static int gfs2_glock_iter_next(struct glock_iter *gi)
+{
+	struct gfs2_glock *gl;
+
+restart:
+	read_lock(gl_lock_addr(gi->hash));
+	gl = gi->gl;
+	if (gl) {
+		gi->gl = hlist_entry(gl->gl_list.next,
+				     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) {
+		if (gi->hash >= GFS2_GL_HASH_SIZE)
+			return 1;
+		read_lock(gl_lock_addr(gi->hash));
+		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));
+		gi->hash++;
+	}
+
+	if (gi->sdp != gi->gl->gl_sbd)
+		goto restart;
+
 	return 0;
 }
 
+static void gfs2_glock_iter_free(struct glock_iter *gi)
+{
+	if (gi->gl)
+		gfs2_glock_put(gi->gl);
+	kfree(gi);
+}
+
+static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
+{
+	struct glock_iter *gi;
+
+	gi = kmalloc(sizeof (*gi), GFP_KERNEL);
+	if (!gi)
+		return NULL;
+
+	gi->sdp = sdp;
+	gi->hash = 0;
+	gi->seq = NULL;
+	gi->gl = NULL;
+	memset(gi->string, 0, sizeof(gi->string));
+
+	if (gfs2_glock_iter_next(gi)) {
+		gfs2_glock_iter_free(gi);
+		return NULL;
+	}
+
+	return gi;
+}
+
+static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
+{
+	struct glock_iter *gi;
+	loff_t n = *pos;
+
+	gi = gfs2_glock_iter_init(file->private);
+	if (!gi)
+		return NULL;
+
+	while(n--) {
+		if (gfs2_glock_iter_next(gi)) {
+			gfs2_glock_iter_free(gi);
+			return NULL;
+		}
+	}
+
+	return gi;
+}
+
+static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
+				 loff_t *pos)
+{
+	struct glock_iter *gi = iter_ptr;
+
+	(*pos)++;
+
+	if (gfs2_glock_iter_next(gi)) {
+		gfs2_glock_iter_free(gi);
+		return NULL;
+	}
+
+	return gi;
+}
+
+static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
+{
+	struct glock_iter *gi = iter_ptr;
+	if (gi)
+		gfs2_glock_iter_free(gi);
+}
+
+static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
+{
+	struct glock_iter *gi = iter_ptr;
+
+	gi->seq = file;
+	dump_glock(gi, gi->gl);
+
+	return 0;
+}
+
+static const struct seq_operations gfs2_glock_seq_ops = {
+	.start = gfs2_glock_seq_start,
+	.next  = gfs2_glock_seq_next,
+	.stop  = gfs2_glock_seq_stop,
+	.show  = gfs2_glock_seq_show,
+};
+
+static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int ret;
+
+	ret = seq_open(file, &gfs2_glock_seq_ops);
+	if (ret)
+		return ret;
+
+	seq = file->private_data;
+	seq->private = inode->i_private;
+
+	return 0;
+}
+
+static const struct file_operations gfs2_debug_fops = {
+	.owner   = THIS_MODULE,
+	.open    = gfs2_debugfs_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
+{
+	sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root);
+	if (!sdp->debugfs_dir)
+		return -ENOMEM;
+	sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
+							 S_IFREG | S_IRUGO,
+							 sdp->debugfs_dir, sdp,
+							 &gfs2_debug_fops);
+	if (!sdp->debugfs_dentry_glocks)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
+{
+	if (sdp && sdp->debugfs_dir) {
+		if (sdp->debugfs_dentry_glocks) {
+			debugfs_remove(sdp->debugfs_dentry_glocks);
+			sdp->debugfs_dentry_glocks = NULL;
+		}
+		debugfs_remove(sdp->debugfs_dir);
+		sdp->debugfs_dir = NULL;
+	}
+}
+
+int gfs2_register_debugfs(void)
+{
+	gfs2_root = debugfs_create_dir("gfs2", NULL);
+	return gfs2_root ? 0 : -ENOMEM;
+}
+
+void gfs2_unregister_debugfs(void)
+{
+	debugfs_remove(gfs2_root);
+	gfs2_root = NULL;
+}