Attachment 304098 Details for Bug 432057 – Latest upstream patch

[patch] Latest upstream patch

glock-fix-7.diff (text/plain), 57.78 KB, created by Steve Whitehouse on 2008-04-29 10:43:32 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Steve Whitehouse

Created: 2008-04-29 10:43:32 UTC

Size: 57.78 KB

patch

obsolete

>diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
>index d636b3e..628aed6 100644
>--- a/fs/gfs2/glock.c
>+++ b/fs/gfs2/glock.c
>@@ -45,21 +45,11 @@ struct gfs2_gl_hash_bucket {
>         struct hlist_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 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 int dump_glock(struct gfs2_glock_iter *gi, struct gfs2_glock *gl);
>+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
> 
> static DECLARE_RWSEM(gfs2_umount_flush_sem);
> static struct dentry *gfs2_root;
>@@ -123,33 +113,6 @@ static inline rwlock_t *gl_lock_addr(unsigned int x)
> #endif
> 
> /**
>- * relaxed_state_ok - is a requested lock compatible with the current lock mode?
>- * @actual: the current state of the lock
>- * @requested: the lock state that was requested by the caller
>- * @flags: the modifier flags passed in by the caller
>- *
>- * Returns: 1 if the locks are compatible, 0 otherwise
>- */
>-
>-static inline int relaxed_state_ok(unsigned int actual, unsigned requested,
>-				   int flags)
>-{
>-	if (actual == requested)
>-		return 1;
>-
>-	if (flags & GL_EXACT)
>-		return 0;
>-
>-	if (actual == LM_ST_EXCLUSIVE && requested == LM_ST_SHARED)
>-		return 1;
>-
>-	if (actual != LM_ST_UNLOCKED && (flags & LM_FLAG_ANY))
>-		return 1;
>-
>-	return 0;
>-}
>-
>-/**
>  * gl_hash() - Turn glock number into hash bucket number
>  * @lock: The glock number
>  *
>@@ -220,8 +183,6 @@ int gfs2_glock_put(struct gfs2_glock *gl)
> 		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;
>@@ -281,6 +242,341 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
> 	return gl;
> }
> 
>+/**
>+ * may_grant - check if its ok to grant a new lock
>+ * @gl: The glock
>+ * @gh: The lock request which we wish to grant
>+ *
>+ * Returns: true if its ok to grant the lock
>+ */
>+
>+static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
>+{
>+	const struct gfs2_holder *gh_head = list_entry(gl->gl_holders.next, const struct gfs2_holder, gh_list);
>+	if ((gh->gh_state == LM_ST_EXCLUSIVE ||
>+	     gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
>+		return 0;
>+	if (gl->gl_state == gh->gh_state)
>+		return 1;
>+	if (gh->gh_flags & GL_EXACT)
>+		return 0;
>+	if (gh->gh_state == LM_ST_SHARED && gl->gl_state == LM_ST_EXCLUSIVE)
>+		return 1;
>+	if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
>+		return 1;
>+	return 0;
>+}
>+
>+static void gfs2_holder_wake(struct gfs2_holder *gh)
>+{
>+	clear_bit(HIF_WAIT, &gh->gh_iflags);
>+	smp_mb__after_clear_bit();
>+	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
>+}
>+
>+/**
>+ * do_promote - promote as many requests as possible on the current queue
>+ * @gl: The glock
>+ * 
>+ * Returns: true if there is a blocked holder at the head of the list
>+ */
>+
>+static int do_promote(struct gfs2_glock *gl)
>+{
>+	const struct gfs2_glock_operations *glops = gl->gl_ops;
>+	struct gfs2_holder *gh, *tmp;
>+	int ret;
>+
>+restart:
>+	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
>+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
>+			continue;
>+		if (may_grant(gl, gh)) {
>+			if (gh->gh_list.prev == &gl->gl_holders &&
>+			    glops->go_lock) {
>+				spin_unlock(&gl->gl_spin);
>+				/* FIXME: eliminate this eventually */
>+				ret = glops->go_lock(gh);
>+				spin_lock(&gl->gl_spin);
>+				if (ret) {
>+					gh->gh_error = ret;
>+					list_del_init(&gh->gh_list);
>+					gfs2_holder_wake(gh);
>+				}
>+				set_bit(HIF_HOLDER, &gh->gh_iflags);
>+				gfs2_holder_wake(gh);
>+				goto restart;
>+			}
>+			set_bit(HIF_HOLDER, &gh->gh_iflags);
>+			gfs2_holder_wake(gh);
>+			continue;
>+		}
>+		if (gh->gh_list.prev == &gl->gl_holders)
>+			return 1;
>+		break;
>+	}
>+	return 0;
>+}
>+
>+/**
>+ * do_error - Something unexpected has happened during a lock request
>+ *
>+ */
>+
>+static inline void do_error(struct gfs2_glock *gl, const int ret)
>+{
>+	struct gfs2_holder *gh, *tmp;
>+
>+	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
>+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
>+			continue;
>+		if (ret & LM_OUT_ERROR)
>+			gh->gh_error = -EIO;
>+		else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
>+			gh->gh_error = GLR_TRYFAILED;
>+		else
>+			continue;
>+		list_del_init(&gh->gh_list);
>+		gfs2_holder_wake(gh);
>+	}
>+}
>+
>+/**
>+ * find_first_waiter - find the first gh that's waiting for the glock
>+ * @gl: the glock
>+ */
>+
>+static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
>+{
>+	struct gfs2_holder *gh;
>+
>+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
>+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
>+			return gh;
>+	}
>+	return NULL;
>+}
>+
>+/**
>+ * state_change - record that the glock is now in a different state
>+ * @gl: the glock
>+ * @new_state the new state
>+ *
>+ */
>+
>+static void state_change(struct gfs2_glock *gl, unsigned int new_state)
>+{
>+	int held1, held2;
>+
>+	held1 = (gl->gl_state != LM_ST_UNLOCKED);
>+	held2 = (new_state != LM_ST_UNLOCKED);
>+
>+	if (held1 != held2) {
>+		if (held2)
>+			gfs2_glock_hold(gl);
>+		else
>+			gfs2_glock_put(gl);
>+	}
>+
>+	gl->gl_state = new_state;
>+	gl->gl_tchange = jiffies;
>+}
>+
>+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);
>+}
>+
>+/**
>+ * finish_xmote - The DLM has replied to one of our lock requests
>+ * @gl: The glock
>+ * @ret: The status from the DLM
>+ *
>+ */
>+
>+static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
>+{
>+	const struct gfs2_glock_operations *glops = gl->gl_ops;
>+	struct gfs2_holder *gh;
>+	unsigned state = ret & LM_OUT_ST_MASK;
>+
>+	spin_lock(&gl->gl_spin);
>+	state_change(gl, state);
>+	gh = find_first_waiter(gl);
>+
>+	/* Demote to UN request arrived during demote to SH or DF */
>+	if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
>+	    state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
>+		gl->gl_target = LM_ST_UNLOCKED;
>+
>+	/* Check for state != intended state */
>+	if (unlikely(state != gl->gl_target)) {
>+		if (gh) {
>+			/* move to back of queue and try next entry */
>+			if (ret & LM_OUT_CANCELED) {
>+				if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
>+					list_move_tail(&gh->gh_list, &gl->gl_holders);
>+				gh = find_first_waiter(gl);
>+				gl->gl_target = gh->gh_state;
>+				goto retry;
>+			}
>+			/* Some error or failed "try lock" - report it */
>+			if ((ret & LM_OUT_ERROR) ||
>+			    (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
>+				gl->gl_target = gl->gl_state;
>+				do_error(gl, ret);
>+				goto out;
>+			}
>+		}
>+		switch(state) {
>+		/* Unlocked due to conversion deadlock, try again */
>+		case LM_ST_UNLOCKED:
>+retry:
>+			do_xmote(gl, gh, gl->gl_target);
>+			break;
>+		/* Conversion fails, unlock and try again */
>+		case LM_ST_SHARED:
>+		case LM_ST_DEFERRED:
>+			do_xmote(gl, gh, LM_ST_UNLOCKED);
>+			break;
>+		default: /* Everything else */
>+			printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
>+			BUG();
>+		}
>+		spin_unlock(&gl->gl_spin);
>+		gfs2_glock_put(gl);
>+		return;
>+	}
>+
>+	/* Fast path - we got what we asked for */
>+	if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
>+		gfs2_demote_wake(gl);
>+	if (state != LM_ST_UNLOCKED) {
>+		if (glops->go_xmote_bh) {
>+			spin_unlock(&gl->gl_spin);
>+			glops->go_xmote_bh(gl, gh);
>+			spin_lock(&gl->gl_spin);
>+		}
>+		do_promote(gl);
>+	}
>+out:
>+	clear_bit(GLF_LOCK, &gl->gl_flags);
>+	spin_unlock(&gl->gl_spin);
>+	gfs2_glock_put(gl);
>+}
>+
>+static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
>+				 unsigned int cur_state, unsigned int req_state,
>+				 unsigned int flags)
>+{
>+	int ret = LM_OUT_ERROR;
>+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
>+		ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
>+							 req_state, flags);
>+	return ret;
>+}
>+
>+/**
>+ * do_xmote - Calls the DLM to change the state of a lock
>+ * @gl: The lock state
>+ * @gh: The holder (only for promotes)
>+ * @target: The target lock state
>+ *
>+ */
>+
>+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
>+{
>+	const struct gfs2_glock_operations *glops = gl->gl_ops;
>+	struct gfs2_sbd *sdp = gl->gl_sbd;
>+	unsigned int lck_flags = gh ? gh->gh_flags : 0;
>+	int ret;
>+
>+	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
>+		      LM_FLAG_PRIORITY);
>+	BUG_ON(gl->gl_state == target);
>+	BUG_ON(gl->gl_state == gl->gl_target);
>+	spin_unlock(&gl->gl_spin);
>+	if (glops->go_xmote_th)
>+		glops->go_xmote_th(gl);
>+	if ((target == LM_ST_UNLOCKED  ||
>+	     target == LM_ST_DEFERRED) && glops->go_inval)
>+		glops->go_inval(gl, DIO_METADATA);
>+	gfs2_glock_hold(gl);
>+	if (target != LM_ST_UNLOCKED && (gl->gl_state == LM_ST_SHARED ||
>+	    gl->gl_state == LM_ST_DEFERRED) &&
>+	    !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
>+		lck_flags |= LM_FLAG_TRY_1CB;
>+	ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, target, lck_flags);
>+
>+	if (!(ret & LM_OUT_ASYNC))
>+		finish_xmote(gl, ret);
>+	else
>+		gfs2_assert_warn(sdp, ret == LM_OUT_ASYNC);
>+	spin_lock(&gl->gl_spin);
>+}
>+
>+/**
>+ * find_first_holder - find the first "holder" gh
>+ * @gl: the glock
>+ */
>+
>+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
>+{
>+	struct gfs2_holder *gh;
>+
>+	if (!list_empty(&gl->gl_holders)) {
>+		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
>+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
>+			return gh;
>+	}
>+	return NULL;
>+}
>+
>+/**
>+ * run_queue - do all outstanding tasks related to a glock
>+ * @gl: The glock in question
>+ * @nonblock: True if we must not block in run_queue
>+ *
>+ */
>+
>+static void run_queue(struct gfs2_glock *gl, const int nonblock)
>+{
>+	struct gfs2_holder *gh;
>+
>+	if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
>+		if (gl->gl_demote_state == gl->gl_state) {
>+			gfs2_demote_wake(gl);
>+			goto promote;
>+		}
>+		do_error(gl, 0); /* Fail queued try locks */
>+		if (nonblock) {
>+			gfs2_glock_hold(gl);
>+			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
>+				gfs2_glock_put(gl);
>+			return;
>+		}
>+		gh = find_first_holder(gl);
>+		if (gh || test_and_set_bit(GLF_LOCK, &gl->gl_flags))
>+			return;
>+		BUG_ON(test_and_set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));
>+		gl->gl_target = gl->gl_demote_state;
>+		do_xmote(gl, NULL, gl->gl_demote_state);
>+	}
>+promote:
>+	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
>+		return;
>+	if (do_promote(gl) == 0) {
>+		clear_bit(GLF_LOCK, &gl->gl_flags);
>+		return;
>+	}
>+	gh = find_first_waiter(gl);
>+	gl->gl_target = gh->gh_state;
>+	do_xmote(gl, gh, gh->gh_state);
>+}
>+
> static void glock_work_func(struct work_struct *work)
> {
> 	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
>@@ -288,7 +584,7 @@ static void glock_work_func(struct work_struct *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);
>+	run_queue(gl, 0);
> 	spin_unlock(&gl->gl_spin);
> 	gfs2_glock_put(gl);
> }
>@@ -342,12 +638,10 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
> 	gl->gl_name = name;
> 	atomic_set(&gl->gl_ref, 1);
> 	gl->gl_state = LM_ST_UNLOCKED;
>+	gl->gl_target = LM_ST_UNLOCKED;
> 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
> 	gl->gl_hash = hash;
>-	gl->gl_owner_pid = NULL;
>-	gl->gl_ip = 0;
> 	gl->gl_ops = glops;
>-	gl->gl_req_gh = NULL;
> 	gl->gl_stamp = jiffies;
> 	gl->gl_tchange = jiffies;
> 	gl->gl_object = NULL;
>@@ -447,13 +741,6 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
> 	gh->gh_ip = 0;
> }
> 
>-static void gfs2_holder_wake(struct gfs2_holder *gh)
>-{
>-	clear_bit(HIF_WAIT, &gh->gh_iflags);
>-	smp_mb__after_clear_bit();
>-	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
>-}
>-
> static int just_schedule(void *word)
> {
>         schedule();
>@@ -466,14 +753,6 @@ static void wait_on_holder(struct gfs2_holder *gh)
> 	wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
> }
> 
>-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 wait_on_demote(struct gfs2_glock *gl)
> {
> 	might_sleep();
>@@ -481,217 +760,6 @@ static void wait_on_demote(struct gfs2_glock *gl)
> }
> 
> /**
>- * rq_mutex - process a mutex request in the queue
>- * @gh: the glock holder
>- *
>- * Returns: 1 if the queue is blocked
>- */
>-
>-static int rq_mutex(struct gfs2_holder *gh)
>-{
>-	struct gfs2_glock *gl = gh->gh_gl;
>-
>-	list_del_init(&gh->gh_list);
>-	/*  gh->gh_error never examined.  */
>-	set_bit(GLF_LOCK, &gl->gl_flags);
>-	clear_bit(HIF_WAIT, &gh->gh_iflags);
>-	smp_mb();
>-	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
>-
>-	return 1;
>-}
>-
>-/**
>- * rq_promote - process a promote request in the queue
>- * @gh: the glock holder
>- *
>- * Acquire a new inter-node lock, or change a lock state to more restrictive.
>- *
>- * Returns: 1 if the queue is blocked
>- */
>-
>-static int rq_promote(struct gfs2_holder *gh)
>-{
>-	struct gfs2_glock *gl = gh->gh_gl;
>-
>-	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);
>-			gfs2_glock_xmote_th(gh->gh_gl, gh);
>-			spin_lock(&gl->gl_spin);
>-		}
>-		return 1;
>-	}
>-
>-	if (list_empty(&gl->gl_holders)) {
>-		set_bit(HIF_FIRST, &gh->gh_iflags);
>-		set_bit(GLF_LOCK, &gl->gl_flags);
>-	} else {
>-		struct gfs2_holder *next_gh;
>-		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_state == LM_ST_EXCLUSIVE)
>-			 return 1;
>-	}
>-
>-	list_move_tail(&gh->gh_list, &gl->gl_holders);
>-	gh->gh_error = 0;
>-	set_bit(HIF_HOLDER, &gh->gh_iflags);
>-
>-	gfs2_holder_wake(gh);
>-
>-	return 0;
>-}
>-
>-/**
>- * rq_demote - process a demote request in the queue
>- * @gh: the glock holder
>- *
>- * Returns: 1 if the queue is blocked
>- */
>-
>-static int rq_demote(struct gfs2_glock *gl)
>-{
>-	if (!list_empty(&gl->gl_holders))
>-		return 1;
>-
>-	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);
>-		gfs2_glock_drop_th(gl);
>-	} else {
>-		spin_unlock(&gl->gl_spin);
>-		gfs2_glock_xmote_th(gl, NULL);
>-	}
>-
>-	spin_lock(&gl->gl_spin);
>-	clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
>-
>-	return 0;
>-}
>-
>-/**
>- * run_queue - process holder structures on a glock
>- * @gl: the glock
>- *
>- */
>-static void run_queue(struct gfs2_glock *gl)
>-{
>-	struct gfs2_holder *gh;
>-	int blocked = 1;
>-
>-	for (;;) {
>-		if (test_bit(GLF_LOCK, &gl->gl_flags))
>-			break;
>-
>-		if (!list_empty(&gl->gl_waiters1)) {
>-			gh = list_entry(gl->gl_waiters1.next,
>-					struct gfs2_holder, gh_list);
>-			blocked = rq_mutex(gh);
>-		} else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
>-			blocked = rq_demote(gl);
>-			if (test_bit(GLF_WAITERS2, &gl->gl_flags) &&
>-				     !blocked) {
>-				set_bit(GLF_DEMOTE, &gl->gl_flags);
>-				gl->gl_demote_state = LM_ST_UNLOCKED;
>-			}
>-			clear_bit(GLF_WAITERS2, &gl->gl_flags);
>-		} else if (!list_empty(&gl->gl_waiters3)) {
>-			gh = list_entry(gl->gl_waiters3.next,
>-					struct gfs2_holder, gh_list);
>-			blocked = rq_promote(gh);
>-		} else
>-			break;
>-
>-		if (blocked)
>-			break;
>-	}
>-}
>-
>-/**
>- * gfs2_glmutex_lock - acquire a local lock on a glock
>- * @gl: the glock
>- *
>- * Gives caller exclusive access to manipulate a glock structure.
>- */
>-
>-static void gfs2_glmutex_lock(struct gfs2_glock *gl)
>-{
>-	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_pid = get_pid(task_pid(current));
>-		gl->gl_ip = (unsigned long)__builtin_return_address(0);
>-		spin_unlock(&gl->gl_spin);
>-	}
>-}
>-
>-/**
>- * gfs2_glmutex_trylock - try to acquire a local lock on a glock
>- * @gl: the glock
>- *
>- * Returns: 1 if the glock is acquired
>- */
>-
>-static int gfs2_glmutex_trylock(struct gfs2_glock *gl)
>-{
>-	int acquired = 1;
>-
>-	spin_lock(&gl->gl_spin);
>-	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
>-		acquired = 0;
>-	} else {
>-		gl->gl_owner_pid = get_pid(task_pid(current));
>-		gl->gl_ip = (unsigned long)__builtin_return_address(0);
>-	}
>-	spin_unlock(&gl->gl_spin);
>-
>-	return acquired;
>-}
>-
>-/**
>- * gfs2_glmutex_unlock - release a local lock on a glock
>- * @gl: the glock
>- *
>- */
>-
>-static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
>-{
>-	struct pid *pid;
>-
>-	spin_lock(&gl->gl_spin);
>-	clear_bit(GLF_LOCK, &gl->gl_flags);
>-	pid = gl->gl_owner_pid;
>-	gl->gl_owner_pid = NULL;
>-	gl->gl_ip = 0;
>-	run_queue(gl);
>-	spin_unlock(&gl->gl_spin);
>-
>-	put_pid(pid);
>-}
>-
>-/**
>  * handle_callback - process a demote request
>  * @gl: the glock
>  * @state: the state the caller wants us to change to
>@@ -705,388 +773,39 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
> {
> 	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
> 
>-	spin_lock(&gl->gl_spin);
> 	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) {
>+		    gl->gl_object)
> 			gfs2_glock_schedule_for_reclaim(gl);
>-			spin_unlock(&gl->gl_spin);
>-			return;
>-		}
> 	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
> 			gl->gl_demote_state != state) {
>-		if (test_bit(GLF_DEMOTE_IN_PROGRESS,  &gl->gl_flags)) 
>-			set_bit(GLF_WAITERS2, &gl->gl_flags);
>-		else 
>-			gl->gl_demote_state = LM_ST_UNLOCKED;
>-	}
>-	spin_unlock(&gl->gl_spin);
>-}
>-
>-/**
>- * state_change - record that the glock is now in a different state
>- * @gl: the glock
>- * @new_state the new state
>- *
>- */
>-
>-static void state_change(struct gfs2_glock *gl, unsigned int new_state)
>-{
>-	int held1, held2;
>-
>-	held1 = (gl->gl_state != LM_ST_UNLOCKED);
>-	held2 = (new_state != LM_ST_UNLOCKED);
>-
>-	if (held1 != held2) {
>-		if (held2)
>-			gfs2_glock_hold(gl);
>-		else
>-			gfs2_glock_put(gl);
>-	}
>-
>-	gl->gl_state = new_state;
>-	gl->gl_tchange = jiffies;
>-}
>-
>-/**
>- * drop_bh - Called after a lock module unlock completes
>- * @gl: the glock
>- * @ret: the return status
>- *
>- * Doesn't wake up the process waiting on the struct gfs2_holder (if any)
>- * Doesn't drop the reference on the glock the top half took out
>- *
>- */
>-
>-static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
>-{
>-	struct gfs2_sbd *sdp = gl->gl_sbd;
>-	struct gfs2_holder *gh = gl->gl_req_gh;
>-
>-	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
>-	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
>-	gfs2_assert_warn(sdp, !ret);
>-
>-	state_change(gl, LM_ST_UNLOCKED);
>-
>-	if (test_and_clear_bit(GLF_CONV_DEADLK, &gl->gl_flags)) {
>-		spin_lock(&gl->gl_spin);
>-		gh->gh_error = 0;
>-		spin_unlock(&gl->gl_spin);
>-		gfs2_glock_xmote_th(gl, gl->gl_req_gh);
>-		gfs2_glock_put(gl);
>-		return;
>-	}
>-
>-	spin_lock(&gl->gl_spin);
>-	gfs2_demote_wake(gl);
>-	clear_bit(GLF_LOCK, &gl->gl_flags);
>-	spin_unlock(&gl->gl_spin);
>-	gfs2_glock_put(gl);
>-}
>-
>-/**
>- * xmote_bh - Called after the lock module is done acquiring a lock
>- * @gl: The glock in question
>- * @ret: the int returned from the lock module
>- *
>- */
>-
>-static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
>-{
>-	struct gfs2_sbd *sdp = gl->gl_sbd;
>-	const struct gfs2_glock_operations *glops = gl->gl_ops;
>-	struct gfs2_holder *gh = gl->gl_req_gh;
>-	int op_done = 1;
>-
>-	if (!gh && (ret & LM_OUT_ST_MASK) == LM_ST_UNLOCKED) {
>-		drop_bh(gl, ret);
>-		return;
>-	}
>-
>-	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
>-	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);
>-
>-	/*  Deal with each possible exit condition  */
>-
>-	if (!gh) {
>-		gl->gl_stamp = jiffies;
>-		if (ret & LM_OUT_CANCELED) {
>-			op_done = 0;
>-		} else {
>-			spin_lock(&gl->gl_spin);
>-			if (gl->gl_state != gl->gl_demote_state) {
>-				spin_unlock(&gl->gl_spin);
>-				gfs2_glock_drop_th(gl);
>-				gfs2_glock_put(gl);
>-				return;
>-			}
>-			gfs2_demote_wake(gl);
>-			spin_unlock(&gl->gl_spin);
>-		}
>-	} else {
>-		spin_lock(&gl->gl_spin);
>-		if (ret & LM_OUT_CONV_DEADLK) {
>-			gh->gh_error = 0;
>-			set_bit(GLF_CONV_DEADLK, &gl->gl_flags);
>-			spin_unlock(&gl->gl_spin);
>-			gfs2_glock_drop_th(gl);
>-			gfs2_glock_put(gl);
>-			return;
>-		}
>-		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;
>-		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;
>-		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);
>+		gl->gl_demote_state = LM_ST_UNLOCKED;
> 	}
>-
>-	if (glops->go_xmote_bh)
>-		glops->go_xmote_bh(gl);
>-
>-	if (op_done) {
>-		spin_lock(&gl->gl_spin);
>-		gl->gl_req_gh = NULL;
>-		clear_bit(GLF_LOCK, &gl->gl_flags);
>-		spin_unlock(&gl->gl_spin);
>-	}
>-
>-	gfs2_glock_put(gl);
>-
>-	if (gh)
>-		gfs2_holder_wake(gh);
>-}
>-
>-static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
>-				 unsigned int cur_state, unsigned int req_state,
>-				 unsigned int flags)
>-{
>-	int ret = 0;
>-	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
>-		ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
>-							 req_state, flags);
>-	return ret;
>-}
>-
>-/**
>- * gfs2_glock_xmote_th - Call into the lock module to acquire or change a glock
>- * @gl: The glock in question
>- * @state: the requested state
>- * @flags: modifier flags to the lock call
>- *
>- */
>-
>-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);
>-	if (state == LM_ST_DEFERRED && glops->go_inval)
>-		glops->go_inval(gl, DIO_METADATA);
>-
>-	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
>-	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);
>-
>-	gfs2_glock_hold(gl);
>-
>-	lck_ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, state, lck_flags);
>-
>-	if (gfs2_assert_withdraw(sdp, !(lck_ret & LM_OUT_ERROR)))
>-		return;
>-
>-	if (lck_ret & LM_OUT_ASYNC)
>-		gfs2_assert_warn(sdp, lck_ret == LM_OUT_ASYNC);
>-	else
>-		xmote_bh(gl, lck_ret);
>-}
>-
>-static unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
>-				   unsigned int cur_state)
>-{
>-	int ret = 0;
>-	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
>-		ret =  sdp->sd_lockstruct.ls_ops->lm_unlock(lock, cur_state);
>-	return ret;
> }
> 
> /**
>- * gfs2_glock_drop_th - call into the lock module to unlock a lock
>- * @gl: the glock
>- *
>- */
>-
>-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);
>-	if (glops->go_inval)
>-		glops->go_inval(gl, DIO_METADATA);
>-
>-	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
>-	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
>-	gfs2_assert_warn(sdp, gl->gl_state != LM_ST_UNLOCKED);
>-
>-	gfs2_glock_hold(gl);
>-
>-	ret = gfs2_lm_unlock(sdp, gl->gl_lock, gl->gl_state);
>-
>-	if (gfs2_assert_withdraw(sdp, !(ret & LM_OUT_ERROR)))
>-		return;
>-
>-	if (!ret)
>-		drop_bh(gl, ret);
>-	else
>-		gfs2_assert_warn(sdp, ret == LM_OUT_ASYNC);
>-}
>-
>-/**
>- * do_cancels - cancel requests for locks stuck waiting on an expire flag
>- * @gh: the LM_FLAG_PRIORITY holder waiting to acquire the lock
>- *
>- * Don't cancel GL_NOCANCEL requests.
>- */
>-
>-static void do_cancels(struct gfs2_holder *gh)
>-{
>-	struct gfs2_glock *gl = gh->gh_gl;
>-	struct gfs2_sbd *sdp = gl->gl_sbd;
>-
>-	spin_lock(&gl->gl_spin);
>-
>-	while (gl->gl_req_gh != gh &&
>-	       !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
>-	       !list_empty(&gh->gh_list)) {
>-		if (!(gl->gl_req_gh && (gl->gl_req_gh->gh_flags & GL_NOCANCEL))) {
>-			spin_unlock(&gl->gl_spin);
>-			if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
>-				sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
>-			msleep(100);
>-			spin_lock(&gl->gl_spin);
>-		} else {
>-			spin_unlock(&gl->gl_spin);
>-			msleep(100);
>-			spin_lock(&gl->gl_spin);
>-		}
>-	}
>-
>-	spin_unlock(&gl->gl_spin);
>-}
>-
>-/**
>- * glock_wait_internal - wait on a glock acquisition
>+ * gfs2_glock_wait - wait on a glock acquisition
>  * @gh: the glock holder
>  *
>  * Returns: 0 on success
>  */
> 
>-static int glock_wait_internal(struct gfs2_holder *gh)
>+int gfs2_glock_wait(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 (test_bit(HIF_ABORTED, &gh->gh_iflags))
>-		return -EIO;
>-
>-	if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
>-		spin_lock(&gl->gl_spin);
>-		if (gl->gl_req_gh != gh &&
>-		    !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
>-		    !list_empty(&gh->gh_list)) {
>-			list_del_init(&gh->gh_list);
>-			gh->gh_error = GLR_TRYFAILED;
>-			run_queue(gl);
>-			spin_unlock(&gl->gl_spin);
>-			return gh->gh_error;
>-		}
>-		spin_unlock(&gl->gl_spin);
>-	}
>-
>-	if (gh->gh_flags & LM_FLAG_PRIORITY)
>-		do_cancels(gh);
> 
> 	wait_on_holder(gh);
>-	if (gh->gh_error)
>-		return gh->gh_error;
>-
>-	gfs2_assert_withdraw(sdp, test_bit(HIF_HOLDER, &gh->gh_iflags));
>-	gfs2_assert_withdraw(sdp, relaxed_state_ok(gl->gl_state, gh->gh_state,
>-						   gh->gh_flags));
>-
>-	if (test_bit(HIF_FIRST, &gh->gh_iflags)) {
>-		gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
>-
>-		if (glops->go_lock) {
>-			gh->gh_error = glops->go_lock(gh);
>-			if (gh->gh_error) {
>-				spin_lock(&gl->gl_spin);
>-				list_del_init(&gh->gh_list);
>-				spin_unlock(&gl->gl_spin);
>-			}
>-		}
>-
>-		spin_lock(&gl->gl_spin);
>-		gl->gl_req_gh = NULL;
>-		clear_bit(GLF_LOCK, &gl->gl_flags);
>-		run_queue(gl);
>-		spin_unlock(&gl->gl_spin);
>-	}
>+	if (gh->gh_error == 0)
>+		gfs2_assert_withdraw(sdp, test_bit(HIF_HOLDER, &gh->gh_iflags));
> 
> 	return gh->gh_error;
> }
> 
>-static inline struct gfs2_holder *
>-find_holder_by_owner(struct list_head *head, struct pid *pid)
>-{
>-	struct gfs2_holder *gh;
>-
>-	list_for_each_entry(gh, head, gh_list) {
>-		if (gh->gh_owner_pid == pid)
>-			return gh;
>-	}
>-
>-	return NULL;
>-}
>-
>-static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
>+void gfs2_print_dbg(struct gfs2_glock_iter *gi, const char *fmt, ...)
> {
> 	va_list args;
> 
>@@ -1104,50 +823,54 @@ static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
>  * add_to_queue - Add a holder to the wait queue (but look for recursion)
>  * @gh: the holder structure to add
>  *
>+ * Eventually we should move the recursive locking trap to a
>+ * debugging option or something like that. This is the fast
>+ * path and needs to have the minimum number of distractions.
>+ * 
>  */
> 
>-static void add_to_queue(struct gfs2_holder *gh)
>+static inline void add_to_queue(struct gfs2_holder *gh)
> {
> 	struct gfs2_glock *gl = gh->gh_gl;
>-	struct gfs2_holder *existing;
>+	struct gfs2_sbd *sdp = gl->gl_sbd;
>+	struct list_head *insert_pt = NULL;
>+	struct gfs2_holder *gh2;
> 
> 	BUG_ON(gh->gh_owner_pid == NULL);
> 	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
> 		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",
>-					pid_nr(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",
>-					pid_nr(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();
>-		}
>+	list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
>+		if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
>+		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
>+			goto trap_recursive;
>+		if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) &&
>+			     !insert_pt && !test_bit(HIF_HOLDER, &gh2->gh_iflags)))
>+			insert_pt = &gh2->gh_list;
>+	}
>+	if (likely(insert_pt == NULL)) {
>+		list_add_tail(&gh->gh_list, &gl->gl_holders);
>+		return;
>+	}
>+	list_add_tail(&gh->gh_list, insert_pt);
>+	if (test_bit(GLF_LOCK, &gl->gl_flags)) {
>+		spin_unlock(&gl->gl_spin);
>+		sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
>+		spin_lock(&gl->gl_spin);
> 	}
>+	return;
> 
>-	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);
>+trap_recursive:
>+	print_symbol(KERN_WARNING "original: %s\n", gh2->gh_ip);
>+	printk(KERN_INFO "pid: %d\n", pid_nr(gh2->gh_owner_pid));
>+	printk(KERN_INFO "lock type: %d req lock state : %d\n",
>+	       gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
>+	print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
>+	printk(KERN_INFO "pid: %d\n", pid_nr(gh->gh_owner_pid));
>+	printk(KERN_INFO "lock type: %d req lock state : %d\n",
>+	       gh->gh_gl->gl_name.ln_type, gh->gh_state);
>+	printk(KERN_INFO "current lock state: %u\n", gl->gl_state);
>+	BUG();
> }
> 
> /**
>@@ -1165,24 +888,16 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
> 	struct gfs2_sbd *sdp = gl->gl_sbd;
> 	int error = 0;
> 
>-restart:
>-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
>-		set_bit(HIF_ABORTED, &gh->gh_iflags);
>+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> 		return -EIO;
>-	}
> 
> 	spin_lock(&gl->gl_spin);
> 	add_to_queue(gh);
>-	run_queue(gl);
>+	run_queue(gl, 1);
> 	spin_unlock(&gl->gl_spin);
> 
>-	if (!(gh->gh_flags & GL_ASYNC)) {
>-		error = glock_wait_internal(gh);
>-		if (error == GLR_CANCELED) {
>-			msleep(100);
>-			goto restart;
>-		}
>-	}
>+	if (!(gh->gh_flags & GL_ASYNC))
>+		error = gfs2_glock_wait(gh);
> 
> 	return error;
> }
>@@ -1196,48 +911,7 @@ restart:
> 
> int gfs2_glock_poll(struct gfs2_holder *gh)
> {
>-	struct gfs2_glock *gl = gh->gh_gl;
>-	int ready = 0;
>-
>-	spin_lock(&gl->gl_spin);
>-
>-	if (test_bit(HIF_HOLDER, &gh->gh_iflags))
>-		ready = 1;
>-	else if (list_empty(&gh->gh_list)) {
>-		if (gh->gh_error == GLR_CANCELED) {
>-			spin_unlock(&gl->gl_spin);
>-			msleep(100);
>-			if (gfs2_glock_nq(gh))
>-				return 1;
>-			return 0;
>-		} else
>-			ready = 1;
>-	}
>-
>-	spin_unlock(&gl->gl_spin);
>-
>-	return ready;
>-}
>-
>-/**
>- * gfs2_glock_wait - wait for a lock acquisition that ended in a GLR_ASYNC
>- * @gh: the holder structure
>- *
>- * Returns: 0, GLR_TRYFAILED, or errno on failure
>- */
>-
>-int gfs2_glock_wait(struct gfs2_holder *gh)
>-{
>-	int error;
>-
>-	error = glock_wait_internal(gh);
>-	if (error == GLR_CANCELED) {
>-		msleep(100);
>-		gh->gh_flags &= ~GL_ASYNC;
>-		error = gfs2_glock_nq(gh);
>-	}
>-
>-	return error;
>+	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
> }
> 
> /**
>@@ -1251,26 +925,30 @@ 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;
>+	int fast_path = 0;
> 
>+	spin_lock(&gl->gl_spin);
> 	if (gh->gh_flags & GL_NOCACHE)
> 		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
> 
>-	gfs2_glmutex_lock(gl);
>-
>-	spin_lock(&gl->gl_spin);
> 	list_del_init(&gh->gh_list);
>-
>-	if (list_empty(&gl->gl_holders)) {
>+	if (find_first_holder(gl) == NULL) {
> 		if (glops->go_unlock) {
>+			BUG_ON(test_and_set_bit(GLF_LOCK, &gl->gl_flags));
> 			spin_unlock(&gl->gl_spin);
> 			glops->go_unlock(gh);
> 			spin_lock(&gl->gl_spin);
>+			clear_bit(GLF_LOCK, &gl->gl_flags);
> 		}
> 		gl->gl_stamp = jiffies;
>+		if (list_empty(&gl->gl_holders) &&
>+		    !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
>+		    !test_bit(GLF_DEMOTE, &gl->gl_flags))
>+			fast_path = 1;
> 	}
>-
>-	clear_bit(GLF_LOCK, &gl->gl_flags);
> 	spin_unlock(&gl->gl_spin);
>+	if (likely(fast_path))
>+		return;
> 
> 	gfs2_glock_hold(gl);
> 	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
>@@ -1469,20 +1147,14 @@ int gfs2_lvb_hold(struct gfs2_glock *gl)
> {
> 	int error;
> 
>-	gfs2_glmutex_lock(gl);
>-
> 	if (!atomic_read(&gl->gl_lvb_count)) {
> 		error = gfs2_lm_hold_lvb(gl->gl_sbd, gl->gl_lock, &gl->gl_lvb);
>-		if (error) {
>-			gfs2_glmutex_unlock(gl);
>+		if (error) 
> 			return error;
>-		}
> 		gfs2_glock_hold(gl);
> 	}
> 	atomic_inc(&gl->gl_lvb_count);
> 
>-	gfs2_glmutex_unlock(gl);
>-
> 	return 0;
> }
> 
>@@ -1497,8 +1169,6 @@ void gfs2_lvb_unhold(struct gfs2_glock *gl)
> 	struct gfs2_sbd *sdp = gl->gl_sbd;
> 
> 	gfs2_glock_hold(gl);
>-	gfs2_glmutex_lock(gl);
>-
> 	gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count) > 0);
> 	if (atomic_dec_and_test(&gl->gl_lvb_count)) {
> 		if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
>@@ -1506,8 +1176,6 @@ void gfs2_lvb_unhold(struct gfs2_glock *gl)
> 		gl->gl_lvb = NULL;
> 		gfs2_glock_put(gl);
> 	}
>-
>-	gfs2_glmutex_unlock(gl);
> 	gfs2_glock_put(gl);
> }
> 
>@@ -1527,7 +1195,9 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
> 	if (time_before(now, holdtime))
> 		delay = holdtime - now;
> 
>+	spin_lock(&gl->gl_spin);
> 	handle_callback(gl, state, 1, delay);
>+	spin_unlock(&gl->gl_spin);
> 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
> 		gfs2_glock_put(gl);
> }
>@@ -1568,7 +1238,7 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
> 		gl = gfs2_glock_find(sdp, &async->lc_name);
> 		if (gfs2_assert_warn(sdp, gl))
> 			return;
>-		xmote_bh(gl, async->lc_ret);
>+		finish_xmote(gl, async->lc_ret);
> 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
> 			gfs2_glock_put(gl);
> 		up_read(&gfs2_umount_flush_sem);
>@@ -1646,6 +1316,7 @@ void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
> void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
> {
> 	struct gfs2_glock *gl;
>+	int done_callback = 0;
> 
> 	spin_lock(&sdp->sd_reclaim_lock);
> 	if (list_empty(&sdp->sd_reclaim_list)) {
>@@ -1660,14 +1331,16 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
> 	atomic_dec(&sdp->sd_reclaim_count);
> 	atomic_inc(&sdp->sd_reclaimed);
> 
>-	if (gfs2_glmutex_trylock(gl)) {
>-		if (list_empty(&gl->gl_holders) &&
>-		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
>-			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
>-		gfs2_glmutex_unlock(gl);
>+	spin_lock(&gl->gl_spin);
>+	if (find_first_holder(gl) == NULL &&
>+	    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl)) {
>+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
>+		done_callback = 1;
> 	}
>-
>-	gfs2_glock_put(gl);
>+	spin_unlock(&gl->gl_spin);
>+	if (!done_callback ||
>+	    queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
>+		gfs2_glock_put(gl);
> }
> 
> /**
>@@ -1724,18 +1397,14 @@ static void scan_glock(struct gfs2_glock *gl)
> {
> 	if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object)
> 		return;
>+	if (test_bit(GLF_LOCK, &gl->gl_flags))
>+		return;
> 
>-	if (gfs2_glmutex_trylock(gl)) {
>-		if (list_empty(&gl->gl_holders) &&
>-		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
>-			goto out_schedule;
>-		gfs2_glmutex_unlock(gl);
>-	}
>-	return;
>-
>-out_schedule:
>-	gfs2_glmutex_unlock(gl);
>-	gfs2_glock_schedule_for_reclaim(gl);
>+	spin_lock(&gl->gl_spin);
>+	if (find_first_holder(gl) == NULL &&
>+	    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
>+		gfs2_glock_schedule_for_reclaim(gl);
>+	spin_unlock(&gl->gl_spin);
> }
> 
> /**
>@@ -1760,12 +1429,13 @@ static void clear_glock(struct gfs2_glock *gl)
> 		spin_unlock(&sdp->sd_reclaim_lock);
> 	}
> 
>-	if (gfs2_glmutex_trylock(gl)) {
>-		if (list_empty(&gl->gl_holders) &&
>-		    gl->gl_state != LM_ST_UNLOCKED)
>-			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
>-		gfs2_glmutex_unlock(gl);
>-	}
>+	spin_lock(&gl->gl_spin);
>+	if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
>+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
>+	spin_unlock(&gl->gl_spin);
>+	gfs2_glock_hold(gl);
>+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
>+		gfs2_glock_put(gl);
> }
> 
> /**
>@@ -1810,175 +1480,147 @@ 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)
>+static const char *state2str(unsigned state)
> {
>-	char buffer[KSYM_SYMBOL_LEN];
>-
>-	sprint_symbol(buffer, address);
>-	print_dbg(gi, fmt, buffer);
>+	switch(state) {
>+	case LM_ST_UNLOCKED:
>+		return "UN";
>+	case LM_ST_SHARED:
>+		return "SH";
>+	case LM_ST_DEFERRED:
>+		return "DF";
>+	case LM_ST_EXCLUSIVE:
>+		return "EX";
>+	}
>+	return "??";
>+}
>+
>+static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
>+{
>+	char *p = buf;
>+	if (flags & LM_FLAG_TRY)
>+		*p++ = 't';
>+	if (flags & LM_FLAG_TRY_1CB)
>+		*p++ = 'T';
>+	if (flags & LM_FLAG_NOEXP)
>+		*p++ = 'e';
>+	if (flags & LM_FLAG_ANY)
>+		*p++ = 'a';
>+	if (flags & LM_FLAG_PRIORITY)
>+		*p++ = 'p';
>+	if (flags & GL_ASYNC)
>+		*p++ = 'a';
>+	if (flags & GL_EXACT)
>+		*p++ = 'E';
>+	if (flags & GL_ATIME)
>+		*p++ = 'a';
>+	if (flags & GL_NOCACHE)
>+		*p++ = 'c';
>+	if (test_bit(HIF_HOLDER, &iflags))
>+		*p++ = 'H';
>+	if (test_bit(HIF_WAIT, &iflags))
>+		*p++ = 'W';
>+	if (test_bit(HIF_FIRST, &iflags))
>+		*p++ = 'F';
>+	*p = 0;
>+	return buf;
> }
> 
> /**
>  * dump_holder - print information about a glock holder
>- * @str: a string naming the type of holder
>  * @gh: the glock holder
>  *
>  * Returns: 0 on success, -ENOBUFS when we run out of space
>  */
> 
>-static int dump_holder(struct glock_iter *gi, char *str,
>-		       struct gfs2_holder *gh)
>+static int dump_holder(struct gfs2_glock_iter *gi, struct gfs2_holder *gh)
> {
>-	unsigned int x;
>-	struct task_struct *gh_owner;
>+	struct task_struct *gh_owner = NULL;
>+	char buffer[KSYM_SYMBOL_LEN];
>+	char flags_buf[32];
> 
>-	print_dbg(gi, "  %s\n", str);
>-	if (gh->gh_owner_pid) {
>-		print_dbg(gi, "    owner = %ld ",
>-				(long)pid_nr(gh->gh_owner_pid));
>+	sprint_symbol(buffer, gh->gh_ip);
>+	if (gh->gh_owner_pid)
> 		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_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))
>-			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))
>-			print_dbg(gi, " %u", x);
>-	print_dbg(gi, " \n");
>-        gfs2_print_symbol(gi, "    initialized at: %s\n", gh->gh_ip);
>-
>+	gfs2_print_dbg(gi, " H: s:%s f:%s e:%d p:%ld [%s] %s\n",
>+		  state2str(gh->gh_state),
>+		  hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
>+		  gh->gh_error, 
>+		  gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
>+		  gh_owner ? gh_owner->comm : "(ended)", buffer);
> 	return 0;
> }
> 
>-/**
>- * dump_inode - print information about an inode
>- * @ip: the inode
>- *
>- * Returns: 0 on success, -ENOBUFS when we run out of space
>- */
>-
>-static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
>+static const char *gflags2str(char *buf, unsigned long gflags)
> {
>-	unsigned int x;
>-
>-	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))
>-			print_dbg(gi, " %u", x);
>-	print_dbg(gi, " \n");
>-	return 0;
>+	char *p = buf;
>+	if (test_bit(GLF_LOCK, &gflags))
>+		*p++ = 'l';
>+	if (test_bit(GLF_STICKY, &gflags))
>+		*p++ = 's';
>+	if (test_bit(GLF_DEMOTE, &gflags))
>+		*p++ = 'D';
>+	if (test_bit(GLF_PENDING_DEMOTE, &gflags))
>+		*p++ = 'd';
>+	if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gflags))
>+		*p++ = 'p';
>+	if (test_bit(GLF_DIRTY, &gflags))
>+		*p++ = 'y';
>+	if (test_bit(GLF_LFLUSH, &gflags))
>+		*p++ = 'f';
>+	*p = 0;
>+	return buf;
> }
> 
> /**
>  * dump_glock - print information about a glock
>+ * @gi: The iteration state
>  * @gl: the glock
>- * @count: where we are in the buffer
>+ *
>+ * The file format is as follows:
>+ * One line per object, capital letters are used to indicate objects
>+ * G = glock, I = Inode, R = rgrp, H = holder. Glocks are not indented
>+ * other objects are indented by a single space and follow the glock to
>+ * which they are related. Fields are indicated by lower case letters
>+ * followed by a colon and the field value, except for strings which are in
>+ * [] so that its possible to see if they are composed of spaces for
>+ * example. The field's are n = number (id of the object), f = flags,
>+ * t = type, s = state, r = refcount, e = error, p = pid.
>  *
>  * Returns: 0 on success, -ENOBUFS when we run out of space
>  */
> 
>-static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
>+static int dump_glock(struct gfs2_glock_iter *gi, struct gfs2_glock *gl)
> {
>+	const struct gfs2_glock_operations *glops = gl->gl_ops;
>+	unsigned long long dtime;
> 	struct gfs2_holder *gh;
>-	unsigned int x;
>-	int error = -ENOBUFS;
>-	struct task_struct *gl_owner;
>+	char gflags_buf[32];
>+	int error = 0;
> 
> 	spin_lock(&gl->gl_spin);
>+	dtime = jiffies - gl->gl_demote_time;
>+	dtime *= 1000000/HZ; /* demote time in uSec */
>+	if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
>+		dtime = 0;
>+	gfs2_print_dbg(gi, "G:  s:%s n:%u/%llu f:%s t:%s d:%s/%llu l:%d a:%d r:%d\n",
>+		  state2str(gl->gl_state),
>+		  gl->gl_name.ln_type,
>+		  (unsigned long long)gl->gl_name.ln_number,
>+		  gflags2str(gflags_buf, gl->gl_flags),
>+		  state2str(gl->gl_target),
>+		  state2str(gl->gl_demote_state), dtime,
>+		  atomic_read(&gl->gl_lvb_count),
>+		  atomic_read(&gl->gl_ail_count),
>+		  atomic_read(&gl->gl_ref));
> 
>-	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))
>-			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 = pid_task(gl->gl_owner_pid, PIDTYPE_PID);
>-		if (gl_owner)
>-			print_dbg(gi, "  gl_owner = pid %d (%s)\n",
>-				  pid_nr(gl->gl_owner_pid), gl_owner->comm);
>-		else
>-			print_dbg(gi, "  gl_owner = %d (ended)\n",
>-				  pid_nr(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, "  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)
>-		print_dbg(gi, "  aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
>-			   gl->gl_aspace->i_mapping->nrpages);
>-	else
>-		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(gi, "Request", gl->gl_req_gh);
>-		if (error)
>-			goto out;
>-	}
> 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
>-		error = dump_holder(gi, "Holder", gh);
>+		error = dump_holder(gi, gh);
> 		if (error)
> 			goto out;
> 	}
>-	list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
>-		error = dump_holder(gi, "Waiter1", gh);
>-		if (error)
>-			goto out;
>-	}
>-	list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
>-		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(gi, gl->gl_object);
>-			if (error)
>-				goto out;
>-		} else {
>-			error = -ENOBUFS;
>-			print_dbg(gi, "  Inode: busy\n");
>-		}
>-	}
>-
>-	error = 0;
>-
>+	if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
>+		error = glops->go_dump(gi, gl);
> out:
> 	spin_unlock(&gl->gl_spin);
> 	return error;
>@@ -2086,7 +1728,7 @@ void gfs2_glock_exit(void)
> 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)
>+static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
> {
> 	struct gfs2_glock *gl;
> 
>@@ -2104,7 +1746,7 @@ restart:
> 		gfs2_glock_put(gl);
> 	if (gl && gi->gl == NULL)
> 		gi->hash++;
>-	while(gi->gl == NULL) {
>+	while (gi->gl == NULL) {
> 		if (gi->hash >= GFS2_GL_HASH_SIZE)
> 			return 1;
> 		read_lock(gl_lock_addr(gi->hash));
>@@ -2122,16 +1764,16 @@ restart:
> 	return 0;
> }
> 
>-static void gfs2_glock_iter_free(struct glock_iter *gi)
>+static void gfs2_glock_iter_free(struct gfs2_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)
>+static struct gfs2_glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
> {
>-	struct glock_iter *gi;
>+	struct gfs2_glock_iter *gi;
> 
> 	gi = kmalloc(sizeof (*gi), GFP_KERNEL);
> 	if (!gi)
>@@ -2153,14 +1795,14 @@ static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
> 
> static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
> {
>-	struct glock_iter *gi;
>+	struct gfs2_glock_iter *gi;
> 	loff_t n = *pos;
> 
> 	gi = gfs2_glock_iter_init(file->private);
> 	if (!gi)
> 		return NULL;
> 
>-	while(n--) {
>+	while (n--) {
> 		if (gfs2_glock_iter_next(gi)) {
> 			gfs2_glock_iter_free(gi);
> 			return NULL;
>@@ -2173,7 +1815,7 @@ static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
> static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
> 				 loff_t *pos)
> {
>-	struct glock_iter *gi = iter_ptr;
>+	struct gfs2_glock_iter *gi = iter_ptr;
> 
> 	(*pos)++;
> 
>@@ -2187,14 +1829,14 @@ static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
> 
> static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
> {
>-	struct glock_iter *gi = iter_ptr;
>+	struct gfs2_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;
>+	struct gfs2_glock_iter *gi = iter_ptr;
> 
> 	gi->seq = file;
> 	dump_glock(gi, gi->gl);
>diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
>index cdad3e6..d68a060 100644
>--- a/fs/gfs2/glock.h
>+++ b/fs/gfs2/glock.h
>@@ -26,11 +26,8 @@
> #define GL_SKIP			0x00000100
> #define GL_ATIME		0x00000200
> #define GL_NOCACHE		0x00000400
>-#define GL_FLOCK		0x00000800
>-#define GL_NOCANCEL		0x00001000
> 
> #define GLR_TRYFAILED		13
>-#define GLR_CANCELED		14
> 
> static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
> {
>@@ -41,6 +38,8 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
> 	spin_lock(&gl->gl_spin);
> 	pid = task_pid(current);
> 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
>+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
>+			break;
> 		if (gh->gh_owner_pid == pid)
> 			goto out;
> 	}
>@@ -70,7 +69,7 @@ static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
> {
> 	int ret;
> 	spin_lock(&gl->gl_spin);
>-	ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
>+	ret = test_bit(GLF_DEMOTE, &gl->gl_flags);
> 	spin_unlock(&gl->gl_spin);
> 	return ret;
> }
>@@ -98,6 +97,7 @@ int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
> int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
> void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
> void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
>+void gfs2_print_dbg(struct gfs2_glock_iter *gi, const char *fmt, ...);
> 
> /**
>  * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
>diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
>index d31bada..11c7e5e 100644
>--- a/fs/gfs2/glops.c
>+++ b/fs/gfs2/glops.c
>@@ -177,9 +177,8 @@ static void inode_go_sync(struct gfs2_glock *gl)
>  *
>  */
> 
>-static void inode_go_xmote_bh(struct gfs2_glock *gl)
>+static void inode_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
> {
>-	struct gfs2_holder *gh = gl->gl_req_gh;
> 	struct buffer_head *bh;
> 	int error;
> 
>@@ -267,6 +266,26 @@ static int inode_go_lock(struct gfs2_holder *gh)
> }
> 
> /**
>+ * inode_go_dump - print information about an inode
>+ * @gi: The iterator
>+ * @ip: the inode
>+ *
>+ * Returns: 0 on success, -ENOBUFS when we run out of space
>+ */
>+
>+static int inode_go_dump(struct gfs2_glock_iter *gi, struct gfs2_glock *gl)
>+{
>+	struct gfs2_inode *ip = gl->gl_object;
>+	if (ip == NULL)
>+		return 0;
>+	gfs2_print_dbg(gi, " I: n:%llu/%llu t:%u f:0x%08lx\n",
>+		  (unsigned long long)ip->i_no_formal_ino,
>+		  (unsigned long long)ip->i_no_addr,
>+		  IF2DT(ip->i_inode.i_mode), ip->i_flags);
>+	return 0;
>+}
>+
>+/**
>  * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
>  * @gl: the glock
>  *
>@@ -306,6 +325,22 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
> }
> 
> /**
>+ * rgrp_go_dump - print out an rgrp
>+ * @gi: The iterator
>+ * @gl: The glock in question
>+ *
>+ */
>+
>+static int rgrp_go_dump(struct gfs2_glock_iter *gi, struct gfs2_glock *gl)
>+{
>+	struct gfs2_rgrpd *rgd = gl->gl_object;
>+	if (rgd == NULL)
>+		return 0;
>+	gfs2_print_dbg(gi, " R: n:%llu\n", (unsigned long long)rgd->rd_addr);
>+	return 0;
>+}
>+
>+/**
>  * trans_go_sync - promote/demote the transaction glock
>  * @gl: the glock
>  * @state: the requested state
>@@ -330,7 +365,7 @@ static void trans_go_sync(struct gfs2_glock *gl)
>  *
>  */
> 
>-static void trans_go_xmote_bh(struct gfs2_glock *gl)
>+static void trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
> {
> 	struct gfs2_sbd *sdp = gl->gl_sbd;
> 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
>@@ -379,6 +414,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
> 	.go_inval = inode_go_inval,
> 	.go_demote_ok = inode_go_demote_ok,
> 	.go_lock = inode_go_lock,
>+	.go_dump = inode_go_dump,
> 	.go_type = LM_TYPE_INODE,
> 	.go_min_hold_time = HZ / 10,
> };
>@@ -389,6 +425,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
> 	.go_demote_ok = rgrp_go_demote_ok,
> 	.go_lock = rgrp_go_lock,
> 	.go_unlock = rgrp_go_unlock,
>+	.go_dump = rgrp_go_dump,
> 	.go_type = LM_TYPE_RGRP,
> 	.go_min_hold_time = HZ / 10,
> };
>diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
>index 9c2c0b9..0527a5c 100644
>--- a/fs/gfs2/incore.h
>+++ b/fs/gfs2/incore.h
>@@ -126,22 +126,30 @@ struct gfs2_bufdata {
> 	struct list_head bd_ail_gl_list;
> };
> 
>+struct gfs2_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             */
>+};
>+
> struct gfs2_glock_operations {
> 	void (*go_xmote_th) (struct gfs2_glock *gl);
>-	void (*go_xmote_bh) (struct gfs2_glock *gl);
>+	void (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
> 	void (*go_inval) (struct gfs2_glock *gl, int flags);
> 	int (*go_demote_ok) (struct gfs2_glock *gl);
> 	int (*go_lock) (struct gfs2_holder *gh);
> 	void (*go_unlock) (struct gfs2_holder *gh);
>+	int (*go_dump)(struct gfs2_glock_iter *gi, struct gfs2_glock *gl);
> 	const int go_type;
> 	const unsigned long go_min_hold_time;
> };
> 
> enum {
> 	/* States */
>-	HIF_HOLDER		= 6,
>+	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
> 	HIF_FIRST		= 7,
>-	HIF_ABORTED		= 9,
> 	HIF_WAIT		= 10,
> };
> 
>@@ -154,7 +162,7 @@ struct gfs2_holder {
> 	unsigned gh_flags;
> 
> 	int gh_error;
>-	unsigned long gh_iflags;
>+	unsigned long gh_iflags; /* HIF_... */
> 	unsigned long gh_ip;
> };
> 
>@@ -163,11 +171,9 @@ enum {
> 	GLF_STICKY		= 2,
> 	GLF_DEMOTE		= 3,
> 	GLF_PENDING_DEMOTE	= 4,
>-	GLF_DIRTY		= 5,
>-	GLF_DEMOTE_IN_PROGRESS	= 6,
>+	GLF_DEMOTE_IN_PROGRESS	= 5,
>+	GLF_DIRTY		= 6,
> 	GLF_LFLUSH		= 7,
>-	GLF_WAITERS2		= 8,
>-	GLF_CONV_DEADLK		= 9,
> };
> 
> struct gfs2_glock {
>@@ -179,19 +185,13 @@ struct gfs2_glock {
> 	spinlock_t gl_spin;
> 
> 	unsigned int gl_state;
>+	unsigned int gl_target;
> 	unsigned int gl_hash;
> 	unsigned int gl_demote_state; /* state requested by remote node */
> 	unsigned long gl_demote_time; /* time of first demote request */
>-	struct pid *gl_owner_pid;
>-	unsigned long gl_ip;
> 	struct list_head gl_holders;
>-	struct list_head gl_waiters1;	/* HIF_MUTEX */
>-	struct list_head gl_waiters3;	/* HIF_PROMOTE */
> 
> 	const struct gfs2_glock_operations *gl_ops;
>-
>-	struct gfs2_holder *gl_req_gh;
>-
> 	void *gl_lock;
> 	char *gl_lvb;
> 	atomic_t gl_lvb_count;
>diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c
>index cf7ea8a..fed9a67 100644
>--- a/fs/gfs2/locking/dlm/lock.c
>+++ b/fs/gfs2/locking/dlm/lock.c
>@@ -308,6 +308,9 @@ unsigned int gdlm_lock(void *lock, unsigned int cur_state,
> {
> 	struct gdlm_lock *lp = lock;
> 
>+	if (req_state == LM_ST_UNLOCKED)
>+		return gdlm_unlock(lock, cur_state);
>+
> 	clear_bit(LFL_DLM_CANCEL, &lp->flags);
> 	if (flags & LM_FLAG_NOEXP)
> 		set_bit(LFL_NOBLOCK, &lp->flags);
>diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c
>index 284a5ec..627bfb7 100644
>--- a/fs/gfs2/locking/nolock/main.c
>+++ b/fs/gfs2/locking/nolock/main.c
>@@ -107,6 +107,8 @@ static void nolock_put_lock(void *lock)
> static unsigned int nolock_lock(void *lock, unsigned int cur_state,
> 				unsigned int req_state, unsigned int flags)
> {
>+	if (req_state == LM_ST_UNLOCKED)
>+		return 0;
> 	return req_state | LM_OUT_CACHEABLE;
> }
> 
>diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
>index 053e2eb..bcc668d 100644
>--- a/fs/gfs2/main.c
>+++ b/fs/gfs2/main.c
>@@ -40,8 +40,6 @@ static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo)
> 	INIT_HLIST_NODE(&gl->gl_list);
> 	spin_lock_init(&gl->gl_spin);
> 	INIT_LIST_HEAD(&gl->gl_holders);
>-	INIT_LIST_HEAD(&gl->gl_waiters1);
>-	INIT_LIST_HEAD(&gl->gl_waiters3);
> 	gl->gl_lvb = NULL;
> 	atomic_set(&gl->gl_lvb_count, 0);
> 	INIT_LIST_HEAD(&gl->gl_reclaim);
>diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
>index 90a04a6..aba0df1 100644
>--- a/fs/gfs2/ops_address.c
>+++ b/fs/gfs2/ops_address.c
>@@ -507,26 +507,23 @@ static int __gfs2_readpage(void *file, struct page *page)
> static int gfs2_readpage(struct file *file, struct page *page)
> {
> 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
>-	struct gfs2_holder *gh;
>+	struct gfs2_holder gh;
> 	int error;
> 
>-	gh = gfs2_glock_is_locked_by_me(ip->i_gl);
>-	if (!gh) {
>-		gh = kmalloc(sizeof(struct gfs2_holder), GFP_NOFS);
>-		if (!gh)
>-			return -ENOBUFS;
>-		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, gh);
>+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
>+	error = gfs2_glock_nq_atime(&gh);
>+	if (unlikely(error)) {
> 		unlock_page(page);
>-		error = gfs2_glock_nq_atime(gh);
>-		if (likely(error != 0))
>-			goto out;
>-		return AOP_TRUNCATED_PAGE;
>+		goto out;
> 	}
> 	error = __gfs2_readpage(file, page);
>-	gfs2_glock_dq(gh);
>+	gfs2_glock_dq(&gh);
> out:
>-	gfs2_holder_uninit(gh);
>-	kfree(gh);
>+	gfs2_holder_uninit(&gh);
>+	if (error == GLR_TRYFAILED) {
>+		yield();
>+		return AOP_TRUNCATED_PAGE;
>+	}
> 	return error;
> }
> 
>diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
>index e1b7d52..0ff512a 100644
>--- a/fs/gfs2/ops_file.c
>+++ b/fs/gfs2/ops_file.c
>@@ -669,8 +669,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
> 	int error = 0;
> 
> 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
>-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE 
>-		| GL_FLOCK;
>+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
> 
> 	mutex_lock(&fp->f_fl_mutex);
> 
>@@ -683,9 +682,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
> 		gfs2_glock_dq_wait(fl_gh);
> 		gfs2_holder_reinit(state, flags, fl_gh);
> 	} else {
>-		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
>-				      ip->i_no_addr, &gfs2_flock_glops,
>-				      CREATE, &gl);
>+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
>+				       &gfs2_flock_glops, CREATE, &gl);
> 		if (error)
> 			goto out;
> 		gfs2_holder_init(gl, state, flags, fl_gh);
>diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
>index 2888e4b..fdd3f0f 100644
>--- a/fs/gfs2/recovery.c
>+++ b/fs/gfs2/recovery.c
>@@ -505,7 +505,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
> 
> 		error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
> 					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
>-					   GL_NOCANCEL | GL_NOCACHE, &t_gh);
>+					   GL_NOCACHE, &t_gh);
> 		if (error)
> 			goto fail_gunlock_ji;
> 
>diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
>index 7aeacbc..12fe38f 100644
>--- a/fs/gfs2/super.c
>+++ b/fs/gfs2/super.c
>@@ -941,8 +941,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
> 	}
> 
> 	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
>-			       LM_FLAG_PRIORITY | GL_NOCACHE,
>-			       t_gh);
>+				   GL_NOCACHE, t_gh);
> 
> 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
> 		error = gfs2_jdesc_check(jd);

Actions: View | Diff

Attachments on bug 432057: 294383 | 295614 | 296569 | 297894 | 298191 | 302891 | 303203 | 303208 | 303209 | 303500 | 303542 | 303631 | 303637 | 303646 | 304026 | 304098 | 304112 | 304161 | 304398 | 304409 | 304572 | 304636 | 304637 | 304749 | 304755 | 304811 | 304837 | 304876 | 304898 | 304946 | 304955 | 304976 | 304984 | 305126 | 305185 | 305237 | 305266 | 305377 | 305387 | 305404 | 305506 | 305513 | 305678 | 305702 | 305727 | 306084 | 306111 | 306191 | 306207 | 306208 | 306275 | 306287 | 306832 | 306972 | 307077 | 307096 | 307158