Ocfs2 devel - Mar 2008 - New dlm debug infrastructure - 3rd attempt

__dlm_print_one_lock_resource was printing lockname incorrectly.
Also, we now use printk directly instead of mlog as the latter prints
the line context which is not useful for this print.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
---
 fs/ocfs2/dlm/dlmdebug.c |  126 +++++++++++++++++++----------------------------
 1 files changed, 51 insertions(+), 75 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 58e4579..53a9e60 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -5,7 +5,7 @@
  *
  * debug functionality for the dlm
  *
- * Copyright (C) 2004 Oracle.  All rights reserved.
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
@@ -44,11 +44,10 @@
 #define MLOG_MASK_PREFIX ML_DLM
 #include "cluster/masklog.h"
 
+int stringify_lockname(const char *lockname, int locklen, char *buf, int len);
+
 void dlm_print_one_lock_resource(struct dlm_lock_resource *res)
 {
-	mlog(ML_NOTICE, "lockres: %.*s, owner=%u, state=%u\n",
-	       res->lockname.len, res->lockname.name,
-	       res->owner, res->state);
 	spin_lock(&res->spinlock);
 	__dlm_print_one_lock_resource(res);
 	spin_unlock(&res->spinlock);
@@ -59,75 +58,78 @@ static void dlm_print_lockres_refmap(struct
dlm_lock_resource *res)
 	int bit;
 	assert_spin_locked(&res->spinlock);
 
-	mlog(ML_NOTICE, "  refmap nodes: [ ");
+	printk(KERN_NOTICE "  refmap nodes: [ ");
 	bit = 0;
 	while (1) {
 		bit = find_next_bit(res->refmap, O2NM_MAX_NODES, bit);
 		if (bit >= O2NM_MAX_NODES)
 			break;
-		printk("%u ", bit);
+		printk(KERN_NOTICE "%u ", bit);
 		bit++;
 	}
-	printk("], inflight=%u\n", res->inflight_locks);
+	printk(KERN_NOTICE "], inflight=%u\n", res->inflight_locks);
+}
+
+static void __dlm_print_lock(struct dlm_lock *lock)
+{
+	spin_lock(&lock->spinlock);
+
+	printk(KERN_NOTICE "    type=%d, conv=%d, node=%u, cookie=%u:%llu, "
+	       "ref=%u, ast=(empty=%c,pend=%c), bast=(empty=%c,pend=%c), "
+	       "pending=(conv=%c,lock=%c,cancel=%c,unlock=%c)\n",
+	       lock->ml.type, lock->ml.convert_type, lock->ml.node,
+	       dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+	       dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+	       atomic_read(&lock->lock_refs.refcount),
+	       (list_empty(&lock->ast_list) ? 'y' : 'n'),
+	       (lock->ast_pending ? 'y' : 'n'),
+	       (list_empty(&lock->bast_list) ? 'y' : 'n'),
+	       (lock->bast_pending ? 'y' : 'n'),
+	       (lock->convert_pending ? 'y' : 'n'),
+	       (lock->lock_pending ? 'y' : 'n'),
+	       (lock->cancel_pending ? 'y' : 'n'),
+	       (lock->unlock_pending ? 'y' : 'n'));
+
+	spin_unlock(&lock->spinlock);
 }
 
 void __dlm_print_one_lock_resource(struct dlm_lock_resource *res)
 {
 	struct list_head *iter2;
 	struct dlm_lock *lock;
+	char buf[DLM_LOCKID_NAME_MAX];
 
 	assert_spin_locked(&res->spinlock);
 
-	mlog(ML_NOTICE, "lockres: %.*s, owner=%u, state=%u\n",
-	       res->lockname.len, res->lockname.name,
-	       res->owner, res->state);
-	mlog(ML_NOTICE, "  last used: %lu, on purge list: %s\n",
-	     res->last_used, list_empty(&res->purge) ? "no" :
"yes");
+	stringify_lockname(res->lockname.name, res->lockname.len,
+			   buf, sizeof(buf) - 1);
+	printk(KERN_NOTICE "lockres: %s, owner=%u, state=%u\n",
+	       buf, res->owner, res->state);
+	printk(KERN_NOTICE "  last used: %lu, refcnt: %u, on purge list:
%s\n",
+	       res->last_used, atomic_read(&res->refs.refcount),
+	       list_empty(&res->purge) ? "no" : "yes");
+	printk(KERN_NOTICE "  on dirty list: %s, on reco list: %s, "
+	       "migrating pending: %s\n",
+	       list_empty(&res->dirty) ? "no" : "yes",
+	       list_empty(&res->recovering) ? "no" : "yes",
+	       res->migration_pending ? "yes" : "no");
+	printk(KERN_NOTICE "  inflight locks: %d, asts reserved: %d\n",
+	       res->inflight_locks, atomic_read(&res->asts_reserved));
 	dlm_print_lockres_refmap(res);
-	mlog(ML_NOTICE, "  granted queue: \n");
+	printk(KERN_NOTICE "  granted queue:\n");
 	list_for_each(iter2, &res->granted) {
 		lock = list_entry(iter2, struct dlm_lock, list);
-		spin_lock(&lock->spinlock);
-		mlog(ML_NOTICE, "    type=%d, conv=%d, node=%u, "
-		       "cookie=%u:%llu, ast=(empty=%c,pend=%c),
bast=(empty=%c,pend=%c)\n",
-		       lock->ml.type, lock->ml.convert_type, lock->ml.node, 
-		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
-		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-		       list_empty(&lock->ast_list) ? 'y' : 'n',
-		       lock->ast_pending ? 'y' : 'n',
-		       list_empty(&lock->bast_list) ? 'y' : 'n',
-		       lock->bast_pending ? 'y' : 'n');
-		spin_unlock(&lock->spinlock);
+		__dlm_print_lock(lock);
 	}
-	mlog(ML_NOTICE, "  converting queue: \n");
+	printk(KERN_NOTICE "  converting queue:\n");
 	list_for_each(iter2, &res->converting) {
 		lock = list_entry(iter2, struct dlm_lock, list);
-		spin_lock(&lock->spinlock);
-		mlog(ML_NOTICE, "    type=%d, conv=%d, node=%u, "
-		       "cookie=%u:%llu, ast=(empty=%c,pend=%c),
bast=(empty=%c,pend=%c)\n",
-		       lock->ml.type, lock->ml.convert_type, lock->ml.node, 
-		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
-		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-		       list_empty(&lock->ast_list) ? 'y' : 'n',
-		       lock->ast_pending ? 'y' : 'n',
-		       list_empty(&lock->bast_list) ? 'y' : 'n',
-		       lock->bast_pending ? 'y' : 'n');
-		spin_unlock(&lock->spinlock);
+		__dlm_print_lock(lock);
 	}
-	mlog(ML_NOTICE, "  blocked queue: \n");
+	printk(KERN_NOTICE "  blocked queue:\n");
 	list_for_each(iter2, &res->blocked) {
 		lock = list_entry(iter2, struct dlm_lock, list);
-		spin_lock(&lock->spinlock);
-		mlog(ML_NOTICE, "    type=%d, conv=%d, node=%u, "
-		       "cookie=%u:%llu, ast=(empty=%c,pend=%c),
bast=(empty=%c,pend=%c)\n",
-		       lock->ml.type, lock->ml.convert_type, lock->ml.node, 
-		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
-		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-		       list_empty(&lock->ast_list) ? 'y' : 'n',
-		       lock->ast_pending ? 'y' : 'n',
-		       list_empty(&lock->bast_list) ? 'y' : 'n',
-		       lock->bast_pending ? 'y' : 'n');
-		spin_unlock(&lock->spinlock);
+		__dlm_print_lock(lock);
 	}
 }
 
@@ -137,31 +139,6 @@ void dlm_print_one_lock(struct dlm_lock *lockid)
 }
 EXPORT_SYMBOL_GPL(dlm_print_one_lock);
 
-#if 0
-void dlm_dump_lock_resources(struct dlm_ctxt *dlm)
-{
-	struct dlm_lock_resource *res;
-	struct hlist_node *iter;
-	struct hlist_head *bucket;
-	int i;
-
-	mlog(ML_NOTICE, "struct dlm_ctxt: %s, node=%u, key=%u\n",
-		  dlm->name, dlm->node_num, dlm->key);
-	if (!dlm || !dlm->name) {
-		mlog(ML_ERROR, "dlm=%p\n", dlm);
-		return;
-	}
-
-	spin_lock(&dlm->spinlock);
-	for (i=0; i<DLM_HASH_BUCKETS; i++) {
-		bucket = dlm_lockres_hash(dlm, i);
-		hlist_for_each_entry(res, iter, bucket, hash_node)
-			dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->spinlock);
-}
-#endif  /*  0  */
-
 static const char *dlm_errnames[] = {
 	[DLM_NORMAL] =			"DLM_NORMAL",
 	[DLM_GRANTED] =			"DLM_GRANTED",
@@ -274,8 +251,7 @@ EXPORT_SYMBOL_GPL(dlm_errname);
  *
  * For more on lockname formats, please refer to dlmglue.c and ocfs2_lockid.h.
  */
-static int stringify_lockname(const char *lockname, int locklen,
-			      char *buf, int len)
+int stringify_lockname(const char *lockname, int locklen, char *buf, int len)
 {
 	int out = 0;
 	__be64 inode_blkno_be;
-- 
1.5.3.6

This patch dumps all mles it can fit in one page into a debugfs file.
Useful for debugging.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdebug.c |  119 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmdebug.h |    1 +
 2 files changed, 120 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index cccb1ce..6de326b 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -302,6 +302,7 @@ static int stringify_lockname(const char *lockname, int
locklen,
 #define DLM_DEBUGFS_DIR				"o2dlm"
 #define DLM_DEBUGFS_DLM_STATE			"dlm_state"
 #define DLM_DEBUGFS_LOCKING_STATE		"locking_state"
+#define DLM_DEBUGFS_MLE_STATE			"mle_state"
 
 /* begin - utils funcs */
 static void dlm_debug_free(struct kref *kref)
@@ -395,6 +396,112 @@ static int debug_buffer_release(struct inode *inode,
struct file *file)
 }
 /* end - util funcs */
 
+/* begin - debug mle funcs */
+static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
+{
+	int out = 0;
+	unsigned int namelen;
+	const char *name;
+	char *mle_type;
+
+	if (mle->type != DLM_MLE_MASTER) {
+		namelen = mle->u.name.len;
+		name = mle->u.name.name;
+	} else {
+		namelen = mle->u.res->lockname.len;
+		name = mle->u.res->lockname.name;
+	}
+
+	if (mle->type == DLM_MLE_BLOCK)
+		mle_type = "BLK";
+	else if (mle->type == DLM_MLE_MASTER)
+		mle_type = "MAS";
+	else
+		mle_type = "MIG";
+
+	out += stringify_lockname(name, namelen, buf + out, len - out);
+	out += snprintf(buf + out, len - out,
+			"\t%3s\tmas=%3u\tnew=%3u\tevt=%1d\tuse=%1d\tref=%3d\n",
+			mle_type, mle->master, mle->new_master,
+			!list_empty(&mle->hb_events),
+			!!mle->inuse,
+			atomic_read(&mle->mle_refs.refcount));
+
+	out += snprintf(buf + out, len - out, "Maybe=");
+	out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Vote=");
+	out += stringify_nodemap(mle->vote_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Response=");
+	out += stringify_nodemap(mle->response_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Node=");
+	out += stringify_nodemap(mle->node_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "\n");
+
+	return out;
+}
+
+static int debug_mle_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
+{
+	struct dlm_master_list_entry *mle;
+	int out = 0;
+	unsigned long total = 0;
+
+	out += snprintf(db->buf + out, db->len - out,
+			"Dumping MLEs for Domain: %s\n", dlm->name);
+
+	spin_lock(&dlm->master_lock);
+	list_for_each_entry(mle, &dlm->master_list, list) {
+		++total;
+		if (db->len - out < 200)
+			continue;
+		out += dump_mle(mle, db->buf + out, db->len - out);
+	}
+	spin_unlock(&dlm->master_lock);
+
+	out += snprintf(db->buf + out, db->len - out,
+			"Total on list: %ld\n", total);
+	return out;
+}
+
+static int debug_mle_open(struct inode *inode, struct file *file)
+{
+	struct dlm_ctxt *dlm = inode->i_private;
+	struct debug_buffer *db;
+
+	db = debug_buffer_allocate();
+	if (!db)
+		goto bail;
+
+	db->len = debug_mle_print(dlm, db);
+
+	file->private_data = db;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static struct file_operations debug_mle_fops = {
+	.open =		debug_mle_open,
+	.release =	debug_buffer_release,
+	.read =		debug_buffer_read,
+	.llseek =	debug_buffer_llseek,
+};
+
+/* end - debug mle funcs */
+
 /* begin - debug lockres funcs */
 static int dump_lock(struct dlm_lock *lock, int list_type, char *buf, int len)
 {
@@ -789,6 +896,16 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
+	/* for dumping mles */
+	dc->debug_mle_dentry = debugfs_create_file(DLM_DEBUGFS_MLE_STATE,
+						   S_IFREG|S_IRUSR,
+						   dlm->dlm_debugfs_subroot,
+						   dlm, &debug_mle_fops);
+	if (!dc->debug_mle_dentry) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+
 	dlm_debug_get(dc);
 	return 0;
 
@@ -802,6 +919,8 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
 
 	if (dc) {
+		if (dc->debug_mle_dentry)
+			debugfs_remove(dc->debug_mle_dentry);
 		if (dc->debug_lockres_dentry)
 			debugfs_remove(dc->debug_lockres_dentry);
 		if (dc->debug_state_dentry)
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index 7c5b2b0..cbc69f2 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -31,6 +31,7 @@ struct dlm_debug_ctxt {
 	struct kref debug_refcnt;
 	struct dentry *debug_state_dentry;
 	struct dentry *debug_lockres_dentry;
+	struct dentry *debug_mle_dentry;
 };
 
 struct debug_buffer {
-- 
1.5.3.6

The following patches follow:

[PATCH 01/11] ocfs2/dlm: Rename slabcache dlm_mle_cache to o2dlm_mle
[PATCH 02/11] ocfs2/dlm: Creates slabcaches for lock and lockres
[PATCH 03/11] ocfs2/dlm: Link all lockres' to a tracking list
[PATCH 04/11] ocfs2/dlm: Create debugfs dirs
[PATCH 05/11] ocfs2/dlm: Dump the dlm state in a debugfs file
[PATCH 06/11] ocfs2/dlm: Dumps the lockres' into a debugfs file
[PATCH 07/11] ocfs2/dlm: Move struct dlm_master_list_entry to dlmcommon.h
[PATCH 08/11] ocfs2/dlm: Dumps the mles into a debugfs file
[PATCH 09/11] ocfs2/dlm: Dumps the purgelist into a debugfs file
[PATCH 10/11] ocfs2/dlm: Move dlm_print_one_mle() from dlmmaster.c to dlmdebug.c
[PATCH 11/11] ocfs2/dlm: Fix lockname in lockres print function

Changes suggested by Joel Becker have been incorporated.

This patch series has been tested with ocfs2.git upstream-linus branch.

Sunil

This patch dumps all the lockres' alongwith all the locks into
a debugfs file. Useful for debugging.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdebug.c |  247 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmdebug.h |    8 ++
 2 files changed, 255 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e335403..cccb1ce 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -273,8 +273,35 @@ EXPORT_SYMBOL_GPL(dlm_errname);
 
 static struct dentry *dlm_debugfs_root = NULL;
 
+/* NOTE: This function converts a lockname into a string. It uses knowledge
+ * of the format of the lockname that should be outside the purview of the dlm.
+ * We are adding only to make dlm debugging slightly easier.
+ *
+ * For more on lockname formats, please refer to dlmglue.c and ocfs2_lockid.h.
+ */
+static int stringify_lockname(const char *lockname, int locklen,
+			      char *buf, int len)
+{
+	int out = 0;
+	__be64 inode_blkno_be;
+
+#define OCFS2_DENTRY_LOCK_INO_START	18
+	if (*lockname == 'N') {
+		memcpy((__be64 *)&inode_blkno_be,
+		       (char *)&lockname[OCFS2_DENTRY_LOCK_INO_START],
+		       sizeof(__be64));
+		out += snprintf(buf + out, len - out, "%.*s%08x",
+				OCFS2_DENTRY_LOCK_INO_START - 1, lockname,
+				(unsigned int)be64_to_cpu(inode_blkno_be));
+	} else
+		out += snprintf(buf + out, len - out, "%.*s",
+				locklen, lockname);
+	return out;
+}
+
 #define DLM_DEBUGFS_DIR				"o2dlm"
 #define DLM_DEBUGFS_DLM_STATE			"dlm_state"
+#define DLM_DEBUGFS_LOCKING_STATE		"locking_state"
 
 /* begin - utils funcs */
 static void dlm_debug_free(struct kref *kref)
@@ -368,6 +395,213 @@ static int debug_buffer_release(struct inode *inode,
struct file *file)
 }
 /* end - util funcs */
 
+/* begin - debug lockres funcs */
+static int dump_lock(struct dlm_lock *lock, int list_type, char *buf, int len)
+{
+	int out;
+
+#define DEBUG_LOCK_VERSION	1
+	spin_lock(&lock->spinlock);
+	out = snprintf(buf, len,
"LOCK:%d,%d,%d,%d,%d,%d:%lld,%d,%d,%d,%d,%d,"
+		       "%d,%d,%d,%d\n",
+		       DEBUG_LOCK_VERSION,
+		       list_type, lock->ml.type, lock->ml.convert_type,
+		       lock->ml.node,
+		       dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+		       dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+		       !list_empty(&lock->ast_list),
+		       !list_empty(&lock->bast_list),
+		       lock->ast_pending, lock->bast_pending,
+		       lock->convert_pending, lock->lock_pending,
+		       lock->cancel_pending, lock->unlock_pending,
+		       atomic_read(&lock->lock_refs.refcount));
+	spin_unlock(&lock->spinlock);
+
+	return out;
+}
+
+static int dump_lockres(struct dlm_lock_resource *res, char *buf, int len)
+{
+	struct dlm_lock *lock;
+	int i;
+	int out = 0;
+
+	out += snprintf(buf + out, len - out, "NAME:");
+	out += stringify_lockname(res->lockname.name, res->lockname.len,
+				  buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+#define DEBUG_LRES_VERSION	1
+	out += snprintf(buf + out, len - out,
+			"LRES:%d,%d,%d,%ld,%d,%d,%d,%d,%d,%d,%d\n",
+			DEBUG_LRES_VERSION,
+			res->owner, res->state, res->last_used,
+			!list_empty(&res->purge),
+			!list_empty(&res->dirty),
+			!list_empty(&res->recovering),
+			res->inflight_locks, res->migration_pending,
+			atomic_read(&res->asts_reserved),
+			atomic_read(&res->refs.refcount));
+
+	/* refmap */
+	out += snprintf(buf + out, len - out, "RMAP:");
+	out += stringify_nodemap(res->refmap, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	/* lvb */
+	out += snprintf(buf + out, len - out, "LVBX:");
+	for (i = 0; i < DLM_LVB_LEN; i++)
+		out += snprintf(buf + out, len - out,
+					"%02x", (unsigned char)res->lvb[i]);
+	out += snprintf(buf + out, len - out, "\n");
+
+	/* granted */
+	list_for_each_entry(lock, &res->granted, list)
+		out += dump_lock(lock, 0, buf + out, len - out);
+
+	/* converting */
+	list_for_each_entry(lock, &res->converting, list)
+		out += dump_lock(lock, 1, buf + out, len - out);
+
+	/* blocked */
+	list_for_each_entry(lock, &res->blocked, list)
+		out += dump_lock(lock, 2, buf + out, len - out);
+
+	out += snprintf(buf + out, len - out, "\n");
+
+	return out;
+}
+
+static void *lockres_seq_start(struct seq_file *m, loff_t *pos)
+{
+	struct debug_lockres *dl = m->private;
+	struct dlm_ctxt *dlm = dl->dl_ctxt;
+	struct dlm_lock_resource *res = NULL;
+
+	spin_lock(&dlm->spinlock);
+
+	if (dl->dl_res) {
+		list_for_each_entry(res, &dl->dl_res->tracking, tracking) {
+			if (dl->dl_res) {
+				dlm_lockres_put(dl->dl_res);
+				dl->dl_res = NULL;
+			}
+			if (&res->tracking == &dlm->tracking_list) {
+				mlog(0, "End of list found, %p\n", res);
+				dl = NULL;
+				break;
+			}
+			dlm_lockres_get(res);
+			dl->dl_res = res;
+			break;
+		}
+	} else {
+		if (!list_empty(&dlm->tracking_list)) {
+			list_for_each_entry(res, &dlm->tracking_list, tracking)
+				break;
+			dlm_lockres_get(res);
+			dl->dl_res = res;
+		} else
+			dl = NULL;
+	}
+
+	if (dl) {
+		spin_lock(&dl->dl_res->spinlock);
+		dump_lockres(dl->dl_res, dl->dl_buf, dl->dl_len - 1);
+		spin_unlock(&dl->dl_res->spinlock);
+	}
+
+	spin_unlock(&dlm->spinlock);
+
+	return dl;
+}
+
+static void lockres_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static void *lockres_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return NULL;
+}
+
+static int lockres_seq_show(struct seq_file *s, void *v)
+{
+	struct debug_lockres *dl = (struct debug_lockres *)v;
+
+	seq_printf(s, "%s", dl->dl_buf);
+
+	return 0;
+}
+
+static struct seq_operations debug_lockres_ops = {
+	.start =	lockres_seq_start,
+	.stop =		lockres_seq_stop,
+	.next =		lockres_seq_next,
+	.show =		lockres_seq_show,
+};
+
+static int debug_lockres_open(struct inode *inode, struct file *file)
+{
+	struct dlm_ctxt *dlm = inode->i_private;
+	int ret = -ENOMEM;
+	struct seq_file *seq;
+	struct debug_lockres *dl = NULL;
+
+	dl = kzalloc(sizeof(struct debug_lockres), GFP_KERNEL);
+	if (!dl) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	dl->dl_len = PAGE_SIZE;
+	dl->dl_buf = kmalloc(dl->dl_len, GFP_KERNEL);
+	if (!dl->dl_buf) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	ret = seq_open(file, &debug_lockres_ops);
+	if (ret) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	seq = (struct seq_file *) file->private_data;
+	seq->private = dl;
+
+	dlm_grab(dlm);
+	dl->dl_ctxt = dlm;
+
+	return 0;
+bail:
+	if (dl)
+		kfree(dl->dl_buf);
+	kfree(dl);
+	return ret;
+}
+
+static int debug_lockres_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = (struct seq_file *)file->private_data;
+	struct debug_lockres *dl = (struct debug_lockres *)seq->private;
+
+	if (dl->dl_res)
+		dlm_lockres_put(dl->dl_res);
+	dlm_put(dl->dl_ctxt);
+	kfree(dl->dl_buf);
+	return seq_release_private(inode, file);
+}
+
+static struct file_operations debug_lockres_fops = {
+	.open =		debug_lockres_open,
+	.release =	debug_lockres_release,
+	.read =		seq_read,
+	.llseek =	seq_lseek,
+};
+/* end - debug lockres funcs */
+
 /* begin - debug state funcs */
 static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
 {
@@ -544,6 +778,17 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
+	/* for dumping lockres */
+	dc->debug_lockres_dentry +			debugfs_create_file(DLM_DEBUGFS_LOCKING_STATE,
+					    S_IFREG|S_IRUSR,
+					    dlm->dlm_debugfs_subroot,
+					    dlm, &debug_lockres_fops);
+	if (!dc->debug_lockres_dentry) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+
 	dlm_debug_get(dc);
 	return 0;
 
@@ -557,6 +802,8 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
 
 	if (dc) {
+		if (dc->debug_lockres_dentry)
+			debugfs_remove(dc->debug_lockres_dentry);
 		if (dc->debug_state_dentry)
 			debugfs_remove(dc->debug_state_dentry);
 		dlm_debug_put(dc);
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index 94cc10a..7c5b2b0 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -30,6 +30,7 @@
 struct dlm_debug_ctxt {
 	struct kref debug_refcnt;
 	struct dentry *debug_state_dentry;
+	struct dentry *debug_lockres_dentry;
 };
 
 struct debug_buffer {
@@ -37,6 +38,13 @@ struct debug_buffer {
 	char *buf;
 };
 
+struct debug_lockres {
+	int dl_len;
+	char *dl_buf;
+	struct dlm_ctxt *dl_ctxt;
+	struct dlm_lock_resource *dl_res;
+};
+
 int dlm_debug_init(struct dlm_ctxt *dlm);
 void dlm_debug_shutdown(struct dlm_ctxt *dlm);
 
-- 
1.5.3.6

This patch dumps the dlm state (dlm_ctxt) into a debugfs file.
Useful for debugging.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
---
 fs/ocfs2/dlm/dlmcommon.h |    1 +
 fs/ocfs2/dlm/dlmdebug.c  |  296 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmdebug.h  |   20 +++
 fs/ocfs2/dlm/dlmdomain.c |    8 ++
 4 files changed, 325 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 6a49140..f7a51ca 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -123,6 +123,7 @@ struct dlm_ctxt
 	atomic_t remote_resources;
 	atomic_t unknown_resources;
 
+	struct dlm_debug_ctxt *dlm_debug_ctxt;
 	struct dentry *dlm_debugfs_subroot;
 
 	/* NOTE: Next three are protected by dlm_domain_lock */
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 62e2a4c..e335403 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -274,6 +274,294 @@ EXPORT_SYMBOL_GPL(dlm_errname);
 static struct dentry *dlm_debugfs_root = NULL;
 
 #define DLM_DEBUGFS_DIR				"o2dlm"
+#define DLM_DEBUGFS_DLM_STATE			"dlm_state"
+
+/* begin - utils funcs */
+static void dlm_debug_free(struct kref *kref)
+{
+	struct dlm_debug_ctxt *dc;
+
+	dc = container_of(kref, struct dlm_debug_ctxt, debug_refcnt);
+
+	kfree(dc);
+}
+
+void dlm_debug_put(struct dlm_debug_ctxt *dc)
+{
+	if (dc)
+		kref_put(&dc->debug_refcnt, dlm_debug_free);
+}
+
+static void dlm_debug_get(struct dlm_debug_ctxt *dc)
+{
+	kref_get(&dc->debug_refcnt);
+}
+
+static int stringify_nodemap(unsigned long *nodemap, int maxnodes,
+			     char *buf, int len)
+{
+	int out = 0;
+	int i = -1;
+
+	while ((i = find_next_bit(nodemap, maxnodes, i + 1)) < maxnodes)
+		out += snprintf(buf + out, len - out, "%d ", i);
+
+	return out;
+}
+
+static struct debug_buffer *debug_buffer_allocate(void)
+{
+	struct debug_buffer *db = NULL;
+
+	db = kzalloc(sizeof(struct debug_buffer), GFP_KERNEL);
+	if (!db)
+		goto bail;
+
+	db->len = PAGE_SIZE;
+	db->buf = kmalloc(db->len, GFP_KERNEL);
+	if (!db->buf)
+		goto bail;
+
+	return db;
+bail:
+	kfree(db);
+	return NULL;
+}
+
+static ssize_t debug_buffer_read(struct file *file, char __user *buf,
+				 size_t nbytes, loff_t *ppos)
+{
+	struct debug_buffer *db = file->private_data;
+
+	return simple_read_from_buffer(buf, nbytes, ppos, db->buf, db->len);
+}
+
+static loff_t debug_buffer_llseek(struct file *file, loff_t off, int whence)
+{
+	struct debug_buffer *db = file->private_data;
+	loff_t new = -1;
+
+	switch (whence) {
+	case 0:
+		new = off;
+		break;
+	case 1:
+		new = file->f_pos + off;
+		break;
+	}
+
+	if (new < 0 || new > db->len)
+		return -EINVAL;
+
+	return (file->f_pos = new);
+}
+
+static int debug_buffer_release(struct inode *inode, struct file *file)
+{
+	struct debug_buffer *db = (struct debug_buffer *)file->private_data;
+
+	if (db)
+		kfree(db->buf);
+	kfree(db);
+
+	return 0;
+}
+/* end - util funcs */
+
+/* begin - debug state funcs */
+static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
+{
+	int out = 0;
+	struct dlm_reco_node_data *node;
+	char *state;
+	int lres, rres, ures, tres;
+
+	lres = atomic_read(&dlm->local_resources);
+	rres = atomic_read(&dlm->remote_resources);
+	ures = atomic_read(&dlm->unknown_resources);
+	tres = lres + rres + ures;
+
+	spin_lock(&dlm->spinlock);
+
+	switch (dlm->dlm_state) {
+	case DLM_CTXT_NEW:
+		state = "NEW"; break;
+	case DLM_CTXT_JOINED:
+		state = "JOINED"; break;
+	case DLM_CTXT_IN_SHUTDOWN:
+		state = "SHUTDOWN"; break;
+	case DLM_CTXT_LEAVING:
+		state = "LEAVING"; break;
+	default:
+		state = "UNKNOWN"; break;
+	}
+
+	/* Domain: xxxxxxxxxx  Key: 0xdfbac769 */
+	out += snprintf(db->buf + out, db->len - out,
+			"Domain: %s  Key: 0x%08x\n", dlm->name, dlm->key);
+
+	/* Thread Pid: xxx  Node: xxx  State: xxxxx */
+	out += snprintf(db->buf + out, db->len - out,
+			"Thread Pid: %d  Node: %d  State: %s\n",
+			dlm->dlm_thread_task->pid, dlm->node_num, state);
+
+	/* Number of Joins: xxx  Joining Node: xxx */
+	out += snprintf(db->buf + out, db->len - out,
+			"Number of Joins: %d  Joining Node: %d\n",
+			dlm->num_joins, dlm->joining_node);
+
+	/* Domain Map: xx xx xx */
+	out += snprintf(db->buf + out, db->len - out, "Domain Map: ");
+	out += stringify_nodemap(dlm->domain_map, O2NM_MAX_NODES,
+				 db->buf + out, db->len - out);
+	out += snprintf(db->buf + out, db->len - out, "\n");
+
+	/* Live Map: xx xx xx */
+	out += snprintf(db->buf + out, db->len - out, "Live Map: ");
+	out += stringify_nodemap(dlm->live_nodes_map, O2NM_MAX_NODES,
+				 db->buf + out, db->len - out);
+	out += snprintf(db->buf + out, db->len - out, "\n");
+
+	/* Mastered Resources Total: xxx  Locally: xxx  Remotely: ... */
+	out += snprintf(db->buf + out, db->len - out,
+			"Mastered Resources Total: %d  Locally: %d  "
+			"Remotely: %d  Unknown: %d\n",
+			tres, lres, rres, ures);
+
+	/* Lists: Dirty=Empty  Purge=InUse  PendingASTs=Empty  ... */
+	out += snprintf(db->buf + out, db->len - out,
+			"Lists: Dirty=%s  Purge=%s  PendingASTs=%s  "
+			"PendingBASTs=%s  Master=%s\n",
+			(list_empty(&dlm->dirty_list) ? "Empty" :
"InUse"),
+			(list_empty(&dlm->purge_list) ? "Empty" :
"InUse"),
+			(list_empty(&dlm->pending_asts) ? "Empty" :
"InUse"),
+			(list_empty(&dlm->pending_basts) ? "Empty" :
"InUse"),
+			(list_empty(&dlm->master_list) ? "Empty" :
"InUse"));
+
+	/* Purge Count: xxx  Refs: xxx */
+	out += snprintf(db->buf + out, db->len - out,
+			"Purge Count: %d  Refs: %d\n", dlm->purge_count,
+			atomic_read(&dlm->dlm_refs.refcount));
+
+	/* Dead Node: xxx */
+	out += snprintf(db->buf + out, db->len - out,
+			"Dead Node: %d\n", dlm->reco.dead_node);
+
+	/* What about DLM_RECO_STATE_FINALIZE? */
+	if (dlm->reco.state == DLM_RECO_STATE_ACTIVE)
+		state = "ACTIVE";
+	else
+		state = "INACTIVE";
+
+	/* Recovery Pid: xxxx  Master: xxx  State: xxxx */
+	out += snprintf(db->buf + out, db->len - out,
+			"Recovery Pid: %d  Master: %d  State: %s\n",
+			dlm->dlm_reco_thread_task->pid,
+			dlm->reco.new_master, state);
+
+	/* Recovery Map: xx xx */
+	out += snprintf(db->buf + out, db->len - out, "Recovery Map:
");
+	out += stringify_nodemap(dlm->recovery_map, O2NM_MAX_NODES,
+				 db->buf + out, db->len - out);
+	out += snprintf(db->buf + out, db->len - out, "\n");
+
+	/* Recovery Node State: */
+	out += snprintf(db->buf + out, db->len - out, "Recovery Node
State:\n");
+	list_for_each_entry(node, &dlm->reco.node_data, list) {
+		switch (node->state) {
+		case DLM_RECO_NODE_DATA_INIT:
+			state = "INIT";
+			break;
+		case DLM_RECO_NODE_DATA_REQUESTING:
+			state = "REQUESTING";
+			break;
+		case DLM_RECO_NODE_DATA_DEAD:
+			state = "DEAD";
+			break;
+		case DLM_RECO_NODE_DATA_RECEIVING:
+			state = "RECEIVING";
+			break;
+		case DLM_RECO_NODE_DATA_REQUESTED:
+			state = "REQUESTED";
+			break;
+		case DLM_RECO_NODE_DATA_DONE:
+			state = "DONE";
+			break;
+		case DLM_RECO_NODE_DATA_FINALIZE_SENT:
+			state = "FINALIZE-SENT";
+			break;
+		default:
+			state = "BAD";
+			break;
+		}
+		out += snprintf(db->buf + out, db->len - out, "\t%u - %s\n",
+				node->node_num, state);
+	}
+
+	spin_unlock(&dlm->spinlock);
+
+	return out;
+}
+
+static int debug_state_open(struct inode *inode, struct file *file)
+{
+	struct dlm_ctxt *dlm = inode->i_private;
+	struct debug_buffer *db = NULL;
+
+	db = debug_buffer_allocate();
+	if (!db)
+		goto bail;
+
+	db->len = debug_state_print(dlm, db);
+
+	file->private_data = db;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static struct file_operations debug_state_fops = {
+	.open =		debug_state_open,
+	.release =	debug_buffer_release,
+	.read =		debug_buffer_read,
+	.llseek =	debug_buffer_llseek,
+};
+/* end  - debug state funcs */
+
+/* files in subroot */
+int dlm_debug_init(struct dlm_ctxt *dlm)
+{
+	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
+
+	/* for dumping dlm_ctxt */
+	dc->debug_state_dentry = debugfs_create_file(DLM_DEBUGFS_DLM_STATE,
+						     S_IFREG|S_IRUSR,
+						     dlm->dlm_debugfs_subroot,
+						     dlm, &debug_state_fops);
+	if (!dc->debug_state_dentry) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+
+	dlm_debug_get(dc);
+	return 0;
+
+bail:
+	dlm_debug_shutdown(dlm);
+	return -ENOMEM;
+}
+
+void dlm_debug_shutdown(struct dlm_ctxt *dlm)
+{
+	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
+
+	if (dc) {
+		if (dc->debug_state_dentry)
+			debugfs_remove(dc->debug_state_dentry);
+		dlm_debug_put(dc);
+	}
+}
 
 /* subroot - domain dir */
 int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
@@ -285,6 +573,14 @@ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
+	dlm->dlm_debug_ctxt = kzalloc(sizeof(struct dlm_debug_ctxt),
+				      GFP_KERNEL);
+	if (!dlm->dlm_debug_ctxt) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+	kref_init(&dlm->dlm_debug_ctxt->debug_refcnt);
+
 	return 0;
 bail:
 	dlm_destroy_debugfs_subroot(dlm);
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index b969595..94cc10a 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -27,6 +27,19 @@
 
 #ifdef CONFIG_DEBUG_FS
 
+struct dlm_debug_ctxt {
+	struct kref debug_refcnt;
+	struct dentry *debug_state_dentry;
+};
+
+struct debug_buffer {
+	int len;
+	char *buf;
+};
+
+int dlm_debug_init(struct dlm_ctxt *dlm);
+void dlm_debug_shutdown(struct dlm_ctxt *dlm);
+
 int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm);
 void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm);
 
@@ -35,6 +48,13 @@ void dlm_destroy_debugfs_root(void);
 
 #else
 
+static int dlm_debug_init(struct dlm_ctxt *dlm)
+{
+	return 0;
+}
+static void dlm_debug_shutdown(struct dlm_ctxt *dlm)
+{
+}
 static int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
 {
 	return 0;
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index c137d69..63f8125 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -398,6 +398,7 @@ static void dlm_destroy_dlm_worker(struct dlm_ctxt *dlm)
 static void dlm_complete_dlm_shutdown(struct dlm_ctxt *dlm)
 {
 	dlm_unregister_domain_handlers(dlm);
+	dlm_debug_shutdown(dlm);
 	dlm_complete_thread(dlm);
 	dlm_complete_recovery_thread(dlm);
 	dlm_destroy_dlm_worker(dlm);
@@ -1418,6 +1419,12 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
+	status = dlm_debug_init(dlm);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
 	status = dlm_launch_thread(dlm);
 	if (status < 0) {
 		mlog_errno(status);
@@ -1485,6 +1492,7 @@ bail:
 
 	if (status) {
 		dlm_unregister_domain_handlers(dlm);
+		dlm_debug_shutdown(dlm);
 		dlm_complete_thread(dlm);
 		dlm_complete_recovery_thread(dlm);
 		dlm_destroy_dlm_worker(dlm);
-- 
1.5.3.6

This patch creates the debugfs directories that will hold the
files to be used to dump the dlm state.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
---
 fs/ocfs2/dlm/dlmcommon.h |    2 +
 fs/ocfs2/dlm/dlmdebug.c  |   50 +++++++++++++++++++++++++++++++++++++++++-
 fs/ocfs2/dlm/dlmdebug.h  |   54 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmdomain.c |   21 +++++++++++++++++-
 4 files changed, 125 insertions(+), 2 deletions(-)
 create mode 100644 fs/ocfs2/dlm/dlmdebug.h

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index cc31abe..6a49140 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -123,6 +123,8 @@ struct dlm_ctxt
 	atomic_t remote_resources;
 	atomic_t unknown_resources;
 
+	struct dentry *dlm_debugfs_subroot;
+
 	/* NOTE: Next three are protected by dlm_domain_lock */
 	struct kref dlm_refs;
 	enum dlm_ctxt_state dlm_state;
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 64239b3..62e2a4c 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -30,6 +30,7 @@
 #include <linux/utsname.h>
 #include <linux/sysctl.h>
 #include <linux/spinlock.h>
+#include <linux/debugfs.h>
 
 #include "cluster/heartbeat.h"
 #include "cluster/nodemanager.h"
@@ -37,8 +38,8 @@
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
-
 #include "dlmdomain.h"
+#include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
 #include "cluster/masklog.h"
@@ -266,3 +267,50 @@ const char *dlm_errname(enum dlm_status err)
 	return dlm_errnames[err];
 }
 EXPORT_SYMBOL_GPL(dlm_errname);
+
+
+#ifdef CONFIG_DEBUG_FS
+
+static struct dentry *dlm_debugfs_root = NULL;
+
+#define DLM_DEBUGFS_DIR				"o2dlm"
+
+/* subroot - domain dir */
+int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
+{
+	dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name,
+						      dlm_debugfs_root);
+	if (!dlm->dlm_debugfs_subroot) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+
+	return 0;
+bail:
+	dlm_destroy_debugfs_subroot(dlm);
+	return -ENOMEM;
+}
+
+void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
+{
+	if (dlm->dlm_debugfs_subroot)
+		debugfs_remove(dlm->dlm_debugfs_subroot);
+}
+
+/* debugfs root */
+int dlm_create_debugfs_root(void)
+{
+	dlm_debugfs_root = debugfs_create_dir(DLM_DEBUGFS_DIR, NULL);
+	if (!dlm_debugfs_root) {
+		mlog_errno(-ENOMEM);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void dlm_destroy_debugfs_root(void)
+{
+	if (dlm_debugfs_root)
+		debugfs_remove(dlm_debugfs_root);
+}
+#endif	/* CONFIG_DEBUG_FS */
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
new file mode 100644
index 0000000..b969595
--- /dev/null
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -0,0 +1,54 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * dlmdebug.h
+ *
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ */
+
+#ifndef DLMDEBUG_H
+#define DLMDEBUG_H
+
+#ifdef CONFIG_DEBUG_FS
+
+int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm);
+void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm);
+
+int dlm_create_debugfs_root(void);
+void dlm_destroy_debugfs_root(void);
+
+#else
+
+static int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
+{
+	return 0;
+}
+static void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
+{
+}
+static int dlm_create_debugfs_root(void)
+{
+	return 0;
+}
+static void dlm_destroy_debugfs_root(void)
+{
+}
+
+#endif	/* CONFIG_DEBUG_FS */
+#endif	/* DLMDEBUG_H */
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 4f7695c..c137d69 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -33,6 +33,7 @@
 #include <linux/spinlock.h>
 #include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/debugfs.h>
 
 #include "cluster/heartbeat.h"
 #include "cluster/nodemanager.h"
@@ -40,8 +41,8 @@
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
-
 #include "dlmdomain.h"
+#include "dlmdebug.h"
 
 #include "dlmver.h"
 
@@ -298,6 +299,8 @@ static int dlm_wait_on_domain_helper(const char *domain)
 
 static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm)
 {
+	dlm_destroy_debugfs_subroot(dlm);
+
 	if (dlm->lockres_hash)
 		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
 
@@ -1494,6 +1497,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 				u32 key)
 {
 	int i;
+	int ret;
 	struct dlm_ctxt *dlm = NULL;
 
 	dlm = kzalloc(sizeof(*dlm), GFP_KERNEL);
@@ -1526,6 +1530,15 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char
*domain,
 	dlm->key = key;
 	dlm->node_num = o2nm_this_node();
 
+	ret = dlm_create_debugfs_subroot(dlm);
+	if (ret < 0) {
+		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
+		kfree(dlm->name);
+		kfree(dlm);
+		dlm = NULL;
+		goto leave;
+	}
+
 	spin_lock_init(&dlm->spinlock);
 	spin_lock_init(&dlm->master_lock);
 	spin_lock_init(&dlm->ast_lock);
@@ -1851,8 +1864,13 @@ static int __init dlm_init(void)
 		goto error;
 	}
 
+	status = dlm_create_debugfs_root();
+	if (status)
+		goto error;
+
 	return 0;
 error:
+	dlm_unregister_net_handlers();
 	dlm_destroy_lock_cache();
 	dlm_destroy_master_caches();
 	dlm_destroy_mle_cache();
@@ -1861,6 +1879,7 @@ error:
 
 static void __exit dlm_exit (void)
 {
+	dlm_destroy_debugfs_root();
 	dlm_unregister_net_handlers();
 	dlm_destroy_lock_cache();
 	dlm_destroy_master_caches();
-- 
1.5.3.6

This patch dumps all the lockres' on the purgelist it can fit in one page
into a debugfs file. Useful for debugging.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdebug.c |   71 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmdebug.h |    1 +
 2 files changed, 72 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 6de326b..a109005 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -303,6 +303,7 @@ static int stringify_lockname(const char *lockname, int
locklen,
 #define DLM_DEBUGFS_DLM_STATE			"dlm_state"
 #define DLM_DEBUGFS_LOCKING_STATE		"locking_state"
 #define DLM_DEBUGFS_MLE_STATE			"mle_state"
+#define DLM_DEBUGFS_PURGE_LIST			"purge_list"
 
 /* begin - utils funcs */
 static void dlm_debug_free(struct kref *kref)
@@ -396,6 +397,63 @@ static int debug_buffer_release(struct inode *inode, struct
file *file)
 }
 /* end - util funcs */
 
+/* begin - purge list funcs */
+static int debug_purgelist_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
+{
+	struct dlm_lock_resource *res;
+	int out = 0;
+	unsigned long total = 0;
+
+	out += snprintf(db->buf + out, db->len - out,
+			"Dumping Purgelist for Domain: %s\n", dlm->name);
+
+	spin_lock(&dlm->spinlock);
+	list_for_each_entry(res, &dlm->purge_list, purge) {
+		++total;
+		if (db->len - out < 100)
+			continue;
+		spin_lock(&res->spinlock);
+		out += stringify_lockname(res->lockname.name,
+					  res->lockname.len,
+					  db->buf + out, db->len - out);
+		out += snprintf(db->buf + out, db->len - out, "\t%ld\n",
+				(jiffies - res->last_used)/HZ);
+		spin_unlock(&res->spinlock);
+	}
+	spin_unlock(&dlm->spinlock);
+
+	out += snprintf(db->buf + out, db->len - out,
+			"Total on list: %ld\n", total);
+
+	return out;
+}
+
+static int debug_purgelist_open(struct inode *inode, struct file *file)
+{
+	struct dlm_ctxt *dlm = inode->i_private;
+	struct debug_buffer *db;
+
+	db = debug_buffer_allocate();
+	if (!db)
+		goto bail;
+
+	db->len = debug_purgelist_print(dlm, db);
+
+	file->private_data = db;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static struct file_operations debug_purgelist_fops = {
+	.open =		debug_purgelist_open,
+	.release =	debug_buffer_release,
+	.read =		debug_buffer_read,
+	.llseek =	debug_buffer_llseek,
+};
+/* end - purge list funcs */
+
 /* begin - debug mle funcs */
 static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
 {
@@ -906,6 +964,17 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
+	/* for dumping lockres on the purge list */
+	dc->debug_purgelist_dentry +			debugfs_create_file(DLM_DEBUGFS_PURGE_LIST,
+					    S_IFREG|S_IRUSR,
+					    dlm->dlm_debugfs_subroot,
+					    dlm, &debug_purgelist_fops);
+	if (!dc->debug_purgelist_dentry) {
+		mlog_errno(-ENOMEM);
+		goto bail;
+	}
+
 	dlm_debug_get(dc);
 	return 0;
 
@@ -919,6 +988,8 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
 
 	if (dc) {
+		if (dc->debug_purgelist_dentry)
+			debugfs_remove(dc->debug_purgelist_dentry);
 		if (dc->debug_mle_dentry)
 			debugfs_remove(dc->debug_mle_dentry);
 		if (dc->debug_lockres_dentry)
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index cbc69f2..8857743 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -32,6 +32,7 @@ struct dlm_debug_ctxt {
 	struct dentry *debug_state_dentry;
 	struct dentry *debug_lockres_dentry;
 	struct dentry *debug_mle_dentry;
+	struct dentry *debug_purgelist_dentry;
 };
 
 struct debug_buffer {
-- 
1.5.3.6

This patch links all the lockres' to a tracking list in dlm_ctxt.
We will use this in the upcoming patch that will walk the entire
list and to dump the lockres states to a debugfs file.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmcommon.h |    4 ++++
 fs/ocfs2/dlm/dlmdomain.c |   11 +++++++++++
 fs/ocfs2/dlm/dlmmaster.c |   11 +++++++++++
 3 files changed, 26 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 7525a8a..cc31abe 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -101,6 +101,7 @@ struct dlm_ctxt
 	struct list_head purge_list;
 	struct list_head pending_asts;
 	struct list_head pending_basts;
+	struct list_head tracking_list;
 	unsigned int purge_count;
 	spinlock_t spinlock;
 	spinlock_t ast_lock;
@@ -270,6 +271,9 @@ struct dlm_lock_resource
 	struct list_head dirty;
 	struct list_head recovering; // dlm_recovery_ctxt.resources list
 
+	/* Added during init and removed during release */
+	struct list_head tracking;	/* dlm->tracking_list */
+
 	/* unused lock resources have their last_used stamped and are
 	 * put on a list for the dlm thread to run. */
 	unsigned long    last_used;
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index b092364..4f7695c 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -644,6 +644,7 @@ int dlm_shutting_down(struct dlm_ctxt *dlm)
 void dlm_unregister_domain(struct dlm_ctxt *dlm)
 {
 	int leave = 0;
+	struct dlm_lock_resource *res;
 
 	spin_lock(&dlm_domain_lock);
 	BUG_ON(dlm->dlm_state != DLM_CTXT_JOINED);
@@ -673,6 +674,15 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm)
 			msleep(500);
 			mlog(0, "%s: more migration to do\n", dlm->name);
 		}
+
+		/* This list should be empty. If not, print remaining lockres */
+		if (!list_empty(&dlm->tracking_list)) {
+			mlog(ML_ERROR, "Following lockres' are still on the "
+			     "tracking list:\n");
+			list_for_each_entry(res, &dlm->tracking_list, tracking)
+				dlm_print_one_lock_resource(res);
+		}
+
 		dlm_mark_domain_leaving(dlm);
 		dlm_leave_domain(dlm);
 		dlm_complete_dlm_shutdown(dlm);
@@ -1526,6 +1536,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	INIT_LIST_HEAD(&dlm->reco.node_data);
 	INIT_LIST_HEAD(&dlm->purge_list);
 	INIT_LIST_HEAD(&dlm->dlm_domain_handlers);
+	INIT_LIST_HEAD(&dlm->tracking_list);
 	dlm->reco.state = 0;
 
 	INIT_LIST_HEAD(&dlm->pending_asts);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ac9ed31..9713346 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -639,6 +639,14 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+		     res->lockname.len, res->lockname.name);
+		dlm_print_one_lock_resource(res);
+	}
+
 	if (!hlist_unhashed(&res->hash_node) ||
 	    !list_empty(&res->granted) ||
 	    !list_empty(&res->converting) ||
@@ -706,6 +714,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	INIT_LIST_HEAD(&res->dirty);
 	INIT_LIST_HEAD(&res->recovering);
 	INIT_LIST_HEAD(&res->purge);
+	INIT_LIST_HEAD(&res->tracking);
 	atomic_set(&res->asts_reserved, 0);
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
@@ -721,6 +730,8 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 
 	res->last_used = 0;
 
+	list_add_tail(&res->tracking, &dlm->tracking_list);
+
 	memset(res->lvb, 0, DLM_LVB_LEN);
 	memset(res->refmap, 0, sizeof(res->refmap));
 }
-- 
1.5.3.6

This patch helps in consolidating debugging related functions in dlmdebug.c.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
---
 fs/ocfs2/dlm/dlmdebug.c  |  154 ++++++++++++++++++++++++---------------------
 fs/ocfs2/dlm/dlmdebug.h  |    2 +
 fs/ocfs2/dlm/dlmmaster.c |   89 +--------------------------
 3 files changed, 85 insertions(+), 160 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index a109005..58e4579 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -268,11 +268,6 @@ const char *dlm_errname(enum dlm_status err)
 }
 EXPORT_SYMBOL_GPL(dlm_errname);
 
-
-#ifdef CONFIG_DEBUG_FS
-
-static struct dentry *dlm_debugfs_root = NULL;
-
 /* NOTE: This function converts a lockname into a string. It uses knowledge
  * of the format of the lockname that should be outside the purview of the dlm.
  * We are adding only to make dlm debugging slightly easier.
@@ -299,6 +294,88 @@ static int stringify_lockname(const char *lockname, int
locklen,
 	return out;
 }
 
+static int stringify_nodemap(unsigned long *nodemap, int maxnodes,
+			     char *buf, int len)
+{
+	int out = 0;
+	int i = -1;
+
+	while ((i = find_next_bit(nodemap, maxnodes, i + 1)) < maxnodes)
+		out += snprintf(buf + out, len - out, "%d ", i);
+
+	return out;
+}
+
+static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
+{
+	int out = 0;
+	unsigned int namelen;
+	const char *name;
+	char *mle_type;
+
+	if (mle->type != DLM_MLE_MASTER) {
+		namelen = mle->u.name.len;
+		name = mle->u.name.name;
+	} else {
+		namelen = mle->u.res->lockname.len;
+		name = mle->u.res->lockname.name;
+	}
+
+	if (mle->type == DLM_MLE_BLOCK)
+		mle_type = "BLK";
+	else if (mle->type == DLM_MLE_MASTER)
+		mle_type = "MAS";
+	else
+		mle_type = "MIG";
+
+	out += stringify_lockname(name, namelen, buf + out, len - out);
+	out += snprintf(buf + out, len - out,
+			"\t%3s\tmas=%3u\tnew=%3u\tevt=%1d\tuse=%1d\tref=%3d\n",
+			mle_type, mle->master, mle->new_master,
+			!list_empty(&mle->hb_events),
+			!!mle->inuse,
+			atomic_read(&mle->mle_refs.refcount));
+
+	out += snprintf(buf + out, len - out, "Maybe=");
+	out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Vote=");
+	out += stringify_nodemap(mle->vote_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Response=");
+	out += stringify_nodemap(mle->response_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "Node=");
+	out += stringify_nodemap(mle->node_map, O2NM_MAX_NODES,
+				 buf + out, len - out);
+	out += snprintf(buf + out, len - out, "\n");
+
+	out += snprintf(buf + out, len - out, "\n");
+
+	return out;
+}
+
+void dlm_print_one_mle(struct dlm_master_list_entry *mle)
+{
+	char *buf;
+
+	buf = (char *) get_zeroed_page(GFP_NOFS);
+	if (buf) {
+		dump_mle(mle, buf, PAGE_SIZE - 1);
+		free_page((unsigned long)buf);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static struct dentry *dlm_debugfs_root = NULL;
+
 #define DLM_DEBUGFS_DIR				"o2dlm"
 #define DLM_DEBUGFS_DLM_STATE			"dlm_state"
 #define DLM_DEBUGFS_LOCKING_STATE		"locking_state"
@@ -326,18 +403,6 @@ static void dlm_debug_get(struct dlm_debug_ctxt *dc)
 	kref_get(&dc->debug_refcnt);
 }
 
-static int stringify_nodemap(unsigned long *nodemap, int maxnodes,
-			     char *buf, int len)
-{
-	int out = 0;
-	int i = -1;
-
-	while ((i = find_next_bit(nodemap, maxnodes, i + 1)) < maxnodes)
-		out += snprintf(buf + out, len - out, "%d ", i);
-
-	return out;
-}
-
 static struct debug_buffer *debug_buffer_allocate(void)
 {
 	struct debug_buffer *db = NULL;
@@ -455,61 +520,6 @@ static struct file_operations debug_purgelist_fops = {
 /* end - purge list funcs */
 
 /* begin - debug mle funcs */
-static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
-{
-	int out = 0;
-	unsigned int namelen;
-	const char *name;
-	char *mle_type;
-
-	if (mle->type != DLM_MLE_MASTER) {
-		namelen = mle->u.name.len;
-		name = mle->u.name.name;
-	} else {
-		namelen = mle->u.res->lockname.len;
-		name = mle->u.res->lockname.name;
-	}
-
-	if (mle->type == DLM_MLE_BLOCK)
-		mle_type = "BLK";
-	else if (mle->type == DLM_MLE_MASTER)
-		mle_type = "MAS";
-	else
-		mle_type = "MIG";
-
-	out += stringify_lockname(name, namelen, buf + out, len - out);
-	out += snprintf(buf + out, len - out,
-			"\t%3s\tmas=%3u\tnew=%3u\tevt=%1d\tuse=%1d\tref=%3d\n",
-			mle_type, mle->master, mle->new_master,
-			!list_empty(&mle->hb_events),
-			!!mle->inuse,
-			atomic_read(&mle->mle_refs.refcount));
-
-	out += snprintf(buf + out, len - out, "Maybe=");
-	out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES,
-				 buf + out, len - out);
-	out += snprintf(buf + out, len - out, "\n");
-
-	out += snprintf(buf + out, len - out, "Vote=");
-	out += stringify_nodemap(mle->vote_map, O2NM_MAX_NODES,
-				 buf + out, len - out);
-	out += snprintf(buf + out, len - out, "\n");
-
-	out += snprintf(buf + out, len - out, "Response=");
-	out += stringify_nodemap(mle->response_map, O2NM_MAX_NODES,
-				 buf + out, len - out);
-	out += snprintf(buf + out, len - out, "\n");
-
-	out += snprintf(buf + out, len - out, "Node=");
-	out += stringify_nodemap(mle->node_map, O2NM_MAX_NODES,
-				 buf + out, len - out);
-	out += snprintf(buf + out, len - out, "\n");
-
-	out += snprintf(buf + out, len - out, "\n");
-
-	return out;
-}
-
 static int debug_mle_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
 {
 	struct dlm_master_list_entry *mle;
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index 8857743..d34a62a 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -25,6 +25,8 @@
 #ifndef DLMDEBUG_H
 #define DLMDEBUG_H
 
+void dlm_print_one_mle(struct dlm_master_list_entry *mle);
+
 #ifdef CONFIG_DEBUG_FS
 
 struct dlm_debug_ctxt {
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 94cadcb..efc015c 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -48,6 +48,7 @@
 #include "dlmapi.h"
 #include "dlmcommon.h"
 #include "dlmdomain.h"
+#include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
 #include "cluster/masklog.h"
@@ -91,94 +92,6 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm,
 	return 1;
 }
 
-#define dlm_print_nodemap(m)  _dlm_print_nodemap(m,#m)
-static void _dlm_print_nodemap(unsigned long *map, const char *mapname)
-{
-	int i;
-	printk("%s=[ ", mapname);
-	for (i=0; i<O2NM_MAX_NODES; i++)
-		if (test_bit(i, map))
-			printk("%d ", i);
-	printk("]");
-}
-
-static void dlm_print_one_mle(struct dlm_master_list_entry *mle)
-{
-	int refs;
-	char *type;
-	char attached;
-	u8 master;
-	unsigned int namelen;
-	const char *name;
-	struct kref *k;
-	unsigned long *maybe = mle->maybe_map,
-		      *vote = mle->vote_map,
-		      *resp = mle->response_map,
-		      *node = mle->node_map;
-
-	k = &mle->mle_refs;
-	if (mle->type == DLM_MLE_BLOCK)
-		type = "BLK";
-	else if (mle->type == DLM_MLE_MASTER)
-		type = "MAS";
-	else
-		type = "MIG";
-	refs = atomic_read(&k->refcount);
-	master = mle->master;
-	attached = (list_empty(&mle->hb_events) ? 'N' : 'Y');
-
-	if (mle->type != DLM_MLE_MASTER) {
-		namelen = mle->u.name.len;
-		name = mle->u.name.name;
-	} else {
-		namelen = mle->u.res->lockname.len;
-		name = mle->u.res->lockname.name;
-	}
-
-	mlog(ML_NOTICE, "%.*s: %3s refs=%3d mas=%3u new=%3u evt=%c inuse=%d
",
-		  namelen, name, type, refs, master, mle->new_master, attached,
-		  mle->inuse);
-	dlm_print_nodemap(maybe);
-	printk(", ");
-	dlm_print_nodemap(vote);
-	printk(", ");
-	dlm_print_nodemap(resp);
-	printk(", ");
-	dlm_print_nodemap(node);
-	printk(", ");
-	printk("\n");
-}
-
-#if 0
-/* Code here is included but defined out as it aids debugging */
-
-static void dlm_dump_mles(struct dlm_ctxt *dlm)
-{
-	struct dlm_master_list_entry *mle;
-	
-	mlog(ML_NOTICE, "dumping all mles for domain %s:\n", dlm->name);
-	spin_lock(&dlm->master_lock);
-	list_for_each_entry(mle, &dlm->master_list, list)
-		dlm_print_one_mle(mle);
-	spin_unlock(&dlm->master_lock);
-}
-
-int dlm_dump_all_mles(const char __user *data, unsigned int len)
-{
-	struct dlm_ctxt *dlm;
-
-	spin_lock(&dlm_domain_lock);
-	list_for_each_entry(dlm, &dlm_domains, list) {
-		mlog(ML_NOTICE, "found dlm: %p, name=%s\n", dlm, dlm->name);
-		dlm_dump_mles(dlm);
-	}
-	spin_unlock(&dlm_domain_lock);
-	return len;
-}
-EXPORT_SYMBOL_GPL(dlm_dump_all_mles);
-
-#endif  /*  0  */
-
 static struct kmem_cache *dlm_lockres_cache = NULL;
 static struct kmem_cache *dlm_lockname_cache = NULL;
 static struct kmem_cache *dlm_mle_cache = NULL;
-- 
1.5.3.6

This patch renames dlm_mle_slabcache to prevent namespace clashes with fs/dlm.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdomain.c |    4 +++-
 fs/ocfs2/dlm/dlmmaster.c |    2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 0879d86..2ce6207 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1816,8 +1816,10 @@ static int __init dlm_init(void)
 	dlm_print_version();
 
 	status = dlm_init_mle_cache();
-	if (status)
+	if (status) {
+		mlog(ML_ERROR, "Could not create o2dlm_mle slabcache\n");
 		return -1;
+	}
 
 	status = dlm_register_net_handlers();
 	if (status) {
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ea6b895..90797c5 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -507,7 +507,7 @@ static void dlm_mle_node_up(struct dlm_ctxt *dlm,
 
 int dlm_init_mle_cache(void)
 {
-	dlm_mle_cache = kmem_cache_create("dlm_mle_cache",
+	dlm_mle_cache = kmem_cache_create("o2dlm_mle",
 					  sizeof(struct dlm_master_list_entry),
 					  0, SLAB_HWCACHE_ALIGN,
 					  NULL);
-- 
1.5.3.6

This patch makes the o2dlm allocate memory for lockres, lockname and lock
structures from slabcaches rather than kmalloc. This allows us to not only
make these allocs more efficient but also allows us to track the memory being
consumed by these structures.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmcommon.h |    7 +++++
 fs/ocfs2/dlm/dlmdomain.c |   26 +++++++++++++++++--
 fs/ocfs2/dlm/dlmlock.c   |   22 +++++++++++++++-
 fs/ocfs2/dlm/dlmmaster.c |   61 +++++++++++++++++++++++++++++++++++++---------
 4 files changed, 99 insertions(+), 17 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index dc8ea66..7525a8a 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -963,9 +963,16 @@ static inline void __dlm_wait_on_lockres(struct
dlm_lock_resource *res)
 					  DLM_LOCK_RES_MIGRATING));
 }
 
+/* create/destroy slab caches */
+int dlm_init_master_caches(void);
+void dlm_destroy_master_caches(void);
+
+int dlm_init_lock_cache(void);
+void dlm_destroy_lock_cache(void);
 
 int dlm_init_mle_cache(void);
 void dlm_destroy_mle_cache(void);
+
 void dlm_hb_event_notify_attached(struct dlm_ctxt *dlm, int idx, int node_up);
 int dlm_drop_lockres_ref(struct dlm_ctxt *dlm,
 			 struct dlm_lock_resource *res);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ce6207..b092364 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1818,21 +1818,41 @@ static int __init dlm_init(void)
 	status = dlm_init_mle_cache();
 	if (status) {
 		mlog(ML_ERROR, "Could not create o2dlm_mle slabcache\n");
-		return -1;
+		goto error;
+	}
+
+	status = dlm_init_master_caches();
+	if (status) {
+		mlog(ML_ERROR, "Could not create o2dlm_lockres and "
+		     "o2dlm_lockname slabcaches\n");
+		goto error;
+	}
+
+	status = dlm_init_lock_cache();
+	if (status) {
+		mlog(ML_ERROR, "Count not create o2dlm_lock slabcache\n");
+		goto error;
 	}
 
 	status = dlm_register_net_handlers();
 	if (status) {
-		dlm_destroy_mle_cache();
-		return -1;
+		mlog(ML_ERROR, "Unable to register network handlers\n");
+		goto error;
 	}
 
 	return 0;
+error:
+	dlm_destroy_lock_cache();
+	dlm_destroy_master_caches();
+	dlm_destroy_mle_cache();
+	return -1;
 }
 
 static void __exit dlm_exit (void)
 {
 	dlm_unregister_net_handlers();
+	dlm_destroy_lock_cache();
+	dlm_destroy_master_caches();
 	dlm_destroy_mle_cache();
 }
 
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 52578d9..83a9f29 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -53,6 +53,8 @@
 #define MLOG_MASK_PREFIX ML_DLM
 #include "cluster/masklog.h"
 
+static struct kmem_cache *dlm_lock_cache = NULL;
+
 static DEFINE_SPINLOCK(dlm_cookie_lock);
 static u64 dlm_next_cookie = 1;
 
@@ -64,6 +66,22 @@ static void dlm_init_lock(struct dlm_lock *newlock, int type,
 static void dlm_lock_release(struct kref *kref);
 static void dlm_lock_detach_lockres(struct dlm_lock *lock);
 
+int dlm_init_lock_cache(void)
+{
+	dlm_lock_cache = kmem_cache_create("o2dlm_lock",
+					   sizeof(struct dlm_lock),
+					   0, SLAB_HWCACHE_ALIGN, NULL);
+	if (dlm_lock_cache == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void dlm_destroy_lock_cache(void)
+{
+	if (dlm_lock_cache)
+		kmem_cache_destroy(dlm_lock_cache);
+}
+
 /* Tell us whether we can grant a new lock request.
  * locking:
  *   caller needs:  res->spinlock
@@ -353,7 +371,7 @@ static void dlm_lock_release(struct kref *kref)
 		mlog(0, "freeing kernel-allocated lksb\n");
 		kfree(lock->lksb);
 	}
-	kfree(lock);
+	kmem_cache_free(dlm_lock_cache, lock);
 }
 
 /* associate a lock with it's lockres, getting a ref on the lockres */
@@ -412,7 +430,7 @@ struct dlm_lock * dlm_new_lock(int type, u8 node, u64
cookie,
 	struct dlm_lock *lock;
 	int kernel_allocated = 0;
 
-	lock = kzalloc(sizeof(*lock), GFP_NOFS);
+	lock = (struct dlm_lock *) kmem_cache_zalloc(dlm_lock_cache, GFP_NOFS);
 	if (!lock)
 		return NULL;
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 90797c5..ac9ed31 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -216,10 +216,10 @@ EXPORT_SYMBOL_GPL(dlm_dump_all_mles);
 
 #endif  /*  0  */
 
-
+static struct kmem_cache *dlm_lockres_cache = NULL;
+static struct kmem_cache *dlm_lockname_cache = NULL;
 static struct kmem_cache *dlm_mle_cache = NULL;
 
-
 static void dlm_mle_release(struct kref *kref);
 static void dlm_init_mle(struct dlm_master_list_entry *mle,
 			enum dlm_mle_type type,
@@ -560,6 +560,35 @@ static void dlm_mle_release(struct kref *kref)
  * LOCK RESOURCE FUNCTIONS
  */
 
+int dlm_init_master_caches(void)
+{
+	dlm_lockres_cache = kmem_cache_create("o2dlm_lockres",
+					      sizeof(struct dlm_lock_resource),
+					      0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!dlm_lockres_cache)
+		goto bail;
+
+	dlm_lockname_cache = kmem_cache_create("o2dlm_lockname",
+					       DLM_LOCKID_NAME_MAX, 0,
+					       SLAB_HWCACHE_ALIGN, NULL);
+	if (!dlm_lockname_cache)
+		goto bail;
+
+	return 0;
+bail:
+	dlm_destroy_master_caches();
+	return -ENOMEM;
+}
+
+void dlm_destroy_master_caches(void)
+{
+	if (dlm_lockname_cache)
+		kmem_cache_destroy(dlm_lockname_cache);
+
+	if (dlm_lockres_cache)
+		kmem_cache_destroy(dlm_lockres_cache);
+}
+
 static void dlm_set_lockres_owner(struct dlm_ctxt *dlm,
 				  struct dlm_lock_resource *res,
 				  u8 owner)
@@ -642,9 +671,9 @@ static void dlm_lockres_release(struct kref *kref)
 	BUG_ON(!list_empty(&res->recovering));
 	BUG_ON(!list_empty(&res->purge));
 
-	kfree(res->lockname.name);
+	kmem_cache_free(dlm_lockname_cache, (void *)res->lockname.name);
 
-	kfree(res);
+	kmem_cache_free(dlm_lockres_cache, res);
 }
 
 void dlm_lockres_put(struct dlm_lock_resource *res)
@@ -700,20 +729,28 @@ struct dlm_lock_resource *dlm_new_lockres(struct dlm_ctxt
*dlm,
 				   const char *name,
 				   unsigned int namelen)
 {
-	struct dlm_lock_resource *res;
+	struct dlm_lock_resource *res = NULL;
 
-	res = kmalloc(sizeof(struct dlm_lock_resource), GFP_NOFS);
+	res = (struct dlm_lock_resource *)
+				kmem_cache_zalloc(dlm_lockres_cache, GFP_NOFS);
 	if (!res)
-		return NULL;
+		goto error;
 
-	res->lockname.name = kmalloc(namelen, GFP_NOFS);
-	if (!res->lockname.name) {
-		kfree(res);
-		return NULL;
-	}
+	res->lockname.name = (char *)
+				kmem_cache_zalloc(dlm_lockname_cache, GFP_NOFS);
+	if (!res->lockname.name)
+		goto error;
 
 	dlm_init_lockres(dlm, res, name, namelen);
 	return res;
+
+error:
+	if (res && res->lockname.name)
+		kmem_cache_free(dlm_lockname_cache, (void *)res->lockname.name);
+
+	if (res)
+		kmem_cache_free(dlm_lockres_cache, res);
+	return NULL;
 }
 
 void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
-- 
1.5.3.6

This patch moves some mle related definitions from dlmmaster.c
to dlmcommon.h. Future patches need these definitions to dump mle
debugging information.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.beckeroracle.com>
---
 fs/ocfs2/dlm/dlmcommon.h |   35 +++++++++++++++++++++++++++++++++++
 fs/ocfs2/dlm/dlmmaster.c |   37 -------------------------------------
 2 files changed, 35 insertions(+), 37 deletions(-)

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index f7a51ca..d5a86fb 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -49,6 +49,41 @@
 /* Intended to make it easier for us to switch out hash functions */
 #define dlm_lockid_hash(_n, _l) full_name_hash(_n, _l)
 
+enum dlm_mle_type {
+	DLM_MLE_BLOCK,
+	DLM_MLE_MASTER,
+	DLM_MLE_MIGRATION
+};
+
+struct dlm_lock_name {
+	u8 len;
+	u8 name[DLM_LOCKID_NAME_MAX];
+};
+
+struct dlm_master_list_entry {
+	struct list_head list;
+	struct list_head hb_events;
+	struct dlm_ctxt *dlm;
+	spinlock_t spinlock;
+	wait_queue_head_t wq;
+	atomic_t woken;
+	struct kref mle_refs;
+	int inuse;
+	unsigned long maybe_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long vote_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long response_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long node_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	u8 master;
+	u8 new_master;
+	enum dlm_mle_type type;
+	struct o2hb_callback_func mle_hb_up;
+	struct o2hb_callback_func mle_hb_down;
+	union {
+		struct dlm_lock_resource *res;
+		struct dlm_lock_name name;
+	} u;
+};
+
 enum dlm_ast_type {
 	DLM_AST = 0,
 	DLM_BAST,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9713346..94cadcb 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -52,43 +52,6 @@
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
 #include "cluster/masklog.h"
 
-enum dlm_mle_type {
-	DLM_MLE_BLOCK,
-	DLM_MLE_MASTER,
-	DLM_MLE_MIGRATION
-};
-
-struct dlm_lock_name
-{
-	u8 len;
-	u8 name[DLM_LOCKID_NAME_MAX];
-};
-
-struct dlm_master_list_entry
-{
-	struct list_head list;
-	struct list_head hb_events;
-	struct dlm_ctxt *dlm;
-	spinlock_t spinlock;
-	wait_queue_head_t wq;
-	atomic_t woken;
-	struct kref mle_refs;
-	int inuse;
-	unsigned long maybe_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long vote_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long response_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long node_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	u8 master;
-	u8 new_master;
-	enum dlm_mle_type type;
-	struct o2hb_callback_func mle_hb_up;
-	struct o2hb_callback_func mle_hb_down;
-	union {
-		struct dlm_lock_resource *res;
-		struct dlm_lock_name name;
-	} u;
-};
-
 static void dlm_mle_node_down(struct dlm_ctxt *dlm,
 			      struct dlm_master_list_entry *mle,
 			      struct o2nm_node *node,
-- 
1.5.3.6

On Mon, Mar 10, 2008 at 03:16:22PM -0700, Sunil Mushran
wrote:
> This patch creates the debugfs directories that will hold the
> files to be used to dump the dlm state.
> 
> Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
> ---
>  fs/ocfs2/dlm/dlmcommon.h |    2 +
>  fs/ocfs2/dlm/dlmdebug.c  |   50 +++++++++++++++++++++++++++++++++++++++++-
>  fs/ocfs2/dlm/dlmdebug.h  |   54
++++++++++++++++++++++++++++++++++++++++++++++
>  fs/ocfs2/dlm/dlmdomain.c |   21 +++++++++++++++++-
>  4 files changed, 125 insertions(+), 2 deletions(-)
>  create mode 100644 fs/ocfs2/dlm/dlmdebug.h
> 
> diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
> index cc31abe..6a49140 100644
> --- a/fs/ocfs2/dlm/dlmcommon.h
> +++ b/fs/ocfs2/dlm/dlmcommon.h
> @@ -123,6 +123,8 @@ struct dlm_ctxt
>  	atomic_t remote_resources;
>  	atomic_t unknown_resources;
>  
> +	struct dentry *dlm_debugfs_subroot;
> +
>  	/* NOTE: Next three are protected by dlm_domain_lock */
>  	struct kref dlm_refs;
>  	enum dlm_ctxt_state dlm_state;
> diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
> index 64239b3..62e2a4c 100644
> --- a/fs/ocfs2/dlm/dlmdebug.c
> +++ b/fs/ocfs2/dlm/dlmdebug.c
> @@ -30,6 +30,7 @@
>  #include <linux/utsname.h>
>  #include <linux/sysctl.h>
>  #include <linux/spinlock.h>
> +#include <linux/debugfs.h>
>  
>  #include "cluster/heartbeat.h"
>  #include "cluster/nodemanager.h"
> @@ -37,8 +38,8 @@
>  
>  #include "dlmapi.h"
>  #include "dlmcommon.h"
> -
>  #include "dlmdomain.h"
> +#include "dlmdebug.h"
>  
>  #define MLOG_MASK_PREFIX ML_DLM
>  #include "cluster/masklog.h"
> @@ -266,3 +267,50 @@ const char *dlm_errname(enum dlm_status err)
>  	return dlm_errnames[err];
>  }
>  EXPORT_SYMBOL_GPL(dlm_errname);
> +
> +
> +#ifdef CONFIG_DEBUG_FS
> +
> +static struct dentry *dlm_debugfs_root = NULL;
> +
> +#define DLM_DEBUGFS_DIR				"o2dlm"
> +
> +/* subroot - domain dir */
> +int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
> +{
> +	dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name,
> +						      dlm_debugfs_root);
> +	if (!dlm->dlm_debugfs_subroot) {
> +		mlog_errno(-ENOMEM);
> +		goto bail;
> +	}
> +
> +	return 0;
> +bail:
> +	dlm_destroy_debugfs_subroot(dlm);
> +	return -ENOMEM;
> +}
> +
> +void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
> +{
> +	if (dlm->dlm_debugfs_subroot)
> +		debugfs_remove(dlm->dlm_debugfs_subroot);
> +}
> +
> +/* debugfs root */
> +int dlm_create_debugfs_root(void)
> +{
> +	dlm_debugfs_root = debugfs_create_dir(DLM_DEBUGFS_DIR, NULL);
> +	if (!dlm_debugfs_root) {
> +		mlog_errno(-ENOMEM);
> +		return -ENOMEM;
> +	}
> +	return 0;
> +}
> +
> +void dlm_destroy_debugfs_root(void)
> +{
> +	if (dlm_debugfs_root)
> +		debugfs_remove(dlm_debugfs_root);
> +}
> +#endif	/* CONFIG_DEBUG_FS */
> diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
> new file mode 100644
> index 0000000..b969595
> --- /dev/null
> +++ b/fs/ocfs2/dlm/dlmdebug.h
> @@ -0,0 +1,54 @@
> +/* -*- mode: c; c-basic-offset: 8; -*-
> + * vim: noexpandtab sw=8 ts=8 sts=0:
> + *
> + * dlmdebug.h
> + *
> + * Copyright (C) 2008 Oracle.  All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public
> + * License as published by the Free Software Foundation; either
> + * version 2 of the License, or (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
> + * General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public
> + * License along with this program; if not, write to the
> + * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
> + * Boston, MA 021110-1307, USA.
> + *
> + */
> +
> +#ifndef DLMDEBUG_H
> +#define DLMDEBUG_H
> +
> +#ifdef CONFIG_DEBUG_FS
> +
> +int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm);
> +void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm);
> +
> +int dlm_create_debugfs_root(void);
> +void dlm_destroy_debugfs_root(void);
> +
> +#else
> +
> +static int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
> +{
> +	return 0;
> +}
> +static void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
> +{
> +}
> +static int dlm_create_debugfs_root(void)
> +{
> +	return 0;
> +}
> +static void dlm_destroy_debugfs_root(void)
> +{
> +}
> +
> +#endif	/* CONFIG_DEBUG_FS */
> +#endif	/* DLMDEBUG_H */
> diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
> index 4f7695c..c137d69 100644
> --- a/fs/ocfs2/dlm/dlmdomain.c
> +++ b/fs/ocfs2/dlm/dlmdomain.c
> @@ -33,6 +33,7 @@
>  #include <linux/spinlock.h>
>  #include <linux/delay.h>
>  #include <linux/err.h>
> +#include <linux/debugfs.h>
>  
>  #include "cluster/heartbeat.h"
>  #include "cluster/nodemanager.h"
> @@ -40,8 +41,8 @@
>  
>  #include "dlmapi.h"
>  #include "dlmcommon.h"
> -
>  #include "dlmdomain.h"
> +#include "dlmdebug.h"
>  
>  #include "dlmver.h"
>  
> @@ -298,6 +299,8 @@ static int dlm_wait_on_domain_helper(const char
*domain)
>  
>  static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm)
>  {
> +	dlm_destroy_debugfs_subroot(dlm);
> +
>  	if (dlm->lockres_hash)
>  		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
>  
> @@ -1494,6 +1497,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char
*domain,
>  				u32 key)
>  {
>  	int i;
> +	int ret;
>  	struct dlm_ctxt *dlm = NULL;
>  
>  	dlm = kzalloc(sizeof(*dlm), GFP_KERNEL);
> @@ -1526,6 +1530,15 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char
*domain,
>  	dlm->key = key;
>  	dlm->node_num = o2nm_this_node();
>  
> +	ret = dlm_create_debugfs_subroot(dlm);
> +	if (ret < 0) {
> +		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
> +		kfree(dlm->name);
> +		kfree(dlm);
> +		dlm = NULL;
> +		goto leave;
> +	}
> +
>  	spin_lock_init(&dlm->spinlock);
>  	spin_lock_init(&dlm->master_lock);
>  	spin_lock_init(&dlm->ast_lock);
> @@ -1851,8 +1864,13 @@ static int __init dlm_init(void)
>  		goto error;
>  	}
>  
> +	status = dlm_create_debugfs_root();
> +	if (status)
> +		goto error;
> +
>  	return 0;
>  error:
> +	dlm_unregister_net_handlers();
>  	dlm_destroy_lock_cache();
>  	dlm_destroy_master_caches();
>  	dlm_destroy_mle_cache();
> @@ -1861,6 +1879,7 @@ error:
>  
>  static void __exit dlm_exit (void)
>  {
> +	dlm_destroy_debugfs_root();
>  	dlm_unregister_net_handlers();
>  	dlm_destroy_lock_cache();
>  	dlm_destroy_master_caches();
> -- 
> 1.5.3.6
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-devel
-- 

"What do you take me for, an idiot?"  
        - General Charles de Gaulle, when a journalist asked him
          if he was happy.

Joel Becker
Principal Software Developer
Oracle
E-mail: joel.becker@oracle.com
Phone: (650) 506-8127

On Mon, Mar 10, 2008 at 03:16:23PM -0700, Sunil Mushran
wrote:
> This patch dumps the dlm state (dlm_ctxt) into a debugfs file.
> Useful for debugging.
> 
> Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
> ---
>  fs/ocfs2/dlm/dlmcommon.h |    1 +
>  fs/ocfs2/dlm/dlmdebug.c  |  296
++++++++++++++++++++++++++++++++++++++++++++++
>  fs/ocfs2/dlm/dlmdebug.h  |   20 +++
>  fs/ocfs2/dlm/dlmdomain.c |    8 ++
>  4 files changed, 325 insertions(+), 0 deletions(-)
> 
> diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
> index 6a49140..f7a51ca 100644
> --- a/fs/ocfs2/dlm/dlmcommon.h
> +++ b/fs/ocfs2/dlm/dlmcommon.h
> @@ -123,6 +123,7 @@ struct dlm_ctxt
>  	atomic_t remote_resources;
>  	atomic_t unknown_resources;
>  
> +	struct dlm_debug_ctxt *dlm_debug_ctxt;
>  	struct dentry *dlm_debugfs_subroot;
>  
>  	/* NOTE: Next three are protected by dlm_domain_lock */
> diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
> index 62e2a4c..e335403 100644
> --- a/fs/ocfs2/dlm/dlmdebug.c
> +++ b/fs/ocfs2/dlm/dlmdebug.c
> @@ -274,6 +274,294 @@ EXPORT_SYMBOL_GPL(dlm_errname);
>  static struct dentry *dlm_debugfs_root = NULL;
>  
>  #define DLM_DEBUGFS_DIR				"o2dlm"
> +#define DLM_DEBUGFS_DLM_STATE			"dlm_state"
> +
> +/* begin - utils funcs */
> +static void dlm_debug_free(struct kref *kref)
> +{
> +	struct dlm_debug_ctxt *dc;
> +
> +	dc = container_of(kref, struct dlm_debug_ctxt, debug_refcnt);
> +
> +	kfree(dc);
> +}
> +
> +void dlm_debug_put(struct dlm_debug_ctxt *dc)
> +{
> +	if (dc)
> +		kref_put(&dc->debug_refcnt, dlm_debug_free);
> +}
> +
> +static void dlm_debug_get(struct dlm_debug_ctxt *dc)
> +{
> +	kref_get(&dc->debug_refcnt);
> +}
> +
> +static int stringify_nodemap(unsigned long *nodemap, int maxnodes,
> +			     char *buf, int len)
> +{
> +	int out = 0;
> +	int i = -1;
> +
> +	while ((i = find_next_bit(nodemap, maxnodes, i + 1)) < maxnodes)
> +		out += snprintf(buf + out, len - out, "%d ", i);
> +
> +	return out;
> +}
> +
> +static struct debug_buffer *debug_buffer_allocate(void)
> +{
> +	struct debug_buffer *db = NULL;
> +
> +	db = kzalloc(sizeof(struct debug_buffer), GFP_KERNEL);
> +	if (!db)
> +		goto bail;
> +
> +	db->len = PAGE_SIZE;
> +	db->buf = kmalloc(db->len, GFP_KERNEL);
> +	if (!db->buf)
> +		goto bail;
> +
> +	return db;
> +bail:
> +	kfree(db);
> +	return NULL;
> +}
> +
> +static ssize_t debug_buffer_read(struct file *file, char __user *buf,
> +				 size_t nbytes, loff_t *ppos)
> +{
> +	struct debug_buffer *db = file->private_data;
> +
> +	return simple_read_from_buffer(buf, nbytes, ppos, db->buf,
db->len);
> +}
> +
> +static loff_t debug_buffer_llseek(struct file *file, loff_t off, int
whence)
> +{
> +	struct debug_buffer *db = file->private_data;
> +	loff_t new = -1;
> +
> +	switch (whence) {
> +	case 0:
> +		new = off;
> +		break;
> +	case 1:
> +		new = file->f_pos + off;
> +		break;
> +	}
> +
> +	if (new < 0 || new > db->len)
> +		return -EINVAL;
> +
> +	return (file->f_pos = new);
> +}
> +
> +static int debug_buffer_release(struct inode *inode, struct file *file)
> +{
> +	struct debug_buffer *db = (struct debug_buffer *)file->private_data;
> +
> +	if (db)
> +		kfree(db->buf);
> +	kfree(db);
> +
> +	return 0;
> +}
> +/* end - util funcs */
> +
> +/* begin - debug state funcs */
> +static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer
*db)
> +{
> +	int out = 0;
> +	struct dlm_reco_node_data *node;
> +	char *state;
> +	int lres, rres, ures, tres;
> +
> +	lres = atomic_read(&dlm->local_resources);
> +	rres = atomic_read(&dlm->remote_resources);
> +	ures = atomic_read(&dlm->unknown_resources);
> +	tres = lres + rres + ures;
> +
> +	spin_lock(&dlm->spinlock);
> +
> +	switch (dlm->dlm_state) {
> +	case DLM_CTXT_NEW:
> +		state = "NEW"; break;
> +	case DLM_CTXT_JOINED:
> +		state = "JOINED"; break;
> +	case DLM_CTXT_IN_SHUTDOWN:
> +		state = "SHUTDOWN"; break;
> +	case DLM_CTXT_LEAVING:
> +		state = "LEAVING"; break;
> +	default:
> +		state = "UNKNOWN"; break;
> +	}
> +
> +	/* Domain: xxxxxxxxxx  Key: 0xdfbac769 */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Domain: %s  Key: 0x%08x\n", dlm->name, dlm->key);
> +
> +	/* Thread Pid: xxx  Node: xxx  State: xxxxx */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Thread Pid: %d  Node: %d  State: %s\n",
> +			dlm->dlm_thread_task->pid, dlm->node_num, state);
> +
> +	/* Number of Joins: xxx  Joining Node: xxx */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Number of Joins: %d  Joining Node: %d\n",
> +			dlm->num_joins, dlm->joining_node);
> +
> +	/* Domain Map: xx xx xx */
> +	out += snprintf(db->buf + out, db->len - out, "Domain Map:
");
> +	out += stringify_nodemap(dlm->domain_map, O2NM_MAX_NODES,
> +				 db->buf + out, db->len - out);
> +	out += snprintf(db->buf + out, db->len - out, "\n");
> +
> +	/* Live Map: xx xx xx */
> +	out += snprintf(db->buf + out, db->len - out, "Live Map:
");
> +	out += stringify_nodemap(dlm->live_nodes_map, O2NM_MAX_NODES,
> +				 db->buf + out, db->len - out);
> +	out += snprintf(db->buf + out, db->len - out, "\n");
> +
> +	/* Mastered Resources Total: xxx  Locally: xxx  Remotely: ... */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Mastered Resources Total: %d  Locally: %d  "
> +			"Remotely: %d  Unknown: %d\n",
> +			tres, lres, rres, ures);
> +
> +	/* Lists: Dirty=Empty  Purge=InUse  PendingASTs=Empty  ... */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Lists: Dirty=%s  Purge=%s  PendingASTs=%s  "
> +			"PendingBASTs=%s  Master=%s\n",
> +			(list_empty(&dlm->dirty_list) ? "Empty" :
"InUse"),
> +			(list_empty(&dlm->purge_list) ? "Empty" :
"InUse"),
> +			(list_empty(&dlm->pending_asts) ? "Empty" :
"InUse"),
> +			(list_empty(&dlm->pending_basts) ? "Empty" :
"InUse"),
> +			(list_empty(&dlm->master_list) ? "Empty" :
"InUse"));
> +
> +	/* Purge Count: xxx  Refs: xxx */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Purge Count: %d  Refs: %d\n", dlm->purge_count,
> +			atomic_read(&dlm->dlm_refs.refcount));
> +
> +	/* Dead Node: xxx */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Dead Node: %d\n", dlm->reco.dead_node);
> +
> +	/* What about DLM_RECO_STATE_FINALIZE? */
> +	if (dlm->reco.state == DLM_RECO_STATE_ACTIVE)
> +		state = "ACTIVE";
> +	else
> +		state = "INACTIVE";
> +
> +	/* Recovery Pid: xxxx  Master: xxx  State: xxxx */
> +	out += snprintf(db->buf + out, db->len - out,
> +			"Recovery Pid: %d  Master: %d  State: %s\n",
> +			dlm->dlm_reco_thread_task->pid,
> +			dlm->reco.new_master, state);
> +
> +	/* Recovery Map: xx xx */
> +	out += snprintf(db->buf + out, db->len - out, "Recovery Map:
");
> +	out += stringify_nodemap(dlm->recovery_map, O2NM_MAX_NODES,
> +				 db->buf + out, db->len - out);
> +	out += snprintf(db->buf + out, db->len - out, "\n");
> +
> +	/* Recovery Node State: */
> +	out += snprintf(db->buf + out, db->len - out, "Recovery Node
State:\n");
> +	list_for_each_entry(node, &dlm->reco.node_data, list) {
> +		switch (node->state) {
> +		case DLM_RECO_NODE_DATA_INIT:
> +			state = "INIT";
> +			break;
> +		case DLM_RECO_NODE_DATA_REQUESTING:
> +			state = "REQUESTING";
> +			break;
> +		case DLM_RECO_NODE_DATA_DEAD:
> +			state = "DEAD";
> +			break;
> +		case DLM_RECO_NODE_DATA_RECEIVING:
> +			state = "RECEIVING";
> +			break;
> +		case DLM_RECO_NODE_DATA_REQUESTED:
> +			state = "REQUESTED";
> +			break;
> +		case DLM_RECO_NODE_DATA_DONE:
> +			state = "DONE";
> +			break;
> +		case DLM_RECO_NODE_DATA_FINALIZE_SENT:
> +			state = "FINALIZE-SENT";
> +			break;
> +		default:
> +			state = "BAD";
> +			break;
> +		}
> +		out += snprintf(db->buf + out, db->len - out, "\t%u -
%s\n",
> +				node->node_num, state);
> +	}
> +
> +	spin_unlock(&dlm->spinlock);
> +
> +	return out;
> +}
> +
> +static int debug_state_open(struct inode *inode, struct file *file)
> +{
> +	struct dlm_ctxt *dlm = inode->i_private;
> +	struct debug_buffer *db = NULL;
> +
> +	db = debug_buffer_allocate();
> +	if (!db)
> +		goto bail;
> +
> +	db->len = debug_state_print(dlm, db);
> +
> +	file->private_data = db;
> +
> +	return 0;
> +bail:
> +	return -ENOMEM;
> +}
> +
> +static struct file_operations debug_state_fops = {
> +	.open =		debug_state_open,
> +	.release =	debug_buffer_release,
> +	.read =		debug_buffer_read,
> +	.llseek =	debug_buffer_llseek,
> +};
> +/* end  - debug state funcs */
> +
> +/* files in subroot */
> +int dlm_debug_init(struct dlm_ctxt *dlm)
> +{
> +	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
> +
> +	/* for dumping dlm_ctxt */
> +	dc->debug_state_dentry = debugfs_create_file(DLM_DEBUGFS_DLM_STATE,
> +						     S_IFREG|S_IRUSR,
> +						     dlm->dlm_debugfs_subroot,
> +						     dlm, &debug_state_fops);
> +	if (!dc->debug_state_dentry) {
> +		mlog_errno(-ENOMEM);
> +		goto bail;
> +	}
> +
> +	dlm_debug_get(dc);
> +	return 0;
> +
> +bail:
> +	dlm_debug_shutdown(dlm);
> +	return -ENOMEM;
> +}
> +
> +void dlm_debug_shutdown(struct dlm_ctxt *dlm)
> +{
> +	struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
> +
> +	if (dc) {
> +		if (dc->debug_state_dentry)
> +			debugfs_remove(dc->debug_state_dentry);
> +		dlm_debug_put(dc);
> +	}
> +}
>  
>  /* subroot - domain dir */
>  int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
> @@ -285,6 +573,14 @@ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
>  		goto bail;
>  	}
>  
> +	dlm->dlm_debug_ctxt = kzalloc(sizeof(struct dlm_debug_ctxt),
> +				      GFP_KERNEL);
> +	if (!dlm->dlm_debug_ctxt) {
> +		mlog_errno(-ENOMEM);
> +		goto bail;
> +	}
> +	kref_init(&dlm->dlm_debug_ctxt->debug_refcnt);
> +
>  	return 0;
>  bail:
>  	dlm_destroy_debugfs_subroot(dlm);
> diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
> index b969595..94cc10a 100644
> --- a/fs/ocfs2/dlm/dlmdebug.h
> +++ b/fs/ocfs2/dlm/dlmdebug.h
> @@ -27,6 +27,19 @@
>  
>  #ifdef CONFIG_DEBUG_FS
>  
> +struct dlm_debug_ctxt {
> +	struct kref debug_refcnt;
> +	struct dentry *debug_state_dentry;
> +};
> +
> +struct debug_buffer {
> +	int len;
> +	char *buf;
> +};
> +
> +int dlm_debug_init(struct dlm_ctxt *dlm);
> +void dlm_debug_shutdown(struct dlm_ctxt *dlm);
> +
>  int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm);
>  void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm);
>  
> @@ -35,6 +48,13 @@ void dlm_destroy_debugfs_root(void);
>  
>  #else
>  
> +static int dlm_debug_init(struct dlm_ctxt *dlm)
> +{
> +	return 0;
> +}
> +static void dlm_debug_shutdown(struct dlm_ctxt *dlm)
> +{
> +}
>  static int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
>  {
>  	return 0;
> diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
> index c137d69..63f8125 100644
> --- a/fs/ocfs2/dlm/dlmdomain.c
> +++ b/fs/ocfs2/dlm/dlmdomain.c
> @@ -398,6 +398,7 @@ static void dlm_destroy_dlm_worker(struct dlm_ctxt
*dlm)
>  static void dlm_complete_dlm_shutdown(struct dlm_ctxt *dlm)
>  {
>  	dlm_unregister_domain_handlers(dlm);
> +	dlm_debug_shutdown(dlm);
>  	dlm_complete_thread(dlm);
>  	dlm_complete_recovery_thread(dlm);
>  	dlm_destroy_dlm_worker(dlm);
> @@ -1418,6 +1419,12 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
>  		goto bail;
>  	}
>  
> +	status = dlm_debug_init(dlm);
> +	if (status < 0) {
> +		mlog_errno(status);
> +		goto bail;
> +	}
> +
>  	status = dlm_launch_thread(dlm);
>  	if (status < 0) {
>  		mlog_errno(status);
> @@ -1485,6 +1492,7 @@ bail:
>  
>  	if (status) {
>  		dlm_unregister_domain_handlers(dlm);
> +		dlm_debug_shutdown(dlm);
>  		dlm_complete_thread(dlm);
>  		dlm_complete_recovery_thread(dlm);
>  		dlm_destroy_dlm_worker(dlm);
> -- 
> 1.5.3.6
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-devel
-- 

"Any man who is under 30, and is not a liberal, has not heart;
 and any man who is over 30, and is not a conservative, has no brains."
         - Sir Winston Churchill 

Joel Becker
Principal Software Developer
Oracle
E-mail: joel.becker@oracle.com
Phone: (650) 506-8127

On Mon, Mar 10, 2008 at 03:16:18PM -0700, Sunil Mushran
wrote:
> The following patches follow:
Ok, these are all in ocfs2.git now.
	--Mark

> 
> [PATCH 01/11] ocfs2/dlm: Rename slabcache dlm_mle_cache to o2dlm_mle
> [PATCH 02/11] ocfs2/dlm: Creates slabcaches for lock and lockres
> [PATCH 03/11] ocfs2/dlm: Link all lockres' to a tracking list
> [PATCH 04/11] ocfs2/dlm: Create debugfs dirs
> [PATCH 05/11] ocfs2/dlm: Dump the dlm state in a debugfs file
> [PATCH 06/11] ocfs2/dlm: Dumps the lockres' into a debugfs file
> [PATCH 07/11] ocfs2/dlm: Move struct dlm_master_list_entry to dlmcommon.h
> [PATCH 08/11] ocfs2/dlm: Dumps the mles into a debugfs file
> [PATCH 09/11] ocfs2/dlm: Dumps the purgelist into a debugfs file
> [PATCH 10/11] ocfs2/dlm: Move dlm_print_one_mle() from dlmmaster.c to
dlmdebug.c
> [PATCH 11/11] ocfs2/dlm: Fix lockname in lockres print function
> 
> Changes suggested by Joel Becker have been incorporated.
> 
> This patch series has been tested with ocfs2.git upstream-linus branch.
> 
> Sunil
> 
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel@oss.oracle.com
> http://oss.oracle.com/mailman/listinfo/ocfs2-devel
--
Mark Fasheh
Principal Software Developer, Oracle
mark.fasheh@oracle.com