[DLM] The core of the DLM for GFS2/CLVM

This is the core of the distributed lock manager which is required
to use GFS2 as a cluster filesystem. It is also used by CLVM and
can be used as a standalone lock manager independantly of either
of these two projects.

It implements VAX-style locking modes.
Signed-off-by: NDavid Teigland <teigland@redhat.com>
Signed-off-by: NSteve Whitehouse <swhiteho@redhat.com>

fs/Kconfig

@@ -1831,6 +1831,7 @@ source "fs/partitions/Kconfig"
 endmenu
 
 source "fs/nls/Kconfig"
+source "fs/dlm/Kconfig"
 
 endmenu
 

fs/Makefile

@@ -48,6 +48,7 @@ obj-$(CONFIG_SYSFS)		+= sysfs/
 obj-y				+= devpts/
 
 obj-$(CONFIG_PROFILING)		+= dcookies.o
+obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/

fs/dlm/Kconfig

+menu "Distributed Lock Manager"
+	depends on INET && EXPERIMENTAL
+
+config DLM
+	tristate "Distributed Lock Manager (DLM)"
+	depends on SYSFS
+	depends on IPV6 || IPV6=n
+	select IP_SCTP
+	select CONFIGFS_FS
+	help
+	A general purpose distributed lock manager for kernel or userspace
+	applications.
+
+config DLM_DEVICE
+	tristate "DLM device for userspace access"
+	depends on DLM
+	help
+	This module creates a misc device through which the dlm lockspace
+	and locking functions become available to userspace applications
+	(usually through the libdlm library).
+
+config DLM_DEBUG
+	bool "DLM debugging"
+	depends on DLM
+	help
+	Under the debugfs mount point, the name of each lockspace will
+	appear as a file in the "dlm" directory.  The output is the
+	list of resource and locks the local node knows about.
+
+endmenu

fs/dlm/Makefile

+obj-$(CONFIG_DLM) +=		dlm.o
+obj-$(CONFIG_DLM_DEVICE) +=	dlm_device.o
+
+dlm-y :=			ast.o \
+				config.o \
+				dir.o \
+				lock.o \
+				lockspace.o \
+				lowcomms.o \
+				main.o \
+				member.o \
+				memory.o \
+				midcomms.o \
+				rcom.o \
+				recover.o \
+				recoverd.o \
+				requestqueue.o \
+				util.o
+dlm-$(CONFIG_DLM_DEBUG) +=	debug_fs.o
+
+dlm_device-y :=			device.o

fs/dlm/ast.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lock.h"
+#include "ast.h"
+
+#define WAKE_ASTS  0
+
+static struct list_head		ast_queue;
+static spinlock_t		ast_queue_lock;
+static struct task_struct *	astd_task;
+static unsigned long		astd_wakeflags;
+static struct semaphore		astd_running;
+
+
+void dlm_del_ast(struct dlm_lkb *lkb)
+{
+	spin_lock(&ast_queue_lock);
+	if (lkb->lkb_ast_type & (AST_COMP | AST_BAST))
+		list_del(&lkb->lkb_astqueue);
+	spin_unlock(&ast_queue_lock);
+}
+
+void dlm_add_ast(struct dlm_lkb *lkb, int type)
+{
+	spin_lock(&ast_queue_lock);
+	if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+		kref_get(&lkb->lkb_ref);
+		list_add_tail(&lkb->lkb_astqueue, &ast_queue);
+	}
+	lkb->lkb_ast_type |= type;
+	spin_unlock(&ast_queue_lock);
+
+	set_bit(WAKE_ASTS, &astd_wakeflags);
+	wake_up_process(astd_task);
+}
+
+static void process_asts(void)
+{
+	struct dlm_ls *ls = NULL;
+	struct dlm_rsb *r = NULL;
+	struct dlm_lkb *lkb;
+	void (*cast) (long param);
+	void (*bast) (long param, int mode);
+	int type = 0, found, bmode;
+
+	for (;;) {
+		found = FALSE;
+		spin_lock(&ast_queue_lock);
+		list_for_each_entry(lkb, &ast_queue, lkb_astqueue) {
+			r = lkb->lkb_resource;
+			ls = r->res_ls;
+
+			if (dlm_locking_stopped(ls))
+				continue;
+
+			list_del(&lkb->lkb_astqueue);
+			type = lkb->lkb_ast_type;
+			lkb->lkb_ast_type = 0;
+			found = TRUE;
+			break;
+		}
+		spin_unlock(&ast_queue_lock);
+
+		if (!found)
+			break;
+
+		cast = lkb->lkb_astaddr;
+		bast = lkb->lkb_bastaddr;
+		bmode = lkb->lkb_bastmode;
+
+		if ((type & AST_COMP) && cast)
+			cast(lkb->lkb_astparam);
+
+		/* FIXME: Is it safe to look at lkb_grmode here
+		   without doing a lock_rsb() ?
+		   Look at other checks in v1 to avoid basts. */
+
+		if ((type & AST_BAST) && bast)
+			if (!dlm_modes_compat(lkb->lkb_grmode, bmode))
+				bast(lkb->lkb_astparam, bmode);
+
+		/* this removes the reference added by dlm_add_ast
+		   and may result in the lkb being freed */
+		dlm_put_lkb(lkb);
+
+		schedule();
+	}
+}
+
+static inline int no_asts(void)
+{
+	int ret;
+
+	spin_lock(&ast_queue_lock);
+	ret = list_empty(&ast_queue);
+	spin_unlock(&ast_queue_lock);
+	return ret;
+}
+
+static int dlm_astd(void *data)
+{
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!test_bit(WAKE_ASTS, &astd_wakeflags))
+			schedule();
+		set_current_state(TASK_RUNNING);
+
+		down(&astd_running);
+		if (test_and_clear_bit(WAKE_ASTS, &astd_wakeflags))
+			process_asts();
+		up(&astd_running);
+	}
+	return 0;
+}
+
+void dlm_astd_wake(void)
+{
+	if (!no_asts()) {
+		set_bit(WAKE_ASTS, &astd_wakeflags);
+		wake_up_process(astd_task);
+	}
+}
+
+int dlm_astd_start(void)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	INIT_LIST_HEAD(&ast_queue);
+	spin_lock_init(&ast_queue_lock);
+	init_MUTEX(&astd_running);
+
+	p = kthread_run(dlm_astd, NULL, "dlm_astd");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+		astd_task = p;
+	return error;
+}
+
+void dlm_astd_stop(void)
+{
+	kthread_stop(astd_task);
+}
+
+void dlm_astd_suspend(void)
+{
+	down(&astd_running);
+}
+
+void dlm_astd_resume(void)
+{
+	up(&astd_running);
+}
+

fs/dlm/ast.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __ASTD_DOT_H__
+#define __ASTD_DOT_H__
+
+void dlm_add_ast(struct dlm_lkb *lkb, int type);
+void dlm_del_ast(struct dlm_lkb *lkb);
+
+void dlm_astd_wake(void);
+int dlm_astd_start(void);
+void dlm_astd_stop(void);
+void dlm_astd_suspend(void);
+void dlm_astd_resume(void);
+
+#endif
+

fs/dlm/config.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/configfs.h>
+#include <net/sock.h>
+
+#include "config.h"
+
+/*
+ * /config/dlm/<cluster>/spaces/<space>/nodes/<node>/nodeid
+ * /config/dlm/<cluster>/spaces/<space>/nodes/<node>/weight
+ * /config/dlm/<cluster>/comms/<comm>/nodeid
+ * /config/dlm/<cluster>/comms/<comm>/local
+ * /config/dlm/<cluster>/comms/<comm>/addr
+ * The <cluster> level is useless, but I haven't figured out how to avoid it.
+ */
+
+static struct config_group *space_list;
+static struct config_group *comm_list;
+static struct comm *local_comm;
+
+struct clusters;
+struct cluster;
+struct spaces;
+struct space;
+struct comms;
+struct comm;
+struct nodes;
+struct node;
+
+static struct config_group *make_cluster(struct config_group *, const char *);
+static void drop_cluster(struct config_group *, struct config_item *);
+static void release_cluster(struct config_item *);
+static struct config_group *make_space(struct config_group *, const char *);
+static void drop_space(struct config_group *, struct config_item *);
+static void release_space(struct config_item *);
+static struct config_item *make_comm(struct config_group *, const char *);
+static void drop_comm(struct config_group *, struct config_item *);
+static void release_comm(struct config_item *);
+static struct config_item *make_node(struct config_group *, const char *);
+static void drop_node(struct config_group *, struct config_item *);
+static void release_node(struct config_item *);
+
+static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
+			 char *buf);
+static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len);
+static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
+			 char *buf);
+static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len);
+
+static ssize_t comm_nodeid_read(struct comm *cm, char *buf);
+static ssize_t comm_nodeid_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t comm_local_read(struct comm *cm, char *buf);
+static ssize_t comm_local_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t comm_addr_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t node_nodeid_read(struct node *nd, char *buf);
+static ssize_t node_nodeid_write(struct node *nd, const char *buf, size_t len);
+static ssize_t node_weight_read(struct node *nd, char *buf);
+static ssize_t node_weight_write(struct node *nd, const char *buf, size_t len);
+
+enum {
+	COMM_ATTR_NODEID = 0,
+	COMM_ATTR_LOCAL,
+	COMM_ATTR_ADDR,
+};
+
+struct comm_attribute {
+	struct configfs_attribute attr;
+	ssize_t (*show)(struct comm *, char *);
+	ssize_t (*store)(struct comm *, const char *, size_t);
+};
+
+static struct comm_attribute comm_attr_nodeid = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "nodeid",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = comm_nodeid_read,
+	.store  = comm_nodeid_write,
+};
+
+static struct comm_attribute comm_attr_local = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "local",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = comm_local_read,
+	.store  = comm_local_write,
+};
+
+static struct comm_attribute comm_attr_addr = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "addr",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.store  = comm_addr_write,
+};
+
+static struct configfs_attribute *comm_attrs[] = {
+	[COMM_ATTR_NODEID] = &comm_attr_nodeid.attr,
+	[COMM_ATTR_LOCAL] = &comm_attr_local.attr,
+	[COMM_ATTR_ADDR] = &comm_attr_addr.attr,
+	NULL,
+};
+
+enum {
+	NODE_ATTR_NODEID = 0,
+	NODE_ATTR_WEIGHT,
+};
+
+struct node_attribute {
+	struct configfs_attribute attr;
+	ssize_t (*show)(struct node *, char *);
+	ssize_t (*store)(struct node *, const char *, size_t);
+};
+
+static struct node_attribute node_attr_nodeid = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "nodeid",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = node_nodeid_read,
+	.store  = node_nodeid_write,
+};
+
+static struct node_attribute node_attr_weight = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "weight",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = node_weight_read,
+	.store  = node_weight_write,
+};
+
+static struct configfs_attribute *node_attrs[] = {
+	[NODE_ATTR_NODEID] = &node_attr_nodeid.attr,
+	[NODE_ATTR_WEIGHT] = &node_attr_weight.attr,
+	NULL,
+};
+
+struct clusters {
+	struct configfs_subsystem subsys;
+};
+
+struct cluster {
+	struct config_group group;
+};
+
+struct spaces {
+	struct config_group ss_group;
+};
+
+struct space {
+	struct config_group group;
+	struct list_head members;
+	struct semaphore members_lock;
+	int members_count;
+};
+
+struct comms {
+	struct config_group cs_group;
+};
+
+struct comm {
+	struct config_item item;
+	int nodeid;
+	int local;
+	int addr_count;
+	struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
+};
+
+struct nodes {
+	struct config_group ns_group;
+};
+
+struct node {
+	struct config_item item;
+	struct list_head list; /* space->members */
+	int nodeid;
+	int weight;
+};
+
+static struct configfs_group_operations clusters_ops = {
+	.make_group = make_cluster,
+	.drop_item = drop_cluster,
+};
+
+static struct configfs_item_operations cluster_ops = {
+	.release = release_cluster,
+};
+
+static struct configfs_group_operations spaces_ops = {
+	.make_group = make_space,
+	.drop_item = drop_space,
+};
+
+static struct configfs_item_operations space_ops = {
+	.release = release_space,
+};
+
+static struct configfs_group_operations comms_ops = {
+	.make_item = make_comm,
+	.drop_item = drop_comm,
+};
+
+static struct configfs_item_operations comm_ops = {
+	.release = release_comm,
+	.show_attribute = show_comm,
+	.store_attribute = store_comm,
+};
+
+static struct configfs_group_operations nodes_ops = {
+	.make_item = make_node,
+	.drop_item = drop_node,
+};
+
+static struct configfs_item_operations node_ops = {
+	.release = release_node,
+	.show_attribute = show_node,
+	.store_attribute = store_node,
+};
+
+static struct config_item_type clusters_type = {
+	.ct_group_ops = &clusters_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type cluster_type = {
+	.ct_item_ops = &cluster_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type spaces_type = {
+	.ct_group_ops = &spaces_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type space_type = {
+	.ct_item_ops = &space_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type comms_type = {
+	.ct_group_ops = &comms_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type comm_type = {
+	.ct_item_ops = &comm_ops,
+	.ct_attrs = comm_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type nodes_type = {
+	.ct_group_ops = &nodes_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type node_type = {
+	.ct_item_ops = &node_ops,
+	.ct_attrs = node_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct cluster *to_cluster(struct config_item *i)
+{
+	return i ? container_of(to_config_group(i), struct cluster, group):NULL;
+}
+
+static struct space *to_space(struct config_item *i)
+{
+	return i ? container_of(to_config_group(i), struct space, group) : NULL;
+}
+
+static struct comm *to_comm(struct config_item *i)
+{
+	return i ? container_of(i, struct comm, item) : NULL;
+}
+
+static struct node *to_node(struct config_item *i)
+{
+	return i ? container_of(i, struct node, item) : NULL;
+}
+
+static struct config_group *make_cluster(struct config_group *g,
+					 const char *name)
+{
+	struct cluster *cl = NULL;
+	struct spaces *sps = NULL;
+	struct comms *cms = NULL;
+	void *gps = NULL;
+
+	cl = kzalloc(sizeof(struct cluster), GFP_KERNEL);
+	gps = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
+	sps = kzalloc(sizeof(struct spaces), GFP_KERNEL);
+	cms = kzalloc(sizeof(struct comms), GFP_KERNEL);
+
+	if (!cl || !gps || !sps || !cms)
+		goto fail;
+
+	config_group_init_type_name(&cl->group, name, &cluster_type);
+	config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type);
+	config_group_init_type_name(&cms->cs_group, "comms", &comms_type);
+
+	cl->group.default_groups = gps;
+	cl->group.default_groups[0] = &sps->ss_group;
+	cl->group.default_groups[1] = &cms->cs_group;
+	cl->group.default_groups[2] = NULL;
+
+	space_list = &sps->ss_group;
+	comm_list = &cms->cs_group;
+	return &cl->group;
+
+ fail:
+	kfree(cl);
+	kfree(gps);
+	kfree(sps);
+	kfree(cms);
+	return NULL;
+}
+
+static void drop_cluster(struct config_group *g, struct config_item *i)
+{
+	struct cluster *cl = to_cluster(i);
+	struct config_item *tmp;
+	int j;
+
+	for (j = 0; cl->group.default_groups[j]; j++) {
+		tmp = &cl->group.default_groups[j]->cg_item;
+		cl->group.default_groups[j] = NULL;
+		config_item_put(tmp);
+	}
+
+	space_list = NULL;
+	comm_list = NULL;
+
+	config_item_put(i);
+}
+
+static void release_cluster(struct config_item *i)
+{
+	struct cluster *cl = to_cluster(i);
+	kfree(cl->group.default_groups);
+	kfree(cl);
+}
+
+static struct config_group *make_space(struct config_group *g, const char *name)
+{
+	struct space *sp = NULL;
+	struct nodes *nds = NULL;
+	void *gps = NULL;
+
+	sp = kzalloc(sizeof(struct space), GFP_KERNEL);
+	gps = kcalloc(2, sizeof(struct config_group *), GFP_KERNEL);
+	nds = kzalloc(sizeof(struct nodes), GFP_KERNEL);
+
+	if (!sp || !gps || !nds)
+		goto fail;
+
+	config_group_init_type_name(&sp->group, name, &space_type);
+	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
+
+	sp->group.default_groups = gps;
+	sp->group.default_groups[0] = &nds->ns_group;
+	sp->group.default_groups[1] = NULL;
+
+	INIT_LIST_HEAD(&sp->members);
+	init_MUTEX(&sp->members_lock);
+	sp->members_count = 0;
+	return &sp->group;
+
+ fail:
+	kfree(sp);
+	kfree(gps);
+	kfree(nds);
+	return NULL;
+}
+
+static void drop_space(struct config_group *g, struct config_item *i)
+{
+	struct space *sp = to_space(i);
+	struct config_item *tmp;
+	int j;
+
+	/* assert list_empty(&sp->members) */
+
+	for (j = 0; sp->group.default_groups[j]; j++) {
+		tmp = &sp->group.default_groups[j]->cg_item;
+		sp->group.default_groups[j] = NULL;
+		config_item_put(tmp);
+	}
+
+	config_item_put(i);
+}
+
+static void release_space(struct config_item *i)
+{
+	struct space *sp = to_space(i);
+	kfree(sp->group.default_groups);
+	kfree(sp);
+}
+
+static struct config_item *make_comm(struct config_group *g, const char *name)
+{
+	struct comm *cm;
+
+	cm = kzalloc(sizeof(struct comm), GFP_KERNEL);
+	if (!cm)
+		return NULL;
+
+	config_item_init_type_name(&cm->item, name, &comm_type);
+	cm->nodeid = -1;
+	cm->local = 0;
+	cm->addr_count = 0;
+	return &cm->item;
+}
+
+static void drop_comm(struct config_group *g, struct config_item *i)
+{
+	struct comm *cm = to_comm(i);
+	if (local_comm == cm)
+		local_comm = NULL;
+	while (cm->addr_count--)
+		kfree(cm->addr[cm->addr_count]);
+	config_item_put(i);
+}
+
+static void release_comm(struct config_item *i)
+{
+	struct comm *cm = to_comm(i);
+	kfree(cm);
+}
+
+static struct config_item *make_node(struct config_group *g, const char *name)
+{
+	struct space *sp = to_space(g->cg_item.ci_parent);
+	struct node *nd;
+
+	nd = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!nd)
+		return NULL;
+
+	config_item_init_type_name(&nd->item, name, &node_type);
+	nd->nodeid = -1;
+	nd->weight = 1;  /* default weight of 1 if none is set */
+
+	down(&sp->members_lock);
+	list_add(&nd->list, &sp->members);
+	sp->members_count++;
+	up(&sp->members_lock);
+
+	return &nd->item;
+}
+
+static void drop_node(struct config_group *g, struct config_item *i)
+{
+	struct space *sp = to_space(g->cg_item.ci_parent);
+	struct node *nd = to_node(i);
+
+	down(&sp->members_lock);
+	list_del(&nd->list);
+	sp->members_count--;
+	up(&sp->members_lock);
+
+	config_item_put(i);
+}
+
+static void release_node(struct config_item *i)
+{
+	struct node *nd = to_node(i);
+	kfree(nd);
+}
+
+static struct clusters clusters_root = {
+	.subsys = {
+		.su_group = {
+			.cg_item = {
+				.ci_namebuf = "dlm",
+				.ci_type = &clusters_type,
+			},
+		},
+	},
+};
+
+int dlm_config_init(void)
+{
+	config_group_init(&clusters_root.subsys.su_group);
+	init_MUTEX(&clusters_root.subsys.su_sem);
+	return configfs_register_subsystem(&clusters_root.subsys);
+}
+
+void dlm_config_exit(void)
+{
+	configfs_unregister_subsystem(&clusters_root.subsys);
+}
+
+/*
+ * Functions for user space to read/write attributes
+ */
+
+static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
+			 char *buf)
+{
+	struct comm *cm = to_comm(i);
+	struct comm_attribute *cma =
+			container_of(a, struct comm_attribute, attr);
+	return cma->show ? cma->show(cm, buf) : 0;
+}
+
+static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len)
+{
+	struct comm *cm = to_comm(i);
+	struct comm_attribute *cma =
+		container_of(a, struct comm_attribute, attr);
+	return cma->store ? cma->store(cm, buf, len) : -EINVAL;
+}
+
+static ssize_t comm_nodeid_read(struct comm *cm, char *buf)
+{
+	return sprintf(buf, "%d\n", cm->nodeid);
+}
+
+static ssize_t comm_nodeid_write(struct comm *cm, const char *buf, size_t len)
+{
+	cm->nodeid = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+static ssize_t comm_local_read(struct comm *cm, char *buf)
+{
+	return sprintf(buf, "%d\n", cm->local);
+}
+
+static ssize_t comm_local_write(struct comm *cm, const char *buf, size_t len)
+{
+	cm->local= simple_strtol(buf, NULL, 0);
+	if (cm->local && !local_comm)
+		local_comm = cm;
+	return len;
+}
+
+static ssize_t comm_addr_write(struct comm *cm, const char *buf, size_t len)
+{
+	struct sockaddr_storage *addr;
+
+	if (len != sizeof(struct sockaddr_storage))
+		return -EINVAL;
+
+	if (cm->addr_count >= DLM_MAX_ADDR_COUNT)
+		return -ENOSPC;
+
+	addr = kzalloc(sizeof(*addr), GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+
+	memcpy(addr, buf, len);
+	cm->addr[cm->addr_count++] = addr;
+	return len;
+}
+
+static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
+			 char *buf)
+{
+	struct node *nd = to_node(i);
+	struct node_attribute *nda =
+			container_of(a, struct node_attribute, attr);
+	return nda->show ? nda->show(nd, buf) : 0;
+}
+
+static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len)
+{
+	struct node *nd = to_node(i);
+	struct node_attribute *nda =
+		container_of(a, struct node_attribute, attr);
+	return nda->store ? nda->store(nd, buf, len) : -EINVAL;
+}
+
+static ssize_t node_nodeid_read(struct node *nd, char *buf)
+{
+	return sprintf(buf, "%d\n", nd->nodeid);
+}
+
+static ssize_t node_nodeid_write(struct node *nd, const char *buf, size_t len)
+{
+	nd->nodeid = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+static ssize_t node_weight_read(struct node *nd, char *buf)
+{
+	return sprintf(buf, "%d\n", nd->weight);
+}
+
+static ssize_t node_weight_write(struct node *nd, const char *buf, size_t len)
+{
+	nd->weight = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+/*
+ * Functions for the dlm to get the info that's been configured
+ */
+
+static struct space *get_space(char *name)
+{
+	if (!space_list)
+		return NULL;
+	return to_space(config_group_find_obj(space_list, name));
+}
+
+static void put_space(struct space *sp)
+{
+	config_item_put(&sp->group.cg_item);
+}
+
+static struct comm *get_comm(int nodeid, struct sockaddr_storage *addr)
+{
+	struct config_item *i;
+	struct comm *cm = NULL;
+	int found = 0;
+
+	if (!comm_list)
+		return NULL;
+
+	down(&clusters_root.subsys.su_sem);
+
+	list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
+		cm = to_comm(i);
+
+		if (nodeid) {
+			if (cm->nodeid != nodeid)
+				continue;
+			found = 1;
+			break;
+		} else {
+			if (!cm->addr_count ||
+			    memcmp(cm->addr[0], addr, sizeof(*addr)))
+				continue;
+			found = 1;
+			break;
+		}
+	}
+	up(&clusters_root.subsys.su_sem);
+
+	if (found)
+		config_item_get(i);
+	else
+		cm = NULL;
+	return cm;
+}
+
+static void put_comm(struct comm *cm)
+{
+	config_item_put(&cm->item);
+}
+
+/* caller must free mem */
+int dlm_nodeid_list(char *lsname, int **ids_out)
+{
+	struct space *sp;
+	struct node *nd;
+	int i = 0, rv = 0;
+	int *ids;
+
+	sp = get_space(lsname);
+	if (!sp)
+		return -EEXIST;
+
+	down(&sp->members_lock);
+	if (!sp->members_count) {
+		rv = 0;
+		goto out;
+	}
+
+	ids = kcalloc(sp->members_count, sizeof(int), GFP_KERNEL);
+	if (!ids) {
+		rv = -ENOMEM;
+		goto out;
+	}
+
+	rv = sp->members_count;
+	list_for_each_entry(nd, &sp->members, list)
+		ids[i++] = nd->nodeid;
+
+	if (rv != i)
+		printk("bad nodeid count %d %d\n", rv, i);
+
+	*ids_out = ids;
+ out:
+	up(&sp->members_lock);
+	put_space(sp);
+	return rv;
+}
+
+int dlm_node_weight(char *lsname, int nodeid)
+{
+	struct space *sp;
+	struct node *nd;
+	int w = -EEXIST;
+
+	sp = get_space(lsname);
+	if (!sp)
+		goto out;
+
+	down(&sp->members_lock);
+	list_for_each_entry(nd, &sp->members, list) {
+		if (nd->nodeid != nodeid)
+			continue;
+		w = nd->weight;
+		break;
+	}
+	up(&sp->members_lock);
+	put_space(sp);
+ out:
+	return w;
+}
+
+int dlm_nodeid_to_addr(int nodeid, struct sockaddr_storage *addr)
+{
+	struct comm *cm = get_comm(nodeid, NULL);
+	if (!cm)
+		return -EEXIST;
+	if (!cm->addr_count)
+		return -ENOENT;
+	memcpy(addr, cm->addr[0], sizeof(*addr));
+	put_comm(cm);
+	return 0;
+}
+
+int dlm_addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
+{
+	struct comm *cm = get_comm(0, addr);
+	if (!cm)
+		return -EEXIST;
+	*nodeid = cm->nodeid;
+	put_comm(cm);
+	return 0;
+}
+
+int dlm_our_nodeid(void)
+{
+	return local_comm ? local_comm->nodeid : 0;
+}
+
+/* num 0 is first addr, num 1 is second addr */
+int dlm_our_addr(struct sockaddr_storage *addr, int num)
+{
+	if (!local_comm)
+		return -1;
+	if (num + 1 > local_comm->addr_count)
+		return -1;
+	memcpy(addr, local_comm->addr[num], sizeof(*addr));
+	return 0;
+}
+
+/* Config file defaults */
+#define DEFAULT_TCP_PORT       21064
+#define DEFAULT_BUFFER_SIZE     4096
+#define DEFAULT_RSBTBL_SIZE      256
+#define DEFAULT_LKBTBL_SIZE     1024
+#define DEFAULT_DIRTBL_SIZE      512
+#define DEFAULT_RECOVER_TIMER      5
+#define DEFAULT_TOSS_SECS         10
+#define DEFAULT_SCAN_SECS          5
+
+struct dlm_config_info dlm_config = {
+	.tcp_port = DEFAULT_TCP_PORT,
+	.buffer_size = DEFAULT_BUFFER_SIZE,
+	.rsbtbl_size = DEFAULT_RSBTBL_SIZE,
+	.lkbtbl_size = DEFAULT_LKBTBL_SIZE,
+	.dirtbl_size = DEFAULT_DIRTBL_SIZE,
+	.recover_timer = DEFAULT_RECOVER_TIMER,
+	.toss_secs = DEFAULT_TOSS_SECS,
+	.scan_secs = DEFAULT_SCAN_SECS
+};
+

fs/dlm/config.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __CONFIG_DOT_H__
+#define __CONFIG_DOT_H__
+
+#define DLM_MAX_ADDR_COUNT 3
+
+struct dlm_config_info {
+	int tcp_port;
+	int buffer_size;
+	int rsbtbl_size;
+	int lkbtbl_size;
+	int dirtbl_size;
+	int recover_timer;
+	int toss_secs;
+	int scan_secs;
+};
+
+extern struct dlm_config_info dlm_config;
+
+int dlm_config_init(void);
+void dlm_config_exit(void);
+int dlm_node_weight(char *lsname, int nodeid);
+int dlm_nodeid_list(char *lsname, int **ids_out);
+int dlm_nodeid_to_addr(int nodeid, struct sockaddr_storage *addr);
+int dlm_addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid);
+int dlm_our_nodeid(void);
+int dlm_our_addr(struct sockaddr_storage *addr, int num);
+
+#endif				/* __CONFIG_DOT_H__ */
+

fs/dlm/debug_fs.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+
+#include "dlm_internal.h"
+
+
+static struct dentry *dlm_root;
+
+struct rsb_iter {
+	int entry;
+	struct dlm_ls *ls;
+	struct list_head *next;
+	struct dlm_rsb *rsb;
+};
+
+static char *print_lockmode(int mode)
+{
+	switch (mode) {
+	case DLM_LOCK_IV:
+		return "--";
+	case DLM_LOCK_NL:
+		return "NL";
+	case DLM_LOCK_CR:
+		return "CR";
+	case DLM_LOCK_CW:
+		return "CW";
+	case DLM_LOCK_PR:
+		return "PR";
+	case DLM_LOCK_PW:
+		return "PW";
+	case DLM_LOCK_EX:
+		return "EX";
+	default:
+		return "??";
+	}
+}
+
+static void print_lock(struct seq_file *s, struct dlm_lkb *lkb,
+		       struct dlm_rsb *res)
+{
+	seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode));
+
+	if (lkb->lkb_status == DLM_LKSTS_CONVERT
+	    || lkb->lkb_status == DLM_LKSTS_WAITING)
+		seq_printf(s, " (%s)", print_lockmode(lkb->lkb_rqmode));
+
+	if (lkb->lkb_range) {
+		/* FIXME: this warns on Alpha */
+		if (lkb->lkb_status == DLM_LKSTS_CONVERT
+		    || lkb->lkb_status == DLM_LKSTS_GRANTED)
+			seq_printf(s, " %" PRIx64 "-%" PRIx64,
+				   lkb->lkb_range[GR_RANGE_START],
+				   lkb->lkb_range[GR_RANGE_END]);
+		if (lkb->lkb_status == DLM_LKSTS_CONVERT
+		    || lkb->lkb_status == DLM_LKSTS_WAITING)
+			seq_printf(s, " (%" PRIx64 "-%" PRIx64 ")",
+				   lkb->lkb_range[RQ_RANGE_START],
+				   lkb->lkb_range[RQ_RANGE_END]);
+	}
+
+	if (lkb->lkb_nodeid) {
+		if (lkb->lkb_nodeid != res->res_nodeid)
+			seq_printf(s, " Remote: %3d %08x", lkb->lkb_nodeid,
+				   lkb->lkb_remid);
+		else
+			seq_printf(s, " Master:     %08x", lkb->lkb_remid);
+	}
+
+	if (lkb->lkb_wait_type)
+		seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
+
+	seq_printf(s, "\n");
+}
+
+static int print_resource(struct dlm_rsb *res, struct seq_file *s)
+{
+	struct dlm_lkb *lkb;
+	int i, lvblen = res->res_ls->ls_lvblen;
+
+	seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length);
+	for (i = 0; i < res->res_length; i++) {
+		if (isprint(res->res_name[i]))
+			seq_printf(s, "%c", res->res_name[i]);
+		else
+			seq_printf(s, "%c", '.');
+	}
+	if (res->res_nodeid > 0)
+		seq_printf(s, "\"  \nLocal Copy, Master is node %d\n",
+			   res->res_nodeid);
+	else if (res->res_nodeid == 0)
+		seq_printf(s, "\"  \nMaster Copy\n");
+	else if (res->res_nodeid == -1)
+		seq_printf(s, "\"  \nLooking up master (lkid %x)\n",
+			   res->res_first_lkid);
+	else
+		seq_printf(s, "\"  \nInvalid master %d\n", res->res_nodeid);
+
+	/* Print the LVB: */
+	if (res->res_lvbptr) {
+		seq_printf(s, "LVB: ");
+		for (i = 0; i < lvblen; i++) {
+			if (i == lvblen / 2)
+				seq_printf(s, "\n     ");
+			seq_printf(s, "%02x ",
+				   (unsigned char) res->res_lvbptr[i]);
+		}
+		if (rsb_flag(res, RSB_VALNOTVALID))
+			seq_printf(s, " (INVALID)");
+		seq_printf(s, "\n");
+	}
+
+	/* Print the locks attached to this resource */
+	seq_printf(s, "Granted Queue\n");
+	list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	seq_printf(s, "Conversion Queue\n");
+	list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	seq_printf(s, "Waiting Queue\n");
+	list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	return 0;
+}
+
+static int rsb_iter_next(struct rsb_iter *ri)
+{
+	struct dlm_ls *ls = ri->ls;
+	int i;
+
+	if (!ri->next) {
+ top:
+		/* Find the next non-empty hash bucket */
+		for (i = ri->entry; i < ls->ls_rsbtbl_size; i++) {
+			read_lock(&ls->ls_rsbtbl[i].lock);
+			if (!list_empty(&ls->ls_rsbtbl[i].list)) {
+				ri->next = ls->ls_rsbtbl[i].list.next;
+				read_unlock(&ls->ls_rsbtbl[i].lock);
+				break;
+			}
+			read_unlock(&ls->ls_rsbtbl[i].lock);
+                }
+		ri->entry = i;
+
+		if (ri->entry >= ls->ls_rsbtbl_size)
+			return 1;
+	} else {
+		i = ri->entry;
+		read_lock(&ls->ls_rsbtbl[i].lock);
+		ri->next = ri->next->next;
+		if (ri->next->next == ls->ls_rsbtbl[i].list.next) {
+			/* End of list - move to next bucket */
+			ri->next = NULL;
+			ri->entry++;
+			read_unlock(&ls->ls_rsbtbl[i].lock);
+			goto top;
+                }
+		read_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+	ri->rsb = list_entry(ri->next, struct dlm_rsb, res_hashchain);
+
+	return 0;
+}
+
+static void rsb_iter_free(struct rsb_iter *ri)
+{
+	kfree(ri);
+}
+
+static struct rsb_iter *rsb_iter_init(struct dlm_ls *ls)
+{
+	struct rsb_iter *ri;
+
+	ri = kmalloc(sizeof *ri, GFP_KERNEL);
+	if (!ri)
+		return NULL;
+
+	ri->ls = ls;
+	ri->entry = 0;
+	ri->next = NULL;
+
+	if (rsb_iter_next(ri)) {
+		rsb_iter_free(ri);
+		return NULL;
+	}
+
+	return ri;
+}
+
+static void *seq_start(struct seq_file *file, loff_t *pos)
+{
+	struct rsb_iter *ri;
+	loff_t n = *pos;
+
+	ri = rsb_iter_init(file->private);
+	if (!ri)
+		return NULL;
+
+	while (n--) {
+		if (rsb_iter_next(ri)) {
+			rsb_iter_free(ri);
+			return NULL;
+		}
+	}
+
+	return ri;
+}
+
+static void *seq_next(struct seq_file *file, void *iter_ptr, loff_t *pos)
+{
+	struct rsb_iter *ri = iter_ptr;
+
+	(*pos)++;
+
+	if (rsb_iter_next(ri)) {
+		rsb_iter_free(ri);
+		return NULL;
+	}
+
+	return ri;
+}
+
+static void seq_stop(struct seq_file *file, void *iter_ptr)
+{
+	/* nothing for now */
+}
+
+static int seq_show(struct seq_file *file, void *iter_ptr)
+{
+	struct rsb_iter *ri = iter_ptr;
+
+	print_resource(ri->rsb, file);
+
+	return 0;
+}
+
+static struct seq_operations dlm_seq_ops = {
+	.start = seq_start,
+	.next  = seq_next,
+	.stop  = seq_stop,
+	.show  = seq_show,
+};
+
+static int do_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int ret;
+
+	ret = seq_open(file, &dlm_seq_ops);
+	if (ret)
+		return ret;
+
+	seq = file->private_data;
+	seq->private = inode->u.generic_ip;
+
+	return 0;
+}
+
+static struct file_operations dlm_fops = {
+	.owner   = THIS_MODULE,
+	.open    = do_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+int dlm_create_debug_file(struct dlm_ls *ls)
+{
+	ls->ls_debug_dentry = debugfs_create_file(ls->ls_name,
+						  S_IFREG | S_IRUGO,
+						  dlm_root,
+						  ls,
+						  &dlm_fops);
+	return ls->ls_debug_dentry ? 0 : -ENOMEM;
+}
+
+void dlm_delete_debug_file(struct dlm_ls *ls)
+{
+	if (ls->ls_debug_dentry)
+		debugfs_remove(ls->ls_debug_dentry);
+}
+
+int dlm_register_debugfs(void)
+{
+	dlm_root = debugfs_create_dir("dlm", NULL);
+	return dlm_root ? 0 : -ENOMEM;
+}
+
+void dlm_unregister_debugfs(void)
+{
+	debugfs_remove(dlm_root);
+}
+

fs/dlm/dir.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "lowcomms.h"
+#include "rcom.h"
+#include "config.h"
+#include "memory.h"
+#include "recover.h"
+#include "util.h"
+#include "lock.h"
+#include "dir.h"
+
+
+static void put_free_de(struct dlm_ls *ls, struct dlm_direntry *de)
+{
+	spin_lock(&ls->ls_recover_list_lock);
+	list_add(&de->list, &ls->ls_recover_list);
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+static struct dlm_direntry *get_free_de(struct dlm_ls *ls, int len)
+{
+	int found = FALSE;
+	struct dlm_direntry *de;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_for_each_entry(de, &ls->ls_recover_list, list) {
+		if (de->length == len) {
+			list_del(&de->list);
+			de->master_nodeid = 0;
+			memset(de->name, 0, len);
+			found = TRUE;
+			break;
+		}
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	if (!found)
+		de = allocate_direntry(ls, len);
+	return de;
+}
+
+void dlm_clear_free_entries(struct dlm_ls *ls)
+{
+	struct dlm_direntry *de;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	while (!list_empty(&ls->ls_recover_list)) {
+		de = list_entry(ls->ls_recover_list.next, struct dlm_direntry,
+				list);
+		list_del(&de->list);
+		free_direntry(de);
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+/*
+ * We use the upper 16 bits of the hash value to select the directory node.
+ * Low bits are used for distribution of rsb's among hash buckets on each node.
+ *
+ * To give the exact range wanted (0 to num_nodes-1), we apply a modulus of
+ * num_nodes to the hash value.  This value in the desired range is used as an
+ * offset into the sorted list of nodeid's to give the particular nodeid.
+ */
+
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash)
+{
+	struct list_head *tmp;
+	struct dlm_member *memb = NULL;
+	uint32_t node, n = 0;
+	int nodeid;
+
+	if (ls->ls_num_nodes == 1) {
+		nodeid = dlm_our_nodeid();
+		goto out;
+	}
+
+	if (ls->ls_node_array) {
+		node = (hash >> 16) % ls->ls_total_weight;
+		nodeid = ls->ls_node_array[node];
+		goto out;
+	}
+
+	/* make_member_array() failed to kmalloc ls_node_array... */
+
+	node = (hash >> 16) % ls->ls_num_nodes;
+
+	list_for_each(tmp, &ls->ls_nodes) {
+		if (n++ != node)
+			continue;
+		memb = list_entry(tmp, struct dlm_member, list);
+		break;
+	}
+
+	DLM_ASSERT(memb , printk("num_nodes=%u n=%u node=%u\n",
+				 ls->ls_num_nodes, n, node););
+	nodeid = memb->nodeid;
+ out:
+	return nodeid;
+}
+
+int dlm_dir_nodeid(struct dlm_rsb *r)
+{
+	return dlm_hash2nodeid(r->res_ls, r->res_hash);
+}
+
+static inline uint32_t dir_hash(struct dlm_ls *ls, char *name, int len)
+{
+	uint32_t val;
+
+	val = jhash(name, len, 0);
+	val &= (ls->ls_dirtbl_size - 1);
+
+	return val;
+}
+
+static void add_entry_to_hash(struct dlm_ls *ls, struct dlm_direntry *de)
+{
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, de->name, de->length);
+	list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
+}
+
+static struct dlm_direntry *search_bucket(struct dlm_ls *ls, char *name,
+					  int namelen, uint32_t bucket)
+{
+	struct dlm_direntry *de;
+
+	list_for_each_entry(de, &ls->ls_dirtbl[bucket].list, list) {
+		if (de->length == namelen && !memcmp(name, de->name, namelen))
+			goto out;
+	}
+	de = NULL;
+ out:
+	return de;
+}
+
+void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int namelen)
+{
+	struct dlm_direntry *de;
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+
+	de = search_bucket(ls, name, namelen, bucket);
+
+	if (!de) {
+		log_error(ls, "remove fr %u none", nodeid);
+		goto out;
+	}
+
+	if (de->master_nodeid != nodeid) {
+		log_error(ls, "remove fr %u ID %u", nodeid, de->master_nodeid);
+		goto out;
+	}
+
+	list_del(&de->list);
+	free_direntry(de);
+ out:
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+}
+
+void dlm_dir_clear(struct dlm_ls *ls)
+{
+	struct list_head *head;
+	struct dlm_direntry *de;
+	int i;
+
+	DLM_ASSERT(list_empty(&ls->ls_recover_list), );
+
+	for (i = 0; i < ls->ls_dirtbl_size; i++) {
+		write_lock(&ls->ls_dirtbl[i].lock);
+		head = &ls->ls_dirtbl[i].list;
+		while (!list_empty(head)) {
+			de = list_entry(head->next, struct dlm_direntry, list);
+			list_del(&de->list);
+			put_free_de(ls, de);
+		}
+		write_unlock(&ls->ls_dirtbl[i].lock);
+	}
+}
+
+int dlm_recover_directory(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	struct dlm_direntry *de;
+	char *b, *last_name = NULL;
+	int error = -ENOMEM, last_len, count = 0;
+	uint16_t namelen;
+
+	log_debug(ls, "dlm_recover_directory");
+
+	if (dlm_no_directory(ls))
+		goto out_status;
+
+	dlm_dir_clear(ls);
+
+	last_name = kmalloc(DLM_RESNAME_MAXLEN, GFP_KERNEL);
+	if (!last_name)
+		goto out;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		memset(last_name, 0, DLM_RESNAME_MAXLEN);
+		last_len = 0;
+
+		for (;;) {
+			error = dlm_recovery_stopped(ls);
+			if (error)
+				goto out_free;
+
+			error = dlm_rcom_names(ls, memb->nodeid,
+					       last_name, last_len);
+			if (error)
+				goto out_free;
+
+			schedule();
+
+			/*
+			 * pick namelen/name pairs out of received buffer
+			 */
+
+			b = ls->ls_recover_buf + sizeof(struct dlm_rcom);
+
+			for (;;) {
+				memcpy(&namelen, b, sizeof(uint16_t));
+				namelen = be16_to_cpu(namelen);
+				b += sizeof(uint16_t);
+
+				/* namelen of 0xFFFFF marks end of names for
+				   this node; namelen of 0 marks end of the
+				   buffer */
+
+				if (namelen == 0xFFFF)
+					goto done;
+				if (!namelen)
+					break;
+
+				error = -ENOMEM;
+				de = get_free_de(ls, namelen);
+				if (!de)
+					goto out_free;
+
+				de->master_nodeid = memb->nodeid;
+				de->length = namelen;
+				last_len = namelen;
+				memcpy(de->name, b, namelen);
+				memcpy(last_name, b, namelen);
+				b += namelen;
+
+				add_entry_to_hash(ls, de);
+				count++;
+			}
+		}
+         done:
+		;
+	}
+
+ out_status:
+	error = 0;
+	dlm_set_recover_status(ls, DLM_RS_DIR);
+	log_debug(ls, "dlm_recover_directory %d entries", count);
+ out_free:
+	kfree(last_name);
+ out:
+	dlm_clear_free_entries(ls);
+	return error;
+}
+
+static int get_entry(struct dlm_ls *ls, int nodeid, char *name,
+		     int namelen, int *r_nodeid)
+{
+	struct dlm_direntry *de, *tmp;
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+	de = search_bucket(ls, name, namelen, bucket);
+	if (de) {
+		*r_nodeid = de->master_nodeid;
+		write_unlock(&ls->ls_dirtbl[bucket].lock);
+		if (*r_nodeid == nodeid)
+			return -EEXIST;
+		return 0;
+	}
+
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+
+	de = allocate_direntry(ls, namelen);
+	if (!de)
+		return -ENOMEM;
+
+	de->master_nodeid = nodeid;
+	de->length = namelen;
+	memcpy(de->name, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+	tmp = search_bucket(ls, name, namelen, bucket);
+	if (tmp) {
+		free_direntry(de);
+		de = tmp;
+	} else {
+		list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
+	}
+	*r_nodeid = de->master_nodeid;
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+	return 0;
+}
+
+int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
+		   int *r_nodeid)
+{
+	return get_entry(ls, nodeid, name, namelen, r_nodeid);
+}
+
+/* Copy the names of master rsb's into the buffer provided.
+   Only select names whose dir node is the given nodeid. */
+
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+ 			   char *outbuf, int outlen, int nodeid)
+{
+	struct list_head *list;
+	struct dlm_rsb *start_r = NULL, *r = NULL;
+	int offset = 0, start_namelen, error, dir_nodeid;
+	char *start_name;
+	uint16_t be_namelen;
+
+	/*
+	 * Find the rsb where we left off (or start again)
+	 */
+
+	start_namelen = inlen;
+	start_name = inbuf;
+
+	if (start_namelen > 1) {
+		/*
+		 * We could also use a find_rsb_root() function here that
+		 * searched the ls_root_list.
+		 */
+		error = dlm_find_rsb(ls, start_name, start_namelen, R_MASTER,
+				     &start_r);
+		DLM_ASSERT(!error && start_r,
+			   printk("error %d\n", error););
+		DLM_ASSERT(!list_empty(&start_r->res_root_list),
+			   dlm_print_rsb(start_r););
+		dlm_put_rsb(start_r);
+	}
+
+	/*
+	 * Send rsb names for rsb's we're master of and whose directory node
+	 * matches the requesting node.
+	 */
+
+	down_read(&ls->ls_root_sem);
+	if (start_r)
+		list = start_r->res_root_list.next;
+	else
+		list = ls->ls_root_list.next;
+
+	for (offset = 0; list != &ls->ls_root_list; list = list->next) {
+		r = list_entry(list, struct dlm_rsb, res_root_list);
+		if (r->res_nodeid)
+			continue;
+
+		dir_nodeid = dlm_dir_nodeid(r);
+		if (dir_nodeid != nodeid)
+			continue;
+
+		/*
+		 * The block ends when we can't fit the following in the
+		 * remaining buffer space:
+		 * namelen (uint16_t) +
+		 * name (r->res_length) +
+		 * end-of-block record 0x0000 (uint16_t)
+		 */
+
+		if (offset + sizeof(uint16_t)*2 + r->res_length > outlen) {
+			/* Write end-of-block record */
+			be_namelen = 0;
+			memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+			offset += sizeof(uint16_t);
+			goto out;
+		}
+
+		be_namelen = cpu_to_be16(r->res_length);
+		memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+		offset += sizeof(uint16_t);
+		memcpy(outbuf + offset, r->res_name, r->res_length);
+		offset += r->res_length;
+	}
+
+	/*
+	 * If we've reached the end of the list (and there's room) write a
+	 * terminating record.
+	 */
+
+	if ((list == &ls->ls_root_list) &&
+	    (offset + sizeof(uint16_t) <= outlen)) {
+		be_namelen = 0xFFFF;
+		memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+		offset += sizeof(uint16_t);
+	}
+
+ out:
+	up_read(&ls->ls_root_sem);
+}
+

fs/dlm/dir.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+
+int dlm_dir_nodeid(struct dlm_rsb *rsb);
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash);
+void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int len);
+void dlm_dir_clear(struct dlm_ls *ls);
+void dlm_clear_free_entries(struct dlm_ls *ls);
+int dlm_recover_directory(struct dlm_ls *ls);
+int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
+	int *r_nodeid);
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+	char *outbuf, int outlen, int nodeid);
+
+#endif				/* __DIR_DOT_H__ */
+

fs/dlm/dlm_internal.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DLM_INTERNAL_DOT_H__
+#define __DLM_INTERNAL_DOT_H__
+
+/*
+ * This is the main header file to be included in each DLM source file.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <linux/delay.h>
+#include <linux/socket.h>
+#include <linux/kthread.h>
+#include <linux/kobject.h>
+#include <linux/kref.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <asm/semaphore.h>
+#include <asm/uaccess.h>
+
+#include <linux/dlm.h>
+
+#define DLM_LOCKSPACE_LEN	64
+
+#ifndef TRUE
+#define TRUE 1
+#endif
+
+#ifndef FALSE
+#define FALSE 0
+#endif
+
+#if (BITS_PER_LONG == 64)
+#define PRIx64 "lx"
+#else
+#define PRIx64 "Lx"
+#endif
+
+/* Size of the temp buffer midcomms allocates on the stack.
+   We try to make this large enough so most messages fit.
+   FIXME: should sctp make this unnecessary? */
+
+#define DLM_INBUF_LEN		148
+
+struct dlm_ls;
+struct dlm_lkb;
+struct dlm_rsb;
+struct dlm_member;
+struct dlm_lkbtable;
+struct dlm_rsbtable;
+struct dlm_dirtable;
+struct dlm_direntry;
+struct dlm_recover;
+struct dlm_header;
+struct dlm_message;
+struct dlm_rcom;
+struct dlm_mhandle;
+
+#define log_print(fmt, args...) \
+	printk(KERN_ERR "dlm: "fmt"\n" , ##args)
+#define log_error(ls, fmt, args...) \
+	printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
+
+#ifdef DLM_LOG_DEBUG
+#define log_debug(ls, fmt, args...) log_error(ls, fmt, ##args)
+#else
+#define log_debug(ls, fmt, args...)
+#endif
+
+#define DLM_ASSERT(x, do) \
+{ \
+  if (!(x)) \
+  { \
+    printk(KERN_ERR "\nDLM:  Assertion failed on line %d of file %s\n" \
+               "DLM:  assertion:  \"%s\"\n" \
+               "DLM:  time = %lu\n", \
+               __LINE__, __FILE__, #x, jiffies); \
+    {do} \
+    printk("\n"); \
+    BUG(); \
+    panic("DLM:  Record message above and reboot.\n"); \
+  } \
+}
+
+
+struct dlm_direntry {
+	struct list_head	list;
+	uint32_t		master_nodeid;
+	uint16_t		length;
+	char			name[1];
+};
+
+struct dlm_dirtable {
+	struct list_head	list;
+	rwlock_t		lock;
+};
+
+struct dlm_rsbtable {
+	struct list_head	list;
+	struct list_head	toss;
+	rwlock_t		lock;
+};
+
+struct dlm_lkbtable {
+	struct list_head	list;
+	rwlock_t		lock;
+	uint16_t		counter;
+};
+
+/*
+ * Lockspace member (per node in a ls)
+ */
+
+struct dlm_member {
+	struct list_head	list;
+	int			nodeid;
+	int			weight;
+};
+
+/*
+ * Save and manage recovery state for a lockspace.
+ */
+
+struct dlm_recover {
+	struct list_head	list;
+	int			*nodeids;
+	int			node_count;
+	uint64_t		seq;
+};
+
+/*
+ * Pass input args to second stage locking function.
+ */
+
+struct dlm_args {
+	uint32_t		flags;
+	void			*astaddr;
+	long			astparam;
+	void			*bastaddr;
+	int			mode;
+	struct dlm_lksb		*lksb;
+	struct dlm_range	*range;
+};
+
+
+/*
+ * Lock block
+ *
+ * A lock can be one of three types:
+ *
+ * local copy      lock is mastered locally
+ *                 (lkb_nodeid is zero and DLM_LKF_MSTCPY is not set)
+ * process copy    lock is mastered on a remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is not set)
+ * master copy     master node's copy of a lock owned by remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is set)
+ *
+ * lkb_exflags: a copy of the most recent flags arg provided to dlm_lock or
+ * dlm_unlock.  The dlm does not modify these or use any private flags in
+ * this field; it only contains DLM_LKF_ flags from dlm.h.  These flags
+ * are sent as-is to the remote master when the lock is remote.
+ *
+ * lkb_flags: internal dlm flags (DLM_IFL_ prefix) from dlm_internal.h.
+ * Some internal flags are shared between the master and process nodes;
+ * these shared flags are kept in the lower two bytes.  One of these
+ * flags set on the master copy will be propagated to the process copy
+ * and v.v.  Other internal flags are private to the master or process
+ * node (e.g. DLM_IFL_MSTCPY).  These are kept in the high two bytes.
+ *
+ * lkb_sbflags: status block flags.  These flags are copied directly into
+ * the caller's lksb.sb_flags prior to the dlm_lock/dlm_unlock completion
+ * ast.  All defined in dlm.h with DLM_SBF_ prefix.
+ *
+ * lkb_status: the lock status indicates which rsb queue the lock is
+ * on, grant, convert, or wait.  DLM_LKSTS_ WAITING/GRANTED/CONVERT
+ *
+ * lkb_wait_type: the dlm message type (DLM_MSG_ prefix) for which a
+ * reply is needed.  Only set when the lkb is on the lockspace waiters
+ * list awaiting a reply from a remote node.
+ *
+ * lkb_nodeid: when the lkb is a local copy, nodeid is 0; when the lkb
+ * is a master copy, nodeid specifies the remote lock holder, when the
+ * lkb is a process copy, the nodeid specifies the lock master.
+ */
+
+/* lkb_ast_type */
+
+#define AST_COMP		1
+#define AST_BAST		2
+
+/* lkb_range[] */
+
+#define GR_RANGE_START		0
+#define GR_RANGE_END		1
+#define RQ_RANGE_START		2
+#define RQ_RANGE_END		3
+
+/* lkb_status */
+
+#define DLM_LKSTS_WAITING	1
+#define DLM_LKSTS_GRANTED	2
+#define DLM_LKSTS_CONVERT	3
+
+/* lkb_flags */
+
+#define DLM_IFL_MSTCPY		0x00010000
+#define DLM_IFL_RESEND		0x00020000
+#define DLM_IFL_RANGE		0x00000001
+
+struct dlm_lkb {
+	struct dlm_rsb		*lkb_resource;	/* the rsb */
+	struct kref		lkb_ref;
+	int			lkb_nodeid;	/* copied from rsb */
+	int			lkb_ownpid;	/* pid of lock owner */
+	uint32_t		lkb_id;		/* our lock ID */
+	uint32_t		lkb_remid;	/* lock ID on remote partner */
+	uint32_t		lkb_exflags;	/* external flags from caller */
+	uint32_t		lkb_sbflags;	/* lksb flags */
+	uint32_t		lkb_flags;	/* internal flags */
+	uint32_t		lkb_lvbseq;	/* lvb sequence number */
+
+	int8_t			lkb_status;     /* granted, waiting, convert */
+	int8_t			lkb_rqmode;	/* requested lock mode */
+	int8_t			lkb_grmode;	/* granted lock mode */
+	int8_t			lkb_bastmode;	/* requested mode */
+	int8_t			lkb_highbast;	/* highest mode bast sent for */
+
+	int8_t			lkb_wait_type;	/* type of reply waiting for */
+	int8_t			lkb_ast_type;	/* type of ast queued for */
+
+	struct list_head	lkb_idtbl_list;	/* lockspace lkbtbl */
+	struct list_head	lkb_statequeue;	/* rsb g/c/w list */
+	struct list_head	lkb_rsb_lookup;	/* waiting for rsb lookup */
+	struct list_head	lkb_wait_reply;	/* waiting for remote reply */
+	struct list_head	lkb_astqueue;	/* need ast to be sent */
+
+	uint64_t		*lkb_range;	/* array of gr/rq ranges */
+	char			*lkb_lvbptr;
+	struct dlm_lksb		*lkb_lksb;      /* caller's status block */
+	void			*lkb_astaddr;	/* caller's ast function */
+	void			*lkb_bastaddr;	/* caller's bast function */
+	long			lkb_astparam;	/* caller's ast arg */
+};
+
+
+struct dlm_rsb {
+	struct dlm_ls		*res_ls;	/* the lockspace */
+	struct kref		res_ref;
+	struct semaphore	res_sem;
+	unsigned long		res_flags;
+	int			res_length;	/* length of rsb name */
+	int			res_nodeid;
+	uint32_t                res_lvbseq;
+	uint32_t		res_hash;
+	uint32_t		res_bucket;	/* rsbtbl */
+	unsigned long		res_toss_time;
+	uint32_t		res_first_lkid;
+	struct list_head	res_lookup;	/* lkbs waiting on first */
+	struct list_head	res_hashchain;	/* rsbtbl */
+	struct list_head	res_grantqueue;
+	struct list_head	res_convertqueue;
+	struct list_head	res_waitqueue;
+
+	struct list_head	res_root_list;	    /* used for recovery */
+	struct list_head	res_recover_list;   /* used for recovery */
+	int			res_recover_locks_count;
+
+	char			*res_lvbptr;
+	char			res_name[1];
+};
+
+/* find_rsb() flags */
+
+#define R_MASTER		1	/* only return rsb if it's a master */
+#define R_CREATE		2	/* create/add rsb if not found */
+
+/* rsb_flags */
+
+enum rsb_flags {
+	RSB_MASTER_UNCERTAIN,
+	RSB_VALNOTVALID,
+	RSB_VALNOTVALID_PREV,
+	RSB_NEW_MASTER,
+	RSB_NEW_MASTER2,
+	RSB_RECOVER_CONVERT,
+};
+
+static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__set_bit(flag, &r->res_flags);
+}
+
+static inline void rsb_clear_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__clear_bit(flag, &r->res_flags);
+}
+
+static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	return test_bit(flag, &r->res_flags);
+}
+
+
+/* dlm_header is first element of all structs sent between nodes */
+
+#define DLM_HEADER_MAJOR	0x00020000
+#define DLM_HEADER_MINOR	0x00000001
+
+#define DLM_MSG			1
+#define DLM_RCOM		2
+
+struct dlm_header {
+	uint32_t		h_version;
+	uint32_t		h_lockspace;
+	uint32_t		h_nodeid;	/* nodeid of sender */
+	uint16_t		h_length;
+	uint8_t			h_cmd;		/* DLM_MSG, DLM_RCOM */
+	uint8_t			h_pad;
+};
+
+
+#define DLM_MSG_REQUEST		1
+#define DLM_MSG_CONVERT		2
+#define DLM_MSG_UNLOCK		3
+#define DLM_MSG_CANCEL		4
+#define DLM_MSG_REQUEST_REPLY	5
+#define DLM_MSG_CONVERT_REPLY	6
+#define DLM_MSG_UNLOCK_REPLY	7
+#define DLM_MSG_CANCEL_REPLY	8
+#define DLM_MSG_GRANT		9
+#define DLM_MSG_BAST		10
+#define DLM_MSG_LOOKUP		11
+#define DLM_MSG_REMOVE		12
+#define DLM_MSG_LOOKUP_REPLY	13
+
+struct dlm_message {
+	struct dlm_header	m_header;
+	uint32_t		m_type;		/* DLM_MSG_ */
+	uint32_t		m_nodeid;
+	uint32_t		m_pid;
+	uint32_t		m_lkid;		/* lkid on sender */
+	uint32_t		m_remid;	/* lkid on receiver */
+	uint32_t		m_parent_lkid;
+	uint32_t		m_parent_remid;
+	uint32_t		m_exflags;
+	uint32_t		m_sbflags;
+	uint32_t		m_flags;
+	uint32_t		m_lvbseq;
+	uint32_t		m_hash;
+	int			m_status;
+	int			m_grmode;
+	int			m_rqmode;
+	int			m_bastmode;
+	int			m_asts;
+	int			m_result;	/* 0 or -EXXX */
+	uint64_t		m_range[2];
+	char			m_extra[0];	/* name or lvb */
+};
+
+
+#define DLM_RS_NODES		0x00000001
+#define DLM_RS_NODES_ALL	0x00000002
+#define DLM_RS_DIR		0x00000004
+#define DLM_RS_DIR_ALL		0x00000008
+#define DLM_RS_LOCKS		0x00000010
+#define DLM_RS_LOCKS_ALL	0x00000020
+#define DLM_RS_DONE		0x00000040
+#define DLM_RS_DONE_ALL		0x00000080
+
+#define DLM_RCOM_STATUS		1
+#define DLM_RCOM_NAMES		2
+#define DLM_RCOM_LOOKUP		3
+#define DLM_RCOM_LOCK		4
+#define DLM_RCOM_STATUS_REPLY	5
+#define DLM_RCOM_NAMES_REPLY	6
+#define DLM_RCOM_LOOKUP_REPLY	7
+#define DLM_RCOM_LOCK_REPLY	8
+
+struct dlm_rcom {
+	struct dlm_header	rc_header;
+	uint32_t		rc_type;	/* DLM_RCOM_ */
+	int			rc_result;	/* multi-purpose */
+	uint64_t		rc_id;		/* match reply with request */
+	char			rc_buf[0];
+};
+
+struct rcom_config {
+	uint32_t		rf_lvblen;
+	uint32_t		rf_lsflags;
+	uint64_t		rf_unused;
+};
+
+struct rcom_lock {
+	uint32_t		rl_ownpid;
+	uint32_t		rl_lkid;
+	uint32_t		rl_remid;
+	uint32_t		rl_parent_lkid;
+	uint32_t		rl_parent_remid;
+	uint32_t		rl_exflags;
+	uint32_t		rl_flags;
+	uint32_t		rl_lvbseq;
+	int			rl_result;
+	int8_t			rl_rqmode;
+	int8_t			rl_grmode;
+	int8_t			rl_status;
+	int8_t			rl_asts;
+	uint16_t		rl_wait_type;
+	uint16_t		rl_namelen;
+	uint64_t		rl_range[4];
+	char			rl_name[DLM_RESNAME_MAXLEN];
+	char			rl_lvb[0];
+};
+
+struct dlm_ls {
+	struct list_head	ls_list;	/* list of lockspaces */
+	uint32_t		ls_global_id;	/* global unique lockspace ID */
+	uint32_t		ls_exflags;
+	int			ls_lvblen;
+	int			ls_count;	/* reference count */
+	unsigned long		ls_flags;	/* LSFL_ */
+	struct kobject		ls_kobj;
+
+	struct dlm_rsbtable	*ls_rsbtbl;
+	uint32_t		ls_rsbtbl_size;
+
+	struct dlm_lkbtable	*ls_lkbtbl;
+	uint32_t		ls_lkbtbl_size;
+
+	struct dlm_dirtable	*ls_dirtbl;
+	uint32_t		ls_dirtbl_size;
+
+	struct semaphore	ls_waiters_sem;
+	struct list_head	ls_waiters;	/* lkbs needing a reply */
+
+	struct list_head	ls_nodes;	/* current nodes in ls */
+	struct list_head	ls_nodes_gone;	/* dead node list, recovery */
+	int			ls_num_nodes;	/* number of nodes in ls */
+	int			ls_low_nodeid;
+	int			ls_total_weight;
+	int			*ls_node_array;
+
+	struct dlm_rsb		ls_stub_rsb;	/* for returning errors */
+	struct dlm_lkb		ls_stub_lkb;	/* for returning errors */
+	struct dlm_message	ls_stub_ms;	/* for faking a reply */
+
+	struct dentry		*ls_debug_dentry; /* debugfs */
+
+	wait_queue_head_t	ls_uevent_wait;	/* user part of join/leave */
+	int			ls_uevent_result;
+
+	/* recovery related */
+
+	struct timer_list	ls_timer;
+	struct task_struct	*ls_recoverd_task;
+	struct semaphore	ls_recoverd_active;
+	spinlock_t		ls_recover_lock;
+	uint32_t		ls_recover_status; /* DLM_RS_ */
+	uint64_t		ls_recover_seq;
+	struct dlm_recover	*ls_recover_args;
+	struct rw_semaphore	ls_in_recovery;	/* block local requests */
+	struct list_head	ls_requestqueue;/* queue remote requests */
+	struct semaphore	ls_requestqueue_lock;
+	char			*ls_recover_buf;
+	struct list_head	ls_recover_list;
+	spinlock_t		ls_recover_list_lock;
+	int			ls_recover_list_count;
+	wait_queue_head_t	ls_wait_general;
+
+	struct list_head	ls_root_list;	/* root resources */
+	struct rw_semaphore	ls_root_sem;	/* protect root_list */
+
+	int			ls_namelen;
+	char			ls_name[1];
+};
+
+#define LSFL_WORK		0
+#define LSFL_RUNNING		1
+#define LSFL_RECOVERY_STOP	2
+#define LSFL_RCOM_READY		3
+#define LSFL_UEVENT_WAIT	4
+
+static inline int dlm_locking_stopped(struct dlm_ls *ls)
+{
+	return !test_bit(LSFL_RUNNING, &ls->ls_flags);
+}
+
+static inline int dlm_recovery_stopped(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+}
+
+static inline int dlm_no_directory(struct dlm_ls *ls)
+{
+	return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0;
+}
+
+#endif				/* __DLM_INTERNAL_DOT_H__ */
+

fs/dlm/lock.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCK_DOT_H__
+#define __LOCK_DOT_H__
+
+void dlm_print_rsb(struct dlm_rsb *r);
+int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery);
+int dlm_modes_compat(int mode1, int mode2);
+int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
+	unsigned int flags, struct dlm_rsb **r_ret);
+void dlm_put_rsb(struct dlm_rsb *r);
+void dlm_hold_rsb(struct dlm_rsb *r);
+int dlm_put_lkb(struct dlm_lkb *lkb);
+void dlm_scan_rsbs(struct dlm_ls *ls);
+
+int dlm_purge_locks(struct dlm_ls *ls);
+void dlm_purge_mstcpy_locks(struct dlm_rsb *r);
+int dlm_grant_after_purge(struct dlm_ls *ls);
+int dlm_recover_waiters_post(struct dlm_ls *ls);
+void dlm_recover_waiters_pre(struct dlm_ls *ls);
+int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+
+static inline int is_master(struct dlm_rsb *r)
+{
+	return !r->res_nodeid;
+}
+
+static inline void lock_rsb(struct dlm_rsb *r)
+{
+	down(&r->res_sem);
+}
+
+static inline void unlock_rsb(struct dlm_rsb *r)
+{
+	up(&r->res_sem);
+}
+
+#endif
+

fs/dlm/lockspace.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "ast.h"
+#include "dir.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "memory.h"
+#include "lock.h"
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_create_debug_file(struct dlm_ls *ls);
+void dlm_delete_debug_file(struct dlm_ls *ls);
+#else
+static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
+static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+#endif
+
+static int			ls_count;
+static struct semaphore		ls_lock;
+static struct list_head		lslist;
+static spinlock_t		lslist_lock;
+static struct task_struct *	scand_task;
+
+
+static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int n = simple_strtol(buf, NULL, 0);
+
+	switch (n) {
+	case 0:
+		dlm_ls_stop(ls);
+		break;
+	case 1:
+		dlm_ls_start(ls);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ls->ls_uevent_result = simple_strtol(buf, NULL, 0);
+	set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags);
+	wake_up(&ls->ls_uevent_wait);
+	return len;
+}
+
+static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%u\n", ls->ls_global_id);
+}
+
+static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ls->ls_global_id = simple_strtoul(buf, NULL, 0);
+	return len;
+}
+
+struct dlm_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dlm_ls *, char *);
+	ssize_t (*store)(struct dlm_ls *, const char *, size_t);
+};
+
+static struct dlm_attr dlm_attr_control = {
+	.attr  = {.name = "control", .mode = S_IWUSR},
+	.store = dlm_control_store
+};
+
+static struct dlm_attr dlm_attr_event = {
+	.attr  = {.name = "event_done", .mode = S_IWUSR},
+	.store = dlm_event_store
+};
+
+static struct dlm_attr dlm_attr_id = {
+	.attr  = {.name = "id", .mode = S_IRUGO | S_IWUSR},
+	.show  = dlm_id_show,
+	.store = dlm_id_store
+};
+
+static struct attribute *dlm_attrs[] = {
+	&dlm_attr_control.attr,
+	&dlm_attr_event.attr,
+	&dlm_attr_id.attr,
+	NULL,
+};
+
+static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->show ? a->show(ls, buf) : 0;
+}
+
+static ssize_t dlm_attr_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t len)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->store ? a->store(ls, buf, len) : len;
+}
+
+static struct sysfs_ops dlm_attr_ops = {
+	.show  = dlm_attr_show,
+	.store = dlm_attr_store,
+};
+
+static struct kobj_type dlm_ktype = {
+	.default_attrs = dlm_attrs,
+	.sysfs_ops     = &dlm_attr_ops,
+};
+
+static struct kset dlm_kset = {
+	.subsys = &kernel_subsys,
+	.kobj   = {.name = "dlm",},
+	.ktype  = &dlm_ktype,
+};
+
+static int kobject_setup(struct dlm_ls *ls)
+{
+	char lsname[DLM_LOCKSPACE_LEN];
+	int error;
+
+	memset(lsname, 0, DLM_LOCKSPACE_LEN);
+	snprintf(lsname, DLM_LOCKSPACE_LEN, "%s", ls->ls_name);
+
+	error = kobject_set_name(&ls->ls_kobj, "%s", lsname);
+	if (error)
+		return error;
+
+	ls->ls_kobj.kset = &dlm_kset;
+	ls->ls_kobj.ktype = &dlm_ktype;
+	return 0;
+}
+
+static int do_uevent(struct dlm_ls *ls, int in)
+{
+	int error;
+
+	if (in)
+		kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
+	else
+		kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);
+
+	error = wait_event_interruptible(ls->ls_uevent_wait,
+			test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
+	if (error)
+		goto out;
+
+	error = ls->ls_uevent_result;
+ out:
+	return error;
+}
+
+
+int dlm_lockspace_init(void)
+{
+	int error;
+
+	ls_count = 0;
+	init_MUTEX(&ls_lock);
+	INIT_LIST_HEAD(&lslist);
+	spin_lock_init(&lslist_lock);
+
+	error = kset_register(&dlm_kset);
+	if (error)
+		printk("dlm_lockspace_init: cannot register kset %d\n", error);
+	return error;
+}
+
+void dlm_lockspace_exit(void)
+{
+	kset_unregister(&dlm_kset);
+}
+
+static int dlm_scand(void *data)
+{
+	struct dlm_ls *ls;
+
+	while (!kthread_should_stop()) {
+		list_for_each_entry(ls, &lslist, ls_list)
+			dlm_scan_rsbs(ls);
+		schedule_timeout_interruptible(dlm_config.scan_secs * HZ);
+	}
+	return 0;
+}
+
+static int dlm_scand_start(void)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(dlm_scand, NULL, "dlm_scand");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+		scand_task = p;
+	return error;
+}
+
+static void dlm_scand_stop(void)
+{
+	kthread_stop(scand_task);
+}
+
+static struct dlm_ls *dlm_find_lockspace_name(char *name, int namelen)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_namelen == namelen &&
+		    memcmp(ls->ls_name, name, namelen) == 0)
+			goto out;
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_global_id == id) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_local(void *id)
+{
+	struct dlm_ls *ls = id;
+
+	spin_lock(&lslist_lock);
+	ls->ls_count++;
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+void dlm_put_lockspace(struct dlm_ls *ls)
+{
+	spin_lock(&lslist_lock);
+	ls->ls_count--;
+	spin_unlock(&lslist_lock);
+}
+
+static void remove_lockspace(struct dlm_ls *ls)
+{
+	for (;;) {
+		spin_lock(&lslist_lock);
+		if (ls->ls_count == 0) {
+			list_del(&ls->ls_list);
+			spin_unlock(&lslist_lock);
+			return;
+		}
+		spin_unlock(&lslist_lock);
+		ssleep(1);
+	}
+}
+
+static int threads_start(void)
+{
+	int error;
+
+	/* Thread which process lock requests for all lockspace's */
+	error = dlm_astd_start();
+	if (error) {
+		log_print("cannot start dlm_astd thread %d", error);
+		goto fail;
+	}
+
+	error = dlm_scand_start();
+	if (error) {
+		log_print("cannot start dlm_scand thread %d", error);
+		goto astd_fail;
+	}
+
+	/* Thread for sending/receiving messages for all lockspace's */
+	error = dlm_lowcomms_start();
+	if (error) {
+		log_print("cannot start dlm lowcomms %d", error);
+		goto scand_fail;
+	}
+
+	return 0;
+
+ scand_fail:
+	dlm_scand_stop();
+ astd_fail:
+	dlm_astd_stop();
+ fail:
+	return error;
+}
+
+static void threads_stop(void)
+{
+	dlm_scand_stop();
+	dlm_lowcomms_stop();
+	dlm_astd_stop();
+}
+
+static int new_lockspace(char *name, int namelen, void **lockspace,
+			 uint32_t flags, int lvblen)
+{
+	struct dlm_ls *ls;
+	int i, size, error = -ENOMEM;
+
+	if (namelen > DLM_LOCKSPACE_LEN)
+		return -EINVAL;
+
+	if (!lvblen || (lvblen % 8))
+		return -EINVAL;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	ls = dlm_find_lockspace_name(name, namelen);
+	if (ls) {
+		*lockspace = ls;
+		module_put(THIS_MODULE);
+		return -EEXIST;
+	}
+
+	ls = kmalloc(sizeof(struct dlm_ls) + namelen, GFP_KERNEL);
+	if (!ls)
+		goto out;
+	memset(ls, 0, sizeof(struct dlm_ls) + namelen);
+	memcpy(ls->ls_name, name, namelen);
+	ls->ls_namelen = namelen;
+	ls->ls_exflags = flags;
+	ls->ls_lvblen = lvblen;
+	ls->ls_count = 0;
+	ls->ls_flags = 0;
+
+	size = dlm_config.rsbtbl_size;
+	ls->ls_rsbtbl_size = size;
+
+	ls->ls_rsbtbl = kmalloc(sizeof(struct dlm_rsbtable) * size, GFP_KERNEL);
+	if (!ls->ls_rsbtbl)
+		goto out_lsfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_rsbtbl[i].list);
+		INIT_LIST_HEAD(&ls->ls_rsbtbl[i].toss);
+		rwlock_init(&ls->ls_rsbtbl[i].lock);
+	}
+
+	size = dlm_config.lkbtbl_size;
+	ls->ls_lkbtbl_size = size;
+
+	ls->ls_lkbtbl = kmalloc(sizeof(struct dlm_lkbtable) * size, GFP_KERNEL);
+	if (!ls->ls_lkbtbl)
+		goto out_rsbfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_lkbtbl[i].list);
+		rwlock_init(&ls->ls_lkbtbl[i].lock);
+		ls->ls_lkbtbl[i].counter = 1;
+	}
+
+	size = dlm_config.dirtbl_size;
+	ls->ls_dirtbl_size = size;
+
+	ls->ls_dirtbl = kmalloc(sizeof(struct dlm_dirtable) * size, GFP_KERNEL);
+	if (!ls->ls_dirtbl)
+		goto out_lkbfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_dirtbl[i].list);
+		rwlock_init(&ls->ls_dirtbl[i].lock);
+	}
+
+	INIT_LIST_HEAD(&ls->ls_waiters);
+	init_MUTEX(&ls->ls_waiters_sem);
+
+	INIT_LIST_HEAD(&ls->ls_nodes);
+	INIT_LIST_HEAD(&ls->ls_nodes_gone);
+	ls->ls_num_nodes = 0;
+	ls->ls_low_nodeid = 0;
+	ls->ls_total_weight = 0;
+	ls->ls_node_array = NULL;
+
+	memset(&ls->ls_stub_rsb, 0, sizeof(struct dlm_rsb));
+	ls->ls_stub_rsb.res_ls = ls;
+
+	ls->ls_debug_dentry = NULL;
+
+	init_waitqueue_head(&ls->ls_uevent_wait);
+	ls->ls_uevent_result = 0;
+
+	ls->ls_recoverd_task = NULL;
+	init_MUTEX(&ls->ls_recoverd_active);
+	spin_lock_init(&ls->ls_recover_lock);
+	ls->ls_recover_status = 0;
+	ls->ls_recover_seq = 0;
+	ls->ls_recover_args = NULL;
+	init_rwsem(&ls->ls_in_recovery);
+	INIT_LIST_HEAD(&ls->ls_requestqueue);
+	init_MUTEX(&ls->ls_requestqueue_lock);
+
+	ls->ls_recover_buf = kmalloc(dlm_config.buffer_size, GFP_KERNEL);
+	if (!ls->ls_recover_buf)
+		goto out_dirfree;
+
+	INIT_LIST_HEAD(&ls->ls_recover_list);
+	spin_lock_init(&ls->ls_recover_list_lock);
+	ls->ls_recover_list_count = 0;
+	init_waitqueue_head(&ls->ls_wait_general);
+	INIT_LIST_HEAD(&ls->ls_root_list);
+	init_rwsem(&ls->ls_root_sem);
+
+	down_write(&ls->ls_in_recovery);
+
+	error = dlm_recoverd_start(ls);
+	if (error) {
+		log_error(ls, "can't start dlm_recoverd %d", error);
+		goto out_rcomfree;
+	}
+
+	spin_lock(&lslist_lock);
+	list_add(&ls->ls_list, &lslist);
+	spin_unlock(&lslist_lock);
+
+	dlm_create_debug_file(ls);
+
+	error = kobject_setup(ls);
+	if (error)
+		goto out_del;
+
+	error = kobject_register(&ls->ls_kobj);
+	if (error)
+		goto out_del;
+
+	error = do_uevent(ls, 1);
+	if (error)
+		goto out_unreg;
+
+	*lockspace = ls;
+	return 0;
+
+ out_unreg:
+	kobject_unregister(&ls->ls_kobj);
+ out_del:
+	dlm_delete_debug_file(ls);
+	spin_lock(&lslist_lock);
+	list_del(&ls->ls_list);
+	spin_unlock(&lslist_lock);
+	dlm_recoverd_stop(ls);
+ out_rcomfree:
+	kfree(ls->ls_recover_buf);
+ out_dirfree:
+	kfree(ls->ls_dirtbl);
+ out_lkbfree:
+	kfree(ls->ls_lkbtbl);
+ out_rsbfree:
+	kfree(ls->ls_rsbtbl);
+ out_lsfree:
+	kfree(ls);
+ out:
+	module_put(THIS_MODULE);
+	return error;
+}
+
+int dlm_new_lockspace(char *name, int namelen, void **lockspace,
+		      uint32_t flags, int lvblen)
+{
+	int error = 0;
+
+	down(&ls_lock);
+	if (!ls_count)
+		error = threads_start();
+	if (error)
+		goto out;
+
+	error = new_lockspace(name, namelen, lockspace, flags, lvblen);
+	if (!error)
+		ls_count++;
+ out:
+	up(&ls_lock);
+	return error;
+}
+
+/* Return 1 if the lockspace still has active remote locks,
+ *        2 if the lockspace still has active local locks.
+ */
+static int lockspace_busy(struct dlm_ls *ls)
+{
+	int i, lkb_found = 0;
+	struct dlm_lkb *lkb;
+
+	/* NOTE: We check the lockidtbl here rather than the resource table.
+	   This is because there may be LKBs queued as ASTs that have been
+	   unlinked from their RSBs and are pending deletion once the AST has
+	   been delivered */
+
+	for (i = 0; i < ls->ls_lkbtbl_size; i++) {
+		read_lock(&ls->ls_lkbtbl[i].lock);
+		if (!list_empty(&ls->ls_lkbtbl[i].list)) {
+			lkb_found = 1;
+			list_for_each_entry(lkb, &ls->ls_lkbtbl[i].list,
+					    lkb_idtbl_list) {
+				if (!lkb->lkb_nodeid) {
+					read_unlock(&ls->ls_lkbtbl[i].lock);
+					return 2;
+				}
+			}
+		}
+		read_unlock(&ls->ls_lkbtbl[i].lock);
+	}
+	return lkb_found;
+}
+
+static int release_lockspace(struct dlm_ls *ls, int force)
+{
+	struct dlm_lkb *lkb;
+	struct dlm_rsb *rsb;
+	struct list_head *head;
+	int i;
+	int busy = lockspace_busy(ls);
+
+	if (busy > force)
+		return -EBUSY;
+
+	if (force < 3)
+		do_uevent(ls, 0);
+
+	dlm_recoverd_stop(ls);
+
+	remove_lockspace(ls);
+
+	dlm_delete_debug_file(ls);
+
+	dlm_astd_suspend();
+
+	kfree(ls->ls_recover_buf);
+
+	/*
+	 * Free direntry structs.
+	 */
+
+	dlm_dir_clear(ls);
+	kfree(ls->ls_dirtbl);
+
+	/*
+	 * Free all lkb's on lkbtbl[] lists.
+	 */
+
+	for (i = 0; i < ls->ls_lkbtbl_size; i++) {
+		head = &ls->ls_lkbtbl[i].list;
+		while (!list_empty(head)) {
+			lkb = list_entry(head->next, struct dlm_lkb,
+					 lkb_idtbl_list);
+
+			list_del(&lkb->lkb_idtbl_list);
+
+			dlm_del_ast(lkb);
+
+			if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
+				free_lvb(lkb->lkb_lvbptr);
+
+			free_lkb(lkb);
+		}
+	}
+	dlm_astd_resume();
+
+	kfree(ls->ls_lkbtbl);
+
+	/*
+	 * Free all rsb's on rsbtbl[] lists
+	 */
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		head = &ls->ls_rsbtbl[i].list;
+		while (!list_empty(head)) {
+			rsb = list_entry(head->next, struct dlm_rsb,
+					 res_hashchain);
+
+			list_del(&rsb->res_hashchain);
+			free_rsb(rsb);
+		}
+
+		head = &ls->ls_rsbtbl[i].toss;
+		while (!list_empty(head)) {
+			rsb = list_entry(head->next, struct dlm_rsb,
+					 res_hashchain);
+			list_del(&rsb->res_hashchain);
+			free_rsb(rsb);
+		}
+	}
+
+	kfree(ls->ls_rsbtbl);
+
+	/*
+	 * Free structures on any other lists
+	 */
+
+	kfree(ls->ls_recover_args);
+	dlm_clear_free_entries(ls);
+	dlm_clear_members(ls);
+	dlm_clear_members_gone(ls);
+	kfree(ls->ls_node_array);
+	kobject_unregister(&ls->ls_kobj);
+	kfree(ls);
+
+	down(&ls_lock);
+	ls_count--;
+	if (!ls_count)
+		threads_stop();
+	up(&ls_lock);
+
+	module_put(THIS_MODULE);
+	return 0;
+}
+
+/*
+ * Called when a system has released all its locks and is not going to use the
+ * lockspace any longer.  We free everything we're managing for this lockspace.
+ * Remaining nodes will go through the recovery process as if we'd died.  The
+ * lockspace must continue to function as usual, participating in recoveries,
+ * until this returns.
+ *
+ * Force has 4 possible values:
+ * 0 - don't destroy locksapce if it has any LKBs
+ * 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs
+ * 2 - destroy lockspace regardless of LKBs
+ * 3 - destroy lockspace as part of a forced shutdown
+ */
+
+int dlm_release_lockspace(void *lockspace, int force)
+{
+	struct dlm_ls *ls;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+	dlm_put_lockspace(ls);
+	return release_lockspace(ls, force);
+}
+

fs/dlm/lockspace.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCKSPACE_DOT_H__
+#define __LOCKSPACE_DOT_H__
+
+int dlm_lockspace_init(void);
+void dlm_lockspace_exit(void);
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
+struct dlm_ls *dlm_find_lockspace_local(void *id);
+void dlm_put_lockspace(struct dlm_ls *ls);
+
+#endif				/* __LOCKSPACE_DOT_H__ */
+

fs/dlm/lowcomms.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOWCOMMS_DOT_H__
+#define __LOWCOMMS_DOT_H__
+
+int dlm_lowcomms_init(void);
+void dlm_lowcomms_exit(void);
+int dlm_lowcomms_start(void);
+void dlm_lowcomms_stop(void);
+void *dlm_lowcomms_get_buffer(int nodeid, int len, int allocation, char **ppc);
+void dlm_lowcomms_commit_buffer(void *mh);
+
+#endif				/* __LOWCOMMS_DOT_H__ */
+

fs/dlm/lvb_table.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LVB_TABLE_DOT_H__
+#define __LVB_TABLE_DOT_H__
+
+extern const int dlm_lvb_operations[8][8];
+
+#endif

fs/dlm/main.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "lock.h"
+#include "memory.h"
+#include "lowcomms.h"
+#include "config.h"
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_register_debugfs(void);
+void dlm_unregister_debugfs(void);
+#else
+static inline int dlm_register_debugfs(void) { return 0; }
+static inline void dlm_unregister_debugfs(void) { }
+#endif
+
+static int __init init_dlm(void)
+{
+	int error;
+
+	error = dlm_memory_init();
+	if (error)
+		goto out;
+
+	error = dlm_lockspace_init();
+	if (error)
+		goto out_mem;
+
+	error = dlm_config_init();
+	if (error)
+		goto out_lockspace;
+
+	error = dlm_register_debugfs();
+	if (error)
+		goto out_config;
+
+	error = dlm_lowcomms_init();
+	if (error)
+		goto out_debug;
+
+	printk("DLM (built %s %s) installed\n", __DATE__, __TIME__);
+
+	return 0;
+
+ out_debug:
+	dlm_unregister_debugfs();
+ out_config:
+	dlm_config_exit();
+ out_lockspace:
+	dlm_lockspace_exit();
+ out_mem:
+	dlm_memory_exit();
+ out:
+	return error;
+}
+
+static void __exit exit_dlm(void)
+{
+	dlm_lowcomms_exit();
+	dlm_config_exit();
+	dlm_memory_exit();
+	dlm_lockspace_exit();
+	dlm_unregister_debugfs();
+}
+
+module_init(init_dlm);
+module_exit(exit_dlm);
+
+MODULE_DESCRIPTION("Distributed Lock Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+EXPORT_SYMBOL_GPL(dlm_new_lockspace);
+EXPORT_SYMBOL_GPL(dlm_release_lockspace);
+EXPORT_SYMBOL_GPL(dlm_lock);
+EXPORT_SYMBOL_GPL(dlm_unlock);
+

fs/dlm/member.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "recover.h"
+#include "lowcomms.h"
+#include "rcom.h"
+#include "config.h"
+
+/*
+ * Following called by dlm_recoverd thread
+ */
+
+static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
+{
+	struct dlm_member *memb = NULL;
+	struct list_head *tmp;
+	struct list_head *newlist = &new->list;
+	struct list_head *head = &ls->ls_nodes;
+
+	list_for_each(tmp, head) {
+		memb = list_entry(tmp, struct dlm_member, list);
+		if (new->nodeid < memb->nodeid)
+			break;
+	}
+
+	if (!memb)
+		list_add_tail(newlist, head);
+	else {
+		/* FIXME: can use list macro here */
+		newlist->prev = tmp->prev;
+		newlist->next = tmp;
+		tmp->prev->next = newlist;
+		tmp->prev = newlist;
+	}
+}
+
+static int dlm_add_member(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+	int w;
+
+	memb = kmalloc(sizeof(struct dlm_member), GFP_KERNEL);
+	if (!memb)
+		return -ENOMEM;
+
+	w = dlm_node_weight(ls->ls_name, nodeid);
+	if (w < 0)
+		return w;
+
+	memb->nodeid = nodeid;
+	memb->weight = w;
+	add_ordered_member(ls, memb);
+	ls->ls_num_nodes++;
+	return 0;
+}
+
+static void dlm_remove_member(struct dlm_ls *ls, struct dlm_member *memb)
+{
+	list_move(&memb->list, &ls->ls_nodes_gone);
+	ls->ls_num_nodes--;
+}
+
+static int dlm_is_member(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->nodeid == nodeid)
+			return TRUE;
+	}
+	return FALSE;
+}
+
+int dlm_is_removed(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+
+	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
+		if (memb->nodeid == nodeid)
+			return TRUE;
+	}
+	return FALSE;
+}
+
+static void clear_memb_list(struct list_head *head)
+{
+	struct dlm_member *memb;
+
+	while (!list_empty(head)) {
+		memb = list_entry(head->next, struct dlm_member, list);
+		list_del(&memb->list);
+		kfree(memb);
+	}
+}
+
+void dlm_clear_members(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes);
+	ls->ls_num_nodes = 0;
+}
+
+void dlm_clear_members_gone(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes_gone);
+}
+
+static void make_member_array(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	int i, w, x = 0, total = 0, all_zero = 0, *array;
+
+	kfree(ls->ls_node_array);
+	ls->ls_node_array = NULL;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->weight)
+			total += memb->weight;
+	}
+
+	/* all nodes revert to weight of 1 if all have weight 0 */
+
+	if (!total) {
+		total = ls->ls_num_nodes;
+		all_zero = 1;
+	}
+
+	ls->ls_total_weight = total;
+
+	array = kmalloc(sizeof(int) * total, GFP_KERNEL);
+	if (!array)
+		return;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (!all_zero && !memb->weight)
+			continue;
+
+		if (all_zero)
+			w = 1;
+		else
+			w = memb->weight;
+
+		DLM_ASSERT(x < total, printk("total %d x %d\n", total, x););
+
+		for (i = 0; i < w; i++)
+			array[x++] = memb->nodeid;
+	}
+
+	ls->ls_node_array = array;
+}
+
+/* send a status request to all members just to establish comms connections */
+
+static void ping_members(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	list_for_each_entry(memb, &ls->ls_nodes, list)
+		dlm_rcom_status(ls, memb->nodeid);
+}
+
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
+{
+	struct dlm_member *memb, *safe;
+	int i, error, found, pos = 0, neg = 0, low = -1;
+
+	/* move departed members from ls_nodes to ls_nodes_gone */
+
+	list_for_each_entry_safe(memb, safe, &ls->ls_nodes, list) {
+		found = FALSE;
+		for (i = 0; i < rv->node_count; i++) {
+			if (memb->nodeid == rv->nodeids[i]) {
+				found = TRUE;
+				break;
+			}
+		}
+
+		if (!found) {
+			neg++;
+			dlm_remove_member(ls, memb);
+			log_debug(ls, "remove member %d", memb->nodeid);
+		}
+	}
+
+	/* add new members to ls_nodes */
+
+	for (i = 0; i < rv->node_count; i++) {
+		if (dlm_is_member(ls, rv->nodeids[i]))
+			continue;
+		dlm_add_member(ls, rv->nodeids[i]);
+		pos++;
+		log_debug(ls, "add member %d", rv->nodeids[i]);
+	}
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (low == -1 || memb->nodeid < low)
+			low = memb->nodeid;
+	}
+	ls->ls_low_nodeid = low;
+
+	make_member_array(ls);
+	dlm_set_recover_status(ls, DLM_RS_NODES);
+	*neg_out = neg;
+
+	ping_members(ls);
+
+	error = dlm_recover_members_wait(ls);
+	log_debug(ls, "total members %d", ls->ls_num_nodes);
+	return error;
+}
+
+/*
+ * Following called from lockspace.c
+ */
+
+int dlm_ls_stop(struct dlm_ls *ls)
+{
+	int new;
+
+	/*
+	 * A stop cancels any recovery that's in progress (see RECOVERY_STOP,
+	 * dlm_recovery_stopped()) and prevents any new locks from being
+	 * processed (see RUNNING, dlm_locking_stopped()).
+	 */
+
+	spin_lock(&ls->ls_recover_lock);
+	set_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+	new = test_and_clear_bit(LSFL_RUNNING, &ls->ls_flags);
+	ls->ls_recover_seq++;
+	spin_unlock(&ls->ls_recover_lock);
+
+	/*
+	 * This in_recovery lock does two things:
+	 *
+	 * 1) Keeps this function from returning until all threads are out
+	 *    of locking routines and locking is truely stopped.
+	 * 2) Keeps any new requests from being processed until it's unlocked
+	 *    when recovery is complete.
+	 */
+
+	if (new)
+		down_write(&ls->ls_in_recovery);
+
+	/*
+	 * The recoverd suspend/resume makes sure that dlm_recoverd (if
+	 * running) has noticed the clearing of RUNNING above and quit
+	 * processing the previous recovery.  This will be true for all nodes
+	 * before any nodes start the new recovery.
+	 */
+
+	dlm_recoverd_suspend(ls);
+	ls->ls_recover_status = 0;
+	dlm_recoverd_resume(ls);
+	return 0;
+}
+
+int dlm_ls_start(struct dlm_ls *ls)
+{
+	struct dlm_recover *rv = NULL, *rv_old;
+	int *ids = NULL;
+	int error, count;
+
+	rv = kmalloc(sizeof(struct dlm_recover), GFP_KERNEL);
+	if (!rv)
+		return -ENOMEM;
+	memset(rv, 0, sizeof(struct dlm_recover));
+
+	error = count = dlm_nodeid_list(ls->ls_name, &ids);
+	if (error <= 0)
+		goto fail;
+
+	spin_lock(&ls->ls_recover_lock);
+
+	/* the lockspace needs to be stopped before it can be started */
+
+	if (!dlm_locking_stopped(ls)) {
+		spin_unlock(&ls->ls_recover_lock);
+		log_error(ls, "start ignored: lockspace running");
+		error = -EINVAL;
+		goto fail;
+	}
+
+	rv->nodeids = ids;
+	rv->node_count = count;
+	rv->seq = ++ls->ls_recover_seq;
+	rv_old = ls->ls_recover_args;
+	ls->ls_recover_args = rv;
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (rv_old) {
+		kfree(rv_old->nodeids);
+		kfree(rv_old);
+	}
+
+	dlm_recoverd_kick(ls);
+	return 0;
+
+ fail:
+	kfree(rv);
+	kfree(ids);
+	return error;
+}
+

fs/dlm/member.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMBER_DOT_H__
+#define __MEMBER_DOT_H__
+
+int dlm_ls_stop(struct dlm_ls *ls);
+int dlm_ls_start(struct dlm_ls *ls);
+void dlm_clear_members(struct dlm_ls *ls);
+void dlm_clear_members_gone(struct dlm_ls *ls);
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out);
+int dlm_is_removed(struct dlm_ls *ls, int nodeid);
+
+#endif                          /* __MEMBER_DOT_H__ */
+

fs/dlm/memory.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "config.h"
+#include "memory.h"
+
+static kmem_cache_t *lkb_cache;
+
+
+int dlm_memory_init(void)
+{
+	int ret = 0;
+
+	lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb),
+				__alignof__(struct dlm_lkb), 0, NULL, NULL);
+	if (!lkb_cache)
+		ret = -ENOMEM;
+	return ret;
+}
+
+void dlm_memory_exit(void)
+{
+	if (lkb_cache)
+		kmem_cache_destroy(lkb_cache);
+}
+
+char *allocate_lvb(struct dlm_ls *ls)
+{
+	char *p;
+
+	p = kmalloc(ls->ls_lvblen, GFP_KERNEL);
+	if (p)
+		memset(p, 0, ls->ls_lvblen);
+	return p;
+}
+
+void free_lvb(char *p)
+{
+	kfree(p);
+}
+
+uint64_t *allocate_range(struct dlm_ls *ls)
+{
+	int ralen = 4*sizeof(uint64_t);
+	uint64_t *p;
+
+	p = kmalloc(ralen, GFP_KERNEL);
+	if (p)
+		memset(p, 0, ralen);
+	return p;
+}
+
+void free_range(uint64_t *p)
+{
+	kfree(p);
+}
+
+/* FIXME: have some minimal space built-in to rsb for the name and
+   kmalloc a separate name if needed, like dentries are done */
+
+struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen)
+{
+	struct dlm_rsb *r;
+
+	DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,);
+
+	r = kmalloc(sizeof(*r) + namelen, GFP_KERNEL);
+	if (r)
+		memset(r, 0, sizeof(*r) + namelen);
+	return r;
+}
+
+void free_rsb(struct dlm_rsb *r)
+{
+	if (r->res_lvbptr)
+		free_lvb(r->res_lvbptr);
+	kfree(r);
+}
+
+struct dlm_lkb *allocate_lkb(struct dlm_ls *ls)
+{
+	struct dlm_lkb *lkb;
+
+	lkb = kmem_cache_alloc(lkb_cache, GFP_KERNEL);
+	if (lkb)
+		memset(lkb, 0, sizeof(*lkb));
+	return lkb;
+}
+
+void free_lkb(struct dlm_lkb *lkb)
+{
+	kmem_cache_free(lkb_cache, lkb);
+}
+
+struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen)
+{
+	struct dlm_direntry *de;
+
+	DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,);
+
+	de = kmalloc(sizeof(*de) + namelen, GFP_KERNEL);
+	if (de)
+		memset(de, 0, sizeof(*de) + namelen);
+	return de;
+}
+
+void free_direntry(struct dlm_direntry *de)
+{
+	kfree(de);
+}
+

fs/dlm/memory.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMORY_DOT_H__
+#define __MEMORY_DOT_H__
+
+int dlm_memory_init(void);
+void dlm_memory_exit(void);
+struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen);
+void free_rsb(struct dlm_rsb *r);
+struct dlm_lkb *allocate_lkb(struct dlm_ls *ls);
+void free_lkb(struct dlm_lkb *l);
+struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen);
+void free_direntry(struct dlm_direntry *de);
+char *allocate_lvb(struct dlm_ls *ls);
+void free_lvb(char *l);
+uint64_t *allocate_range(struct dlm_ls *ls);
+void free_range(uint64_t *l);
+
+#endif		/* __MEMORY_DOT_H__ */
+

fs/dlm/midcomms.c

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+/*
+ * midcomms.c
+ *
+ * This is the appallingly named "mid-level" comms layer.
+ *
+ * Its purpose is to take packets from the "real" comms layer,
+ * split them up into packets and pass them to the interested
+ * part of the locking mechanism.
+ *
+ * It also takes messages from the locking layer, formats them
+ * into packets and sends them to the comms layer.
+ */
+
+#include "dlm_internal.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "rcom.h"
+#include "lock.h"
+#include "midcomms.h"
+
+
+static void copy_from_cb(void *dst, const void *base, unsigned offset,
+			 unsigned len, unsigned limit)
+{
+	unsigned copy = len;
+
+	if ((copy + offset) > limit)
+		copy = limit - offset;
+	memcpy(dst, base + offset, copy);
+	len -= copy;
+	if (len)
+		memcpy(dst + copy, base, len);
+}
+
+/*
+ * Called from the low-level comms layer to process a buffer of
+ * commands.
+ *
+ * Only complete messages are processed here, any "spare" bytes from
+ * the end of a buffer are saved and tacked onto the front of the next
+ * message that comes in. I doubt this will happen very often but we
+ * need to be able to cope with it and I don't want the task to be waiting
+ * for packets to come in when there is useful work to be done.
+ */
+
+int dlm_process_incoming_buffer(int nodeid, const void *base,
+				unsigned offset, unsigned len, unsigned limit)
+{
+	unsigned char __tmp[DLM_INBUF_LEN];
+	struct dlm_header *msg = (struct dlm_header *) __tmp;
+	int ret = 0;
+	int err = 0;
+	uint16_t msglen;
+	uint32_t lockspace;
+
+	while (len > sizeof(struct dlm_header)) {
+
+		/* Copy just the header to check the total length.  The
+		   message may wrap around the end of the buffer back to the
+		   start, so we need to use a temp buffer and copy_from_cb. */
+
+		copy_from_cb(msg, base, offset, sizeof(struct dlm_header),
+			     limit);
+
+		msglen = le16_to_cpu(msg->h_length);
+		lockspace = msg->h_lockspace;
+
+		err = -EINVAL;
+		if (msglen < sizeof(struct dlm_header))
+			break;
+		err = -E2BIG;
+		if (msglen > dlm_config.buffer_size) {
+			log_print("message size %d from %d too big, buf len %d",
+				  msglen, nodeid, len);
+			break;
+		}
+		err = 0;
+
+		/* If only part of the full message is contained in this
+		   buffer, then do nothing and wait for lowcomms to call
+		   us again later with more data.  We return 0 meaning
+		   we've consumed none of the input buffer. */
+
+		if (msglen > len)
+			break;
+
+		/* Allocate a larger temp buffer if the full message won't fit
+		   in the buffer on the stack (which should work for most
+		   ordinary messages). */
+
+		if (msglen > sizeof(__tmp) &&
+		    msg == (struct dlm_header *) __tmp) {
+			msg = kmalloc(dlm_config.buffer_size, GFP_KERNEL);
+			if (msg == NULL)
+				return ret;
+		}
+
+		copy_from_cb(msg, base, offset, msglen, limit);
+
+		BUG_ON(lockspace != msg->h_lockspace);
+
+		ret += msglen;
+		offset += msglen;
+		offset &= (limit - 1);
+		len -= msglen;
+
+		switch (msg->h_cmd) {
+		case DLM_MSG:
+			dlm_receive_message(msg, nodeid, FALSE);
+			break;
+
+		case DLM_RCOM:
+			dlm_receive_rcom(msg, nodeid);
+			break;
+
+		default:
+			log_print("unknown msg type %x from %u: %u %u %u %u",
+				  msg->h_cmd, nodeid, msglen, len, offset, ret);
+		}
+	}
+
+	if (msg != (struct dlm_header *) __tmp)
+		kfree(msg);
+
+	return err ? err : ret;
+}
+

fs/dlm/midcomms.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MIDCOMMS_DOT_H__
+#define __MIDCOMMS_DOT_H__
+
+int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset,
+				unsigned len, unsigned limit);
+
+#endif				/* __MIDCOMMS_DOT_H__ */
+

fs/dlm/rcom.h

+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RCOM_DOT_H__
+#define __RCOM_DOT_H__
+
+int dlm_rcom_status(struct dlm_ls *ls, int nodeid);
+int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name,int last_len);
+int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid);
+int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
+void dlm_receive_rcom(struct dlm_header *hd, int nodeid);
+
+#endif
+