include/linux/if_ether.h


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Global definitions for the Ethernet IEEE 802.3 interface.
 *
 * Version:	@(#)if_ether.h	1.0.1a	02/08/94
 *
 * Author:	Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Donald Becker, <becker@super.org>
 *		Alan Cox, <alan@lxorguk.ukuu.org.uk>
 *		Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */

#ifndef _LINUX_IF_ETHER_H
#define _LINUX_IF_ETHER_H

#include <linux/types.h>

/*
 *	IEEE 802.3 Ethernet magic constants.  The frame sizes omit the preamble
 *	and FCS/CRC (frame check sequence).
 */

#define ETH_ALEN	6		/* Octets in one ethernet addr	 */
#define ETH_HLEN	14		/* Total octets in header.	 */
#define ETH_ZLEN	60		/* Min. octets in frame sans FCS */
#define ETH_DATA_LEN	1500		/* Max. octets in payload	 */
#define ETH_FRAME_LEN	1514		/* Max. octets in frame sans FCS */
#define ETH_FCS_LEN	4		/* Octets in the FCS		 */

/*
 *	These are the defined Ethernet Protocol ID's.
 */

#define ETH_P_LOOP	0x0060		/* Ethernet Loopback packet	*/
#define ETH_P_PUP	0x0200		/* Xerox PUP packet		*/
#define ETH_P_PUPAT	0x0201		/* Xerox PUP Addr Trans packet	*/
#define ETH_P_IP	0x0800		/* Internet Protocol packet	*/
#define ETH_P_X25	0x0805		/* CCITT X.25			*/
#define ETH_P_ARP	0x0806		/* Address Resolution packet	*/
#define	ETH_P_BPQ	0x08FF		/* G8BPQ AX.25 Ethernet Packet	[ NOT AN OFFICIALLY REGISTERED ID ] */
#define ETH_P_IEEEPUP	0x0a00		/* Xerox IEEE802.3 PUP packet */
#define ETH_P_IEEEPUPAT	0x0a01		/* Xerox IEEE802.3 PUP Addr Trans packet */
#define ETH_P_DEC       0x6000          /* DEC Assigned proto           */
#define ETH_P_DNA_DL    0x6001          /* DEC DNA Dump/Load            */
#define ETH_P_DNA_RC    0x6002          /* DEC DNA Remote Console       */
#define ETH_P_DNA_RT    0x6003          /* DEC DNA Routing              */
#define ETH_P_LAT       0x6004          /* DEC LAT                      */
#define ETH_P_DIAG      0x6005          /* DEC Diagnostics              */
#define ETH_P_CUST      0x6006          /* DEC Customer use             */
#define ETH_P_SCA       0x6007          /* DEC Systems Comms Arch       */
#define ETH_P_TEB	0x6558		/* Trans Ether Bridging		*/
#define ETH_P_RARP      0x8035		/* Reverse Addr Res packet	*/
#define ETH_P_ATALK	0x809B		/* Appletalk DDP		*/
#define ETH_P_AARP	0x80F3		/* Appletalk AARP		*/
#define ETH_P_8021Q	0x8100          /* 802.1Q VLAN Extended Header  */
#define ETH_P_IPX	0x8137		/* IPX over DIX			*/
#define ETH_P_IPV6	0x86DD		/* IPv6 over bluebook		*/
#define ETH_P_PAUSE	0x8808		/* IEEE Pause frames. See 802.3 31B */
#define ETH_P_SLOW	0x8809		/* Slow Protocol. See 802.3ad 43B */
#define ETH_P_WCCP	0x883E		/* Web-cache coordination protocol
					 * defined in draft-wilson-wrec-wccp-v2-00.txt */
#define ETH_P_PPP_DISC	0x8863		/* PPPoE discovery messages     */
#define ETH_P_PPP_SES	0x8864		/* PPPoE session messages	*/
#define ETH_P_MPLS_UC	0x8847		/* MPLS Unicast traffic		*/
#define ETH_P_MPLS_MC	0x8848		/* MPLS Multicast traffic	*/
#define ETH_P_ATMMPOA	0x884c		/* MultiProtocol Over ATM	*/
#define ETH_P_ATMFATE	0x8884		/* Frame-based ATM Transport
					 * over Ethernet
					 */
#define ETH_P_PAE	0x888E		/* Port Access Entity (IEEE 802.1X) */
#define ETH_P_AOE	0x88A2		/* ATA over Ethernet		*/
#define ETH_P_TIPC	0x88CA		/* TIPC 			*/
#define ETH_P_FCOE	0x8906		/* Fibre Channel over Ethernet  */
#define ETH_P_FIP	0x8914		/* FCoE Initialization Protocol */
#define ETH_P_EDSA	0xDADA		/* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */

/*
 *	Non DIX types. Won't clash for 1500 types.
 */

#define ETH_P_802_3	0x0001		/* Dummy type for 802.3 frames  */
#define ETH_P_AX25	0x0002		/* Dummy protocol id for AX.25  */
#define ETH_P_ALL	0x0003		/* Every packet (be careful!!!) */
#define ETH_P_802_2	0x0004		/* 802.2 frames 		*/
#define ETH_P_SNAP	0x0005		/* Internal only		*/
#define ETH_P_DDCMP     0x0006          /* DEC DDCMP: Internal only     */
#define ETH_P_WAN_PPP   0x0007          /* Dummy type for WAN PPP frames*/
#define ETH_P_PPP_MP    0x0008          /* Dummy type for PPP MP frames */
#define ETH_P_LOCALTALK 0x0009		/* Localtalk pseudo type 	*/
#define ETH_P_CAN	0x000C		/* Controller Area Network      */
#define ETH_P_PPPTALK	0x0010		/* Dummy type for Atalk over PPP*/
#define ETH_P_TR_802_2	0x0011		/* 802.2 frames 		*/
#define ETH_P_MOBITEX	0x0015		/* Mobitex (kaz@cafe.net)	*/
#define ETH_P_CONTROL	0x0016		/* Card specific control frames */
#define ETH_P_IRDA	0x0017		/* Linux-IrDA			*/
#define ETH_P_ECONET	0x0018		/* Acorn Econet			*/
#define ETH_P_HDLC	0x0019		/* HDLC frames			*/
#define ETH_P_ARCNET	0x001A		/* 1A for ArcNet :-)            */
#define ETH_P_DSA	0x001B		/* Distributed Switch Arch.	*/
#define ETH_P_TRAILER	0x001C		/* Trailer switch tagging	*/
#define ETH_P_PHONET	0x00F5		/* Nokia Phonet frames          */

/*
 *	This is an Ethernet frame header.
 */

struct ethhdr {
	unsigned char	h_dest[ETH_ALEN];	/* destination eth addr	*/
	unsigned char	h_source[ETH_ALEN];	/* source ether addr	*/
	__be16		h_proto;		/* packet type ID field	*/
} __attribute__((packed));

#ifdef __KERNEL__
#include <linux/skbuff.h>

static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
{
	return (struct ethhdr *)skb_mac_header(skb);
}

int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);

#ifdef CONFIG_SYSCTL
extern struct ctl_table ether_table[];
#endif

extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len);

/*
 *	Display a 6 byte device address (MAC) in a readable format.
 */
extern char *print_mac(char *buf, const unsigned char *addr);
#define MAC_FMT "%02x:%02x:%02x:%02x:%02x:%02x"
#define MAC_BUF_SIZE	18
#define DECLARE_MAC_BUF(var) char var[MAC_BUF_SIZE] __maybe_unused

#endif

#endif	/* _LINUX_IF_ETHER_H */
// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
**
**
*******************************************************************************
******************************************************************************/

#include <linux/module.h>

#include "dlm_internal.h"
#include "lockspace.h"
#include "member.h"
#include "recoverd.h"
#include "dir.h"
#include "lowcomms.h"
#include "config.h"
#include "memory.h"
#include "lock.h"
#include "recover.h"
#include "requestqueue.h"
#include "user.h"
#include "ast.h"

static int			ls_count;
static struct mutex		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;
	int rc = kstrtoint(buf, 0, &n);

	if (rc)
		return rc;
	ls = dlm_find_lockspace_local(ls->ls_local_handle);
	if (!ls)
		return -EINVAL;

	switch (n) {
	case 0:
		dlm_ls_stop(ls);
		break;
	case 1:
		dlm_ls_start(ls);
		break;
	default:
		ret = -EINVAL;
	}
	dlm_put_lockspace(ls);
	return ret;
}

static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	int rc = kstrtoint(buf, 0, &ls->ls_uevent_result);

	if (rc)
		return rc;
	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 snprintf(buf, PAGE_SIZE, "%u\n", ls->ls_global_id);
}

static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	int rc = kstrtouint(buf, 0, &ls->ls_global_id);

	if (rc)
		return rc;
	return len;
}

static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%u\n", dlm_no_directory(ls));
}

static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	int val;
	int rc = kstrtoint(buf, 0, &val);

	if (rc)
		return rc;
	if (val == 1)
		set_bit(LSFL_NODIR, &ls->ls_flags);
	return len;
}

static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf)
{
	uint32_t status = dlm_recover_status(ls);
	return snprintf(buf, PAGE_SIZE, "%x\n", status);
}

static ssize_t dlm_recover_nodeid_show(struct dlm_ls *ls, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%d\n", ls->ls_recover_nodeid);
}

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 dlm_attr dlm_attr_nodir = {
	.attr  = {.name = "nodir", .mode = S_IRUGO | S_IWUSR},
	.show  = dlm_nodir_show,
	.store = dlm_nodir_store
};

static struct dlm_attr dlm_attr_recover_status = {
	.attr  = {.name = "recover_status", .mode = S_IRUGO},
	.show  = dlm_recover_status_show
};

static struct dlm_attr dlm_attr_recover_nodeid = {
	.attr  = {.name = "recover_nodeid", .mode = S_IRUGO},
	.show  = dlm_recover_nodeid_show
};

static struct attribute *dlm_attrs[] = {
	&dlm_attr_control.attr,
	&dlm_attr_event.attr,
	&dlm_attr_id.attr,
	&dlm_attr_nodir.attr,
	&dlm_attr_recover_status.attr,
	&dlm_attr_recover_nodeid.attr,
	NULL,
};
ATTRIBUTE_GROUPS(dlm);

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 void lockspace_kobj_release(struct kobject *k)
{
	struct dlm_ls *ls  = container_of(k, struct dlm_ls, ls_kobj);
	kfree(ls);
}

static const struct sysfs_ops dlm_attr_ops = {
	.show  = dlm_attr_show,
	.store = dlm_attr_store,
};

static struct kobj_type dlm_ktype = {
	.default_groups = dlm_groups,
	.sysfs_ops     = &dlm_attr_ops,
	.release       = lockspace_kobj_release,
};

static struct kset *dlm_kset;

static int do_uevent(struct dlm_ls *ls, int in)
{
	if (in)
		kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
	else
		kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);

	log_rinfo(ls, "%s the lockspace group...", in ? "joining" : "leaving");

	/* dlm_controld will see the uevent, do the necessary group management
	   and then write to sysfs to wake us */

	wait_event(ls->ls_uevent_wait,
		   test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));

	log_rinfo(ls, "group event done %d", ls->ls_uevent_result);

	return ls->ls_uevent_result;
}

static int dlm_uevent(struct kset *kset, struct kobject *kobj,
		      struct kobj_uevent_env *env)
{
	struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj);

	add_uevent_var(env, "LOCKSPACE=%s", ls->ls_name);
	return 0;
}

static const struct kset_uevent_ops dlm_uevent_ops = {
	.uevent = dlm_uevent,
};

int __init dlm_lockspace_init(void)
{
	ls_count = 0;
	mutex_init(&ls_lock);
	INIT_LIST_HEAD(&lslist);
	spin_lock_init(&lslist_lock);

	dlm_kset = kset_create_and_add("dlm", &dlm_uevent_ops, kernel_kobj);
	if (!dlm_kset) {
		printk(KERN_WARNING "%s: can not create kset\n", __func__);
		return -ENOMEM;
	}
	return 0;
}

void dlm_lockspace_exit(void)
{
	kset_unregister(dlm_kset);
}

static struct dlm_ls *find_ls_to_scan(void)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (time_after_eq(jiffies, ls->ls_scan_time +
					    dlm_config.ci_scan_secs * HZ)) {
			spin_unlock(&lslist_lock);
			return ls;
		}
	}
	spin_unlock(&lslist_lock);
	return NULL;
}

static int dlm_scand(void *data)
{
	struct dlm_ls *ls;

	while (!kthread_should_stop()) {
		ls = find_ls_to_scan();
		if (ls) {
			if (dlm_lock_recovery_try(ls)) {
				ls->ls_scan_time = jiffies;
				dlm_scan_rsbs(ls);
				dlm_scan_timeout(ls);
				dlm_scan_waiters(ls);
				dlm_unlock_recovery(ls);
			} else {
				ls->ls_scan_time += HZ;
			}
			continue;
		}
		schedule_timeout_interruptible(dlm_config.ci_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);
}

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(dlm_lockspace_t *lockspace)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (ls->ls_local_handle == lockspace) {
			ls->ls_count++;
			goto out;
		}
	}
	ls = NULL;
 out:
	spin_unlock(&lslist_lock);
	return ls;
}

struct dlm_ls *dlm_find_lockspace_device(int minor)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (ls->ls_device.minor == minor) {
			ls->ls_count++;
			goto out;
		}
	}
	ls = NULL;
 out:
	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) {
			WARN_ON(ls->ls_create_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;

	error = dlm_scand_start();
	if (error) {
		log_print("cannot start dlm_scand thread %d", error);
		goto 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();
 fail:
	return error;
}

static void threads_stop(void)
{
	dlm_scand_stop();
	dlm_lowcomms_stop();
}

static int new_lockspace(const char *name, const char *cluster,
			 uint32_t flags, int lvblen,
			 const struct dlm_lockspace_ops *ops, void *ops_arg,
			 int *ops_result, dlm_lockspace_t **lockspace)
{
	struct dlm_ls *ls;
	int i, size, error;
	int do_unreg = 0;
	int namelen = strlen(name);

	if (namelen > DLM_LOCKSPACE_LEN || namelen == 0)
		return -EINVAL;

	if (!lvblen || (lvblen % 8))
		return -EINVAL;

	if (!try_module_get(THIS_MODULE))
		return -EINVAL;

	if (!dlm_user_daemon_available()) {
		log_print("dlm user daemon not available");
		error = -EUNATCH;
		goto out;
	}

	if (ops && ops_result) {
	       	if (!dlm_config.ci_recover_callbacks)
			*ops_result = -EOPNOTSUPP;
		else
			*ops_result = 0;
	}

	if (!cluster)
		log_print("dlm cluster name '%s' is being used without an application provided cluster name",
			  dlm_config.ci_cluster_name);

	if (dlm_config.ci_recover_callbacks && cluster &&
	    strncmp(cluster, dlm_config.ci_cluster_name, DLM_LOCKSPACE_LEN)) {
		log_print("dlm cluster name '%s' does not match "
			  "the application cluster name '%s'",
			  dlm_config.ci_cluster_name, cluster);
		error = -EBADR;
		goto out;
	}

	error = 0;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		WARN_ON(ls->ls_create_count <= 0);
		if (ls->ls_namelen != namelen)
			continue;
		if (memcmp(ls->ls_name, name, namelen))
			continue;
		if (flags & DLM_LSFL_NEWEXCL) {
			error = -EEXIST;
			break;
		}
		ls->ls_create_count++;
		*lockspace = ls;
		error = 1;
		break;
	}
	spin_unlock(&lslist_lock);

	if (error)
		goto out;

	error = -ENOMEM;

	ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_NOFS);
	if (!ls)
		goto out;
	memcpy(ls->ls_name, name, namelen);
	ls->ls_namelen = namelen;
	ls->ls_lvblen = lvblen;
	ls->ls_count = 0;
	ls->ls_flags = 0;
	ls->ls_scan_time = jiffies;

	if (ops && dlm_config.ci_recover_callbacks) {
		ls->ls_ops = ops;
		ls->ls_ops_arg = ops_arg;
	}

	if (flags & DLM_LSFL_TIMEWARN)
		set_bit(LSFL_TIMEWARN, &ls->ls_flags);

	/* ls_exflags are forced to match among nodes, and we don't
	   need to require all nodes to have some flags set */
	ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
				    DLM_LSFL_NEWEXCL));

	size = dlm_config.ci_rsbtbl_size;
	ls->ls_rsbtbl_size = size;

	ls->ls_rsbtbl = vmalloc(array_size(size, sizeof(struct dlm_rsbtable)));
	if (!ls->ls_rsbtbl)
		goto out_lsfree;
	for (i = 0; i < size; i++) {
		ls->ls_rsbtbl[i].keep.rb_node = NULL;
		ls->ls_rsbtbl[i].toss.rb_node = NULL;
		spin_lock_init(&ls->ls_rsbtbl[i].lock);
	}

	spin_lock_init(&ls->ls_remove_spin);

	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
		ls->ls_remove_names[i] = kzalloc(DLM_RESNAME_MAXLEN+1,
						 GFP_KERNEL);
		if (!ls->ls_remove_names[i])
			goto out_rsbtbl;
	}

	idr_init(&ls->ls_lkbidr);
	spin_lock_init(&ls->ls_lkbidr_spin);

	INIT_LIST_HEAD(&ls->ls_waiters);
	mutex_init(&ls->ls_waiters_mutex);
	INIT_LIST_HEAD(&ls->ls_orphans);
	mutex_init(&ls->ls_orphans_mutex);
	INIT_LIST_HEAD(&ls->ls_timeout);
	mutex_init(&ls->ls_timeout_mutex);

	INIT_LIST_HEAD(&ls->ls_new_rsb);
	spin_lock_init(&ls->ls_new_rsb_spin);

	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_rsb_dentry = NULL;
	ls->ls_debug_waiters_dentry = NULL;

	init_waitqueue_head(&ls->ls_uevent_wait);
	ls->ls_uevent_result = 0;
	init_completion(&ls->ls_members_done);
	ls->ls_members_result = -1;

	mutex_init(&ls->ls_cb_mutex);
	INIT_LIST_HEAD(&ls->ls_cb_delay);

	ls->ls_recoverd_task = NULL;
	mutex_init(&ls->ls_recoverd_active);
	spin_lock_init(&ls->ls_recover_lock);
	spin_lock_init(&ls->ls_rcom_spin);
	get_random_bytes(&ls->ls_rcom_seq, sizeof(uint64_t));
	ls->ls_recover_status = 0;
	ls->ls_recover_seq = 0;
	ls->ls_recover_args = NULL;
	init_rwsem(&ls->ls_in_recovery);
	init_rwsem(&ls->ls_recv_active);
	INIT_LIST_HEAD(&ls->ls_requestqueue);
	mutex_init(&ls->ls_requestqueue_mutex);
	mutex_init(&ls->ls_clear_proc_locks);

	ls->ls_recover_buf = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
	if (!ls->ls_recover_buf)
		goto out_lkbidr;

	ls->ls_slot = 0;
	ls->ls_num_slots = 0;
	ls->ls_slots_size = 0;
	ls->ls_slots = NULL;

	INIT_LIST_HEAD(&ls->ls_recover_list);
	spin_lock_init(&ls->ls_recover_list_lock);
	idr_init(&ls->ls_recover_idr);
	spin_lock_init(&ls->ls_recover_idr_lock);
	ls->ls_recover_list_count = 0;
	ls->ls_local_handle = ls;
	init_waitqueue_head(&ls->ls_wait_general);
	INIT_LIST_HEAD(&ls->ls_root_list);
	init_rwsem(&ls->ls_root_sem);

	spin_lock(&lslist_lock);
	ls->ls_create_count = 1;
	list_add(&ls->ls_list, &lslist);
	spin_unlock(&lslist_lock);

	if (flags & DLM_LSFL_FS) {
		error = dlm_callback_start(ls);
		if (error) {
			log_error(ls, "can't start dlm_callback %d", error);
			goto out_delist;
		}
	}

	init_waitqueue_head(&ls->ls_recover_lock_wait);

	/*
	 * Once started, dlm_recoverd first looks for ls in lslist, then
	 * initializes ls_in_recovery as locked in "down" mode.  We need
	 * to wait for the wakeup from dlm_recoverd because in_recovery
	 * has to start out in down mode.
	 */

	error = dlm_recoverd_start(ls);
	if (error) {
		log_error(ls, "can't start dlm_recoverd %d", error);
		goto out_callback;
	}

	wait_event(ls->ls_recover_lock_wait,
		   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));

	/* let kobject handle freeing of ls if there's an error */
	do_unreg = 1;

	ls->ls_kobj.kset = dlm_kset;
	error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
				     "%s", ls->ls_name);
	if (error)
		goto out_recoverd;
	kobject_uevent(&ls->ls_kobj, KOBJ_ADD);

	/* This uevent triggers dlm_controld in userspace to add us to the
	   group of nodes that are members of this lockspace (managed by the
	   cluster infrastructure.)  Once it's done that, it tells us who the
	   current lockspace members are (via configfs) and then tells the
	   lockspace to start running (via sysfs) in dlm_ls_start(). */

	error = do_uevent(ls, 1);
	if (error)
		goto out_recoverd;

	wait_for_completion(&ls->ls_members_done);
	error = ls->ls_members_result;
	if (error)
		goto out_members;

	dlm_create_debug_file(ls);

	log_rinfo(ls, "join complete");
	*lockspace = ls;
	return 0;

 out_members:
	do_uevent(ls, 0);
	dlm_clear_members(ls);
	kfree(ls->ls_node_array);
 out_recoverd:
	dlm_recoverd_stop(ls);
 out_callback:
	dlm_callback_stop(ls);
 out_delist:
	spin_lock(&lslist_lock);
	list_del(&ls->ls_list);
	spin_unlock(&lslist_lock);
	idr_destroy(&ls->ls_recover_idr);
	kfree(ls->ls_recover_buf);
 out_lkbidr:
	idr_destroy(&ls->ls_lkbidr);
 out_rsbtbl:
	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++)
		kfree(ls->ls_remove_names[i]);
	vfree(ls->ls_rsbtbl);
 out_lsfree:
	if (do_unreg)
		kobject_put(&ls->ls_kobj);
	else
		kfree(ls);
 out:
	module_put(THIS_MODULE);
	return error;
}

int dlm_new_lockspace(const char *name, const char *cluster,
		      uint32_t flags, int lvblen,
		      const struct dlm_lockspace_ops *ops, void *ops_arg,
		      int *ops_result, dlm_lockspace_t **lockspace)
{
	int error = 0;

	mutex_lock(&ls_lock);
	if (!ls_count)
		error = threads_start();
	if (error)
		goto out;

	error = new_lockspace(name, cluster, flags, lvblen, ops, ops_arg,
			      ops_result, lockspace);
	if (!error)
		ls_count++;
	if (error > 0)
		error = 0;
	if (!ls_count)
		threads_stop();
 out:
	mutex_unlock(&ls_lock);
	return error;
}

static int lkb_idr_is_local(int id, void *p, void *data)
{
	struct dlm_lkb *lkb = p;

	return lkb->lkb_nodeid == 0 && lkb->lkb_grmode != DLM_LOCK_IV;
}

static int lkb_idr_is_any(int id, void *p, void *data)
{
	return 1;
}

static int lkb_idr_free(int id, void *p, void *data)
{
	struct dlm_lkb *lkb = p;

	if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
		dlm_free_lvb(lkb->lkb_lvbptr);

	dlm_free_lkb(lkb);
	return 0;
}

/* NOTE: We check the lkbidr 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 */

static int lockspace_busy(struct dlm_ls *ls, int force)
{
	int rv;

	spin_lock(&ls->ls_lkbidr_spin);
	if (force == 0) {
		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_any, ls);
	} else if (force == 1) {
		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_local, ls);
	} else {
		rv = 0;
	}
	spin_unlock(&ls->ls_lkbidr_spin);
	return rv;
}

static int release_lockspace(struct dlm_ls *ls, int force)
{
	struct dlm_rsb *rsb;
	struct rb_node *n;
	int i, busy, rv;

	busy = lockspace_busy(ls, force);

	spin_lock(&lslist_lock);
	if (ls->ls_create_count == 1) {
		if (busy) {
			rv = -EBUSY;
		} else {
			/* remove_lockspace takes ls off lslist */
			ls->ls_create_count = 0;
			rv = 0;
		}
	} else if (ls->ls_create_count > 1) {
		rv = --ls->ls_create_count;
	} else {
		rv = -EINVAL;
	}
	spin_unlock(&lslist_lock);

	if (rv) {
		log_debug(ls, "release_lockspace no remove %d", rv);
		return rv;
	}

	dlm_device_deregister(ls);

	if (force < 3 && dlm_user_daemon_available())
		do_uevent(ls, 0);

	dlm_recoverd_stop(ls);

	dlm_callback_stop(ls);

	remove_lockspace(ls);

	dlm_delete_debug_file(ls);

	idr_destroy(&ls->ls_recover_idr);
	kfree(ls->ls_recover_buf);

	/*
	 * Free all lkb's in idr
	 */

	idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls);
	idr_destroy(&ls->ls_lkbidr);

	/*
	 * Free all rsb's on rsbtbl[] lists
	 */

	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
		while ((n = rb_first(&ls->ls_rsbtbl[i].keep))) {
			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
			rb_erase(n, &ls->ls_rsbtbl[i].keep);
			dlm_free_rsb(rsb);
		}

		while ((n = rb_first(&ls->ls_rsbtbl[i].toss))) {
			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
			rb_erase(n, &ls->ls_rsbtbl[i].toss);
			dlm_free_rsb(rsb);
		}
	}

	vfree(ls->ls_rsbtbl);

	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++)
		kfree(ls->ls_remove_names[i]);

	while (!list_empty(&ls->ls_new_rsb)) {
		rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb,
				       res_hashchain);
		list_del(&rsb->res_hashchain);
		dlm_free_rsb(rsb);
	}

	/*
	 * Free structures on any other lists
	 */

	dlm_purge_requestqueue(ls);
	kfree(ls->ls_recover_args);
	dlm_clear_members(ls);
	dlm_clear_members_gone(ls);
	kfree(ls->ls_node_array);
	log_rinfo(ls, "release_lockspace final free");
	kobject_put(&ls->ls_kobj);
	/* The ls structure will be freed when the kobject is done with */

	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;
	int error;

	ls = dlm_find_lockspace_local(lockspace);
	if (!ls)
		return -EINVAL;
	dlm_put_lockspace(ls);

	mutex_lock(&ls_lock);
	error = release_lockspace(ls, force);
	if (!error)
		ls_count--;
	if (!ls_count)
		threads_stop();
	mutex_unlock(&ls_lock);

	return error;
}

void dlm_stop_lockspaces(void)
{
	struct dlm_ls *ls;
	int count;

 restart:
	count = 0;
	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (!test_bit(LSFL_RUNNING, &ls->ls_flags)) {
			count++;
			continue;
		}
		spin_unlock(&lslist_lock);
		log_error(ls, "no userland control daemon, stopping lockspace");
		dlm_ls_stop(ls);
		goto restart;
	}
	spin_unlock(&lslist_lock);

	if (count)
		log_print("dlm user daemon left %d lockspaces", count);
}