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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
|
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* stack_user.c
*
* Code which interfaces ocfs2 with fs/dlm and a userspace stack.
*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation, version 2.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/reboot.h>
#include "stackglue.h"
/*
* The control protocol starts with a handshake. Until the handshake
* is complete, the control device will fail all write(2)s.
*
* The handshake is simple. First, the client reads until EOF. Each line
* of output is a supported protocol tag. All protocol tags are a single
* character followed by a two hex digit version number. Currently the
* only things supported is T01, for "Text-base version 0x01". Next, the
* client writes the version they would like to use. If the version tag
* written is unknown, -EINVAL is returned. Once the negotiation is
* complete, the client can start sending messages.
*/
/*
* ocfs2_live_connection is refcounted because the filesystem and
* miscdevice sides can detach in different order. Let's just be safe.
*/
struct ocfs2_live_connection {
struct list_head oc_list;
struct ocfs2_cluster_connection *oc_conn;
};
static atomic_t ocfs2_control_opened;
static LIST_HEAD(ocfs2_live_connection_list);
static DEFINE_MUTEX(ocfs2_control_lock);
static struct ocfs2_live_connection *ocfs2_connection_find(const char *name)
{
size_t len = strlen(name);
struct ocfs2_live_connection *c;
BUG_ON(!mutex_is_locked(&ocfs2_control_lock));
list_for_each_entry(c, &ocfs2_live_connection_list, oc_list) {
if ((c->oc_conn->cc_namelen == len) &&
!strncmp(c->oc_conn->cc_name, name, len))
return c;
}
return c;
}
/*
* ocfs2_live_connection structures are created underneath the ocfs2
* mount path. Since the VFS prevents multiple calls to
* fill_super(), we can't get dupes here.
*/
static int ocfs2_live_connection_new(struct ocfs2_cluster_connection *conn,
struct ocfs2_live_connection **c_ret)
{
int rc = 0;
struct ocfs2_live_connection *c;
c = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL);
if (!c)
return -ENOMEM;
mutex_lock(&ocfs2_control_lock);
c->oc_conn = conn;
if (atomic_read(&ocfs2_control_opened))
list_add(&c->oc_list, &ocfs2_live_connection_list);
else {
printk(KERN_ERR
"ocfs2: Userspace control daemon is not present\n");
rc = -ESRCH;
}
mutex_unlock(&ocfs2_control_lock);
if (!rc)
*c_ret = c;
else
kfree(c);
return rc;
}
/*
* This function disconnects the cluster connection from ocfs2_control.
* Afterwards, userspace can't affect the cluster connection.
*/
static void ocfs2_live_connection_drop(struct ocfs2_live_connection *c)
{
mutex_lock(&ocfs2_control_lock);
list_del_init(&c->oc_list);
c->oc_conn = NULL;
mutex_unlock(&ocfs2_control_lock);
kfree(c);
}
static ssize_t ocfs2_control_write(struct file *file,
const char __user *buf,
size_t count,
loff_t *ppos)
{
return 0;
}
static ssize_t ocfs2_control_read(struct file *file,
char __user *buf,
size_t count,
loff_t *ppos)
{
return 0;
}
static int ocfs2_control_release(struct inode *inode, struct file *file)
{
if (atomic_dec_and_test(&ocfs2_control_opened)) {
mutex_lock(&ocfs2_control_lock);
if (!list_empty(&ocfs2_live_connection_list)) {
/* XXX: Do bad things! */
printk(KERN_ERR
"ocfs2: Unexpected release of ocfs2_control!\n"
" Loss of cluster connection requires "
"an emergency restart!\n");
emergency_restart();
}
mutex_unlock(&ocfs2_control_lock);
}
return 0;
}
static int ocfs2_control_open(struct inode *inode, struct file *file)
{
atomic_inc(&ocfs2_control_opened);
return 0;
}
static const struct file_operations ocfs2_control_fops = {
.open = ocfs2_control_open,
.release = ocfs2_control_release,
.read = ocfs2_control_read,
.write = ocfs2_control_write,
.owner = THIS_MODULE,
};
struct miscdevice ocfs2_control_device = {
.minor = MISC_DYNAMIC_MINOR,
.name = "ocfs2_control",
.fops = &ocfs2_control_fops,
};
static int ocfs2_control_init(void)
{
int rc;
atomic_set(&ocfs2_control_opened, 0);
rc = misc_register(&ocfs2_control_device);
if (rc)
printk(KERN_ERR
"ocfs2: Unable to register ocfs2_control device "
"(errno %d)\n",
-rc);
return rc;
}
static void ocfs2_control_exit(void)
{
int rc;
rc = misc_deregister(&ocfs2_control_device);
if (rc)
printk(KERN_ERR
"ocfs2: Unable to deregister ocfs2_control device "
"(errno %d)\n",
-rc);
}
static int __init user_stack_init(void)
{
return ocfs2_control_init();
}
static void __exit user_stack_exit(void)
{
ocfs2_control_exit();
}
MODULE_AUTHOR("Oracle");
MODULE_DESCRIPTION("ocfs2 driver for userspace cluster stacks");
MODULE_LICENSE("GPL");
module_init(user_stack_init);
module_exit(user_stack_exit);
|
