summaryrefslogtreecommitdiff
path: root/fs/ocfs2/stack_user.c
blob: a5e58e2b9d591e3f07fdd551dc8eb2a08ebfd0de (plain)
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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
/* -*- 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 <asm/uaccess.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, including the newline.
 * Thus, the protocol tag is 'T01\n'.  If the version tag written is
 * unknown, -EINVAL is returned.  Once the negotiation is complete, the
 * client can start sending messages.
 *
 * The T01 protocol only has one message, "DOWN".  It has the following
 * syntax:
 *
 *  DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline>
 *
 * eg:
 *
 *  DOWN 632A924FDD844190BDA93C0DF6B94899 00000001\n
 *
 * This is 47 characters.
 */

/*
 * Whether or not the client has done the handshake.
 * For now, we have just one protocol version.
 */
#define OCFS2_CONTROL_PROTO			"T01\n"
#define OCFS2_CONTROL_PROTO_LEN			4
#define OCFS2_CONTROL_HANDSHAKE_INVALID		(0)
#define OCFS2_CONTROL_HANDSHAKE_READ		(1)
#define OCFS2_CONTROL_HANDSHAKE_VALID		(2)
#define OCFS2_CONTROL_MESSAGE_DOWN		"DOWN"
#define OCFS2_CONTROL_MESSAGE_DOWN_LEN		4
#define OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN	47
#define OCFS2_TEXT_UUID_LEN			32
#define OCFS2_CONTROL_MESSAGE_NODENUM_LEN	8

/*
 * 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;
};

struct ocfs2_control_private {
	struct list_head op_list;
	int op_state;
};

static atomic_t ocfs2_control_opened;

static LIST_HEAD(ocfs2_live_connection_list);
static LIST_HEAD(ocfs2_control_private_list);
static DEFINE_MUTEX(ocfs2_control_lock);

static inline void ocfs2_control_set_handshake_state(struct file *file,
						     int state)
{
	struct ocfs2_control_private *p = file->private_data;
	p->op_state = state;
}

static inline int ocfs2_control_get_handshake_state(struct file *file)
{
	struct ocfs2_control_private *p = file->private_data;
	return p->op_state;
}

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_cfu(void *target, size_t target_len,
				 const char __user *buf, size_t count)
{
	/* The T01 expects write(2) calls to have exactly one command */
	if (count != target_len)
		return -EINVAL;

	if (copy_from_user(target, buf, target_len))
		return -EFAULT;

	return count;
}

static ssize_t ocfs2_control_validate_handshake(struct file *file,
						const char __user *buf,
						size_t count)
{
	ssize_t ret;
	char kbuf[OCFS2_CONTROL_PROTO_LEN];

	ret = ocfs2_control_cfu(kbuf, OCFS2_CONTROL_PROTO_LEN,
				buf, count);
	if (ret != count)
		return ret;

	if (strncmp(kbuf, OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN))
		return -EINVAL;

	atomic_inc(&ocfs2_control_opened);
	ocfs2_control_set_handshake_state(file,
					  OCFS2_CONTROL_HANDSHAKE_VALID);


	return count;
}

static void ocfs2_control_send_down(const char *uuid,
				    int nodenum)
{
	struct ocfs2_live_connection *c;

	mutex_lock(&ocfs2_control_lock);

	c = ocfs2_connection_find(uuid);
	if (c) {
		BUG_ON(c->oc_conn == NULL);
		c->oc_conn->cc_recovery_handler(nodenum,
						c->oc_conn->cc_recovery_data);
	}

	mutex_unlock(&ocfs2_control_lock);
}

/* DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline> */
struct ocfs2_control_message_down {
	char	tag[OCFS2_CONTROL_MESSAGE_DOWN_LEN];
	char	space1;
	char	uuid[OCFS2_TEXT_UUID_LEN];
	char	space2;
	char	nodestr[OCFS2_CONTROL_MESSAGE_NODENUM_LEN];
	char	newline;
};

static ssize_t ocfs2_control_message(struct file *file,
				     const char __user *buf,
				     size_t count)
{
	ssize_t ret;
	char *p = NULL;
	long nodenum;
	struct ocfs2_control_message_down msg;

	/* Try to catch padding issues */
	WARN_ON(offsetof(struct ocfs2_control_message_down, uuid) !=
		(sizeof(msg.tag) + sizeof(msg.space1)));

	memset(&msg, 0, sizeof(struct ocfs2_control_message_down));
	ret = ocfs2_control_cfu(&msg, OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN,
				buf, count);
	if (ret != count)
		return ret;

	if (strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_DOWN,
		    strlen(OCFS2_CONTROL_MESSAGE_DOWN)))
		return -EINVAL;

	if ((msg.space1 != ' ') || (msg.space2 != ' ') ||
	    (msg.newline != '\n'))
		return -EINVAL;
	msg.space1 = msg.space2 = msg.newline = '\0';

	nodenum = simple_strtol(msg.nodestr, &p, 16);
	if (!p || *p)
		return -EINVAL;

	if ((nodenum == LONG_MIN) || (nodenum == LONG_MAX) ||
	    (nodenum > INT_MAX) || (nodenum < 0))
		return -ERANGE;

	ocfs2_control_send_down(msg.uuid, nodenum);

	return count;
}

static ssize_t ocfs2_control_write(struct file *file,
				   const char __user *buf,
				   size_t count,
				   loff_t *ppos)
{
	ssize_t ret;

	switch (ocfs2_control_get_handshake_state(file)) {
		case OCFS2_CONTROL_HANDSHAKE_INVALID:
			ret = -EINVAL;
			break;

		case OCFS2_CONTROL_HANDSHAKE_READ:
			ret = ocfs2_control_validate_handshake(file, buf,
							       count);
			break;

		case OCFS2_CONTROL_HANDSHAKE_VALID:
			ret = ocfs2_control_message(file, buf, count);
			break;

		default:
			BUG();
			ret = -EIO;
			break;
	}

	return ret;
}

/*
 * This is a naive version.  If we ever have a new protocol, we'll expand
 * it.  Probably using seq_file.
 */
static ssize_t ocfs2_control_read(struct file *file,
				  char __user *buf,
				  size_t count,
				  loff_t *ppos)
{
	char *proto_string = OCFS2_CONTROL_PROTO;
	size_t to_write = 0;

	if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
		return 0;

	to_write = OCFS2_CONTROL_PROTO_LEN - *ppos;
	if (to_write > count)
		to_write = count;
	if (copy_to_user(buf, proto_string + *ppos, to_write))
		return -EFAULT;

	*ppos += to_write;

	/* Have we read the whole protocol list? */
	if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
		ocfs2_control_set_handshake_state(file,
						  OCFS2_CONTROL_HANDSHAKE_READ);

	return to_write;
}

static int ocfs2_control_release(struct inode *inode, struct file *file)
{
	struct ocfs2_control_private *p = file->private_data;

	mutex_lock(&ocfs2_control_lock);

	if (ocfs2_control_get_handshake_state(file) !=
	    OCFS2_CONTROL_HANDSHAKE_VALID)
		goto out;

	if (atomic_dec_and_test(&ocfs2_control_opened)) {
		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();
		}
	}

out:
	list_del_init(&p->op_list);
	file->private_data = NULL;

	mutex_unlock(&ocfs2_control_lock);

	kfree(p);

	return 0;
}

static int ocfs2_control_open(struct inode *inode, struct file *file)
{
	struct ocfs2_control_private *p;

	p = kzalloc(sizeof(struct ocfs2_control_private), GFP_KERNEL);
	if (!p)
		return -ENOMEM;

	mutex_lock(&ocfs2_control_lock);
	file->private_data = p;
	list_add(&p->op_list, &ocfs2_control_private_list);
	mutex_unlock(&ocfs2_control_lock);

	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);