aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/netconsole.c
blob: ca142c47b2e4c631a90c5b61382c99c49f784dd2 (plain) (blame)
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
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
/*
 *  linux/drivers/net/netconsole.c
 *
 *  Copyright (C) 2001  Ingo Molnar <mingo@redhat.com>
 *
 *  This file contains the implementation of an IRQ-safe, crash-safe
 *  kernel console implementation that outputs kernel messages to the
 *  network.
 *
 * Modification history:
 *
 * 2001-09-17    started by Ingo Molnar.
 * 2003-08-11    2.6 port by Matt Mackall
 *               simplified options
 *               generic card hooks
 *               works non-modular
 * 2003-09-07    rewritten with netpoll api
 */

/****************************************************************
 *      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, or (at your option)
 *      any later version.
 *
 *      This program is distributed in the hope that it will be useful,
 *      but WITHOUT ANY WARRANTY; without even the implied warranty of
 *      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *      GNU General Public License for more details.
 *
 *      You should have received a copy of the GNU General Public License
 *      along with this program; if not, write to the Free Software
 *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 ****************************************************************/

#include <linux/mm.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/console.h>
#include <linux/moduleparam.h>
#include <linux/string.h>
#include <linux/netpoll.h>
#include <linux/inet.h>
#include <linux/configfs.h>

MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>");
MODULE_DESCRIPTION("Console driver for network interfaces");
MODULE_LICENSE("GPL");

#define MAX_PARAM_LENGTH	256
#define MAX_PRINT_CHUNK		1000

static char config[MAX_PARAM_LENGTH];
module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0);
MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]");

#ifndef	MODULE
static int __init option_setup(char *opt)
{
	strlcpy(config, opt, MAX_PARAM_LENGTH);
	return 1;
}
__setup("netconsole=", option_setup);
#endif	/* MODULE */

/* Linked list of all configured targets */
static LIST_HEAD(target_list);

/* This needs to be a spinlock because write_msg() cannot sleep */
static DEFINE_SPINLOCK(target_list_lock);

/**
 * struct netconsole_target - Represents a configured netconsole target.
 * @list:	Links this target into the target_list.
 * @item:	Links us into the configfs subsystem hierarchy.
 * @enabled:	On / off knob to enable / disable target.
 *		Visible from userspace (read-write).
 *		We maintain a strict 1:1 correspondence between this and
 *		whether the corresponding netpoll is active or inactive.
 *		Also, other parameters of a target may be modified at
 *		runtime only when it is disabled (enabled == 0).
 * @np:		The netpoll structure for this target.
 *		Contains the other userspace visible parameters:
 *		dev_name	(read-write)
 *		local_port	(read-write)
 *		remote_port	(read-write)
 *		local_ip	(read-write)
 *		remote_ip	(read-write)
 *		local_mac	(read-only)
 *		remote_mac	(read-write)
 */
struct netconsole_target {
	struct list_head	list;
#ifdef	CONFIG_NETCONSOLE_DYNAMIC
	struct config_item	item;
#endif
	int			enabled;
	struct netpoll		np;
};

#ifdef	CONFIG_NETCONSOLE_DYNAMIC

static struct configfs_subsystem netconsole_subsys;

static int __init dynamic_netconsole_init(void)
{
	config_group_init(&netconsole_subsys.su_group);
	mutex_init(&netconsole_subsys.su_mutex);
	return configfs_register_subsystem(&netconsole_subsys);
}

static void __exit dynamic_netconsole_exit(void)
{
	configfs_unregister_subsystem(&netconsole_subsys);
}

/*
 * Targets that were created by parsing the boot/module option string
 * do not exist in the configfs hierarchy (and have NULL names) and will
 * never go away, so make these a no-op for them.
 */
static void netconsole_target_get(struct netconsole_target *nt)
{
	if (config_item_name(&nt->item))
		config_item_get(&nt->item);
}

static void netconsole_target_put(struct netconsole_target *nt)
{
	if (config_item_name(&nt->item))
		config_item_put(&nt->item);
}

#else	/* !CONFIG_NETCONSOLE_DYNAMIC */

static int __init dynamic_netconsole_init(void)
{
	return 0;
}

static void __exit dynamic_netconsole_exit(void)
{
}

/*
 * No danger of targets going away from under us when dynamic
 * reconfigurability is off.
 */
static void netconsole_target_get(struct netconsole_target *nt)
{
}

static void netconsole_target_put(struct netconsole_target *nt)
{
}

#endif	/* CONFIG_NETCONSOLE_DYNAMIC */

/* Allocate new target (from boot/module param) and setup netpoll for it */
static struct netconsole_target *alloc_param_target(char *target_config)
{
	int err = -ENOMEM;
	struct netconsole_target *nt;

	/*
	 * Allocate and initialize with defaults.
	 * Note that these targets get their config_item fields zeroed-out.
	 */
	nt = kzalloc(sizeof(*nt), GFP_KERNEL);
	if (!nt) {
		printk(KERN_ERR "netconsole: failed to allocate memory\n");
		goto fail;
	}

	nt->np.name = "netconsole";
	strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ);
	nt->np.local_port = 6665;
	nt->np.remote_port = 6666;
	memset(nt->np.remote_mac, 0xff, ETH_ALEN);

	/* Parse parameters and setup netpoll */
	err = netpoll_parse_options(&nt->np, target_config);
	if (err)
		goto fail;

	err = netpoll_setup(&nt->np);
	if (err)
		goto fail;

	nt->enabled = 1;

	return nt;

fail:
	kfree(nt);
	return ERR_PTR(err);
}

/* Cleanup netpoll for given target (from boot/module param) and free it */
static void free_param_target(struct netconsole_target *nt)
{
	netpoll_cleanup(&nt->np);
	kfree(nt);
}

#ifdef	CONFIG_NETCONSOLE_DYNAMIC

/*
 * Our subsystem hierarchy is:
 *
 * /sys/kernel/config/netconsole/
 *				|
 *				<target>/
 *				|	enabled
 *				|	dev_name
 *				|	local_port
 *				|	remote_port
 *				|	local_ip
 *				|	remote_ip
 *				|	local_mac
 *				|	remote_mac
 *				|
 *				<target>/...
 */

struct netconsole_target_attr {
	struct configfs_attribute	attr;
	ssize_t				(*show)(struct netconsole_target *nt,
						char *buf);
	ssize_t				(*store)(struct netconsole_target *nt,
						 const char *buf,
						 size_t count);
};

static struct netconsole_target *to_target(struct config_item *item)
{
	return item ?
		container_of(item, struct netconsole_target, item) :
		NULL;
}

/*
 * Wrapper over simple_strtol (base 10) with sanity and range checking.
 * We return (signed) long only because we may want to return errors.
 * Do not use this to convert numbers that are allowed to be negative.
 */
static long strtol10_check_range(const char *cp, long min, long max)
{
	long ret;
	char *p = (char *) cp;

	WARN_ON(min < 0);
	WARN_ON(max < min);

	ret = simple_strtol(p, &p, 10);

	if (*p && (*p != '\n')) {
		printk(KERN_ERR "netconsole: invalid input\n");
		return -EINVAL;
	}
	if ((ret < min) || (ret > max)) {
		printk(KERN_ERR "netconsole: input %ld must be between "
				"%ld and %ld\n", ret, min, max);
		return -EINVAL;
	}

	return ret;
}

/*
 * Attribute operations for netconsole_target.
 */

static ssize_t show_enabled(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%d\n", nt->enabled);
}

static ssize_t show_dev_name(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%s\n", nt->np.dev_name);
}

static ssize_t show_local_port(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%d\n", nt->np.local_port);
}

static ssize_t show_remote_port(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%d\n", nt->np.remote_port);
}

static ssize_t show_local_ip(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip);
}

static ssize_t show_remote_ip(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip);
}

static ssize_t show_local_mac(struct netconsole_target *nt, char *buf)
{
	struct net_device *dev = nt->np.dev;
	static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };

	return snprintf(buf, PAGE_SIZE, "%pM\n", dev ? dev->dev_addr : bcast);
}

static ssize_t show_remote_mac(struct netconsole_target *nt, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%pM\n", nt->np.remote_mac);
}

/*
 * This one is special -- targets created through the configfs interface
 * are not enabled (and the corresponding netpoll activated) by default.
 * The user is expected to set the desired parameters first (which
 * would enable him to dynamically add new netpoll targets for new
 * network interfaces as and when they come up).
 */
static ssize_t store_enabled(struct netconsole_target *nt,
			     const char *buf,
			     size_t count)
{
	int err;
	long enabled;

	enabled = strtol10_check_range(buf, 0, 1);
	if (enabled < 0)
		return enabled;

	if (enabled) {	/* 1 */

		/*
		 * Skip netpoll_parse_options() -- all the attributes are
		 * already configured via configfs. Just print them out.
		 */
		netpoll_print_options(&nt->np);

		err = netpoll_setup(&nt->np);
		if (err)
			return err;

		printk(KERN_INFO "netconsole: network logging started\n");

	} else {	/* 0 */
		netpoll_cleanup(&nt->np);
	}

	nt->enabled = enabled;

	return strnlen(buf, count);
}

static ssize_t store_dev_name(struct netconsole_target *nt,
			      const char *buf,
			      size_t count)
{
	size_t len;

	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	strlcpy(nt->np.dev_name, buf, IFNAMSIZ);

	/* Get rid of possible trailing newline from echo(1) */
	len = strnlen(nt->np.dev_name, IFNAMSIZ);
	if (nt->np.dev_name[len - 1] == '\n')
		nt->np.dev_name[len - 1] = '\0';

	return strnlen(buf, count);
}

static ssize_t store_local_port(struct netconsole_target *nt,
				const char *buf,
				size_t count)
{
	long local_port;
#define __U16_MAX	((__u16) ~0U)

	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	local_port = strtol10_check_range(buf, 0, __U16_MAX);
	if (local_port < 0)
		return local_port;

	nt->np.local_port = local_port;

	return strnlen(buf, count);
}

static ssize_t store_remote_port(struct netconsole_target *nt,
				 const char *buf,
				 size_t count)
{
	long remote_port;
#define __U16_MAX	((__u16) ~0U)

	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	remote_port = strtol10_check_range(buf, 0, __U16_MAX);
	if (remote_port < 0)
		return remote_port;

	nt->np.remote_port = remote_port;

	return strnlen(buf, count);
}

static ssize_t store_local_ip(struct netconsole_target *nt,
			      const char *buf,
			      size_t count)
{
	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	nt->np.local_ip = in_aton(buf);

	return strnlen(buf, count);
}

static ssize_t store_remote_ip(struct netconsole_target *nt,
			       const char *buf,
			       size_t count)
{
	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	nt->np.remote_ip = in_aton(buf);

	return strnlen(buf, count);
}

static ssize_t store_remote_mac(struct netconsole_target *nt,
				const char *buf,
				size_t count)
{
	u8 remote_mac[ETH_ALEN];
	char *p = (char *) buf;
	int i;

	if (nt->enabled) {
		printk(KERN_ERR "netconsole: target (%s) is enabled, "
				"disable to update parameters\n",
				config_item_name(&nt->item));
		return -EINVAL;
	}

	for (i = 0; i < ETH_ALEN - 1; i++) {
		remote_mac[i] = simple_strtoul(p, &p, 16);
		if (*p != ':')
			goto invalid;
		p++;
	}
	remote_mac[ETH_ALEN - 1] = simple_strtoul(p, &p, 16);
	if (*p && (*p != '\n'))
		goto invalid;

	memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN);

	return strnlen(buf, count);

invalid:
	printk(KERN_ERR "netconsole: invalid input\n");
	return -EINVAL;
}

/*
 * Attribute definitions for netconsole_target.
 */

#define NETCONSOLE_TARGET_ATTR_RO(_name)				\
static struct netconsole_target_attr netconsole_target_##_name =	\
	__CONFIGFS_ATTR(_name, S_IRUGO, show_##_name, NULL)

#define NETCONSOLE_TARGET_ATTR_RW(_name)				\
static struct netconsole_target_attr netconsole_target_##_name =	\
	__CONFIGFS_ATTR(_name, S_IRUGO | S_IWUSR, show_##_name, store_##_name)

NETCONSOLE_TARGET_ATTR_RW(enabled);
NETCONSOLE_TARGET_ATTR_RW(dev_name);
NETCONSOLE_TARGET_ATTR_RW(local_port);
NETCONSOLE_TARGET_ATTR_RW(remote_port);
NETCONSOLE_TARGET_ATTR_RW(local_ip);
NETCONSOLE_TARGET_ATTR_RW(remote_ip);
NETCONSOLE_TARGET_ATTR_RO(local_mac);
NETCONSOLE_TARGET_ATTR_RW(remote_mac);

static struct configfs_attribute *netconsole_target_attrs[] = {
	&netconsole_target_enabled.attr,
	&netconsole_target_dev_name.attr,
	&netconsole_target_local_port.attr,
	&netconsole_target_remote_port.attr,
	&netconsole_target_local_ip.attr,
	&netconsole_target_remote_ip.attr,
	&netconsole_target_local_mac.attr,
	&netconsole_target_remote_mac.attr,
	NULL,
};

/*
 * Item operations and type for netconsole_target.
 */

static void netconsole_target_release(struct config_item *item)
{
	kfree(to_target(item));
}

static ssize_t netconsole_target_attr_show(struct config_item *item,
					   struct configfs_attribute *attr,
					   char *buf)
{
	ssize_t ret = -EINVAL;
	struct netconsole_target *nt = to_target(item);
	struct netconsole_target_attr *na =
		container_of(attr, struct netconsole_target_attr, attr);

	if (na->show)
		ret = na->show(nt, buf);

	return ret;
}

static ssize_t netconsole_target_attr_store(struct config_item *item,
					    struct configfs_attribute *attr,
					    const char *buf,
					    size_t count)
{
	ssize_t ret = -EINVAL;
	struct netconsole_target *nt = to_target(item);
	struct netconsole_target_attr *na =
		container_of(attr, struct netconsole_target_attr, attr);

	if (na->store)
		ret = na->store(nt, buf, count);

	return ret;
}

static struct configfs_item_operations netconsole_target_item_ops = {
	.release		= netconsole_target_release,
	.show_attribute		= netconsole_target_attr_show,
	.store_attribute	= netconsole_target_attr_store,
};

static struct config_item_type netconsole_target_type = {
	.ct_attrs		= netconsole_target_attrs,
	.ct_item_ops		= &netconsole_target_item_ops,
	.ct_owner		= THIS_MODULE,
};

/*
 * Group operations and type for netconsole_subsys.
 */

static struct config_item *make_netconsole_target(struct config_group *group,
						  const char *name)
{
	unsigned long flags;
	struct netconsole_target *nt;

	/*
	 * Allocate and initialize with defaults.
	 * Target is disabled at creation (enabled == 0).
	 */
	nt = kzalloc(sizeof(*nt), GFP_KERNEL);
	if (!nt) {
		printk(KERN_ERR "netconsole: failed to allocate memory\n");
		return ERR_PTR(-ENOMEM);
	}

	nt->np.name = "netconsole";
	strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ);
	nt->np.local_port = 6665;
	nt->np.remote_port = 6666;
	memset(nt->np.remote_mac, 0xff, ETH_ALEN);

	/* Initialize the config_item member */
	config_item_init_type_name(&nt->item, name, &netconsole_target_type);

	/* Adding, but it is disabled */
	spin_lock_irqsave(&target_list_lock, flags);
	list_add(&nt->list, &target_list);
	spin_unlock_irqrestore(&target_list_lock, flags);

	return &nt->item;
}

static void drop_netconsole_target(struct config_group *group,
				   struct config_item *item)
{
	unsigned long flags;
	struct netconsole_target *nt = to_target(item);

	spin_lock_irqsave(&target_list_lock, flags);
	list_del(&nt->list);
	spin_unlock_irqrestore(&target_list_lock, flags);

	/*
	 * The target may have never been enabled, or was manually disabled
	 * before being removed so netpoll may have already been cleaned up.
	 */
	if (nt->enabled)
		netpoll_cleanup(&nt->np);

	config_item_put(&nt->item);
}

static struct configfs_group_operations netconsole_subsys_group_ops = {
	.make_item	= make_netconsole_target,
	.drop_item	= drop_netconsole_target,
};

static struct config_item_type netconsole_subsys_type = {
	.ct_group_ops	= &netconsole_subsys_group_ops,
	.ct_owner	= THIS_MODULE,
};

/* The netconsole configfs subsystem */
static struct configfs_subsystem netconsole_subsys = {
	.su_group	= {
		.cg_item	= {
			.ci_namebuf	= "netconsole",
			.ci_type	= &netconsole_subsys_type,
		},
	},
};

#endif	/* CONFIG_NETCONSOLE_DYNAMIC */

/* Handle network interface device notifications */
static int netconsole_netdev_event(struct notifier_block *this,
				   unsigned long event,
				   void *ptr)
{
	unsigned long flags;
	struct netconsole_target *nt;
	struct net_device *dev = ptr;

	if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER ||
	      event == NETDEV_BONDING_DESLAVE || event == NETDEV_GOING_DOWN))
		goto done;

	spin_lock_irqsave(&target_list_lock, flags);
	list_for_each_entry(nt, &target_list, list) {
		netconsole_target_get(nt);
		if (nt->np.dev == dev) {
			switch (event) {
			case NETDEV_CHANGENAME:
				strlcpy(nt->np.dev_name, dev->name, IFNAMSIZ);
				break;
			case NETDEV_UNREGISTER:
				netpoll_cleanup(&nt->np);
				/* Fall through */
			case NETDEV_GOING_DOWN:
			case NETDEV_BONDING_DESLAVE:
				nt->enabled = 0;
				break;
			}
		}
		netconsole_target_put(nt);
	}
	spin_unlock_irqrestore(&target_list_lock, flags);
	if (event == NETDEV_UNREGISTER || event == NETDEV_BONDING_DESLAVE)
		printk(KERN_INFO "netconsole: network logging stopped, "
			"interface %s %s\n",  dev->name,
			event == NETDEV_UNREGISTER ? "unregistered" : "released slaves");

done:
	return NOTIFY_DONE;
}

static struct notifier_block netconsole_netdev_notifier = {
	.notifier_call  = netconsole_netdev_event,
};

static void write_msg(struct console *con, const char *msg, unsigned int len)
{
	int frag, left;
	unsigned long flags;
	struct netconsole_target *nt;
	const char *tmp;

	/* Avoid taking lock and disabling interrupts unnecessarily */
	if (list_empty(&target_list))
		return;

	spin_lock_irqsave(&target_list_lock, flags);
	list_for_each_entry(nt, &target_list, list) {
		netconsole_target_get(nt);
		if (nt->enabled && netif_running(nt->np.dev)) {
			/*
			 * We nest this inside the for-each-target loop above
			 * so that we're able to get as much logging out to
			 * at least one target if we die inside here, instead
			 * of unnecessarily keeping all targets in lock-step.
			 */
			tmp = msg;
			for (left = len; left;) {
				frag = min(left, MAX_PRINT_CHUNK);
				netpoll_send_udp(&nt->np, tmp, frag);
				tmp += frag;
				left -= frag;
			}
		}
		netconsole_target_put(nt);
	}
	spin_unlock_irqrestore(&target_list_lock, flags);
}

static struct console netconsole = {
	.name	= "netcon",
	.flags	= CON_ENABLED,
	.write	= write_msg,
};

static int __init init_netconsole(void)
{
	int err;
	struct netconsole_target *nt, *tmp;
	unsigned long flags;
	char *target_config;
	char *input = config;

	if (strnlen(input, MAX_PARAM_LENGTH)) {
		while ((target_config = strsep(&input, ";"))) {
			nt = alloc_param_target(target_config);
			if (IS_ERR(nt)) {
				err = PTR_ERR(nt);
				goto fail;
			}
			/* Dump existing printks when we register */
			netconsole.flags |= CON_PRINTBUFFER;

			spin_lock_irqsave(&target_list_lock, flags);
			list_add(&nt->list, &target_list);
			spin_unlock_irqrestore(&target_list_lock, flags);
		}
	}

	err = register_netdevice_notifier(&netconsole_netdev_notifier);
	if (err)
		goto fail;

	err = dynamic_netconsole_init();
	if (err)
		goto undonotifier;

	register_console(&netconsole);
	printk(KERN_INFO "netconsole: network logging started\n");

	return err;

undonotifier:
	unregister_netdevice_notifier(&netconsole_netdev_notifier);

fail:
	printk(KERN_ERR "netconsole: cleaning up\n");

	/*
	 * Remove all targets and destroy them (only targets created
	 * from the boot/module option exist here). Skipping the list
	 * lock is safe here, and netpoll_cleanup() will sleep.
	 */
	list_for_each_entry_safe(nt, tmp, &target_list, list) {
		list_del(&nt->list);
		free_param_target(nt);
	}

	return err;
}

static void __exit cleanup_netconsole(void)
{
	struct netconsole_target *nt, *tmp;

	unregister_console(&netconsole);
	dynamic_netconsole_exit();
	unregister_netdevice_notifier(&netconsole_netdev_notifier);

	/*
	 * Targets created via configfs pin references on our module
	 * and would first be rmdir(2)'ed from userspace. We reach
	 * here only when they are already destroyed, and only those
	 * created from the boot/module option are left, so remove and
	 * destroy them. Skipping the list lock is safe here, and
	 * netpoll_cleanup() will sleep.
	 */
	list_for_each_entry_safe(nt, tmp, &target_list, list) {
		list_del(&nt->list);
		free_param_target(nt);
	}
}

module_init(init_netconsole);
module_exit(cleanup_netconsole);
> } static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent) { return dent->de_inum.no_addr == 0 || dent->de_inum.no_formal_ino == 0; } static inline int __gfs2_dirent_find(const struct gfs2_dirent *dent, const struct qstr *name, int ret) { if (!gfs2_dirent_sentinel(dent) && be32_to_cpu(dent->de_hash) == name->hash && be16_to_cpu(dent->de_name_len) == name->len && memcmp(dent+1, name->name, name->len) == 0) return ret; return 0; } static int gfs2_dirent_find(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) { return __gfs2_dirent_find(dent, name, 1); } static int gfs2_dirent_prev(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) { return __gfs2_dirent_find(dent, name, 2); } /* * name->name holds ptr to start of block. * name->len holds size of block. */ static int gfs2_dirent_last(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) { const char *start = name->name; const char *end = (const char *)dent + be16_to_cpu(dent->de_rec_len); if (name->len == (end - start)) return 1; return 0; } static int gfs2_dirent_find_space(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) { unsigned required = GFS2_DIRENT_SIZE(name->len); unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); unsigned totlen = be16_to_cpu(dent->de_rec_len); if (gfs2_dirent_sentinel(dent)) actual = GFS2_DIRENT_SIZE(0); if (totlen - actual >= required) return 1; return 0; } struct dirent_gather { const struct gfs2_dirent **pdent; unsigned offset; }; static int gfs2_dirent_gather(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) { struct dirent_gather *g = opaque; if (!gfs2_dirent_sentinel(dent)) { g->pdent[g->offset++] = dent; } return 0; } /* * Other possible things to check: * - Inode located within filesystem size (and on valid block) * - Valid directory entry type * Not sure how heavy-weight we want to make this... could also check * hash is correct for example, but that would take a lot of extra time. * For now the most important thing is to check that the various sizes * are correct. */ static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset, unsigned int size, unsigned int len, int first) { const char *msg = "gfs2_dirent too small"; if (unlikely(size < sizeof(struct gfs2_dirent))) goto error; msg = "gfs2_dirent misaligned"; if (unlikely(offset & 0x7)) goto error; msg = "gfs2_dirent points beyond end of block"; if (unlikely(offset + size > len)) goto error; msg = "zero inode number"; if (unlikely(!first && gfs2_dirent_sentinel(dent))) goto error; msg = "name length is greater than space in dirent"; if (!gfs2_dirent_sentinel(dent) && unlikely(sizeof(struct gfs2_dirent)+be16_to_cpu(dent->de_name_len) > size)) goto error; return 0; error: printk(KERN_WARNING "gfs2_check_dirent: %s (%s)\n", msg, first ? "first in block" : "not first in block"); return -EIO; } static int gfs2_dirent_offset(const void *buf) { const struct gfs2_meta_header *h = buf; int offset; BUG_ON(buf == NULL); switch(be32_to_cpu(h->mh_type)) { case GFS2_METATYPE_LF: offset = sizeof(struct gfs2_leaf); break; case GFS2_METATYPE_DI: offset = sizeof(struct gfs2_dinode); break; default: goto wrong_type; } return offset; wrong_type: printk(KERN_WARNING "gfs2_scan_dirent: wrong block type %u\n", be32_to_cpu(h->mh_type)); return -1; } static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf, unsigned int len, gfs2_dscan_t scan, const struct qstr *name, void *opaque) { struct gfs2_dirent *dent, *prev; unsigned offset; unsigned size; int ret = 0; ret = gfs2_dirent_offset(buf); if (ret < 0) goto consist_inode; offset = ret; prev = NULL; dent = buf + offset; size = be16_to_cpu(dent->de_rec_len); if (gfs2_check_dirent(dent, offset, size, len, 1)) goto consist_inode; do { ret = scan(dent, name, opaque); if (ret) break; offset += size; if (offset == len) break; prev = dent; dent = buf + offset; size = be16_to_cpu(dent->de_rec_len); if (gfs2_check_dirent(dent, offset, size, len, 0)) goto consist_inode; } while(1); switch(ret) { case 0: return NULL; case 1: return dent; case 2: return prev ? prev : dent; default: BUG_ON(ret > 0); return ERR_PTR(ret); } consist_inode: gfs2_consist_inode(GFS2_I(inode)); return ERR_PTR(-EIO); } /** * dirent_first - Return the first dirent * @dip: the directory * @bh: The buffer * @dent: Pointer to list of dirents * * return first dirent whether bh points to leaf or stuffed dinode * * Returns: IS_LEAF, IS_DINODE, or -errno */ static int dirent_first(struct gfs2_inode *dip, struct buffer_head *bh, struct gfs2_dirent **dent) { struct gfs2_meta_header *h = (struct gfs2_meta_header *)bh->b_data; if (be32_to_cpu(h->mh_type) == GFS2_METATYPE_LF) { if (gfs2_meta_check(GFS2_SB(&dip->i_inode), bh)) return -EIO; *dent = (struct gfs2_dirent *)(bh->b_data + sizeof(struct gfs2_leaf)); return IS_LEAF; } else { if (gfs2_metatype_check(GFS2_SB(&dip->i_inode), bh, GFS2_METATYPE_DI)) return -EIO; *dent = (struct gfs2_dirent *)(bh->b_data + sizeof(struct gfs2_dinode)); return IS_DINODE; } } static int dirent_check_reclen(struct gfs2_inode *dip, const struct gfs2_dirent *d, const void *end_p) { const void *ptr = d; u16 rec_len = be16_to_cpu(d->de_rec_len); if (unlikely(rec_len < sizeof(struct gfs2_dirent))) goto broken; ptr += rec_len; if (ptr < end_p) return rec_len; if (ptr == end_p) return -ENOENT; broken: gfs2_consist_inode(dip); return -EIO; } /** * dirent_next - Next dirent * @dip: the directory * @bh: The buffer * @dent: Pointer to list of dirents * * Returns: 0 on success, error code otherwise */ static int dirent_next(struct gfs2_inode *dip, struct buffer_head *bh, struct gfs2_dirent **dent) { struct gfs2_dirent *cur = *dent, *tmp; char *bh_end = bh->b_data + bh->b_size; int ret; ret = dirent_check_reclen(dip, cur, bh_end); if (ret < 0) return ret; tmp = (void *)cur + ret; ret = dirent_check_reclen(dip, tmp, bh_end); if (ret == -EIO) return ret; /* Only the first dent could ever have de_inum.no_addr == 0 */ if (gfs2_dirent_sentinel(tmp)) { gfs2_consist_inode(dip); return -EIO; } *dent = tmp; return 0; } /** * dirent_del - Delete a dirent * @dip: The GFS2 inode * @bh: The buffer * @prev: The previous dirent * @cur: The current dirent * */ static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh, struct gfs2_dirent *prev, struct gfs2_dirent *cur) { u16 cur_rec_len, prev_rec_len; if (gfs2_dirent_sentinel(cur)) { gfs2_consist_inode(dip); return; } gfs2_trans_add_bh(dip->i_gl, bh, 1); /* If there is no prev entry, this is the first entry in the block. The de_rec_len is already as big as it needs to be. Just zero out the inode number and return. */ if (!prev) { cur->de_inum.no_addr = 0; cur->de_inum.no_formal_ino = 0; return; } /* Combine this dentry with the previous one. */ prev_rec_len = be16_to_cpu(prev->de_rec_len); cur_rec_len = be16_to_cpu(cur->de_rec_len); if ((char *)prev + prev_rec_len != (char *)cur) gfs2_consist_inode(dip); if ((char *)cur + cur_rec_len > bh->b_data + bh->b_size) gfs2_consist_inode(dip); prev_rec_len += cur_rec_len; prev->de_rec_len = cpu_to_be16(prev_rec_len); } /* * Takes a dent from which to grab space as an argument. Returns the * newly created dent. */ static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode, struct gfs2_dirent *dent, const struct qstr *name, struct buffer_head *bh) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_dirent *ndent; unsigned offset = 0, totlen; if (!gfs2_dirent_sentinel(dent)) offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); totlen = be16_to_cpu(dent->de_rec_len); BUG_ON(offset + name->len > totlen); gfs2_trans_add_bh(ip->i_gl, bh, 1); ndent = (struct gfs2_dirent *)((char *)dent + offset); dent->de_rec_len = cpu_to_be16(offset); gfs2_qstr2dirent(name, totlen - offset, ndent); return ndent; } static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode, struct buffer_head *bh, const struct qstr *name) { struct gfs2_dirent *dent; dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, gfs2_dirent_find_space, name, NULL); if (!dent || IS_ERR(dent)) return dent; return gfs2_init_dirent(inode, dent, name, bh); } static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, struct buffer_head **bhp) { int error; error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp); if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) { /* printk(KERN_INFO "block num=%llu\n", leaf_no); */ error = -EIO; } return error; } /** * get_leaf_nr - Get a leaf number associated with the index * @dip: The GFS2 inode * @index: * @leaf_out: * * Returns: 0 on success, error code otherwise */ static int get_leaf_nr(struct gfs2_inode *dip, u32 index, u64 *leaf_out) { __be64 leaf_no; int error; error = gfs2_dir_read_data(dip, (char *)&leaf_no, index * sizeof(__be64), sizeof(__be64), 0); if (error != sizeof(u64)) return (error < 0) ? error : -EIO; *leaf_out = be64_to_cpu(leaf_no); return 0; } static int get_first_leaf(struct gfs2_inode *dip, u32 index, struct buffer_head **bh_out) { u64 leaf_no; int error; error = get_leaf_nr(dip, index, &leaf_no); if (!error) error = get_leaf(dip, leaf_no, bh_out); return error; } static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode, const struct qstr *name, gfs2_dscan_t scan, struct buffer_head **pbh) { struct buffer_head *bh; struct gfs2_dirent *dent; struct gfs2_inode *ip = GFS2_I(inode); int error; if (ip->i_diskflags & GFS2_DIF_EXHASH) { struct gfs2_leaf *leaf; unsigned hsize = 1 << ip->i_depth; unsigned index; u64 ln; if (hsize * sizeof(u64) != ip->i_disksize) { gfs2_consist_inode(ip); return ERR_PTR(-EIO); } index = name->hash >> (32 - ip->i_depth); error = get_first_leaf(ip, index, &bh); if (error) return ERR_PTR(error); do { dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, scan, name, NULL); if (dent) goto got_dent; leaf = (struct gfs2_leaf *)bh->b_data; ln = be64_to_cpu(leaf->lf_next); brelse(bh); if (!ln) break; error = get_leaf(ip, ln, &bh); } while(!error); return error ? ERR_PTR(error) : NULL; } error = gfs2_meta_inode_buffer(ip, &bh); if (error) return ERR_PTR(error); dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, scan, name, NULL); got_dent: if (unlikely(dent == NULL || IS_ERR(dent))) { brelse(bh); bh = NULL; } *pbh = bh; return dent; } static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, u16 depth) { struct gfs2_inode *ip = GFS2_I(inode); unsigned int n = 1; u64 bn; int error; struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; struct qstr name = { .name = "", .len = 0, .hash = 0 }; error = gfs2_alloc_block(ip, &bn, &n); if (error) return NULL; bh = gfs2_meta_new(ip->i_gl, bn); if (!bh) return NULL; gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1); gfs2_trans_add_bh(ip->i_gl, bh, 1); gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF); leaf = (struct gfs2_leaf *)bh->b_data; leaf->lf_depth = cpu_to_be16(depth); leaf->lf_entries = 0; leaf->lf_dirent_format = cpu_to_be32(GFS2_FORMAT_DE); leaf->lf_next = 0; memset(leaf->lf_reserved, 0, sizeof(leaf->lf_reserved)); dent = (struct gfs2_dirent *)(leaf+1); gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent); *pbh = bh; return leaf; } /** * dir_make_exhash - Convert a stuffed directory into an ExHash directory * @dip: The GFS2 inode * * Returns: 0 on success, error code otherwise */ static int dir_make_exhash(struct inode *inode) { struct gfs2_inode *dip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_dirent *dent; struct qstr args; struct buffer_head *bh, *dibh; struct gfs2_leaf *leaf; int y; u32 x; __be64 *lp; u64 bn; int error; error = gfs2_meta_inode_buffer(dip, &dibh); if (error) return error; /* Turn over a new leaf */ leaf = new_leaf(inode, &bh, 0); if (!leaf) return -ENOSPC; bn = bh->b_blocknr; gfs2_assert(sdp, dip->i_entries < (1 << 16)); leaf->lf_entries = cpu_to_be16(dip->i_entries); /* Copy dirents */ gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_leaf), dibh, sizeof(struct gfs2_dinode)); /* Find last entry */ x = 0; args.len = bh->b_size - sizeof(struct gfs2_dinode) + sizeof(struct gfs2_leaf); args.name = bh->b_data; dent = gfs2_dirent_scan(&dip->i_inode, bh->b_data, bh->b_size, gfs2_dirent_last, &args, NULL); if (!dent) { brelse(bh); brelse(dibh); return -EIO; } if (IS_ERR(dent)) { brelse(bh); brelse(dibh); return PTR_ERR(dent); } /* Adjust the last dirent's record length (Remember that dent still points to the last entry.) */ dent->de_rec_len = cpu_to_be16(be16_to_cpu(dent->de_rec_len) + sizeof(struct gfs2_dinode) - sizeof(struct gfs2_leaf)); brelse(bh); /* We're done with the new leaf block, now setup the new hash table. */ gfs2_trans_add_bh(dip->i_gl, dibh, 1); gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); lp = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode)); for (x = sdp->sd_hash_ptrs; x--; lp++) *lp = cpu_to_be64(bn); dip->i_disksize = sdp->sd_sb.sb_bsize / 2; gfs2_add_inode_blocks(&dip->i_inode, 1); dip->i_diskflags |= GFS2_DIF_EXHASH; for (x = sdp->sd_hash_ptrs, y = -1; x; x >>= 1, y++) ; dip->i_depth = y; gfs2_dinode_out(dip, dibh->b_data); brelse(dibh); return 0; } /** * dir_split_leaf - Split a leaf block into two * @dip: The GFS2 inode * @index: * @leaf_no: * * Returns: 0 on success, error code on failure */ static int dir_split_leaf(struct inode *inode, const struct qstr *name) { struct gfs2_inode *dip = GFS2_I(inode); struct buffer_head *nbh, *obh, *dibh; struct gfs2_leaf *nleaf, *oleaf; struct gfs2_dirent *dent = NULL, *prev = NULL, *next = NULL, *new; u32 start, len, half_len, divider; u64 bn, leaf_no; __be64 *lp; u32 index; int x, moved = 0; int error; index = name->hash >> (32 - dip->i_depth); error = get_leaf_nr(dip, index, &leaf_no); if (error) return error; /* Get the old leaf block */ error = get_leaf(dip, leaf_no, &obh); if (error) return error; oleaf = (struct gfs2_leaf *)obh->b_data; if (dip->i_depth == be16_to_cpu(oleaf->lf_depth)) { brelse(obh); return 1; /* can't split */ } gfs2_trans_add_bh(dip->i_gl, obh, 1); nleaf = new_leaf(inode, &nbh, be16_to_cpu(oleaf->lf_depth) + 1); if (!nleaf) { brelse(obh); return -ENOSPC; } bn = nbh->b_blocknr; /* Compute the start and len of leaf pointers in the hash table. */ len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth)); half_len = len >> 1; if (!half_len) { printk(KERN_WARNING "i_depth %u lf_depth %u index %u\n", dip->i_depth, be16_to_cpu(oleaf->lf_depth), index); gfs2_consist_inode(dip); error = -EIO; goto fail_brelse; } start = (index & ~(len - 1)); /* Change the pointers. Don't bother distinguishing stuffed from non-stuffed. This code is complicated enough already. */ lp = kmalloc(half_len * sizeof(__be64), GFP_NOFS | __GFP_NOFAIL); /* Change the pointers */ for (x = 0; x < half_len; x++) lp[x] = cpu_to_be64(bn); error = gfs2_dir_write_data(dip, (char *)lp, start * sizeof(u64), half_len * sizeof(u64)); if (error != half_len * sizeof(u64)) { if (error >= 0) error = -EIO; goto fail_lpfree; } kfree(lp); /* Compute the divider */ divider = (start + half_len) << (32 - dip->i_depth); /* Copy the entries */ dirent_first(dip, obh, &dent); do { next = dent; if (dirent_next(dip, obh, &next)) next = NULL; if (!gfs2_dirent_sentinel(dent) && be32_to_cpu(dent->de_hash) < divider) { struct qstr str; str.name = (char*)(dent+1); str.len = be16_to_cpu(dent->de_name_len); str.hash = be32_to_cpu(dent->de_hash); new = gfs2_dirent_alloc(inode, nbh, &str); if (IS_ERR(new)) { error = PTR_ERR(new); break; } new->de_inum = dent->de_inum; /* No endian worries */ new->de_type = dent->de_type; /* No endian worries */ be16_add_cpu(&nleaf->lf_entries, 1); dirent_del(dip, obh, prev, dent); if (!oleaf->lf_entries) gfs2_consist_inode(dip); be16_add_cpu(&oleaf->lf_entries, -1); if (!prev) prev = dent; moved = 1; } else { prev = dent; } dent = next; } while (dent); oleaf->lf_depth = nleaf->lf_depth; error = gfs2_meta_inode_buffer(dip, &dibh); if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) { gfs2_trans_add_bh(dip->i_gl, dibh, 1); gfs2_add_inode_blocks(&dip->i_inode, 1); gfs2_dinode_out(dip, dibh->b_data); brelse(dibh); } brelse(obh); brelse(nbh); return error; fail_lpfree: kfree(lp); fail_brelse: brelse(obh); brelse(nbh); return error; } /** * dir_double_exhash - Double size of ExHash table * @dip: The GFS2 dinode * * Returns: 0 on success, error code on failure */ static int dir_double_exhash(struct gfs2_inode *dip) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct buffer_head *dibh; u32 hsize; u64 *buf; u64 *from, *to; u64 block; int x; int error = 0; hsize = 1 << dip->i_depth; if (hsize * sizeof(u64) != dip->i_disksize) { gfs2_consist_inode(dip); return -EIO; } /* Allocate both the "from" and "to" buffers in one big chunk */ buf = kcalloc(3, sdp->sd_hash_bsize, GFP_NOFS | __GFP_NOFAIL); for (block = dip->i_disksize >> sdp->sd_hash_bsize_shift; block--;) { error = gfs2_dir_read_data(dip, (char *)buf, block * sdp->sd_hash_bsize, sdp->sd_hash_bsize, 1); if (error != sdp->sd_hash_bsize) { if (error >= 0) error = -EIO; goto fail; } from = buf; to = (u64 *)((char *)buf + sdp->sd_hash_bsize); for (x = sdp->sd_hash_ptrs; x--; from++) { *to++ = *from; /* No endianess worries */ *to++ = *from; } error = gfs2_dir_write_data(dip, (char *)buf + sdp->sd_hash_bsize, block * sdp->sd_sb.sb_bsize, sdp->sd_sb.sb_bsize); if (error != sdp->sd_sb.sb_bsize) { if (error >= 0) error = -EIO; goto fail; } } kfree(buf); error = gfs2_meta_inode_buffer(dip, &dibh); if (!gfs2_assert_withdraw(sdp, !error)) { dip->i_depth++; gfs2_dinode_out(dip, dibh->b_data); brelse(dibh); } return error; fail: kfree(buf); return error; } /** * compare_dents - compare directory entries by hash value * @a: first dent * @b: second dent * * When comparing the hash entries of @a to @b: * gt: returns 1 * lt: returns -1 * eq: returns 0 */ static int compare_dents(const void *a, const void *b) { const struct gfs2_dirent *dent_a, *dent_b; u32 hash_a, hash_b; int ret = 0; dent_a = *(const struct gfs2_dirent **)a; hash_a = be32_to_cpu(dent_a->de_hash); dent_b = *(const struct gfs2_dirent **)b; hash_b = be32_to_cpu(dent_b->de_hash); if (hash_a > hash_b) ret = 1; else if (hash_a < hash_b) ret = -1; else { unsigned int len_a = be16_to_cpu(dent_a->de_name_len); unsigned int len_b = be16_to_cpu(dent_b->de_name_len); if (len_a > len_b) ret = 1; else if (len_a < len_b) ret = -1; else ret = memcmp(dent_a + 1, dent_b + 1, len_a); } return ret; } /** * do_filldir_main - read out directory entries * @dip: The GFS2 inode * @offset: The offset in the file to read from * @opaque: opaque data to pass to filldir * @filldir: The function to pass entries to * @darr: an array of struct gfs2_dirent pointers to read * @entries: the number of entries in darr * @copied: pointer to int that's non-zero if a entry has been copied out * * Jump through some hoops to make sure that if there are hash collsions, * they are read out at the beginning of a buffer. We want to minimize * the possibility that they will fall into different readdir buffers or * that someone will want to seek to that location. * * Returns: errno, >0 on exception from filldir */ static int do_filldir_main(struct gfs2_inode *dip, u64 *offset, void *opaque, filldir_t filldir, const struct gfs2_dirent **darr, u32 entries, int *copied) { const struct gfs2_dirent *dent, *dent_next; u64 off, off_next; unsigned int x, y; int run = 0; int error = 0; sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL); dent_next = darr[0]; off_next = be32_to_cpu(dent_next->de_hash); off_next = gfs2_disk_hash2offset(off_next); for (x = 0, y = 1; x < entries; x++, y++) { dent = dent_next; off = off_next; if (y < entries) { dent_next = darr[y]; off_next = be32_to_cpu(dent_next->de_hash); off_next = gfs2_disk_hash2offset(off_next); if (off < *offset) continue; *offset = off; if (off_next == off) { if (*copied && !run) return 1; run = 1; } else run = 0; } else { if (off < *offset) continue; *offset = off; } error = filldir(opaque, (const char *)(dent + 1), be16_to_cpu(dent->de_name_len), off, be64_to_cpu(dent->de_inum.no_addr), be16_to_cpu(dent->de_type)); if (error) return 1; *copied = 1; } /* Increment the *offset by one, so the next time we come into the do_filldir fxn, we get the next entry instead of the last one in the current leaf */ (*offset)++; return 0; } static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque, filldir_t filldir, int *copied, unsigned *depth, u64 leaf_no) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *bh; struct gfs2_leaf *lf; unsigned entries = 0, entries2 = 0; unsigned leaves = 0; const struct gfs2_dirent **darr, *dent; struct dirent_gather g; struct buffer_head **larr; int leaf = 0; int error, i; u64 lfn = leaf_no; do { error = get_leaf(ip, lfn, &bh); if (error) goto out; lf = (struct gfs2_leaf *)bh->b_data; if (leaves == 0) *depth = be16_to_cpu(lf->lf_depth); entries += be16_to_cpu(lf->lf_entries); leaves++; lfn = be64_to_cpu(lf->lf_next); brelse(bh); } while(lfn); if (!entries) return 0; error = -ENOMEM; /* * The extra 99 entries are not normally used, but are a buffer * zone in case the number of entries in the leaf is corrupt. * 99 is the maximum number of entries that can fit in a single * leaf block. */ larr = vmalloc((leaves + entries + 99) * sizeof(void *)); if (!larr) goto out; darr = (const struct gfs2_dirent **)(larr + leaves); g.pdent = darr; g.offset = 0; lfn = leaf_no; do { error = get_leaf(ip, lfn, &bh); if (error) goto out_kfree; lf = (struct gfs2_leaf *)bh->b_data; lfn = be64_to_cpu(lf->lf_next); if (lf->lf_entries) { entries2 += be16_to_cpu(lf->lf_entries); dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, gfs2_dirent_gather, NULL, &g); error = PTR_ERR(dent); if (IS_ERR(dent)) goto out_kfree; if (entries2 != g.offset) { fs_warn(sdp, "Number of entries corrupt in dir " "leaf %llu, entries2 (%u) != " "g.offset (%u)\n", (unsigned long long)bh->b_blocknr, entries2, g.offset); error = -EIO; goto out_kfree; } error = 0; larr[leaf++] = bh; } else { brelse(bh); } } while(lfn); BUG_ON(entries2 != entries); error = do_filldir_main(ip, offset, opaque, filldir, darr, entries, copied); out_kfree: for(i = 0; i < leaf; i++) brelse(larr[i]); vfree(larr); out: return error; } /** * dir_e_read - Reads the entries from a directory into a filldir buffer * @dip: dinode pointer * @offset: the hash of the last entry read shifted to the right once * @opaque: buffer for the filldir function to fill * @filldir: points to the filldir function to use * * Returns: errno */ static int dir_e_read(struct inode *inode, u64 *offset, void *opaque, filldir_t filldir) { struct gfs2_inode *dip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); u32 hsize, len = 0; u32 ht_offset, lp_offset, ht_offset_cur = -1; u32 hash, index; __be64 *lp; int copied = 0; int error = 0; unsigned depth = 0; hsize = 1 << dip->i_depth; if (hsize * sizeof(u64) != dip->i_disksize) { gfs2_consist_inode(dip); return -EIO; } hash = gfs2_dir_offset2hash(*offset); index = hash >> (32 - dip->i_depth); lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS); if (!lp) return -ENOMEM; while (index < hsize) { lp_offset = index & (sdp->sd_hash_ptrs - 1); ht_offset = index - lp_offset; if (ht_offset_cur != ht_offset) { error = gfs2_dir_read_data(dip, (char *)lp, ht_offset * sizeof(__be64), sdp->sd_hash_bsize, 1); if (error != sdp->sd_hash_bsize) { if (error >= 0) error = -EIO; goto out; } ht_offset_cur = ht_offset; } error = gfs2_dir_read_leaf(inode, offset, opaque, filldir, &copied, &depth, be64_to_cpu(lp[lp_offset])); if (error) break; len = 1 << (dip->i_depth - depth); index = (index & ~(len - 1)) + len; } out: kfree(lp); if (error > 0) error = 0; return error; } int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque, filldir_t filldir) { struct gfs2_inode *dip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct dirent_gather g; const struct gfs2_dirent **darr, *dent; struct buffer_head *dibh; int copied = 0; int error; if (!dip->i_entries) return 0; if (dip->i_diskflags & GFS2_DIF_EXHASH) return dir_e_read(inode, offset, opaque, filldir); if (!gfs2_is_stuffed(dip)) { gfs2_consist_inode(dip); return -EIO; } error = gfs2_meta_inode_buffer(dip, &dibh); if (error) return error; error = -ENOMEM; /* 96 is max number of dirents which can be stuffed into an inode */ darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS); if (darr) { g.pdent = darr; g.offset = 0; dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size, gfs2_dirent_gather, NULL, &g); if (IS_ERR(dent)) { error = PTR_ERR(dent); goto out; } if (dip->i_entries != g.offset) { fs_warn(sdp, "Number of entries corrupt in dir %llu, " "ip->i_entries (%u) != g.offset (%u)\n", (unsigned long long)dip->i_no_addr, dip->i_entries, g.offset); error = -EIO; goto out; } error = do_filldir_main(dip, offset, opaque, filldir, darr, dip->i_entries, &copied); out: kfree(darr); } if (error > 0) error = 0; brelse(dibh); return error; } /** * gfs2_dir_search - Search a directory * @dip: The GFS2 inode * @filename: * @inode: * * This routine searches a directory for a file or another directory. * Assumes a glock is held on dip. * * Returns: errno */ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name) { struct buffer_head *bh; struct gfs2_dirent *dent; struct inode *inode; dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); if (dent) { if (IS_ERR(dent)) return ERR_CAST(dent); inode = gfs2_inode_lookup(dir->i_sb, be16_to_cpu(dent->de_type), be64_to_cpu(dent->de_inum.no_addr), be64_to_cpu(dent->de_inum.no_formal_ino), 0); brelse(bh); return inode; } return ERR_PTR(-ENOENT); } int gfs2_dir_check(struct inode *dir, const struct qstr *name, const struct gfs2_inode *ip) { struct buffer_head *bh; struct gfs2_dirent *dent; int ret = -ENOENT; dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); if (dent) { if (IS_ERR(dent)) return PTR_ERR(dent); if (ip) { if (be64_to_cpu(dent->de_inum.no_addr) != ip->i_no_addr) goto out; if (be64_to_cpu(dent->de_inum.no_formal_ino) != ip->i_no_formal_ino) goto out; if (unlikely(IF2DT(ip->i_inode.i_mode) != be16_to_cpu(dent->de_type))) { gfs2_consist_inode(GFS2_I(dir)); ret = -EIO; goto out; } } ret = 0; out: brelse(bh); } return ret; } static int dir_new_leaf(struct inode *inode, const struct qstr *name) { struct buffer_head *bh, *obh; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_leaf *leaf, *oleaf; int error; u32 index; u64 bn; index = name->hash >> (32 - ip->i_depth); error = get_first_leaf(ip, index, &obh); if (error) return error; do { oleaf = (struct gfs2_leaf *)obh->b_data; bn = be64_to_cpu(oleaf->lf_next); if (!bn) break; brelse(obh); error = get_leaf(ip, bn, &obh); if (error) return error; } while(1); gfs2_trans_add_bh(ip->i_gl, obh, 1); leaf = new_leaf(inode, &bh, be16_to_cpu(oleaf->lf_depth)); if (!leaf) { brelse(obh); return -ENOSPC; } oleaf->lf_next = cpu_to_be64(bh->b_blocknr); brelse(bh); brelse(obh);