aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/params.c
blob: ed35345be536eefb68f1cd585b7c0213f24419b4 (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
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
/* Helpers for initial module or kernel cmdline parsing
   Copyright (C) 2001 Rusty Russell.

    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.

    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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
*/
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/ctype.h>

/* Protects all parameters, and incidentally kmalloced_param list. */
static DEFINE_MUTEX(param_lock);

/* This just allows us to keep track of which parameters are kmalloced. */
struct kmalloced_param {
	struct list_head list;
	char val[];
};
static LIST_HEAD(kmalloced_params);

static void *kmalloc_parameter(unsigned int size)
{
	struct kmalloced_param *p;

	p = kmalloc(sizeof(*p) + size, GFP_KERNEL);
	if (!p)
		return NULL;

	list_add(&p->list, &kmalloced_params);
	return p->val;
}

/* Does nothing if parameter wasn't kmalloced above. */
static void maybe_kfree_parameter(void *param)
{
	struct kmalloced_param *p;

	list_for_each_entry(p, &kmalloced_params, list) {
		if (p->val == param) {
			list_del(&p->list);
			kfree(p);
			break;
		}
	}
}

static char dash2underscore(char c)
{
	if (c == '-')
		return '_';
	return c;
}

bool parameqn(const char *a, const char *b, size_t n)
{
	size_t i;

	for (i = 0; i < n; i++) {
		if (dash2underscore(a[i]) != dash2underscore(b[i]))
			return false;
	}
	return true;
}

bool parameq(const char *a, const char *b)
{
	return parameqn(a, b, strlen(a)+1);
}

static int parse_one(char *param,
		     char *val,
		     const char *doing,
		     const struct kernel_param *params,
		     unsigned num_params,
		     s16 min_level,
		     s16 max_level,
		     int (*handle_unknown)(char *param, char *val,
				     const char *doing))
{
	unsigned int i;
	int err;

	/* Find parameter */
	for (i = 0; i < num_params; i++) {
		if (parameq(param, params[i].name)) {
			if (params[i].level < min_level
			    || params[i].level > max_level)
				return 0;
			/* No one handled NULL, so do it here. */
			if (!val && params[i].ops->set != param_set_bool
			    && params[i].ops->set != param_set_bint)
				return -EINVAL;
			pr_debug("handling %s with %p\n", param,
				params[i].ops->set);
			mutex_lock(&param_lock);
			err = params[i].ops->set(val, &params[i]);
			mutex_unlock(&param_lock);
			return err;
		}
	}

	if (handle_unknown) {
		pr_debug("doing %s: %s='%s'\n", doing, param, val);
		return handle_unknown(param, val, doing);
	}

	pr_debug("Unknown argument '%s'\n", param);
	return -ENOENT;
}

/* You can use " around spaces, but can't escape ". */
/* Hyphens and underscores equivalent in parameter names. */
static char *next_arg(char *args, char **param, char **val)
{
	unsigned int i, equals = 0;
	int in_quote = 0, quoted = 0;
	char *next;

	if (*args == '"') {
		args++;
		in_quote = 1;
		quoted = 1;
	}

	for (i = 0; args[i]; i++) {
		if (isspace(args[i]) && !in_quote)
			break;
		if (equals == 0) {
			if (args[i] == '=')
				equals = i;
		}
		if (args[i] == '"')
			in_quote = !in_quote;
	}

	*param = args;
	if (!equals)
		*val = NULL;
	else {
		args[equals] = '\0';
		*val = args + equals + 1;

		/* Don't include quotes in value. */
		if (**val == '"') {
			(*val)++;
			if (args[i-1] == '"')
				args[i-1] = '\0';
		}
		if (quoted && args[i-1] == '"')
			args[i-1] = '\0';
	}

	if (args[i]) {
		args[i] = '\0';
		next = args + i + 1;
	} else
		next = args + i;

	/* Chew up trailing spaces. */
	return skip_spaces(next);
}

/* Args looks like "foo=bar,bar2 baz=fuz wiz". */
int parse_args(const char *doing,
	       char *args,
	       const struct kernel_param *params,
	       unsigned num,
	       s16 min_level,
	       s16 max_level,
	       int (*unknown)(char *param, char *val, const char *doing))
{
	char *param, *val;

	/* Chew leading spaces */
	args = skip_spaces(args);

	if (*args)
		pr_debug("doing %s, parsing ARGS: '%s'\n", doing, args);

	while (*args) {
		int ret;
		int irq_was_disabled;

		args = next_arg(args, &param, &val);
		irq_was_disabled = irqs_disabled();
		ret = parse_one(param, val, doing, params, num,
				min_level, max_level, unknown);
		if (irq_was_disabled && !irqs_disabled())
			pr_warn("%s: option '%s' enabled irq's!\n",
				doing, param);

		switch (ret) {
		case -ENOENT:
			pr_err("%s: Unknown parameter `%s'\n", doing, param);
			return ret;
		case -ENOSPC:
			pr_err("%s: `%s' too large for parameter `%s'\n",
			       doing, val ?: "", param);
			return ret;
		case 0:
			break;
		default:
			pr_err("%s: `%s' invalid for parameter `%s'\n",
			       doing, val ?: "", param);
			return ret;
		}
	}

	/* All parsed OK. */
	return 0;
}

/* Lazy bastard, eh? */
#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn)      	\
	int param_set_##name(const char *val, const struct kernel_param *kp) \
	{								\
		tmptype l;						\
		int ret;						\
									\
		ret = strtolfn(val, 0, &l);				\
		if (ret < 0 || ((type)l != l))				\
			return ret < 0 ? ret : -EINVAL;			\
		*((type *)kp->arg) = l;					\
		return 0;						\
	}								\
	int param_get_##name(char *buffer, const struct kernel_param *kp) \
	{								\
		return sprintf(buffer, format, *((type *)kp->arg));	\
	}								\
	struct kernel_param_ops param_ops_##name = {			\
		.set = param_set_##name,				\
		.get = param_get_##name,				\
	};								\
	EXPORT_SYMBOL(param_set_##name);				\
	EXPORT_SYMBOL(param_get_##name);				\
	EXPORT_SYMBOL(param_ops_##name)


STANDARD_PARAM_DEF(byte, unsigned char, "%c", unsigned long, strict_strtoul);
STANDARD_PARAM_DEF(short, short, "%hi", long, strict_strtol);
STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, strict_strtoul);
STANDARD_PARAM_DEF(int, int, "%i", long, strict_strtol);
STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, strict_strtoul);
STANDARD_PARAM_DEF(long, long, "%li", long, strict_strtol);
STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, strict_strtoul);

int param_set_charp(const char *val, const struct kernel_param *kp)
{
	if (strlen(val) > 1024) {
		pr_err("%s: string parameter too long\n", kp->name);
		return -ENOSPC;
	}

	maybe_kfree_parameter(*(char **)kp->arg);

	/* This is a hack.  We can't kmalloc in early boot, and we
	 * don't need to; this mangled commandline is preserved. */
	if (slab_is_available()) {
		*(char **)kp->arg = kmalloc_parameter(strlen(val)+1);
		if (!*(char **)kp->arg)
			return -ENOMEM;
		strcpy(*(char **)kp->arg, val);
	} else
		*(const char **)kp->arg = val;

	return 0;
}
EXPORT_SYMBOL(param_set_charp);

int param_get_charp(char *buffer, const struct kernel_param *kp)
{
	return sprintf(buffer, "%s", *((char **)kp->arg));
}
EXPORT_SYMBOL(param_get_charp);

static void param_free_charp(void *arg)
{
	maybe_kfree_parameter(*((char **)arg));
}

struct kernel_param_ops param_ops_charp = {
	.set = param_set_charp,
	.get = param_get_charp,
	.free = param_free_charp,
};
EXPORT_SYMBOL(param_ops_charp);

/* Actually could be a bool or an int, for historical reasons. */
int param_set_bool(const char *val, const struct kernel_param *kp)
{
	/* No equals means "set"... */
	if (!val) val = "1";

	/* One of =[yYnN01] */
	return strtobool(val, kp->arg);
}
EXPORT_SYMBOL(param_set_bool);

int param_get_bool(char *buffer, const struct kernel_param *kp)
{
	/* Y and N chosen as being relatively non-coder friendly */
	return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N');
}
EXPORT_SYMBOL(param_get_bool);

struct kernel_param_ops param_ops_bool = {
	.set = param_set_bool,
	.get = param_get_bool,
};
EXPORT_SYMBOL(param_ops_bool);

/* This one must be bool. */
int param_set_invbool(const char *val, const struct kernel_param *kp)
{
	int ret;
	bool boolval;
	struct kernel_param dummy;

	dummy.arg = &boolval;
	ret = param_set_bool(val, &dummy);
	if (ret == 0)
		*(bool *)kp->arg = !boolval;
	return ret;
}
EXPORT_SYMBOL(param_set_invbool);

int param_get_invbool(char *buffer, const struct kernel_param *kp)
{
	return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y');
}
EXPORT_SYMBOL(param_get_invbool);

struct kernel_param_ops param_ops_invbool = {
	.set = param_set_invbool,
	.get = param_get_invbool,
};
EXPORT_SYMBOL(param_ops_invbool);

int param_set_bint(const char *val, const struct kernel_param *kp)
{
	struct kernel_param boolkp;
	bool v;
	int ret;

	/* Match bool exactly, by re-using it. */
	boolkp = *kp;
	boolkp.arg = &v;

	ret = param_set_bool(val, &boolkp);
	if (ret == 0)
		*(int *)kp->arg = v;
	return ret;
}
EXPORT_SYMBOL(param_set_bint);

struct kernel_param_ops param_ops_bint = {
	.set = param_set_bint,
	.get = param_get_int,
};
EXPORT_SYMBOL(param_ops_bint);

/* We break the rule and mangle the string. */
static int param_array(const char *name,
		       const char *val,
		       unsigned int min, unsigned int max,
		       void *elem, int elemsize,
		       int (*set)(const char *, const struct kernel_param *kp),
		       s16 level,
		       unsigned int *num)
{
	int ret;
	struct kernel_param kp;
	char save;

	/* Get the name right for errors. */
	kp.name = name;
	kp.arg = elem;
	kp.level = level;

	*num = 0;
	/* We expect a comma-separated list of values. */
	do {
		int len;

		if (*num == max) {
			pr_err("%s: can only take %i arguments\n", name, max);
			return -EINVAL;
		}
		len = strcspn(val, ",");

		/* nul-terminate and parse */
		save = val[len];
		((char *)val)[len] = '\0';
		BUG_ON(!mutex_is_locked(&param_lock));
		ret = set(val, &kp);

		if (ret != 0)
			return ret;
		kp.arg += elemsize;
		val += len+1;
		(*num)++;
	} while (save == ',');

	if (*num < min) {
		pr_err("%s: needs at least %i arguments\n", name, min);
		return -EINVAL;
	}
	return 0;
}

static int param_array_set(const char *val, const struct kernel_param *kp)
{
	const struct kparam_array *arr = kp->arr;
	unsigned int temp_num;

	return param_array(kp->name, val, 1, arr->max, arr->elem,
			   arr->elemsize, arr->ops->set, kp->level,
			   arr->num ?: &temp_num);
}

static int param_array_get(char *buffer, const struct kernel_param *kp)
{
	int i, off, ret;
	const struct kparam_array *arr = kp->arr;
	struct kernel_param p;

	p = *kp;
	for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) {
		if (i)
			buffer[off++] = ',';
		p.arg = arr->elem + arr->elemsize * i;
		BUG_ON(!mutex_is_locked(&param_lock));
		ret = arr->ops->get(buffer + off, &p);
		if (ret < 0)
			return ret;
		off += ret;
	}
	buffer[off] = '\0';
	return off;
}

static void param_array_free(void *arg)
{
	unsigned int i;
	const struct kparam_array *arr = arg;

	if (arr->ops->free)
		for (i = 0; i < (arr->num ? *arr->num : arr->max); i++)
			arr->ops->free(arr->elem + arr->elemsize * i);
}

struct kernel_param_ops param_array_ops = {
	.set = param_array_set,
	.get = param_array_get,
	.free = param_array_free,
};
EXPORT_SYMBOL(param_array_ops);

int param_set_copystring(const char *val, const struct kernel_param *kp)
{
	const struct kparam_string *kps = kp->str;

	if (strlen(val)+1 > kps->maxlen) {
		pr_err("%s: string doesn't fit in %u chars.\n",
		       kp->name, kps->maxlen-1);
		return -ENOSPC;
	}
	strcpy(kps->string, val);
	return 0;
}
EXPORT_SYMBOL(param_set_copystring);

int param_get_string(char *buffer, const struct kernel_param *kp)
{
	const struct kparam_string *kps = kp->str;
	return strlcpy(buffer, kps->string, kps->maxlen);
}
EXPORT_SYMBOL(param_get_string);

struct kernel_param_ops param_ops_string = {
	.set = param_set_copystring,
	.get = param_get_string,
};
EXPORT_SYMBOL(param_ops_string);

/* sysfs output in /sys/modules/XYZ/parameters/ */
#define to_module_attr(n) container_of(n, struct module_attribute, attr)
#define to_module_kobject(n) container_of(n, struct module_kobject, kobj)

extern struct kernel_param __start___param[], __stop___param[];

struct param_attribute
{
	struct module_attribute mattr;
	const struct kernel_param *param;
};

struct module_param_attrs
{
	unsigned int num;
	struct attribute_group grp;
	struct param_attribute attrs[0];
};

#ifdef CONFIG_SYSFS
#define to_param_attr(n) container_of(n, struct param_attribute, mattr)

static ssize_t param_attr_show(struct module_attribute *mattr,
			       struct module_kobject *mk, char *buf)
{
	int count;
	struct param_attribute *attribute = to_param_attr(mattr);

	if (!attribute->param->ops->get)
		return -EPERM;

	mutex_lock(&param_lock);
	count = attribute->param->ops->get(buf, attribute->param);
	mutex_unlock(&param_lock);
	if (count > 0) {
		strcat(buf, "\n");
		++count;
	}
	return count;
}

/* sysfs always hands a nul-terminated string in buf.  We rely on that. */
static ssize_t param_attr_store(struct module_attribute *mattr,
				struct module_kobject *km,
				const char *buf, size_t len)
{
 	int err;
	struct param_attribute *attribute = to_param_attr(mattr);

	if (!attribute->param->ops->set)
		return -EPERM;

	mutex_lock(&param_lock);
	err = attribute->param->ops->set(buf, attribute->param);
	mutex_unlock(&param_lock);
	if (!err)
		return len;
	return err;
}
#endif

#ifdef CONFIG_MODULES
#define __modinit
#else
#define __modinit __init
#endif

#ifdef CONFIG_SYSFS
void __kernel_param_lock(void)
{
	mutex_lock(&param_lock);
}
EXPORT_SYMBOL(__kernel_param_lock);

void __kernel_param_unlock(void)
{
	mutex_unlock(&param_lock);
}
EXPORT_SYMBOL(__kernel_param_unlock);

/*
 * add_sysfs_param - add a parameter to sysfs
 * @mk: struct module_kobject
 * @kparam: the actual parameter definition to add to sysfs
 * @name: name of parameter
 *
 * Create a kobject if for a (per-module) parameter if mp NULL, and
 * create file in sysfs.  Returns an error on out of memory.  Always cleans up
 * if there's an error.
 */
static __modinit int add_sysfs_param(struct module_kobject *mk,
				     const struct kernel_param *kp,
				     const char *name)
{
	struct module_param_attrs *new;
	struct attribute **attrs;
	int err, num;

	/* We don't bother calling this with invisible parameters. */
	BUG_ON(!kp->perm);

	if (!mk->mp) {
		num = 0;
		attrs = NULL;
	} else {
		num = mk->mp->num;
		attrs = mk->mp->grp.attrs;
	}

	/* Enlarge. */
	new = krealloc(mk->mp,
		       sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (num+1),
		       GFP_KERNEL);
	if (!new) {
		kfree(mk->mp);
		err = -ENOMEM;
		goto fail;
	}
	attrs = krealloc(attrs, sizeof(new->grp.attrs[0])*(num+2), GFP_KERNEL);
	if (!attrs) {
		err = -ENOMEM;
		goto fail_free_new;
	}

	/* Sysfs wants everything zeroed. */
	memset(new, 0, sizeof(*new));
	memset(&new->attrs[num], 0, sizeof(new->attrs[num]));
	memset(&attrs[num], 0, sizeof(attrs[num]));
	new->grp.name = "parameters";
	new->grp.attrs = attrs;

	/* Tack new one on the end. */
	sysfs_attr_init(&new->attrs[num].mattr.attr);
	new->attrs[num].param = kp;
	new->attrs[num].mattr.show = param_attr_show;
	new->attrs[num].mattr.store = param_attr_store;
	new->attrs[num].mattr.attr.name = (char *)name;
	new->attrs[num].mattr.attr.mode = kp->perm;
	new->num = num+1;

	/* Fix up all the pointers, since krealloc can move us */
	for (num = 0; num < new->num; num++)
		new->grp.attrs[num] = &new->attrs[num].mattr.attr;
	new->grp.attrs[num] = NULL;

	mk->mp = new;
	return 0;

fail_free_new:
	kfree(new);
fail:
	mk->mp = NULL;
	return err;
}

#ifdef CONFIG_MODULES
static void free_module_param_attrs(struct module_kobject *mk)
{
	kfree(mk->mp->grp.attrs);
	kfree(mk->mp);
	mk->mp = NULL;
}

/*
 * module_param_sysfs_setup - setup sysfs support for one module
 * @mod: module
 * @kparam: module parameters (array)
 * @num_params: number of module parameters
 *
 * Adds sysfs entries for module parameters under
 * /sys/module/[mod->name]/parameters/
 */
int module_param_sysfs_setup(struct module *mod,
			     const struct kernel_param *kparam,
			     unsigned int num_params)
{
	int i, err;
	bool params = false;

	for (i = 0; i < num_params; i++) {
		if (kparam[i].perm == 0)
			continue;
		err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name);
		if (err)
			return err;
		params = true;
	}

	if (!params)
		return 0;

	/* Create the param group. */
	err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
	if (err)
		free_module_param_attrs(&mod->mkobj);
	return err;
}

/*
 * module_param_sysfs_remove - remove sysfs support for one module
 * @mod: module
 *
 * Remove sysfs entries for module parameters and the corresponding
 * kobject.
 */
void module_param_sysfs_remove(struct module *mod)
{
	if (mod->mkobj.mp) {
		sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
		/* We are positive that no one is using any param
		 * attrs at this point.  Deallocate immediately. */
		free_module_param_attrs(&mod->mkobj);
	}
}
#endif

void destroy_params(const struct kernel_param *params, unsigned num)
{
	unsigned int i;

	for (i = 0; i < num; i++)
		if (params[i].ops->free)
			params[i].ops->free(params[i].arg);
}

static struct module_kobject * __init locate_module_kobject(const char *name)
{
	struct module_kobject *mk;
	struct kobject *kobj;
	int err;

	kobj = kset_find_obj(module_kset, name);
	if (kobj) {
		mk = to_module_kobject(kobj);
	} else {
		mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
		BUG_ON(!mk);

		mk->mod = THIS_MODULE;
		mk->kobj.kset = module_kset;
		err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
					   "%s", name);
#ifdef CONFIG_MODULES
		if (!err)
			err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
#endif
		if (err) {
			kobject_put(&mk->kobj);
			pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
				name, err);
			return NULL;
		}

		/* So that we hold reference in both cases. */
		kobject_get(&mk->kobj);
	}

	return mk;
}

static void __init kernel_add_sysfs_param(const char *name,
					  struct kernel_param *kparam,
					  unsigned int name_skip)
{
	struct module_kobject *mk;
	int err;

	mk = locate_module_kobject(name);
	if (!mk)
		return;

	/* We need to remove old parameters before adding more. */
	if (mk->mp)
		sysfs_remove_group(&mk->kobj, &mk->mp->grp);

	/* These should not fail at boot. */
	err = add_sysfs_param(mk, kparam, kparam->name + name_skip);
	BUG_ON(err);
	err = sysfs_create_group(&mk->kobj, &mk->mp->grp);
	BUG_ON(err);
	kobject_uevent(&mk->kobj, KOBJ_ADD);
	kobject_put(&mk->kobj);
}

/*
 * param_sysfs_builtin - add contents in /sys/parameters for built-in modules
 *
 * Add module_parameters to sysfs for "modules" built into the kernel.
 *
 * The "module" name (KBUILD_MODNAME) is stored before a dot, the
 * "parameter" name is stored behind a dot in kernel_param->name. So,
 * extract the "module" name for all built-in kernel_param-eters,
 * and for all who have the same, call kernel_add_sysfs_param.
 */
static void __init param_sysfs_builtin(void)
{
	struct kernel_param *kp;
	unsigned int name_len;
	char modname[MODULE_NAME_LEN];

	for (kp = __start___param; kp < __stop___param; kp++) {
		char *dot;

		if (kp->perm == 0)
			continue;

		dot = strchr(kp->name, '.');
		if (!dot) {
			/* This happens for core_param() */
			strcpy(modname, "kernel");
			name_len = 0;
		} else {
			name_len = dot - kp->name + 1;
			strlcpy(modname, kp->name, name_len);
		}
		kernel_add_sysfs_param(modname, kp, name_len);
	}
}

ssize_t __modver_version_show(struct module_attribute *mattr,
			      struct module_kobject *mk, char *buf)
{
	struct module_version_attribute *vattr =
		container_of(mattr, struct module_version_attribute, mattr);

	return sprintf(buf, "%s\n", vattr->version);
}

extern const struct module_version_attribute *__start___modver[];
extern const struct module_version_attribute *__stop___modver[];

static void __init version_sysfs_builtin(void)
{
	const struct module_version_attribute **p;
	struct module_kobject *mk;
	int err;

	for (p = __start___modver; p < __stop___modver; p++) {
		const struct module_version_attribute *vattr = *p;

		mk = locate_module_kobject(vattr->module_name);
		if (mk) {
			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
			kobject_uevent(&mk->kobj, KOBJ_ADD);
			kobject_put(&mk->kobj);
		}
	}
}

/* module-related sysfs stuff */

static ssize_t module_attr_show(struct kobject *kobj,
				struct attribute *attr,
				char *buf)
{
	struct module_attribute *attribute;
	struct module_kobject *mk;
	int ret;

	attribute = to_module_attr(attr);
	mk = to_module_kobject(kobj);

	if (!attribute->show)
		return -EIO;

	ret = attribute->show(attribute, mk, buf);

	return ret;
}

static ssize_t module_attr_store(struct kobject *kobj,
				struct attribute *attr,
				const char *buf, size_t len)
{
	struct module_attribute *attribute;
	struct module_kobject *mk;
	int ret;

	attribute = to_module_attr(attr);
	mk = to_module_kobject(kobj);

	if (!attribute->store)
		return -EIO;

	ret = attribute->store(attribute, mk, buf, len);

	return ret;
}

static const struct sysfs_ops module_sysfs_ops = {
	.show = module_attr_show,
	.store = module_attr_store,
};

static int uevent_filter(struct kset *kset, struct kobject *kobj)
{
	struct kobj_type *ktype = get_ktype(kobj);

	if (ktype == &module_ktype)
		return 1;
	return 0;
}

static const struct kset_uevent_ops module_uevent_ops = {
	.filter = uevent_filter,
};

struct kset *module_kset;
int module_sysfs_initialized;

struct kobj_type module_ktype = {
	.sysfs_ops =	&module_sysfs_ops,
};

/*
 * param_sysfs_init - wrapper for built-in params support
 */
static int __init param_sysfs_init(void)
{
	module_kset = kset_create_and_add("module", &module_uevent_ops, NULL);
	if (!module_kset) {
		printk(KERN_WARNING "%s (%d): error creating kset\n",
			__FILE__, __LINE__);
		return -ENOMEM;
	}
	module_sysfs_initialized = 1;

	version_sysfs_builtin();
	param_sysfs_builtin();

	return 0;
}
subsys_initcall(param_sysfs_init);

#endif /* CONFIG_SYSFS */
'n3613' href='#n3613'>3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457
/*
 * Copyright (C) 1991, 1992 Linus Torvalds
 * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
 * Elevator latency, (C) 2000  Andrea Arcangeli <andrea@suse.de> SuSE
 * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
 * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> -  July2000
 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
 */

/*
 * This handles all read/write requests to block devices
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
#include <linux/scatterlist.h>

/*
 * for max sense size
 */
#include <scsi/scsi_cmnd.h>

static void blk_unplug_work(struct work_struct *work);
static void blk_unplug_timeout(unsigned long data);
static void drive_stat_acct(struct request *rq, int new_io);
static void init_request_from_bio(struct request *req, struct bio *bio);
static int __make_request(struct request_queue *q, struct bio *bio);
static struct io_context *current_io_context(gfp_t gfp_flags, int node);
static void blk_recalc_rq_segments(struct request *rq);
static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
			    struct bio *bio);

/*
 * For the allocated request tables
 */
static struct kmem_cache *request_cachep;

/*
 * For queue allocation
 */
static struct kmem_cache *requestq_cachep;

/*
 * For io context allocations
 */
static struct kmem_cache *iocontext_cachep;

/*
 * Controlling structure to kblockd
 */
static struct workqueue_struct *kblockd_workqueue;

unsigned long blk_max_low_pfn, blk_max_pfn;

EXPORT_SYMBOL(blk_max_low_pfn);
EXPORT_SYMBOL(blk_max_pfn);

static DEFINE_PER_CPU(struct list_head, blk_cpu_done);

/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME	(HZ/50UL)

/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ	32

/*
 * Return the threshold (number of used requests) at which the queue is
 * considered to be congested.  It include a little hysteresis to keep the
 * context switch rate down.
 */
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
	return q->nr_congestion_on;
}

/*
 * The threshold at which a queue is considered to be uncongested
 */
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
	return q->nr_congestion_off;
}

static void blk_queue_congestion_threshold(struct request_queue *q)
{
	int nr;

	nr = q->nr_requests - (q->nr_requests / 8) + 1;
	if (nr > q->nr_requests)
		nr = q->nr_requests;
	q->nr_congestion_on = nr;

	nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
	if (nr < 1)
		nr = 1;
	q->nr_congestion_off = nr;
}

/**
 * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
 * @bdev:	device
 *
 * Locates the passed device's request queue and returns the address of its
 * backing_dev_info
 *
 * Will return NULL if the request queue cannot be located.
 */
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
	struct backing_dev_info *ret = NULL;
	struct request_queue *q = bdev_get_queue(bdev);

	if (q)
		ret = &q->backing_dev_info;
	return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);

/**
 * blk_queue_prep_rq - set a prepare_request function for queue
 * @q:		queue
 * @pfn:	prepare_request function
 *
 * It's possible for a queue to register a prepare_request callback which
 * is invoked before the request is handed to the request_fn. The goal of
 * the function is to prepare a request for I/O, it can be used to build a
 * cdb from the request data for instance.
 *
 */
void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
{
	q->prep_rq_fn = pfn;
}

EXPORT_SYMBOL(blk_queue_prep_rq);

/**
 * blk_queue_merge_bvec - set a merge_bvec function for queue
 * @q:		queue
 * @mbfn:	merge_bvec_fn
 *
 * Usually queues have static limitations on the max sectors or segments that
 * we can put in a request. Stacking drivers may have some settings that
 * are dynamic, and thus we have to query the queue whether it is ok to
 * add a new bio_vec to a bio at a given offset or not. If the block device
 * has such limitations, it needs to register a merge_bvec_fn to control
 * the size of bio's sent to it. Note that a block device *must* allow a
 * single page to be added to an empty bio. The block device driver may want
 * to use the bio_split() function to deal with these bio's. By default
 * no merge_bvec_fn is defined for a queue, and only the fixed limits are
 * honored.
 */
void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
{
	q->merge_bvec_fn = mbfn;
}

EXPORT_SYMBOL(blk_queue_merge_bvec);

void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
	q->softirq_done_fn = fn;
}

EXPORT_SYMBOL(blk_queue_softirq_done);

/**
 * blk_queue_make_request - define an alternate make_request function for a device
 * @q:  the request queue for the device to be affected
 * @mfn: the alternate make_request function
 *
 * Description:
 *    The normal way for &struct bios to be passed to a device
 *    driver is for them to be collected into requests on a request
 *    queue, and then to allow the device driver to select requests
 *    off that queue when it is ready.  This works well for many block
 *    devices. However some block devices (typically virtual devices
 *    such as md or lvm) do not benefit from the processing on the
 *    request queue, and are served best by having the requests passed
 *    directly to them.  This can be achieved by providing a function
 *    to blk_queue_make_request().
 *
 * Caveat:
 *    The driver that does this *must* be able to deal appropriately
 *    with buffers in "highmemory". This can be accomplished by either calling
 *    __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
 *    blk_queue_bounce() to create a buffer in normal memory.
 **/
void blk_queue_make_request(struct request_queue * q, make_request_fn * mfn)
{
	/*
	 * set defaults
	 */
	q->nr_requests = BLKDEV_MAX_RQ;
	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
	q->make_request_fn = mfn;
	q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
	q->backing_dev_info.state = 0;
	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
	blk_queue_hardsect_size(q, 512);
	blk_queue_dma_alignment(q, 511);
	blk_queue_congestion_threshold(q);
	q->nr_batching = BLK_BATCH_REQ;

	q->unplug_thresh = 4;		/* hmm */
	q->unplug_delay = (3 * HZ) / 1000;	/* 3 milliseconds */
	if (q->unplug_delay == 0)
		q->unplug_delay = 1;

	INIT_WORK(&q->unplug_work, blk_unplug_work);

	q->unplug_timer.function = blk_unplug_timeout;
	q->unplug_timer.data = (unsigned long)q;

	/*
	 * by default assume old behaviour and bounce for any highmem page
	 */
	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}

EXPORT_SYMBOL(blk_queue_make_request);

static void rq_init(struct request_queue *q, struct request *rq)
{
	INIT_LIST_HEAD(&rq->queuelist);
	INIT_LIST_HEAD(&rq->donelist);

	rq->errors = 0;
	rq->bio = rq->biotail = NULL;
	INIT_HLIST_NODE(&rq->hash);
	RB_CLEAR_NODE(&rq->rb_node);
	rq->ioprio = 0;
	rq->buffer = NULL;
	rq->ref_count = 1;
	rq->q = q;
	rq->special = NULL;
	rq->data_len = 0;
	rq->data = NULL;
	rq->nr_phys_segments = 0;
	rq->sense = NULL;
	rq->end_io = NULL;
	rq->end_io_data = NULL;
	rq->completion_data = NULL;
	rq->next_rq = NULL;
}

/**
 * blk_queue_ordered - does this queue support ordered writes
 * @q:        the request queue
 * @ordered:  one of QUEUE_ORDERED_*
 * @prepare_flush_fn: rq setup helper for cache flush ordered writes
 *
 * Description:
 *   For journalled file systems, doing ordered writes on a commit
 *   block instead of explicitly doing wait_on_buffer (which is bad
 *   for performance) can be a big win. Block drivers supporting this
 *   feature should call this function and indicate so.
 *
 **/
int blk_queue_ordered(struct request_queue *q, unsigned ordered,
		      prepare_flush_fn *prepare_flush_fn)
{
	if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) &&
	    prepare_flush_fn == NULL) {
		printk(KERN_ERR "blk_queue_ordered: prepare_flush_fn required\n");
		return -EINVAL;
	}

	if (ordered != QUEUE_ORDERED_NONE &&
	    ordered != QUEUE_ORDERED_DRAIN &&
	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
	    ordered != QUEUE_ORDERED_TAG &&
	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
	    ordered != QUEUE_ORDERED_TAG_FUA) {
		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
		return -EINVAL;
	}

	q->ordered = ordered;
	q->next_ordered = ordered;
	q->prepare_flush_fn = prepare_flush_fn;

	return 0;
}

EXPORT_SYMBOL(blk_queue_ordered);

/*
 * Cache flushing for ordered writes handling
 */
inline unsigned blk_ordered_cur_seq(struct request_queue *q)
{
	if (!q->ordseq)
		return 0;
	return 1 << ffz(q->ordseq);
}

unsigned blk_ordered_req_seq(struct request *rq)
{
	struct request_queue *q = rq->q;

	BUG_ON(q->ordseq == 0);

	if (rq == &q->pre_flush_rq)
		return QUEUE_ORDSEQ_PREFLUSH;
	if (rq == &q->bar_rq)
		return QUEUE_ORDSEQ_BAR;
	if (rq == &q->post_flush_rq)
		return QUEUE_ORDSEQ_POSTFLUSH;

	/*
	 * !fs requests don't need to follow barrier ordering.  Always
	 * put them at the front.  This fixes the following deadlock.
	 *
	 * http://thread.gmane.org/gmane.linux.kernel/537473
	 */
	if (!blk_fs_request(rq))
		return QUEUE_ORDSEQ_DRAIN;

	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
		return QUEUE_ORDSEQ_DRAIN;
	else
		return QUEUE_ORDSEQ_DONE;
}

void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
{
	struct request *rq;

	if (error && !q->orderr)
		q->orderr = error;

	BUG_ON(q->ordseq & seq);
	q->ordseq |= seq;

	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
		return;

	/*
	 * Okay, sequence complete.
	 */
	q->ordseq = 0;
	rq = q->orig_bar_rq;

	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
		BUG();
}

static void pre_flush_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
}

static void bar_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
}

static void post_flush_end_io(struct request *rq, int error)
{
	elv_completed_request(rq->q, rq);
	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
}

static void queue_flush(struct request_queue *q, unsigned which)
{
	struct request *rq;
	rq_end_io_fn *end_io;

	if (which == QUEUE_ORDERED_PREFLUSH) {
		rq = &q->pre_flush_rq;
		end_io = pre_flush_end_io;
	} else {
		rq = &q->post_flush_rq;
		end_io = post_flush_end_io;
	}

	rq->cmd_flags = REQ_HARDBARRIER;
	rq_init(q, rq);
	rq->elevator_private = NULL;
	rq->elevator_private2 = NULL;
	rq->rq_disk = q->bar_rq.rq_disk;
	rq->end_io = end_io;
	q->prepare_flush_fn(q, rq);

	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}

static inline struct request *start_ordered(struct request_queue *q,
					    struct request *rq)
{
	q->orderr = 0;
	q->ordered = q->next_ordered;
	q->ordseq |= QUEUE_ORDSEQ_STARTED;

	/*
	 * Prep proxy barrier request.
	 */
	blkdev_dequeue_request(rq);
	q->orig_bar_rq = rq;
	rq = &q->bar_rq;
	rq->cmd_flags = 0;
	rq_init(q, rq);
	if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
		rq->cmd_flags |= REQ_RW;
	if (q->ordered & QUEUE_ORDERED_FUA)
		rq->cmd_flags |= REQ_FUA;
	rq->elevator_private = NULL;
	rq->elevator_private2 = NULL;
	init_request_from_bio(rq, q->orig_bar_rq->bio);
	rq->end_io = bar_end_io;

	/*
	 * Queue ordered sequence.  As we stack them at the head, we
	 * need to queue in reverse order.  Note that we rely on that
	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
	 * request gets inbetween ordered sequence. If this request is
	 * an empty barrier, we don't need to do a postflush ever since
	 * there will be no data written between the pre and post flush.
	 * Hence a single flush will suffice.
	 */
	if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
		queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
	else
		q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;

	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);

	if (q->ordered & QUEUE_ORDERED_PREFLUSH) {
		queue_flush(q, QUEUE_ORDERED_PREFLUSH);
		rq = &q->pre_flush_rq;
	} else
		q->ordseq |= QUEUE_ORDSEQ_PREFLUSH;

	if ((q->ordered & QUEUE_ORDERED_TAG) || q->in_flight == 0)
		q->ordseq |= QUEUE_ORDSEQ_DRAIN;
	else
		rq = NULL;

	return rq;
}

int blk_do_ordered(struct request_queue *q, struct request **rqp)
{
	struct request *rq = *rqp;
	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);

	if (!q->ordseq) {
		if (!is_barrier)
			return 1;

		if (q->next_ordered != QUEUE_ORDERED_NONE) {
			*rqp = start_ordered(q, rq);
			return 1;
		} else {
			/*
			 * This can happen when the queue switches to
			 * ORDERED_NONE while this request is on it.
			 */
			blkdev_dequeue_request(rq);
			if (__blk_end_request(rq, -EOPNOTSUPP,
					      blk_rq_bytes(rq)))
				BUG();
			*rqp = NULL;
			return 0;
		}
	}

	/*
	 * Ordered sequence in progress
	 */

	/* Special requests are not subject to ordering rules. */
	if (!blk_fs_request(rq) &&
	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
		return 1;

	if (q->ordered & QUEUE_ORDERED_TAG) {
		/* Ordered by tag.  Blocking the next barrier is enough. */
		if (is_barrier && rq != &q->bar_rq)
			*rqp = NULL;
	} else {
		/* Ordered by draining.  Wait for turn. */
		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
			*rqp = NULL;
	}

	return 1;
}

static void req_bio_endio(struct request *rq, struct bio *bio,
			  unsigned int nbytes, int error)
{
	struct request_queue *q = rq->q;

	if (&q->bar_rq != rq) {
		if (error)
			clear_bit(BIO_UPTODATE, &bio->bi_flags);
		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
			error = -EIO;

		if (unlikely(nbytes > bio->bi_size)) {
			printk("%s: want %u bytes done, only %u left\n",
			       __FUNCTION__, nbytes, bio->bi_size);
			nbytes = bio->bi_size;
		}

		bio->bi_size -= nbytes;
		bio->bi_sector += (nbytes >> 9);
		if (bio->bi_size == 0)
			bio_endio(bio, error);
	} else {

		/*
		 * Okay, this is the barrier request in progress, just
		 * record the error;
		 */
		if (error && !q->orderr)
			q->orderr = error;
	}
}

/**
 * blk_queue_bounce_limit - set bounce buffer limit for queue
 * @q:  the request queue for the device
 * @dma_addr:   bus address limit
 *
 * Description:
 *    Different hardware can have different requirements as to what pages
 *    it can do I/O directly to. A low level driver can call
 *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
 *    buffers for doing I/O to pages residing above @page.
 **/
void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
{
	unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
	int dma = 0;

	q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
	/* Assume anything <= 4GB can be handled by IOMMU.
	   Actually some IOMMUs can handle everything, but I don't
	   know of a way to test this here. */
	if (bounce_pfn < (min_t(u64,0xffffffff,BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
		dma = 1;
	q->bounce_pfn = max_low_pfn;
#else
	if (bounce_pfn < blk_max_low_pfn)
		dma = 1;
	q->bounce_pfn = bounce_pfn;
#endif
	if (dma) {
		init_emergency_isa_pool();
		q->bounce_gfp = GFP_NOIO | GFP_DMA;
		q->bounce_pfn = bounce_pfn;
	}
}

EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
 * blk_queue_max_sectors - set max sectors for a request for this queue
 * @q:  the request queue for the device
 * @max_sectors:  max sectors in the usual 512b unit
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of
 *    received requests.
 **/
void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
{
	if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
		max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
		printk("%s: set to minimum %d\n", __FUNCTION__, max_sectors);
	}

	if (BLK_DEF_MAX_SECTORS > max_sectors)
		q->max_hw_sectors = q->max_sectors = max_sectors;
 	else {
		q->max_sectors = BLK_DEF_MAX_SECTORS;
		q->max_hw_sectors = max_sectors;
	}
}

EXPORT_SYMBOL(blk_queue_max_sectors);

/**
 * blk_queue_max_phys_segments - set max phys segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    physical data segments in a request.  This would be the largest sized
 *    scatter list the driver could handle.
 **/
void blk_queue_max_phys_segments(struct request_queue *q,
				 unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
	}

	q->max_phys_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_phys_segments);

/**
 * blk_queue_max_hw_segments - set max hw segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    hw data segments in a request.  This would be the largest number of
 *    address/length pairs the host adapter can actually give as once
 *    to the device.
 **/
void blk_queue_max_hw_segments(struct request_queue *q,
			       unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
	}

	q->max_hw_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_hw_segments);

/**
 * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
 * @q:  the request queue for the device
 * @max_size:  max size of segment in bytes
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of a
 *    coalesced segment
 **/
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
{
	if (max_size < PAGE_CACHE_SIZE) {
		max_size = PAGE_CACHE_SIZE;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_size);
	}

	q->max_segment_size = max_size;
}

EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
 * blk_queue_hardsect_size - set hardware sector size for the queue
 * @q:  the request queue for the device
 * @size:  the hardware sector size, in bytes
 *
 * Description:
 *   This should typically be set to the lowest possible sector size
 *   that the hardware can operate on (possible without reverting to
 *   even internal read-modify-write operations). Usually the default
 *   of 512 covers most hardware.
 **/
void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
{
	q->hardsect_size = size;
}

EXPORT_SYMBOL(blk_queue_hardsect_size);

/*
 * Returns the minimum that is _not_ zero, unless both are zero.
 */
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))

/**
 * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
 * @t:	the stacking driver (top)
 * @b:  the underlying device (bottom)
 **/
void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
{
	/* zero is "infinity" */
	t->max_sectors = min_not_zero(t->max_sectors,b->max_sectors);
	t->max_hw_sectors = min_not_zero(t->max_hw_sectors,b->max_hw_sectors);

	t->max_phys_segments = min(t->max_phys_segments,b->max_phys_segments);
	t->max_hw_segments = min(t->max_hw_segments,b->max_hw_segments);
	t->max_segment_size = min(t->max_segment_size,b->max_segment_size);
	t->hardsect_size = max(t->hardsect_size,b->hardsect_size);
	if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
		clear_bit(QUEUE_FLAG_CLUSTER, &t->queue_flags);
}

EXPORT_SYMBOL(blk_queue_stack_limits);

/**
 * blk_queue_dma_drain - Set up a drain buffer for excess dma.
 *
 * @q:  the request queue for the device
 * @buf:	physically contiguous buffer
 * @size:	size of the buffer in bytes
 *
 * Some devices have excess DMA problems and can't simply discard (or
 * zero fill) the unwanted piece of the transfer.  They have to have a
 * real area of memory to transfer it into.  The use case for this is
 * ATAPI devices in DMA mode.  If the packet command causes a transfer
 * bigger than the transfer size some HBAs will lock up if there
 * aren't DMA elements to contain the excess transfer.  What this API
 * does is adjust the queue so that the buf is always appended
 * silently to the scatterlist.
 *
 * Note: This routine adjusts max_hw_segments to make room for
 * appending the drain buffer.  If you call
 * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
 * calling this routine, you must set the limit to one fewer than your
 * device can support otherwise there won't be room for the drain
 * buffer.
 */
int blk_queue_dma_drain(struct request_queue *q, void *buf,
				unsigned int size)
{
	if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
		return -EINVAL;
	/* make room for appending the drain */
	--q->max_hw_segments;
	--q->max_phys_segments;
	q->dma_drain_buffer = buf;
	q->dma_drain_size = size;

	return 0;
}

EXPORT_SYMBOL_GPL(blk_queue_dma_drain);

/**
 * blk_queue_segment_boundary - set boundary rules for segment merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
	if (mask < PAGE_CACHE_SIZE - 1) {
		mask = PAGE_CACHE_SIZE - 1;
		printk("%s: set to minimum %lx\n", __FUNCTION__, mask);
	}

	q->seg_boundary_mask = mask;
}

EXPORT_SYMBOL(blk_queue_segment_boundary);

/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    set required memory and length aligment for direct dma transactions.
 *    this is used when buiding direct io requests for the queue.
 *
 **/
void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
	q->dma_alignment = mask;
}

EXPORT_SYMBOL(blk_queue_dma_alignment);

/**
 * blk_queue_update_dma_alignment - update dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    update required memory and length aligment for direct dma transactions.
 *    If the requested alignment is larger than the current alignment, then
 *    the current queue alignment is updated to the new value, otherwise it
 *    is left alone.  The design of this is to allow multiple objects
 *    (driver, device, transport etc) to set their respective
 *    alignments without having them interfere.
 *
 **/
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
{
	BUG_ON(mask > PAGE_SIZE);

	if (mask > q->dma_alignment)
		q->dma_alignment = mask;
}

EXPORT_SYMBOL(blk_queue_update_dma_alignment);

/**
 * blk_queue_find_tag - find a request by its tag and queue
 * @q:	 The request queue for the device
 * @tag: The tag of the request
 *
 * Notes:
 *    Should be used when a device returns a tag and you want to match
 *    it with a request.
 *
 *    no locks need be held.
 **/
struct request *blk_queue_find_tag(struct request_queue *q, int tag)
{
	return blk_map_queue_find_tag(q->queue_tags, tag);
}

EXPORT_SYMBOL(blk_queue_find_tag);

/**
 * __blk_free_tags - release a given set of tag maintenance info
 * @bqt:	the tag map to free
 *
 * Tries to free the specified @bqt@.  Returns true if it was
 * actually freed and false if there are still references using it
 */
static int __blk_free_tags(struct blk_queue_tag *bqt)
{
	int retval;

	retval = atomic_dec_and_test(&bqt->refcnt);
	if (retval) {
		BUG_ON(bqt->busy);

		kfree(bqt->tag_index);
		bqt->tag_index = NULL;

		kfree(bqt->tag_map);
		bqt->tag_map = NULL;

		kfree(bqt);

	}

	return retval;
}

/**
 * __blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *    blk_cleanup_queue() will take care of calling this function, if tagging
 *    has been used. So there's no need to call this directly.
 **/
static void __blk_queue_free_tags(struct request_queue *q)
{
	struct blk_queue_tag *bqt = q->queue_tags;

	if (!bqt)
		return;

	__blk_free_tags(bqt);

	q->queue_tags = NULL;
	q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
}


/**
 * blk_free_tags - release a given set of tag maintenance info
 * @bqt:	the tag map to free
 *
 * For externally managed @bqt@ frees the map.  Callers of this
 * function must guarantee to have released all the queues that
 * might have been using this tag map.
 */
void blk_free_tags(struct blk_queue_tag *bqt)
{
	if (unlikely(!__blk_free_tags(bqt)))
		BUG();
}
EXPORT_SYMBOL(blk_free_tags);

/**
 * blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *	This is used to disabled tagged queuing to a device, yet leave
 *	queue in function.
 **/
void blk_queue_free_tags(struct request_queue *q)
{
	clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
}

EXPORT_SYMBOL(blk_queue_free_tags);

static int
init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
{
	struct request **tag_index;
	unsigned long *tag_map;
	int nr_ulongs;

	if (q && depth > q->nr_requests * 2) {
		depth = q->nr_requests * 2;
		printk(KERN_ERR "%s: adjusted depth to %d\n",
				__FUNCTION__, depth);
	}

	tag_index = kzalloc(depth * sizeof(struct request *), GFP_ATOMIC);
	if (!tag_index)
		goto fail;

	nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
	tag_map = kzalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
	if (!tag_map)
		goto fail;

	tags->real_max_depth = depth;
	tags->max_depth = depth;
	tags->tag_index = tag_index;
	tags->tag_map = tag_map;

	return 0;
fail:
	kfree(tag_index);
	return -ENOMEM;
}

static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
						   int depth)
{
	struct blk_queue_tag *tags;

	tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
	if (!tags)
		goto fail;

	if (init_tag_map(q, tags, depth))
		goto fail;

	tags->busy = 0;
	atomic_set(&tags->refcnt, 1);
	return tags;
fail:
	kfree(tags);
	return NULL;
}

/**
 * blk_init_tags - initialize the tag info for an external tag map
 * @depth:	the maximum queue depth supported
 * @tags: the tag to use
 **/
struct blk_queue_tag *blk_init_tags(int depth)
{
	return __blk_queue_init_tags(NULL, depth);
}
EXPORT_SYMBOL(blk_init_tags);

/**
 * blk_queue_init_tags - initialize the queue tag info
 * @q:  the request queue for the device
 * @depth:  the maximum queue depth supported
 * @tags: the tag to use
 **/
int blk_queue_init_tags(struct request_queue *q, int depth,
			struct blk_queue_tag *tags)
{
	int rc;

	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);

	if (!tags && !q->queue_tags) {
		tags = __blk_queue_init_tags(q, depth);

		if (!tags)
			goto fail;
	} else if (q->queue_tags) {
		if ((rc = blk_queue_resize_tags(q, depth)))
			return rc;
		set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
		return 0;
	} else
		atomic_inc(&tags->refcnt);

	/*
	 * assign it, all done
	 */
	q->queue_tags = tags;
	q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
	INIT_LIST_HEAD(&q->tag_busy_list);
	return 0;
fail:
	kfree(tags);
	return -ENOMEM;
}

EXPORT_SYMBOL(blk_queue_init_tags);

/**
 * blk_queue_resize_tags - change the queueing depth
 * @q:  the request queue for the device
 * @new_depth: the new max command queueing depth
 *
 *  Notes:
 *    Must be called with the queue lock held.
 **/
int blk_queue_resize_tags(struct request_queue *q, int new_depth)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	struct request **tag_index;
	unsigned long *tag_map;
	int max_depth, nr_ulongs;

	if (!bqt)
		return -ENXIO;

	/*
	 * if we already have large enough real_max_depth.  just
	 * adjust max_depth.  *NOTE* as requests with tag value
	 * between new_depth and real_max_depth can be in-flight, tag
	 * map can not be shrunk blindly here.
	 */
	if (new_depth <= bqt->real_max_depth) {
		bqt->max_depth = new_depth;
		return 0;
	}

	/*
	 * Currently cannot replace a shared tag map with a new
	 * one, so error out if this is the case
	 */
	if (atomic_read(&bqt->refcnt) != 1)
		return -EBUSY;

	/*
	 * save the old state info, so we can copy it back
	 */
	tag_index = bqt->tag_index;
	tag_map = bqt->tag_map;
	max_depth = bqt->real_max_depth;

	if (init_tag_map(q, bqt, new_depth))
		return -ENOMEM;

	memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
	nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
	memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));

	kfree(tag_index);
	kfree(tag_map);
	return 0;
}

EXPORT_SYMBOL(blk_queue_resize_tags);

/**
 * blk_queue_end_tag - end tag operations for a request
 * @q:  the request queue for the device
 * @rq: the request that has completed
 *
 *  Description:
 *    Typically called when end_that_request_first() returns 0, meaning
 *    all transfers have been done for a request. It's important to call
 *    this function before end_that_request_last(), as that will put the
 *    request back on the free list thus corrupting the internal tag list.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	int tag = rq->tag;

	BUG_ON(tag == -1);

	if (unlikely(tag >= bqt->real_max_depth))
		/*
		 * This can happen after tag depth has been reduced.
		 * FIXME: how about a warning or info message here?
		 */
		return;

	list_del_init(&rq->queuelist);
	rq->cmd_flags &= ~REQ_QUEUED;
	rq->tag = -1;

	if (unlikely(bqt->tag_index[tag] == NULL))
		printk(KERN_ERR "%s: tag %d is missing\n",
		       __FUNCTION__, tag);

	bqt->tag_index[tag] = NULL;

	if (unlikely(!test_bit(tag, bqt->tag_map))) {
		printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
		       __FUNCTION__, tag);
		return;
	}
	/*
	 * The tag_map bit acts as a lock for tag_index[bit], so we need
	 * unlock memory barrier semantics.
	 */
	clear_bit_unlock(tag, bqt->tag_map);
	bqt->busy--;
}

EXPORT_SYMBOL(blk_queue_end_tag);

/**
 * blk_queue_start_tag - find a free tag and assign it
 * @q:  the request queue for the device
 * @rq:  the block request that needs tagging
 *
 *  Description:
 *    This can either be used as a stand-alone helper, or possibly be
 *    assigned as the queue &prep_rq_fn (in which case &struct request
 *    automagically gets a tag assigned). Note that this function
 *    assumes that any type of request can be queued! if this is not
 *    true for your device, you must check the request type before
 *    calling this function.  The request will also be removed from
 *    the request queue, so it's the drivers responsibility to readd
 *    it if it should need to be restarted for some reason.
 *
 *  Notes:
 *   queue lock must be held.
 **/
int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	int tag;

	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
		printk(KERN_ERR 
		       "%s: request %p for device [%s] already tagged %d",
		       __FUNCTION__, rq,
		       rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
		BUG();
	}

	/*
	 * Protect against shared tag maps, as we may not have exclusive
	 * access to the tag map.
	 */
	do {
		tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
		if (tag >= bqt->max_depth)
			return 1;

	} while (test_and_set_bit_lock(tag, bqt->tag_map));
	/*
	 * We need lock ordering semantics given by test_and_set_bit_lock.
	 * See blk_queue_end_tag for details.
	 */

	rq->cmd_flags |= REQ_QUEUED;
	rq->tag = tag;
	bqt->tag_index[tag] = rq;
	blkdev_dequeue_request(rq);
	list_add(&rq->queuelist, &q->tag_busy_list);
	bqt->busy++;
	return 0;
}

EXPORT_SYMBOL(blk_queue_start_tag);

/**
 * blk_queue_invalidate_tags - invalidate all pending tags
 * @q:  the request queue for the device
 *
 *  Description:
 *   Hardware conditions may dictate a need to stop all pending requests.
 *   In this case, we will safely clear the block side of the tag queue and
 *   readd all requests to the request queue in the right order.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_invalidate_tags(struct request_queue *q)
{
	struct list_head *tmp, *n;

	list_for_each_safe(tmp, n, &q->tag_busy_list)
		blk_requeue_request(q, list_entry_rq(tmp));
}

EXPORT_SYMBOL(blk_queue_invalidate_tags);

void blk_dump_rq_flags(struct request *rq, char *msg)
{
	int bit;

	printk("%s: dev %s: type=%x, flags=%x\n", msg,
		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
		rq->cmd_flags);

	printk("\nsector %llu, nr/cnr %lu/%u\n", (unsigned long long)rq->sector,
						       rq->nr_sectors,
						       rq->current_nr_sectors);
	printk("bio %p, biotail %p, buffer %p, data %p, len %u\n", rq->bio, rq->biotail, rq->buffer, rq->data, rq->data_len);

	if (blk_pc_request(rq)) {
		printk("cdb: ");
		for (bit = 0; bit < sizeof(rq->cmd); bit++)
			printk("%02x ", rq->cmd[bit]);
		printk("\n");
	}
}

EXPORT_SYMBOL(blk_dump_rq_flags);

void blk_recount_segments(struct request_queue *q, struct bio *bio)
{
	struct request rq;
	struct bio *nxt = bio->bi_next;
	rq.q = q;
	rq.bio = rq.biotail = bio;
	bio->bi_next = NULL;
	blk_recalc_rq_segments(&rq);
	bio->bi_next = nxt;
	bio->bi_phys_segments = rq.nr_phys_segments;
	bio->bi_hw_segments = rq.nr_hw_segments;
	bio->bi_flags |= (1 << BIO_SEG_VALID);
}
EXPORT_SYMBOL(blk_recount_segments);

static void blk_recalc_rq_segments(struct request *rq)
{
	int nr_phys_segs;
	int nr_hw_segs;
	unsigned int phys_size;
	unsigned int hw_size;
	struct bio_vec *bv, *bvprv = NULL;
	int seg_size;
	int hw_seg_size;
	int cluster;
	struct req_iterator iter;
	int high, highprv = 1;
	struct request_queue *q = rq->q;

	if (!rq->bio)
		return;

	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
	hw_seg_size = seg_size = 0;
	phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
	rq_for_each_segment(bv, rq, iter) {
		/*
		 * the trick here is making sure that a high page is never
		 * considered part of another segment, since that might
		 * change with the bounce page.
		 */
		high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
		if (high || highprv)
			goto new_hw_segment;
		if (cluster) {
			if (seg_size + bv->bv_len > q->max_segment_size)
				goto new_segment;
			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
				goto new_segment;
			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
				goto new_segment;
			if (BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
				goto new_hw_segment;

			seg_size += bv->bv_len;
			hw_seg_size += bv->bv_len;
			bvprv = bv;
			continue;
		}
new_segment:
		if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
		    !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
			hw_seg_size += bv->bv_len;
		else {
new_hw_segment:
			if (nr_hw_segs == 1 &&
			    hw_seg_size > rq->bio->bi_hw_front_size)
				rq->bio->bi_hw_front_size = hw_seg_size;
			hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
			nr_hw_segs++;
		}

		nr_phys_segs++;
		bvprv = bv;
		seg_size = bv->bv_len;
		highprv = high;
	}

	if (nr_hw_segs == 1 &&
	    hw_seg_size > rq->bio->bi_hw_front_size)
		rq->bio->bi_hw_front_size = hw_seg_size;
	if (hw_seg_size > rq->biotail->bi_hw_back_size)
		rq->biotail->bi_hw_back_size = hw_seg_size;
	rq->nr_phys_segments = nr_phys_segs;
	rq->nr_hw_segments = nr_hw_segs;
}

static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
				   struct bio *nxt)
{
	if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
		return 0;

	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
		return 0;
	if (bio->bi_size + nxt->bi_size > q->max_segment_size)
		return 0;

	/*
	 * bio and nxt are contigous in memory, check if the queue allows
	 * these two to be merged into one
	 */
	if (BIO_SEG_BOUNDARY(q, bio, nxt))
		return 1;

	return 0;
}

static int blk_hw_contig_segment(struct request_queue *q, struct bio *bio,
				 struct bio *nxt)
{
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
		blk_recount_segments(q, nxt);
	if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
	    BIOVEC_VIRT_OVERSIZE(bio->bi_hw_back_size + nxt->bi_hw_front_size))
		return 0;
	if (bio->bi_hw_back_size + nxt->bi_hw_front_size > q->max_segment_size)
		return 0;

	return 1;
}

/*
 * map a request to scatterlist, return number of sg entries setup. Caller
 * must make sure sg can hold rq->nr_phys_segments entries
 */
int blk_rq_map_sg(struct request_queue *q, struct request *rq,
		  struct scatterlist *sglist)
{
	struct bio_vec *bvec, *bvprv;
	struct req_iterator iter;
	struct scatterlist *sg;
	int nsegs, cluster;

	nsegs = 0;
	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);

	/*
	 * for each bio in rq
	 */
	bvprv = NULL;
	sg = NULL;
	rq_for_each_segment(bvec, rq, iter) {
		int nbytes = bvec->bv_len;

		if (bvprv && cluster) {
			if (sg->length + nbytes > q->max_segment_size)
				goto new_segment;

			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
				goto new_segment;
			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
				goto new_segment;

			sg->length += nbytes;
		} else {
new_segment:
			if (!sg)
				sg = sglist;
			else {
				/*
				 * If the driver previously mapped a shorter
				 * list, we could see a termination bit
				 * prematurely unless it fully inits the sg
				 * table on each mapping. We KNOW that there
				 * must be more entries here or the driver
				 * would be buggy, so force clear the
				 * termination bit to avoid doing a full
				 * sg_init_table() in drivers for each command.
				 */
				sg->page_link &= ~0x02;
				sg = sg_next(sg);
			}

			sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
			nsegs++;
		}
		bvprv = bvec;
	} /* segments in rq */

	if (q->dma_drain_size) {
		sg->page_link &= ~0x02;
		sg = sg_next(sg);
		sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
			    q->dma_drain_size,
			    ((unsigned long)q->dma_drain_buffer) &
			    (PAGE_SIZE - 1));
		nsegs++;
	}

	if (sg)
		sg_mark_end(sg);

	return nsegs;
}

EXPORT_SYMBOL(blk_rq_map_sg);

/*
 * the standard queue merge functions, can be overridden with device
 * specific ones if so desired
 */

static inline int ll_new_mergeable(struct request_queue *q,
				   struct request *req,
				   struct bio *bio)
{
	int nr_phys_segs = bio_phys_segments(q, bio);

	if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
		req->cmd_flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}

	/*
	 * A hw segment is just getting larger, bump just the phys
	 * counter.
	 */
	req->nr_phys_segments += nr_phys_segs;
	return 1;
}

static inline int ll_new_hw_segment(struct request_queue *q,
				    struct request *req,
				    struct bio *bio)
{
	int nr_hw_segs = bio_hw_segments(q, bio);
	int nr_phys_segs = bio_phys_segments(q, bio);

	if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
		req->cmd_flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}

	/*
	 * This will form the start of a new hw segment.  Bump both
	 * counters.
	 */
	req->nr_hw_segments += nr_hw_segs;
	req->nr_phys_segments += nr_phys_segs;
	return 1;
}

static int ll_back_merge_fn(struct request_queue *q, struct request *req,
			    struct bio *bio)
{
	unsigned short max_sectors;
	int len;

	if (unlikely(blk_pc_request(req)))
		max_sectors = q->max_hw_sectors;
	else
		max_sectors = q->max_sectors;

	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
		req->cmd_flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}
	if (unlikely(!bio_flagged(req->biotail, BIO_SEG_VALID)))
		blk_recount_segments(q, req->biotail);
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	len = req->biotail->bi_hw_back_size + bio->bi_hw_front_size;
	if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(req->biotail), __BVEC_START(bio)) &&
	    !BIOVEC_VIRT_OVERSIZE(len)) {
		int mergeable =  ll_new_mergeable(q, req, bio);

		if (mergeable) {
			if (req->nr_hw_segments == 1)
				req->bio->bi_hw_front_size = len;
			if (bio->bi_hw_segments == 1)
				bio->bi_hw_back_size = len;
		}
		return mergeable;
	}

	return ll_new_hw_segment(q, req, bio);
}

static int ll_front_merge_fn(struct request_queue *q, struct request *req, 
			     struct bio *bio)
{
	unsigned short max_sectors;
	int len;

	if (unlikely(blk_pc_request(req)))
		max_sectors = q->max_hw_sectors;
	else
		max_sectors = q->max_sectors;


	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
		req->cmd_flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}
	len = bio->bi_hw_back_size + req->bio->bi_hw_front_size;
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	if (unlikely(!bio_flagged(req->bio, BIO_SEG_VALID)))
		blk_recount_segments(q, req->bio);
	if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(req->bio)) &&
	    !BIOVEC_VIRT_OVERSIZE(len)) {
		int mergeable =  ll_new_mergeable(q, req, bio);

		if (mergeable) {
			if (bio->bi_hw_segments == 1)
				bio->bi_hw_front_size = len;
			if (req->nr_hw_segments == 1)
				req->biotail->bi_hw_back_size = len;
		}
		return mergeable;
	}

	return ll_new_hw_segment(q, req, bio);
}

static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
				struct request *next)
{
	int total_phys_segments;
	int total_hw_segments;

	/*
	 * First check if the either of the requests are re-queued
	 * requests.  Can't merge them if they are.
	 */
	if (req->special || next->special)
		return 0;

	/*
	 * Will it become too large?
	 */
	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
		return 0;

	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
	if (blk_phys_contig_segment(q, req->biotail, next->bio))
		total_phys_segments--;

	if (total_phys_segments > q->max_phys_segments)
		return 0;

	total_hw_segments = req->nr_hw_segments + next->nr_hw_segments;
	if (blk_hw_contig_segment(q, req->biotail, next->bio)) {
		int len = req->biotail->bi_hw_back_size + next->bio->bi_hw_front_size;
		/*
		 * propagate the combined length to the end of the requests
		 */
		if (req->nr_hw_segments == 1)
			req->bio->bi_hw_front_size = len;
		if (next->nr_hw_segments == 1)
			next->biotail->bi_hw_back_size = len;
		total_hw_segments--;
	}

	if (total_hw_segments > q->max_hw_segments)
		return 0;

	/* Merge is OK... */
	req->nr_phys_segments = total_phys_segments;
	req->nr_hw_segments = total_hw_segments;
	return 1;
}

/*
 * "plug" the device if there are no outstanding requests: this will
 * force the transfer to start only after we have put all the requests
 * on the list.
 *
 * This is called with interrupts off and no requests on the queue and
 * with the queue lock held.
 */
void blk_plug_device(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	/*
	 * don't plug a stopped queue, it must be paired with blk_start_queue()
	 * which will restart the queueing
	 */
	if (blk_queue_stopped(q))
		return;

	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
		blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
	}
}

EXPORT_SYMBOL(blk_plug_device);

/*
 * remove the queue from the plugged list, if present. called with
 * queue lock held and interrupts disabled.
 */
int blk_remove_plug(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
		return 0;

	del_timer(&q->unplug_timer);
	return 1;
}

EXPORT_SYMBOL(blk_remove_plug);

/*
 * remove the plug and let it rip..
 */
void __generic_unplug_device(struct request_queue *q)
{
	if (unlikely(blk_queue_stopped(q)))
		return;

	if (!blk_remove_plug(q))
		return;

	q->request_fn(q);
}
EXPORT_SYMBOL(__generic_unplug_device);

/**
 * generic_unplug_device - fire a request queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   Linux uses plugging to build bigger requests queues before letting
 *   the device have at them. If a queue is plugged, the I/O scheduler
 *   is still adding and merging requests on the queue. Once the queue
 *   gets unplugged, the request_fn defined for the queue is invoked and
 *   transfers started.
 **/
void generic_unplug_device(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	__generic_unplug_device(q);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL(generic_unplug_device);

static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
				   struct page *page)
{
	struct request_queue *q = bdi->unplug_io_data;

	blk_unplug(q);
}

static void blk_unplug_work(struct work_struct *work)
{
	struct request_queue *q =
		container_of(work, struct request_queue, unplug_work);

	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
				q->rq.count[READ] + q->rq.count[WRITE]);

	q->unplug_fn(q);
}

static void blk_unplug_timeout(unsigned long data)
{
	struct request_queue *q = (struct request_queue *)data;

	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
				q->rq.count[READ] + q->rq.count[WRITE]);

	kblockd_schedule_work(&q->unplug_work);
}

void blk_unplug(struct request_queue *q)
{
	/*
	 * devices don't necessarily have an ->unplug_fn defined
	 */
	if (q->unplug_fn) {
		blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
					q->rq.count[READ] + q->rq.count[WRITE]);

		q->unplug_fn(q);
	}
}
EXPORT_SYMBOL(blk_unplug);

/**
 * blk_start_queue - restart a previously stopped queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   blk_start_queue() will clear the stop flag on the queue, and call
 *   the request_fn for the queue if it was in a stopped state when
 *   entered. Also see blk_stop_queue(). Queue lock must be held.
 **/
void blk_start_queue(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);

	/*
	 * one level of recursion is ok and is much faster than kicking
	 * the unplug handling
	 */
	if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
		q->request_fn(q);
		clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
	} else {
		blk_plug_device(q);
		kblockd_schedule_work(&q->unplug_work);
	}
}

EXPORT_SYMBOL(blk_start_queue);

/**
 * blk_stop_queue - stop a queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   The Linux block layer assumes that a block driver will consume all
 *   entries on the request queue when the request_fn strategy is called.
 *   Often this will not happen, because of hardware limitations (queue
 *   depth settings). If a device driver gets a 'queue full' response,
 *   or if it simply chooses not to queue more I/O at one point, it can
 *   call this function to prevent the request_fn from being called until
 *   the driver has signalled it's ready to go again. This happens by calling
 *   blk_start_queue() to restart queue operations. Queue lock must be held.
 **/
void blk_stop_queue(struct request_queue *q)
{
	blk_remove_plug(q);
	set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
}
EXPORT_SYMBOL(blk_stop_queue);

/**
 * blk_sync_queue - cancel any pending callbacks on a queue
 * @q: the queue
 *
 * Description:
 *     The block layer may perform asynchronous callback activity
 *     on a queue, such as calling the unplug function after a timeout.
 *     A block device may call blk_sync_queue to ensure that any
 *     such activity is cancelled, thus allowing it to release resources
 *     that the callbacks might use. The caller must already have made sure
 *     that its ->make_request_fn will not re-add plugging prior to calling
 *     this function.
 *
 */
void blk_sync_queue(struct request_queue *q)
{
	del_timer_sync(&q->unplug_timer);
	kblockd_flush_work(&q->unplug_work);
}
EXPORT_SYMBOL(blk_sync_queue);

/**
 * blk_run_queue - run a single device queue
 * @q:	The queue to run
 */
void blk_run_queue(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_remove_plug(q);

	/*
	 * Only recurse once to avoid overrunning the stack, let the unplug
	 * handling reinvoke the handler shortly if we already got there.
	 */
	if (!elv_queue_empty(q)) {
		if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
			q->request_fn(q);
			clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
		} else {
			blk_plug_device(q);
			kblockd_schedule_work(&q->unplug_work);
		}
	}

	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);

/**
 * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed
 * @kobj:    the kobj belonging of the request queue to be released
 *
 * Description:
 *     blk_cleanup_queue is the pair to blk_init_queue() or
 *     blk_queue_make_request().  It should be called when a request queue is
 *     being released; typically when a block device is being de-registered.
 *     Currently, its primary task it to free all the &struct request
 *     structures that were allocated to the queue and the queue itself.
 *
 * Caveat:
 *     Hopefully the low level driver will have finished any
 *     outstanding requests first...
 **/
static void blk_release_queue(struct kobject *kobj)
{
	struct request_queue *q =
		container_of(kobj, struct request_queue, kobj);
	struct request_list *rl = &q->rq;

	blk_sync_queue(q);

	if (rl->rq_pool)
		mempool_destroy(rl->rq_pool);

	if (q->queue_tags)
		__blk_queue_free_tags(q);

	blk_trace_shutdown(q);

	bdi_destroy(&q->backing_dev_info);
	kmem_cache_free(requestq_cachep, q);
}

void blk_put_queue(struct request_queue *q)
{
	kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);

void blk_cleanup_queue(struct request_queue * q)
{
	mutex_lock(&q->sysfs_lock);
	set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
	mutex_unlock(&q->sysfs_lock);

	if (q->elevator)
		elevator_exit(q->elevator);

	blk_put_queue(q);
}

EXPORT_SYMBOL(blk_cleanup_queue);

static int blk_init_free_list(struct request_queue *q)
{
	struct request_list *rl = &q->rq;

	rl->count[READ] = rl->count[WRITE] = 0;
	rl->starved[READ] = rl->starved[WRITE] = 0;
	rl->elvpriv = 0;
	init_waitqueue_head(&rl->wait[READ]);
	init_waitqueue_head(&rl->wait[WRITE]);

	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
				mempool_free_slab, request_cachep, q->node);

	if (!rl->rq_pool)
		return -ENOMEM;

	return 0;
}

struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
	return blk_alloc_queue_node(gfp_mask, -1);
}
EXPORT_SYMBOL(blk_alloc_queue);

static struct kobj_type queue_ktype;

struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
	struct request_queue *q;
	int err;

	q = kmem_cache_alloc_node(requestq_cachep,
				gfp_mask | __GFP_ZERO, node_id);
	if (!q)
		return NULL;

	q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
	q->backing_dev_info.unplug_io_data = q;
	err = bdi_init(&q->backing_dev_info);
	if (err) {
		kmem_cache_free(requestq_cachep, q);
		return NULL;
	}

	init_timer(&q->unplug_timer);

	kobject_init(&q->kobj, &queue_ktype);

	mutex_init(&q->sysfs_lock);

	return q;
}
EXPORT_SYMBOL(blk_alloc_queue_node);

/**
 * blk_init_queue  - prepare a request queue for use with a block device
 * @rfn:  The function to be called to process requests that have been
 *        placed on the queue.
 * @lock: Request queue spin lock
 *
 * Description:
 *    If a block device wishes to use the standard request handling procedures,
 *    which sorts requests and coalesces adjacent requests, then it must
 *    call blk_init_queue().  The function @rfn will be called when there
 *    are requests on the queue that need to be processed.  If the device
 *    supports plugging, then @rfn may not be called immediately when requests
 *    are available on the queue, but may be called at some time later instead.
 *    Plugged queues are generally unplugged when a buffer belonging to one
 *    of the requests on the queue is needed, or due to memory pressure.
 *
 *    @rfn is not required, or even expected, to remove all requests off the
 *    queue, but only as many as it can handle at a time.  If it does leave
 *    requests on the queue, it is responsible for arranging that the requests
 *    get dealt with eventually.
 *
 *    The queue spin lock must be held while manipulating the requests on the
 *    request queue; this lock will be taken also from interrupt context, so irq
 *    disabling is needed for it.
 *
 *    Function returns a pointer to the initialized request queue, or NULL if
 *    it didn't succeed.
 *
 * Note:
 *    blk_init_queue() must be paired with a blk_cleanup_queue() call
 *    when the block device is deactivated (such as at module unload).
 **/

struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
	return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);

struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
	struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id);

	if (!q)
		return NULL;

	q->node = node_id;
	if (blk_init_free_list(q)) {
		kmem_cache_free(requestq_cachep, q);
		return NULL;
	}

	/*
	 * if caller didn't supply a lock, they get per-queue locking with
	 * our embedded lock
	 */
	if (!lock) {
		spin_lock_init(&q->__queue_lock);
		lock = &q->__queue_lock;
	}

	q->request_fn		= rfn;
	q->prep_rq_fn		= NULL;
	q->unplug_fn		= generic_unplug_device;
	q->queue_flags		= (1 << QUEUE_FLAG_CLUSTER);
	q->queue_lock		= lock;

	blk_queue_segment_boundary(q, 0xffffffff);

	blk_queue_make_request(q, __make_request);
	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);

	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);

	q->sg_reserved_size = INT_MAX;

	/*
	 * all done
	 */
	if (!elevator_init(q, NULL)) {
		blk_queue_congestion_threshold(q);
		return q;
	}

	blk_put_queue(q);
	return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);

int blk_get_queue(struct request_queue *q)
{
	if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
		kobject_get(&q->kobj);
		return 0;
	}

	return 1;
}

EXPORT_SYMBOL(blk_get_queue);

static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
	if (rq->cmd_flags & REQ_ELVPRIV)
		elv_put_request(q, rq);
	mempool_free(rq, q->rq.rq_pool);
}

static struct request *
blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
{
	struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);

	if (!rq)
		return NULL;

	/*
	 * first three bits are identical in rq->cmd_flags and bio->bi_rw,
	 * see bio.h and blkdev.h
	 */
	rq->cmd_flags = rw | REQ_ALLOCED;

	if (priv) {
		if (unlikely(elv_set_request(q, rq, gfp_mask))) {
			mempool_free(rq, q->rq.rq_pool);
			return NULL;
		}
		rq->cmd_flags |= REQ_ELVPRIV;
	}

	return rq;
}

/*
 * ioc_batching returns true if the ioc is a valid batching request and
 * should be given priority access to a request.
 */
static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
{
	if (!ioc)
		return 0;

	/*
	 * Make sure the process is able to allocate at least 1 request
	 * even if the batch times out, otherwise we could theoretically
	 * lose wakeups.
	 */
	return ioc->nr_batch_requests == q->nr_batching ||
		(ioc->nr_batch_requests > 0
		&& time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
}

/*
 * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
 * will cause the process to be a "batcher" on all queues in the system. This
 * is the behaviour we want though - once it gets a wakeup it should be given
 * a nice run.
 */
static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
{
	if (!ioc || ioc_batching(q, ioc))
		return;

	ioc->nr_batch_requests = q->nr_batching;
	ioc->last_waited = jiffies;
}

static void __freed_request(struct request_queue *q, int rw)
{
	struct request_list *rl = &q->rq;

	if (rl->count[rw] < queue_congestion_off_threshold(q))
		blk_clear_queue_congested(q, rw);

	if (rl->count[rw] + 1 <= q->nr_requests) {
		if (waitqueue_active(&rl->wait[rw]))
			wake_up(&rl->wait[rw]);

		blk_clear_queue_full(q, rw);
	}
}

/*
 * A request has just been released.  Account for it, update the full and
 * congestion status, wake up any waiters.   Called under q->queue_lock.
 */
static void freed_request(struct request_queue *q, int rw, int priv)
{
	struct request_list *rl = &q->rq;

	rl->count[rw]--;
	if (priv)
		rl->elvpriv--;

	__freed_request(q, rw);

	if (unlikely(rl->starved[rw ^ 1]))
		__freed_request(q, rw ^ 1);
}

#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
/*
 * Get a free request, queue_lock must be held.
 * Returns NULL on failure, with queue_lock held.
 * Returns !NULL on success, with queue_lock *not held*.
 */
static struct request *get_request(struct request_queue *q, int rw_flags,
				   struct bio *bio, gfp_t gfp_mask)
{
	struct request *rq = NULL;
	struct request_list *rl = &q->rq;
	struct io_context *ioc = NULL;
	const int rw = rw_flags & 0x01;
	int may_queue, priv;

	may_queue = elv_may_queue(q, rw_flags);
	if (may_queue == ELV_MQUEUE_NO)
		goto rq_starved;

	if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
		if (rl->count[rw]+1 >= q->nr_requests) {
			ioc = current_io_context(GFP_ATOMIC, q->node);
			/*
			 * The queue will fill after this allocation, so set
			 * it as full, and mark this process as "batching".
			 * This process will be allowed to complete a batch of
			 * requests, others will be blocked.
			 */
			if (!blk_queue_full(q, rw)) {
				ioc_set_batching(q, ioc);
				blk_set_queue_full(q, rw);
			} else {
				if (may_queue != ELV_MQUEUE_MUST
						&& !ioc_batching(q, ioc)) {
					/*
					 * The queue is full and the allocating
					 * process is not a "batcher", and not
					 * exempted by the IO scheduler
					 */
					goto out;
				}
			}
		}
		blk_set_queue_congested(q, rw);
	}

	/*
	 * Only allow batching queuers to allocate up to 50% over the defined
	 * limit of requests, otherwise we could have thousands of requests
	 * allocated with any setting of ->nr_requests
	 */
	if (rl->count[rw] >= (3 * q->nr_requests / 2))
		goto out;

	rl->count[rw]++;
	rl->starved[rw] = 0;

	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
	if (priv)
		rl->elvpriv++;

	spin_unlock_irq(q->queue_lock);

	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
	if (unlikely(!rq)) {
		/*
		 * Allocation failed presumably due to memory. Undo anything
		 * we might have messed up.
		 *
		 * Allocating task should really be put onto the front of the
		 * wait queue, but this is pretty rare.
		 */
		spin_lock_irq(q->queue_lock);
		freed_request(q, rw, priv);

		/*
		 * in the very unlikely event that allocation failed and no
		 * requests for this direction was pending, mark us starved
		 * so that freeing of a request in the other direction will
		 * notice us. another possible fix would be to split the
		 * rq mempool into READ and WRITE
		 */
rq_starved:
		if (unlikely(rl->count[rw] == 0))
			rl->starved[rw] = 1;

		goto out;
	}

	/*
	 * ioc may be NULL here, and ioc_batching will be false. That's
	 * OK, if the queue is under the request limit then requests need
	 * not count toward the nr_batch_requests limit. There will always
	 * be some limit enforced by BLK_BATCH_TIME.
	 */
	if (ioc_batching(q, ioc))
		ioc->nr_batch_requests--;
	
	rq_init(q, rq);

	blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
out:
	return rq;
}

/*
 * No available requests for this queue, unplug the device and wait for some
 * requests to become available.
 *
 * Called with q->queue_lock held, and returns with it unlocked.
 */
static struct request *get_request_wait(struct request_queue *q, int rw_flags,
					struct bio *bio)
{
	const int rw = rw_flags & 0x01;
	struct request *rq;

	rq = get_request(q, rw_flags, bio, GFP_NOIO);
	while (!rq) {
		DEFINE_WAIT(wait);
		struct request_list *rl = &q->rq;

		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
				TASK_UNINTERRUPTIBLE);

		rq = get_request(q, rw_flags, bio, GFP_NOIO);

		if (!rq) {
			struct io_context *ioc;

			blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);

			__generic_unplug_device(q);
			spin_unlock_irq(q->queue_lock);
			io_schedule();

			/*
			 * After sleeping, we become a "batching" process and
			 * will be able to allocate at least one request, and
			 * up to a big batch of them for a small period time.
			 * See ioc_batching, ioc_set_batching
			 */
			ioc = current_io_context(GFP_NOIO, q->node);
			ioc_set_batching(q, ioc);

			spin_lock_irq(q->queue_lock);
		}
		finish_wait(&rl->wait[rw], &wait);
	}

	return rq;
}

struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
	struct request *rq;

	BUG_ON(rw != READ && rw != WRITE);

	spin_lock_irq(q->queue_lock);
	if (gfp_mask & __GFP_WAIT) {
		rq = get_request_wait(q, rw, NULL);
	} else {
		rq = get_request(q, rw, NULL, gfp_mask);
		if (!rq)
			spin_unlock_irq(q->queue_lock);
	}
	/* q->queue_lock is unlocked at this point */

	return rq;
}
EXPORT_SYMBOL(blk_get_request);

/**
 * blk_start_queueing - initiate dispatch of requests to device
 * @q:		request queue to kick into gear
 *
 * This is basically a helper to remove the need to know whether a queue
 * is plugged or not if someone just wants to initiate dispatch of requests
 * for this queue.
 *
 * The queue lock must be held with interrupts disabled.
 */
void blk_start_queueing(struct request_queue *q)
{
	if (!blk_queue_plugged(q))
		q->request_fn(q);
	else
		__generic_unplug_device(q);
}
EXPORT_SYMBOL(blk_start_queueing);

/**
 * blk_requeue_request - put a request back on queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 *
 * Description:
 *    Drivers often keep queueing requests until the hardware cannot accept
 *    more, when that condition happens we need to put the request back
 *    on the queue. Must be called with queue lock held.
 */
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);

	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	elv_requeue_request(q, rq);
}

EXPORT_SYMBOL(blk_requeue_request);

/**
 * blk_insert_request - insert a special request in to a request queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 * @at_head:	insert request at head or tail of queue
 * @data:	private data
 *
 * Description:
 *    Many block devices need to execute commands asynchronously, so they don't
 *    block the whole kernel from preemption during request execution.  This is
 *    accomplished normally by inserting aritficial requests tagged as
 *    REQ_SPECIAL in to the corresponding request queue, and letting them be
 *    scheduled for actual execution by the request queue.
 *
 *    We have the option of inserting the head or the tail of the queue.
 *    Typically we use the tail for new ioctls and so forth.  We use the head
 *    of the queue for things like a QUEUE_FULL message from a device, or a
 *    host that is unable to accept a particular command.
 */
void blk_insert_request(struct request_queue *q, struct request *rq,
			int at_head, void *data)
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
	unsigned long flags;

	/*
	 * tell I/O scheduler that this isn't a regular read/write (ie it
	 * must not attempt merges on this) and that it acts as a soft
	 * barrier
	 */
	rq->cmd_type = REQ_TYPE_SPECIAL;
	rq->cmd_flags |= REQ_SOFTBARRIER;

	rq->special = data;

	spin_lock_irqsave(q->queue_lock, flags);

	/*
	 * If command is tagged, release the tag
	 */
	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	drive_stat_acct(rq, 1);
	__elv_add_request(q, rq, where, 0);
	blk_start_queueing(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

EXPORT_SYMBOL(blk_insert_request);

static int __blk_rq_unmap_user(struct bio *bio)
{
	int ret = 0;

	if (bio) {
		if (bio_flagged(bio, BIO_USER_MAPPED))
			bio_unmap_user(bio);
		else
			ret = bio_uncopy_user(bio);
	}

	return ret;
}

int blk_rq_append_bio(struct request_queue *q, struct request *rq,
		      struct bio *bio)
{
	if (!rq->bio)
		blk_rq_bio_prep(q, rq, bio);
	else if (!ll_back_merge_fn(q, rq, bio))
		return -EINVAL;
	else {
		rq->biotail->bi_next = bio;
		rq->biotail = bio;

		rq->data_len += bio->bi_size;
	}
	return 0;
}
EXPORT_SYMBOL(blk_rq_append_bio);

static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
			     void __user *ubuf, unsigned int len)
{
	unsigned long uaddr;
	struct bio *bio, *orig_bio;
	int reading, ret;

	reading = rq_data_dir(rq) == READ;

	/*
	 * if alignment requirement is satisfied, map in user pages for
	 * direct dma. else, set up kernel bounce buffers
	 */
	uaddr = (unsigned long) ubuf;
	if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
		bio = bio_map_user(q, NULL, uaddr, len, reading);
	else
		bio = bio_copy_user(q, uaddr, len, reading);

	if (IS_ERR(bio))
		return PTR_ERR(bio);

	orig_bio = bio;
	blk_queue_bounce(q, &bio);

	/*
	 * We link the bounce buffer in and could have to traverse it
	 * later so we have to get a ref to prevent it from being freed
	 */
	bio_get(bio);

	ret = blk_rq_append_bio(q, rq, bio);
	if (!ret)
		return bio->bi_size;

	/* if it was boucned we must call the end io function */
	bio_endio(bio, 0);
	__blk_rq_unmap_user(orig_bio);
	bio_put(bio);
	return ret;
}

/**
 * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request structure to fill
 * @ubuf:	the user buffer
 * @len:	length of user data
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user(struct request_queue *q, struct request *rq,
		    void __user *ubuf, unsigned long len)
{
	unsigned long bytes_read = 0;
	struct bio *bio = NULL;
	int ret;

	if (len > (q->max_hw_sectors << 9))
		return -EINVAL;
	if (!len || !ubuf)
		return -EINVAL;

	while (bytes_read != len) {
		unsigned long map_len, end, start;

		map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
		end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
								>> PAGE_SHIFT;
		start = (unsigned long)ubuf >> PAGE_SHIFT;

		/*
		 * A bad offset could cause us to require BIO_MAX_PAGES + 1
		 * pages. If this happens we just lower the requested
		 * mapping len by a page so that we can fit
		 */
		if (end - start > BIO_MAX_PAGES)
			map_len -= PAGE_SIZE;

		ret = __blk_rq_map_user(q, rq, ubuf, map_len);
		if (ret < 0)
			goto unmap_rq;
		if (!bio)
			bio = rq->bio;
		bytes_read += ret;
		ubuf += ret;
	}

	rq->buffer = rq->data = NULL;
	return 0;
unmap_rq:
	blk_rq_unmap_user(bio);
	return ret;
}

EXPORT_SYMBOL(blk_rq_map_user);

/**
 * blk_rq_map_user_iov - map user data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request to map data to
 * @iov:	pointer to the iovec
 * @iov_count:	number of elements in the iovec
 * @len:	I/O byte count
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
			struct sg_iovec *iov, int iov_count, unsigned int len)
{
	struct bio *bio;

	if (!iov || iov_count <= 0)
		return -EINVAL;

	/* we don't allow misaligned data like bio_map_user() does.  If the
	 * user is using sg, they're expected to know the alignment constraints
	 * and respect them accordingly */
	bio = bio_map_user_iov(q, NULL, iov, iov_count, rq_data_dir(rq)== READ);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	if (bio->bi_size != len) {
		bio_endio(bio, 0);
		bio_unmap_user(bio);
		return -EINVAL;
	}

	bio_get(bio);
	blk_rq_bio_prep(q, rq, bio);
	rq->buffer = rq->data = NULL;
	return 0;
}

EXPORT_SYMBOL(blk_rq_map_user_iov);

/**
 * blk_rq_unmap_user - unmap a request with user data
 * @bio:	       start of bio list
 *
 * Description:
 *    Unmap a rq previously mapped by blk_rq_map_user(). The caller must
 *    supply the original rq->bio from the blk_rq_map_user() return, since
 *    the io completion may have changed rq->bio.
 */
int blk_rq_unmap_user(struct bio *bio)
{
	struct bio *mapped_bio;
	int ret = 0, ret2;

	while (bio) {
		mapped_bio = bio;
		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
			mapped_bio = bio->bi_private;

		ret2 = __blk_rq_unmap_user(mapped_bio);
		if (ret2 && !ret)
			ret = ret2;

		mapped_bio = bio;
		bio = bio->bi_next;
		bio_put(mapped_bio);
	}

	return ret;
}

EXPORT_SYMBOL(blk_rq_unmap_user);

/**
 * blk_rq_map_kern - map kernel data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request to fill
 * @kbuf:	the kernel buffer
 * @len:	length of user data
 * @gfp_mask:	memory allocation flags
 */
int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
		    unsigned int len, gfp_t gfp_mask)
{
	struct bio *bio;

	if (len > (q->max_hw_sectors << 9))
		return -EINVAL;
	if (!len || !kbuf)
		return -EINVAL;

	bio = bio_map_kern(q, kbuf, len, gfp_mask);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	if (rq_data_dir(rq) == WRITE)
		bio->bi_rw |= (1 << BIO_RW);

	blk_rq_bio_prep(q, rq, bio);
	blk_queue_bounce(q, &rq->bio);
	rq->buffer = rq->data = NULL;
	return 0;
}

EXPORT_SYMBOL(blk_rq_map_kern);

/**
 * blk_execute_rq_nowait - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 * @done:	I/O completion handler
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution.  Don't wait for completion.
 */
void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
			   struct request *rq, int at_head,
			   rq_end_io_fn *done)
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;

	rq->rq_disk = bd_disk;
	rq->cmd_flags |= REQ_NOMERGE;
	rq->end_io = done;
	WARN_ON(irqs_disabled());
	spin_lock_irq(q->queue_lock);
	__elv_add_request(q, rq, where, 1);
	__generic_unplug_device(q);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);

/**
 * blk_execute_rq - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution and wait for completion.
 */
int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
		   struct request *rq, int at_head)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	char sense[SCSI_SENSE_BUFFERSIZE];
	int err = 0;

	/*
	 * we need an extra reference to the request, so we can look at
	 * it after io completion
	 */
	rq->ref_count++;

	if (!rq->sense) {
		memset(sense, 0, sizeof(sense));
		rq->sense = sense;
		rq->sense_len = 0;
	}

	rq->end_io_data = &wait;
	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
	wait_for_completion(&wait);

	if (rq->errors)
		err = -EIO;

	return err;
}

EXPORT_SYMBOL(blk_execute_rq);

static void bio_end_empty_barrier(struct bio *bio, int err)
{
	if (err)
		clear_bit(BIO_UPTODATE, &bio->bi_flags);

	complete(bio->bi_private);
}

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:	blockdev to issue flush for
 * @error_sector:	error sector
 *
 * Description:
 *    Issue a flush for the block device in question. Caller can supply
 *    room for storing the error offset in case of a flush error, if they
 *    wish to.  Caller must run wait_for_completion() on its own.
 */
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	struct request_queue *q;
	struct bio *bio;
	int ret;

	if (bdev->bd_disk == NULL)
		return -ENXIO;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;

	bio = bio_alloc(GFP_KERNEL, 0);
	if (!bio)
		return -ENOMEM;

	bio->bi_end_io = bio_end_empty_barrier;
	bio->bi_private = &wait;
	bio->bi_bdev = bdev;
	submit_bio(1 << BIO_RW_BARRIER, bio);

	wait_for_completion(&wait);

	/*
	 * The driver must store the error location in ->bi_sector, if
	 * it supports it. For non-stacked drivers, this should be copied
	 * from rq->sector.
	 */
	if (error_sector)
		*error_sector = bio->bi_sector;

	ret = 0;
	if (!bio_flagged(bio, BIO_UPTODATE))
		ret = -EIO;

	bio_put(bio);
	return ret;
}

EXPORT_SYMBOL(blkdev_issue_flush);

static void drive_stat_acct(struct request *rq, int new_io)
{
	int rw = rq_data_dir(rq);

	if (!blk_fs_request(rq) || !rq->rq_disk)
		return;

	if (!new_io) {
		__disk_stat_inc(rq->rq_disk, merges[rw]);
	} else {
		disk_round_stats(rq->rq_disk);
		rq->rq_disk->in_flight++;
	}
}

/*
 * add-request adds a request to the linked list.
 * queue lock is held and interrupts disabled, as we muck with the
 * request queue list.
 */
static inline void add_request(struct request_queue * q, struct request * req)
{
	drive_stat_acct(req, 1);

	/*
	 * elevator indicated where it wants this request to be
	 * inserted at elevator_merge time
	 */
	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
}
 
/*
 * disk_round_stats()	- Round off the performance stats on a struct
 * disk_stats.
 *
 * The average IO queue length and utilisation statistics are maintained
 * by observing the current state of the queue length and the amount of
 * time it has been in this state for.
 *
 * Normally, that accounting is done on IO completion, but that can result
 * in more than a second's worth of IO being accounted for within any one
 * second, leading to >100% utilisation.  To deal with that, we call this
 * function to do a round-off before returning the results when reading
 * /proc/diskstats.  This accounts immediately for all queue usage up to
 * the current jiffies and restarts the counters again.
 */
void disk_round_stats(struct gendisk *disk)
{
	unsigned long now = jiffies;

	if (now == disk->stamp)
		return;

	if (disk->in_flight) {
		__disk_stat_add(disk, time_in_queue,
				disk->in_flight * (now - disk->stamp));
		__disk_stat_add(disk, io_ticks, (now - disk->stamp));
	}
	disk->stamp = now;
}

EXPORT_SYMBOL_GPL(disk_round_stats);

/*
 * queue lock must be held
 */
void __blk_put_request(struct request_queue *q, struct request *req)
{
	if (unlikely(!q))
		return;
	if (unlikely(--req->ref_count))
		return;

	elv_completed_request(q, req);

	/*
	 * Request may not have originated from ll_rw_blk. if not,
	 * it didn't come out of our reserved rq pools
	 */
	if (req->cmd_flags & REQ_ALLOCED) {
		int rw = rq_data_dir(req);
		int priv = req->cmd_flags & REQ_ELVPRIV;

		BUG_ON(!list_empty(&req->queuelist));
		BUG_ON(!hlist_unhashed(&req->hash));

		blk_free_request(q, req);
		freed_request(q, rw, priv);
	}
}

EXPORT_SYMBOL_GPL(__blk_put_request);

void blk_put_request(struct request *req)
{
	unsigned long flags;
	struct request_queue *q = req->q;

	/*
	 * Gee, IDE calls in w/ NULL q.  Fix IDE and remove the
	 * following if (q) test.
	 */
	if (q) {
		spin_lock_irqsave(q->queue_lock, flags);
		__blk_put_request(q, req);
		spin_unlock_irqrestore(q->queue_lock, flags);
	}
}

EXPORT_SYMBOL(blk_put_request);

/**
 * blk_end_sync_rq - executes a completion event on a request
 * @rq: request to complete
 * @error: end io status of the request
 */
void blk_end_sync_rq(struct request *rq, int error)
{
	struct completion *waiting = rq->end_io_data;

	rq->end_io_data = NULL;
	__blk_put_request(rq->q, rq);

	/*
	 * complete last, if this is a stack request the process (and thus
	 * the rq pointer) could be invalid right after this complete()
	 */
	complete(waiting);
}
EXPORT_SYMBOL(blk_end_sync_rq);

/*
 * Has to be called with the request spinlock acquired
 */
static int attempt_merge(struct request_queue *q, struct request *req,
			  struct request *next)
{
	if (!rq_mergeable(req) || !rq_mergeable(next))
		return 0;

	/*
	 * not contiguous
	 */
	if (req->sector + req->nr_sectors != next->sector)
		return 0;

	if (rq_data_dir(req) != rq_data_dir(next)
	    || req->rq_disk != next->rq_disk
	    || next->special)
		return 0;

	/*
	 * If we are allowed to merge, then append bio list
	 * from next to rq and release next. merge_requests_fn
	 * will have updated segment counts, update sector
	 * counts here.
	 */
	if (!ll_merge_requests_fn(q, req, next))
		return 0;

	/*
	 * At this point we have either done a back merge
	 * or front merge. We need the smaller start_time of
	 * the merged requests to be the current request
	 * for accounting purposes.
	 */
	if (time_after(req->start_time, next->start_time))
		req->start_time = next->start_time;

	req->biotail->bi_next = next->bio;
	req->biotail = next->biotail;

	req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;

	elv_merge_requests(q, req, next);

	if (req->rq_disk) {
		disk_round_stats(req->rq_disk);
		req->rq_disk->in_flight--;
	}

	req->ioprio = ioprio_best(req->ioprio, next->ioprio);

	__blk_put_request(q, next);
	return 1;
}

static inline int attempt_back_merge(struct request_queue *q,
				     struct request *rq)
{
	struct request *next = elv_latter_request(q, rq);

	if (next)
		return attempt_merge(q, rq, next);

	return 0;
}

static inline int attempt_front_merge(struct request_queue *q,
				      struct request *rq)
{
	struct request *prev = elv_former_request(q, rq);

	if (prev)
		return attempt_merge(q, prev, rq);

	return 0;
}

static void init_request_from_bio(struct request *req, struct bio *bio)
{
	req->cmd_type = REQ_TYPE_FS;

	/*
	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
	 */
	if (bio_rw_ahead(bio) || bio_failfast(bio))
		req->cmd_flags |= REQ_FAILFAST;

	/*
	 * REQ_BARRIER implies no merging, but lets make it explicit
	 */
	if (unlikely(bio_barrier(bio)))
		req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);

	if (bio_sync(bio))
		req->cmd_flags |= REQ_RW_SYNC;
	if (bio_rw_meta(bio))
		req->cmd_flags |= REQ_RW_META;

	req->errors = 0;
	req->hard_sector = req->sector = bio->bi_sector;
	req->ioprio = bio_prio(bio);
	req->start_time = jiffies;
	blk_rq_bio_prep(req->q, req, bio);
}

static int __make_request(struct request_queue *q, struct bio *bio)
{
	struct request *req;
	int el_ret, nr_sectors, barrier, err;
	const unsigned short prio = bio_prio(bio);
	const int sync = bio_sync(bio);
	int rw_flags;

	nr_sectors = bio_sectors(bio);

	/*
	 * low level driver can indicate that it wants pages above a
	 * certain limit bounced to low memory (ie for highmem, or even
	 * ISA dma in theory)
	 */
	blk_queue_bounce(q, &bio);

	barrier = bio_barrier(bio);
	if (unlikely(barrier) && (q->next_ordered == QUEUE_ORDERED_NONE)) {
		err = -EOPNOTSUPP;
		goto end_io;
	}

	spin_lock_irq(q->queue_lock);

	if (unlikely(barrier) || elv_queue_empty(q))
		goto get_rq;

	el_ret = elv_merge(q, &req, bio);
	switch (el_ret) {
		case ELEVATOR_BACK_MERGE:
			BUG_ON(!rq_mergeable(req));

			if (!ll_back_merge_fn(q, req, bio))
				break;

			blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);

			req->biotail->bi_next = bio;
			req->biotail = bio;
			req->nr_sectors = req->hard_nr_sectors += nr_sectors;
			req->ioprio = ioprio_best(req->ioprio, prio);
			drive_stat_acct(req, 0);
			if (!attempt_back_merge(q, req))
				elv_merged_request(q, req, el_ret);
			goto out;

		case ELEVATOR_FRONT_MERGE:
			BUG_ON(!rq_mergeable(req));

			if (!ll_front_merge_fn(q, req, bio))
				break;

			blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);

			bio->bi_next = req->bio;
			req->bio = bio;

			/*
			 * may not be valid. if the low level driver said
			 * it didn't need a bounce buffer then it better
			 * not touch req->buffer either...
			 */
			req->buffer = bio_data(bio);
			req->current_nr_sectors = bio_cur_sectors(bio);
			req->hard_cur_sectors = req->current_nr_sectors;
			req->sector = req->hard_sector = bio->bi_sector;
			req->nr_sectors = req->hard_nr_sectors += nr_sectors;
			req->ioprio = ioprio_best(req->ioprio, prio);
			drive_stat_acct(req, 0);
			if (!attempt_front_merge(q, req))
				elv_merged_request(q, req, el_ret);
			goto out;

		/* ELV_NO_MERGE: elevator says don't/can't merge. */
		default:
			;
	}

get_rq:
	/*
	 * This sync check and mask will be re-done in init_request_from_bio(),
	 * but we need to set it earlier to expose the sync flag to the
	 * rq allocator and io schedulers.
	 */
	rw_flags = bio_data_dir(bio);
	if (sync)
		rw_flags |= REQ_RW_SYNC;

	/*
	 * Grab a free request. This is might sleep but can not fail.
	 * Returns with the queue unlocked.
	 */
	req = get_request_wait(q, rw_flags, bio);

	/*
	 * After dropping the lock and possibly sleeping here, our request
	 * may now be mergeable after it had proven unmergeable (above).
	 * We don't worry about that case for efficiency. It won't happen
	 * often, and the elevators are able to handle it.
	 */
	init_request_from_bio(req, bio);

	spin_lock_irq(q->queue_lock);
	if (elv_queue_empty(q))
		blk_plug_device(q);
	add_request(q, req);
out:
	if (sync)
		__generic_unplug_device(q);

	spin_unlock_irq(q->queue_lock);
	return 0;

end_io:
	bio_endio(bio, err);
	return 0;
}

/*
 * If bio->bi_dev is a partition, remap the location
 */
static inline void blk_partition_remap(struct bio *bio)
{
	struct block_device *bdev = bio->bi_bdev;

	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
		struct hd_struct *p = bdev->bd_part;
		const int rw = bio_data_dir(bio);

		p->sectors[rw] += bio_sectors(bio);
		p->ios[rw]++;

		bio->bi_sector += p->start_sect;
		bio->bi_bdev = bdev->bd_contains;

		blk_add_trace_remap(bdev_get_queue(bio->bi_bdev), bio,
				    bdev->bd_dev, bio->bi_sector,
				    bio->bi_sector - p->start_sect);
	}
}

static void handle_bad_sector(struct bio *bio)
{
	char b[BDEVNAME_SIZE];

	printk(KERN_INFO "attempt to access beyond end of device\n");
	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
			bdevname(bio->bi_bdev, b),
			bio->bi_rw,
			(unsigned long long)bio->bi_sector + bio_sectors(bio),
			(long long)(bio->bi_bdev->bd_inode->i_size >> 9));

	set_bit(BIO_EOF, &bio->bi_flags);
}

#ifdef CONFIG_FAIL_MAKE_REQUEST

static DECLARE_FAULT_ATTR(fail_make_request);

static int __init setup_fail_make_request(char *str)
{
	return setup_fault_attr(&fail_make_request, str);
}
__setup("fail_make_request=", setup_fail_make_request);

static int should_fail_request(struct bio *bio)
{
	if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) ||
	    (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail))
		return should_fail(&fail_make_request, bio->bi_size);

	return 0;
}

static int __init fail_make_request_debugfs(void)
{
	return init_fault_attr_dentries(&fail_make_request,
					"fail_make_request");
}

late_initcall(fail_make_request_debugfs);

#else /* CONFIG_FAIL_MAKE_REQUEST */

static inline int should_fail_request(struct bio *bio)
{
	return 0;
}

#endif /* CONFIG_FAIL_MAKE_REQUEST */

/*
 * Check whether this bio extends beyond the end of the device.
 */
static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
{
	sector_t maxsector;

	if (!nr_sectors)
		return 0;

	/* Test device or partition size, when known. */
	maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
	if (maxsector) {
		sector_t sector = bio->bi_sector;

		if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
			/*
			 * This may well happen - the kernel calls bread()
			 * without checking the size of the device, e.g., when
			 * mounting a device.
			 */
			handle_bad_sector(bio);
			return 1;
		}
	}

	return 0;
}

/**
 * generic_make_request: hand a buffer to its device driver for I/O
 * @bio:  The bio describing the location in memory and on the device.
 *
 * generic_make_request() is used to make I/O requests of block
 * devices. It is passed a &struct bio, which describes the I/O that needs
 * to be done.
 *
 * generic_make_request() does not return any status.  The
 * success/failure status of the request, along with notification of
 * completion, is delivered asynchronously through the bio->bi_end_io
 * function described (one day) else where.
 *
 * The caller of generic_make_request must make sure that bi_io_vec
 * are set to describe the memory buffer, and that bi_dev and bi_sector are
 * set to describe the device address, and the
 * bi_end_io and optionally bi_private are set to describe how
 * completion notification should be signaled.
 *
 * generic_make_request and the drivers it calls may use bi_next if this
 * bio happens to be merged with someone else, and may change bi_dev and
 * bi_sector for remaps as it sees fit.  So the values of these fields
 * should NOT be depended on after the call to generic_make_request.
 */
static inline void __generic_make_request(struct bio *bio)
{
	struct request_queue *q;
	sector_t old_sector;
	int ret, nr_sectors = bio_sectors(bio);
	dev_t old_dev;
	int err = -EIO;

	might_sleep();

	if (bio_check_eod(bio, nr_sectors))
		goto end_io;

	/*
	 * Resolve the mapping until finished. (drivers are
	 * still free to implement/resolve their own stacking
	 * by explicitly returning 0)
	 *
	 * NOTE: we don't repeat the blk_size check for each new device.
	 * Stacking drivers are expected to know what they are doing.
	 */
	old_sector = -1;
	old_dev = 0;
	do {
		char b[BDEVNAME_SIZE];

		q = bdev_get_queue(bio->bi_bdev);
		if (!q) {
			printk(KERN_ERR
			       "generic_make_request: Trying to access "
				"nonexistent block-device %s (%Lu)\n",
				bdevname(bio->bi_bdev, b),
				(long long) bio->bi_sector);
end_io:
			bio_endio(bio, err);
			break;
		}

		if (unlikely(nr_sectors > q->max_hw_sectors)) {
			printk("bio too big device %s (%u > %u)\n", 
				bdevname(bio->bi_bdev, b),
				bio_sectors(bio),
				q->max_hw_sectors);
			goto end_io;
		}

		if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
			goto end_io;

		if (should_fail_request(bio))
			goto end_io;

		/*
		 * If this device has partitions, remap block n
		 * of partition p to block n+start(p) of the disk.
		 */
		blk_partition_remap(bio);

		if (old_sector != -1)
			blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
					    old_sector);

		blk_add_trace_bio(q, bio, BLK_TA_QUEUE);

		old_sector = bio->bi_sector;
		old_dev = bio->bi_bdev->bd_dev;

		if (bio_check_eod(bio, nr_sectors))
			goto end_io;
		if (bio_empty_barrier(bio) && !q->prepare_flush_fn) {
			err = -EOPNOTSUPP;
			goto end_io;
		}

		ret = q->make_request_fn(q, bio);
	} while (ret);
}

/*
 * We only want one ->make_request_fn to be active at a time,
 * else stack usage with stacked devices could be a problem.
 * So use current->bio_{list,tail} to keep a list of requests
 * submited by a make_request_fn function.
 * current->bio_tail is also used as a flag to say if
 * generic_make_request is currently active in this task or not.
 * If it is NULL, then no make_request is active.  If it is non-NULL,
 * then a make_request is active, and new requests should be added
 * at the tail
 */
void generic_make_request(struct bio *bio)
{
	if (current->bio_tail) {
		/* make_request is active */
		*(current->bio_tail) = bio;
		bio->bi_next = NULL;
		current->bio_tail = &bio->bi_next;
		return;
	}
	/* following loop may be a bit non-obvious, and so deserves some
	 * explanation.
	 * Before entering the loop, bio->bi_next is NULL (as all callers
	 * ensure that) so we have a list with a single bio.
	 * We pretend that we have just taken it off a longer list, so
	 * we assign bio_list to the next (which is NULL) and bio_tail
	 * to &bio_list, thus initialising the bio_list of new bios to be
	 * added.  __generic_make_request may indeed add some more bios
	 * through a recursive call to generic_make_request.  If it
	 * did, we find a non-NULL value in bio_list and re-enter the loop
	 * from the top.  In this case we really did just take the bio
	 * of the top of the list (no pretending) and so fixup bio_list and
	 * bio_tail or bi_next, and call into __generic_make_request again.
	 *
	 * The loop was structured like this to make only one call to
	 * __generic_make_request (which is important as it is large and
	 * inlined) and to keep the structure simple.
	 */
	BUG_ON(bio->bi_next);
	do {
		current->bio_list = bio->bi_next;
		if (bio->bi_next == NULL)
			current->bio_tail = &current->bio_list;
		else
			bio->bi_next = NULL;
		__generic_make_request(bio);
		bio = current->bio_list;
	} while (bio);
	current->bio_tail = NULL; /* deactivate */
}

EXPORT_SYMBOL(generic_make_request);

/**
 * submit_bio: submit a bio to the block device layer for I/O
 * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
 * @bio: The &struct bio which describes the I/O
 *
 * submit_bio() is very similar in purpose to generic_make_request(), and
 * uses that function to do most of the work. Both are fairly rough
 * interfaces, @bio must be presetup and ready for I/O.
 *
 */
void submit_bio(int rw, struct bio *bio)
{
	int count = bio_sectors(bio);

	bio->bi_rw |= rw;

	/*
	 * If it's a regular read/write or a barrier with data attached,
	 * go through the normal accounting stuff before submission.
	 */
	if (!bio_empty_barrier(bio)) {

		BIO_BUG_ON(!bio->bi_size);
		BIO_BUG_ON(!bio->bi_io_vec);

		if (rw & WRITE) {
			count_vm_events(PGPGOUT, count);
		} else {
			task_io_account_read(bio->bi_size);
			count_vm_events(PGPGIN, count);
		}

		if (unlikely(block_dump)) {
			char b[BDEVNAME_SIZE];
			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
			current->comm, task_pid_nr(current),
				(rw & WRITE) ? "WRITE" : "READ",
				(unsigned long long)bio->bi_sector,
				bdevname(bio->bi_bdev,b));
		}
	}

	generic_make_request(bio);
}

EXPORT_SYMBOL(submit_bio);

static void blk_recalc_rq_sectors(struct request *rq, int nsect)
{
	if (blk_fs_request(rq)) {
		rq->hard_sector += nsect;
		rq->hard_nr_sectors -= nsect;

		/*
		 * Move the I/O submission pointers ahead if required.
		 */
		if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
		    (rq->sector <= rq->hard_sector)) {
			rq->sector = rq->hard_sector;
			rq->nr_sectors = rq->hard_nr_sectors;
			rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
			rq->current_nr_sectors = rq->hard_cur_sectors;
			rq->buffer = bio_data(rq->bio);
		}

		/*
		 * if total number of sectors is less than the first segment
		 * size, something has gone terribly wrong
		 */
		if (rq->nr_sectors < rq->current_nr_sectors) {
			printk("blk: request botched\n");
			rq->nr_sectors = rq->current_nr_sectors;
		}
	}
}

/**
 * __end_that_request_first - end I/O on a request
 * @req:      the request being processed
 * @error:    0 for success, < 0 for error
 * @nr_bytes: number of bytes to complete
 *
 * Description:
 *     Ends I/O on a number of bytes attached to @req, and sets it up
 *     for the next range of segments (if any) in the cluster.
 *
 * Return:
 *     0 - we are done with this request, call end_that_request_last()
 *     1 - still buffers pending for this request
 **/
static int __end_that_request_first(struct request *req, int error,
				    int nr_bytes)
{
	int total_bytes, bio_nbytes, next_idx = 0;
	struct bio *bio;

	blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);

	/*
	 * for a REQ_BLOCK_PC request, we want to carry any eventual
	 * sense key with us all the way through
	 */
	if (!blk_pc_request(req))
		req->errors = 0;

	if (error) {
		if (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))
			printk("end_request: I/O error, dev %s, sector %llu\n",
				req->rq_disk ? req->rq_disk->disk_name : "?",
				(unsigned long long)req->sector);
	}

	if (blk_fs_request(req) && req->rq_disk) {
		const int rw = rq_data_dir(req);

		disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
	}

	total_bytes = bio_nbytes = 0;
	while ((bio = req->bio) != NULL) {
		int nbytes;

		/*
		 * For an empty barrier request, the low level driver must
		 * store a potential error location in ->sector. We pass
		 * that back up in ->bi_sector.
		 */
		if (blk_empty_barrier(req))
			bio->bi_sector = req->sector;

		if (nr_bytes >= bio->bi_size) {
			req->bio = bio->bi_next;
			nbytes = bio->bi_size;
			req_bio_endio(req, bio, nbytes, error);
			next_idx = 0;
			bio_nbytes = 0;
		} else {
			int idx = bio->bi_idx + next_idx;

			if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
				blk_dump_rq_flags(req, "__end_that");
				printk("%s: bio idx %d >= vcnt %d\n",
						__FUNCTION__,
						bio->bi_idx, bio->bi_vcnt);
				break;
			}

			nbytes = bio_iovec_idx(bio, idx)->bv_len;
			BIO_BUG_ON(nbytes > bio->bi_size);

			/*
			 * not a complete bvec done
			 */
			if (unlikely(nbytes > nr_bytes)) {
				bio_nbytes += nr_bytes;
				total_bytes += nr_bytes;
				break;
			}

			/*
			 * advance to the next vector
			 */
			next_idx++;
			bio_nbytes += nbytes;
		}

		total_bytes += nbytes;
		nr_bytes -= nbytes;

		if ((bio = req->bio)) {
			/*
			 * end more in this run, or just return 'not-done'
			 */
			if (unlikely(nr_bytes <= 0))
				break;
		}
	}

	/*
	 * completely done
	 */
	if (!req->bio)
		return 0;

	/*
	 * if the request wasn't completed, update state
	 */
	if (bio_nbytes) {
		req_bio_endio(req, bio, bio_nbytes, error);
		bio->bi_idx += next_idx;
		bio_iovec(bio)->bv_offset += nr_bytes;
		bio_iovec(bio)->bv_len -= nr_bytes;
	}

	blk_recalc_rq_sectors(req, total_bytes >> 9);
	blk_recalc_rq_segments(req);
	return 1;
}

/*
 * splice the completion data to a local structure and hand off to
 * process_completion_queue() to complete the requests
 */
static void blk_done_softirq(struct softirq_action *h)
{
	struct list_head *cpu_list, local_list;

	local_irq_disable();
	cpu_list = &__get_cpu_var(blk_cpu_done);
	list_replace_init(cpu_list, &local_list);
	local_irq_enable();

	while (!list_empty(&local_list)) {
		struct request *rq = list_entry(local_list.next, struct request, donelist);

		list_del_init(&rq->donelist);
		rq->q->softirq_done_fn(rq);
	}
}

static int __cpuinit blk_cpu_notify(struct notifier_block *self, unsigned long action,
			  void *hcpu)
{
	/*
	 * If a CPU goes away, splice its entries to the current CPU
	 * and trigger a run of the softirq
	 */
	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		int cpu = (unsigned long) hcpu;

		local_irq_disable();