crypto/pcbc.c


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

/*
 * PCBC: Propagating Cipher Block Chaining mode
 *
 * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * Derived from cbc.c
 * - Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
 *
 * 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.
 *
 */

#include <crypto/algapi.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>

struct crypto_pcbc_ctx {
	struct crypto_cipher *child;
};

static int crypto_pcbc_setkey(struct crypto_tfm *parent, const u8 *key,
			      unsigned int keylen)
{
	struct crypto_pcbc_ctx *ctx = crypto_tfm_ctx(parent);
	struct crypto_cipher *child = ctx->child;
	int err;

	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
				CRYPTO_TFM_REQ_MASK);
	err = crypto_cipher_setkey(child, key, keylen);
	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
			     CRYPTO_TFM_RES_MASK);
	return err;
}

static int crypto_pcbc_encrypt_segment(struct blkcipher_desc *desc,
				       struct blkcipher_walk *walk,
				       struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		crypto_cipher_alg(tfm)->cia_encrypt;
	int bsize = crypto_cipher_blocksize(tfm);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	u8 *iv = walk->iv;

	do {
		crypto_xor(iv, src, bsize);
		fn(crypto_cipher_tfm(tfm), dst, iv);
		memcpy(iv, dst, bsize);
		crypto_xor(iv, src, bsize);

		src += bsize;
		dst += bsize;
	} while ((nbytes -= bsize) >= bsize);

	return nbytes;
}

static int crypto_pcbc_encrypt_inplace(struct blkcipher_desc *desc,
				       struct blkcipher_walk *walk,
				       struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		crypto_cipher_alg(tfm)->cia_encrypt;
	int bsize = crypto_cipher_blocksize(tfm);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *iv = walk->iv;
	u8 tmpbuf[bsize];

	do {
		memcpy(tmpbuf, src, bsize);
		crypto_xor(iv, src, bsize);
		fn(crypto_cipher_tfm(tfm), src, iv);
		memcpy(iv, tmpbuf, bsize);
		crypto_xor(iv, src, bsize);

		src += bsize;
	} while ((nbytes -= bsize) >= bsize);

	memcpy(walk->iv, iv, bsize);

	return nbytes;
}

static int crypto_pcbc_encrypt(struct blkcipher_desc *desc,
			       struct scatterlist *dst, struct scatterlist *src,
			       unsigned int nbytes)
{
	struct blkcipher_walk walk;
	struct crypto_blkcipher *tfm = desc->tfm;
	struct crypto_pcbc_ctx *ctx = crypto_blkcipher_ctx(tfm);
	struct crypto_cipher *child = ctx->child;
	int err;

	blkcipher_walk_init(&walk, dst, src, nbytes);
	err = blkcipher_walk_virt(desc, &walk);

	while ((nbytes = walk.nbytes)) {
		if (walk.src.virt.addr == walk.dst.virt.addr)
			nbytes = crypto_pcbc_encrypt_inplace(desc, &walk,
							     child);
		else
			nbytes = crypto_pcbc_encrypt_segment(desc, &walk,
							     child);
		err = blkcipher_walk_done(desc, &walk, nbytes);
	}

	return err;
}

static int crypto_pcbc_decrypt_segment(struct blkcipher_desc *desc,
				       struct blkcipher_walk *walk,
				       struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		crypto_cipher_alg(tfm)->cia_decrypt;
	int bsize = crypto_cipher_blocksize(tfm);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	u8 *iv = walk->iv;

	do {
		fn(crypto_cipher_tfm(tfm), dst, src);
		crypto_xor(dst, iv, bsize);
		memcpy(iv, src, bsize);
		crypto_xor(iv, dst, bsize);

		src += bsize;
		dst += bsize;
	} while ((nbytes -= bsize) >= bsize);

	memcpy(walk->iv, iv, bsize);

	return nbytes;
}

static int crypto_pcbc_decrypt_inplace(struct blkcipher_desc *desc,
				       struct blkcipher_walk *walk,
				       struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		crypto_cipher_alg(tfm)->cia_decrypt;
	int bsize = crypto_cipher_blocksize(tfm);
	unsigned int nbytes = walk->nbytes;
	u8 *src = walk->src.virt.addr;
	u8 *iv = walk->iv;
	u8 tmpbuf[bsize];

	do {
		memcpy(tmpbuf, src, bsize);
		fn(crypto_cipher_tfm(tfm), src, src);
		crypto_xor(src, iv, bsize);
		memcpy(iv, tmpbuf, bsize);
		crypto_xor(iv, src, bsize);

		src += bsize;
	} while ((nbytes -= bsize) >= bsize);

	memcpy(walk->iv, iv, bsize);

	return nbytes;
}

static int crypto_pcbc_decrypt(struct blkcipher_desc *desc,
			       struct scatterlist *dst, struct scatterlist *src,
			       unsigned int nbytes)
{
	struct blkcipher_walk walk;
	struct crypto_blkcipher *tfm = desc->tfm;
	struct crypto_pcbc_ctx *ctx = crypto_blkcipher_ctx(tfm);
	struct crypto_cipher *child = ctx->child;
	int err;

	blkcipher_walk_init(&walk, dst, src, nbytes);
	err = blkcipher_walk_virt(desc, &walk);

	while ((nbytes = walk.nbytes)) {
		if (walk.src.virt.addr == walk.dst.virt.addr)
			nbytes = crypto_pcbc_decrypt_inplace(desc, &walk,
							     child);
		else
			nbytes = crypto_pcbc_decrypt_segment(desc, &walk,
							     child);
		err = blkcipher_walk_done(desc, &walk, nbytes);
	}

	return err;
}

static int crypto_pcbc_init_tfm(struct crypto_tfm *tfm)
{
	struct crypto_instance *inst = (void *)tfm->__crt_alg;
	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
	struct crypto_pcbc_ctx *ctx = crypto_tfm_ctx(tfm);
	struct crypto_cipher *cipher;

	cipher = crypto_spawn_cipher(spawn);
	if (IS_ERR(cipher))
		return PTR_ERR(cipher);

	ctx->child = cipher;
	return 0;
}

static void crypto_pcbc_exit_tfm(struct crypto_tfm *tfm)
{
	struct crypto_pcbc_ctx *ctx = crypto_tfm_ctx(tfm);
	crypto_free_cipher(ctx->child);
}

static struct crypto_instance *crypto_pcbc_alloc(struct rtattr **tb)
{
	struct crypto_instance *inst;
	struct crypto_alg *alg;
	int err;

	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
	if (err)
		return ERR_PTR(err);

	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER,
				  CRYPTO_ALG_TYPE_MASK);
	if (IS_ERR(alg))
		return ERR_CAST(alg);

	inst = crypto_alloc_instance("pcbc", alg);
	if (IS_ERR(inst))
		goto out_put_alg;

	inst->alg.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER;
	inst->alg.cra_priority = alg->cra_priority;
	inst->alg.cra_blocksize = alg->cra_blocksize;
	inst->alg.cra_alignmask = alg->cra_alignmask;
	inst->alg.cra_type = &crypto_blkcipher_type;

	/* We access the data as u32s when xoring. */
	inst->alg.cra_alignmask |= __alignof__(u32) - 1;

	inst->alg.cra_blkcipher.ivsize = alg->cra_blocksize;
	inst->alg.cra_blkcipher.min_keysize = alg->cra_cipher.cia_min_keysize;
	inst->alg.cra_blkcipher.max_keysize = alg->cra_cipher.cia_max_keysize;

	inst->alg.cra_ctxsize = sizeof(struct crypto_pcbc_ctx);

	inst->alg.cra_init = crypto_pcbc_init_tfm;
	inst->alg.cra_exit = crypto_pcbc_exit_tfm;

	inst->alg.cra_blkcipher.setkey = crypto_pcbc_setkey;
	inst->alg.cra_blkcipher.encrypt = crypto_pcbc_encrypt;
	inst->alg.cra_blkcipher.decrypt = crypto_pcbc_decrypt;

out_put_alg:
	crypto_mod_put(alg);
	return inst;
}

static void crypto_pcbc_free(struct crypto_instance *inst)
{
	crypto_drop_spawn(crypto_instance_ctx(inst));
	kfree(inst);
}

static struct crypto_template crypto_pcbc_tmpl = {
	.name = "pcbc",
	.alloc = crypto_pcbc_alloc,
	.free = crypto_pcbc_free,
	.module = THIS_MODULE,
};

static int __init crypto_pcbc_module_init(void)
{
	return crypto_register_template(&crypto_pcbc_tmpl);
}

static void __exit crypto_pcbc_module_exit(void)
{
	crypto_unregister_template(&crypto_pcbc_tmpl);
}

module_init(crypto_pcbc_module_init);
module_exit(crypto_pcbc_module_exit);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("PCBC block cipher algorithm");
/*
 *  Block device elevator/IO-scheduler.
 *
 *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
 *
 * 30042000 Jens Axboe <axboe@kernel.dk> :
 *
 * Split the elevator a bit so that it is possible to choose a different
 * one or even write a new "plug in". There are three pieces:
 * - elevator_fn, inserts a new request in the queue list
 * - elevator_merge_fn, decides whether a new buffer can be merged with
 *   an existing request
 * - elevator_dequeue_fn, called when a request is taken off the active list
 *
 * 20082000 Dave Jones <davej@suse.de> :
 * Removed tests for max-bomb-segments, which was breaking elvtune
 *  when run without -bN
 *
 * Jens:
 * - Rework again to work with bio instead of buffer_heads
 * - loose bi_dev comparisons, partition handling is right now
 * - completely modularize elevator setup and teardown
 *
 */
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>

#include <trace/events/block.h>

#include "blk.h"

static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);

/*
 * Merge hash stuff.
 */
#define rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))

/*
 * Query io scheduler to see if the current process issuing bio may be
 * merged with rq.
 */
static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
{
	struct request_queue *q = rq->q;
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_allow_bio_merge_fn)
		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);

	return 1;
}

/*
 * can we safely merge with this request?
 */
bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
{
	if (!blk_rq_merge_ok(rq, bio))
		return false;

	if (!elv_iosched_allow_bio_merge(rq, bio))
		return false;

	return true;
}
EXPORT_SYMBOL(elv_bio_merge_ok);

static struct elevator_type *elevator_find(const char *name)
{
	struct elevator_type *e;

	list_for_each_entry(e, &elv_list, list) {
		if (!strcmp(e->elevator_name, name))
			return e;
	}

	return NULL;
}

static void elevator_put(struct elevator_type *e)
{
	module_put(e->elevator_owner);
}

static struct elevator_type *elevator_get(const char *name, bool try_loading)
{
	struct elevator_type *e;

	spin_lock(&elv_list_lock);

	e = elevator_find(name);
	if (!e && try_loading) {
		spin_unlock(&elv_list_lock);
		request_module("%s-iosched", name);
		spin_lock(&elv_list_lock);
		e = elevator_find(name);
	}

	if (e && !try_module_get(e->elevator_owner))
		e = NULL;

	spin_unlock(&elv_list_lock);

	return e;
}

static char chosen_elevator[ELV_NAME_MAX];

static int __init elevator_setup(char *str)
{
	/*
	 * Be backwards-compatible with previous kernels, so users
	 * won't get the wrong elevator.
	 */
	strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
	return 1;
}

__setup("elevator=", elevator_setup);

/* called during boot to load the elevator chosen by the elevator param */
void __init load_default_elevator_module(void)
{
	struct elevator_type *e;

	if (!chosen_elevator[0])
		return;

	spin_lock(&elv_list_lock);
	e = elevator_find(chosen_elevator);
	spin_unlock(&elv_list_lock);

	if (!e)
		request_module("%s-iosched", chosen_elevator);
}

static struct kobj_type elv_ktype;

struct elevator_queue *elevator_alloc(struct request_queue *q,
				  struct elevator_type *e)
{
	struct elevator_queue *eq;

	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
	if (unlikely(!eq))
		return NULL;

	eq->type = e;
	kobject_init(&eq->kobj, &elv_ktype);
	mutex_init(&eq->sysfs_lock);
	hash_init(eq->hash);

	return eq;
}
EXPORT_SYMBOL(elevator_alloc);

static void elevator_release(struct kobject *kobj)
{
	struct elevator_queue *e;

	e = container_of(kobj, struct elevator_queue, kobj);
	elevator_put(e->type);
	kfree(e);
}

int elevator_init(struct request_queue *q, char *name)
{
	struct elevator_type *e = NULL;
	int err;

	/*
	 * q->sysfs_lock must be held to provide mutual exclusion between
	 * elevator_switch() and here.
	 */
	lockdep_assert_held(&q->sysfs_lock);

	if (unlikely(q->elevator))
		return 0;

	INIT_LIST_HEAD(&q->queue_head);
	q->last_merge = NULL;
	q->end_sector = 0;
	q->boundary_rq = NULL;

	if (name) {
		e = elevator_get(name, true);
		if (!e)
			return -EINVAL;
	}

	/*
	 * Use the default elevator specified by config boot param or
	 * config option.  Don't try to load modules as we could be running
	 * off async and request_module() isn't allowed from async.
	 */
	if (!e && *chosen_elevator) {
		e = elevator_get(chosen_elevator, false);
		if (!e)
			printk(KERN_ERR "I/O scheduler %s not found\n",
							chosen_elevator);
	}

	if (!e) {
		e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
		if (!e) {
			printk(KERN_ERR
				"Default I/O scheduler not found. " \
				"Using noop.\n");
			e = elevator_get("noop", false);
		}
	}

	err = e->ops.elevator_init_fn(q, e);
	if (err)
		elevator_put(e);
	return err;
}
EXPORT_SYMBOL(elevator_init);

void elevator_exit(struct elevator_queue *e)
{
	mutex_lock(&e->sysfs_lock);
	if (e->type->ops.elevator_exit_fn)
		e->type->ops.elevator_exit_fn(e);
	mutex_unlock(&e->sysfs_lock);

	kobject_put(&e->kobj);
}
EXPORT_SYMBOL(elevator_exit);

static inline void __elv_rqhash_del(struct request *rq)
{
	hash_del(&rq->hash);
	rq->cmd_flags &= ~REQ_HASHED;
}

static void elv_rqhash_del(struct request_queue *q, struct request *rq)
{
	if (ELV_ON_HASH(rq))
		__elv_rqhash_del(rq);
}

static void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	BUG_ON(ELV_ON_HASH(rq));
	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
	rq->cmd_flags |= REQ_HASHED;
}

static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
	__elv_rqhash_del(rq);
	elv_rqhash_add(q, rq);
}

static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
	struct elevator_queue *e = q->elevator;
	struct hlist_node *next;
	struct request *rq;

	hash_for_each_possible_safe(e->hash, rq, next, hash, offset) {
		BUG_ON(!ELV_ON_HASH(rq));

		if (unlikely(!rq_mergeable(rq))) {
			__elv_rqhash_del(rq);
			continue;
		}

		if (rq_hash_key(rq) == offset)
			return rq;
	}

	return NULL;
}

/*
 * RB-tree support functions for inserting/lookup/removal of requests
 * in a sorted RB tree.
 */
void elv_rb_add(struct rb_root *root, struct request *rq)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct request *__rq;

	while (*p) {
		parent = *p;
		__rq = rb_entry(parent, struct request, rb_node);

		if (blk_rq_pos(rq) < blk_rq_pos(__rq))
			p = &(*p)->rb_left;
		else if (blk_rq_pos(rq) >= blk_rq_pos(__rq))
			p = &(*p)->rb_right;
	}

	rb_link_node(&rq->rb_node, parent, p);
	rb_insert_color(&rq->rb_node, root);
}
EXPORT_SYMBOL(elv_rb_add);

void elv_rb_del(struct rb_root *root, struct request *rq)
{
	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
	rb_erase(&rq->rb_node, root);
	RB_CLEAR_NODE(&rq->rb_node);
}
EXPORT_SYMBOL(elv_rb_del);

struct request *elv_rb_find(struct rb_root *root, sector_t sector)
{
	struct rb_node *n = root->rb_node;
	struct request *rq;

	while (n) {
		rq = rb_entry(n, struct request, rb_node);

		if (sector < blk_rq_pos(rq))
			n = n->rb_left;
		else if (sector > blk_rq_pos(rq))
			n = n->rb_right;
		else
			return rq;
	}

	return NULL;
}
EXPORT_SYMBOL(elv_rb_find);

/*
 * Insert rq into dispatch queue of q.  Queue lock must be held on
 * entry.  rq is sort instead into the dispatch queue. To be used by
 * specific elevators.
 */
void elv_dispatch_sort(struct request_queue *q, struct request *rq)
{
	sector_t boundary;
	struct list_head *entry;
	int stop_flags;

	if (q->last_merge == rq)
		q->last_merge = NULL;

	elv_rqhash_del(q, rq);

	q->nr_sorted--;

	boundary = q->end_sector;
	stop_flags = REQ_SOFTBARRIER | REQ_STARTED;
	list_for_each_prev(entry, &q->queue_head) {
		struct request *pos = list_entry_rq(entry);

		if (req_op(rq) != req_op(pos))
			break;
		if (rq_data_dir(rq) != rq_data_dir(pos))
			break;
		if (pos->cmd_flags & stop_flags)
			break;
		if (blk_rq_pos(rq) >= boundary) {
			if (blk_rq_pos(pos) < boundary)
				continue;
		} else {
			if (blk_rq_pos(pos) >= boundary)
				break;
		}
		if (blk_rq_pos(rq) >= blk_rq_pos(pos))
			break;
	}

	list_add(&rq->queuelist, entry);
}
EXPORT_SYMBOL(elv_dispatch_sort);

/*
 * Insert rq into dispatch queue of q.  Queue lock must be held on
 * entry.  rq is added to the back of the dispatch queue. To be used by
 * specific elevators.
 */
void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
{
	if (q->last_merge == rq)
		q->last_merge = NULL;

	elv_rqhash_del(q, rq);

	q->nr_sorted--;

	q->end_sector = rq_end_sector(rq);
	q->boundary_rq = rq;
	list_add_tail(&rq->queuelist, &q->queue_head);
}
EXPORT_SYMBOL(elv_dispatch_add_tail);

int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
	struct elevator_queue *e = q->elevator;
	struct request *__rq;
	int ret;

	/*
	 * Levels of merges:
	 * 	nomerges:  No merges at all attempted
	 * 	noxmerges: Only simple one-hit cache try
	 * 	merges:	   All merge tries attempted
	 */
	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
		return ELEVATOR_NO_MERGE;

	/*
	 * First try one-hit cache.
	 */
	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
		ret = blk_try_merge(q->last_merge, bio);
		if (ret != ELEVATOR_NO_MERGE) {
			*req = q->last_merge;
			return ret;
		}
	}

	if (blk_queue_noxmerges(q))
		return ELEVATOR_NO_MERGE;

	/*
	 * See if our hash lookup can find a potential backmerge.
	 */
	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
	if (__rq && elv_bio_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_BACK_MERGE;
	}

	if (e->type->ops.elevator_merge_fn)
		return e->type->ops.elevator_merge_fn(q, req, bio);

	return ELEVATOR_NO_MERGE;
}

/*
 * Attempt to do an insertion back merge. Only check for the case where
 * we can append 'rq' to an existing request, so we can throw 'rq' away
 * afterwards.
 *
 * Returns true if we merged, false otherwise
 */
static bool elv_attempt_insert_merge(struct request_queue *q,
				     struct request *rq)
{
	struct request *__rq;
	bool ret;

	if (blk_queue_nomerges(q))
		return false;

	/*
	 * First try one-hit cache.
	 */
	if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq))
		return true;

	if (blk_queue_noxmerges(q))
		return false;

	ret = false;
	/*
	 * See if our hash lookup can find a potential backmerge.
	 */
	while (1) {
		__rq = elv_rqhash_find(q, blk_rq_pos(rq));
		if (!__rq || !blk_attempt_req_merge(q, __rq, rq))
			break;

		/* The merged request could be merged with others, try again */
		ret = true;
		rq = __rq;
	}

	return ret;
}

void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_merged_fn)
		e->type->ops.elevator_merged_fn(q, rq, type);

	if (type == ELEVATOR_BACK_MERGE)
		elv_rqhash_reposition(q, rq);

	q->last_merge = rq;
}

void elv_merge_requests(struct request_queue *q, struct request *rq,
			     struct request *next)
{
	struct elevator_queue *e = q->elevator;
	const int next_sorted = next->cmd_flags & REQ_SORTED;

	if (next_sorted && e->type->ops.elevator_merge_req_fn)
		e->type->ops.elevator_merge_req_fn(q, rq, next);

	elv_rqhash_reposition(q, rq);

	if (next_sorted) {
		elv_rqhash_del(q, next);
		q->nr_sorted--;
	}

	q->last_merge = rq;
}

void elv_bio_merged(struct request_queue *q, struct request *rq,
			struct bio *bio)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_bio_merged_fn)
		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
}

#ifdef CONFIG_PM
static void blk_pm_requeue_request(struct request *rq)
{
	if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
		rq->q->nr_pending--;
}

static void blk_pm_add_request(struct request_queue *q, struct request *rq)
{
	if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 &&
	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
		pm_request_resume(q->dev);
}
#else
static inline void blk_pm_requeue_request(struct request *rq) {}
static inline void blk_pm_add_request(struct request_queue *q,
				      struct request *rq)
{
}
#endif

void elv_requeue_request(struct request_queue *q, struct request *rq)
{
	/*
	 * it already went through dequeue, we need to decrement the
	 * in_flight count again
	 */
	if (blk_account_rq(rq)) {
		q->in_flight[rq_is_sync(rq)]--;
		if (rq->cmd_flags & REQ_SORTED)
			elv_deactivate_rq(q, rq);
	}

	rq->cmd_flags &= ~REQ_STARTED;

	blk_pm_requeue_request(rq);

	__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
}

void elv_drain_elevator(struct request_queue *q)
{
	static int printed;

	lockdep_assert_held(q->queue_lock);

	while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
		;
	if (q->nr_sorted && printed++ < 10) {
		printk(KERN_ERR "%s: forced dispatching is broken "
		       "(nr_sorted=%u), please report this\n",
		       q->elevator->type->elevator_name, q->nr_sorted);
	}
}

void __elv_add_request(struct request_queue *q, struct request *rq, int where)
{
	trace_block_rq_insert(q, rq);

	blk_pm_add_request(q, rq);

	rq->q = q;

	if (rq->cmd_flags & REQ_SOFTBARRIER) {
		/* barriers are scheduling boundary, update end_sector */
		if (rq->cmd_type == REQ_TYPE_FS) {
			q->end_sector = rq_end_sector(rq);
			q->boundary_rq = rq;
		}
	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
		    (where == ELEVATOR_INSERT_SORT ||
		     where == ELEVATOR_INSERT_SORT_MERGE))
		where = ELEVATOR_INSERT_BACK;

	switch (where) {
	case ELEVATOR_INSERT_REQUEUE:
	case ELEVATOR_INSERT_FRONT:
		rq->cmd_flags |= REQ_SOFTBARRIER;
		list_add(&rq->queuelist, &q->queue_head);
		break;

	case ELEVATOR_INSERT_BACK:
		rq->cmd_flags |= REQ_SOFTBARRIER;
		elv_drain_elevator(q);
		list_add_tail(&rq->queuelist, &q->queue_head);
		/*
		 * We kick the queue here for the following reasons.
		 * - The elevator might have returned NULL previously
		 *   to delay requests and returned them now.  As the
		 *   queue wasn't empty before this request, ll_rw_blk
		 *   won't run the queue on return, resulting in hang.
		 * - Usually, back inserted requests won't be merged
		 *   with anything.  There's no point in delaying queue
		 *   processing.
		 */
		__blk_run_queue(q);
		break;

	case ELEVATOR_INSERT_SORT_MERGE:
		/*
		 * If we succeed in merging this request with one in the
		 * queue already, we are done - rq has now been freed,
		 * so no need to do anything further.
		 */
		if (elv_attempt_insert_merge(q, rq))
			break;
	case ELEVATOR_INSERT_SORT:
		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
		rq->cmd_flags |= REQ_SORTED;
		q->nr_sorted++;
		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}

		/*
		 * Some ioscheds (cfq) run q->request_fn directly, so
		 * rq cannot be accessed after calling
		 * elevator_add_req_fn.
		 */
		q->elevator->type->ops.elevator_add_req_fn(q, rq);
		break;

	case ELEVATOR_INSERT_FLUSH:
		rq->cmd_flags |= REQ_SOFTBARRIER;
		blk_insert_flush(rq);
		break;
	default:
		printk(KERN_ERR "%s: bad insertion point %d\n",
		       __func__, where);
		BUG();
	}
}
EXPORT_SYMBOL(__elv_add_request);

void elv_add_request(struct request_queue *q, struct request *rq, int where)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	__elv_add_request(q, rq, where);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(elv_add_request);

struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_latter_req_fn)
		return e->type->ops.elevator_latter_req_fn(q, rq);
	return NULL;
}

struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_former_req_fn)
		return e->type->ops.elevator_former_req_fn(q, rq);
	return NULL;
}

int elv_set_request(struct request_queue *q, struct request *rq,
		    struct bio *bio, gfp_t gfp_mask)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_set_req_fn)
		return e->type->ops.elevator_set_req_fn(q, rq, bio, gfp_mask);
	return 0;
}

void elv_put_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_put_req_fn)
		e->type->ops.elevator_put_req_fn(rq);
}

int elv_may_queue(struct request_queue *q, int op, int op_flags)
{
	struct elevator_queue *e = q->elevator;

	if (e->type->ops.elevator_may_queue_fn)
		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);

	return ELV_MQUEUE_MAY;
}

void elv_completed_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	/*
	 * request is released from the driver, io must be done
	 */
	if (blk_account_rq(rq)) {
		q->in_flight[rq_is_sync(rq)]--;
		if ((rq->cmd_flags & REQ_SORTED) &&
		    e->type->ops.elevator_completed_req_fn)
			e->type->ops.elevator_completed_req_fn(q, rq);
	}
}

#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)

static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct elv_fs_entry *entry = to_elv(attr);
	struct elevator_queue *e;
	ssize_t error;

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

	e = container_of(kobj, struct elevator_queue, kobj);
	mutex_lock(&e->sysfs_lock);
	error = e->type ? entry->show(e, page) : -ENOENT;
	mutex_unlock(&e->sysfs_lock);
	return error;
}

static ssize_t
elv_attr_store(struct kobject *kobj, struct attribute *attr,
	       const char *page, size_t length)
{
	struct elv_fs_entry *entry = to_elv(attr);
	struct elevator_queue *e;
	ssize_t error;

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

	e = container_of(kobj, struct elevator_queue, kobj);
	mutex_lock(&e->sysfs_lock);
	error = e->type ? entry->store(e, page, length) : -ENOENT;
	mutex_unlock(&e->sysfs_lock);
	return error;
}

static const struct sysfs_ops elv_sysfs_ops = {
	.show	= elv_attr_show,
	.store	= elv_attr_store,
};

static struct kobj_type elv_ktype = {
	.sysfs_ops	= &elv_sysfs_ops,
	.release	= elevator_release,
};

int elv_register_queue(struct request_queue *q)
{
	struct elevator_queue *e = q->elevator;
	int error;

	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
	if (!error) {
		struct elv_fs_entry *attr = e->type->elevator_attrs;
		if (attr) {
			while (attr->attr.name) {
				if (sysfs_create_file(&e->kobj, &attr->attr))
					break;
				attr++;
			}
		}
		kobject_uevent(&e->kobj, KOBJ_ADD);
		e->registered = 1;