dm-crypt.c

/*
 * Copyright (C) 2003 Jana Saout <jana@saout.de>
 * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
 * Copyright (C) 2006-2015 Red Hat, Inc. All rights reserved.
 * Copyright (C) 2013 Milan Broz <gmazyland@gmail.com>
 *
 * This file is released under the GPL.
 */

#include <linux/completion.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/crypto.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/backing-dev.h>
#include <linux/atomic.h>
#include <linux/scatterlist.h>
#include <linux/rbtree.h>
#include <asm/page.h>
#include <asm/unaligned.h>
#include <crypto/hash.h>
#include <crypto/md5.h>
#include <crypto/algapi.h>

#include <linux/device-mapper.h>

#define DM_MSG_PREFIX "crypt"

/*
 * context holding the current state of a multi-part conversion
 */
struct convert_context {
	struct completion restart;
	struct bio *bio_in;
	struct bio *bio_out;
	struct bvec_iter iter_in;
	struct bvec_iter iter_out;
	sector_t cc_sector;
	atomic_t cc_pending;
	struct ablkcipher_request *req;
};

/*
 * per bio private data
 */
struct dm_crypt_io {
	struct crypt_config *cc;
	struct bio *base_bio;
	struct work_struct work;

	struct convert_context ctx;

	atomic_t io_pending;
	int error;
	sector_t sector;

	struct rb_node rb_node;
} CRYPTO_MINALIGN_ATTR;

struct dm_crypt_request {
	struct convert_context *ctx;
	struct scatterlist sg_in;
	struct scatterlist sg_out;
	sector_t iv_sector;
};

struct crypt_config;

struct crypt_iv_operations {
	int (*ctr)(struct crypt_config *cc, struct dm_target *ti,
		   const char *opts);
	void (*dtr)(struct crypt_config *cc);
	int (*init)(struct crypt_config *cc);
	int (*wipe)(struct crypt_config *cc);
	int (*generator)(struct crypt_config *cc, u8 *iv,
			 struct dm_crypt_request *dmreq);
	int (*post)(struct crypt_config *cc, u8 *iv,
		    struct dm_crypt_request *dmreq);
};

struct iv_essiv_private {
	struct crypto_hash *hash_tfm;
	u8 *salt;
};

struct iv_benbi_private {
	int shift;
};

#define LMK_SEED_SIZE 64 /* hash + 0 */
struct iv_lmk_private {
	struct crypto_shash *hash_tfm;
	u8 *seed;
};

#define TCW_WHITENING_SIZE 16
struct iv_tcw_private {
	struct crypto_shash *crc32_tfm;
	u8 *iv_seed;
	u8 *whitening;
};

/*
 * Crypt: maps a linear range of a block device
 * and encrypts / decrypts at the same time.
 */
enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
	     DM_CRYPT_EXIT_THREAD};

/*
 * The fields in here must be read only after initialization.
 */
struct crypt_config {
	struct dm_dev *dev;
	sector_t start;

	/*
	 * pool for per bio private data, crypto requests and
	 * encryption requeusts/buffer pages
	 */
	mempool_t *req_pool;
	mempool_t *page_pool;
	struct bio_set *bs;
	struct mutex bio_alloc_lock;

	struct workqueue_struct *io_queue;
	struct workqueue_struct *crypt_queue;

	struct task_struct *write_thread;
	wait_queue_head_t write_thread_wait;
	struct rb_root write_tree;

	char *cipher;
	char *cipher_string;

	struct crypt_iv_operations *iv_gen_ops;
	union {
		struct iv_essiv_private essiv;
		struct iv_benbi_private benbi;
		struct iv_lmk_private lmk;
		struct iv_tcw_private tcw;
	} iv_gen_private;
	sector_t iv_offset;
	unsigned int iv_size;

	/* ESSIV: struct crypto_cipher *essiv_tfm */
	void *iv_private;
	struct crypto_ablkcipher **tfms;
	unsigned tfms_count;

	/*
	 * Layout of each crypto request:
	 *
	 *   struct ablkcipher_request
	 *      context
	 *      padding
	 *   struct dm_crypt_request
	 *      padding
	 *   IV
	 *
	 * The padding is added so that dm_crypt_request and the IV are
	 * correctly aligned.
	 */
	unsigned int dmreq_start;

	unsigned int per_bio_data_size;

	unsigned long flags;
	unsigned int key_size;
	unsigned int key_parts;      /* independent parts in key buffer */
	unsigned int key_extra_size; /* additional keys length */
	u8 key[0];
};

#define MIN_IOS        16

static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);

/*
 * Use this to access cipher attributes that are the same for each CPU.
 */
static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc)
{
	return cc->tfms[0];
}

/*
 * Different IV generation algorithms:
 *
 * plain: the initial vector is the 32-bit little-endian version of the sector
 *        number, padded with zeros if necessary.
 *
 * plain64: the initial vector is the 64-bit little-endian version of the sector
 *        number, padded with zeros if necessary.
 *
 * essiv: "encrypted sector|salt initial vector", the sector number is
 *        encrypted with the bulk cipher using a salt as key. The salt
 *        should be derived from the bulk cipher's key via hashing.
 *
 * benbi: the 64-bit "big-endian 'narrow block'-count", starting at 1
 *        (needed for LRW-32-AES and possible other narrow block modes)
 *
 * null: the initial vector is always zero.  Provides compatibility with
 *       obsolete loop_fish2 devices.  Do not use for new devices.
 *
 * lmk:  Compatible implementation of the block chaining mode used
 *       by the Loop-AES block device encryption system
 *       designed by Jari Ruusu. See http://loop-aes.sourceforge.net/
 *       It operates on full 512 byte sectors and uses CBC
 *       with an IV derived from the sector number, the data and
 *       optionally extra IV seed.
 *       This means that after decryption the first block
 *       of sector must be tweaked according to decrypted data.
 *       Loop-AES can use three encryption schemes:
 *         version 1: is plain aes-cbc mode
 *         version 2: uses 64 multikey scheme with lmk IV generator
 *         version 3: the same as version 2 with additional IV seed
 *                   (it uses 65 keys, last key is used as IV seed)
 *
 * tcw:  Compatible implementation of the block chaining mode used
 *       by the TrueCrypt device encryption system (prior to version 4.1).
 *       For more info see: https://gitlab.com/cryptsetup/cryptsetup/wikis/TrueCryptOnDiskFormat
 *       It operates on full 512 byte sectors and uses CBC
 *       with an IV derived from initial key and the sector number.
 *       In addition, whitening value is applied on every sector, whitening
 *       is calculated from initial key, sector number and mixed using CRC32.
 *       Note that this encryption scheme is vulnerable to watermarking attacks
 *       and should be used for old compatible containers access only.
 *
 * plumb: unimplemented, see:
 * http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454
 */

static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv,
			      struct dm_crypt_request *dmreq)
{
	memset(iv, 0, cc->iv_size);
	*(__le32 *)iv = cpu_to_le32(dmreq->iv_sector & 0xffffffff);

	return 0;
}

static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv,
				struct dm_crypt_request *dmreq)
{
	memset(iv, 0, cc->iv_size);
	*(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);

	return 0;
}

/* Initialise ESSIV - compute salt but no local memory allocations */
static int crypt_iv_essiv_init(struct crypt_config *cc)
{
	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
	struct hash_desc desc;
	struct scatterlist sg;
	struct crypto_cipher *essiv_tfm;
	int err;

	sg_init_one(&sg, cc->key, cc->key_size);
	desc.tfm = essiv->hash_tfm;
	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;

	err = crypto_hash_digest(&desc, &sg, cc->key_size, essiv->salt);
	if (err)
		return err;

	essiv_tfm = cc->iv_private;

	err = crypto_cipher_setkey(essiv_tfm, essiv->salt,
			    crypto_hash_digestsize(essiv->hash_tfm));
	if (err)
		return err;

	return 0;
}

/* Wipe salt and reset key derived from volume key */
static int crypt_iv_essiv_wipe(struct crypt_config *cc)
{
	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
	unsigned salt_size = crypto_hash_digestsize(essiv->hash_tfm);
	struct crypto_cipher *essiv_tfm;
	int r, err = 0;

	memset(essiv->salt, 0, salt_size);

	essiv_tfm = cc->iv_private;
	r = crypto_cipher_setkey(essiv_tfm, essiv->salt, salt_size);
	if (r)
		err = r;

	return err;
}

/* Set up per cpu cipher state */
static struct crypto_cipher *setup_essiv_cpu(struct crypt_config *cc,
					     struct dm_target *ti,
					     u8 *salt, unsigned saltsize)
{
	struct crypto_cipher *essiv_tfm;
	int err;

	/* Setup the essiv_tfm with the given salt */
	essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC);
	if (IS_ERR(essiv_tfm)) {
		ti->error = "Error allocating crypto tfm for ESSIV";
		return essiv_tfm;
	}

	if (crypto_cipher_blocksize(essiv_tfm) !=
	    crypto_ablkcipher_ivsize(any_tfm(cc))) {
		ti->error = "Block size of ESSIV cipher does "
			    "not match IV size of block cipher";
		crypto_free_cipher(essiv_tfm);
		return ERR_PTR(-EINVAL);
	}

	err = crypto_cipher_setkey(essiv_tfm, salt, saltsize);
	if (err) {
		ti->error = "Failed to set key for ESSIV cipher";
		crypto_free_cipher(essiv_tfm);
		return ERR_PTR(err);
	}

	return essiv_tfm;
}

static void crypt_iv_essiv_dtr(struct crypt_config *cc)
{
	struct crypto_cipher *essiv_tfm;
	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;

	crypto_free_hash(essiv->hash_tfm);
	essiv->hash_tfm = NULL;

	kzfree(essiv->salt);
	essiv->salt = NULL;

	essiv_tfm = cc->iv_private;

	if (essiv_tfm)
		crypto_free_cipher(essiv_tfm);

	cc->iv_private = NULL;
}

static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
			      const char *opts)
{
	struct crypto_cipher *essiv_tfm = NULL;
	struct crypto_hash *hash_tfm = NULL;
	u8 *salt = NULL;
	int err;

	if (!opts) {
		ti->error = "Digest algorithm missing for ESSIV mode";
		return -EINVAL;
	}

	/* Allocate hash algorithm */
	hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
	if (IS_ERR(hash_tfm)) {
		ti->error = "Error initializing ESSIV hash";
		err = PTR_ERR(hash_tfm);
		goto bad;
	}

	salt = kzalloc(crypto_hash_digestsize(hash_tfm), GFP_KERNEL);
	if (!salt) {
		ti->error = "Error kmallocing salt storage in ESSIV";
		err = -ENOMEM;
		goto bad;
	}

	cc->iv_gen_private.essiv.salt = salt;
	cc->iv_gen_private.essiv.hash_tfm = hash_tfm;

	essiv_tfm = setup_essiv_cpu(cc, ti, salt,
				crypto_hash_digestsize(hash_tfm));
	if (IS_ERR(essiv_tfm)) {
		crypt_iv_essiv_dtr(cc);
		return PTR_ERR(essiv_tfm);
	}
	cc->iv_private = essiv_tfm;

	return 0;

bad:
	if (hash_tfm && !IS_ERR(hash_tfm))
		crypto_free_hash(hash_tfm);
	kfree(salt);
	return err;
}

static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
			      struct dm_crypt_request *dmreq)
{
	struct crypto_cipher *essiv_tfm = cc->iv_private;

	memset(iv, 0, cc->iv_size);
	*(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);
	crypto_cipher_encrypt_one(essiv_tfm, iv, iv);

	return 0;
}

static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
			      const char *opts)
{
	unsigned bs = crypto_ablkcipher_blocksize(any_tfm(cc));
	int log = ilog2(bs);

	/* we need to calculate how far we must shift the sector count
	 * to get the cipher block count, we use this shift in _gen */

	if (1 << log != bs) {
		ti->error = "cypher blocksize is not a power of 2";
		return -EINVAL;
	}

	if (log > 9) {
		ti->error = "cypher blocksize is > 512";
		return -EINVAL;
	}

	cc->iv_gen_private.benbi.shift = 9 - log;

	return 0;
}

static void crypt_iv_benbi_dtr(struct crypt_config *cc)
{
}

static int crypt_iv_benbi_gen(struct crypt_config *cc, u8 *iv,
			      struct dm_crypt_request *dmreq)
{
	__be64 val;

	memset(iv, 0, cc->iv_size - sizeof(u64)); /* rest is cleared below */

	val = cpu_to_be64(((u64)dmreq->iv_sector << cc->iv_gen_private.benbi.shift) + 1);
	put_unaligned(val, (__be64 *)(iv + cc->iv_size - sizeof(u64)));

	return 0;
}

static int crypt_iv_null_gen(struct crypt_config *cc, u8 *iv,
			     struct dm_crypt_request *dmreq)
{
	memset(iv, 0, cc->iv_size);

	return 0;
}

static void crypt_iv_lmk_dtr(struct crypt_config *cc)
{
	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;

	if (lmk->hash_tfm && !IS_ERR(lmk->hash_tfm))
		crypto_free_shash(lmk->hash_tfm);
	lmk->hash_tfm = NULL;

	kzfree(lmk->seed);
	lmk->seed = NULL;
}

static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti,
			    const char *opts)
{
	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;

	lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0);
	if (IS_ERR(lmk->hash_tfm)) {
		ti->error = "Error initializing LMK hash";
		return PTR_ERR(lmk->hash_tfm);
	}

	/* No seed in LMK version 2 */
	if (cc->key_parts == cc->tfms_count) {
		lmk->seed = NULL;
		return 0;
	}

	lmk->seed = kzalloc(LMK_SEED_SIZE, GFP_KERNEL);
	if (!lmk->seed) {
		crypt_iv_lmk_dtr(cc);
		ti->error = "Error kmallocing seed storage in LMK";
		return -ENOMEM;
	}

	return 0;
}

static int crypt_iv_lmk_init(struct crypt_config *cc)
{
	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
	int subkey_size = cc->key_size / cc->key_parts;

	/* LMK seed is on the position of LMK_KEYS + 1 key */
	if (lmk->seed)
		memcpy(lmk->seed, cc->key + (cc->tfms_count * subkey_size),
		       crypto_shash_digestsize(lmk->hash_tfm));

	return 0;
}

static int crypt_iv_lmk_wipe(struct crypt_config *cc)
{
	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;

	if (lmk->seed)
		memset(lmk->seed, 0, LMK_SEED_SIZE);

	return 0;
}

static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
			    struct dm_crypt_request *dmreq,
			    u8 *data)
{
	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
	SHASH_DESC_ON_STACK(desc, lmk->hash_tfm);
	struct md5_state md5state;
	__le32 buf[4];
	int i, r;

	desc->tfm = lmk->hash_tfm;
	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;

	r = crypto_shash_init(desc);
	if (r)
		return r;

	if (lmk->seed) {
		r = crypto_shash_update(desc, lmk->seed, LMK_SEED_SIZE);
		if (r)
			return r;
	}

	/* Sector is always 512B, block size 16, add data of blocks 1-31 */
	r = crypto_shash_update(desc, data + 16, 16 * 31);
	if (r)
		return r;

	/* Sector is cropped to 56 bits here */
	buf[0] = cpu_to_le32(dmreq->iv_sector & 0xFFFFFFFF);
	buf[1] = cpu_to_le32((((u64)dmreq->iv_sector >> 32) & 0x00FFFFFF) | 0x80000000);
	buf[2] = cpu_to_le32(4024);
	buf[3] = 0;
	r = crypto_shash_update(desc, (u8 *)buf, sizeof(buf));
	if (r)
		return r;

	/* No MD5 padding here */
	r = crypto_shash_export(desc, &md5state);
	if (r)
		return r;

	for (i = 0; i < MD5_HASH_WORDS; i++)
		__cpu_to_le32s(&md5state.hash[i]);
	memcpy(iv, &md5state.hash, cc->iv_size);

	return 0;
}

static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv,
			    struct dm_crypt_request *dmreq)
{
	u8 *src;
	int r = 0;

	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
		src = kmap_atomic(sg_page(&dmreq->sg_in));
		r = crypt_iv_lmk_one(cc, iv, dmreq, src + dmreq->sg_in.offset);
		kunmap_atomic(src);
	} else
		memset(iv, 0, cc->iv_size);

	return r;
}

static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv,
			     struct dm_crypt_request *dmreq)
{
	u8 *dst;
	int r;

	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE)
		return 0;

	dst = kmap_atomic(sg_page(&dmreq->sg_out));
	r = crypt_iv_lmk_one(cc, iv, dmreq, dst + dmreq->sg_out.offset);

	/* Tweak the first block of plaintext sector */
	if (!r)
		crypto_xor(dst + dmreq->sg_out.offset, iv, cc->iv_size);

	kunmap_atomic(dst);
	return r;
}

static void crypt_iv_tcw_dtr(struct crypt_config *cc)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;

	kzfree(tcw->iv_seed);
	tcw->iv_seed = NULL;
	kzfree(tcw->whitening);
	tcw->whitening = NULL;

	if (tcw->crc32_tfm && !IS_ERR(tcw->crc32_tfm))
		crypto_free_shash(tcw->crc32_tfm);
	tcw->crc32_tfm = NULL;
}

static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti,
			    const char *opts)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;

	if (cc->key_size <= (cc->iv_size + TCW_WHITENING_SIZE)) {
		ti->error = "Wrong key size for TCW";
		return -EINVAL;
	}

	tcw->crc32_tfm = crypto_alloc_shash("crc32", 0, 0);
	if (IS_ERR(tcw->crc32_tfm)) {
		ti->error = "Error initializing CRC32 in TCW";
		return PTR_ERR(tcw->crc32_tfm);
	}

	tcw->iv_seed = kzalloc(cc->iv_size, GFP_KERNEL);
	tcw->whitening = kzalloc(TCW_WHITENING_SIZE, GFP_KERNEL);
	if (!tcw->iv_seed || !tcw->whitening) {
		crypt_iv_tcw_dtr(cc);
		ti->error = "Error allocating seed storage in TCW";
		return -ENOMEM;
	}

	return 0;
}

static int crypt_iv_tcw_init(struct crypt_config *cc)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
	int key_offset = cc->key_size - cc->iv_size - TCW_WHITENING_SIZE;

	memcpy(tcw->iv_seed, &cc->key[key_offset], cc->iv_size);
	memcpy(tcw->whitening, &cc->key[key_offset + cc->iv_size],
	       TCW_WHITENING_SIZE);

	return 0;
}

static int crypt_iv_tcw_wipe(struct crypt_config *cc)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;

	memset(tcw->iv_seed, 0, cc->iv_size);
	memset(tcw->whitening, 0, TCW_WHITENING_SIZE);

	return 0;
}

static int crypt_iv_tcw_whitening(struct crypt_config *cc,
				  struct dm_crypt_request *dmreq,
				  u8 *data)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
	u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
	u8 buf[TCW_WHITENING_SIZE];
	SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm);
	int i, r;

	/* xor whitening with sector number */
	memcpy(buf, tcw->whitening, TCW_WHITENING_SIZE);
	crypto_xor(buf, (u8 *)&sector, 8);
	crypto_xor(&buf[8], (u8 *)&sector, 8);

	/* calculate crc32 for every 32bit part and xor it */
	desc->tfm = tcw->crc32_tfm;
	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
	for (i = 0; i < 4; i++) {
		r = crypto_shash_init(desc);
		if (r)
			goto out;
		r = crypto_shash_update(desc, &buf[i * 4], 4);
		if (r)
			goto out;
		r = crypto_shash_final(desc, &buf[i * 4]);
		if (r)
			goto out;
	}
	crypto_xor(&buf[0], &buf[12], 4);
	crypto_xor(&buf[4], &buf[8], 4);

	/* apply whitening (8 bytes) to whole sector */
	for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++)
		crypto_xor(data + i * 8, buf, 8);
out:
	memzero_explicit(buf, sizeof(buf));
	return r;
}

static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv,
			    struct dm_crypt_request *dmreq)
{
	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
	u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
	u8 *src;
	int r = 0;

	/* Remove whitening from ciphertext */
	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) {
		src = kmap_atomic(sg_page(&dmreq->sg_in));
		r = crypt_iv_tcw_whitening(cc, dmreq, src + dmreq->sg_in.offset);
		kunmap_atomic(src);
	}

	/* Calculate IV */
	memcpy(iv, tcw->iv_seed, cc->iv_size);
	crypto_xor(iv, (u8 *)&sector, 8);
	if (cc->iv_size > 8)
		crypto_xor(&iv[8], (u8 *)&sector, cc->iv_size - 8);

	return r;
}

static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv,
			     struct dm_crypt_request *dmreq)
{
	u8 *dst;
	int r;

	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE)
		return 0;

	/* Apply whitening on ciphertext */
	dst = kmap_atomic(sg_page(&dmreq->sg_out));
	r = crypt_iv_tcw_whitening(cc, dmreq, dst + dmreq->sg_out.offset);
	kunmap_atomic(dst);

	return r;
}

static struct crypt_iv_operations crypt_iv_plain_ops = {
	.generator = crypt_iv_plain_gen
};

static struct crypt_iv_operations crypt_iv_plain64_ops = {
	.generator = crypt_iv_plain64_gen
};

static struct crypt_iv_operations crypt_iv_essiv_ops = {
	.ctr       = crypt_iv_essiv_ctr,
	.dtr       = crypt_iv_essiv_dtr,
	.init      = crypt_iv_essiv_init,
	.wipe      = crypt_iv_essiv_wipe,
	.generator = crypt_iv_essiv_gen
};

static struct crypt_iv_operations crypt_iv_benbi_ops = {
	.ctr	   = crypt_iv_benbi_ctr,
	.dtr	   = crypt_iv_benbi_dtr,
	.generator = crypt_iv_benbi_gen
};

static struct crypt_iv_operations crypt_iv_null_ops = {
	.generator = crypt_iv_null_gen
};

static struct crypt_iv_operations crypt_iv_lmk_ops = {
	.ctr	   = crypt_iv_lmk_ctr,
	.dtr	   = crypt_iv_lmk_dtr,
	.init	   = crypt_iv_lmk_init,
	.wipe	   = crypt_iv_lmk_wipe,
	.generator = crypt_iv_lmk_gen,
	.post	   = crypt_iv_lmk_post
};

static struct crypt_iv_operations crypt_iv_tcw_ops = {
	.ctr	   = crypt_iv_tcw_ctr,
	.dtr	   = crypt_iv_tcw_dtr,
	.init	   = crypt_iv_tcw_init,
	.wipe	   = crypt_iv_tcw_wipe,
	.generator = crypt_iv_tcw_gen,
	.post	   = crypt_iv_tcw_post
};

static void crypt_convert_init(struct crypt_config *cc,
			       struct convert_context *ctx,
			       struct bio *bio_out, struct bio *bio_in,
			       sector_t sector)
{
	ctx->bio_in = bio_in;
	ctx->bio_out = bio_out;
	if (bio_in)
		ctx->iter_in = bio_in->bi_iter;
	if (bio_out)
		ctx->iter_out = bio_out->bi_iter;
	ctx->cc_sector = sector + cc->iv_offset;
	init_completion(&ctx->restart);
}

static struct dm_crypt_request *dmreq_of_req(struct crypt_config *cc,
					     struct ablkcipher_request *req)
{
	return (struct dm_crypt_request *)((char *)req + cc->dmreq_start);
}

static struct ablkcipher_request *req_of_dmreq(struct crypt_config *cc,
					       struct dm_crypt_request *dmreq)
{
	return (struct ablkcipher_request *)((char *)dmreq - cc->dmreq_start);
}

static u8 *iv_of_dmreq(struct crypt_config *cc,
		       struct dm_crypt_request *dmreq)
{
	return (u8 *)ALIGN((unsigned long)(dmreq + 1),
		crypto_ablkcipher_alignmask(any_tfm(cc)) + 1);
}

static int crypt_convert_block(struct crypt_config *cc,
			       struct convert_context *ctx,
			       struct ablkcipher_request *req)
{
	struct bio_vec bv_in = bio_iter_iovec(ctx->bio_in, ctx->iter_in);
	struct bio_vec bv_out = bio_iter_iovec(ctx->bio_out, ctx->iter_out);
	struct dm_crypt_request *dmreq;
	u8 *iv;
	int r;

	dmreq = dmreq_of_req(cc, req);
	iv = iv_of_dmreq(cc, dmreq);

	dmreq->iv_sector = ctx->cc_sector;
	dmreq->ctx = ctx;
	sg_init_table(&dmreq->sg_in, 1);
	sg_set_page(&dmreq->sg_in, bv_in.bv_page, 1 << SECTOR_SHIFT,
		    bv_in.bv_offset);

	sg_init_table(&dmreq->sg_out, 1);
	sg_set_page(&dmreq->sg_out, bv_out.bv_page, 1 << SECTOR_SHIFT,
		    bv_out.bv_offset);

	bio_advance_iter(ctx->bio_in, &ctx->iter_in, 1 << SECTOR_SHIFT);
	bio_advance_iter(ctx->bio_out, &ctx->iter_out, 1 << SECTOR_SHIFT);

	if (cc->iv_gen_ops) {
		r = cc->iv_gen_ops->generator(cc, iv, dmreq);
		if (r < 0)
			return r;
	}

	ablkcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out,
				     1 << SECTOR_SHIFT, iv);

	if (bio_data_dir(ctx->bio_in) == WRITE)
		r = crypto_ablkcipher_encrypt(req);
	else
		r = crypto_ablkcipher_decrypt(req);

	if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
		r = cc->iv_gen_ops->post(cc, iv, dmreq);

	return r;
}

static void kcryptd_async_done(struct crypto_async_request *async_req,
			       int error);

static void crypt_alloc_req(struct crypt_config *cc,
			    struct convert_context *ctx)
{
	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);

	if (!ctx->req)
		ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);

	ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);

	/*
	 * Use REQ_MAY_BACKLOG so a cipher driver internally backlogs
	 * requests if driver request queue is full.
	 */
	ablkcipher_request_set_callback(ctx->req,
	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
	    kcryptd_async_done, dmreq_of_req(cc, ctx->req));
}

static void crypt_free_req(struct crypt_config *cc,
			   struct ablkcipher_request *req, struct bio *base_bio)
{
	struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);

	if ((struct ablkcipher_request *)(io + 1) != req)
		mempool_free(req, cc->req_pool);
}

/*
 * Encrypt / decrypt data from one bio to another one (can be the same one)
 */
static int crypt_convert(struct crypt_config *cc,
			 struct convert_context *ctx)
{
	int r;

	atomic_set(&ctx->cc_pending, 1);

	while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {

		crypt_alloc_req(cc, ctx);

		atomic_inc(&ctx->cc_pending);

		r = crypt_convert_block(cc, ctx, ctx->req);

		switch (r) {
		/*
		 * The request was queued by a crypto driver
		 * but the driver request queue is full, let's wait.
		 */
		case -EBUSY:
			wait_for_completion(&ctx->restart);
			reinit_completion(&ctx->restart);
			/* fall through */
		/*
		 * The request is queued and processed asynchronously,
		 * completion function kcryptd_async_done() will be called.
		 */
		case -EINPROGRESS:
			ctx->req = NULL;
			ctx->cc_sector++;
			continue;
		/*
		 * The request was already processed (synchronously).
		 */
		case 0:
			atomic_dec(&ctx->cc_pending);
			ctx->cc_sector++;
			cond_resched();
			continue;

		/* There was an error while processing the request. */
		default:
			atomic_dec(&ctx->cc_pending);
			return r;
		}
	}

	return 0;
}

static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);

/*
 * Generate a new unfragmented bio with the given size
 * This should never violate the device limitations (but only because
 * max_segment_size is being constrained to PAGE_SIZE).
 *
 * This function may be called concurrently. If we allocate from the mempool
 * concurrently, there is a possibility of deadlock. For example, if we have
 * mempool of 256 pages, two processes, each wanting 256, pages allocate from
 * the mempool concurrently, it may deadlock in a situation where both processes
 * have allocated 128 pages and the mempool is exhausted.
 *
 * In order to avoid this scenario we allocate the pages under a mutex.
 *
 * In order to not degrade performance with excessive locking, we try
 * non-blocking allocations without a mutex first but on failure we fallback
 * to blocking allocations with a mutex.
 */
static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
{
	struct crypt_config *cc = io->cc;
	struct bio *clone;
	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
	unsigned i, len, remaining_size;
	struct page *page;
	struct bio_vec *bvec;

retry:
	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
		mutex_lock(&cc->bio_alloc_lock);