dm-crypt.c

来自「linux 内核源代码」· C语言 代码 · 共 1,109 行 · 第 1/2 页

/*
 * Copyright (C) 2003 Christophe Saout <[e-mail]>
 * Copyright (C) 2004 Clemens Fruhwirth <[e-mail]>
 * Copyright (C) 2006 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#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/backing-dev.h>
#include <asm/atomic.h>
#include <linux/scatterlist.h>
#include <asm/page.h>
#include <asm/unaligned.h>

#include "dm.h"

#define DM_MSG_PREFIX "crypt"
#define MESG_STR(x) x, sizeof(x)

/*
 * per bio private data
 */
struct dm_crypt_io {
	struct dm_target *target;
	struct bio *base_bio;
	struct work_struct work;
	atomic_t pending;
	int error;
};

/*
 * context holding the current state of a multi-part conversion
 */
struct convert_context {
	struct bio *bio_in;
	struct bio *bio_out;
	unsigned int offset_in;
	unsigned int offset_out;
	unsigned int idx_in;
	unsigned int idx_out;
	sector_t sector;
	int write;
};

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);
	const char *(*status)(struct crypt_config *cc);
	int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector);
};

/*
 * 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 };
struct crypt_config {
	struct dm_dev *dev;
	sector_t start;

	/*
	 * pool for per bio private data and
	 * for encryption buffer pages
	 */
	mempool_t *io_pool;
	mempool_t *page_pool;
	struct bio_set *bs;

	struct workqueue_struct *io_queue;
	struct workqueue_struct *crypt_queue;
	/*
	 * crypto related data
	 */
	struct crypt_iv_operations *iv_gen_ops;
	char *iv_mode;
	union {
		struct crypto_cipher *essiv_tfm;
		int benbi_shift;
	} iv_gen_private;
	sector_t iv_offset;
	unsigned int iv_size;

	char cipher[CRYPTO_MAX_ALG_NAME];
	char chainmode[CRYPTO_MAX_ALG_NAME];
	struct crypto_blkcipher *tfm;
	unsigned long flags;
	unsigned int key_size;
	u8 key[0];
};

#define MIN_IOS        16
#define MIN_POOL_PAGES 32
#define MIN_BIO_PAGES  8

static struct kmem_cache *_crypt_io_pool;

static void clone_init(struct dm_crypt_io *, struct bio *);

/*
 * Different IV generation algorithms:
 *
 * plain: the initial vector is the 32-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.
 *
 * 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, sector_t sector)
{
	memset(iv, 0, cc->iv_size);
	*(u32 *)iv = cpu_to_le32(sector & 0xffffffff);

	return 0;
}

static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
			      const char *opts)
{
	struct crypto_cipher *essiv_tfm;
	struct crypto_hash *hash_tfm;
	struct hash_desc desc;
	struct scatterlist sg;
	unsigned int saltsize;
	u8 *salt;
	int err;

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

	/* Hash the cipher key with the given hash algorithm */
	hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
	if (IS_ERR(hash_tfm)) {
		ti->error = "Error initializing ESSIV hash";
		return PTR_ERR(hash_tfm);
	}

	saltsize = crypto_hash_digestsize(hash_tfm);
	salt = kmalloc(saltsize, GFP_KERNEL);
	if (salt == NULL) {
		ti->error = "Error kmallocing salt storage in ESSIV";
		crypto_free_hash(hash_tfm);
		return -ENOMEM;
	}

	sg_init_one(&sg, cc->key, cc->key_size);
	desc.tfm = hash_tfm;
	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
	err = crypto_hash_digest(&desc, &sg, cc->key_size, salt);
	crypto_free_hash(hash_tfm);

	if (err) {
		ti->error = "Error calculating hash in ESSIV";
		kfree(salt);
		return 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";
		kfree(salt);
		return PTR_ERR(essiv_tfm);
	}
	if (crypto_cipher_blocksize(essiv_tfm) !=
	    crypto_blkcipher_ivsize(cc->tfm)) {
		ti->error = "Block size of ESSIV cipher does "
			    "not match IV size of block cipher";
		crypto_free_cipher(essiv_tfm);
		kfree(salt);
		return -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);
		kfree(salt);
		return err;
	}
	kfree(salt);

	cc->iv_gen_private.essiv_tfm = essiv_tfm;
	return 0;
}

static void crypt_iv_essiv_dtr(struct crypt_config *cc)
{
	crypto_free_cipher(cc->iv_gen_private.essiv_tfm);
	cc->iv_gen_private.essiv_tfm = NULL;
}

static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector)
{
	memset(iv, 0, cc->iv_size);
	*(u64 *)iv = cpu_to_le64(sector);
	crypto_cipher_encrypt_one(cc->iv_gen_private.essiv_tfm, iv, iv);
	return 0;
}

static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
			      const char *opts)
{
	unsigned int bs = crypto_blkcipher_blocksize(cc->tfm);
	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, sector_t sector)
{
	__be64 val;

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

	val = cpu_to_be64(((u64)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, sector_t sector)
{
	memset(iv, 0, cc->iv_size);

	return 0;
}

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

static struct crypt_iv_operations crypt_iv_essiv_ops = {
	.ctr       = crypt_iv_essiv_ctr,
	.dtr       = crypt_iv_essiv_dtr,
	.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 int
crypt_convert_scatterlist(struct crypt_config *cc, struct scatterlist *out,
                          struct scatterlist *in, unsigned int length,
                          int write, sector_t sector)
{
	u8 iv[cc->iv_size] __attribute__ ((aligned(__alignof__(u64))));
	struct blkcipher_desc desc = {
		.tfm = cc->tfm,
		.info = iv,
		.flags = CRYPTO_TFM_REQ_MAY_SLEEP,
	};
	int r;

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

		if (write)
			r = crypto_blkcipher_encrypt_iv(&desc, out, in, length);
		else
			r = crypto_blkcipher_decrypt_iv(&desc, out, in, length);
	} else {
		if (write)
			r = crypto_blkcipher_encrypt(&desc, out, in, length);
		else
			r = crypto_blkcipher_decrypt(&desc, out, in, length);
	}

	return r;
}

static void crypt_convert_init(struct crypt_config *cc,
			       struct convert_context *ctx,
			       struct bio *bio_out, struct bio *bio_in,
			       sector_t sector, int write)
{
	ctx->bio_in = bio_in;
	ctx->bio_out = bio_out;
	ctx->offset_in = 0;
	ctx->offset_out = 0;
	ctx->idx_in = bio_in ? bio_in->bi_idx : 0;
	ctx->idx_out = bio_out ? bio_out->bi_idx : 0;
	ctx->sector = sector + cc->iv_offset;
	ctx->write = write;
}

/*
 * 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 = 0;

	while(ctx->idx_in < ctx->bio_in->bi_vcnt &&
	      ctx->idx_out < ctx->bio_out->bi_vcnt) {
		struct bio_vec *bv_in = bio_iovec_idx(ctx->bio_in, ctx->idx_in);
		struct bio_vec *bv_out = bio_iovec_idx(ctx->bio_out, ctx->idx_out);
		struct scatterlist sg_in, sg_out;

		sg_init_table(&sg_in, 1);
		sg_set_page(&sg_in, bv_in->bv_page, 1 << SECTOR_SHIFT, bv_in->bv_offset + ctx->offset_in);

		sg_init_table(&sg_out, 1);
		sg_set_page(&sg_out, bv_out->bv_page, 1 << SECTOR_SHIFT, bv_out->bv_offset + ctx->offset_out);

		ctx->offset_in += sg_in.length;
		if (ctx->offset_in >= bv_in->bv_len) {
			ctx->offset_in = 0;
			ctx->idx_in++;
		}

		ctx->offset_out += sg_out.length;
		if (ctx->offset_out >= bv_out->bv_len) {
			ctx->offset_out = 0;
			ctx->idx_out++;
		}

		r = crypt_convert_scatterlist(cc, &sg_out, &sg_in, sg_in.length,
					      ctx->write, ctx->sector);
		if (r < 0)
			break;

		ctx->sector++;
	}

	return r;
}

static void dm_crypt_bio_destructor(struct bio *bio)
{
	struct dm_crypt_io *io = bio->bi_private;
	struct crypt_config *cc = io->target->private;

	bio_free(bio, cc->bs);
}

/*
 * Generate a new unfragmented bio with the given size
 * This should never violate the device limitations
 * May return a smaller bio when running out of pages
 */
static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
{
	struct crypt_config *cc = io->target->private;
	struct bio *clone;
	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	gfp_t gfp_mask = GFP_NOIO | __GFP_HIGHMEM;
	unsigned i, len;
	struct page *page;

	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
	if (!clone)
		return NULL;

	clone_init(io, clone);

	for (i = 0; i < nr_iovecs; i++) {
		page = mempool_alloc(cc->page_pool, gfp_mask);
		if (!page)
			break;

		/*
		 * if additional pages cannot be allocated without waiting,
		 * return a partially allocated bio, the caller will then try
		 * to allocate additional bios while submitting this partial bio
		 */
		if (i == (MIN_BIO_PAGES - 1))
			gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;

		len = (size > PAGE_SIZE) ? PAGE_SIZE : size;

		if (!bio_add_page(clone, page, len, 0)) {
			mempool_free(page, cc->page_pool);
			break;
		}

		size -= len;
	}

	if (!clone->bi_size) {
		bio_put(clone);
		return NULL;
	}

	return clone;
}

static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
{
	unsigned int i;
	struct bio_vec *bv;

	for (i = 0; i < clone->bi_vcnt; i++) {
		bv = bio_iovec_idx(clone, i);
		BUG_ON(!bv->bv_page);
		mempool_free(bv->bv_page, cc->page_pool);
		bv->bv_page = NULL;
	}
}

/*
 * One of the bios was finished. Check for completion of
 * the whole request and correctly clean up the buffer.
 */
static void crypt_dec_pending(struct dm_crypt_io *io, int error)
{
	struct crypt_config *cc = (struct crypt_config *) io->target->private;

	if (error < 0)
		io->error = error;

	if (!atomic_dec_and_test(&io->pending))
		return;

	bio_endio(io->base_bio, io->error);

	mempool_free(io, cc->io_pool);
}

/*
 * kcryptd/kcryptd_io:
 *
 * Needed because it would be very unwise to do decryption in an
 * interrupt context.
 *
 * kcryptd performs the actual encryption or decryption.
 *
 * kcryptd_io performs the IO submission.
 *
 * They must be separated as otherwise the final stages could be
 * starved by new requests which can block in the first stages due
 * to memory allocation.
 */
static void kcryptd_do_work(struct work_struct *work);
static void kcryptd_do_crypt(struct work_struct *work);

static void kcryptd_queue_io(struct dm_crypt_io *io)
{
	struct crypt_config *cc = io->target->private;

	INIT_WORK(&io->work, kcryptd_do_work);
	queue_work(cc->io_queue, &io->work);
}

static void kcryptd_queue_crypt(struct dm_crypt_io *io)
{
	struct crypt_config *cc = io->target->private;

	INIT_WORK(&io->work, kcryptd_do_crypt);
	queue_work(cc->crypt_queue, &io->work);
}

static void crypt_endio(struct bio *clone, int error)
{
	struct dm_crypt_io *io = clone->bi_private;
	struct crypt_config *cc = io->target->private;
	unsigned read_io = bio_data_dir(clone) == READ;

	if (unlikely(!bio_flagged(clone, BIO_UPTODATE) && !error))
		error = -EIO;

	/*
	 * free the processed pages
	 */
	if (!read_io) {
		crypt_free_buffer_pages(cc, clone);
		goto out;
	}

	if (unlikely(error))
		goto out;

	bio_put(clone);
	kcryptd_queue_crypt(io);
	return;

out:
	bio_put(clone);
	crypt_dec_pending(io, error);
}

static void clone_init(struct dm_crypt_io *io, struct bio *clone)
{
	struct crypt_config *cc = io->target->private;

	clone->bi_private = io;
	clone->bi_end_io  = crypt_endio;
	clone->bi_bdev    = cc->dev->bdev;
	clone->bi_rw      = io->base_bio->bi_rw;
	clone->bi_destructor = dm_crypt_bio_destructor;
}

static void process_read(struct dm_crypt_io *io)
{
	struct crypt_config *cc = io->target->private;
	struct bio *base_bio = io->base_bio;
	struct bio *clone;
	sector_t sector = base_bio->bi_sector - io->target->begin;

	atomic_inc(&io->pending);

	/*