diff options
Diffstat (limited to 'drivers/md/dm-crypt.c')
| -rw-r--r-- | drivers/md/dm-crypt.c | 3490 |
1 files changed, 2705 insertions, 785 deletions
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 6d2d41ae9e32..5ef43231fe77 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1,7 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2003 Christophe Saout <christophe@saout.de> + * Copyright (C) 2003 Jana Saout <jana@saout.de> * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> - * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved. + * Copyright (C) 2006-2020 Red Hat, Inc. All rights reserved. + * Copyright (C) 2013-2020 Milan Broz <gmazyland@gmail.com> * * This file is released under the GPL. */ @@ -11,39 +13,62 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/key.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> +#include <linux/crc32.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/percpu.h> #include <linux/atomic.h> #include <linux/scatterlist.h> +#include <linux/rbtree.h> +#include <linux/ctype.h> #include <asm/page.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include <crypto/md5.h> -#include <crypto/algapi.h> +#include <crypto/skcipher.h> +#include <crypto/aead.h> +#include <crypto/authenc.h> +#include <crypto/utils.h> +#include <linux/rtnetlink.h> /* for struct rtattr and RTA macros only */ +#include <linux/key-type.h> +#include <keys/user-type.h> +#include <keys/encrypted-type.h> +#include <keys/trusted-type.h> #include <linux/device-mapper.h> +#include "dm-audit.h" + #define DM_MSG_PREFIX "crypt" +static DEFINE_IDA(workqueue_ida); + /* * context holding the current state of a multi-part conversion */ struct convert_context { struct completion restart; struct bio *bio_in; + struct bvec_iter iter_in; struct bio *bio_out; - unsigned int offset_in; - unsigned int offset_out; - unsigned int idx_in; - unsigned int idx_out; - sector_t cc_sector; + struct bvec_iter iter_out; atomic_t cc_pending; + unsigned int tag_offset; + u64 cc_sector; + union { + struct skcipher_request *req; + struct aead_request *req_aead; + } r; + bool aead_recheck; + bool aead_failed; + }; /* @@ -52,21 +77,27 @@ struct convert_context { struct dm_crypt_io { struct crypt_config *cc; struct bio *base_bio; + u8 *integrity_metadata; + bool integrity_metadata_from_pool:1; + struct work_struct work; struct convert_context ctx; atomic_t io_pending; - int error; + blk_status_t error; sector_t sector; - struct dm_crypt_io *base_io; -}; + + struct bvec_iter saved_bi_iter; + + 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 scatterlist sg_in[4]; + struct scatterlist sg_out[4]; + u64 iv_sector; }; struct crypt_config; @@ -83,11 +114,6 @@ struct crypt_iv_operations { struct dm_crypt_request *dmreq); }; -struct iv_essiv_private { - struct crypto_hash *hash_tfm; - u8 *salt; -}; - struct iv_benbi_private { int shift; }; @@ -98,66 +124,77 @@ struct iv_lmk_private { u8 *seed; }; +#define TCW_WHITENING_SIZE 16 +struct iv_tcw_private { + u8 *iv_seed; + u8 *whitening; +}; + +#define ELEPHANT_MAX_KEY_SIZE 32 +struct iv_elephant_private { + struct crypto_skcipher *tfm; +}; + /* * 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 }; - -/* - * Duplicated per-CPU state for cipher. - */ -struct crypt_cpu { - struct ablkcipher_request *req; +enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID, + DM_CRYPT_SAME_CPU, DM_CRYPT_HIGH_PRIORITY, + DM_CRYPT_NO_OFFLOAD, DM_CRYPT_NO_READ_WORKQUEUE, + DM_CRYPT_NO_WRITE_WORKQUEUE, DM_CRYPT_WRITE_INLINE }; + +enum cipher_flags { + CRYPT_MODE_INTEGRITY_AEAD, /* Use authenticated mode for cipher */ + CRYPT_IV_LARGE_SECTORS, /* Calculate IV from sector_size, not 512B sectors */ + CRYPT_ENCRYPT_PREPROCESS, /* Must preprocess data for encryption (elephant) */ + CRYPT_KEY_MAC_SIZE_SET, /* The integrity_key_size option was used */ }; /* - * The fields in here must be read only after initialization, - * changing state should be in crypt_cpu. + * 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 *io_pool; - mempool_t *req_pool; - mempool_t *page_pool; - struct bio_set *bs; + struct percpu_counter n_allocated_pages; struct workqueue_struct *io_queue; struct workqueue_struct *crypt_queue; - char *cipher; + spinlock_t write_thread_lock; + struct task_struct *write_thread; + struct rb_root write_tree; + char *cipher_string; + char *cipher_auth; + char *key_string; - struct crypt_iv_operations *iv_gen_ops; + const 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; + struct iv_elephant_private elephant; } iv_gen_private; - sector_t iv_offset; + u64 iv_offset; unsigned int iv_size; + unsigned short sector_size; + unsigned char sector_shift; - /* - * Duplicated per cpu state. Access through - * per_cpu_ptr() only. - */ - struct crypt_cpu __percpu *cpu; - - /* ESSIV: struct crypto_cipher *essiv_tfm */ - void *iv_private; - struct crypto_ablkcipher **tfms; - unsigned tfms_count; + union { + struct crypto_skcipher **tfms; + struct crypto_aead **tfms_aead; + } cipher_tfm; + unsigned int tfms_count; + int workqueue_id; + unsigned long cipher_flags; /* * Layout of each crypto request: * - * struct ablkcipher_request + * struct skcipher_request * context * padding * struct dm_crypt_request @@ -169,32 +206,106 @@ struct crypt_config { */ unsigned int dmreq_start; + unsigned int per_bio_data_size; + unsigned long flags; unsigned int key_size; - unsigned int key_parts; - u8 key[0]; + unsigned int key_parts; /* independent parts in key buffer */ + unsigned int key_extra_size; /* additional keys length */ + unsigned int key_mac_size; /* MAC key size for authenc(...) */ + + unsigned int integrity_tag_size; + unsigned int integrity_iv_size; + unsigned int used_tag_size; + unsigned int tuple_size; + + /* + * pool for per bio private data, crypto requests, + * encryption requeusts/buffer pages and integrity tags + */ + unsigned int tag_pool_max_sectors; + mempool_t tag_pool; + mempool_t req_pool; + mempool_t page_pool; + + struct bio_set bs; + struct mutex bio_alloc_lock; + + u8 *authenc_key; /* space for keys in authenc() format (if used) */ + u8 key[] __counted_by(key_size); }; -#define MIN_IOS 16 -#define MIN_POOL_PAGES 32 +#define MIN_IOS 64 +#define MAX_TAG_SIZE 480 +#define POOL_ENTRY_SIZE 512 -static struct kmem_cache *_crypt_io_pool; +static DEFINE_SPINLOCK(dm_crypt_clients_lock); +static unsigned int dm_crypt_clients_n; +static volatile unsigned long dm_crypt_pages_per_client; +#define DM_CRYPT_MEMORY_PERCENT 2 +#define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_VECS * 16) +#define DM_CRYPT_DEFAULT_MAX_READ_SIZE 131072 +#define DM_CRYPT_DEFAULT_MAX_WRITE_SIZE 131072 -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); +static unsigned int max_read_size = 0; +module_param(max_read_size, uint, 0644); +MODULE_PARM_DESC(max_read_size, "Maximum size of a read request"); +static unsigned int max_write_size = 0; +module_param(max_write_size, uint, 0644); +MODULE_PARM_DESC(max_write_size, "Maximum size of a write request"); -static struct crypt_cpu *this_crypt_config(struct crypt_config *cc) +static unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio) { - return this_cpu_ptr(cc->cpu); + struct crypt_config *cc = ti->private; + unsigned val, sector_align; + bool wrt = op_is_write(bio_op(bio)); + + if (wrt) { + /* + * For zoned devices, splitting write operations creates the + * risk of deadlocking queue freeze operations with zone write + * plugging BIO work when the reminder of a split BIO is + * issued. So always allow the entire BIO to proceed. + */ + if (ti->emulate_zone_append) + return bio_sectors(bio); + + val = min_not_zero(READ_ONCE(max_write_size), + DM_CRYPT_DEFAULT_MAX_WRITE_SIZE); + } else { + val = min_not_zero(READ_ONCE(max_read_size), + DM_CRYPT_DEFAULT_MAX_READ_SIZE); + } + + if (wrt || cc->used_tag_size) + val = min(val, BIO_MAX_VECS << PAGE_SHIFT); + + sector_align = max(bdev_logical_block_size(cc->dev->bdev), + (unsigned)cc->sector_size); + val = round_down(val, sector_align); + if (unlikely(!val)) + val = sector_align; + return val >> SECTOR_SHIFT; } +static void crypt_endio(struct bio *clone); +static void kcryptd_queue_crypt(struct dm_crypt_io *io); +static struct scatterlist *crypt_get_sg_data(struct crypt_config *cc, + struct scatterlist *sg); + +static bool crypt_integrity_aead(struct crypt_config *cc); + /* - * Use this to access cipher attributes that are the same for each CPU. + * Use this to access cipher attributes that are independent of the key. */ -static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) +static struct crypto_skcipher *any_tfm(struct crypt_config *cc) { - return cc->tfms[0]; + return cc->cipher_tfm.tfms[0]; +} + +static struct crypto_aead *any_tfm_aead(struct crypt_config *cc) +{ + return cc->cipher_tfm.tfms_aead[0]; } /* @@ -206,6 +317,9 @@ static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) * plain64: the initial vector is the 64-bit little-endian version of the sector * number, padded with zeros if necessary. * + * plain64be: the initial vector is the 64-bit big-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. @@ -230,8 +344,24 @@ static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) * version 3: the same as version 2 with additional IV seed * (it uses 65 keys, last key is used as IV seed) * - * plumb: unimplemented, see: - * http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454 + * 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. + * + * eboiv: Encrypted byte-offset IV (used in Bitlocker in CBC mode) + * The IV is encrypted little-endian byte-offset (with the same key + * and cipher as the volume). + * + * elephant: The extended version of eboiv with additional Elephant diffuser + * used with Bitlocker CBC mode. + * This mode was used in older Windows systems + * https://download.microsoft.com/download/0/2/3/0238acaf-d3bf-4a6d-b3d6-0a0be4bbb36e/bitlockercipher200608.pdf */ static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv, @@ -252,159 +382,25 @@ static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv, return 0; } -/* Initialise ESSIV - compute salt but no local memory allocations */ -static int crypt_iv_essiv_init(struct crypt_config *cc) +static int crypt_iv_plain64be_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) { - 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; + memset(iv, 0, cc->iv_size); + /* iv_size is at least of size u64; usually it is 16 bytes */ + *(__be64 *)&iv[cc->iv_size - sizeof(u64)] = cpu_to_be64(dmreq->iv_sector); 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; - + /* + * ESSIV encryption of the IV is now handled by the crypto API, + * so just pass the plain sector number here. + */ memset(iv, 0, cc->iv_size); *(__le64 *)iv = cpu_to_le64(dmreq->iv_sector); - crypto_cipher_encrypt_one(essiv_tfm, iv, iv); return 0; } @@ -412,12 +408,19 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, 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); + unsigned int bs; + int log; - /* 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 (crypt_integrity_aead(cc)) + bs = crypto_aead_blocksize(any_tfm_aead(cc)); + else + bs = crypto_skcipher_blocksize(any_tfm(cc)); + 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; @@ -466,7 +469,7 @@ static void crypt_iv_lmk_dtr(struct crypt_config *cc) crypto_free_shash(lmk->hash_tfm); lmk->hash_tfm = NULL; - kzfree(lmk->seed); + kfree_sensitive(lmk->seed); lmk->seed = NULL; } @@ -475,7 +478,13 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti, { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; - lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0); + if (cc->sector_size != (1 << SECTOR_SHIFT)) { + ti->error = "Unsupported sector size for LMK"; + return -EINVAL; + } + + lmk->hash_tfm = crypto_alloc_shash("md5", 0, + CRYPTO_ALG_ALLOCATES_MEMORY); if (IS_ERR(lmk->hash_tfm)) { ti->error = "Error initializing LMK hash"; return PTR_ERR(lmk->hash_tfm); @@ -525,29 +534,28 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, u8 *data) { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; - struct { - struct shash_desc desc; - char ctx[crypto_shash_descsize(lmk->hash_tfm)]; - } sdesc; - struct md5_state md5state; - u32 buf[4]; + SHASH_DESC_ON_STACK(desc, lmk->hash_tfm); + union { + struct md5_state md5state; + u8 state[CRYPTO_MD5_STATESIZE]; + } u; + __le32 buf[4]; int i, r; - sdesc.desc.tfm = lmk->hash_tfm; - sdesc.desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->tfm = lmk->hash_tfm; - r = crypto_shash_init(&sdesc.desc); + r = crypto_shash_init(desc); if (r) return r; if (lmk->seed) { - r = crypto_shash_update(&sdesc.desc, lmk->seed, LMK_SEED_SIZE); + 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(&sdesc.desc, data + 16, 16 * 31); + r = crypto_shash_update(desc, data + 16, 16 * 31); if (r) return r; @@ -556,18 +564,18 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, 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(&sdesc.desc, (u8 *)buf, sizeof(buf)); + r = crypto_shash_update(desc, (u8 *)buf, sizeof(buf)); if (r) return r; /* No MD5 padding here */ - r = crypto_shash_export(&sdesc.desc, &md5state); + r = crypto_shash_export(desc, &u.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); + __cpu_to_le32s(&u.md5state.hash[i]); + memcpy(iv, &u.md5state.hash, cc->iv_size); return 0; } @@ -575,13 +583,15 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, struct dm_crypt_request *dmreq) { + struct scatterlist *sg; 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); + sg = crypt_get_sg_data(cc, dmreq->sg_in); + src = kmap_local_page(sg_page(sg)); + r = crypt_iv_lmk_one(cc, iv, dmreq, src + sg->offset); + kunmap_local(src); } else memset(iv, 0, cc->iv_size); @@ -591,50 +601,520 @@ static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, struct dm_crypt_request *dmreq) { + struct scatterlist *sg; 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); + sg = crypt_get_sg_data(cc, dmreq->sg_out); + dst = kmap_local_page(sg_page(sg)); + r = crypt_iv_lmk_one(cc, iv, dmreq, dst + sg->offset); /* Tweak the first block of plaintext sector */ if (!r) - crypto_xor(dst + dmreq->sg_out.offset, iv, cc->iv_size); + crypto_xor(dst + sg->offset, iv, cc->iv_size); + + kunmap_local(dst); + return r; +} + +static void crypt_iv_tcw_dtr(struct crypt_config *cc) +{ + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + + kfree_sensitive(tcw->iv_seed); + tcw->iv_seed = NULL; + kfree_sensitive(tcw->whitening); + tcw->whitening = 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->sector_size != (1 << SECTOR_SHIFT)) { + ti->error = "Unsupported sector size for TCW"; + return -EINVAL; + } + + if (cc->key_size <= (cc->iv_size + TCW_WHITENING_SIZE)) { + ti->error = "Wrong key size for TCW"; + return -EINVAL; + } + + 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; - kunmap_atomic(dst); + memset(tcw->iv_seed, 0, cc->iv_size); + memset(tcw->whitening, 0, TCW_WHITENING_SIZE); + + return 0; +} + +static void 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; + __le64 sector = cpu_to_le64(dmreq->iv_sector); + u8 buf[TCW_WHITENING_SIZE]; + int i; + + /* xor whitening with sector number */ + crypto_xor_cpy(buf, tcw->whitening, (u8 *)§or, 8); + crypto_xor_cpy(&buf[8], tcw->whitening + 8, (u8 *)§or, 8); + + /* calculate crc32 for every 32bit part and xor it */ + for (i = 0; i < 4; i++) + put_unaligned_le32(crc32(0, &buf[i * 4], 4), &buf[i * 4]); + 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); + memzero_explicit(buf, sizeof(buf)); +} + +static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + struct scatterlist *sg; + struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; + __le64 sector = cpu_to_le64(dmreq->iv_sector); + u8 *src; + + /* Remove whitening from ciphertext */ + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) { + sg = crypt_get_sg_data(cc, dmreq->sg_in); + src = kmap_local_page(sg_page(sg)); + crypt_iv_tcw_whitening(cc, dmreq, src + sg->offset); + kunmap_local(src); + } + + /* Calculate IV */ + crypto_xor_cpy(iv, tcw->iv_seed, (u8 *)§or, 8); + if (cc->iv_size > 8) + crypto_xor_cpy(&iv[8], tcw->iv_seed + 8, (u8 *)§or, + cc->iv_size - 8); + + return 0; +} + +static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + struct scatterlist *sg; + u8 *dst; + + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) + return 0; + + /* Apply whitening on ciphertext */ + sg = crypt_get_sg_data(cc, dmreq->sg_out); + dst = kmap_local_page(sg_page(sg)); + crypt_iv_tcw_whitening(cc, dmreq, dst + sg->offset); + kunmap_local(dst); + + return 0; +} + +static int crypt_iv_random_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + /* Used only for writes, there must be an additional space to store IV */ + get_random_bytes(iv, cc->iv_size); + return 0; +} + +static int crypt_iv_eboiv_ctr(struct crypt_config *cc, struct dm_target *ti, + const char *opts) +{ + if (crypt_integrity_aead(cc)) { + ti->error = "AEAD transforms not supported for EBOIV"; + return -EINVAL; + } + + if (crypto_skcipher_blocksize(any_tfm(cc)) != cc->iv_size) { + ti->error = "Block size of EBOIV cipher does not match IV size of block cipher"; + return -EINVAL; + } + + return 0; +} + +static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + struct crypto_skcipher *tfm = any_tfm(cc); + struct skcipher_request *req; + struct scatterlist src, dst; + DECLARE_CRYPTO_WAIT(wait); + unsigned int reqsize; + int err; + u8 *buf; + + reqsize = sizeof(*req) + crypto_skcipher_reqsize(tfm); + reqsize = ALIGN(reqsize, __alignof__(__le64)); + + req = kmalloc(reqsize + cc->iv_size, GFP_NOIO); + if (!req) + return -ENOMEM; + + skcipher_request_set_tfm(req, tfm); + + buf = (u8 *)req + reqsize; + memset(buf, 0, cc->iv_size); + *(__le64 *)buf = cpu_to_le64(dmreq->iv_sector * cc->sector_size); + + sg_init_one(&src, page_address(ZERO_PAGE(0)), cc->iv_size); + sg_init_one(&dst, iv, cc->iv_size); + skcipher_request_set_crypt(req, &src, &dst, cc->iv_size, buf); + skcipher_request_set_callback(req, 0, crypto_req_done, &wait); + err = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); + kfree_sensitive(req); + + return err; +} + +static void crypt_iv_elephant_dtr(struct crypt_config *cc) +{ + struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant; + + crypto_free_skcipher(elephant->tfm); + elephant->tfm = NULL; +} + +static int crypt_iv_elephant_ctr(struct crypt_config *cc, struct dm_target *ti, + const char *opts) +{ + struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant; + int r; + + elephant->tfm = crypto_alloc_skcipher("ecb(aes)", 0, + CRYPTO_ALG_ALLOCATES_MEMORY); + if (IS_ERR(elephant->tfm)) { + r = PTR_ERR(elephant->tfm); + elephant->tfm = NULL; + return r; + } + + r = crypt_iv_eboiv_ctr(cc, ti, NULL); + if (r) + crypt_iv_elephant_dtr(cc); return r; } -static struct crypt_iv_operations crypt_iv_plain_ops = { +static void diffuser_disk_to_cpu(u32 *d, size_t n) +{ +#ifndef __LITTLE_ENDIAN + int i; + + for (i = 0; i < n; i++) + d[i] = le32_to_cpu((__le32)d[i]); +#endif +} + +static void diffuser_cpu_to_disk(__le32 *d, size_t n) +{ +#ifndef __LITTLE_ENDIAN + int i; + + for (i = 0; i < n; i++) + d[i] = cpu_to_le32((u32)d[i]); +#endif +} + +static void diffuser_a_decrypt(u32 *d, size_t n) +{ + int i, i1, i2, i3; + + for (i = 0; i < 5; i++) { + i1 = 0; + i2 = n - 2; + i3 = n - 5; + + while (i1 < (n - 1)) { + d[i1] += d[i2] ^ (d[i3] << 9 | d[i3] >> 23); + i1++; i2++; i3++; + + if (i3 >= n) + i3 -= n; + + d[i1] += d[i2] ^ d[i3]; + i1++; i2++; i3++; + + if (i2 >= n) + i2 -= n; + + d[i1] += d[i2] ^ (d[i3] << 13 | d[i3] >> 19); + i1++; i2++; i3++; + + d[i1] += d[i2] ^ d[i3]; + i1++; i2++; i3++; + } + } +} + +static void diffuser_a_encrypt(u32 *d, size_t n) +{ + int i, i1, i2, i3; + + for (i = 0; i < 5; i++) { + i1 = n - 1; + i2 = n - 2 - 1; + i3 = n - 5 - 1; + + while (i1 > 0) { + d[i1] -= d[i2] ^ d[i3]; + i1--; i2--; i3--; + + d[i1] -= d[i2] ^ (d[i3] << 13 | d[i3] >> 19); + i1--; i2--; i3--; + + if (i2 < 0) + i2 += n; + + d[i1] -= d[i2] ^ d[i3]; + i1--; i2--; i3--; + + if (i3 < 0) + i3 += n; + + d[i1] -= d[i2] ^ (d[i3] << 9 | d[i3] >> 23); + i1--; i2--; i3--; + } + } +} + +static void diffuser_b_decrypt(u32 *d, size_t n) +{ + int i, i1, i2, i3; + + for (i = 0; i < 3; i++) { + i1 = 0; + i2 = 2; + i3 = 5; + + while (i1 < (n - 1)) { + d[i1] += d[i2] ^ d[i3]; + i1++; i2++; i3++; + + d[i1] += d[i2] ^ (d[i3] << 10 | d[i3] >> 22); + i1++; i2++; i3++; + + if (i2 >= n) + i2 -= n; + + d[i1] += d[i2] ^ d[i3]; + i1++; i2++; i3++; + + if (i3 >= n) + i3 -= n; + + d[i1] += d[i2] ^ (d[i3] << 25 | d[i3] >> 7); + i1++; i2++; i3++; + } + } +} + +static void diffuser_b_encrypt(u32 *d, size_t n) +{ + int i, i1, i2, i3; + + for (i = 0; i < 3; i++) { + i1 = n - 1; + i2 = 2 - 1; + i3 = 5 - 1; + + while (i1 > 0) { + d[i1] -= d[i2] ^ (d[i3] << 25 | d[i3] >> 7); + i1--; i2--; i3--; + + if (i3 < 0) + i3 += n; + + d[i1] -= d[i2] ^ d[i3]; + i1--; i2--; i3--; + + if (i2 < 0) + i2 += n; + + d[i1] -= d[i2] ^ (d[i3] << 10 | d[i3] >> 22); + i1--; i2--; i3--; + + d[i1] -= d[i2] ^ d[i3]; + i1--; i2--; i3--; + } + } +} + +static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *dmreq) +{ + struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant; + u8 *es, *ks, *data, *data2, *data_offset; + struct skcipher_request *req; + struct scatterlist *sg, *sg2, src, dst; + DECLARE_CRYPTO_WAIT(wait); + int i, r; + + req = skcipher_request_alloc(elephant->tfm, GFP_NOIO); + es = kzalloc(16, GFP_NOIO); /* Key for AES */ + ks = kzalloc(32, GFP_NOIO); /* Elephant sector key */ + + if (!req || !es || !ks) { + r = -ENOMEM; + goto out; + } + + *(__le64 *)es = cpu_to_le64(dmreq->iv_sector * cc->sector_size); + + /* E(Ks, e(s)) */ + sg_init_one(&src, es, 16); + sg_init_one(&dst, ks, 16); + skcipher_request_set_crypt(req, &src, &dst, 16, NULL); + skcipher_request_set_callback(req, 0, crypto_req_done, &wait); + r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); + if (r) + goto out; + + /* E(Ks, e'(s)) */ + es[15] = 0x80; + sg_init_one(&dst, &ks[16], 16); + r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); + if (r) + goto out; + + sg = crypt_get_sg_data(cc, dmreq->sg_out); + data = kmap_local_page(sg_page(sg)); + data_offset = data + sg->offset; + + /* Cannot modify original bio, copy to sg_out and apply Elephant to it */ + if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { + sg2 = crypt_get_sg_data(cc, dmreq->sg_in); + data2 = kmap_local_page(sg_page(sg2)); + memcpy(data_offset, data2 + sg2->offset, cc->sector_size); + kunmap_local(data2); + } + + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) { + diffuser_disk_to_cpu((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_b_decrypt((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_a_decrypt((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_cpu_to_disk((__le32 *)data_offset, cc->sector_size / sizeof(u32)); + } + + for (i = 0; i < (cc->sector_size / 32); i++) + crypto_xor(data_offset + i * 32, ks, 32); + + if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { + diffuser_disk_to_cpu((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_a_encrypt((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_b_encrypt((u32 *)data_offset, cc->sector_size / sizeof(u32)); + diffuser_cpu_to_disk((__le32 *)data_offset, cc->sector_size / sizeof(u32)); + } + + kunmap_local(data); +out: + kfree_sensitive(ks); + kfree_sensitive(es); + skcipher_request_free(req); + return r; +} + +static int crypt_iv_elephant_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + int r; + + if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { + r = crypt_iv_elephant(cc, dmreq); + if (r) + return r; + } + + return crypt_iv_eboiv_gen(cc, iv, dmreq); +} + +static int crypt_iv_elephant_post(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) + return crypt_iv_elephant(cc, dmreq); + + return 0; +} + +static int crypt_iv_elephant_init(struct crypt_config *cc) +{ + struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant; + int key_offset = cc->key_size - cc->key_extra_size; + + return crypto_skcipher_setkey(elephant->tfm, &cc->key[key_offset], cc->key_extra_size); +} + +static int crypt_iv_elephant_wipe(struct crypt_config *cc) +{ + struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant; + u8 key[ELEPHANT_MAX_KEY_SIZE]; + + memset(key, 0, cc->key_extra_size); + return crypto_skcipher_setkey(elephant->tfm, key, cc->key_extra_size); +} + +static const struct crypt_iv_operations crypt_iv_plain_ops = { .generator = crypt_iv_plain_gen }; -static struct crypt_iv_operations crypt_iv_plain64_ops = { +static const 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, +static const struct crypt_iv_operations crypt_iv_plain64be_ops = { + .generator = crypt_iv_plain64be_gen +}; + +static const struct crypt_iv_operations crypt_iv_essiv_ops = { .generator = crypt_iv_essiv_gen }; -static struct crypt_iv_operations crypt_iv_benbi_ops = { +static const 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 = { +static const struct crypt_iv_operations crypt_iv_null_ops = { .generator = crypt_iv_null_gen }; -static struct crypt_iv_operations crypt_iv_lmk_ops = { +static const struct crypt_iv_operations crypt_iv_lmk_ops = { .ctr = crypt_iv_lmk_ctr, .dtr = crypt_iv_lmk_dtr, .init = crypt_iv_lmk_init, @@ -643,6 +1123,128 @@ static struct crypt_iv_operations crypt_iv_lmk_ops = { .post = crypt_iv_lmk_post }; +static const 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 const struct crypt_iv_operations crypt_iv_random_ops = { + .generator = crypt_iv_random_gen +}; + +static const struct crypt_iv_operations crypt_iv_eboiv_ops = { + .ctr = crypt_iv_eboiv_ctr, + .generator = crypt_iv_eboiv_gen +}; + +static const struct crypt_iv_operations crypt_iv_elephant_ops = { + .ctr = crypt_iv_elephant_ctr, + .dtr = crypt_iv_elephant_dtr, + .init = crypt_iv_elephant_init, + .wipe = crypt_iv_elephant_wipe, + .generator = crypt_iv_elephant_gen, + .post = crypt_iv_elephant_post +}; + +/* + * Integrity extensions + */ +static bool crypt_integrity_aead(struct crypt_config *cc) +{ + return test_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags); +} + +static bool crypt_integrity_hmac(struct crypt_config *cc) +{ + return crypt_integrity_aead(cc) && cc->key_mac_size; +} + +/* Get sg containing data */ +static struct scatterlist *crypt_get_sg_data(struct crypt_config *cc, + struct scatterlist *sg) +{ + if (unlikely(crypt_integrity_aead(cc))) + return &sg[2]; + + return sg; +} + +static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) +{ + struct bio_integrity_payload *bip; + unsigned int tag_len; + int ret; + + if (!bio_sectors(bio) || !io->cc->tuple_size) + return 0; + + bip = bio_integrity_alloc(bio, GFP_NOIO, 1); + if (IS_ERR(bip)) + return PTR_ERR(bip); + + tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift); + + bip->bip_iter.bi_sector = bio->bi_iter.bi_sector; + + ret = bio_integrity_add_page(bio, virt_to_page(io->integrity_metadata), + tag_len, offset_in_page(io->integrity_metadata)); + if (unlikely(ret != tag_len)) + return -ENOMEM; + + return 0; +} + +static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) +{ +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk); + struct mapped_device *md = dm_table_get_md(ti->table); + + /* We require an underlying device with non-PI metadata */ + if (!bi || bi->csum_type != BLK_INTEGRITY_CSUM_NONE) { + ti->error = "Integrity profile not supported."; + return -EINVAL; + } + + if (bi->metadata_size < cc->used_tag_size) { + ti->error = "Integrity profile tag size mismatch."; + return -EINVAL; + } + cc->tuple_size = bi->metadata_size; + if (1 << bi->interval_exp != cc->sector_size) { + ti->error = "Integrity profile sector size mismatch."; + return -EINVAL; + } + + if (crypt_integrity_aead(cc)) { + cc->integrity_tag_size = cc->used_tag_size - cc->integrity_iv_size; + DMDEBUG("%s: Integrity AEAD, tag size %u, IV size %u.", dm_device_name(md), + cc->integrity_tag_size, cc->integrity_iv_size); + + if (crypto_aead_setauthsize(any_tfm_aead(cc), cc->integrity_tag_size)) { + ti->error = "Integrity AEAD auth tag size is not supported."; + return -EINVAL; + } + } else if (cc->integrity_iv_size) + DMDEBUG("%s: Additional per-sector space %u bytes for IV.", dm_device_name(md), + cc->integrity_iv_size); + + if ((cc->integrity_tag_size + cc->integrity_iv_size) > cc->tuple_size) { + ti->error = "Not enough space for integrity tag in the profile."; + return -EINVAL; + } + + return 0; +#else + ti->error = "Integrity profile not supported."; + return -EINVAL; +#endif +} + static void crypt_convert_init(struct crypt_config *cc, struct convert_context *ctx, struct bio *bio_out, struct bio *bio_in, @@ -650,235 +1252,557 @@ static void crypt_convert_init(struct crypt_config *cc, { 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; + 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; + ctx->tag_offset = 0; init_completion(&ctx->restart); } static struct dm_crypt_request *dmreq_of_req(struct crypt_config *cc, - struct ablkcipher_request *req) + void *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) +static void *req_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq) { - return (struct ablkcipher_request *)((char *)dmreq - cc->dmreq_start); + return (void *)((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); + if (crypt_integrity_aead(cc)) + return (u8 *)ALIGN((unsigned long)(dmreq + 1), + crypto_aead_alignmask(any_tfm_aead(cc)) + 1); + else + return (u8 *)ALIGN((unsigned long)(dmreq + 1), + crypto_skcipher_alignmask(any_tfm(cc)) + 1); } -static int crypt_convert_block(struct crypt_config *cc, - struct convert_context *ctx, - struct ablkcipher_request *req) +static u8 *org_iv_of_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + return iv_of_dmreq(cc, dmreq) + cc->iv_size; +} + +static __le64 *org_sector_of_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + u8 *ptr = iv_of_dmreq(cc, dmreq) + cc->iv_size + cc->iv_size; + + return (__le64 *) ptr; +} + +static unsigned int *org_tag_of_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + u8 *ptr = iv_of_dmreq(cc, dmreq) + cc->iv_size + + cc->iv_size + sizeof(uint64_t); + + return (unsigned int *)ptr; +} + +static void *tag_from_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + struct convert_context *ctx = dmreq->ctx; + struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); + + return &io->integrity_metadata[*org_tag_of_dmreq(cc, dmreq) * + cc->tuple_size]; +} + +static void *iv_tag_from_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + return tag_from_dmreq(cc, dmreq) + cc->integrity_tag_size; +} + +static int crypt_convert_block_aead(struct crypt_config *cc, + struct convert_context *ctx, + struct aead_request *req, + unsigned int tag_offset) { - 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 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; + u8 *iv, *org_iv, *tag_iv, *tag; + __le64 *sector; + int r = 0; - dmreq = dmreq_of_req(cc, req); - iv = iv_of_dmreq(cc, dmreq); + BUG_ON(cc->integrity_iv_size && cc->integrity_iv_size != cc->iv_size); + + /* Reject unexpected unaligned bio. */ + if (unlikely(bv_in.bv_len & (cc->sector_size - 1))) + return -EIO; + dmreq = dmreq_of_req(cc, req); dmreq->iv_sector = ctx->cc_sector; + if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags)) + dmreq->iv_sector >>= cc->sector_shift; 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 + ctx->offset_in); - sg_init_table(&dmreq->sg_out, 1); - sg_set_page(&dmreq->sg_out, bv_out->bv_page, 1 << SECTOR_SHIFT, - bv_out->bv_offset + ctx->offset_out); + *org_tag_of_dmreq(cc, dmreq) = tag_offset; + + sector = org_sector_of_dmreq(cc, dmreq); + *sector = cpu_to_le64(ctx->cc_sector - cc->iv_offset); + + iv = iv_of_dmreq(cc, dmreq); + org_iv = org_iv_of_dmreq(cc, dmreq); + tag = tag_from_dmreq(cc, dmreq); + tag_iv = iv_tag_from_dmreq(cc, dmreq); + + /* AEAD request: + * |----- AAD -------|------ DATA -------|-- AUTH TAG --| + * | (authenticated) | (auth+encryption) | | + * | sector_LE | IV | sector in/out | tag in/out | + */ + sg_init_table(dmreq->sg_in, 4); + sg_set_buf(&dmreq->sg_in[0], sector, sizeof(uint64_t)); + sg_set_buf(&dmreq->sg_in[1], org_iv, cc->iv_size); + sg_set_page(&dmreq->sg_in[2], bv_in.bv_page, cc->sector_size, bv_in.bv_offset); + sg_set_buf(&dmreq->sg_in[3], tag, cc->integrity_tag_size); + + sg_init_table(dmreq->sg_out, 4); + sg_set_buf(&dmreq->sg_out[0], sector, sizeof(uint64_t)); + sg_set_buf(&dmreq->sg_out[1], org_iv, cc->iv_size); + sg_set_page(&dmreq->sg_out[2], bv_out.bv_page, cc->sector_size, bv_out.bv_offset); + sg_set_buf(&dmreq->sg_out[3], tag, cc->integrity_tag_size); - ctx->offset_in += 1 << SECTOR_SHIFT; - if (ctx->offset_in >= bv_in->bv_len) { - ctx->offset_in = 0; - ctx->idx_in++; + if (cc->iv_gen_ops) { + /* For READs use IV stored in integrity metadata */ + if (cc->integrity_iv_size && bio_data_dir(ctx->bio_in) != WRITE) { + memcpy(org_iv, tag_iv, cc->iv_size); + } else { + r = cc->iv_gen_ops->generator(cc, org_iv, dmreq); + if (r < 0) + return r; + /* Store generated IV in integrity metadata */ + if (cc->integrity_iv_size) + memcpy(tag_iv, org_iv, cc->iv_size); + } + /* Working copy of IV, to be modified in crypto API */ + memcpy(iv, org_iv, cc->iv_size); } - ctx->offset_out += 1 << SECTOR_SHIFT; - if (ctx->offset_out >= bv_out->bv_len) { - ctx->offset_out = 0; - ctx->idx_out++; + aead_request_set_ad(req, sizeof(uint64_t) + cc->iv_size); + if (bio_data_dir(ctx->bio_in) == WRITE) { + aead_request_set_crypt(req, dmreq->sg_in, dmreq->sg_out, + cc->sector_size, iv); + r = crypto_aead_encrypt(req); + if (cc->integrity_tag_size + cc->integrity_iv_size != cc->tuple_size) + memset(tag + cc->integrity_tag_size + cc->integrity_iv_size, 0, + cc->tuple_size - (cc->integrity_tag_size + cc->integrity_iv_size)); + } else { + aead_request_set_crypt(req, dmreq->sg_in, dmreq->sg_out, + cc->sector_size + cc->integrity_tag_size, iv); + r = crypto_aead_decrypt(req); } + if (r == -EBADMSG) { + sector_t s = le64_to_cpu(*sector); + + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } + } + + if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post) + r = cc->iv_gen_ops->post(cc, org_iv, dmreq); + + bio_advance_iter(ctx->bio_in, &ctx->iter_in, cc->sector_size); + bio_advance_iter(ctx->bio_out, &ctx->iter_out, cc->sector_size); + + return r; +} + +static int crypt_convert_block_skcipher(struct crypt_config *cc, + struct convert_context *ctx, + struct skcipher_request *req, + unsigned int tag_offset) +{ + 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 scatterlist *sg_in, *sg_out; + struct dm_crypt_request *dmreq; + u8 *iv, *org_iv, *tag_iv; + __le64 *sector; + int r = 0; + + /* Reject unexpected unaligned bio. */ + if (unlikely(bv_in.bv_len & (cc->sector_size - 1))) + return -EIO; + + dmreq = dmreq_of_req(cc, req); + dmreq->iv_sector = ctx->cc_sector; + if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags)) + dmreq->iv_sector >>= cc->sector_shift; + dmreq->ctx = ctx; + + *org_tag_of_dmreq(cc, dmreq) = tag_offset; + + iv = iv_of_dmreq(cc, dmreq); + org_iv = org_iv_of_dmreq(cc, dmreq); + tag_iv = iv_tag_from_dmreq(cc, dmreq); + + sector = org_sector_of_dmreq(cc, dmreq); + *sector = cpu_to_le64(ctx->cc_sector - cc->iv_offset); + + /* For skcipher we use only the first sg item */ + sg_in = &dmreq->sg_in[0]; + sg_out = &dmreq->sg_out[0]; + + sg_init_table(sg_in, 1); + sg_set_page(sg_in, bv_in.bv_page, cc->sector_size, bv_in.bv_offset); + + sg_init_table(sg_out, 1); + sg_set_page(sg_out, bv_out.bv_page, cc->sector_size, bv_out.bv_offset); + if (cc->iv_gen_ops) { - r = cc->iv_gen_ops->generator(cc, iv, dmreq); - if (r < 0) - return r; + /* For READs use IV stored in integrity metadata */ + if (cc->integrity_iv_size && bio_data_dir(ctx->bio_in) != WRITE) { + memcpy(org_iv, tag_iv, cc->integrity_iv_size); + } else { + r = cc->iv_gen_ops->generator(cc, org_iv, dmreq); + if (r < 0) + return r; + /* Data can be already preprocessed in generator */ + if (test_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags)) + sg_in = sg_out; + /* Store generated IV in integrity metadata */ + if (cc->integrity_iv_size) + memcpy(tag_iv, org_iv, cc->integrity_iv_size); + } + /* Working copy of IV, to be modified in crypto API */ + memcpy(iv, org_iv, cc->iv_size); } - ablkcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out, - 1 << SECTOR_SHIFT, iv); + skcipher_request_set_crypt(req, sg_in, sg_out, cc->sector_size, iv); if (bio_data_dir(ctx->bio_in) == WRITE) - r = crypto_ablkcipher_encrypt(req); + r = crypto_skcipher_encrypt(req); else - r = crypto_ablkcipher_decrypt(req); + r = crypto_skcipher_decrypt(req); if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post) - r = cc->iv_gen_ops->post(cc, iv, dmreq); + r = cc->iv_gen_ops->post(cc, org_iv, dmreq); + + bio_advance_iter(ctx->bio_in, &ctx->iter_in, cc->sector_size); + bio_advance_iter(ctx->bio_out, &ctx->iter_out, cc->sector_size); return r; } -static void kcryptd_async_done(struct crypto_async_request *async_req, - int error); +static void kcryptd_async_done(void *async_req, int error); + +static int crypt_alloc_req_skcipher(struct crypt_config *cc, + struct convert_context *ctx) +{ + unsigned int key_index = ctx->cc_sector & (cc->tfms_count - 1); + + if (!ctx->r.req) { + ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req) + return -ENOMEM; + } + + skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]); + + /* + * Use REQ_MAY_BACKLOG so a cipher driver internally backlogs + * requests if driver request queue is full. + */ + skcipher_request_set_callback(ctx->r.req, + CRYPTO_TFM_REQ_MAY_BACKLOG, + kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); + + return 0; +} + +static int crypt_alloc_req_aead(struct crypt_config *cc, + struct convert_context *ctx) +{ + if (!ctx->r.req_aead) { + ctx->r.req_aead = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req_aead) + return -ENOMEM; + } -static void crypt_alloc_req(struct crypt_config *cc, + aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]); + + /* + * Use REQ_MAY_BACKLOG so a cipher driver internally backlogs + * requests if driver request queue is full. + */ + aead_request_set_callback(ctx->r.req_aead, + CRYPTO_TFM_REQ_MAY_BACKLOG, + kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); + + return 0; +} + +static int crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { - struct crypt_cpu *this_cc = this_crypt_config(cc); - unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); + if (crypt_integrity_aead(cc)) + return crypt_alloc_req_aead(cc, ctx); + else + return crypt_alloc_req_skcipher(cc, ctx); +} + +static void crypt_free_req_skcipher(struct crypt_config *cc, + struct skcipher_request *req, struct bio *base_bio) +{ + struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size); - if (!this_cc->req) - this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO); + if ((struct skcipher_request *)(io + 1) != req) + mempool_free(req, &cc->req_pool); +} + +static void crypt_free_req_aead(struct crypt_config *cc, + struct aead_request *req, struct bio *base_bio) +{ + struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size); - ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]); - ablkcipher_request_set_callback(this_cc->req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - kcryptd_async_done, dmreq_of_req(cc, this_cc->req)); + if ((struct aead_request *)(io + 1) != req) + mempool_free(req, &cc->req_pool); +} + +static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_bio) +{ + if (crypt_integrity_aead(cc)) + crypt_free_req_aead(cc, req, base_bio); + else + crypt_free_req_skcipher(cc, req, base_bio); } /* * 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) +static blk_status_t crypt_convert(struct crypt_config *cc, + struct convert_context *ctx, bool atomic, bool reset_pending) { - struct crypt_cpu *this_cc = this_crypt_config(cc); + unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT; int r; - atomic_set(&ctx->cc_pending, 1); + /* + * if reset_pending is set we are dealing with the bio for the first time, + * else we're continuing to work on the previous bio, so don't mess with + * the cc_pending counter + */ + if (reset_pending) + atomic_set(&ctx->cc_pending, 1); - while(ctx->idx_in < ctx->bio_in->bi_vcnt && - ctx->idx_out < ctx->bio_out->bi_vcnt) { + while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) { - crypt_alloc_req(cc, ctx); + r = crypt_alloc_req(cc, ctx); + if (r) { + complete(&ctx->restart); + return BLK_STS_DEV_RESOURCE; + } atomic_inc(&ctx->cc_pending); - r = crypt_convert_block(cc, ctx, this_cc->req); + if (crypt_integrity_aead(cc)) + r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset); + else + r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset); switch (r) { - /* async */ + /* + * 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); - INIT_COMPLETION(ctx->restart); - /* fall through*/ + if (in_interrupt()) { + if (try_wait_for_completion(&ctx->restart)) { + /* + * we don't have to block to wait for completion, + * so proceed + */ + } else { + /* + * we can't wait for completion without blocking + * exit and continue processing in a workqueue + */ + ctx->r.req = NULL; + ctx->tag_offset++; + ctx->cc_sector += sector_step; + return BLK_STS_DEV_RESOURCE; + } + } else { + wait_for_completion(&ctx->restart); + } + reinit_completion(&ctx->restart); + fallthrough; + /* + * The request is queued and processed asynchronously, + * completion function kcryptd_async_done() will be called. + */ case -EINPROGRESS: - this_cc->req = NULL; - ctx->cc_sector++; + ctx->r.req = NULL; + ctx->tag_offset++; + ctx->cc_sector += sector_step; continue; - - /* sync */ + /* + * The request was already processed (synchronously). + */ case 0: atomic_dec(&ctx->cc_pending); - ctx->cc_sector++; - cond_resched(); + ctx->cc_sector += sector_step; + ctx->tag_offset++; + if (!atomic) + cond_resched(); continue; - - /* error */ + /* + * There was a data integrity error. + */ + case -EBADMSG: + atomic_dec(&ctx->cc_pending); + return BLK_STS_PROTECTION; + /* + * There was an error while processing the request. + */ default: atomic_dec(&ctx->cc_pending); - return r; + return BLK_STS_IOERR; } } 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 - * May return a smaller bio when running out of pages, indicated by - * *out_of_pages set to 1. + * This should never violate the device limitations (but if it did then block + * core should split the bio as needed). + * + * 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. + * + * In order to reduce allocation overhead, we try to allocate compound pages in + * the first pass. If they are not available, we fall back to the mempool. */ -static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size, - unsigned *out_of_pages) +static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int 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_NOIO | __GFP_HIGHMEM; - unsigned i, len; - struct page *page; - - clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs); - if (!clone) - return NULL; + gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM; + unsigned int remaining_size; + unsigned int order = MAX_PAGE_ORDER; - clone_init(io, clone); - *out_of_pages = 0; +retry: + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) + mutex_lock(&cc->bio_alloc_lock); - for (i = 0; i < nr_iovecs; i++) { - page = mempool_alloc(cc->page_pool, gfp_mask); - if (!page) { - *out_of_pages = 1; - break; + clone = bio_alloc_bioset(cc->dev->bdev, nr_iovecs, io->base_bio->bi_opf, + GFP_NOIO, &cc->bs); + clone->bi_private = io; + clone->bi_end_io = crypt_endio; + clone->bi_ioprio = io->base_bio->bi_ioprio; + clone->bi_iter.bi_sector = cc->start + io->sector; + + remaining_size = size; + + while (remaining_size) { + struct page *pages; + unsigned size_to_add; + unsigned remaining_order = __fls((remaining_size + PAGE_SIZE - 1) >> PAGE_SHIFT); + order = min(order, remaining_order); + + while (order > 0) { + if (unlikely(percpu_counter_read_positive(&cc->n_allocated_pages) + + (1 << order) > dm_crypt_pages_per_client)) + goto decrease_order; + pages = alloc_pages(gfp_mask + | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | __GFP_COMP, + order); + if (likely(pages != NULL)) { + percpu_counter_add(&cc->n_allocated_pages, 1 << order); + goto have_pages; + } +decrease_order: + order--; } - /* - * If additional pages cannot be allocated without waiting, - * return a partially-allocated bio. The caller will then try - * to allocate more bios while submitting this partial bio. - */ - 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; + pages = mempool_alloc(&cc->page_pool, gfp_mask); + if (!pages) { + crypt_free_buffer_pages(cc, clone); + bio_put(clone); + gfp_mask |= __GFP_DIRECT_RECLAIM; + order = 0; + goto retry; } - size -= len; +have_pages: + size_to_add = min((unsigned)PAGE_SIZE << order, remaining_size); + __bio_add_page(clone, pages, size_to_add, 0); + remaining_size -= size_to_add; } - if (!clone->bi_size) { + /* Allocate space for integrity tags */ + if (dm_crypt_integrity_io_alloc(io, clone)) { + crypt_free_buffer_pages(cc, clone); bio_put(clone); - return NULL; + clone = NULL; } + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) + mutex_unlock(&cc->bio_alloc_lock); + return clone; } static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone) { - unsigned int i; - struct bio_vec *bv; + struct folio_iter fi; - bio_for_each_segment_all(bv, clone, i) { - BUG_ON(!bv->bv_page); - mempool_free(bv->bv_page, cc->page_pool); - bv->bv_page = NULL; + if (clone->bi_vcnt > 0) { /* bio_for_each_folio_all crashes with an empty bio */ + bio_for_each_folio_all(fi, clone) { + if (folio_test_large(fi.folio)) { + percpu_counter_sub(&cc->n_allocated_pages, + 1 << folio_order(fi.folio)); + folio_put(fi.folio); + } else { + mempool_free(&fi.folio->page, &cc->page_pool); + } + } } } -static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc, - struct bio *bio, sector_t sector) +static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, + struct bio *bio, sector_t sector) { - struct dm_crypt_io *io; - - io = mempool_alloc(cc->io_pool, GFP_NOIO); io->cc = cc; io->base_bio = bio; io->sector = sector; io->error = 0; - io->base_io = NULL; + io->ctx.aead_recheck = false; + io->ctx.aead_failed = false; + io->ctx.r.req = NULL; + io->integrity_metadata = NULL; + io->integrity_metadata_from_pool = false; atomic_set(&io->io_pending, 0); - - return io; } static void crypt_inc_pending(struct dm_crypt_io *io) @@ -886,30 +1810,41 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } +static void kcryptd_queue_read(struct dm_crypt_io *io); + /* * One of the bios was finished. Check for completion of * the whole request and correctly clean up the buffer. - * If base_io is set, wait for the last fragment to complete. */ static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; struct bio *base_bio = io->base_bio; - struct dm_crypt_io *base_io = io->base_io; - int error = io->error; + blk_status_t error = io->error; if (!atomic_dec_and_test(&io->io_pending)) return; - mempool_free(io, cc->io_pool); - - if (likely(!base_io)) - bio_endio(base_bio, error); - else { - if (error && !base_io->error) - base_io->error = error; - crypt_dec_pending(base_io); + if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) && + cc->used_tag_size && bio_data_dir(base_bio) == READ) { + io->ctx.aead_recheck = true; + io->ctx.aead_failed = false; + io->error = 0; + kcryptd_queue_read(io); + return; } + + if (io->ctx.r.req) + crypt_free_req(cc, io->ctx.r.req, base_bio); + + if (unlikely(io->integrity_metadata_from_pool)) + mempool_free(io->integrity_metadata, &io->cc->tag_pool); + else + kfree(io->integrity_metadata); + + base_bio->bi_status = error; + + bio_endio(base_bio); } /* @@ -929,19 +1864,22 @@ static void crypt_dec_pending(struct dm_crypt_io *io) * The work is done per CPU global for all dm-crypt instances. * They should not depend on each other and do not block. */ -static void crypt_endio(struct bio *clone, int error) +static void crypt_endio(struct bio *clone) { struct dm_crypt_io *io = clone->bi_private; struct crypt_config *cc = io->cc; - unsigned rw = bio_data_dir(clone); + unsigned int rw = bio_data_dir(clone); + blk_status_t error = clone->bi_status; - if (unlikely(!bio_flagged(clone, BIO_UPTODATE) && !error)) - error = -EIO; + if (io->ctx.aead_recheck && !error) { + kcryptd_queue_crypt(io); + return; + } /* * free the processed pages */ - if (rw == WRITE) + if (rw == WRITE || io->ctx.aead_recheck) crypt_free_buffer_pages(cc, clone); bio_put(clone); @@ -957,73 +1895,142 @@ static void crypt_endio(struct bio *clone, int error) crypt_dec_pending(io); } -static void clone_init(struct dm_crypt_io *io, struct bio *clone) -{ - struct crypt_config *cc = io->cc; - - clone->bi_private = io; - clone->bi_end_io = crypt_endio; - clone->bi_bdev = cc->dev->bdev; - clone->bi_rw = io->base_bio->bi_rw; -} +#define CRYPT_MAP_READ_GFP GFP_NOWAIT static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) { struct crypt_config *cc = io->cc; - struct bio *base_bio = io->base_bio; struct bio *clone; + if (io->ctx.aead_recheck) { + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return 1; + crypt_inc_pending(io); + clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); + if (unlikely(!clone)) { + crypt_dec_pending(io); + return 1; + } + crypt_convert_init(cc, &io->ctx, clone, clone, io->sector); + io->saved_bi_iter = clone->bi_iter; + dm_submit_bio_remap(io->base_bio, clone); + return 0; + } + /* - * The block layer might modify the bvec array, so always - * copy the required bvecs because we need the original - * one in order to decrypt the whole bio data *afterwards*. + * We need the original biovec array in order to decrypt the whole bio + * data *afterwards* -- thanks to immutable biovecs we don't need to + * worry about the block layer modifying the biovec array; so leverage + * bio_alloc_clone(). */ - clone = bio_clone_bioset(base_bio, gfp, cc->bs); + clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs); if (!clone) return 1; + clone->bi_iter.bi_sector = cc->start + io->sector; + clone->bi_private = io; + clone->bi_end_io = crypt_endio; + crypt_inc_pending(io); - clone_init(io, clone); - clone->bi_sector = cc->start + io->sector; + if (dm_crypt_integrity_io_alloc(io, clone)) { + crypt_dec_pending(io); + bio_put(clone); + return 1; + } - generic_make_request(clone); + dm_submit_bio_remap(io->base_bio, clone); return 0; } -static void kcryptd_io_write(struct dm_crypt_io *io) -{ - struct bio *clone = io->ctx.bio_out; - generic_make_request(clone); -} - -static void kcryptd_io(struct work_struct *work) +static void kcryptd_io_read_work(struct work_struct *work) { struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); - if (bio_data_dir(io->base_bio) == READ) { - crypt_inc_pending(io); - if (kcryptd_io_read(io, GFP_NOIO)) - io->error = -ENOMEM; - crypt_dec_pending(io); - } else - kcryptd_io_write(io); + crypt_inc_pending(io); + if (kcryptd_io_read(io, GFP_NOIO)) + io->error = BLK_STS_RESOURCE; + crypt_dec_pending(io); } -static void kcryptd_queue_io(struct dm_crypt_io *io) +static void kcryptd_queue_read(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; - INIT_WORK(&io->work, kcryptd_io); + INIT_WORK(&io->work, kcryptd_io_read_work); queue_work(cc->io_queue, &io->work); } +static void kcryptd_io_write(struct dm_crypt_io *io) +{ + struct bio *clone = io->ctx.bio_out; + + dm_submit_bio_remap(io->base_bio, clone); +} + +#define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node) + +static int dmcrypt_write(void *data) +{ + struct crypt_config *cc = data; + struct dm_crypt_io *io; + + while (1) { + struct rb_root write_tree; + struct blk_plug plug; + + spin_lock_irq(&cc->write_thread_lock); +continue_locked: + + if (!RB_EMPTY_ROOT(&cc->write_tree)) + goto pop_from_list; + + set_current_state(TASK_INTERRUPTIBLE); + + spin_unlock_irq(&cc->write_thread_lock); + + if (unlikely(kthread_should_stop())) { + set_current_state(TASK_RUNNING); + break; + } + + schedule(); + + spin_lock_irq(&cc->write_thread_lock); + goto continue_locked; + +pop_from_list: + write_tree = cc->write_tree; + cc->write_tree = RB_ROOT; + spin_unlock_irq(&cc->write_thread_lock); + + BUG_ON(rb_parent(write_tree.rb_node)); + + /* + * Note: we cannot walk the tree here with rb_next because + * the structures may be freed when kcryptd_io_write is called. + */ + blk_start_plug(&plug); + do { + io = crypt_io_from_node(rb_first(&write_tree)); + rb_erase(&io->rb_node, &write_tree); + kcryptd_io_write(io); + cond_resched(); + } while (!RB_EMPTY_ROOT(&write_tree)); + blk_finish_plug(&plug); + } + return 0; +} + static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) { struct bio *clone = io->ctx.bio_out; struct crypt_config *cc = io->cc; + unsigned long flags; + sector_t sector; + struct rb_node **rbp, *parent; - if (unlikely(io->error < 0)) { + if (unlikely(io->error)) { crypt_free_buffer_pages(cc, clone); bio_put(clone); crypt_dec_pending(io); @@ -1031,129 +2038,200 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) } /* crypt_convert should have filled the clone bio */ - BUG_ON(io->ctx.idx_out < clone->bi_vcnt); + BUG_ON(io->ctx.iter_out.bi_size); - clone->bi_sector = cc->start + io->sector; + if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) || + test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) { + dm_submit_bio_remap(io->base_bio, clone); + return; + } - if (async) - kcryptd_queue_io(io); - else - generic_make_request(clone); + spin_lock_irqsave(&cc->write_thread_lock, flags); + if (RB_EMPTY_ROOT(&cc->write_tree)) + wake_up_process(cc->write_thread); + rbp = &cc->write_tree.rb_node; + parent = NULL; + sector = io->sector; + while (*rbp) { + parent = *rbp; + if (sector < crypt_io_from_node(parent)->sector) + rbp = &(*rbp)->rb_left; + else + rbp = &(*rbp)->rb_right; + } + rb_link_node(&io->rb_node, parent, rbp); + rb_insert_color(&io->rb_node, &cc->write_tree); + spin_unlock_irqrestore(&cc->write_thread_lock, flags); +} + +static bool kcryptd_crypt_write_inline(struct crypt_config *cc, + struct convert_context *ctx) + +{ + if (!test_bit(DM_CRYPT_WRITE_INLINE, &cc->flags)) + return false; + + /* + * Note: zone append writes (REQ_OP_ZONE_APPEND) do not have ordering + * constraints so they do not need to be issued inline by + * kcryptd_crypt_write_convert(). + */ + switch (bio_op(ctx->bio_in)) { + case REQ_OP_WRITE: + case REQ_OP_WRITE_ZEROES: + return true; + default: + return false; + } +} + +static void kcryptd_crypt_write_continue(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + struct convert_context *ctx = &io->ctx; + int crypt_finished; + blk_status_t r; + + wait_for_completion(&ctx->restart); + reinit_completion(&ctx->restart); + + r = crypt_convert(cc, &io->ctx, false, false); + if (r) + io->error = r; + crypt_finished = atomic_dec_and_test(&ctx->cc_pending); + if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) { + /* Wait for completion signaled by kcryptd_async_done() */ + wait_for_completion(&ctx->restart); + crypt_finished = 1; + } + + /* Encryption was already finished, submit io now */ + if (crypt_finished) + kcryptd_crypt_write_io_submit(io, 0); + + crypt_dec_pending(io); } static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; + struct convert_context *ctx = &io->ctx; struct bio *clone; - struct dm_crypt_io *new_io; int crypt_finished; - unsigned out_of_pages = 0; - unsigned remaining = io->base_bio->bi_size; - sector_t sector = io->sector; - int r; + blk_status_t r; /* * Prevent io from disappearing until this function completes. */ crypt_inc_pending(io); - crypt_convert_init(cc, &io->ctx, NULL, io->base_bio, sector); + crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector); - /* - * The allocated buffers can be smaller than the whole bio, - * so repeat the whole process until all the data can be handled. - */ - while (remaining) { - clone = crypt_alloc_buffer(io, remaining, &out_of_pages); - if (unlikely(!clone)) { - io->error = -ENOMEM; - break; - } - - io->ctx.bio_out = clone; - io->ctx.idx_out = 0; - - remaining -= clone->bi_size; - sector += bio_sectors(clone); - - crypt_inc_pending(io); - - r = crypt_convert(cc, &io->ctx); - if (r < 0) - io->error = -EIO; - - crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending); + clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); + if (unlikely(!clone)) { + io->error = BLK_STS_IOERR; + goto dec; + } - /* Encryption was already finished, submit io now */ - if (crypt_finished) { - kcryptd_crypt_write_io_submit(io, 0); + io->ctx.bio_out = clone; + io->ctx.iter_out = clone->bi_iter; - /* - * If there was an error, do not try next fragments. - * For async, error is processed in async handler. - */ - if (unlikely(r < 0)) - break; + if (crypt_integrity_aead(cc)) { + bio_copy_data(clone, io->base_bio); + io->ctx.bio_in = clone; + io->ctx.iter_in = clone->bi_iter; + } - io->sector = sector; - } + crypt_inc_pending(io); + r = crypt_convert(cc, ctx, + test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true); + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + * (TODO: is it actually possible to be in softirq in the write path?) + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_write_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } + if (r) + io->error = r; + crypt_finished = atomic_dec_and_test(&ctx->cc_pending); + if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) { + /* Wait for completion signaled by kcryptd_async_done() */ + wait_for_completion(&ctx->restart); + crypt_finished = 1; + } - /* - * Out of memory -> run queues - * But don't wait if split was due to the io size restriction - */ - if (unlikely(out_of_pages)) - congestion_wait(BLK_RW_ASYNC, HZ/100); + /* Encryption was already finished, submit io now */ + if (crypt_finished) + kcryptd_crypt_write_io_submit(io, 0); - /* - * With async crypto it is unsafe to share the crypto context - * between fragments, so switch to a new dm_crypt_io structure. - */ - if (unlikely(!crypt_finished && remaining)) { - new_io = crypt_io_alloc(io->cc, io->base_bio, - sector); - crypt_inc_pending(new_io); - crypt_convert_init(cc, &new_io->ctx, NULL, - io->base_bio, sector); - new_io->ctx.idx_in = io->ctx.idx_in; - new_io->ctx.offset_in = io->ctx.offset_in; - - /* - * Fragments after the first use the base_io - * pending count. - */ - if (!io->base_io) - new_io->base_io = io; - else { - new_io->base_io = io->base_io; - crypt_inc_pending(io->base_io); - crypt_dec_pending(io); - } +dec: + crypt_dec_pending(io); +} - io = new_io; +static void kcryptd_crypt_read_done(struct dm_crypt_io *io) +{ + if (io->ctx.aead_recheck) { + if (!io->error) { + io->ctx.bio_in->bi_iter = io->saved_bi_iter; + bio_copy_data(io->base_bio, io->ctx.bio_in); } + crypt_free_buffer_pages(io->cc, io->ctx.bio_in); + bio_put(io->ctx.bio_in); } - crypt_dec_pending(io); } -static void kcryptd_crypt_read_done(struct dm_crypt_io *io) +static void kcryptd_crypt_read_continue(struct work_struct *work) { + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + blk_status_t r; + + wait_for_completion(&io->ctx.restart); + reinit_completion(&io->ctx.restart); + + r = crypt_convert(cc, &io->ctx, false, false); + if (r) + io->error = r; + + if (atomic_dec_and_test(&io->ctx.cc_pending)) + kcryptd_crypt_read_done(io); + crypt_dec_pending(io); } static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; - int r = 0; + blk_status_t r; crypt_inc_pending(io); - crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, - io->sector); + if (io->ctx.aead_recheck) { + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } else { + crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, + io->sector); - r = crypt_convert(cc, &io->ctx); - if (r < 0) - io->error = -EIO; + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_read_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } + if (r) + io->error = r; if (atomic_dec_and_test(&io->ctx.cc_pending)) kcryptd_crypt_read_done(io); @@ -1161,34 +2239,60 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) crypt_dec_pending(io); } -static void kcryptd_async_done(struct crypto_async_request *async_req, - int error) +static void kcryptd_async_done(void *data, int error) { - struct dm_crypt_request *dmreq = async_req->data; + struct dm_crypt_request *dmreq = data; struct convert_context *ctx = dmreq->ctx; struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); struct crypt_config *cc = io->cc; + /* + * A request from crypto driver backlog is going to be processed now, + * finish the completion and continue in crypt_convert(). + * (Callback will be called for the second time for this request.) + */ if (error == -EINPROGRESS) { complete(&ctx->restart); return; } if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post) - error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq); + error = cc->iv_gen_ops->post(cc, org_iv_of_dmreq(cc, dmreq), dmreq); - if (error < 0) - io->error = -EIO; + if (error == -EBADMSG) { + sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)); - mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool); + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } + io->error = BLK_STS_PROTECTION; + } else if (error < 0) + io->error = BLK_STS_IOERR; + + crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio); if (!atomic_dec_and_test(&ctx->cc_pending)) return; - if (bio_data_dir(io->base_bio) == READ) + /* + * The request is fully completed: for inline writes, let + * kcryptd_crypt_write_convert() do the IO submission. + */ + if (bio_data_dir(io->base_bio) == READ) { kcryptd_crypt_read_done(io); - else - kcryptd_crypt_write_io_submit(io, 1); + return; + } + + if (kcryptd_crypt_write_inline(cc, ctx)) { + complete(&ctx->restart); + return; + } + + kcryptd_crypt_write_io_submit(io, 1); } static void kcryptd_crypt(struct work_struct *work) @@ -1205,108 +2309,395 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; + if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) || + (bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) { + /* + * in_hardirq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context. + * irqs_disabled(): the kernel may run some IO completion from the idle thread, but + * it is being executed with irqs disabled. + */ + if (in_hardirq() || irqs_disabled()) { + INIT_WORK(&io->work, kcryptd_crypt); + queue_work(system_bh_wq, &io->work); + return; + } else { + kcryptd_crypt(&io->work); + return; + } + } + INIT_WORK(&io->work, kcryptd_crypt); queue_work(cc->crypt_queue, &io->work); } -/* - * Decode key from its hex representation - */ -static int crypt_decode_key(u8 *key, char *hex, unsigned int size) +static void crypt_free_tfms_aead(struct crypt_config *cc) { - char buffer[3]; - unsigned int i; - - buffer[2] = '\0'; - - for (i = 0; i < size; i++) { - buffer[0] = *hex++; - buffer[1] = *hex++; + if (!cc->cipher_tfm.tfms_aead) + return; - if (kstrtou8(buffer, 16, &key[i])) - return -EINVAL; + if (cc->cipher_tfm.tfms_aead[0] && !IS_ERR(cc->cipher_tfm.tfms_aead[0])) { + crypto_free_aead(cc->cipher_tfm.tfms_aead[0]); + cc->cipher_tfm.tfms_aead[0] = NULL; } - if (*hex != '\0') - return -EINVAL; - - return 0; + kfree(cc->cipher_tfm.tfms_aead); + cc->cipher_tfm.tfms_aead = NULL; } -static void crypt_free_tfms(struct crypt_config *cc) +static void crypt_free_tfms_skcipher(struct crypt_config *cc) { - unsigned i; + unsigned int i; - if (!cc->tfms) + if (!cc->cipher_tfm.tfms) return; for (i = 0; i < cc->tfms_count; i++) - if (cc->tfms[i] && !IS_ERR(cc->tfms[i])) { - crypto_free_ablkcipher(cc->tfms[i]); - cc->tfms[i] = NULL; + if (cc->cipher_tfm.tfms[i] && !IS_ERR(cc->cipher_tfm.tfms[i])) { + crypto_free_skcipher(cc->cipher_tfm.tfms[i]); + cc->cipher_tfm.tfms[i] = NULL; } - kfree(cc->tfms); - cc->tfms = NULL; + kfree(cc->cipher_tfm.tfms); + cc->cipher_tfm.tfms = NULL; } -static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) +static void crypt_free_tfms(struct crypt_config *cc) +{ + if (crypt_integrity_aead(cc)) + crypt_free_tfms_aead(cc); + else + crypt_free_tfms_skcipher(cc); +} + +static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) { - unsigned i; + unsigned int i; int err; - cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_ablkcipher *), - GFP_KERNEL); - if (!cc->tfms) + cc->cipher_tfm.tfms = kcalloc(cc->tfms_count, + sizeof(struct crypto_skcipher *), + GFP_KERNEL); + if (!cc->cipher_tfm.tfms) return -ENOMEM; for (i = 0; i < cc->tfms_count; i++) { - cc->tfms[i] = crypto_alloc_ablkcipher(ciphermode, 0, 0); - if (IS_ERR(cc->tfms[i])) { - err = PTR_ERR(cc->tfms[i]); + cc->cipher_tfm.tfms[i] = crypto_alloc_skcipher(ciphermode, 0, + CRYPTO_ALG_ALLOCATES_MEMORY); + if (IS_ERR(cc->cipher_tfm.tfms[i])) { + err = PTR_ERR(cc->cipher_tfm.tfms[i]); crypt_free_tfms(cc); return err; } } + /* + * dm-crypt performance can vary greatly depending on which crypto + * algorithm implementation is used. Help people debug performance + * problems by logging the ->cra_driver_name. + */ + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, + crypto_skcipher_alg(any_tfm(cc))->base.cra_driver_name); return 0; } -static int crypt_setkey_allcpus(struct crypt_config *cc) +static int crypt_alloc_tfms_aead(struct crypt_config *cc, char *ciphermode) +{ + int err; + + cc->cipher_tfm.tfms = kmalloc(sizeof(struct crypto_aead *), GFP_KERNEL); + if (!cc->cipher_tfm.tfms) + return -ENOMEM; + + cc->cipher_tfm.tfms_aead[0] = crypto_alloc_aead(ciphermode, 0, + CRYPTO_ALG_ALLOCATES_MEMORY); + if (IS_ERR(cc->cipher_tfm.tfms_aead[0])) { + err = PTR_ERR(cc->cipher_tfm.tfms_aead[0]); + crypt_free_tfms(cc); + return err; + } + + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, + crypto_aead_alg(any_tfm_aead(cc))->base.cra_driver_name); + return 0; +} + +static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) +{ + if (crypt_integrity_aead(cc)) + return crypt_alloc_tfms_aead(cc, ciphermode); + else + return crypt_alloc_tfms_skcipher(cc, ciphermode); +} + +static unsigned int crypt_subkey_size(struct crypt_config *cc) +{ + return (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count); +} + +static unsigned int crypt_authenckey_size(struct crypt_config *cc) +{ + return crypt_subkey_size(cc) + RTA_SPACE(sizeof(struct crypto_authenc_key_param)); +} + +/* + * If AEAD is composed like authenc(hmac(sha256),xts(aes)), + * the key must be for some reason in special format. + * This funcion converts cc->key to this special format. + */ +static void crypt_copy_authenckey(char *p, const void *key, + unsigned int enckeylen, unsigned int authkeylen) { - unsigned subkey_size = cc->key_size >> ilog2(cc->tfms_count); + struct crypto_authenc_key_param *param; + struct rtattr *rta; + + rta = (struct rtattr *)p; + param = RTA_DATA(rta); + param->enckeylen = cpu_to_be32(enckeylen); + rta->rta_len = RTA_LENGTH(sizeof(*param)); + rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM; + p += RTA_SPACE(sizeof(*param)); + memcpy(p, key + enckeylen, authkeylen); + p += authkeylen; + memcpy(p, key, enckeylen); +} + +static int crypt_setkey(struct crypt_config *cc) +{ + unsigned int subkey_size; int err = 0, i, r; + /* Ignore extra keys (which are used for IV etc) */ + subkey_size = crypt_subkey_size(cc); + + if (crypt_integrity_hmac(cc)) { + if (subkey_size < cc->key_mac_size) + return -EINVAL; + + crypt_copy_authenckey(cc->authenc_key, cc->key, + subkey_size - cc->key_mac_size, + cc->key_mac_size); + } + for (i = 0; i < cc->tfms_count; i++) { - r = crypto_ablkcipher_setkey(cc->tfms[i], - cc->key + (i * subkey_size), - subkey_size); + if (crypt_integrity_hmac(cc)) + r = crypto_aead_setkey(cc->cipher_tfm.tfms_aead[i], + cc->authenc_key, crypt_authenckey_size(cc)); + else if (crypt_integrity_aead(cc)) + r = crypto_aead_setkey(cc->cipher_tfm.tfms_aead[i], + cc->key + (i * subkey_size), + subkey_size); + else + r = crypto_skcipher_setkey(cc->cipher_tfm.tfms[i], + cc->key + (i * subkey_size), + subkey_size); if (r) err = r; } + if (crypt_integrity_hmac(cc)) + memzero_explicit(cc->authenc_key, crypt_authenckey_size(cc)); + return err; } +#ifdef CONFIG_KEYS + +static bool contains_whitespace(const char *str) +{ + while (*str) + if (isspace(*str++)) + return true; + return false; +} + +static int set_key_user(struct crypt_config *cc, struct key *key) +{ + const struct user_key_payload *ukp; + + ukp = user_key_payload_locked(key); + if (!ukp) + return -EKEYREVOKED; + + if (cc->key_size != ukp->datalen) + return -EINVAL; + + memcpy(cc->key, ukp->data, cc->key_size); + + return 0; +} + +static int set_key_encrypted(struct crypt_config *cc, struct key *key) +{ + const struct encrypted_key_payload *ekp; + + ekp = key->payload.data[0]; + if (!ekp) + return -EKEYREVOKED; + + if (cc->key_size != ekp->decrypted_datalen) + return -EINVAL; + + memcpy(cc->key, ekp->decrypted_data, cc->key_size); + + return 0; +} + +static int set_key_trusted(struct crypt_config *cc, struct key *key) +{ + const struct trusted_key_payload *tkp; + + tkp = key->payload.data[0]; + if (!tkp) + return -EKEYREVOKED; + + if (cc->key_size != tkp->key_len) + return -EINVAL; + + memcpy(cc->key, tkp->key, cc->key_size); + + return 0; +} + +static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string) +{ + char *new_key_string, *key_desc; + int ret; + struct key_type *type; + struct key *key; + int (*set_key)(struct crypt_config *cc, struct key *key); + + /* + * Reject key_string with whitespace. dm core currently lacks code for + * proper whitespace escaping in arguments on DM_TABLE_STATUS path. + */ + if (contains_whitespace(key_string)) { + DMERR("whitespace chars not allowed in key string"); + return -EINVAL; + } + + /* look for next ':' separating key_type from key_description */ + key_desc = strchr(key_string, ':'); + if (!key_desc || key_desc == key_string || !strlen(key_desc + 1)) + return -EINVAL; + + if (!strncmp(key_string, "logon:", key_desc - key_string + 1)) { + type = &key_type_logon; + set_key = set_key_user; + } else if (!strncmp(key_string, "user:", key_desc - key_string + 1)) { + type = &key_type_user; + set_key = set_key_user; + } else if (IS_ENABLED(CONFIG_ENCRYPTED_KEYS) && + !strncmp(key_string, "encrypted:", key_desc - key_string + 1)) { + type = &key_type_encrypted; + set_key = set_key_encrypted; + } else if (IS_ENABLED(CONFIG_TRUSTED_KEYS) && + !strncmp(key_string, "trusted:", key_desc - key_string + 1)) { + type = &key_type_trusted; + set_key = set_key_trusted; + } else { + return -EINVAL; + } + + new_key_string = kstrdup(key_string, GFP_KERNEL); + if (!new_key_string) + return -ENOMEM; + + key = request_key(type, key_desc + 1, NULL); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto free_new_key_string; + } + + down_read(&key->sem); + ret = set_key(cc, key); + up_read(&key->sem); + key_put(key); + if (ret < 0) + goto free_new_key_string; + + /* clear the flag since following operations may invalidate previously valid key */ + clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); + + ret = crypt_setkey(cc); + if (ret) + goto free_new_key_string; + + set_bit(DM_CRYPT_KEY_VALID, &cc->flags); + kfree_sensitive(cc->key_string); + cc->key_string = new_key_string; + return 0; + +free_new_key_string: + kfree_sensitive(new_key_string); + return ret; +} + +static int get_key_size(char **key_string) +{ + char *colon, dummy; + int ret; + + if (*key_string[0] != ':') + return strlen(*key_string) >> 1; + + /* look for next ':' in key string */ + colon = strpbrk(*key_string + 1, ":"); + if (!colon) + return -EINVAL; + + if (sscanf(*key_string + 1, "%u%c", &ret, &dummy) != 2 || dummy != ':') + return -EINVAL; + + *key_string = colon; + + /* remaining key string should be :<logon|user>:<key_desc> */ + + return ret; +} + +#else + +static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string) +{ + return -EINVAL; +} + +static int get_key_size(char **key_string) +{ + return (*key_string[0] == ':') ? -EINVAL : (int)(strlen(*key_string) >> 1); +} + +#endif /* CONFIG_KEYS */ + static int crypt_set_key(struct crypt_config *cc, char *key) { int r = -EINVAL; int key_string_len = strlen(key); - /* The key size may not be changed. */ - if (cc->key_size != (key_string_len >> 1)) - goto out; - /* Hyphen (which gives a key_size of zero) means there is no key. */ if (!cc->key_size && strcmp(key, "-")) goto out; - if (cc->key_size && crypt_decode_key(cc->key, key, cc->key_size) < 0) + /* ':' means the key is in kernel keyring, short-circuit normal key processing */ + if (key[0] == ':') { + r = crypt_set_keyring_key(cc, key + 1); goto out; + } - set_bit(DM_CRYPT_KEY_VALID, &cc->flags); + /* clear the flag since following operations may invalidate previously valid key */ + clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); - r = crypt_setkey_allcpus(cc); + /* wipe references to any kernel keyring key */ + kfree_sensitive(cc->key_string); + cc->key_string = NULL; + + /* Decode key from its hex representation. */ + if (cc->key_size && hex2bin(cc->key, key, cc->key_size) < 0) + goto out; + + r = crypt_setkey(cc); + if (!r) + set_bit(DM_CRYPT_KEY_VALID, &cc->flags); out: /* Hex key string not needed after here, so wipe it. */ @@ -1317,46 +2708,98 @@ out: static int crypt_wipe_key(struct crypt_config *cc) { + int r; + clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); + get_random_bytes(&cc->key, cc->key_size); + + /* Wipe IV private keys */ + if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) { + r = cc->iv_gen_ops->wipe(cc); + if (r) + return r; + } + + kfree_sensitive(cc->key_string); + cc->key_string = NULL; + r = crypt_setkey(cc); memset(&cc->key, 0, cc->key_size * sizeof(u8)); - return crypt_setkey_allcpus(cc); + return r; +} + +static void crypt_calculate_pages_per_client(void) +{ + unsigned long pages = (totalram_pages() - totalhigh_pages()) * DM_CRYPT_MEMORY_PERCENT / 100; + + if (!dm_crypt_clients_n) + return; + + pages /= dm_crypt_clients_n; + if (pages < DM_CRYPT_MIN_PAGES_PER_CLIENT) + pages = DM_CRYPT_MIN_PAGES_PER_CLIENT; + dm_crypt_pages_per_client = pages; +} + +static void *crypt_page_alloc(gfp_t gfp_mask, void *pool_data) +{ + struct crypt_config *cc = pool_data; + struct page *page; + + /* + * Note, percpu_counter_read_positive() may over (and under) estimate + * the current usage by at most (batch - 1) * num_online_cpus() pages, + * but avoids potential spinlock contention of an exact result. + */ + if (unlikely(percpu_counter_read_positive(&cc->n_allocated_pages) >= dm_crypt_pages_per_client) && + likely(gfp_mask & __GFP_NORETRY)) + return NULL; + + page = alloc_page(gfp_mask); + if (likely(page != NULL)) + percpu_counter_add(&cc->n_allocated_pages, 1); + + return page; +} + +static void crypt_page_free(void *page, void *pool_data) +{ + struct crypt_config *cc = pool_data; + + __free_page(page); + percpu_counter_sub(&cc->n_allocated_pages, 1); } static void crypt_dtr(struct dm_target *ti) { struct crypt_config *cc = ti->private; - struct crypt_cpu *cpu_cc; - int cpu; ti->private = NULL; if (!cc) return; + if (cc->write_thread) + kthread_stop(cc->write_thread); + if (cc->io_queue) destroy_workqueue(cc->io_queue); if (cc->crypt_queue) destroy_workqueue(cc->crypt_queue); - if (cc->cpu) - for_each_possible_cpu(cpu) { - cpu_cc = per_cpu_ptr(cc->cpu, cpu); - if (cpu_cc->req) - mempool_free(cpu_cc->req, cc->req_pool); - } + if (cc->workqueue_id) + ida_free(&workqueue_ida, cc->workqueue_id); crypt_free_tfms(cc); - if (cc->bs) - bioset_free(cc->bs); + bioset_exit(&cc->bs); + + mempool_exit(&cc->page_pool); + mempool_exit(&cc->req_pool); + mempool_exit(&cc->tag_pool); - if (cc->page_pool) - mempool_destroy(cc->page_pool); - if (cc->req_pool) - mempool_destroy(cc->req_pool); - if (cc->io_pool) - mempool_destroy(cc->io_pool); + WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0); + percpu_counter_destroy(&cc->n_allocated_pages); if (cc->iv_gen_ops && cc->iv_gen_ops->dtr) cc->iv_gen_ops->dtr(cc); @@ -1364,35 +2807,221 @@ static void crypt_dtr(struct dm_target *ti) if (cc->dev) dm_put_device(ti, cc->dev); - if (cc->cpu) - free_percpu(cc->cpu); + kfree_sensitive(cc->cipher_string); + kfree_sensitive(cc->key_string); + kfree_sensitive(cc->cipher_auth); + kfree_sensitive(cc->authenc_key); - kzfree(cc->cipher); - kzfree(cc->cipher_string); + mutex_destroy(&cc->bio_alloc_lock); /* Must zero key material before freeing */ - kzfree(cc); + kfree_sensitive(cc); + + spin_lock(&dm_crypt_clients_lock); + WARN_ON(!dm_crypt_clients_n); + dm_crypt_clients_n--; + crypt_calculate_pages_per_client(); + spin_unlock(&dm_crypt_clients_lock); + + dm_audit_log_dtr(DM_MSG_PREFIX, ti, 1); +} + +static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode) +{ + struct crypt_config *cc = ti->private; + + if (crypt_integrity_aead(cc)) + cc->iv_size = crypto_aead_ivsize(any_tfm_aead(cc)); + else + cc->iv_size = crypto_skcipher_ivsize(any_tfm(cc)); + + if (cc->iv_size) + /* at least a 64 bit sector number should fit in our buffer */ + cc->iv_size = max(cc->iv_size, + (unsigned int)(sizeof(u64) / sizeof(u8))); + else if (ivmode) { + DMWARN("Selected cipher does not support IVs"); + ivmode = NULL; + } + + /* Choose ivmode, see comments at iv code. */ + if (ivmode == NULL) + cc->iv_gen_ops = NULL; + else if (strcmp(ivmode, "plain") == 0) + cc->iv_gen_ops = &crypt_iv_plain_ops; + else if (strcmp(ivmode, "plain64") == 0) + cc->iv_gen_ops = &crypt_iv_plain64_ops; + else if (strcmp(ivmode, "plain64be") == 0) + cc->iv_gen_ops = &crypt_iv_plain64be_ops; + else if (strcmp(ivmode, "essiv") == 0) + cc->iv_gen_ops = &crypt_iv_essiv_ops; + else if (strcmp(ivmode, "benbi") == 0) + cc->iv_gen_ops = &crypt_iv_benbi_ops; + else if (strcmp(ivmode, "null") == 0) + cc->iv_gen_ops = &crypt_iv_null_ops; + else if (strcmp(ivmode, "eboiv") == 0) + cc->iv_gen_ops = &crypt_iv_eboiv_ops; + else if (strcmp(ivmode, "elephant") == 0) { + cc->iv_gen_ops = &crypt_iv_elephant_ops; + cc->key_parts = 2; + cc->key_extra_size = cc->key_size / 2; + if (cc->key_extra_size > ELEPHANT_MAX_KEY_SIZE) + return -EINVAL; + set_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags); + } else if (strcmp(ivmode, "lmk") == 0) { + cc->iv_gen_ops = &crypt_iv_lmk_ops; + /* + * Version 2 and 3 is recognised according + * to length of provided multi-key string. + * If present (version 3), last key is used as IV seed. + * All keys (including IV seed) are always the same size. + */ + if (cc->key_size % cc->key_parts) { + cc->key_parts++; + cc->key_extra_size = cc->key_size / cc->key_parts; + } + } else if (strcmp(ivmode, "tcw") == 0) { + cc->iv_gen_ops = &crypt_iv_tcw_ops; + cc->key_parts += 2; /* IV + whitening */ + cc->key_extra_size = cc->iv_size + TCW_WHITENING_SIZE; + } else if (strcmp(ivmode, "random") == 0) { + cc->iv_gen_ops = &crypt_iv_random_ops; + /* Need storage space in integrity fields. */ + cc->integrity_iv_size = cc->iv_size; + } else { + ti->error = "Invalid IV mode"; + return -EINVAL; + } + + return 0; } -static int crypt_ctr_cipher(struct dm_target *ti, - char *cipher_in, char *key) +/* + * Workaround to parse HMAC algorithm from AEAD crypto API spec. + * The HMAC is needed to calculate tag size (HMAC digest size). + * This should be probably done by crypto-api calls (once available...) + */ +static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api) +{ + char *start, *end, *mac_alg = NULL; + struct crypto_ahash *mac; + + if (!strstarts(cipher_api, "authenc(")) + return 0; + + start = strchr(cipher_api, '('); + end = strchr(cipher_api, ','); + if (!start || !end || ++start > end) + return -EINVAL; + + mac_alg = kmemdup_nul(start, end - start, GFP_KERNEL); + if (!mac_alg) + return -ENOMEM; + + mac = crypto_alloc_ahash(mac_alg, 0, CRYPTO_ALG_ALLOCATES_MEMORY); + kfree(mac_alg); + + if (IS_ERR(mac)) + return PTR_ERR(mac); + + if (!test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags)) + cc->key_mac_size = crypto_ahash_digestsize(mac); + crypto_free_ahash(mac); + + cc->authenc_key = kmalloc(crypt_authenckey_size(cc), GFP_KERNEL); + if (!cc->authenc_key) + return -ENOMEM; + + return 0; +} + +static int crypt_ctr_cipher_new(struct dm_target *ti, char *cipher_in, char *key, + char **ivmode, char **ivopts) { struct crypt_config *cc = ti->private; - char *tmp, *cipher, *chainmode, *ivmode, *ivopts, *keycount; + char *tmp, *cipher_api, buf[CRYPTO_MAX_ALG_NAME]; + int ret = -EINVAL; + + cc->tfms_count = 1; + + /* + * New format (capi: prefix) + * capi:cipher_api_spec-iv:ivopts + */ + tmp = &cipher_in[strlen("capi:")]; + + /* Separate IV options if present, it can contain another '-' in hash name */ + *ivopts = strrchr(tmp, ':'); + if (*ivopts) { + **ivopts = '\0'; + (*ivopts)++; + } + /* Parse IV mode */ + *ivmode = strrchr(tmp, '-'); + if (*ivmode) { + **ivmode = '\0'; + (*ivmode)++; + } + /* The rest is crypto API spec */ + cipher_api = tmp; + + /* Alloc AEAD, can be used only in new format. */ + if (crypt_integrity_aead(cc)) { + ret = crypt_ctr_auth_cipher(cc, cipher_api); + if (ret < 0) { + ti->error = "Invalid AEAD cipher spec"; + return ret; + } + } + + if (*ivmode && !strcmp(*ivmode, "lmk")) + cc->tfms_count = 64; + + if (*ivmode && !strcmp(*ivmode, "essiv")) { + if (!*ivopts) { + ti->error = "Digest algorithm missing for ESSIV mode"; + return -EINVAL; + } + ret = snprintf(buf, CRYPTO_MAX_ALG_NAME, "essiv(%s,%s)", + cipher_api, *ivopts); + if (ret < 0 || ret >= CRYPTO_MAX_ALG_NAME) { + ti->error = "Cannot allocate cipher string"; + return -ENOMEM; + } + cipher_api = buf; + } + + cc->key_parts = cc->tfms_count; + + /* Allocate cipher */ + ret = crypt_alloc_tfms(cc, cipher_api); + if (ret < 0) { + ti->error = "Error allocating crypto tfm"; + return ret; + } + + if (crypt_integrity_aead(cc)) + cc->iv_size = crypto_aead_ivsize(any_tfm_aead(cc)); + else + cc->iv_size = crypto_skcipher_ivsize(any_tfm(cc)); + + return 0; +} + +static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key, + char **ivmode, char **ivopts) +{ + struct crypt_config *cc = ti->private; + char *tmp, *cipher, *chainmode, *keycount; char *cipher_api = NULL; int ret = -EINVAL; char dummy; - /* Convert to crypto api definition? */ - if (strchr(cipher_in, '(')) { + if (strchr(cipher_in, '(') || crypt_integrity_aead(cc)) { ti->error = "Bad cipher specification"; return -EINVAL; } - cc->cipher_string = kstrdup(cipher_in, GFP_KERNEL); - if (!cc->cipher_string) - goto bad_mem; - /* * Legacy dm-crypt cipher specification * cipher[:keycount]-mode-iv:ivopts @@ -1410,34 +3039,20 @@ static int crypt_ctr_cipher(struct dm_target *ti, } cc->key_parts = cc->tfms_count; - cc->cipher = kstrdup(cipher, GFP_KERNEL); - if (!cc->cipher) - goto bad_mem; - chainmode = strsep(&tmp, "-"); - ivopts = strsep(&tmp, "-"); - ivmode = strsep(&ivopts, ":"); - - if (tmp) - DMWARN("Ignoring unexpected additional cipher options"); - - cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)), - __alignof__(struct crypt_cpu)); - if (!cc->cpu) { - ti->error = "Cannot allocate per cpu state"; - goto bad_mem; - } + *ivmode = strsep(&tmp, ":"); + *ivopts = tmp; /* * For compatibility with the original dm-crypt mapping format, if * only the cipher name is supplied, use cbc-plain. */ - if (!chainmode || (!strcmp(chainmode, "plain") && !ivmode)) { + if (!chainmode || (!strcmp(chainmode, "plain") && !*ivmode)) { chainmode = "cbc"; - ivmode = "plain"; + *ivmode = "plain"; } - if (strcmp(chainmode, "ecb") && !ivmode) { + if (strcmp(chainmode, "ecb") && !*ivmode) { ti->error = "IV mechanism required"; return -EINVAL; } @@ -1446,9 +3061,19 @@ static int crypt_ctr_cipher(struct dm_target *ti, if (!cipher_api) goto bad_mem; - ret = snprintf(cipher_api, CRYPTO_MAX_ALG_NAME, - "%s(%s)", chainmode, cipher); - if (ret < 0) { + if (*ivmode && !strcmp(*ivmode, "essiv")) { + if (!*ivopts) { + ti->error = "Digest algorithm missing for ESSIV mode"; + kfree(cipher_api); + return -EINVAL; + } + ret = snprintf(cipher_api, CRYPTO_MAX_ALG_NAME, + "essiv(%s(%s),%s)", chainmode, cipher, *ivopts); + } else { + ret = snprintf(cipher_api, CRYPTO_MAX_ALG_NAME, + "%s(%s)", chainmode, cipher); + } + if (ret < 0 || ret >= CRYPTO_MAX_ALG_NAME) { kfree(cipher_api); goto bad_mem; } @@ -1457,52 +3082,46 @@ static int crypt_ctr_cipher(struct dm_target *ti, ret = crypt_alloc_tfms(cc, cipher_api); if (ret < 0) { ti->error = "Error allocating crypto tfm"; - goto bad; + kfree(cipher_api); + return ret; } + kfree(cipher_api); - /* Initialize and set key */ - ret = crypt_set_key(cc, key); - if (ret < 0) { - ti->error = "Error decoding and setting key"; - goto bad; + return 0; +bad_mem: + ti->error = "Cannot allocate cipher strings"; + return -ENOMEM; +} + +static int crypt_ctr_cipher(struct dm_target *ti, char *cipher_in, char *key) +{ + struct crypt_config *cc = ti->private; + char *ivmode = NULL, *ivopts = NULL; + int ret; + + cc->cipher_string = kstrdup(cipher_in, GFP_KERNEL); + if (!cc->cipher_string) { + ti->error = "Cannot allocate cipher strings"; + return -ENOMEM; } + if (strstarts(cipher_in, "capi:")) + ret = crypt_ctr_cipher_new(ti, cipher_in, key, &ivmode, &ivopts); + else + ret = crypt_ctr_cipher_old(ti, cipher_in, key, &ivmode, &ivopts); + if (ret) + return ret; + /* Initialize IV */ - cc->iv_size = crypto_ablkcipher_ivsize(any_tfm(cc)); - if (cc->iv_size) - /* at least a 64 bit sector number should fit in our buffer */ - cc->iv_size = max(cc->iv_size, - (unsigned int)(sizeof(u64) / sizeof(u8))); - else if (ivmode) { - DMWARN("Selected cipher does not support IVs"); - ivmode = NULL; - } + ret = crypt_ctr_ivmode(ti, ivmode); + if (ret < 0) + return ret; - /* Choose ivmode, see comments at iv code. */ - if (ivmode == NULL) - cc->iv_gen_ops = NULL; - else if (strcmp(ivmode, "plain") == 0) - cc->iv_gen_ops = &crypt_iv_plain_ops; - else if (strcmp(ivmode, "plain64") == 0) - cc->iv_gen_ops = &crypt_iv_plain64_ops; - else if (strcmp(ivmode, "essiv") == 0) - cc->iv_gen_ops = &crypt_iv_essiv_ops; - else if (strcmp(ivmode, "benbi") == 0) - cc->iv_gen_ops = &crypt_iv_benbi_ops; - else if (strcmp(ivmode, "null") == 0) - cc->iv_gen_ops = &crypt_iv_null_ops; - else if (strcmp(ivmode, "lmk") == 0) { - cc->iv_gen_ops = &crypt_iv_lmk_ops; - /* Version 2 and 3 is recognised according - * to length of provided multi-key string. - * If present (version 3), last key is used as IV seed. - */ - if (cc->key_size % cc->key_parts) - cc->key_parts++; - } else { - ret = -EINVAL; - ti->error = "Invalid IV mode"; - goto bad; + /* Initialize and set key */ + ret = crypt_set_key(cc, key); + if (ret < 0) { + ti->error = "Error decoding and setting key"; + return ret; } /* Allocate IV */ @@ -1510,7 +3129,7 @@ static int crypt_ctr_cipher(struct dm_target *ti, ret = cc->iv_gen_ops->ctr(cc, ti, ivopts); if (ret < 0) { ti->error = "Error creating IV"; - goto bad; + return ret; } } @@ -1519,157 +3138,355 @@ static int crypt_ctr_cipher(struct dm_target *ti, ret = cc->iv_gen_ops->init(cc); if (ret < 0) { ti->error = "Error initialising IV"; - goto bad; + return ret; } } - ret = 0; -bad: - kfree(cipher_api); + /* wipe the kernel key payload copy */ + if (cc->key_string) + memset(cc->key, 0, cc->key_size * sizeof(u8)); + return ret; +} -bad_mem: - ti->error = "Cannot allocate cipher strings"; - return -ENOMEM; +static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **argv) +{ + struct crypt_config *cc = ti->private; + struct dm_arg_set as; + static const struct dm_arg _args[] = { + {0, 9, "Invalid number of feature args"}, + }; + unsigned int opt_params, val; + const char *opt_string, *sval; + char dummy; + int ret; + + /* Optional parameters */ + as.argc = argc; + as.argv = argv; + + ret = dm_read_arg_group(_args, &as, &opt_params, &ti->error); + if (ret) + return ret; + + while (opt_params--) { + opt_string = dm_shift_arg(&as); + if (!opt_string) { + ti->error = "Not enough feature arguments"; + return -EINVAL; + } + + if (!strcasecmp(opt_string, "allow_discards")) + ti->num_discard_bios = 1; + + else if (!strcasecmp(opt_string, "same_cpu_crypt")) + set_bit(DM_CRYPT_SAME_CPU, &cc->flags); + else if (!strcasecmp(opt_string, "high_priority")) + set_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags); + + else if (!strcasecmp(opt_string, "submit_from_crypt_cpus")) + set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags); + else if (!strcasecmp(opt_string, "no_read_workqueue")) + set_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags); + else if (!strcasecmp(opt_string, "no_write_workqueue")) + set_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); + else if (sscanf(opt_string, "integrity:%u:", &val) == 1) { + if (val == 0 || val > MAX_TAG_SIZE) { + ti->error = "Invalid integrity arguments"; + return -EINVAL; + } + cc->used_tag_size = val; + sval = strchr(opt_string + strlen("integrity:"), ':') + 1; + if (!strcasecmp(sval, "aead")) { + set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags); + } else if (strcasecmp(sval, "none")) { + ti->error = "Unknown integrity profile"; + return -EINVAL; + } + + cc->cipher_auth = kstrdup(sval, GFP_KERNEL); + if (!cc->cipher_auth) + return -ENOMEM; + } else if (sscanf(opt_string, "integrity_key_size:%u%c", &val, &dummy) == 1) { + if (!val) { + ti->error = "Invalid integrity_key_size argument"; + return -EINVAL; + } + cc->key_mac_size = val; + set_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags); + } else if (sscanf(opt_string, "sector_size:%hu%c", &cc->sector_size, &dummy) == 1) { + if (cc->sector_size < (1 << SECTOR_SHIFT) || + cc->sector_size > 4096 || + (cc->sector_size & (cc->sector_size - 1))) { + ti->error = "Invalid feature value for sector_size"; + return -EINVAL; + } + if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) { + ti->error = "Device size is not multiple of sector_size feature"; + return -EINVAL; + } + cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT; + } else if (!strcasecmp(opt_string, "iv_large_sectors")) + set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); + else { + ti->error = "Invalid feature arguments"; + return -EINVAL; + } + } + + return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int crypt_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) +{ + struct crypt_config *cc = ti->private; + + return dm_report_zones(cc->dev->bdev, cc->start, + cc->start + dm_target_offset(ti, args->next_sector), + args, nr_zones); +} +#else +#define crypt_report_zones NULL +#endif + /* * Construct an encryption mapping: - * <cipher> <key> <iv_offset> <dev_path> <start> + * <cipher> [<key>|:<key_size>:<user|logon>:<key_description>] <iv_offset> <dev_path> <start> */ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct crypt_config *cc; - unsigned int key_size, opt_params; + const char *devname = dm_table_device_name(ti->table); + int key_size, wq_id; + unsigned int align_mask; + unsigned int common_wq_flags; unsigned long long tmpll; int ret; - struct dm_arg_set as; - const char *opt_string; + size_t iv_size_padding, additional_req_size; char dummy; - static struct dm_arg _args[] = { - {0, 1, "Invalid number of feature args"}, - }; - if (argc < 5) { ti->error = "Not enough arguments"; return -EINVAL; } - key_size = strlen(argv[1]) >> 1; + key_size = get_key_size(&argv[1]); + if (key_size < 0) { + ti->error = "Cannot parse key size"; + return -EINVAL; + } - cc = kzalloc(sizeof(*cc) + key_size * sizeof(u8), GFP_KERNEL); + cc = kzalloc(struct_size(cc, key, key_size), GFP_KERNEL); if (!cc) { ti->error = "Cannot allocate encryption context"; return -ENOMEM; } cc->key_size = key_size; + cc->sector_size = (1 << SECTOR_SHIFT); + cc->sector_shift = 0; ti->private = cc; - ret = crypt_ctr_cipher(ti, argv[0], argv[1]); + + spin_lock(&dm_crypt_clients_lock); + dm_crypt_clients_n++; + crypt_calculate_pages_per_client(); + spin_unlock(&dm_crypt_clients_lock); + + ret = percpu_counter_init(&cc->n_allocated_pages, 0, GFP_KERNEL); if (ret < 0) goto bad; - ret = -ENOMEM; - cc->io_pool = mempool_create_slab_pool(MIN_IOS, _crypt_io_pool); - if (!cc->io_pool) { - ti->error = "Cannot allocate crypt io mempool"; + /* Optional parameters need to be read before cipher constructor */ + if (argc > 5) { + ret = crypt_ctr_optional(ti, argc - 5, &argv[5]); + if (ret) + goto bad; + } + + ret = crypt_ctr_cipher(ti, argv[0], argv[1]); + if (ret < 0) goto bad; + + if (crypt_integrity_aead(cc)) { + cc->dmreq_start = sizeof(struct aead_request); + cc->dmreq_start += crypto_aead_reqsize(any_tfm_aead(cc)); + align_mask = crypto_aead_alignmask(any_tfm_aead(cc)); + } else { + cc->dmreq_start = sizeof(struct skcipher_request); + cc->dmreq_start += crypto_skcipher_reqsize(any_tfm(cc)); + align_mask = crypto_skcipher_alignmask(any_tfm(cc)); } + cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request)); - cc->dmreq_start = sizeof(struct ablkcipher_request); - cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc)); - cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment()); - cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) & - ~(crypto_tfm_ctx_alignment() - 1); + if (align_mask < CRYPTO_MINALIGN) { + /* Allocate the padding exactly */ + iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request)) + & align_mask; + } else { + /* + * If the cipher requires greater alignment than kmalloc + * alignment, we don't know the exact position of the + * initialization vector. We must assume worst case. + */ + iv_size_padding = align_mask; + } + + /* ...| IV + padding | original IV | original sec. number | bio tag offset | */ + additional_req_size = sizeof(struct dm_crypt_request) + + iv_size_padding + cc->iv_size + + cc->iv_size + + sizeof(uint64_t) + + sizeof(unsigned int); - cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + - sizeof(struct dm_crypt_request) + cc->iv_size); - if (!cc->req_pool) { + ret = mempool_init_kmalloc_pool(&cc->req_pool, MIN_IOS, cc->dmreq_start + additional_req_size); + if (ret) { ti->error = "Cannot allocate crypt request mempool"; goto bad; } - cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0); - if (!cc->page_pool) { + cc->per_bio_data_size = ti->per_io_data_size = + ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size, + ARCH_DMA_MINALIGN); + + ret = mempool_init(&cc->page_pool, BIO_MAX_VECS, crypt_page_alloc, crypt_page_free, cc); + if (ret) { ti->error = "Cannot allocate page mempool"; goto bad; } - cc->bs = bioset_create(MIN_IOS, 0); - if (!cc->bs) { + ret = bioset_init(&cc->bs, MIN_IOS, 0, BIOSET_NEED_BVECS); + if (ret) { ti->error = "Cannot allocate crypt bioset"; goto bad; } + mutex_init(&cc->bio_alloc_lock); + ret = -EINVAL; - if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) { + if ((sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) || + (tmpll & ((cc->sector_size >> SECTOR_SHIFT) - 1))) { ti->error = "Invalid iv_offset sector"; goto bad; } cc->iv_offset = tmpll; - if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev)) { + ret = dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev); + if (ret) { ti->error = "Device lookup failed"; goto bad; } - if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) { + ret = -EINVAL; + if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1 || tmpll != (sector_t)tmpll) { ti->error = "Invalid device sector"; goto bad; } cc->start = tmpll; - argv += 5; - argc -= 5; + if (bdev_is_zoned(cc->dev->bdev)) { + /* + * For zoned block devices, we need to preserve the issuer write + * ordering. To do so, disable write workqueues and force inline + * encryption completion. + */ + set_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); + set_bit(DM_CRYPT_WRITE_INLINE, &cc->flags); - /* Optional parameters */ - if (argc) { - as.argc = argc; - as.argv = argv; + /* + * All zone append writes to a zone of a zoned block device will + * have the same BIO sector, the start of the zone. When the + * cypher IV mode uses sector values, all data targeting a + * zone will be encrypted using the first sector numbers of the + * zone. This will not result in write errors but will + * cause most reads to fail as reads will use the sector values + * for the actual data locations, resulting in IV mismatch. + * To avoid this problem, ask DM core to emulate zone append + * operations with regular writes. + */ + DMDEBUG("Zone append operations will be emulated"); + ti->emulate_zone_append = true; + } - ret = dm_read_arg_group(_args, &as, &opt_params, &ti->error); + if (crypt_integrity_aead(cc) || cc->integrity_iv_size) { + ret = crypt_integrity_ctr(cc, ti); if (ret) goto bad; - opt_string = dm_shift_arg(&as); + cc->tag_pool_max_sectors = POOL_ENTRY_SIZE / cc->tuple_size; + if (!cc->tag_pool_max_sectors) + cc->tag_pool_max_sectors = 1; - if (opt_params == 1 && opt_string && - !strcasecmp(opt_string, "allow_discards")) - ti->num_discard_bios = 1; - else if (opt_params) { - ret = -EINVAL; - ti->error = "Invalid feature arguments"; + ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS, + cc->tag_pool_max_sectors * cc->tuple_size); + if (ret) { + ti->error = "Cannot allocate integrity tags mempool"; goto bad; } + + cc->tag_pool_max_sectors <<= cc->sector_shift; } + wq_id = ida_alloc_min(&workqueue_ida, 1, GFP_KERNEL); + if (wq_id < 0) { + ti->error = "Couldn't get workqueue id"; + ret = wq_id; + goto bad; + } + cc->workqueue_id = wq_id; + ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io", - WQ_NON_REENTRANT| - WQ_MEM_RECLAIM, - 1); + common_wq_flags = WQ_MEM_RECLAIM | WQ_SYSFS; + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + common_wq_flags |= WQ_HIGHPRI; + + cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", common_wq_flags, 1, devname, wq_id); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } - cc->crypt_queue = alloc_workqueue("kcryptd", - WQ_NON_REENTRANT| - WQ_CPU_INTENSIVE| - WQ_MEM_RECLAIM, - 1); + if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) { + cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d", + common_wq_flags | WQ_CPU_INTENSIVE, + 1, devname, wq_id); + } else { + /* + * While crypt_queue is certainly CPU intensive, the use of + * WQ_CPU_INTENSIVE is meaningless with WQ_UNBOUND. + */ + cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d", + common_wq_flags | WQ_UNBOUND, + num_online_cpus(), devname, wq_id); + } if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; goto bad; } + spin_lock_init(&cc->write_thread_lock); + cc->write_tree = RB_ROOT; + + cc->write_thread = kthread_run(dmcrypt_write, cc, "dmcrypt_write/%s", devname); + if (IS_ERR(cc->write_thread)) { + ret = PTR_ERR(cc->write_thread); + cc->write_thread = NULL; + ti->error = "Couldn't spawn write thread"; + goto bad; + } + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + set_user_nice(cc->write_thread, MIN_NICE); + ti->num_flush_bios = 1; - ti->discard_zeroes_data_unsupported = true; + ti->limit_swap_bios = true; + ti->accounts_remapped_io = true; + dm_audit_log_ctr(DM_MSG_PREFIX, ti, 1); return 0; bad: + dm_audit_log_ctr(DM_MSG_PREFIX, ti, 0); crypt_dtr(ti); return ret; } @@ -1678,35 +3495,83 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) { struct dm_crypt_io *io; struct crypt_config *cc = ti->private; + unsigned max_sectors; /* - * If bio is REQ_FLUSH or REQ_DISCARD, just bypass crypt queues. - * - for REQ_FLUSH device-mapper core ensures that no IO is in-flight - * - for REQ_DISCARD caller must use flush if IO ordering matters + * If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues. + * - for REQ_PREFLUSH device-mapper core ensures that no IO is in-flight + * - for REQ_OP_DISCARD caller must use flush if IO ordering matters */ - if (unlikely(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) { - bio->bi_bdev = cc->dev->bdev; + if (unlikely(bio->bi_opf & REQ_PREFLUSH || + bio_op(bio) == REQ_OP_DISCARD)) { + bio_set_dev(bio, cc->dev->bdev); if (bio_sectors(bio)) - bio->bi_sector = cc->start + dm_target_offset(ti, bio->bi_sector); + bio->bi_iter.bi_sector = cc->start + + dm_target_offset(ti, bio->bi_iter.bi_sector); return DM_MAPIO_REMAPPED; } - io = crypt_io_alloc(cc, bio, dm_target_offset(ti, bio->bi_sector)); + /* + * Check if bio is too large, split as needed. + */ + max_sectors = get_max_request_sectors(ti, bio); + if (unlikely(bio_sectors(bio) > max_sectors)) + dm_accept_partial_bio(bio, max_sectors); + + /* + * Ensure that bio is a multiple of internal sector encryption size + * and is aligned to this size as defined in IO hints. + */ + if (unlikely((bio->bi_iter.bi_sector & ((cc->sector_size >> SECTOR_SHIFT) - 1)) != 0)) + return DM_MAPIO_KILL; + + if (unlikely(bio->bi_iter.bi_size & (cc->sector_size - 1))) + return DM_MAPIO_KILL; + + io = dm_per_bio_data(bio, cc->per_bio_data_size); + crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector)); + + if (cc->tuple_size) { + unsigned int tag_len = cc->tuple_size * (bio_sectors(bio) >> cc->sector_shift); + + if (unlikely(tag_len > KMALLOC_MAX_SIZE)) + io->integrity_metadata = NULL; + else + io->integrity_metadata = kmalloc(tag_len, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + + if (unlikely(!io->integrity_metadata)) { + if (bio_sectors(bio) > cc->tag_pool_max_sectors) + dm_accept_partial_bio(bio, cc->tag_pool_max_sectors); + io->integrity_metadata = mempool_alloc(&cc->tag_pool, GFP_NOIO); + io->integrity_metadata_from_pool = true; + } + } + + if (crypt_integrity_aead(cc)) + io->ctx.r.req_aead = (struct aead_request *)(io + 1); + else + io->ctx.r.req = (struct skcipher_request *)(io + 1); if (bio_data_dir(io->base_bio) == READ) { - if (kcryptd_io_read(io, GFP_NOWAIT)) - kcryptd_queue_io(io); + if (kcryptd_io_read(io, CRYPT_MAP_READ_GFP)) + kcryptd_queue_read(io); } else kcryptd_queue_crypt(io); return DM_MAPIO_SUBMITTED; } +static char hex2asc(unsigned char c) +{ + return c + '0' + ((unsigned int)(9 - c) >> 4 & 0x27); +} + static void crypt_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) + unsigned int status_flags, char *result, unsigned int maxlen) { struct crypt_config *cc = ti->private; - unsigned i, sz = 0; + unsigned int i, sz = 0; + int num_feature_args = 0; switch (type) { case STATUSTYPE_INFO: @@ -1716,18 +3581,83 @@ static void crypt_status(struct dm_target *ti, status_type_t type, case STATUSTYPE_TABLE: DMEMIT("%s ", cc->cipher_string); - if (cc->key_size > 0) - for (i = 0; i < cc->key_size; i++) - DMEMIT("%02x", cc->key[i]); - else + if (cc->key_size > 0) { + if (cc->key_string) + DMEMIT(":%u:%s", cc->key_size, cc->key_string); + else { + for (i = 0; i < cc->key_size; i++) { + DMEMIT("%c%c", hex2asc(cc->key[i] >> 4), + hex2asc(cc->key[i] & 0xf)); + } + } + } else DMEMIT("-"); DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset, cc->dev->name, (unsigned long long)cc->start); - if (ti->num_discard_bios) - DMEMIT(" 1 allow_discards"); + num_feature_args += !!ti->num_discard_bios; + num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags); + num_feature_args += test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags); + num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags); + num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags); + num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); + num_feature_args += !!cc->used_tag_size; + num_feature_args += cc->sector_size != (1 << SECTOR_SHIFT); + num_feature_args += test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); + num_feature_args += test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags); + if (num_feature_args) { + DMEMIT(" %d", num_feature_args); + if (ti->num_discard_bios) + DMEMIT(" allow_discards"); + if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) + DMEMIT(" same_cpu_crypt"); + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + DMEMIT(" high_priority"); + if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) + DMEMIT(" submit_from_crypt_cpus"); + if (test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) + DMEMIT(" no_read_workqueue"); + if (test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) + DMEMIT(" no_write_workqueue"); + if (cc->used_tag_size) + DMEMIT(" integrity:%u:%s", cc->used_tag_size, cc->cipher_auth); + if (cc->sector_size != (1 << SECTOR_SHIFT)) + DMEMIT(" sector_size:%d", cc->sector_size); + if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags)) + DMEMIT(" iv_large_sectors"); + if (test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags)) + DMEMIT(" integrity_key_size:%u", cc->key_mac_size); + } + break; + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",allow_discards=%c", ti->num_discard_bios ? 'y' : 'n'); + DMEMIT(",same_cpu_crypt=%c", test_bit(DM_CRYPT_SAME_CPU, &cc->flags) ? 'y' : 'n'); + DMEMIT(",high_priority=%c", test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags) ? 'y' : 'n'); + DMEMIT(",submit_from_crypt_cpus=%c", test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",no_read_workqueue=%c", test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",no_write_workqueue=%c", test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",iv_large_sectors=%c", test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags) ? + 'y' : 'n'); + + if (cc->used_tag_size) + DMEMIT(",integrity_tag_size=%u,cipher_auth=%s", + cc->used_tag_size, cc->cipher_auth); + if (cc->sector_size != (1 << SECTOR_SHIFT)) + DMEMIT(",sector_size=%d", cc->sector_size); + if (cc->cipher_string) + DMEMIT(",cipher_string=%s", cc->cipher_string); + + DMEMIT(",key_size=%u", cc->key_size); + DMEMIT(",key_parts=%u", cc->key_parts); + DMEMIT(",key_extra_size=%u", cc->key_extra_size); + DMEMIT(",key_mac_size=%u", cc->key_mac_size); + DMEMIT(";"); break; } } @@ -1762,10 +3692,11 @@ static void crypt_resume(struct dm_target *ti) * key set <key> * key wipe */ -static int crypt_message(struct dm_target *ti, unsigned argc, char **argv) +static int crypt_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) { struct crypt_config *cc = ti->private; - int ret = -EINVAL; + int key_size, ret = -EINVAL; if (argc < 2) goto error; @@ -1776,21 +3707,25 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv) return -EINVAL; } if (argc == 3 && !strcasecmp(argv[1], "set")) { + /* The key size may not be changed. */ + key_size = get_key_size(&argv[2]); + if (key_size < 0 || cc->key_size != key_size) { + memset(argv[2], '0', strlen(argv[2])); + return -EINVAL; + } + ret = crypt_set_key(cc, argv[2]); if (ret) return ret; if (cc->iv_gen_ops && cc->iv_gen_ops->init) ret = cc->iv_gen_ops->init(cc); + /* wipe the kernel key payload copy */ + if (cc->key_string) + memset(cc->key, 0, cc->key_size * sizeof(u8)); return ret; } - if (argc == 2 && !strcasecmp(argv[1], "wipe")) { - if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) { - ret = cc->iv_gen_ops->wipe(cc); - if (ret) - return ret; - } + if (argc == 2 && !strcasecmp(argv[1], "wipe")) return crypt_wipe_key(cc); - } } error: @@ -1798,71 +3733,56 @@ error: return -EINVAL; } -static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm, - struct bio_vec *biovec, int max_size) +static int crypt_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) { struct crypt_config *cc = ti->private; - struct request_queue *q = bdev_get_queue(cc->dev->bdev); - - if (!q->merge_bvec_fn) - return max_size; - bvm->bi_bdev = cc->dev->bdev; - bvm->bi_sector = cc->start + dm_target_offset(ti, bvm->bi_sector); - - return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); + return fn(ti, cc->dev, cc->start, ti->len, data); } -static int crypt_iterate_devices(struct dm_target *ti, - iterate_devices_callout_fn fn, void *data) +static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct crypt_config *cc = ti->private; - return fn(ti, cc->dev, cc->start, ti->len, data); + limits->logical_block_size = + max_t(unsigned int, limits->logical_block_size, cc->sector_size); + limits->physical_block_size = + max_t(unsigned int, limits->physical_block_size, cc->sector_size); + limits->io_min = max_t(unsigned int, limits->io_min, cc->sector_size); + limits->dma_alignment = limits->logical_block_size - 1; + + /* + * For zoned dm-crypt targets, there will be no internal splitting of + * write BIOs to avoid exceeding BIO_MAX_VECS vectors per BIO. But + * without respecting this limit, crypt_alloc_buffer() will trigger a + * BUG(). Avoid this by forcing DM core to split write BIOs to this + * limit. + */ + if (ti->emulate_zone_append) + limits->max_hw_sectors = min(limits->max_hw_sectors, + BIO_MAX_VECS << PAGE_SECTORS_SHIFT); } static struct target_type crypt_target = { .name = "crypt", - .version = {1, 12, 1}, + .version = {1, 28, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, + .features = DM_TARGET_ZONED_HM, + .report_zones = crypt_report_zones, .map = crypt_map, .status = crypt_status, .postsuspend = crypt_postsuspend, .preresume = crypt_preresume, .resume = crypt_resume, .message = crypt_message, - .merge = crypt_merge, .iterate_devices = crypt_iterate_devices, + .io_hints = crypt_io_hints, }; +module_dm(crypt); -static int __init dm_crypt_init(void) -{ - int r; - - _crypt_io_pool = KMEM_CACHE(dm_crypt_io, 0); - if (!_crypt_io_pool) - return -ENOMEM; - - r = dm_register_target(&crypt_target); - if (r < 0) { - DMERR("register failed %d", r); - kmem_cache_destroy(_crypt_io_pool); - } - - return r; -} - -static void __exit dm_crypt_exit(void) -{ - dm_unregister_target(&crypt_target); - kmem_cache_destroy(_crypt_io_pool); -} - -module_init(dm_crypt_init); -module_exit(dm_crypt_exit); - -MODULE_AUTHOR("Christophe Saout <christophe@saout.de>"); +MODULE_AUTHOR("Jana Saout <jana@saout.de>"); MODULE_DESCRIPTION(DM_NAME " target for transparent encryption / decryption"); MODULE_LICENSE("GPL"); |