diff options
Diffstat (limited to 'drivers/md/dm-crypt.c')
| -rw-r--r-- | drivers/md/dm-crypt.c | 1804 |
1 files changed, 1235 insertions, 569 deletions
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 0ff22159a0ca..5ef43231fe77 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1,8 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2003 Jana Saout <jana@saout.de> * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> - * Copyright (C) 2006-2017 Red Hat, Inc. All rights reserved. - * Copyright (C) 2013-2017 Milan Broz <gmazyland@gmail.com> + * 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. */ @@ -15,6 +16,8 @@ #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> @@ -26,35 +29,45 @@ #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 bio *bio_out; struct bvec_iter iter_in; + struct bio *bio_out; struct bvec_iter iter_out; - u64 cc_sector; 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; }; @@ -65,7 +78,8 @@ struct dm_crypt_io { struct crypt_config *cc; struct bio *base_bio; u8 *integrity_metadata; - bool integrity_metadata_from_pool; + bool integrity_metadata_from_pool:1; + struct work_struct work; struct convert_context ctx; @@ -74,6 +88,8 @@ struct dm_crypt_io { blk_status_t error; sector_t sector; + struct bvec_iter saved_bi_iter; + struct rb_node rb_node; } CRYPTO_MINALIGN_ATTR; @@ -98,11 +114,6 @@ struct crypt_iv_operations { struct dm_crypt_request *dmreq); }; -struct iv_essiv_private { - struct crypto_shash *hash_tfm; - u8 *salt; -}; - struct iv_benbi_private { int shift; }; @@ -115,21 +126,29 @@ struct iv_lmk_private { #define TCW_WHITENING_SIZE 16 struct iv_tcw_private { - struct crypto_shash *crc32_tfm; 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, - DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD }; + 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 cihper */ + 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 */ }; /* @@ -148,30 +167,28 @@ struct crypt_config { struct task_struct *write_thread; struct rb_root write_tree; - char *cipher; char *cipher_string; char *cipher_auth; char *key_string; 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; u64 iv_offset; unsigned int iv_size; - unsigned short int sector_size; + unsigned short sector_size; unsigned char sector_shift; - /* ESSIV: struct crypto_cipher *essiv_tfm */ - void *iv_private; union { struct crypto_skcipher **tfms; struct crypto_aead **tfms_aead; } cipher_tfm; - unsigned tfms_count; + unsigned int tfms_count; + int workqueue_id; unsigned long cipher_flags; /* @@ -199,13 +216,14 @@ struct crypt_config { unsigned int integrity_tag_size; unsigned int integrity_iv_size; - unsigned int on_disk_tag_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 tag_pool_max_sectors; + unsigned int tag_pool_max_sectors; mempool_t tag_pool; mempool_t req_pool; mempool_t page_pool; @@ -214,7 +232,7 @@ struct crypt_config { struct mutex bio_alloc_lock; u8 *authenc_key; /* space for keys in authenc() format (if used) */ - u8 key[0]; + u8 key[] __counted_by(key_size); }; #define MIN_IOS 64 @@ -222,16 +240,61 @@ struct crypt_config { #define POOL_ENTRY_SIZE 512 static DEFINE_SPINLOCK(dm_crypt_clients_lock); -static unsigned dm_crypt_clients_n = 0; +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_PAGES * 16) +#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 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 unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio) +{ + 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 independent of the key. */ @@ -291,8 +354,14 @@ static struct crypto_aead *any_tfm_aead(struct crypt_config *cc) * Note that this encryption scheme is vulnerable to watermarking attacks * and should be used for old compatible containers access only. * - * plumb: unimplemented, see: - * http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454 + * 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, @@ -323,158 +392,15 @@ static int crypt_iv_plain64be_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) -{ - struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv; - SHASH_DESC_ON_STACK(desc, essiv->hash_tfm); - struct crypto_cipher *essiv_tfm; - int err; - - desc->tfm = essiv->hash_tfm; - desc->flags = 0; - - err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt); - shash_desc_zero(desc); - if (err) - return err; - - essiv_tfm = cc->iv_private; - - err = crypto_cipher_setkey(essiv_tfm, essiv->salt, - crypto_shash_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_shash_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; -} - -/* Allocate the cipher for ESSIV */ -static struct crypto_cipher *alloc_essiv_cipher(struct crypt_config *cc, - struct dm_target *ti, - const u8 *salt, - unsigned int saltsize) -{ - struct crypto_cipher *essiv_tfm; - int err; - - /* Setup the essiv_tfm with the given salt */ - essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, 0); - if (IS_ERR(essiv_tfm)) { - ti->error = "Error allocating crypto tfm for ESSIV"; - return essiv_tfm; - } - - if (crypto_cipher_blocksize(essiv_tfm) != cc->iv_size) { - 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_shash(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_shash *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_shash(opts, 0, 0); - if (IS_ERR(hash_tfm)) { - ti->error = "Error initializing ESSIV hash"; - err = PTR_ERR(hash_tfm); - goto bad; - } - - salt = kzalloc(crypto_shash_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 = alloc_essiv_cipher(cc, ti, salt, - crypto_shash_digestsize(hash_tfm)); - if (IS_ERR(essiv_tfm)) { - crypt_iv_essiv_dtr(cc); - return PTR_ERR(essiv_tfm); - } - cc->iv_private = essiv_tfm; - - return 0; - -bad: - if (hash_tfm && !IS_ERR(hash_tfm)) - crypto_free_shash(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; } @@ -482,12 +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_skcipher_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; @@ -536,7 +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; } @@ -550,7 +483,8 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti, return -EINVAL; } - lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0); + 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); @@ -601,12 +535,14 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; SHASH_DESC_ON_STACK(desc, lmk->hash_tfm); - struct md5_state md5state; + union { + struct md5_state md5state; + u8 state[CRYPTO_MD5_STATESIZE]; + } u; __le32 buf[4]; int i, r; desc->tfm = lmk->hash_tfm; - desc->flags = 0; r = crypto_shash_init(desc); if (r) @@ -633,13 +569,13 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, return r; /* No MD5 padding here */ - r = crypto_shash_export(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; } @@ -653,9 +589,9 @@ static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { sg = crypt_get_sg_data(cc, dmreq->sg_in); - src = kmap_atomic(sg_page(sg)); + src = kmap_local_page(sg_page(sg)); r = crypt_iv_lmk_one(cc, iv, dmreq, src + sg->offset); - kunmap_atomic(src); + kunmap_local(src); } else memset(iv, 0, cc->iv_size); @@ -673,14 +609,14 @@ static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, return 0; sg = crypt_get_sg_data(cc, dmreq->sg_out); - dst = kmap_atomic(sg_page(sg)); + 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 + sg->offset, iv, cc->iv_size); - kunmap_atomic(dst); + kunmap_local(dst); return r; } @@ -688,14 +624,10 @@ static void crypt_iv_tcw_dtr(struct crypt_config *cc) { struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; - kzfree(tcw->iv_seed); + kfree_sensitive(tcw->iv_seed); tcw->iv_seed = NULL; - kzfree(tcw->whitening); + kfree_sensitive(tcw->whitening); tcw->whitening = NULL; - - if (tcw->crc32_tfm && !IS_ERR(tcw->crc32_tfm)) - crypto_free_shash(tcw->crc32_tfm); - tcw->crc32_tfm = NULL; } static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti, @@ -713,12 +645,6 @@ static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti, return -EINVAL; } - tcw->crc32_tfm = crypto_alloc_shash("crc32", 0, 0); - if (IS_ERR(tcw->crc32_tfm)) { - ti->error = "Error initializing CRC32 in TCW"; - return PTR_ERR(tcw->crc32_tfm); - } - tcw->iv_seed = kzalloc(cc->iv_size, GFP_KERNEL); tcw->whitening = kzalloc(TCW_WHITENING_SIZE, GFP_KERNEL); if (!tcw->iv_seed || !tcw->whitening) { @@ -752,43 +678,28 @@ static int crypt_iv_tcw_wipe(struct crypt_config *cc) return 0; } -static int crypt_iv_tcw_whitening(struct crypt_config *cc, - struct dm_crypt_request *dmreq, - u8 *data) +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]; - SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm); - int i, r; + 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 */ - desc->tfm = tcw->crc32_tfm; - desc->flags = 0; - for (i = 0; i < 4; i++) { - r = crypto_shash_init(desc); - if (r) - goto out; - r = crypto_shash_update(desc, &buf[i * 4], 4); - if (r) - goto out; - r = crypto_shash_final(desc, &buf[i * 4]); - if (r) - goto out; - } + 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); -out: memzero_explicit(buf, sizeof(buf)); - return r; } static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv, @@ -798,14 +709,13 @@ static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv, struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw; __le64 sector = cpu_to_le64(dmreq->iv_sector); u8 *src; - int r = 0; /* Remove whitening from ciphertext */ if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) { sg = crypt_get_sg_data(cc, dmreq->sg_in); - src = kmap_atomic(sg_page(sg)); - r = crypt_iv_tcw_whitening(cc, dmreq, src + sg->offset); - kunmap_atomic(src); + src = kmap_local_page(sg_page(sg)); + crypt_iv_tcw_whitening(cc, dmreq, src + sg->offset); + kunmap_local(src); } /* Calculate IV */ @@ -814,7 +724,7 @@ static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv, crypto_xor_cpy(&iv[8], tcw->iv_seed + 8, (u8 *)§or, cc->iv_size - 8); - return r; + return 0; } static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv, @@ -822,18 +732,17 @@ static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv, { struct scatterlist *sg; u8 *dst; - int r; 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_atomic(sg_page(sg)); - r = crypt_iv_tcw_whitening(cc, dmreq, dst + sg->offset); - kunmap_atomic(dst); + dst = kmap_local_page(sg_page(sg)); + crypt_iv_tcw_whitening(cc, dmreq, dst + sg->offset); + kunmap_local(dst); - return r; + return 0; } static int crypt_iv_random_gen(struct crypt_config *cc, u8 *iv, @@ -844,6 +753,341 @@ static int crypt_iv_random_gen(struct crypt_config *cc, u8 *iv, 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 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 }; @@ -857,10 +1101,6 @@ static const struct crypt_iv_operations crypt_iv_plain64be_ops = { }; static const struct crypt_iv_operations crypt_iv_essiv_ops = { - .ctr = crypt_iv_essiv_ctr, - .dtr = crypt_iv_essiv_dtr, - .init = crypt_iv_essiv_init, - .wipe = crypt_iv_essiv_wipe, .generator = crypt_iv_essiv_gen }; @@ -892,10 +1132,24 @@ static const struct crypt_iv_operations crypt_iv_tcw_ops = { .post = crypt_iv_tcw_post }; -static struct crypt_iv_operations crypt_iv_random_ops = { +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 */ @@ -925,17 +1179,16 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) unsigned int tag_len; int ret; - if (!bio_sectors(bio) || !io->cc->on_disk_tag_size) + 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->on_disk_tag_size * bio_sectors(bio); + tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift); - bip->bip_iter.bi_size = tag_len; - bip->bip_iter.bi_sector = io->cc->start + io->sector; + 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)); @@ -949,26 +1202,27 @@ 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); - /* From now we require underlying device with our integrity profile */ - if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) { + /* 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->tag_size != cc->on_disk_tag_size || - bi->tuple_size != cc->on_disk_tag_size) { + 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->on_disk_tag_size - cc->integrity_iv_size; - DMINFO("Integrity AEAD, tag size %u, IV size %u.", + 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)) { @@ -976,10 +1230,10 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti) return -EINVAL; } } else if (cc->integrity_iv_size) - DMINFO("Additional per-sector space %u bytes for IV.", + 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) != bi->tag_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; } @@ -1003,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc, 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); } @@ -1034,11 +1289,12 @@ static u8 *org_iv_of_dmreq(struct crypt_config *cc, return iv_of_dmreq(cc, dmreq) + cc->iv_size; } -static uint64_t *org_sector_of_dmreq(struct crypt_config *cc, +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 (uint64_t*) ptr; + + return (__le64 *) ptr; } static unsigned int *org_tag_of_dmreq(struct crypt_config *cc, @@ -1046,7 +1302,8 @@ static unsigned int *org_tag_of_dmreq(struct crypt_config *cc, { u8 *ptr = iv_of_dmreq(cc, dmreq) + cc->iv_size + cc->iv_size + sizeof(uint64_t); - return (unsigned int*)ptr; + + return (unsigned int *)ptr; } static void *tag_from_dmreq(struct crypt_config *cc, @@ -1056,7 +1313,7 @@ static void *tag_from_dmreq(struct crypt_config *cc, struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); return &io->integrity_metadata[*org_tag_of_dmreq(cc, dmreq) * - cc->on_disk_tag_size]; + cc->tuple_size]; } static void *iv_tag_from_dmreq(struct crypt_config *cc, @@ -1074,7 +1331,7 @@ static int crypt_convert_block_aead(struct crypt_config *cc, struct bio_vec bv_out = bio_iter_iovec(ctx->bio_out, ctx->iter_out); struct dm_crypt_request *dmreq; u8 *iv, *org_iv, *tag_iv, *tag; - uint64_t *sector; + __le64 *sector; int r = 0; BUG_ON(cc->integrity_iv_size && cc->integrity_iv_size != cc->iv_size); @@ -1137,18 +1394,26 @@ static int crypt_convert_block_aead(struct crypt_config *cc, 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->on_disk_tag_size) + if (cc->integrity_tag_size + cc->integrity_iv_size != cc->tuple_size) memset(tag + cc->integrity_tag_size + cc->integrity_iv_size, 0, - cc->on_disk_tag_size - (cc->integrity_tag_size + cc->integrity_iv_size)); + 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) - DMERR_LIMIT("INTEGRITY AEAD ERROR, sector %llu", - (unsigned long long)le64_to_cpu(*sector)); + 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); @@ -1169,7 +1434,7 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc, struct scatterlist *sg_in, *sg_out; struct dm_crypt_request *dmreq; u8 *iv, *org_iv, *tag_iv; - uint64_t *sector; + __le64 *sector; int r = 0; /* Reject unexpected unaligned bio. */ @@ -1209,6 +1474,9 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc, 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); @@ -1233,16 +1501,18 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc, 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 void crypt_alloc_req_skcipher(struct crypt_config *cc, +static int crypt_alloc_req_skcipher(struct crypt_config *cc, struct convert_context *ctx) { - unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); + unsigned int key_index = ctx->cc_sector & (cc->tfms_count - 1); - if (!ctx->r.req) - ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO); + 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]); @@ -1253,13 +1523,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, 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 void crypt_alloc_req_aead(struct crypt_config *cc, +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, GFP_NOIO); + 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; + } aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]); @@ -1270,15 +1545,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, 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 void crypt_alloc_req(struct crypt_config *cc, +static int crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { if (crypt_integrity_aead(cc)) - crypt_alloc_req_aead(cc, ctx); + return crypt_alloc_req_aead(cc, ctx); else - crypt_alloc_req_skcipher(cc, ctx); + return crypt_alloc_req_skcipher(cc, ctx); } static void crypt_free_req_skcipher(struct crypt_config *cc, @@ -1311,23 +1588,33 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ * Encrypt / decrypt data from one bio to another one (can be the same one) */ static blk_status_t crypt_convert(struct crypt_config *cc, - struct convert_context *ctx) + struct convert_context *ctx, bool atomic, bool reset_pending) { - unsigned int tag_offset = 0; 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->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); if (crypt_integrity_aead(cc)) - r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset); + 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, tag_offset); + r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset); switch (r) { /* @@ -1335,17 +1622,35 @@ static blk_status_t crypt_convert(struct crypt_config *cc, * but the driver request queue is full, let's wait. */ case -EBUSY: - wait_for_completion(&ctx->restart); + 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); - /* fall through */ + fallthrough; /* * The request is queued and processed asynchronously, * completion function kcryptd_async_done() will be called. */ case -EINPROGRESS: ctx->r.req = NULL; + ctx->tag_offset++; ctx->cc_sector += sector_step; - tag_offset++; continue; /* * The request was already processed (synchronously). @@ -1353,8 +1658,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc, case 0: atomic_dec(&ctx->cc_pending); ctx->cc_sector += sector_step; - tag_offset++; - cond_resched(); + ctx->tag_offset++; + if (!atomic) + cond_resched(); continue; /* * There was a data integrity error. @@ -1378,8 +1684,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone); /* * Generate a new unfragmented bio with the given size - * This should never violate the device limitations (but only because - * max_segment_size is being constrained to PAGE_SIZE). + * This 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 @@ -1392,42 +1698,66 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone); * 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) +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_NOWAIT | __GFP_HIGHMEM; - unsigned i, len, remaining_size; - struct page *page; + unsigned int remaining_size; + unsigned int order = MAX_PAGE_ORDER; retry: if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_lock(&cc->bio_alloc_lock); - clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs); - if (!clone) - goto out; - - clone_init(io, clone); + 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; - for (i = 0; i < nr_iovecs; i++) { - page = mempool_alloc(&cc->page_pool, gfp_mask); - if (!page) { + 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--; + } + + 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; } - len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size; - - bio_add_page(clone, page, len, 0); - - remaining_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; } /* Allocate space for integrity tags */ @@ -1436,7 +1766,7 @@ retry: bio_put(clone); clone = NULL; } -out: + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_unlock(&cc->bio_alloc_lock); @@ -1445,12 +1775,18 @@ out: 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); + 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); + } + } } } @@ -1461,6 +1797,8 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->base_bio = bio; io->sector = sector; io->error = 0; + 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; @@ -1472,6 +1810,8 @@ 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. @@ -1485,6 +1825,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io) if (!atomic_dec_and_test(&io->io_pending)) return; + 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); @@ -1494,6 +1843,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) kfree(io->integrity_metadata); base_bio->bi_status = error; + bio_endio(base_bio); } @@ -1518,16 +1868,20 @@ 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); - blk_status_t error; + unsigned int rw = bio_data_dir(clone); + blk_status_t error = clone->bi_status; + + 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); - error = clone->bi_status; bio_put(clone); if (rw == READ && !error) { @@ -1541,35 +1895,43 @@ static void crypt_endio(struct bio *clone) 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; - bio_set_dev(clone, cc->dev->bdev); - clone->bi_opf = io->base_bio->bi_opf; -} +#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 *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; + } + /* - * 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_clone_fast(). + * 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_fast(io->base_bio, gfp, &cc->bs); + clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs); if (!clone) return 1; - crypt_inc_pending(io); - - clone_init(io, clone); clone->bi_iter.bi_sector = cc->start + io->sector; + clone->bi_private = io; + clone->bi_end_io = crypt_endio; + + crypt_inc_pending(io); if (dm_crypt_integrity_io_alloc(io, clone)) { crypt_dec_pending(io); @@ -1577,7 +1939,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) return 1; } - generic_make_request(clone); + dm_submit_bio_remap(io->base_bio, clone); return 0; } @@ -1603,7 +1965,7 @@ static void kcryptd_io_write(struct dm_crypt_io *io) { struct bio *clone = io->ctx.bio_out; - generic_make_request(clone); + dm_submit_bio_remap(io->base_bio, clone); } #define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node) @@ -1634,7 +1996,6 @@ continue_locked: schedule(); - set_current_state(TASK_RUNNING); spin_lock_irq(&cc->write_thread_lock); goto continue_locked; @@ -1654,6 +2015,7 @@ pop_from_list: 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); } @@ -1678,10 +2040,9 @@ 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.iter_out.bi_size); - clone->bi_iter.bi_sector = cc->start + io->sector; - - if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) { - generic_make_request(clone); + 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; } @@ -1703,19 +2064,68 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) 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; int crypt_finished; - sector_t sector = io->sector; 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); clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); if (unlikely(!clone)) { @@ -1726,19 +2136,37 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.bio_out = clone; io->ctx.iter_out = clone->bi_iter; - sector += bio_sectors(clone); + if (crypt_integrity_aead(cc)) { + bio_copy_data(clone, io->base_bio); + io->ctx.bio_in = clone; + io->ctx.iter_in = clone->bi_iter; + } crypt_inc_pending(io); - r = crypt_convert(cc, &io->ctx); + 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(&io->ctx.cc_pending); + 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) { + if (crypt_finished) kcryptd_crypt_write_io_submit(io, 0); - io->sector = sector; - } dec: crypt_dec_pending(io); @@ -1746,6 +2174,33 @@ dec: 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_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); } @@ -1756,10 +2211,25 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) 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); + 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; @@ -1769,10 +2239,9 @@ 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; @@ -1791,8 +2260,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, error = cc->iv_gen_ops->post(cc, org_iv_of_dmreq(cc, dmreq), dmreq); if (error == -EBADMSG) { - DMERR_LIMIT("INTEGRITY AEAD ERROR, sector %llu", - (unsigned long long)le64_to_cpu(*org_sector_of_dmreq(cc, dmreq))); + sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)); + + 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; @@ -1802,10 +2278,21 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, 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) @@ -1822,6 +2309,23 @@ 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); } @@ -1842,7 +2346,7 @@ static void crypt_free_tfms_aead(struct crypt_config *cc) static void crypt_free_tfms_skcipher(struct crypt_config *cc) { - unsigned i; + unsigned int i; if (!cc->cipher_tfm.tfms) return; @@ -1867,7 +2371,7 @@ static void crypt_free_tfms(struct crypt_config *cc) static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) { - unsigned i; + unsigned int i; int err; cc->cipher_tfm.tfms = kcalloc(cc->tfms_count, @@ -1877,7 +2381,8 @@ static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) return -ENOMEM; for (i = 0; i < cc->tfms_count; i++) { - cc->cipher_tfm.tfms[i] = crypto_alloc_skcipher(ciphermode, 0, 0); + 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); @@ -1890,7 +2395,7 @@ static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) * algorithm implementation is used. Help people debug performance * problems by logging the ->cra_driver_name. */ - DMINFO("%s using implementation \"%s\"", ciphermode, + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, crypto_skcipher_alg(any_tfm(cc))->base.cra_driver_name); return 0; } @@ -1903,14 +2408,15 @@ static int crypt_alloc_tfms_aead(struct crypt_config *cc, char *ciphermode) if (!cc->cipher_tfm.tfms) return -ENOMEM; - cc->cipher_tfm.tfms_aead[0] = crypto_alloc_aead(ciphermode, 0, 0); + 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; } - DMINFO("%s using implementation \"%s\"", ciphermode, + DMDEBUG_LIMIT("%s using implementation \"%s\"", ciphermode, crypto_aead_alg(any_tfm_aead(cc))->base.cra_driver_name); return 0; } @@ -1923,12 +2429,12 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode) return crypt_alloc_tfms_skcipher(cc, ciphermode); } -static unsigned crypt_subkey_size(struct crypt_config *cc) +static unsigned int crypt_subkey_size(struct crypt_config *cc) { return (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count); } -static unsigned crypt_authenckey_size(struct crypt_config *cc) +static unsigned int crypt_authenckey_size(struct crypt_config *cc) { return crypt_subkey_size(cc) + RTA_SPACE(sizeof(struct crypto_authenc_key_param)); } @@ -1939,7 +2445,7 @@ static unsigned crypt_authenckey_size(struct crypt_config *cc) * This funcion converts cc->key to this special format. */ static void crypt_copy_authenckey(char *p, const void *key, - unsigned enckeylen, unsigned authkeylen) + unsigned int enckeylen, unsigned int authkeylen) { struct crypto_authenc_key_param *param; struct rtattr *rta; @@ -1957,7 +2463,7 @@ static void crypt_copy_authenckey(char *p, const void *key, static int crypt_setkey(struct crypt_config *cc) { - unsigned subkey_size; + unsigned int subkey_size; int err = 0, i, r; /* Ignore extra keys (which are used for IV etc) */ @@ -2004,12 +2510,61 @@ static bool contains_whitespace(const char *str) 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; - const struct user_key_payload *ukp; + int (*set_key)(struct crypt_config *cc, struct key *key); /* * Reject key_string with whitespace. dm core currently lacks code for @@ -2021,59 +2576,59 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string } /* look for next ':' separating key_type from key_description */ - key_desc = strpbrk(key_string, ":"); + 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) && - strncmp(key_string, "user:", key_desc - key_string + 1)) + 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(key_string[0] == 'l' ? &key_type_logon : &key_type_user, - key_desc + 1, NULL); + key = request_key(type, key_desc + 1, NULL); if (IS_ERR(key)) { - kzfree(new_key_string); - return PTR_ERR(key); + ret = PTR_ERR(key); + goto free_new_key_string; } down_read(&key->sem); - - ukp = user_key_payload_locked(key); - if (!ukp) { - up_read(&key->sem); - key_put(key); - kzfree(new_key_string); - return -EKEYREVOKED; - } - - if (cc->key_size != ukp->datalen) { - up_read(&key->sem); - key_put(key); - kzfree(new_key_string); - return -EINVAL; - } - - memcpy(cc->key, ukp->data, cc->key_size); - + 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; - if (!ret) { - set_bit(DM_CRYPT_KEY_VALID, &cc->flags); - kzfree(cc->key_string); - cc->key_string = new_key_string; - } else - kzfree(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; } @@ -2109,10 +2664,10 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string static int get_key_size(char **key_string) { - return (*key_string[0] == ':') ? -EINVAL : strlen(*key_string) >> 1; + return (*key_string[0] == ':') ? -EINVAL : (int)(strlen(*key_string) >> 1); } -#endif +#endif /* CONFIG_KEYS */ static int crypt_set_key(struct crypt_config *cc, char *key) { @@ -2133,7 +2688,7 @@ static int crypt_set_key(struct crypt_config *cc, char *key) clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); /* wipe references to any kernel keyring key */ - kzfree(cc->key_string); + kfree_sensitive(cc->key_string); cc->key_string = NULL; /* Decode key from its hex representation. */ @@ -2157,7 +2712,15 @@ static int crypt_wipe_key(struct crypt_config *cc) clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); get_random_bytes(&cc->key, cc->key_size); - kzfree(cc->key_string); + + /* 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)); @@ -2183,7 +2746,12 @@ static void *crypt_page_alloc(gfp_t gfp_mask, void *pool_data) struct crypt_config *cc = pool_data; struct page *page; - if (unlikely(percpu_counter_compare(&cc->n_allocated_pages, dm_crypt_pages_per_client) >= 0) && + /* + * 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; @@ -2219,6 +2787,9 @@ static void crypt_dtr(struct dm_target *ti) if (cc->crypt_queue) destroy_workqueue(cc->crypt_queue); + if (cc->workqueue_id) + ida_free(&workqueue_ida, cc->workqueue_id); + crypt_free_tfms(cc); bioset_exit(&cc->bs); @@ -2236,22 +2807,23 @@ static void crypt_dtr(struct dm_target *ti) if (cc->dev) dm_put_device(ti, cc->dev); - kzfree(cc->cipher); - kzfree(cc->cipher_string); - kzfree(cc->key_string); - kzfree(cc->cipher_auth); - kzfree(cc->authenc_key); + kfree_sensitive(cc->cipher_string); + kfree_sensitive(cc->key_string); + kfree_sensitive(cc->cipher_auth); + kfree_sensitive(cc->authenc_key); 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) @@ -2287,7 +2859,16 @@ static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode) 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) { + 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 @@ -2316,52 +2897,6 @@ static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode) } /* - * Workaround to parse cipher algorithm from crypto API spec. - * The cc->cipher is currently used only in ESSIV. - * This should be probably done by crypto-api calls (once available...) - */ -static int crypt_ctr_blkdev_cipher(struct crypt_config *cc) -{ - const char *alg_name = NULL; - char *start, *end; - - if (crypt_integrity_aead(cc)) { - alg_name = crypto_tfm_alg_name(crypto_aead_tfm(any_tfm_aead(cc))); - if (!alg_name) - return -EINVAL; - if (crypt_integrity_hmac(cc)) { - alg_name = strchr(alg_name, ','); - if (!alg_name) - return -EINVAL; - } - alg_name++; - } else { - alg_name = crypto_tfm_alg_name(crypto_skcipher_tfm(any_tfm(cc))); - if (!alg_name) - return -EINVAL; - } - - start = strchr(alg_name, '('); - end = strchr(alg_name, ')'); - - if (!start && !end) { - cc->cipher = kstrdup(alg_name, GFP_KERNEL); - return cc->cipher ? 0 : -ENOMEM; - } - - if (!start || !end || ++start >= end) - return -EINVAL; - - cc->cipher = kzalloc(end - start + 1, GFP_KERNEL); - if (!cc->cipher) - return -ENOMEM; - - strncpy(cc->cipher, start, end - start); - - return 0; -} - -/* * 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...) @@ -2379,18 +2914,18 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api) if (!start || !end || ++start > end) return -EINVAL; - mac_alg = kzalloc(end - start + 1, GFP_KERNEL); + mac_alg = kmemdup_nul(start, end - start, GFP_KERNEL); if (!mac_alg) return -ENOMEM; - strncpy(mac_alg, start, end - start); - mac = crypto_alloc_ahash(mac_alg, 0, 0); + mac = crypto_alloc_ahash(mac_alg, 0, CRYPTO_ALG_ALLOCATES_MEMORY); kfree(mac_alg); if (IS_ERR(mac)) return PTR_ERR(mac); - cc->key_mac_size = crypto_ahash_digestsize(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); @@ -2404,7 +2939,7 @@ 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_api; + char *tmp, *cipher_api, buf[CRYPTO_MAX_ALG_NAME]; int ret = -EINVAL; cc->tfms_count = 1; @@ -2414,13 +2949,48 @@ static int crypt_ctr_cipher_new(struct dm_target *ti, char *cipher_in, char *key * capi:cipher_api_spec-iv:ivopts */ tmp = &cipher_in[strlen("capi:")]; - cipher_api = strsep(&tmp, "-"); - *ivmode = strsep(&tmp, ":"); - *ivopts = tmp; + + /* 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 */ @@ -2430,23 +3000,11 @@ static int crypt_ctr_cipher_new(struct dm_target *ti, char *cipher_in, char *key return ret; } - /* 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 -ENOMEM; - } + if (crypt_integrity_aead(cc)) cc->iv_size = crypto_aead_ivsize(any_tfm_aead(cc)); - } else + else cc->iv_size = crypto_skcipher_ivsize(any_tfm(cc)); - ret = crypt_ctr_blkdev_cipher(cc); - if (ret < 0) { - ti->error = "Cannot allocate cipher string"; - return -ENOMEM; - } - return 0; } @@ -2481,16 +3039,9 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key } 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"); + *ivmode = strsep(&tmp, ":"); + *ivopts = tmp; /* * For compatibility with the original dm-crypt mapping format, if @@ -2510,9 +3061,19 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key 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; } @@ -2593,7 +3154,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar struct crypt_config *cc = ti->private; struct dm_arg_set as; static const struct dm_arg _args[] = { - {0, 6, "Invalid number of feature args"}, + {0, 9, "Invalid number of feature args"}, }; unsigned int opt_params, val; const char *opt_string, *sval; @@ -2620,19 +3181,25 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar 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->on_disk_tag_size = val; + 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")) { + } else if (strcasecmp(sval, "none")) { ti->error = "Unknown integrity profile"; return -EINVAL; } @@ -2640,6 +3207,13 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar 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 || @@ -2663,6 +3237,20 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar 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>|:<key_size>:<user|logon>:<key_description>] <iv_offset> <dev_path> <start> @@ -2671,8 +3259,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct crypt_config *cc; const char *devname = dm_table_device_name(ti->table); - int key_size; + int key_size, wq_id; unsigned int align_mask; + unsigned int common_wq_flags; unsigned long long tmpll; int ret; size_t iv_size_padding, additional_req_size; @@ -2689,7 +3278,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) 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; @@ -2759,9 +3348,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->per_bio_data_size = ti->per_io_data_size = ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size, - ARCH_KMALLOC_MINALIGN); + ARCH_DMA_MINALIGN); - ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc); + 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; @@ -2796,17 +3385,41 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } cc->start = tmpll; + 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); + + /* + * 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; + } + if (crypt_integrity_aead(cc) || cc->integrity_iv_size) { ret = crypt_integrity_ctr(cc, ti); if (ret) goto bad; - cc->tag_pool_max_sectors = POOL_ENTRY_SIZE / cc->on_disk_tag_size; + cc->tag_pool_max_sectors = POOL_ENTRY_SIZE / cc->tuple_size; if (!cc->tag_pool_max_sectors) cc->tag_pool_max_sectors = 1; ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS, - cc->tag_pool_max_sectors * cc->on_disk_tag_size); + cc->tag_pool_max_sectors * cc->tuple_size); if (ret) { ti->error = "Cannot allocate integrity tags mempool"; goto bad; @@ -2815,23 +3428,38 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) 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/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); + 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; } - if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); - else - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, - num_online_cpus(), devname); + 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; @@ -2840,20 +3468,25 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) spin_lock_init(&cc->write_thread_lock); cc->write_tree = RB_ROOT; - cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write/%s", devname); + 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; } - wake_up_process(cc->write_thread); + if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) + set_user_nice(cc->write_thread, MIN_NICE); ti->num_flush_bios = 1; + 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; } @@ -2862,6 +3495,7 @@ 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_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues. @@ -2880,9 +3514,9 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) /* * Check if bio is too large, split as needed. */ - if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) && - (bio_data_dir(bio) == WRITE || cc->on_disk_tag_size)) - dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT)); + 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 @@ -2897,12 +3531,15 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) 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->on_disk_tag_size) { - unsigned tag_len = cc->on_disk_tag_size * (bio_sectors(bio) >> cc->sector_shift); + 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(tag_len > KMALLOC_MAX_SIZE) || - unlikely(!(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); @@ -2916,7 +3553,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) io->ctx.r.req = (struct skcipher_request *)(io + 1); if (bio_data_dir(io->base_bio) == READ) { - if (kcryptd_io_read(io, GFP_NOWAIT)) + if (kcryptd_io_read(io, CRYPT_MAP_READ_GFP)) kcryptd_queue_read(io); } else kcryptd_queue_crypt(io); @@ -2924,11 +3561,16 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) 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) { @@ -2942,9 +3584,12 @@ static void crypt_status(struct dm_target *ti, status_type_t type, 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("%02x", cc->key[i]); + else { + for (i = 0; i < cc->key_size; i++) { + DMEMIT("%c%c", hex2asc(cc->key[i] >> 4), + hex2asc(cc->key[i] & 0xf)); + } + } } else DMEMIT("-"); @@ -2953,27 +3598,66 @@ static void crypt_status(struct dm_target *ti, status_type_t type, 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); - if (cc->on_disk_tag_size) - num_feature_args++; + 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 (cc->on_disk_tag_size) - DMEMIT(" integrity:%u:%s", cc->on_disk_tag_size, cc->cipher_auth); + 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; } } @@ -3008,8 +3692,8 @@ 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, - char *result, unsigned maxlen) +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 key_size, ret = -EINVAL; @@ -3040,14 +3724,8 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv, 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: @@ -3067,27 +3745,33 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct crypt_config *cc = ti->private; - /* - * Unfortunate constraint that is required to avoid the potential - * for exceeding underlying device's max_segments limits -- due to - * crypt_alloc_buffer() possibly allocating pages for the encryption - * bio that are not as physically contiguous as the original bio. - */ - limits->max_segment_size = PAGE_SIZE; - limits->logical_block_size = - max_t(unsigned short, limits->logical_block_size, cc->sector_size); + max_t(unsigned int, limits->logical_block_size, cc->sector_size); limits->physical_block_size = - max_t(unsigned, limits->physical_block_size, cc->sector_size); - limits->io_min = max_t(unsigned, limits->io_min, cc->sector_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, 18, 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, @@ -3097,25 +3781,7 @@ static struct target_type crypt_target = { .iterate_devices = crypt_iterate_devices, .io_hints = crypt_io_hints, }; - -static int __init dm_crypt_init(void) -{ - int r; - - r = dm_register_target(&crypt_target); - if (r < 0) - DMERR("register failed %d", r); - - return r; -} - -static void __exit dm_crypt_exit(void) -{ - dm_unregister_target(&crypt_target); -} - -module_init(dm_crypt_init); -module_exit(dm_crypt_exit); +module_dm(crypt); MODULE_AUTHOR("Jana Saout <jana@saout.de>"); MODULE_DESCRIPTION(DM_NAME " target for transparent encryption / decryption"); |