From 150c7e85526e80474b87004f4b420e8834fdeb43 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 29 Mar 2009 15:39:02 +0800 Subject: crypto: fpu - Add template for blkcipher touching FPU Blkcipher touching FPU need to be enclosed by kernel_fpu_begin() and kernel_fpu_end(). If they are invoked in cipher algorithm implementation, they will be invoked for each block, so that performance will be hurt, because they are "slow" operations. This patch implements "fpu" template, which makes these operations to be invoked for each request. Signed-off-by: Huang Ying Signed-off-by: Herbert Xu --- arch/x86/crypto/Makefile | 2 + arch/x86/crypto/fpu.c | 166 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 168 insertions(+) create mode 100644 arch/x86/crypto/fpu.c (limited to 'arch') diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index ebe7deedd5b..cfb0010fa94 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +obj-$(CONFIG_CRYPTO_FPU) += fpu.o + obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c new file mode 100644 index 00000000000..5f9781a3815 --- /dev/null +++ b/arch/x86/crypto/fpu.c @@ -0,0 +1,166 @@ +/* + * FPU: Wrapper for blkcipher touching fpu + * + * Copyright (c) Intel Corp. + * Author: Huang Ying + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#include +#include +#include +#include +#include +#include + +struct crypto_fpu_ctx { + struct crypto_blkcipher *child; +}; + +static int crypto_fpu_setkey(struct crypto_tfm *parent, const u8 *key, + unsigned int keylen) +{ + struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(parent); + struct crypto_blkcipher *child = ctx->child; + int err; + + crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); + crypto_blkcipher_set_flags(child, crypto_tfm_get_flags(parent) & + CRYPTO_TFM_REQ_MASK); + err = crypto_blkcipher_setkey(child, key, keylen); + crypto_tfm_set_flags(parent, crypto_blkcipher_get_flags(child) & + CRYPTO_TFM_RES_MASK); + return err; +} + +static int crypto_fpu_encrypt(struct blkcipher_desc *desc_in, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + int err; + struct crypto_fpu_ctx *ctx = crypto_blkcipher_ctx(desc_in->tfm); + struct crypto_blkcipher *child = ctx->child; + struct blkcipher_desc desc = { + .tfm = child, + .info = desc_in->info, + .flags = desc_in->flags, + }; + + kernel_fpu_begin(); + err = crypto_blkcipher_crt(desc.tfm)->encrypt(&desc, dst, src, nbytes); + kernel_fpu_end(); + return err; +} + +static int crypto_fpu_decrypt(struct blkcipher_desc *desc_in, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + int err; + struct crypto_fpu_ctx *ctx = crypto_blkcipher_ctx(desc_in->tfm); + struct crypto_blkcipher *child = ctx->child; + struct blkcipher_desc desc = { + .tfm = child, + .info = desc_in->info, + .flags = desc_in->flags, + }; + + kernel_fpu_begin(); + err = crypto_blkcipher_crt(desc.tfm)->decrypt(&desc, dst, src, nbytes); + kernel_fpu_end(); + return err; +} + +static int crypto_fpu_init_tfm(struct crypto_tfm *tfm) +{ + struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); + struct crypto_spawn *spawn = crypto_instance_ctx(inst); + struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(tfm); + struct crypto_blkcipher *cipher; + + cipher = crypto_spawn_blkcipher(spawn); + if (IS_ERR(cipher)) + return PTR_ERR(cipher); + + ctx->child = cipher; + return 0; +} + +static void crypto_fpu_exit_tfm(struct crypto_tfm *tfm) +{ + struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(tfm); + crypto_free_blkcipher(ctx->child); +} + +static struct crypto_instance *crypto_fpu_alloc(struct rtattr **tb) +{ + struct crypto_instance *inst; + struct crypto_alg *alg; + int err; + + err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER); + if (err) + return ERR_PTR(err); + + alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_BLKCIPHER, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(alg)) + return ERR_CAST(alg); + + inst = crypto_alloc_instance("fpu", alg); + if (IS_ERR(inst)) + goto out_put_alg; + + inst->alg.cra_flags = alg->cra_flags; + inst->alg.cra_priority = alg->cra_priority; + inst->alg.cra_blocksize = alg->cra_blocksize; + inst->alg.cra_alignmask = alg->cra_alignmask; + inst->alg.cra_type = alg->cra_type; + inst->alg.cra_blkcipher.ivsize = alg->cra_blkcipher.ivsize; + inst->alg.cra_blkcipher.min_keysize = alg->cra_blkcipher.min_keysize; + inst->alg.cra_blkcipher.max_keysize = alg->cra_blkcipher.max_keysize; + inst->alg.cra_ctxsize = sizeof(struct crypto_fpu_ctx); + inst->alg.cra_init = crypto_fpu_init_tfm; + inst->alg.cra_exit = crypto_fpu_exit_tfm; + inst->alg.cra_blkcipher.setkey = crypto_fpu_setkey; + inst->alg.cra_blkcipher.encrypt = crypto_fpu_encrypt; + inst->alg.cra_blkcipher.decrypt = crypto_fpu_decrypt; + +out_put_alg: + crypto_mod_put(alg); + return inst; +} + +static void crypto_fpu_free(struct crypto_instance *inst) +{ + crypto_drop_spawn(crypto_instance_ctx(inst)); + kfree(inst); +} + +static struct crypto_template crypto_fpu_tmpl = { + .name = "fpu", + .alloc = crypto_fpu_alloc, + .free = crypto_fpu_free, + .module = THIS_MODULE, +}; + +static int __init crypto_fpu_module_init(void) +{ + return crypto_register_template(&crypto_fpu_tmpl); +} + +static void __exit crypto_fpu_module_exit(void) +{ + crypto_unregister_template(&crypto_fpu_tmpl); +} + +module_init(crypto_fpu_module_init); +module_exit(crypto_fpu_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("FPU block cipher wrapper"); -- cgit v1.2.3 From 2cf4ac8beb9dc50a315a6155b7b70e754d511958 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 29 Mar 2009 15:41:20 +0800 Subject: crypto: aes-ni - Add support for more modes Because kernel_fpu_begin() and kernel_fpu_end() operations are too slow, the performance gain of general mode implementation + aes-aesni is almost all compensated. The AES-NI support for more modes are implemented as follow: - Add a new AES algorithm implementation named __aes-aesni without kernel_fpu_begin/end() - Use fpu((AES)) to provide kenrel_fpu_begin/end() invoking - Add (AES) ablkcipher, which uses cryptd(fpu((AES))) to defer cryption to cryptd context in soft_irq context. Now the ctr, lrw, pcbc and xts support are added. Performance testing based on dm-crypt shows that cryption time can be reduced to 50% of general mode implementation + aes-aesni implementation. Signed-off-by: Huang Ying Signed-off-by: Herbert Xu --- arch/x86/crypto/aesni-intel_glue.c | 267 ++++++++++++++++++++++++++++++++++++- 1 file changed, 266 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 02af0af6549..4e663398f77 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -21,6 +21,22 @@ #include #include +#if defined(CONFIG_CRYPTO_CTR) || defined(CONFIG_CRYPTO_CTR_MODULE) +#define HAS_CTR +#endif + +#if defined(CONFIG_CRYPTO_LRW) || defined(CONFIG_CRYPTO_LRW_MODULE) +#define HAS_LRW +#endif + +#if defined(CONFIG_CRYPTO_PCBC) || defined(CONFIG_CRYPTO_PCBC_MODULE) +#define HAS_PCBC +#endif + +#if defined(CONFIG_CRYPTO_XTS) || defined(CONFIG_CRYPTO_XTS_MODULE) +#define HAS_XTS +#endif + struct async_aes_ctx { struct cryptd_ablkcipher *cryptd_tfm; }; @@ -137,6 +153,41 @@ static struct crypto_alg aesni_alg = { } }; +static void __aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + aesni_enc(ctx, dst, src); +} + +static void __aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + aesni_dec(ctx, dst, src); +} + +static struct crypto_alg __aesni_alg = { + .cra_name = "__aes-aesni", + .cra_driver_name = "__driver-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(__aesni_alg.cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = AES_MIN_KEY_SIZE, + .cia_max_keysize = AES_MAX_KEY_SIZE, + .cia_setkey = aes_set_key, + .cia_encrypt = __aes_encrypt, + .cia_decrypt = __aes_decrypt + } + } +}; + static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) @@ -277,8 +328,16 @@ static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, unsigned int key_len) { struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base; + int err; - return crypto_ablkcipher_setkey(&ctx->cryptd_tfm->base, key, key_len); + crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); + crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm) + & CRYPTO_TFM_REQ_MASK); + err = crypto_ablkcipher_setkey(child, key, key_len); + crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child) + & CRYPTO_TFM_RES_MASK); + return err; } static int ablk_encrypt(struct ablkcipher_request *req) @@ -411,6 +470,163 @@ static struct crypto_alg ablk_cbc_alg = { }, }; +#ifdef HAS_CTR +static int ablk_ctr_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("fpu(ctr(__driver-aes-aesni))", + 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_ctr_alg = { + .cra_name = "ctr(aes)", + .cra_driver_name = "ctr-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_ctr_alg.cra_list), + .cra_init = ablk_ctr_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + .geniv = "chainiv", + }, + }, +}; +#endif + +#ifdef HAS_LRW +static int ablk_lrw_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("fpu(lrw(__driver-aes-aesni))", + 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_lrw_alg = { + .cra_name = "lrw(aes)", + .cra_driver_name = "lrw-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_lrw_alg.cra_list), + .cra_init = ablk_lrw_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE + AES_BLOCK_SIZE, + .max_keysize = AES_MAX_KEY_SIZE + AES_BLOCK_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; +#endif + +#ifdef HAS_PCBC +static int ablk_pcbc_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("fpu(pcbc(__driver-aes-aesni))", + 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_pcbc_alg = { + .cra_name = "pcbc(aes)", + .cra_driver_name = "pcbc-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_pcbc_alg.cra_list), + .cra_init = ablk_pcbc_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; +#endif + +#ifdef HAS_XTS +static int ablk_xts_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("fpu(xts(__driver-aes-aesni))", + 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_xts_alg = { + .cra_name = "xts(aes)", + .cra_driver_name = "xts-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_xts_alg.cra_list), + .cra_init = ablk_xts_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; +#endif + static int __init aesni_init(void) { int err; @@ -421,6 +637,8 @@ static int __init aesni_init(void) } if ((err = crypto_register_alg(&aesni_alg))) goto aes_err; + if ((err = crypto_register_alg(&__aesni_alg))) + goto __aes_err; if ((err = crypto_register_alg(&blk_ecb_alg))) goto blk_ecb_err; if ((err = crypto_register_alg(&blk_cbc_alg))) @@ -429,9 +647,41 @@ static int __init aesni_init(void) goto ablk_ecb_err; if ((err = crypto_register_alg(&ablk_cbc_alg))) goto ablk_cbc_err; +#ifdef HAS_CTR + if ((err = crypto_register_alg(&ablk_ctr_alg))) + goto ablk_ctr_err; +#endif +#ifdef HAS_LRW + if ((err = crypto_register_alg(&ablk_lrw_alg))) + goto ablk_lrw_err; +#endif +#ifdef HAS_PCBC + if ((err = crypto_register_alg(&ablk_pcbc_alg))) + goto ablk_pcbc_err; +#endif +#ifdef HAS_XTS + if ((err = crypto_register_alg(&ablk_xts_alg))) + goto ablk_xts_err; +#endif return err; +#ifdef HAS_XTS +ablk_xts_err: +#endif +#ifdef HAS_PCBC + crypto_unregister_alg(&ablk_pcbc_alg); +ablk_pcbc_err: +#endif +#ifdef HAS_LRW + crypto_unregister_alg(&ablk_lrw_alg); +ablk_lrw_err: +#endif +#ifdef HAS_CTR + crypto_unregister_alg(&ablk_ctr_alg); +ablk_ctr_err: +#endif + crypto_unregister_alg(&ablk_cbc_alg); ablk_cbc_err: crypto_unregister_alg(&ablk_ecb_alg); ablk_ecb_err: @@ -439,6 +689,8 @@ ablk_ecb_err: blk_cbc_err: crypto_unregister_alg(&blk_ecb_alg); blk_ecb_err: + crypto_unregister_alg(&__aesni_alg); +__aes_err: crypto_unregister_alg(&aesni_alg); aes_err: return err; @@ -446,10 +698,23 @@ aes_err: static void __exit aesni_exit(void) { +#ifdef HAS_XTS + crypto_unregister_alg(&ablk_xts_alg); +#endif +#ifdef HAS_PCBC + crypto_unregister_alg(&ablk_pcbc_alg); +#endif +#ifdef HAS_LRW + crypto_unregister_alg(&ablk_lrw_alg); +#endif +#ifdef HAS_CTR + crypto_unregister_alg(&ablk_ctr_alg); +#endif crypto_unregister_alg(&ablk_cbc_alg); crypto_unregister_alg(&ablk_ecb_alg); crypto_unregister_alg(&blk_cbc_alg); crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_alg(&__aesni_alg); crypto_unregister_alg(&aesni_alg); } -- cgit v1.2.3