From 1ca1b917940c24ca3d1f490118c5474168622953 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 16 Nov 2018 17:26:21 -0800 Subject: crypto: chacha20-generic - refactor to allow varying number of rounds In preparation for adding XChaCha12 support, rename/refactor chacha20-generic to support different numbers of rounds. The justification for needing XChaCha12 support is explained in more detail in the patch "crypto: chacha - add XChaCha12 support". The only difference between ChaCha{8,12,20} are the number of rounds itself; all other parts of the algorithm are the same. Therefore, remove the "20" from all definitions, structures, functions, files, etc. that will be shared by all ChaCha versions. Also make ->setkey() store the round count in the chacha_ctx (previously chacha20_ctx). The generic code then passes the round count through to chacha_block(). There will be a ->setkey() function for each explicitly allowed round count; the encrypt/decrypt functions will be the same. I decided not to do it the opposite way (same ->setkey() function for all round counts, with different encrypt/decrypt functions) because that would have required more boilerplate code in architecture-specific implementations of ChaCha and XChaCha. Reviewed-by: Ard Biesheuvel Acked-by: Martin Willi Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/arm/crypto/chacha20-neon-glue.c | 40 +++---- arch/arm64/crypto/chacha20-neon-glue.c | 40 +++---- arch/x86/crypto/chacha20_glue.c | 48 ++++---- crypto/Makefile | 2 +- crypto/chacha20_generic.c | 185 ------------------------------- crypto/chacha20poly1305.c | 10 +- crypto/chacha_generic.c | 193 +++++++++++++++++++++++++++++++++ drivers/char/random.c | 51 +++++---- drivers/crypto/caam/caamalg.c | 2 +- drivers/crypto/caam/caamalg_qi2.c | 8 +- drivers/crypto/caam/compat.h | 2 +- include/crypto/chacha.h | 47 ++++++++ include/crypto/chacha20.h | 42 ------- lib/Makefile | 2 +- lib/chacha.c | 117 ++++++++++++++++++++ lib/chacha20.c | 112 ------------------- 16 files changed, 459 insertions(+), 442 deletions(-) delete mode 100644 crypto/chacha20_generic.c create mode 100644 crypto/chacha_generic.c create mode 100644 include/crypto/chacha.h delete mode 100644 include/crypto/chacha20.h create mode 100644 lib/chacha.c delete mode 100644 lib/chacha20.c diff --git a/arch/arm/crypto/chacha20-neon-glue.c b/arch/arm/crypto/chacha20-neon-glue.c index 59a7be08e80c..7386eb1c1889 100644 --- a/arch/arm/crypto/chacha20-neon-glue.c +++ b/arch/arm/crypto/chacha20-neon-glue.c @@ -19,7 +19,7 @@ */ #include -#include +#include #include #include #include @@ -34,20 +34,20 @@ asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, unsigned int bytes) { - u8 buf[CHACHA20_BLOCK_SIZE]; + u8 buf[CHACHA_BLOCK_SIZE]; - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + while (bytes >= CHACHA_BLOCK_SIZE * 4) { chacha20_4block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; state[12] += 4; } - while (bytes >= CHACHA20_BLOCK_SIZE) { + while (bytes >= CHACHA_BLOCK_SIZE) { chacha20_block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; + bytes -= CHACHA_BLOCK_SIZE; + src += CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; state[12]++; } if (bytes) { @@ -60,17 +60,17 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, static int chacha20_neon(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk walk; u32 state[16]; int err; - if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd()) - return crypto_chacha20_crypt(req); + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha_crypt(req); err = skcipher_walk_virt(&walk, req, true); - crypto_chacha20_init(state, ctx, walk.iv); + crypto_chacha_init(state, ctx, walk.iv); kernel_neon_begin(); while (walk.nbytes > 0) { @@ -93,14 +93,14 @@ static struct skcipher_alg alg = { .base.cra_driver_name = "chacha20-neon", .base.cra_priority = 300, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .walksize = 4 * CHACHA20_BLOCK_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, .setkey = crypto_chacha20_setkey, .encrypt = chacha20_neon, .decrypt = chacha20_neon, diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index 727579c93ded..96e0cfb8c3f5 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -19,7 +19,7 @@ */ #include -#include +#include #include #include #include @@ -34,15 +34,15 @@ asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, unsigned int bytes) { - u8 buf[CHACHA20_BLOCK_SIZE]; + u8 buf[CHACHA_BLOCK_SIZE]; - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + while (bytes >= CHACHA_BLOCK_SIZE * 4) { kernel_neon_begin(); chacha20_4block_xor_neon(state, dst, src); kernel_neon_end(); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; state[12] += 4; } @@ -50,11 +50,11 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, return; kernel_neon_begin(); - while (bytes >= CHACHA20_BLOCK_SIZE) { + while (bytes >= CHACHA_BLOCK_SIZE) { chacha20_block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; + bytes -= CHACHA_BLOCK_SIZE; + src += CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; state[12]++; } if (bytes) { @@ -68,17 +68,17 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, static int chacha20_neon(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk walk; u32 state[16]; int err; - if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) - return crypto_chacha20_crypt(req); + if (!may_use_simd() || req->cryptlen <= CHACHA_BLOCK_SIZE) + return crypto_chacha_crypt(req); err = skcipher_walk_virt(&walk, req, false); - crypto_chacha20_init(state, ctx, walk.iv); + crypto_chacha_init(state, ctx, walk.iv); while (walk.nbytes > 0) { unsigned int nbytes = walk.nbytes; @@ -99,14 +99,14 @@ static struct skcipher_alg alg = { .base.cra_driver_name = "chacha20-neon", .base.cra_priority = 300, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .walksize = 4 * CHACHA20_BLOCK_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, .setkey = crypto_chacha20_setkey, .encrypt = chacha20_neon, .decrypt = chacha20_neon, diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 9fd84fe6ec09..1e9e66509226 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -10,7 +10,7 @@ */ #include -#include +#include #include #include #include @@ -35,8 +35,8 @@ static bool chacha20_use_avx2; static unsigned int chacha20_advance(unsigned int len, unsigned int maxblocks) { - len = min(len, maxblocks * CHACHA20_BLOCK_SIZE); - return round_up(len, CHACHA20_BLOCK_SIZE) / CHACHA20_BLOCK_SIZE; + len = min(len, maxblocks * CHACHA_BLOCK_SIZE); + return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE; } static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, @@ -44,38 +44,38 @@ static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, { #ifdef CONFIG_AS_AVX2 if (chacha20_use_avx2) { - while (bytes >= CHACHA20_BLOCK_SIZE * 8) { + while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha20_8block_xor_avx2(state, dst, src, bytes); - bytes -= CHACHA20_BLOCK_SIZE * 8; - src += CHACHA20_BLOCK_SIZE * 8; - dst += CHACHA20_BLOCK_SIZE * 8; + bytes -= CHACHA_BLOCK_SIZE * 8; + src += CHACHA_BLOCK_SIZE * 8; + dst += CHACHA_BLOCK_SIZE * 8; state[12] += 8; } - if (bytes > CHACHA20_BLOCK_SIZE * 4) { + if (bytes > CHACHA_BLOCK_SIZE * 4) { chacha20_8block_xor_avx2(state, dst, src, bytes); state[12] += chacha20_advance(bytes, 8); return; } - if (bytes > CHACHA20_BLOCK_SIZE * 2) { + if (bytes > CHACHA_BLOCK_SIZE * 2) { chacha20_4block_xor_avx2(state, dst, src, bytes); state[12] += chacha20_advance(bytes, 4); return; } - if (bytes > CHACHA20_BLOCK_SIZE) { + if (bytes > CHACHA_BLOCK_SIZE) { chacha20_2block_xor_avx2(state, dst, src, bytes); state[12] += chacha20_advance(bytes, 2); return; } } #endif - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + while (bytes >= CHACHA_BLOCK_SIZE * 4) { chacha20_4block_xor_ssse3(state, dst, src, bytes); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; state[12] += 4; } - if (bytes > CHACHA20_BLOCK_SIZE) { + if (bytes > CHACHA_BLOCK_SIZE) { chacha20_4block_xor_ssse3(state, dst, src, bytes); state[12] += chacha20_advance(bytes, 4); return; @@ -89,7 +89,7 @@ static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, static int chacha20_simd(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); u32 *state, state_buf[16 + 2] __aligned(8); struct skcipher_walk walk; int err; @@ -97,12 +97,12 @@ static int chacha20_simd(struct skcipher_request *req) BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16); state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN); - if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd()) - return crypto_chacha20_crypt(req); + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha_crypt(req); err = skcipher_walk_virt(&walk, req, true); - crypto_chacha20_init(state, ctx, walk.iv); + crypto_chacha_init(state, ctx, walk.iv); kernel_fpu_begin(); @@ -128,13 +128,13 @@ static struct skcipher_alg alg = { .base.cra_driver_name = "chacha20-simd", .base.cra_priority = 300, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, .setkey = crypto_chacha20_setkey, .encrypt = chacha20_simd, .decrypt = chacha20_simd, diff --git a/crypto/Makefile b/crypto/Makefile index abbd86fdbad2..102e8525814f 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -117,7 +117,7 @@ obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o obj-$(CONFIG_CRYPTO_SEED) += seed.o obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o -obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o +obj-$(CONFIG_CRYPTO_CHACHA20) += chacha_generic.o obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c deleted file mode 100644 index 4305b1b62b16..000000000000 --- a/crypto/chacha20_generic.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * ChaCha20 (RFC7539) and XChaCha20 stream cipher algorithms - * - * Copyright (C) 2015 Martin Willi - * Copyright (C) 2018 Google LLC - * - * 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 - -static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src, - unsigned int bytes) -{ - /* aligned to potentially speed up crypto_xor() */ - u8 stream[CHACHA20_BLOCK_SIZE] __aligned(sizeof(long)); - - if (dst != src) - memcpy(dst, src, bytes); - - while (bytes >= CHACHA20_BLOCK_SIZE) { - chacha20_block(state, stream); - crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE); - bytes -= CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; - } - if (bytes) { - chacha20_block(state, stream); - crypto_xor(dst, stream, bytes); - } -} - -static int chacha20_stream_xor(struct skcipher_request *req, - struct chacha20_ctx *ctx, u8 *iv) -{ - struct skcipher_walk walk; - u32 state[16]; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - crypto_chacha20_init(state, ctx, iv); - - while (walk.nbytes > 0) { - unsigned int nbytes = walk.nbytes; - - if (nbytes < walk.total) - nbytes = round_down(nbytes, walk.stride); - - chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, - nbytes); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); - } - - return err; -} - -void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv) -{ - state[0] = 0x61707865; /* "expa" */ - state[1] = 0x3320646e; /* "nd 3" */ - state[2] = 0x79622d32; /* "2-by" */ - state[3] = 0x6b206574; /* "te k" */ - state[4] = ctx->key[0]; - state[5] = ctx->key[1]; - state[6] = ctx->key[2]; - state[7] = ctx->key[3]; - state[8] = ctx->key[4]; - state[9] = ctx->key[5]; - state[10] = ctx->key[6]; - state[11] = ctx->key[7]; - state[12] = get_unaligned_le32(iv + 0); - state[13] = get_unaligned_le32(iv + 4); - state[14] = get_unaligned_le32(iv + 8); - state[15] = get_unaligned_le32(iv + 12); -} -EXPORT_SYMBOL_GPL(crypto_chacha20_init); - -int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keysize) -{ - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - int i; - - if (keysize != CHACHA20_KEY_SIZE) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(ctx->key); i++) - ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); - - return 0; -} -EXPORT_SYMBOL_GPL(crypto_chacha20_setkey); - -int crypto_chacha20_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - - return chacha20_stream_xor(req, ctx, req->iv); -} -EXPORT_SYMBOL_GPL(crypto_chacha20_crypt); - -int crypto_xchacha20_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - struct chacha20_ctx subctx; - u32 state[16]; - u8 real_iv[16]; - - /* Compute the subkey given the original key and first 128 nonce bits */ - crypto_chacha20_init(state, ctx, req->iv); - hchacha20_block(state, subctx.key); - - /* Build the real IV */ - memcpy(&real_iv[0], req->iv + 24, 8); /* stream position */ - memcpy(&real_iv[8], req->iv + 16, 8); /* remaining 64 nonce bits */ - - /* Generate the stream and XOR it with the data */ - return chacha20_stream_xor(req, &subctx, real_iv); -} -EXPORT_SYMBOL_GPL(crypto_xchacha20_crypt); - -static struct skcipher_alg algs[] = { - { - .base.cra_name = "chacha20", - .base.cra_driver_name = "chacha20-generic", - .base.cra_priority = 100, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), - .base.cra_module = THIS_MODULE, - - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, - .encrypt = crypto_chacha20_crypt, - .decrypt = crypto_chacha20_crypt, - }, { - .base.cra_name = "xchacha20", - .base.cra_driver_name = "xchacha20-generic", - .base.cra_priority = 100, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), - .base.cra_module = THIS_MODULE, - - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = XCHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, - .encrypt = crypto_xchacha20_crypt, - .decrypt = crypto_xchacha20_crypt, - } -}; - -static int __init chacha20_generic_mod_init(void) -{ - return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); -} - -static void __exit chacha20_generic_mod_fini(void) -{ - crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); -} - -module_init(chacha20_generic_mod_init); -module_exit(chacha20_generic_mod_fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Martin Willi "); -MODULE_DESCRIPTION("ChaCha20 and XChaCha20 stream ciphers (generic)"); -MODULE_ALIAS_CRYPTO("chacha20"); -MODULE_ALIAS_CRYPTO("chacha20-generic"); -MODULE_ALIAS_CRYPTO("xchacha20"); -MODULE_ALIAS_CRYPTO("xchacha20-generic"); diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c index f9dd5453046a..fef11446ab1b 100644 --- a/crypto/chacha20poly1305.c +++ b/crypto/chacha20poly1305.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include @@ -49,7 +49,7 @@ struct poly_req { }; struct chacha_req { - u8 iv[CHACHA20_IV_SIZE]; + u8 iv[CHACHA_IV_SIZE]; struct scatterlist src[1]; struct skcipher_request req; /* must be last member */ }; @@ -89,7 +89,7 @@ static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb) memcpy(iv, &leicb, sizeof(leicb)); memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen); memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv, - CHACHA20_IV_SIZE - sizeof(leicb) - ctx->saltlen); + CHACHA_IV_SIZE - sizeof(leicb) - ctx->saltlen); } static int poly_verify_tag(struct aead_request *req) @@ -492,7 +492,7 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, struct chachapoly_ctx *ctx = crypto_aead_ctx(aead); int err; - if (keylen != ctx->saltlen + CHACHA20_KEY_SIZE) + if (keylen != ctx->saltlen + CHACHA_KEY_SIZE) return -EINVAL; keylen -= ctx->saltlen; @@ -637,7 +637,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb, err = -EINVAL; /* Need 16-byte IV size, including Initial Block Counter value */ - if (crypto_skcipher_alg_ivsize(chacha) != CHACHA20_IV_SIZE) + if (crypto_skcipher_alg_ivsize(chacha) != CHACHA_IV_SIZE) goto out_drop_chacha; /* Not a stream cipher? */ if (chacha->base.cra_blocksize != 1) diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c new file mode 100644 index 000000000000..438f15a14054 --- /dev/null +++ b/crypto/chacha_generic.c @@ -0,0 +1,193 @@ +/* + * ChaCha20 (RFC7539) and XChaCha20 stream cipher algorithms + * + * Copyright (C) 2015 Martin Willi + * Copyright (C) 2018 Google LLC + * + * 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 + +static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + /* aligned to potentially speed up crypto_xor() */ + u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long)); + + if (dst != src) + memcpy(dst, src, bytes); + + while (bytes >= CHACHA_BLOCK_SIZE) { + chacha_block(state, stream, nrounds); + crypto_xor(dst, stream, CHACHA_BLOCK_SIZE); + bytes -= CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; + } + if (bytes) { + chacha_block(state, stream, nrounds); + crypto_xor(dst, stream, bytes); + } +} + +static int chacha_stream_xor(struct skcipher_request *req, + struct chacha_ctx *ctx, u8 *iv) +{ + struct skcipher_walk walk; + u32 state[16]; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + crypto_chacha_init(state, ctx, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + + chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, + nbytes, ctx->nrounds); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +} + +void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv) +{ + state[0] = 0x61707865; /* "expa" */ + state[1] = 0x3320646e; /* "nd 3" */ + state[2] = 0x79622d32; /* "2-by" */ + state[3] = 0x6b206574; /* "te k" */ + state[4] = ctx->key[0]; + state[5] = ctx->key[1]; + state[6] = ctx->key[2]; + state[7] = ctx->key[3]; + state[8] = ctx->key[4]; + state[9] = ctx->key[5]; + state[10] = ctx->key[6]; + state[11] = ctx->key[7]; + state[12] = get_unaligned_le32(iv + 0); + state[13] = get_unaligned_le32(iv + 4); + state[14] = get_unaligned_le32(iv + 8); + state[15] = get_unaligned_le32(iv + 12); +} +EXPORT_SYMBOL_GPL(crypto_chacha_init); + +static int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize, int nrounds) +{ + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + int i; + + if (keysize != CHACHA_KEY_SIZE) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(ctx->key); i++) + ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); + + ctx->nrounds = nrounds; + return 0; +} + +int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize) +{ + return chacha_setkey(tfm, key, keysize, 20); +} +EXPORT_SYMBOL_GPL(crypto_chacha20_setkey); + +int crypto_chacha_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + return chacha_stream_xor(req, ctx, req->iv); +} +EXPORT_SYMBOL_GPL(crypto_chacha_crypt); + +int crypto_xchacha_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx subctx; + u32 state[16]; + u8 real_iv[16]; + + /* Compute the subkey given the original key and first 128 nonce bits */ + crypto_chacha_init(state, ctx, req->iv); + hchacha_block(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + + /* Build the real IV */ + memcpy(&real_iv[0], req->iv + 24, 8); /* stream position */ + memcpy(&real_iv[8], req->iv + 16, 8); /* remaining 64 nonce bits */ + + /* Generate the stream and XOR it with the data */ + return chacha_stream_xor(req, &subctx, real_iv); +} +EXPORT_SYMBOL_GPL(crypto_xchacha_crypt); + +static struct skcipher_alg algs[] = { + { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-generic", + .base.cra_priority = 100, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = crypto_chacha_crypt, + .decrypt = crypto_chacha_crypt, + }, { + .base.cra_name = "xchacha20", + .base.cra_driver_name = "xchacha20-generic", + .base.cra_priority = 100, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = crypto_xchacha_crypt, + .decrypt = crypto_xchacha_crypt, + } +}; + +static int __init chacha_generic_mod_init(void) +{ + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +} + +static void __exit chacha_generic_mod_fini(void) +{ + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +} + +module_init(chacha_generic_mod_init); +module_exit(chacha_generic_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi "); +MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (generic)"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-generic"); +MODULE_ALIAS_CRYPTO("xchacha20"); +MODULE_ALIAS_CRYPTO("xchacha20-generic"); diff --git a/drivers/char/random.c b/drivers/char/random.c index 2eb70e76ed35..38c6d1af6d1c 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -265,7 +265,7 @@ #include #include #include -#include +#include #include #include @@ -431,11 +431,10 @@ static int crng_init = 0; #define crng_ready() (likely(crng_init > 1)) static int crng_init_cnt = 0; static unsigned long crng_global_init_time = 0; -#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE) -static void _extract_crng(struct crng_state *crng, - __u8 out[CHACHA20_BLOCK_SIZE]); +#define CRNG_INIT_CNT_THRESH (2*CHACHA_KEY_SIZE) +static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]); static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA20_BLOCK_SIZE], int used); + __u8 tmp[CHACHA_BLOCK_SIZE], int used); static void process_random_ready_list(void); static void _get_random_bytes(void *buf, int nbytes); @@ -863,7 +862,7 @@ static int crng_fast_load(const char *cp, size_t len) } p = (unsigned char *) &primary_crng.state[4]; while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) { - p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp; + p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp; cp++; crng_init_cnt++; len--; } spin_unlock_irqrestore(&primary_crng.lock, flags); @@ -895,7 +894,7 @@ static int crng_slow_load(const char *cp, size_t len) unsigned long flags; static unsigned char lfsr = 1; unsigned char tmp; - unsigned i, max = CHACHA20_KEY_SIZE; + unsigned i, max = CHACHA_KEY_SIZE; const char * src_buf = cp; char * dest_buf = (char *) &primary_crng.state[4]; @@ -913,8 +912,8 @@ static int crng_slow_load(const char *cp, size_t len) lfsr >>= 1; if (tmp & 1) lfsr ^= 0xE1; - tmp = dest_buf[i % CHACHA20_KEY_SIZE]; - dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr; + tmp = dest_buf[i % CHACHA_KEY_SIZE]; + dest_buf[i % CHACHA_KEY_SIZE] ^= src_buf[i % len] ^ lfsr; lfsr += (tmp << 3) | (tmp >> 5); } spin_unlock_irqrestore(&primary_crng.lock, flags); @@ -926,7 +925,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) unsigned long flags; int i, num; union { - __u8 block[CHACHA20_BLOCK_SIZE]; + __u8 block[CHACHA_BLOCK_SIZE]; __u32 key[8]; } buf; @@ -937,7 +936,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } else { _extract_crng(&primary_crng, buf.block); _crng_backtrack_protect(&primary_crng, buf.block, - CHACHA20_KEY_SIZE); + CHACHA_KEY_SIZE); } spin_lock_irqsave(&crng->lock, flags); for (i = 0; i < 8; i++) { @@ -973,7 +972,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } static void _extract_crng(struct crng_state *crng, - __u8 out[CHACHA20_BLOCK_SIZE]) + __u8 out[CHACHA_BLOCK_SIZE]) { unsigned long v, flags; @@ -990,7 +989,7 @@ static void _extract_crng(struct crng_state *crng, spin_unlock_irqrestore(&crng->lock, flags); } -static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE]) +static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE]) { struct crng_state *crng = NULL; @@ -1008,14 +1007,14 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE]) * enough) to mutate the CRNG key to provide backtracking protection. */ static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA20_BLOCK_SIZE], int used) + __u8 tmp[CHACHA_BLOCK_SIZE], int used) { unsigned long flags; __u32 *s, *d; int i; used = round_up(used, sizeof(__u32)); - if (used + CHACHA20_KEY_SIZE > CHACHA20_BLOCK_SIZE) { + if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) { extract_crng(tmp); used = 0; } @@ -1027,7 +1026,7 @@ static void _crng_backtrack_protect(struct crng_state *crng, spin_unlock_irqrestore(&crng->lock, flags); } -static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used) +static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used) { struct crng_state *crng = NULL; @@ -1042,8 +1041,8 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used) static ssize_t extract_crng_user(void __user *buf, size_t nbytes) { - ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE; - __u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4); + ssize_t ret = 0, i = CHACHA_BLOCK_SIZE; + __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); int large_request = (nbytes > 256); while (nbytes) { @@ -1057,7 +1056,7 @@ static ssize_t extract_crng_user(void __user *buf, size_t nbytes) } extract_crng(tmp); - i = min_t(int, nbytes, CHACHA20_BLOCK_SIZE); + i = min_t(int, nbytes, CHACHA_BLOCK_SIZE); if (copy_to_user(buf, tmp, i)) { ret = -EFAULT; break; @@ -1622,14 +1621,14 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, */ static void _get_random_bytes(void *buf, int nbytes) { - __u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4); + __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); trace_get_random_bytes(nbytes, _RET_IP_); - while (nbytes >= CHACHA20_BLOCK_SIZE) { + while (nbytes >= CHACHA_BLOCK_SIZE) { extract_crng(buf); - buf += CHACHA20_BLOCK_SIZE; - nbytes -= CHACHA20_BLOCK_SIZE; + buf += CHACHA_BLOCK_SIZE; + nbytes -= CHACHA_BLOCK_SIZE; } if (nbytes > 0) { @@ -1637,7 +1636,7 @@ static void _get_random_bytes(void *buf, int nbytes) memcpy(buf, tmp, nbytes); crng_backtrack_protect(tmp, nbytes); } else - crng_backtrack_protect(tmp, CHACHA20_BLOCK_SIZE); + crng_backtrack_protect(tmp, CHACHA_BLOCK_SIZE); memzero_explicit(tmp, sizeof(tmp)); } @@ -2208,8 +2207,8 @@ struct ctl_table random_table[] = { struct batched_entropy { union { - u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)]; - u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)]; + u64 entropy_u64[CHACHA_BLOCK_SIZE / sizeof(u64)]; + u32 entropy_u32[CHACHA_BLOCK_SIZE / sizeof(u32)]; }; unsigned int position; }; diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index 523565ce0060..92e593e2069a 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -559,7 +559,7 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, unsigned int ivsize = crypto_aead_ivsize(aead); unsigned int saltlen = CHACHAPOLY_IV_SIZE - ivsize; - if (keylen != CHACHA20_KEY_SIZE + saltlen) { + if (keylen != CHACHA_KEY_SIZE + saltlen) { crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 2598640aa98b..425d5d974613 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -591,7 +591,7 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, unsigned int ivsize = crypto_aead_ivsize(aead); unsigned int saltlen = CHACHAPOLY_IV_SIZE - ivsize; - if (keylen != CHACHA20_KEY_SIZE + saltlen) { + if (keylen != CHACHA_KEY_SIZE + saltlen) { crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } @@ -1577,9 +1577,9 @@ static struct caam_skcipher_alg driver_algs[] = { .setkey = skcipher_setkey, .encrypt = skcipher_encrypt, .decrypt = skcipher_decrypt, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, }, .caam.class1_alg_type = OP_ALG_ALGSEL_CHACHA20, }, diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h index 8bde903f9f4a..87d9efe4c7aa 100644 --- a/drivers/crypto/caam/compat.h +++ b/drivers/crypto/caam/compat.h @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h new file mode 100644 index 000000000000..b722a23e54bb --- /dev/null +++ b/include/crypto/chacha.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common values and helper functions for the ChaCha and XChaCha stream ciphers. + * + * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's + * security. Here they share the same key size, tfm context, and setkey + * function; only their IV size and encrypt/decrypt function differ. + */ + +#ifndef _CRYPTO_CHACHA_H +#define _CRYPTO_CHACHA_H + +#include +#include +#include + +/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ +#define CHACHA_IV_SIZE 16 + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 +#define CHACHAPOLY_IV_SIZE 12 + +/* 192-bit nonce, then 64-bit stream position */ +#define XCHACHA_IV_SIZE 32 + +struct chacha_ctx { + u32 key[8]; + int nrounds; +}; + +void chacha_block(u32 *state, u8 *stream, int nrounds); +static inline void chacha20_block(u32 *state, u8 *stream) +{ + chacha_block(state, stream, 20); +} +void hchacha_block(const u32 *in, u32 *out, int nrounds); + +void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv); + +int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize); + +int crypto_chacha_crypt(struct skcipher_request *req); +int crypto_xchacha_crypt(struct skcipher_request *req); + +#endif /* _CRYPTO_CHACHA_H */ diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h deleted file mode 100644 index c24b4ac03b85..000000000000 --- a/include/crypto/chacha20.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Common values and helper functions for the ChaCha20 and XChaCha20 algorithms. - * - * XChaCha20 extends ChaCha20's nonce to 192 bits, while provably retaining - * ChaCha20's security. Here they share the same key size, tfm context, and - * setkey function; only their IV size and encrypt/decrypt function differ. - */ - -#ifndef _CRYPTO_CHACHA20_H -#define _CRYPTO_CHACHA20_H - -#include -#include -#include - -/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ -#define CHACHA20_IV_SIZE 16 - -#define CHACHA20_KEY_SIZE 32 -#define CHACHA20_BLOCK_SIZE 64 -#define CHACHAPOLY_IV_SIZE 12 - -/* 192-bit nonce, then 64-bit stream position */ -#define XCHACHA20_IV_SIZE 32 - -struct chacha20_ctx { - u32 key[8]; -}; - -void chacha20_block(u32 *state, u8 *stream); -void hchacha20_block(const u32 *in, u32 *out); - -void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv); - -int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keysize); - -int crypto_chacha20_crypt(struct skcipher_request *req); -int crypto_xchacha20_crypt(struct skcipher_request *req); - -#endif diff --git a/lib/Makefile b/lib/Makefile index db06d1237898..4c2b6fc5cde9 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -20,7 +20,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o timerqueue.o xarray.o \ idr.o int_sqrt.o extable.o \ - sha1.o chacha20.o irq_regs.o argv_split.o \ + sha1.o chacha.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ diff --git a/lib/chacha.c b/lib/chacha.c new file mode 100644 index 000000000000..1bdc688c18df --- /dev/null +++ b/lib/chacha.c @@ -0,0 +1,117 @@ +/* + * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) + * + * Copyright (C) 2015 Martin Willi + * + * 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 + +static void chacha_permute(u32 *x, int nrounds) +{ + int i; + + /* whitelist the allowed round counts */ + WARN_ON_ONCE(nrounds != 20); + + for (i = 0; i < nrounds; i += 2) { + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); + + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); + + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); + + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); + + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); + + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); + + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); + + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); + } +} + +/** + * chacha_block - generate one keystream block and increment block counter + * @state: input state matrix (16 32-bit words) + * @stream: output keystream block (64 bytes) + * @nrounds: number of rounds (currently must be 20) + * + * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. + * The caller has already converted the endianness of the input. This function + * also handles incrementing the block counter in the input matrix. + */ +void chacha_block(u32 *state, u8 *stream, int nrounds) +{ + u32 x[16]; + int i; + + memcpy(x, state, 64); + + chacha_permute(x, nrounds); + + for (i = 0; i < ARRAY_SIZE(x); i++) + put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); + + state[12]++; +} +EXPORT_SYMBOL(chacha_block); + +/** + * hchacha_block - abbreviated ChaCha core, for XChaCha + * @in: input state matrix (16 32-bit words) + * @out: output (8 32-bit words) + * @nrounds: number of rounds (currently must be 20) + * + * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step + * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha + * skips the final addition of the initial state, and outputs only certain words + * of the state. It should not be used for streaming directly. + */ +void hchacha_block(const u32 *in, u32 *out, int nrounds) +{ + u32 x[16]; + + memcpy(x, in, 64); + + chacha_permute(x, nrounds); + + memcpy(&out[0], &x[0], 16); + memcpy(&out[4], &x[12], 16); +} +EXPORT_SYMBOL(hchacha_block); diff --git a/lib/chacha20.c b/lib/chacha20.c deleted file mode 100644 index 6a484e16171d..000000000000 --- a/lib/chacha20.c +++ /dev/null @@ -1,112 +0,0 @@ -/* - * The "hash function" used as the core of the ChaCha20 stream cipher (RFC7539) - * - * Copyright (C) 2015 Martin Willi - * - * 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 - -static void chacha20_permute(u32 *x) -{ - int i; - - for (i = 0; i < 20; i += 2) { - x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); - x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); - x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); - x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); - - x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); - x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); - x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); - x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); - - x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); - x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); - x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); - x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); - - x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); - x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); - x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); - x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); - - x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); - x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); - x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); - x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); - - x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); - x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); - x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); - x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); - - x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); - x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); - x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); - x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); - - x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); - x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); - x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); - x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); - } -} - -/** - * chacha20_block - generate one keystream block and increment block counter - * @state: input state matrix (16 32-bit words) - * @stream: output keystream block (64 bytes) - * - * This is the ChaCha20 core, a function from 64-byte strings to 64-byte - * strings. The caller has already converted the endianness of the input. This - * function also handles incrementing the block counter in the input matrix. - */ -void chacha20_block(u32 *state, u8 *stream) -{ - u32 x[16]; - int i; - - memcpy(x, state, 64); - - chacha20_permute(x); - - for (i = 0; i < ARRAY_SIZE(x); i++) - put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); - - state[12]++; -} -EXPORT_SYMBOL(chacha20_block); - -/** - * hchacha20_block - abbreviated ChaCha20 core, for XChaCha20 - * @in: input state matrix (16 32-bit words) - * @out: output (8 32-bit words) - * - * HChaCha20 is the ChaCha equivalent of HSalsa20 and is an intermediate step - * towards XChaCha20 (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). - * HChaCha20 skips the final addition of the initial state, and outputs only - * certain words of the state. It should not be used for streaming directly. - */ -void hchacha20_block(const u32 *in, u32 *out) -{ - u32 x[16]; - - memcpy(x, in, 64); - - chacha20_permute(x); - - memcpy(&out[0], &x[0], 16); - memcpy(&out[4], &x[12], 16); -} -EXPORT_SYMBOL(hchacha20_block); -- cgit v1.2.3