diff options
Diffstat (limited to 'lib/crypto')
-rw-r--r-- | lib/crypto/Kconfig | 3 | ||||
-rw-r--r-- | lib/crypto/Makefile | 3 | ||||
-rw-r--r-- | lib/crypto/blake2s-selftest.c | 41 | ||||
-rw-r--r-- | lib/crypto/blake2s.c | 37 | ||||
-rw-r--r-- | lib/crypto/sha1.c | 140 |
5 files changed, 217 insertions, 7 deletions
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 2082af43d51f..9ff549f63540 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -121,6 +121,9 @@ config CRYPTO_LIB_CHACHA20POLY1305 select CRYPTO_LIB_POLY1305 select CRYPTO_ALGAPI +config CRYPTO_LIB_SHA1 + tristate + config CRYPTO_LIB_SHA256 tristate diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 26be2bbe09c5..919cbb2c220d 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -34,6 +34,9 @@ libpoly1305-y := poly1305-donna32.o libpoly1305-$(CONFIG_ARCH_SUPPORTS_INT128) := poly1305-donna64.o libpoly1305-y += poly1305.o +obj-$(CONFIG_CRYPTO_LIB_SHA1) += libsha1.o +libsha1-y := sha1.o + obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o libsha256-y := sha256.o diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c index 409e4b728770..7d77dea15587 100644 --- a/lib/crypto/blake2s-selftest.c +++ b/lib/crypto/blake2s-selftest.c @@ -4,6 +4,8 @@ */ #include <crypto/internal/blake2s.h> +#include <linux/kernel.h> +#include <linux/random.h> #include <linux/string.h> /* @@ -587,5 +589,44 @@ bool __init blake2s_selftest(void) } } + for (i = 0; i < 32; ++i) { + enum { TEST_ALIGNMENT = 16 }; + u8 unaligned_block[BLAKE2S_BLOCK_SIZE + TEST_ALIGNMENT - 1] + __aligned(TEST_ALIGNMENT); + u8 blocks[BLAKE2S_BLOCK_SIZE * 2]; + struct blake2s_state state1, state2; + + get_random_bytes(blocks, sizeof(blocks)); + get_random_bytes(&state, sizeof(state)); + +#if defined(CONFIG_CRYPTO_LIB_BLAKE2S_GENERIC) && \ + defined(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S) + memcpy(&state1, &state, sizeof(state1)); + memcpy(&state2, &state, sizeof(state2)); + blake2s_compress(&state1, blocks, 2, BLAKE2S_BLOCK_SIZE); + blake2s_compress_generic(&state2, blocks, 2, BLAKE2S_BLOCK_SIZE); + if (memcmp(&state1, &state2, sizeof(state1))) { + pr_err("blake2s random compress self-test %d: FAIL\n", + i + 1); + success = false; + } +#endif + + memcpy(&state1, &state, sizeof(state1)); + blake2s_compress(&state1, blocks, 1, BLAKE2S_BLOCK_SIZE); + for (l = 1; l < TEST_ALIGNMENT; ++l) { + memcpy(unaligned_block + l, blocks, + BLAKE2S_BLOCK_SIZE); + memcpy(&state2, &state, sizeof(state2)); + blake2s_compress(&state2, unaligned_block + l, 1, + BLAKE2S_BLOCK_SIZE); + if (memcmp(&state1, &state2, sizeof(state1))) { + pr_err("blake2s random compress align %d self-test %d: FAIL\n", + l, i + 1); + success = false; + } + } + } + return success; } diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index c71c09621c09..98e688c6d891 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -16,16 +16,44 @@ #include <linux/init.h> #include <linux/bug.h> +static inline void blake2s_set_lastblock(struct blake2s_state *state) +{ + state->f[0] = -1; +} + void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { - __blake2s_update(state, in, inlen, false); + const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; + + if (unlikely(!inlen)) + return; + if (inlen > fill) { + memcpy(state->buf + state->buflen, in, fill); + blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); + state->buflen = 0; + in += fill; + inlen -= fill; + } + if (inlen > BLAKE2S_BLOCK_SIZE) { + const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); + blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); + inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); + } + memcpy(state->buf + state->buflen, in, inlen); + state->buflen += inlen; } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); - __blake2s_final(state, out, false); + blake2s_set_lastblock(state); + memset(state->buf + state->buflen, 0, + BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ + blake2s_compress(state, state->buf, 1, state->buflen); + cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); + memcpy(out, state->h, state->outlen); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); @@ -38,12 +66,7 @@ static int __init blake2s_mod_init(void) return 0; } -static void __exit blake2s_mod_exit(void) -{ -} - module_init(blake2s_mod_init); -module_exit(blake2s_mod_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); diff --git a/lib/crypto/sha1.c b/lib/crypto/sha1.c new file mode 100644 index 000000000000..1aebe7be9401 --- /dev/null +++ b/lib/crypto/sha1.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SHA1 routine optimized to do word accesses rather than byte accesses, + * and to avoid unnecessary copies into the context array. + * + * This was based on the git SHA1 implementation. + */ + +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/module.h> +#include <linux/bitops.h> +#include <linux/string.h> +#include <crypto/sha1.h> +#include <asm/unaligned.h> + +/* + * If you have 32 registers or more, the compiler can (and should) + * try to change the array[] accesses into registers. However, on + * machines with less than ~25 registers, that won't really work, + * and at least gcc will make an unholy mess of it. + * + * So to avoid that mess which just slows things down, we force + * the stores to memory to actually happen (we might be better off + * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as + * suggested by Artur Skawina - that will also make gcc unable to + * try to do the silly "optimize away loads" part because it won't + * see what the value will be). + * + * Ben Herrenschmidt reports that on PPC, the C version comes close + * to the optimized asm with this (ie on PPC you don't want that + * 'volatile', since there are lots of registers). + * + * On ARM we get the best code generation by forcing a full memory barrier + * between each SHA_ROUND, otherwise gcc happily get wild with spilling and + * the stack frame size simply explode and performance goes down the drain. + */ + +#ifdef CONFIG_X86 + #define setW(x, val) (*(volatile __u32 *)&W(x) = (val)) +#elif defined(CONFIG_ARM) + #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0) +#else + #define setW(x, val) (W(x) = (val)) +#endif + +/* This "rolls" over the 512-bit array */ +#define W(x) (array[(x)&15]) + +/* + * Where do we get the source from? The first 16 iterations get it from + * the input data, the next mix it from the 512-bit array. + */ +#define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t) +#define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1) + +#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \ + __u32 TEMP = input(t); setW(t, TEMP); \ + E += TEMP + rol32(A,5) + (fn) + (constant); \ + B = ror32(B, 2); \ + TEMP = E; E = D; D = C; C = B; B = A; A = TEMP; } while (0) + +#define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) +#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) +#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E ) +#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E ) +#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0xca62c1d6, A, B, C, D, E ) + +/** + * sha1_transform - single block SHA1 transform (deprecated) + * + * @digest: 160 bit digest to update + * @data: 512 bits of data to hash + * @array: 16 words of workspace (see note) + * + * This function executes SHA-1's internal compression function. It updates the + * 160-bit internal state (@digest) with a single 512-bit data block (@data). + * + * Don't use this function. SHA-1 is no longer considered secure. And even if + * you do have to use SHA-1, this isn't the correct way to hash something with + * SHA-1 as this doesn't handle padding and finalization. + * + * Note: If the hash is security sensitive, the caller should be sure + * to clear the workspace. This is left to the caller to avoid + * unnecessary clears between chained hashing operations. + */ +void sha1_transform(__u32 *digest, const char *data, __u32 *array) +{ + __u32 A, B, C, D, E; + unsigned int i = 0; + + A = digest[0]; + B = digest[1]; + C = digest[2]; + D = digest[3]; + E = digest[4]; + + /* Round 1 - iterations 0-16 take their input from 'data' */ + for (; i < 16; ++i) + T_0_15(i, A, B, C, D, E); + + /* Round 1 - tail. Input from 512-bit mixing array */ + for (; i < 20; ++i) + T_16_19(i, A, B, C, D, E); + + /* Round 2 */ + for (; i < 40; ++i) + T_20_39(i, A, B, C, D, E); + + /* Round 3 */ + for (; i < 60; ++i) + T_40_59(i, A, B, C, D, E); + + /* Round 4 */ + for (; i < 80; ++i) + T_60_79(i, A, B, C, D, E); + + digest[0] += A; + digest[1] += B; + digest[2] += C; + digest[3] += D; + digest[4] += E; +} +EXPORT_SYMBOL(sha1_transform); + +/** + * sha1_init - initialize the vectors for a SHA1 digest + * @buf: vector to initialize + */ +void sha1_init(__u32 *buf) +{ + buf[0] = 0x67452301; + buf[1] = 0xefcdab89; + buf[2] = 0x98badcfe; + buf[3] = 0x10325476; + buf[4] = 0xc3d2e1f0; +} +EXPORT_SYMBOL(sha1_init); + +MODULE_LICENSE("GPL"); |