--- zzzz-none-000/linux-3.10.107/arch/x86/crypto/sha512_ssse3_glue.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/x86/crypto/sha512_ssse3_glue.c 2021-02-04 17:41:59.000000000 +0000 @@ -34,243 +34,309 @@ #include #include #include -#include -#include -#include -#include +#include +#include #include -asmlinkage void sha512_transform_ssse3(const char *data, u64 *digest, - u64 rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha512_transform_avx(const char *data, u64 *digest, - u64 rounds); -#endif -#ifdef CONFIG_AS_AVX2 -asmlinkage void sha512_transform_rorx(const char *data, u64 *digest, - u64 rounds); -#endif - -static asmlinkage void (*sha512_transform_asm)(const char *, u64 *, u64); +asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data, + u64 rounds); +typedef void (sha512_transform_fn)(u64 *digest, const char *data, u64 rounds); -static int sha512_ssse3_init(struct shash_desc *desc) +static int sha512_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha512_transform_fn *sha512_xform) { struct sha512_state *sctx = shash_desc_ctx(desc); - sctx->state[0] = SHA512_H0; - sctx->state[1] = SHA512_H1; - sctx->state[2] = SHA512_H2; - sctx->state[3] = SHA512_H3; - sctx->state[4] = SHA512_H4; - sctx->state[5] = SHA512_H5; - sctx->state[6] = SHA512_H6; - sctx->state[7] = SHA512_H7; - sctx->count[0] = sctx->count[1] = 0; + if (!irq_fpu_usable() || + (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE) + return crypto_sha512_update(desc, data, len); + + /* make sure casting to sha512_block_fn() is safe */ + BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0); + + kernel_fpu_begin(); + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_xform); + kernel_fpu_end(); return 0; } -static int __sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) +static int sha512_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha512_transform_fn *sha512_xform) { - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; + if (!irq_fpu_usable()) + return crypto_sha512_finup(desc, data, len, out); - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; + kernel_fpu_begin(); + if (len) + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_xform); + sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_xform); + kernel_fpu_end(); - if (partial) { - done = SHA512_BLOCK_SIZE - partial; - memcpy(sctx->buf + partial, data, done); - sha512_transform_asm(sctx->buf, sctx->state, 1); - } + return sha512_base_finish(desc, out); +} - if (len - done >= SHA512_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE; +static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_ssse3); +} - sha512_transform_asm(data + done, sctx->state, (u64) rounds); +static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_ssse3); +} - done += rounds * SHA512_BLOCK_SIZE; - } +/* Add padding and return the message digest. */ +static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) +{ + return sha512_ssse3_finup(desc, NULL, 0, out); +} - memcpy(sctx->buf, data + done, len - done); +static struct shash_alg sha512_ssse3_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_ssse3_update, + .final = sha512_ssse3_final, + .finup = sha512_ssse3_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-ssse3", + .cra_priority = 150, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_ssse3_update, + .final = sha512_ssse3_final, + .finup = sha512_ssse3_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-ssse3", + .cra_priority = 150, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; +static int register_sha512_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); return 0; } -static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static void unregister_sha512_ssse3(void) { - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; - int res; - - /* Handle the fast case right here */ - if (partial + len < SHA512_BLOCK_SIZE) { - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; - memcpy(sctx->buf + partial, data, len); + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); +} - return 0; +#ifdef CONFIG_AS_AVX +asmlinkage void sha512_transform_avx(u64 *digest, const char *data, + u64 rounds); +static bool avx_usable(void) +{ + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); + return false; } - if (!irq_fpu_usable()) { - res = crypto_sha512_update(desc, data, len); - } else { - kernel_fpu_begin(); - res = __sha512_ssse3_update(desc, data, len, partial); - kernel_fpu_end(); - } + return true; +} - return res; +static int sha512_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_avx); } +static int sha512_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_avx); +} /* Add padding and return the message digest. */ -static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) +static int sha512_avx_final(struct shash_desc *desc, u8 *out) { - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be64 *dst = (__be64 *)out; - __be64 bits[2]; - static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, }; - - /* save number of bits */ - bits[1] = cpu_to_be64(sctx->count[0] << 3); - bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); - - /* Pad out to 112 mod 128 and append length */ - index = sctx->count[0] & 0x7f; - padlen = (index < 112) ? (112 - index) : ((128+112) - index); - - if (!irq_fpu_usable()) { - crypto_sha512_update(desc, padding, padlen); - crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_fpu_begin(); - /* We need to fill a whole block for __sha512_ssse3_update() */ - if (padlen <= 112) { - sctx->count[0] += padlen; - if (sctx->count[0] < padlen) - sctx->count[1]++; - memcpy(sctx->buf + index, padding, padlen); - } else { - __sha512_ssse3_update(desc, padding, padlen, index); - } - __sha512_ssse3_update(desc, (const u8 *)&bits, - sizeof(bits), 112); - kernel_fpu_end(); - } - - /* Store state in digest */ - for (i = 0; i < 8; i++) - dst[i] = cpu_to_be64(sctx->state[i]); + return sha512_avx_finup(desc, NULL, 0, out); +} - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); +static struct shash_alg sha512_avx_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; +static int register_sha512_avx(void) +{ + if (avx_usable()) + return crypto_register_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); return 0; } -static int sha512_ssse3_export(struct shash_desc *desc, void *out) +static void unregister_sha512_avx(void) { - struct sha512_state *sctx = shash_desc_ctx(desc); + if (avx_usable()) + crypto_unregister_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); +} +#else +static inline int register_sha512_avx(void) { return 0; } +static inline void unregister_sha512_avx(void) { } +#endif - memcpy(out, sctx, sizeof(*sctx)); +#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) +asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, + u64 rounds); - return 0; +static int sha512_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_rorx); } -static int sha512_ssse3_import(struct shash_desc *desc, const void *in) +static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - struct sha512_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); + return sha512_finup(desc, data, len, out, sha512_transform_rorx); +} - return 0; +/* Add padding and return the message digest. */ +static int sha512_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha512_avx2_finup(desc, NULL, 0, out); } -static struct shash_alg alg = { +static struct shash_alg sha512_avx2_algs[] = { { .digestsize = SHA512_DIGEST_SIZE, - .init = sha512_ssse3_init, - .update = sha512_ssse3_update, - .final = sha512_ssse3_final, - .export = sha512_ssse3_export, - .import = sha512_ssse3_import, + .init = sha512_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, .descsize = sizeof(struct sha512_state), - .statesize = sizeof(struct sha512_state), .base = { .cra_name = "sha512", - .cra_driver_name = "sha512-ssse3", - .cra_priority = 150, + .cra_driver_name = "sha512-avx2", + .cra_priority = 170, .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } -}; +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; -#ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +static bool avx2_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_BMI2)) + return true; - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + return false; +} - return false; - } +static int register_sha512_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); + return 0; +} - return true; +static void unregister_sha512_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); } +#else +static inline int register_sha512_avx2(void) { return 0; } +static inline void unregister_sha512_avx2(void) { } #endif static int __init sha512_ssse3_mod_init(void) { - /* test for SSE3 first */ - if (cpu_has_ssse3) - sha512_transform_asm = sha512_transform_ssse3; -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { -#ifdef CONFIG_AS_AVX2 - if (boot_cpu_has(X86_FEATURE_AVX2)) - sha512_transform_asm = sha512_transform_rorx; - else -#endif - sha512_transform_asm = sha512_transform_avx; + if (register_sha512_ssse3()) + goto fail; + + if (register_sha512_avx()) { + unregister_sha512_ssse3(); + goto fail; } -#endif - if (sha512_transform_asm) { -#ifdef CONFIG_AS_AVX - if (sha512_transform_asm == sha512_transform_avx) - pr_info("Using AVX optimized SHA-512 implementation\n"); -#ifdef CONFIG_AS_AVX2 - else if (sha512_transform_asm == sha512_transform_rorx) - pr_info("Using AVX2 optimized SHA-512 implementation\n"); -#endif - else -#endif - pr_info("Using SSSE3 optimized SHA-512 implementation\n"); - return crypto_register_shash(&alg); + if (register_sha512_avx2()) { + unregister_sha512_avx(); + unregister_sha512_ssse3(); + goto fail; } - pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + return 0; +fail: return -ENODEV; } static void __exit sha512_ssse3_mod_fini(void) { - crypto_unregister_shash(&alg); + unregister_sha512_avx2(); + unregister_sha512_avx(); + unregister_sha512_ssse3(); } module_init(sha512_ssse3_mod_init); @@ -280,3 +346,4 @@ MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated"); MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha384");