diff options
Diffstat (limited to 'arch/x86/crypto')
| -rw-r--r-- | arch/x86/crypto/Makefile | 7 | ||||
| -rw-r--r-- | arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 232 | ||||
| -rw-r--r-- | arch/x86/crypto/aesni-intel_glue.c | 114 | ||||
| -rw-r--r-- | arch/x86/crypto/blake2s-glue.c | 3 | ||||
| -rw-r--r-- | arch/x86/crypto/blake2s-shash.c | 77 | ||||
| -rw-r--r-- | arch/x86/crypto/blowfish_glue.c | 4 | ||||
| -rw-r--r-- | arch/x86/crypto/polyval-clmulni_asm.S | 321 | ||||
| -rw-r--r-- | arch/x86/crypto/polyval-clmulni_glue.c | 203 |
8 files changed, 796 insertions, 165 deletions
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 2831685adf6f..04d07ab744b2 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -61,14 +61,15 @@ sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o -obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o -blake2s-x86_64-y := blake2s-shash.o -obj-$(if $(CONFIG_CRYPTO_BLAKE2S_X86),y) += libblake2s-x86_64.o +obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o +obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o +polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o + obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o crc32c-intel-y := crc32c-intel_glue.o crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 43852ba6e19c..2402b9418cd7 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -23,6 +23,11 @@ #define VMOVDQ vmovdqu +/* + * Note: the "x" prefix in these aliases means "this is an xmm register". The + * alias prefixes have no relation to XCTR where the "X" prefix means "XOR + * counter". + */ #define xdata0 %xmm0 #define xdata1 %xmm1 #define xdata2 %xmm2 @@ -31,8 +36,10 @@ #define xdata5 %xmm5 #define xdata6 %xmm6 #define xdata7 %xmm7 -#define xcounter %xmm8 -#define xbyteswap %xmm9 +#define xcounter %xmm8 // CTR mode only +#define xiv %xmm8 // XCTR mode only +#define xbyteswap %xmm9 // CTR mode only +#define xtmp %xmm9 // XCTR mode only #define xkey0 %xmm10 #define xkey4 %xmm11 #define xkey8 %xmm12 @@ -45,7 +52,7 @@ #define p_keys %rdx #define p_out %rcx #define num_bytes %r8 - +#define counter %r9 // XCTR mode only #define tmp %r10 #define DDQ_DATA 0 #define XDATA 1 @@ -102,7 +109,7 @@ ddq_add_8: * do_aes num_in_par load_keys key_len * This increments p_in, but not p_out */ -.macro do_aes b, k, key_len +.macro do_aes b, k, key_len, xctr .set by, \b .set load_keys, \k .set klen, \key_len @@ -111,29 +118,48 @@ ddq_add_8: vmovdqa 0*16(p_keys), xkey0 .endif - vpshufb xbyteswap, xcounter, xdata0 - - .set i, 1 - .rept (by - 1) - club XDATA, i - vpaddq (ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata - vptest ddq_low_msk(%rip), var_xdata - jnz 1f - vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata - vpaddq ddq_high_add_1(%rip), xcounter, xcounter - 1: - vpshufb xbyteswap, var_xdata, var_xdata - .set i, (i +1) - .endr + .if \xctr + movq counter, xtmp + .set i, 0 + .rept (by) + club XDATA, i + vpaddq (ddq_add_1 + 16 * i)(%rip), xtmp, var_xdata + .set i, (i +1) + .endr + .set i, 0 + .rept (by) + club XDATA, i + vpxor xiv, var_xdata, var_xdata + .set i, (i +1) + .endr + .else + vpshufb xbyteswap, xcounter, xdata0 + .set i, 1 + .rept (by - 1) + club XDATA, i + vpaddq (ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata + vptest ddq_low_msk(%rip), var_xdata + jnz 1f + vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata + vpaddq ddq_high_add_1(%rip), xcounter, xcounter + 1: + vpshufb xbyteswap, var_xdata, var_xdata + .set i, (i +1) + .endr + .endif vmovdqa 1*16(p_keys), xkeyA vpxor xkey0, xdata0, xdata0 - vpaddq (ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter - vptest ddq_low_msk(%rip), xcounter - jnz 1f - vpaddq ddq_high_add_1(%rip), xcounter, xcounter - 1: + .if \xctr + add $by, counter + .else + vpaddq (ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter + vptest ddq_low_msk(%rip), xcounter + jnz 1f + vpaddq ddq_high_add_1(%rip), xcounter, xcounter + 1: + .endif .set i, 1 .rept (by - 1) @@ -371,94 +397,99 @@ ddq_add_8: .endr .endm -.macro do_aes_load val, key_len - do_aes \val, 1, \key_len +.macro do_aes_load val, key_len, xctr + do_aes \val, 1, \key_len, \xctr .endm -.macro do_aes_noload val, key_len - do_aes \val, 0, \key_len +.macro do_aes_noload val, key_len, xctr + do_aes \val, 0, \key_len, \xctr .endm /* main body of aes ctr load */ -.macro do_aes_ctrmain key_len +.macro do_aes_ctrmain key_len, xctr cmp $16, num_bytes - jb .Ldo_return2\key_len + jb .Ldo_return2\xctr\key_len - vmovdqa byteswap_const(%rip), xbyteswap - vmovdqu (p_iv), xcounter - vpshufb xbyteswap, xcounter, xcounter + .if \xctr + shr $4, counter + vmovdqu (p_iv), xiv + .else + vmovdqa byteswap_const(%rip), xbyteswap + vmovdqu (p_iv), xcounter + vpshufb xbyteswap, xcounter, xcounter + .endif mov num_bytes, tmp and $(7*16), tmp - jz .Lmult_of_8_blks\key_len + jz .Lmult_of_8_blks\xctr\key_len /* 1 <= tmp <= 7 */ cmp $(4*16), tmp - jg .Lgt4\key_len - je .Leq4\key_len + jg .Lgt4\xctr\key_len + je .Leq4\xctr\key_len -.Llt4\key_len: +.Llt4\xctr\key_len: cmp $(2*16), tmp - jg .Leq3\key_len - je .Leq2\key_len + jg .Leq3\xctr\key_len + je .Leq2\xctr\key_len -.Leq1\key_len: - do_aes_load 1, \key_len +.Leq1\xctr\key_len: + do_aes_load 1, \key_len, \xctr add $(1*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Leq2\key_len: - do_aes_load 2, \key_len +.Leq2\xctr\key_len: + do_aes_load 2, \key_len, \xctr add $(2*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Leq3\key_len: - do_aes_load 3, \key_len +.Leq3\xctr\key_len: + do_aes_load 3, \key_len, \xctr add $(3*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Leq4\key_len: - do_aes_load 4, \key_len +.Leq4\xctr\key_len: + do_aes_load 4, \key_len, \xctr add $(4*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Lgt4\key_len: +.Lgt4\xctr\key_len: cmp $(6*16), tmp - jg .Leq7\key_len - je .Leq6\key_len + jg .Leq7\xctr\key_len + je .Leq6\xctr\key_len -.Leq5\key_len: - do_aes_load 5, \key_len +.Leq5\xctr\key_len: + do_aes_load 5, \key_len, \xctr add $(5*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Leq6\key_len: - do_aes_load 6, \key_len +.Leq6\xctr\key_len: + do_aes_load 6, \key_len, \xctr add $(6*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Leq7\key_len: - do_aes_load 7, \key_len +.Leq7\xctr\key_len: + do_aes_load 7, \key_len, \xctr add $(7*16), p_out and $(~7*16), num_bytes - jz .Ldo_return2\key_len - jmp .Lmain_loop2\key_len + jz .Ldo_return2\xctr\key_len + jmp .Lmain_loop2\xctr\key_len -.Lmult_of_8_blks\key_len: +.Lmult_of_8_blks\xctr\key_len: .if (\key_len != KEY_128) vmovdqa 0*16(p_keys), xkey0 vmovdqa 4*16(p_keys), xkey4 @@ -471,17 +502,19 @@ ddq_add_8: vmovdqa 9*16(p_keys), xkey12 .endif .align 16 -.Lmain_loop2\key_len: +.Lmain_loop2\xctr\key_len: /* num_bytes is a multiple of 8 and >0 */ - do_aes_noload 8, \key_len + do_aes_noload 8, \key_len, \xctr add $(8*16), p_out sub $(8*16), num_bytes - jne .Lmain_loop2\key_len + jne .Lmain_loop2\xctr\key_len -.Ldo_return2\key_len: - /* return updated IV */ - vpshufb xbyteswap, xcounter, xcounter - vmovdqu xcounter, (p_iv) +.Ldo_return2\xctr\key_len: + .if !\xctr + /* return updated IV */ + vpshufb xbyteswap, xcounter, xcounter + vmovdqu xcounter, (p_iv) + .endif RET .endm @@ -494,7 +527,7 @@ ddq_add_8: */ SYM_FUNC_START(aes_ctr_enc_128_avx_by8) /* call the aes main loop */ - do_aes_ctrmain KEY_128 + do_aes_ctrmain KEY_128 0 SYM_FUNC_END(aes_ctr_enc_128_avx_by8) @@ -507,7 +540,7 @@ SYM_FUNC_END(aes_ctr_enc_128_avx_by8) */ SYM_FUNC_START(aes_ctr_enc_192_avx_by8) /* call the aes main loop */ - do_aes_ctrmain KEY_192 + do_aes_ctrmain KEY_192 0 SYM_FUNC_END(aes_ctr_enc_192_avx_by8) @@ -520,6 +553,45 @@ SYM_FUNC_END(aes_ctr_enc_192_avx_by8) */ SYM_FUNC_START(aes_ctr_enc_256_avx_by8) /* call the aes main loop */ - do_aes_ctrmain KEY_256 + do_aes_ctrmain KEY_256 0 SYM_FUNC_END(aes_ctr_enc_256_avx_by8) + +/* + * routine to do AES128 XCTR enc/decrypt "by8" + * XMM registers are clobbered. + * Saving/restoring must be done at a higher level + * aes_xctr_enc_128_avx_by8(const u8 *in, const u8 *iv, const void *keys, + * u8* out, unsigned int num_bytes, unsigned int byte_ctr) + */ +SYM_FUNC_START(aes_xctr_enc_128_avx_by8) + /* call the aes main loop */ + do_aes_ctrmain KEY_128 1 + +SYM_FUNC_END(aes_xctr_enc_128_avx_by8) + +/* + * routine to do AES192 XCTR enc/decrypt "by8" + * XMM registers are clobbered. + * Saving/restoring must be done at a higher level + * aes_xctr_enc_192_avx_by8(const u8 *in, const u8 *iv, const void *keys, + * u8* out, unsigned int num_bytes, unsigned int byte_ctr) + */ +SYM_FUNC_START(aes_xctr_enc_192_avx_by8) + /* call the aes main loop */ + do_aes_ctrmain KEY_192 1 + +SYM_FUNC_END(aes_xctr_enc_192_avx_by8) + +/* + * routine to do AES256 XCTR enc/decrypt "by8" + * XMM registers are clobbered. + * Saving/restoring must be done at a higher level + * aes_xctr_enc_256_avx_by8(const u8 *in, const u8 *iv, const void *keys, + * u8* out, unsigned int num_bytes, unsigned int byte_ctr) + */ +SYM_FUNC_START(aes_xctr_enc_256_avx_by8) + /* call the aes main loop */ + do_aes_ctrmain KEY_256 1 + +SYM_FUNC_END(aes_xctr_enc_256_avx_by8) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 41901ba9d3a2..a5b0cb3efeba 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -135,6 +135,20 @@ asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv, void *keys, u8 *out, unsigned int num_bytes); asmlinkage void aes_ctr_enc_256_avx_by8(const u8 *in, u8 *iv, void *keys, u8 *out, unsigned int num_bytes); + + +asmlinkage void aes_xctr_enc_128_avx_by8(const u8 *in, const u8 *iv, + const void *keys, u8 *out, unsigned int num_bytes, + unsigned int byte_ctr); + +asmlinkage void aes_xctr_enc_192_avx_by8(const u8 *in, const u8 *iv, + const void *keys, u8 *out, unsigned int num_bytes, + unsigned int byte_ctr); + +asmlinkage void aes_xctr_enc_256_avx_by8(const u8 *in, const u8 *iv, + const void *keys, u8 *out, unsigned int num_bytes, + unsigned int byte_ctr); + /* * asmlinkage void aesni_gcm_init_avx_gen2() * gcm_data *my_ctx_data, context data @@ -527,6 +541,59 @@ static int ctr_crypt(struct skcipher_request *req) return err; } +static void aesni_xctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv, + unsigned int byte_ctr) +{ + if (ctx->key_length == AES_KEYSIZE_128) + aes_xctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len, + byte_ctr); + else if (ctx->key_length == AES_KEYSIZE_192) + aes_xctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len, + byte_ctr); + else + aes_xctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len, + byte_ctr); +} + +static int xctr_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm)); + u8 keystream[AES_BLOCK_SIZE]; + struct skcipher_walk walk; + unsigned int nbytes; + unsigned int byte_ctr = 0; + int err; + __le32 block[AES_BLOCK_SIZE / sizeof(__le32)]; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + kernel_fpu_begin(); + if (nbytes & AES_BLOCK_MASK) + aesni_xctr_enc_avx_tfm(ctx, walk.dst.virt.addr, + walk.src.virt.addr, nbytes & AES_BLOCK_MASK, + walk.iv, byte_ctr); + nbytes &= ~AES_BLOCK_MASK; + byte_ctr += walk.nbytes - nbytes; + + if (walk.nbytes == walk.total && nbytes > 0) { + memcpy(block, walk.iv, AES_BLOCK_SIZE); + block[0] ^= cpu_to_le32(1 + byte_ctr / AES_BLOCK_SIZE); + aesni_enc(ctx, keystream, (u8 *)block); + crypto_xor_cpy(walk.dst.virt.addr + walk.nbytes - + nbytes, walk.src.virt.addr + walk.nbytes + - nbytes, keystream, nbytes); + byte_ctr += nbytes; + nbytes = 0; + } + kernel_fpu_end(); + err = skcipher_walk_done(&walk, nbytes); + } + return err; +} + static int rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) { @@ -1051,6 +1118,33 @@ static struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)]; #ifdef CONFIG_X86_64 +/* + * XCTR does not have a non-AVX implementation, so it must be enabled + * conditionally. + */ +static struct skcipher_alg aesni_xctr = { + .base = { + .cra_name = "__xctr(aes)", + .cra_driver_name = "__xctr-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = CRYPTO_AES_CTX_SIZE, + .cra_module = THIS_MODULE, + }, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .chunksize = AES_BLOCK_SIZE, + .setkey = aesni_skcipher_setkey, + .encrypt = xctr_crypt, + .decrypt = xctr_crypt, +}; + +static struct simd_skcipher_alg *aesni_simd_xctr; +#endif /* CONFIG_X86_64 */ + +#ifdef CONFIG_X86_64 static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key, unsigned int key_len) { @@ -1163,7 +1257,7 @@ static int __init aesni_init(void) static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm); pr_info("AES CTR mode by8 optimization enabled\n"); } -#endif +#endif /* CONFIG_X86_64 */ err = crypto_register_alg(&aesni_cipher_alg); if (err) @@ -1180,8 +1274,22 @@ static int __init aesni_init(void) if (err) goto unregister_skciphers; +#ifdef CONFIG_X86_64 + if (boot_cpu_has(X86_FEATURE_AVX)) + err = simd_register_skciphers_compat(&aesni_xctr, 1, + &aesni_simd_xctr); + if (err) + goto unregister_aeads; +#endif /* CONFIG_X86_64 */ + return 0; +#ifdef CONFIG_X86_64 +unregister_aeads: + simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads), + aesni_simd_aeads); +#endif /* CONFIG_X86_64 */ + unregister_skciphers: simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers), aesni_simd_skciphers); @@ -1197,6 +1305,10 @@ static void __exit aesni_exit(void) simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers), aesni_simd_skciphers); crypto_unregister_alg(&aesni_cipher_alg); +#ifdef CONFIG_X86_64 + if (boot_cpu_has(X86_FEATURE_AVX)) + simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr); +#endif /* CONFIG_X86_64 */ } late_initcall(aesni_init); diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 69853c13e8fb..aaba21230528 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -4,7 +4,6 @@ */ #include <crypto/internal/blake2s.h> -#include <crypto/internal/simd.h> #include <linux/types.h> #include <linux/jump_label.h> @@ -33,7 +32,7 @@ void blake2s_compress(struct blake2s_state *state, const u8 *block, /* SIMD disables preemption, so relax after processing each page. */ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); - if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { + if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) { blake2s_compress_generic(state, block, nblocks, inc); return; } diff --git a/arch/x86/crypto/blake2s-shash.c b/arch/x86/crypto/blake2s-shash.c deleted file mode 100644 index 59ae28abe35c..000000000000 --- a/arch/x86/crypto/blake2s-shash.c +++ /dev/null @@ -1,77 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR MIT -/* - * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. - */ - -#include <crypto/internal/blake2s.h> -#include <crypto/internal/simd.h> -#include <crypto/internal/hash.h> - -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/sizes.h> - -#include <asm/cpufeature.h> -#include <asm/processor.h> - -static int crypto_blake2s_update_x86(struct shash_desc *desc, - const u8 *in, unsigned int inlen) -{ - return crypto_blake2s_update(desc, in, inlen, false); -} - -static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) -{ - return crypto_blake2s_final(desc, out, false); -} - -#define BLAKE2S_ALG(name, driver_name, digest_size) \ - { \ - .base.cra_name = name, \ - .base.cra_driver_name = driver_name, \ - .base.cra_priority = 200, \ - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, \ - .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, \ - .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), \ - .base.cra_module = THIS_MODULE, \ - .digestsize = digest_size, \ - .setkey = crypto_blake2s_setkey, \ - .init = crypto_blake2s_init, \ - .update = crypto_blake2s_update_x86, \ - .final = crypto_blake2s_final_x86, \ - .descsize = sizeof(struct blake2s_state), \ - } - -static struct shash_alg blake2s_algs[] = { - BLAKE2S_ALG("blake2s-128", "blake2s-128-x86", BLAKE2S_128_HASH_SIZE), - BLAKE2S_ALG("blake2s-160", "blake2s-160-x86", BLAKE2S_160_HASH_SIZE), - BLAKE2S_ALG("blake2s-224", "blake2s-224-x86", BLAKE2S_224_HASH_SIZE), - BLAKE2S_ALG("blake2s-256", "blake2s-256-x86", BLAKE2S_256_HASH_SIZE), -}; - -static int __init blake2s_mod_init(void) -{ - if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3)) - return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); - return 0; -} - -static void __exit blake2s_mod_exit(void) -{ - if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3)) - crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); -} - -module_init(blake2s_mod_init); -module_exit(blake2s_mod_exit); - -MODULE_ALIAS_CRYPTO("blake2s-128"); -MODULE_ALIAS_CRYPTO("blake2s-128-x86"); -MODULE_ALIAS_CRYPTO("blake2s-160"); -MODULE_ALIAS_CRYPTO("blake2s-160-x86"); -MODULE_ALIAS_CRYPTO("blake2s-224"); -MODULE_ALIAS_CRYPTO("blake2s-224-x86"); -MODULE_ALIAS_CRYPTO("blake2s-256"); -MODULE_ALIAS_CRYPTO("blake2s-256-x86"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index ba06322c1e39..019c64c1340a 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -144,7 +144,7 @@ static int cbc_encrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes)) { + while (walk.nbytes) { nbytes = __cbc_encrypt(ctx, &walk); err = skcipher_walk_done(&walk, nbytes); } @@ -225,7 +225,7 @@ static int cbc_decrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes)) { + while (walk.nbytes) { nbytes = __cbc_decrypt(ctx, &walk); err = skcipher_walk_done(&walk, nbytes); } diff --git a/arch/x86/crypto/polyval-clmulni_asm.S b/arch/x86/crypto/polyval-clmulni_asm.S new file mode 100644 index 000000000000..a6ebe4e7dd2b --- /dev/null +++ b/arch/x86/crypto/polyval-clmulni_asm.S @@ -0,0 +1,321 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2021 Google LLC + */ +/* + * This is an efficient implementation of POLYVAL using intel PCLMULQDQ-NI + * instructions. It works on 8 blocks at a time, by precomputing the first 8 + * keys powers h^8, ..., h^1 in the POLYVAL finite field. This precomputation + * allows us to split finite field multiplication into two steps. + * + * In the first step, we consider h^i, m_i as normal polynomials of degree less + * than 128. We then compute p(x) = h^8m_0 + ... + h^1m_7 where multiplication + * is simply polynomial multiplication. + * + * In the second step, we compute the reduction of p(x) modulo the finite field + * modulus g(x) = x^128 + x^127 + x^126 + x^121 + 1. + * + * This two step process is equivalent to computing h^8m_0 + ... + h^1m_7 where + * multiplication is finite field multiplication. The advantage is that the + * two-step process only requires 1 finite field reduction for every 8 + * polynomial multiplications. Further parallelism is gained by interleaving the + * multiplications and polynomial reductions. + */ + +#include <linux/linkage.h> +#include <asm/frame.h> + +#define STRIDE_BLOCKS 8 + +#define GSTAR %xmm7 +#define PL %xmm8 +#define PH %xmm9 +#define TMP_XMM %xmm11 +#define LO %xmm12 +#define HI %xmm13 +#define MI %xmm14 +#define SUM %xmm15 + +#define KEY_POWERS %rdi +#define MSG %rsi +#define BLOCKS_LEFT %rdx +#define ACCUMULATOR %rcx +#define TMP %rax + +.section .rodata.cst16.gstar, "aM", @progbits, 16 +.align 16 + +.Lgstar: + .quad 0xc200000000000000, 0xc200000000000000 + +.text + +/* + * Performs schoolbook1_iteration on two lists of 128-bit polynomials of length + * count pointed to by MSG and KEY_POWERS. + */ +.macro schoolbook1 count + .set i, 0 + .rept (\count) + schoolbook1_iteration i 0 + .set i, (i +1) + .endr +.endm + +/* + * Computes the product of two 128-bit polynomials at the memory locations + * specified by (MSG + 16*i) and (KEY_POWERS + 16*i) and XORs the components of + * the 256-bit product into LO, MI, HI. + * + * Given: + * X = [X_1 : X_0] + * Y = [Y_1 : Y_0] + * + * We compute: + * LO += X_0 * Y_0 + * MI += X_0 * Y_1 + X_1 * Y_0 + * HI += X_1 * Y_1 + * + * Later, the 256-bit result can be extracted as: + * [HI_1 : HI_0 + MI_1 : LO_1 + MI_0 : LO_0] + * This step is done when computing the polynomial reduction for efficiency + * reasons. + * + * If xor_sum == 1, then also XOR the value of SUM into m_0. This avoids an + * extra multiplication of SUM and h^8. + */ +.macro schoolbook1_iteration i xor_sum + movups (16*\i)(MSG), %xmm0 + .if (\i == 0 && \xor_sum == 1) + pxor SUM, %xmm0 + .endif + vpclmulqdq $0x01, (16*\i)(KEY_POWERS), %xmm0, %xmm2 + vpclmulqdq $0x00, (16*\i)(KEY_POWERS), %xmm0, %xmm1 + vpclmulqdq $0x10, (16*\i)(KEY_POWERS), %xmm0, %xmm3 + vpclmulqdq $0x11, (16*\i)(KEY_POWERS), %xmm0, %xmm4 + vpxor %xmm2, MI, MI + vpxor %xmm1, LO, LO + vpxor %xmm4, HI, HI + vpxor %xmm3, MI, MI +.endm + +/* + * Performs the same computation as schoolbook1_iteration, except we expect the + * arguments to already be loaded into xmm0 and xmm1 and we set the result + * registers LO, MI, and HI directly rather than XOR'ing into them. + */ +.macro schoolbook1_noload + vpclmulqdq $0x01, %xmm0, %xmm1, MI + vpclmulqdq $0x10, %xmm0, %xmm1, %xmm2 + vpclmulqdq $0x00, %xmm0, %xmm1, LO + vpclmulqdq $0x11, %xmm0, %xmm1, HI + vpxor %xmm2, MI, MI +.endm + +/* + * Computes the 256-bit polynomial represented by LO, HI, MI. Stores + * the result in PL, PH. + * [PH : PL] = [HI_1 : HI_0 + MI_1 : LO_1 + MI_0 : LO_0] + */ +.macro schoolbook2 + vpslldq $8, MI, PL + vpsrldq $8, MI, PH + pxor LO, PL + pxor HI, PH +.endm + +/* + * Computes the 128-bit reduction of PH : PL. Stores the result in dest. + * + * This macro computes p(x) mod g(x) where p(x) is in montgomery form and g(x) = + * x^128 + x^127 + x^126 + x^121 + 1. + * + * We have a 256-bit polynomial PH : PL = P_3 : P_2 : P_1 : P_0 that is the + * product of two 128-bit polynomials in Montgomery form. We need to reduce it + * mod g(x). Also, since polynomials in Montgomery form have an "extra" factor + * of x^128, this product has two extra factors of x^128. To get it back into + * Montgomery form, we need to remove one of these factors by dividing by x^128. + * + * To accomplish both of these goals, we add multiples of g(x) that cancel out + * the low 128 bits P_1 : P_0, leaving just the high 128 bits. Since the low + * bits are zero, the polynomial division by x^128 can be done by right shifting. + * + * Since the only nonzero term in the low 64 bits of g(x) is the constant term, + * the multiple of g(x) needed to cancel out P_0 is P_0 * g(x). The CPU can + * only do 64x64 bit multiplications, so split P_0 * g(x) into x^128 * P_0 + + * x^64 * g*(x) * P_0 + P_0, where g*(x) is bits 64-127 of g(x). Adding this to + * the original polynomial gives P_3 : P_2 + P_0 + T_1 : P_1 + T_0 : 0, where T + * = T_1 : T_0 = g*(x) * P_0. Thus, bits 0-63 got "folded" into bits 64-191. + * + * Repeating this same process on the next 64 bits "folds" bits 64-127 into bits + * 128-255, giving the answer in bits 128-255. This time, we need to cancel P_1 + * + T_0 in bits 64-127. The multiple of g(x) required is (P_1 + T_0) * g(x) * + * x^64. Adding this to our previous computation gives P_3 + P_1 + T_0 + V_1 : + * P_2 + P_0 + T_1 + V_0 : 0 : 0, where V = V_1 : V_0 = g*(x) * (P_1 + T_0). + * + * So our final computation is: + * T = T_1 : T_0 = g*(x) * P_0 + * V = V_1 : V_0 = g*(x) * (P_1 + T_0) + * p(x) / x^{128} mod g(x) = P_3 + P_1 + T_0 + V_1 : P_2 + P_0 + T_1 + V_0 + * + * The implementation below saves a XOR instruction by computing P_1 + T_0 : P_0 + * + T_1 and XORing into dest, rather than separately XORing P_1 : P_0 and T_0 : + * T_1 into dest. This allows us to reuse P_1 + T_0 when computing V. + */ +.macro montgomery_reduction dest + vpclmulqdq $0x00, PL, GSTAR, TMP_XMM # TMP_XMM = T_1 : T_0 = P_0 * g*(x) + pshufd $0b01001110, TMP_XMM, TMP_XMM # TMP_XMM = T_0 : T_1 + pxor PL, TMP_XMM # TMP_XMM = P_1 + T_0 : P_0 + T_1 + pxor TMP_XMM, PH # PH = P_3 + P_1 + T_0 : P_2 + P_0 + T_1 + pclmulqdq $0x11, GSTAR, TMP_XMM # TMP_XMM = V_1 : V_0 = V = [(P_1 + T_0) * g*(x)] + vpxor TMP_XMM, PH, \dest +.endm + +/* + * Compute schoolbook multiplication for 8 blocks + * m_0h^8 + ... + m_7h^1 + * + * If reduce is set, also computes the montgomery reduction of the + * previous full_stride call and XORs with the first message block. + * (m_0 + REDUCE(PL, PH))h^8 + ... + m_7h^1. + * I.e., the first multiplication uses m_0 + REDUCE(PL, PH) instead of m_0. + */ +.macro full_stride reduce + pxor LO, LO + pxor HI, HI + pxor MI, MI + + schoolbook1_iteration 7 0 + .if \reduce + vpclmulqdq $0x00, PL, GSTAR, TMP_XMM + .endif + + schoolbook1_iteration 6 0 + .if \reduce + pshufd $0b01001110, TMP_XMM, TMP_XMM + .endif + + schoolbook1_iteration 5 0 + .if \reduce + pxor PL, TMP_XMM + .endif + + schoolbook1_iteration 4 0 + .if \reduce + pxor TMP_XMM, PH + .endif + + schoolbook1_iteration 3 0 + .if \reduce + pclmulqdq $0x11, GSTAR, TMP_XMM + .endif + + schoolbook1_iteration 2 0 + .if \reduce + vpxor TMP_XMM, PH, SUM + .endif + + schoolbook1_iteration 1 0 + + schoolbook1_iteration 0 1 + + addq $(8*16), MSG + schoolbook2 +.endm + +/* + * Process BLOCKS_LEFT blocks, where 0 < BLOCKS_LEFT < STRIDE_BLOCKS + */ +.macro partial_stride + mov BLOCKS_LEFT, TMP + shlq $4, TMP + addq $(16*STRIDE_BLOCKS), KEY_POWERS + subq TMP, KEY_POWERS + + movups (MSG), %xmm0 + pxor SUM, %xmm0 + movaps (KEY_POWERS), %xmm1 + schoolbook1_noload + dec BLOCKS_LEFT + addq $16, MSG + addq $16, KEY_POWERS + + test $4, BLOCKS_LEFT + jz .Lpartial4BlocksDone + schoolbook1 4 + addq $(4*16), MSG + addq $(4*16), KEY_POWERS +.Lpartial4BlocksDone: + test $2, BLOCKS_LEFT + jz .Lpartial2BlocksDone + schoolbook1 2 + addq $(2*16), MSG + addq $(2*16), KEY_POWERS +.Lpartial2BlocksDone: + test $1, BLOCKS_LEFT + jz .LpartialDone + schoolbook1 1 +.LpartialDone: + schoolbook2 + montgomery_reduction SUM +.endm + +/* + * Perform montgomery multiplication in GF(2^128) and store result in op1. + * + * Computes op1*op2*x^{-128} mod x^128 + x^127 + x^126 + x^121 + 1 + * If op1, op2 are in montgomery form, this computes the montgomery + * form of op1*op2. + * + * void clmul_polyval_mul(u8 *op1, const u8 *op2); + */ +SYM_FUNC_START(clmul_polyval_mul) + FRAME_BEGIN + vmovdqa .Lgstar(%rip), GSTAR + movups (%rdi), %xmm0 + movups (%rsi), %xmm1 + schoolbook1_noload + schoolbook2 + montgomery_reduction SUM + movups SUM, (%rdi) + FRAME_END + RET +SYM_FUNC_END(clmul_polyval_mul) + +/* + * Perform polynomial evaluation as specified by POLYVAL. This computes: + * h^n * accumulator + h^n * m_0 + ... + h^1 * m_{n-1} + * where n=nblocks, h is the hash key, and m_i are the message blocks. + * + * rdi - pointer to precomputed key powers h^8 ... h^1 + * rsi - pointer to message blocks + * rdx - number of blocks to hash + * rcx - pointer to the accumulator + * + * void clmul_polyval_update(const struct polyval_tfm_ctx *keys, + * const u8 *in, size_t nblocks, u8 *accumulator); + */ +SYM_FUNC_START(clmul_polyval_update) + FRAME_BEGIN + vmovdqa .Lgstar(%rip), GSTAR + movups (ACCUMULATOR), SUM + subq $STRIDE_BLOCKS, BLOCKS_LEFT + js .LstrideLoopExit + full_stride 0 + subq $STRIDE_BLOCKS, BLOCKS_LEFT + js .LstrideLoopExitReduce +.LstrideLoop: + full_stride 1 + subq $STRIDE_BLOCKS, BLOCKS_LEFT + jns .LstrideLoop +.LstrideLoopExitReduce: + montgomery_reduction SUM +.LstrideLoopExit: + add $STRIDE_BLOCKS, BLOCKS_LEFT + jz .LskipPartial + partial_stride +.LskipPartial: + movups SUM, (ACCUMULATOR) + FRAME_END + RET +SYM_FUNC_END(clmul_polyval_update) diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c new file mode 100644 index 000000000000..b7664d018851 --- /dev/null +++ b/arch/x86/crypto/polyval-clmulni_glue.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Glue code for POLYVAL using PCMULQDQ-NI + * + * Copyright (c) 2007 Nokia Siemens Networks - Mikko Herranen <mh1@iki.fi> + * Copyright (c) 2009 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * Copyright 2021 Google LLC + */ + +/* + * Glue code based on ghash-clmulni-intel_glue.c. + * + * This implementation of POLYVAL uses montgomery multiplication + * accelerated by PCLMULQDQ-NI to implement the finite field + * operations. + */ + +#include <crypto/algapi.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/simd.h> +#include <crypto/polyval.h> +#include <linux/crypto.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/cpu_device_id.h> +#include <asm/simd.h> + +#define NUM_KEY_POWERS 8 + +struct polyval_tfm_ctx { + /* + * These powers must be in the order h^8, ..., h^1. + */ + u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE]; +}; + +struct polyval_desc_ctx { + u8 buffer[POLYVAL_BLOCK_SIZE]; + u32 bytes; +}; + +asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys, + const u8 *in, size_t nblocks, u8 *accumulator); +asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2); + +static void internal_polyval_update(const struct polyval_tfm_ctx *keys, + const u8 *in, size_t nblocks, u8 *accumulator) +{ + if (likely(crypto_simd_usable())) { + kernel_fpu_begin(); + clmul_polyval_update(keys, in, nblocks, accumulator); + kernel_fpu_end(); + } else { + polyval_update_non4k(keys->key_powers[NUM_KEY_POWERS-1], in, + nblocks, accumulator); + } +} + +static void internal_polyval_mul(u8 *op1, const u8 *op2) +{ + if (likely(crypto_simd_usable())) { + kernel_fpu_begin(); + clmul_polyval_mul(op1, op2); + kernel_fpu_end(); + } else { + polyval_mul_non4k(op1, op2); + } +} + +static int polyval_x86_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm); + int i; + + if (keylen != POLYVAL_BLOCK_SIZE) + return -EINVAL; + + memcpy(tctx->key_powers[NUM_KEY_POWERS-1], key, POLYVAL_BLOCK_SIZE); + + for (i = NUM_KEY_POWERS-2; i >= 0; i--) { + memcpy(tctx->key_powers[i], key, POLYVAL_BLOCK_SIZE); + internal_polyval_mul(tctx->key_powers[i], + tctx->key_powers[i+1]); + } + + return 0; +} + +static int polyval_x86_init(struct shash_desc *desc) +{ + struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); + + memset(dctx, 0, sizeof(*dctx)); + + return 0; +} + +static int polyval_x86_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); + const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + u8 *pos; + unsigned int nblocks; + unsigned int n; + + if (dctx->bytes) { + n = min(srclen, dctx->bytes); + pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes; + + dctx->bytes -= n; + srclen -= n; + + while (n--) + *pos++ ^= *src++; + + if (!dctx->bytes) + internal_polyval_mul(dctx->buffer, + tctx->key_powers[NUM_KEY_POWERS-1]); + } + + while (srclen >= POLYVAL_BLOCK_SIZE) { + /* Allow rescheduling every 4K bytes. */ + nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE; + internal_polyval_update(tctx, src, nblocks, dctx->buffer); + srclen -= nblocks * POLYVAL_BLOCK_SIZE; + src += nblocks * POLYVAL_BLOCK_SIZE; + } + + if (srclen) { + dctx->bytes = POLYVAL_BLOCK_SIZE - srclen; + pos = dctx->buffer; + while (srclen--) + *pos++ ^= *src++; + } + + return 0; +} + +static int polyval_x86_final(struct shash_desc *desc, u8 *dst) +{ + struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); + const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + + if (dctx->bytes) { + internal_polyval_mul(dctx->buffer, + tctx->key_powers[NUM_KEY_POWERS-1]); + } + + memcpy(dst, dctx->buffer, POLYVAL_BLOCK_SIZE); + + return 0; +} + +static struct shash_alg polyval_alg = { + .digestsize = POLYVAL_DIGEST_SIZE, + .init = polyval_x86_init, + .update = polyval_x86_update, + .final = polyval_x86_final, + .setkey = polyval_x86_setkey, + .descsize = sizeof(struct polyval_desc_ctx), + .base = { + .cra_name = "polyval", + .cra_driver_name = "polyval-clmulni", + .cra_priority = 200, + .cra_blocksize = POLYVAL_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct polyval_tfm_ctx), + .cra_module = THIS_MODULE, + }, +}; + +__maybe_unused static const struct x86_cpu_id pcmul_cpu_id[] = { + X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id); + +static int __init polyval_clmulni_mod_init(void) +{ + if (!x86_match_cpu(pcmul_cpu_id)) + return -ENODEV; + + if (!boot_cpu_has(X86_FEATURE_AVX)) + return -ENODEV; + + return crypto_register_shash(&polyval_alg); +} + +static void __exit polyval_clmulni_mod_exit(void) +{ + crypto_unregister_shash(&polyval_alg); +} + +module_init(polyval_clmulni_mod_init); +module_exit(polyval_clmulni_mod_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("POLYVAL hash function accelerated by PCLMULQDQ-NI"); +MODULE_ALIAS_CRYPTO("polyval"); +MODULE_ALIAS_CRYPTO("polyval-clmulni"); |