From: Eric Biggers <ebiggers@xxxxxxxxxx> Add a 64-bit SSE2 implementation of NHPoly1305, an ε-almost-∆-universal hash function used in the Adiantum encryption mode. For now, only the NH portion is actually SSE2-accelerated; the Poly1305 part is less performance-critical so is just implemented in C. Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx> --- arch/x86/crypto/Makefile | 4 + arch/x86/crypto/nh-sse2-x86_64.S | 123 +++++++++++++++++++++++++ arch/x86/crypto/nhpoly1305-sse2-glue.c | 76 +++++++++++++++ crypto/Kconfig | 8 ++ 4 files changed, 211 insertions(+) create mode 100644 arch/x86/crypto/nh-sse2-x86_64.S create mode 100644 arch/x86/crypto/nhpoly1305-sse2-glue.c diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index a4b0007a54e17..49dc3d50041c9 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -46,6 +46,8 @@ obj-$(CONFIG_CRYPTO_MORUS1280_GLUE) += morus1280_glue.o obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o +obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o + # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \ @@ -84,6 +86,8 @@ aegis256-aesni-y := aegis256-aesni-asm.o aegis256-aesni-glue.o morus640-sse2-y := morus640-sse2-asm.o morus640-sse2-glue.o morus1280-sse2-y := morus1280-sse2-asm.o morus1280-sse2-glue.o +nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o + ifeq ($(avx_supported),yes) camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ camellia_aesni_avx_glue.o diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S new file mode 100644 index 0000000000000..51f52d4ab4bbc --- /dev/null +++ b/arch/x86/crypto/nh-sse2-x86_64.S @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NH - ε-almost-universal hash function, x86_64 SSE2 accelerated + * + * Copyright 2018 Google LLC + * + * Author: Eric Biggers <ebiggers@xxxxxxxxxx> + */ + +#include <linux/linkage.h> + +#define PASS0_SUMS %xmm0 +#define PASS1_SUMS %xmm1 +#define PASS2_SUMS %xmm2 +#define PASS3_SUMS %xmm3 +#define K0 %xmm4 +#define K1 %xmm5 +#define K2 %xmm6 +#define K3 %xmm7 +#define T0 %xmm8 +#define T1 %xmm9 +#define T2 %xmm10 +#define T3 %xmm11 +#define T4 %xmm12 +#define T5 %xmm13 +#define T6 %xmm14 +#define T7 %xmm15 +#define KEY %rdi +#define MESSAGE %rsi +#define MESSAGE_LEN %rdx +#define HASH %rcx + +.macro _nh_stride k0, k1, k2, k3, offset + + // Load next message stride + movdqu \offset(MESSAGE), T1 + + // Load next key stride + movdqu \offset(KEY), \k3 + + // Add message words to key words + movdqa T1, T2 + movdqa T1, T3 + paddd T1, \k0 // reuse k0 to avoid a move + paddd \k1, T1 + paddd \k2, T2 + paddd \k3, T3 + + // Multiply 32x32 => 64 and accumulate + pshufd $0x10, \k0, T4 + pshufd $0x32, \k0, \k0 + pshufd $0x10, T1, T5 + pshufd $0x32, T1, T1 + pshufd $0x10, T2, T6 + pshufd $0x32, T2, T2 + pshufd $0x10, T3, T7 + pshufd $0x32, T3, T3 + pmuludq T4, \k0 + pmuludq T5, T1 + pmuludq T6, T2 + pmuludq T7, T3 + paddq \k0, PASS0_SUMS + paddq T1, PASS1_SUMS + paddq T2, PASS2_SUMS + paddq T3, PASS3_SUMS +.endm + +/* + * void nh_sse2(const u32 *key, const u8 *message, size_t message_len, + * u8 hash[NH_HASH_BYTES]) + * + * It's guaranteed that message_len % 16 == 0. + */ +ENTRY(nh_sse2) + + movdqu 0x00(KEY), K0 + movdqu 0x10(KEY), K1 + movdqu 0x20(KEY), K2 + add $0x30, KEY + pxor PASS0_SUMS, PASS0_SUMS + pxor PASS1_SUMS, PASS1_SUMS + pxor PASS2_SUMS, PASS2_SUMS + pxor PASS3_SUMS, PASS3_SUMS + + sub $0x40, MESSAGE_LEN + jl .Lloop4_done +.Lloop4: + _nh_stride K0, K1, K2, K3, 0x00 + _nh_stride K1, K2, K3, K0, 0x10 + _nh_stride K2, K3, K0, K1, 0x20 + _nh_stride K3, K0, K1, K2, 0x30 + add $0x40, KEY + add $0x40, MESSAGE + sub $0x40, MESSAGE_LEN + jge .Lloop4 + +.Lloop4_done: + and $0x3f, MESSAGE_LEN + jz .Ldone + _nh_stride K0, K1, K2, K3, 0x00 + + sub $0x10, MESSAGE_LEN + jz .Ldone + _nh_stride K1, K2, K3, K0, 0x10 + + sub $0x10, MESSAGE_LEN + jz .Ldone + _nh_stride K2, K3, K0, K1, 0x20 + +.Ldone: + // Sum the accumulators for each pass, then store the sums to 'hash' + movdqa PASS0_SUMS, T0 + movdqa PASS2_SUMS, T1 + punpcklqdq PASS1_SUMS, T0 // => (PASS0_SUM_A PASS1_SUM_A) + punpcklqdq PASS3_SUMS, T1 // => (PASS2_SUM_A PASS3_SUM_A) + punpckhqdq PASS1_SUMS, PASS0_SUMS // => (PASS0_SUM_B PASS1_SUM_B) + punpckhqdq PASS3_SUMS, PASS2_SUMS // => (PASS2_SUM_B PASS3_SUM_B) + paddq PASS0_SUMS, T0 + paddq PASS2_SUMS, T1 + movdqu T0, 0x00(HASH) + movdqu T1, 0x10(HASH) + ret +ENDPROC(nh_sse2) diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c new file mode 100644 index 0000000000000..ed68d164ce140 --- /dev/null +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum + * (SSE2 accelerated version) + * + * Copyright 2018 Google LLC + */ + +#include <crypto/internal/hash.h> +#include <crypto/nhpoly1305.h> +#include <linux/module.h> +#include <asm/fpu/api.h> + +asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len, + u8 hash[NH_HASH_BYTES]); + +/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */ +static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]) +{ + nh_sse2(key, message, message_len, (u8 *)hash); +} + +static int nhpoly1305_sse2_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + if (srclen < 64 || !irq_fpu_usable()) + return crypto_nhpoly1305_update(desc, src, srclen); + + do { + unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + + kernel_fpu_begin(); + crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); + kernel_fpu_end(); + src += n; + srclen -= n; + } while (srclen); + return 0; +} + +static struct shash_alg nhpoly1305_alg = { + .base.cra_name = "nhpoly1305", + .base.cra_driver_name = "nhpoly1305-sse2", + .base.cra_priority = 200, + .base.cra_ctxsize = sizeof(struct nhpoly1305_key), + .base.cra_module = THIS_MODULE, + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_nhpoly1305_init, + .update = nhpoly1305_sse2_update, + .final = crypto_nhpoly1305_final, + .setkey = crypto_nhpoly1305_setkey, + .descsize = sizeof(struct nhpoly1305_state), +}; + +static int __init nhpoly1305_mod_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_XMM2)) + return -ENODEV; + + return crypto_register_shash(&nhpoly1305_alg); +} + +static void __exit nhpoly1305_mod_exit(void) +{ + crypto_unregister_shash(&nhpoly1305_alg); +} + +module_init(nhpoly1305_mod_init); +module_exit(nhpoly1305_mod_exit); + +MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (SSE2-accelerated)"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Biggers <ebiggers@xxxxxxxxxx>"); +MODULE_ALIAS_CRYPTO("nhpoly1305"); +MODULE_ALIAS_CRYPTO("nhpoly1305-sse2"); diff --git a/crypto/Kconfig b/crypto/Kconfig index b6376d5d973e0..b85133966d643 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -501,6 +501,14 @@ config CRYPTO_NHPOLY1305 select CRYPTO_HASH select CRYPTO_POLY1305 +config CRYPTO_NHPOLY1305_SSE2 + tristate "NHPoly1305 hash function (x86_64 SSE2 implementation)" + depends on X86 && 64BIT + select CRYPTO_NHPOLY1305 + help + SSE2 optimized implementation of the hash function used by the + Adiantum encryption mode. + config CRYPTO_ADIANTUM tristate "Adiantum support" select CRYPTO_CHACHA20 -- 2.19.2