From b4a8528d17fbcd9027290c168efd6ba7ac4d4cd2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 10 Dec 2025 17:18:36 -0800 Subject: lib/crypto: arm64/nh: Migrate optimized code into library Migrate the arm64 NEON implementation of NH into lib/crypto/. This makes the nh() function be optimized on arm64 kernels. Note: this temporarily makes the adiantum template not utilize the arm64 optimized NH code. This is resolved in a later commit that converts the adiantum template to use nh() instead of "nhpoly1305". Link: https://lore.kernel.org/r/20251211011846.8179-5-ebiggers@kernel.org Signed-off-by: Eric Biggers --- lib/crypto/Kconfig | 1 + lib/crypto/Makefile | 1 + lib/crypto/arm64/nh-neon-core.S | 103 ++++++++++++++++++++++++++++++++++++++++ lib/crypto/arm64/nh.h | 34 +++++++++++++ 4 files changed, 139 insertions(+) create mode 100644 lib/crypto/arm64/nh-neon-core.S create mode 100644 lib/crypto/arm64/nh.h (limited to 'lib') diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index c6ee7ca77632..aa3f850ece24 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -118,6 +118,7 @@ config CRYPTO_LIB_NH_ARCH bool depends on CRYPTO_LIB_NH && !UML default y if ARM && KERNEL_MODE_NEON + default y if ARM64 && KERNEL_MODE_NEON config CRYPTO_LIB_POLY1305 tristate diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 6dae7e182847..e3a13952bc2a 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -136,6 +136,7 @@ libnh-y := nh.o ifeq ($(CONFIG_CRYPTO_LIB_NH_ARCH),y) CFLAGS_nh.o += -I$(src)/$(SRCARCH) libnh-$(CONFIG_ARM) += arm/nh-neon-core.o +libnh-$(CONFIG_ARM64) += arm64/nh-neon-core.o endif ################################################################################ diff --git a/lib/crypto/arm64/nh-neon-core.S b/lib/crypto/arm64/nh-neon-core.S new file mode 100644 index 000000000000..6fa57fce8085 --- /dev/null +++ b/lib/crypto/arm64/nh-neon-core.S @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NH - ε-almost-universal hash function, ARM64 NEON accelerated version + * + * Copyright 2018 Google LLC + * + * Author: Eric Biggers + */ + +#include + + KEY .req x0 + MESSAGE .req x1 + MESSAGE_LEN .req x2 + HASH .req x3 + + PASS0_SUMS .req v0 + PASS1_SUMS .req v1 + PASS2_SUMS .req v2 + PASS3_SUMS .req v3 + K0 .req v4 + K1 .req v5 + K2 .req v6 + K3 .req v7 + T0 .req v8 + T1 .req v9 + T2 .req v10 + T3 .req v11 + T4 .req v12 + T5 .req v13 + T6 .req v14 + T7 .req v15 + +.macro _nh_stride k0, k1, k2, k3 + + // Load next message stride + ld1 {T3.16b}, [MESSAGE], #16 + + // Load next key stride + ld1 {\k3\().4s}, [KEY], #16 + + // Add message words to key words + add T0.4s, T3.4s, \k0\().4s + add T1.4s, T3.4s, \k1\().4s + add T2.4s, T3.4s, \k2\().4s + add T3.4s, T3.4s, \k3\().4s + + // Multiply 32x32 => 64 and accumulate + mov T4.d[0], T0.d[1] + mov T5.d[0], T1.d[1] + mov T6.d[0], T2.d[1] + mov T7.d[0], T3.d[1] + umlal PASS0_SUMS.2d, T0.2s, T4.2s + umlal PASS1_SUMS.2d, T1.2s, T5.2s + umlal PASS2_SUMS.2d, T2.2s, T6.2s + umlal PASS3_SUMS.2d, T3.2s, T7.2s +.endm + +/* + * void nh_neon(const u32 *key, const u8 *message, size_t message_len, + * __le64 hash[NH_NUM_PASSES]) + * + * It's guaranteed that message_len % 16 == 0. + */ +SYM_FUNC_START(nh_neon) + + ld1 {K0.4s,K1.4s}, [KEY], #32 + movi PASS0_SUMS.2d, #0 + movi PASS1_SUMS.2d, #0 + ld1 {K2.4s}, [KEY], #16 + movi PASS2_SUMS.2d, #0 + movi PASS3_SUMS.2d, #0 + + subs MESSAGE_LEN, MESSAGE_LEN, #64 + blt .Lloop4_done +.Lloop4: + _nh_stride K0, K1, K2, K3 + _nh_stride K1, K2, K3, K0 + _nh_stride K2, K3, K0, K1 + _nh_stride K3, K0, K1, K2 + subs MESSAGE_LEN, MESSAGE_LEN, #64 + bge .Lloop4 + +.Lloop4_done: + ands MESSAGE_LEN, MESSAGE_LEN, #63 + beq .Ldone + _nh_stride K0, K1, K2, K3 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K1, K2, K3, K0 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K2, K3, K0, K1 + +.Ldone: + // Sum the accumulators for each pass, then store the sums to 'hash' + addp T0.2d, PASS0_SUMS.2d, PASS1_SUMS.2d + addp T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d + st1 {T0.16b,T1.16b}, [HASH] + ret +SYM_FUNC_END(nh_neon) diff --git a/lib/crypto/arm64/nh.h b/lib/crypto/arm64/nh.h new file mode 100644 index 000000000000..08902630bdd1 --- /dev/null +++ b/lib/crypto/arm64/nh.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * ARM64 accelerated implementation of NH + * + * Copyright 2018 Google LLC + */ + +#include +#include +#include + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); + +asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]); + +static bool nh_arch(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]) +{ + if (static_branch_likely(&have_neon) && message_len >= 64 && + may_use_simd()) { + scoped_ksimd() + nh_neon(key, message, message_len, hash); + return true; + } + return false; +} + +#define nh_mod_init_arch nh_mod_init_arch +static void nh_mod_init_arch(void) +{ + if (cpu_have_named_feature(ASIMD)) + static_branch_enable(&have_neon); +} -- cgit v1.2.3