From ca4477e41c68b58043e67bc78074cd6fcc59ee5e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 28 Apr 2025 10:00:27 -0700 Subject: crypto: arm/sha256 - implement library instead of shash Instead of providing crypto_shash algorithms for the arch-optimized SHA-256 code, instead implement the SHA-256 library. This is much simpler, it makes the SHA-256 library functions be arch-optimized, and it fixes the longstanding issue where the arch-optimized SHA-256 was disabled by default. SHA-256 still remains available through crypto_shash, but individual architectures no longer need to handle it. To merge the scalar, NEON, and CE code all into one module cleanly, add !CPU_V7M as a direct dependency of the CE code. Previously, !CPU_V7M was only a direct dependency of the scalar and NEON code. The result is still the same because CPU_V7M implies !KERNEL_MODE_NEON, so !CPU_V7M was already an indirect dependency of the CE code. To match sha256_blocks_arch(), change the type of the nblocks parameter of the assembly functions from int to size_t. The assembly functions actually already treated it as size_t. While renaming the assembly files, also fix the naming quirk where "sha2" meant sha256. (SHA-512 is also part of SHA-2.) Reviewed-by: Ard Biesheuvel Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/arm/configs/exynos_defconfig | 1 - arch/arm/configs/milbeaut_m10v_defconfig | 1 - arch/arm/configs/multi_v7_defconfig | 1 - arch/arm/configs/omap2plus_defconfig | 1 - arch/arm/configs/pxa_defconfig | 1 - arch/arm/crypto/Kconfig | 21 - arch/arm/crypto/Makefile | 8 +- arch/arm/crypto/sha2-ce-core.S | 123 ------ arch/arm/crypto/sha2-ce-glue.c | 87 ---- arch/arm/crypto/sha256-armv4.pl | 724 ------------------------------- arch/arm/crypto/sha256_glue.c | 107 ----- arch/arm/crypto/sha256_glue.h | 9 - arch/arm/crypto/sha256_neon_glue.c | 75 ---- arch/arm/lib/crypto/.gitignore | 1 + arch/arm/lib/crypto/Kconfig | 6 + arch/arm/lib/crypto/Makefile | 8 +- arch/arm/lib/crypto/sha256-armv4.pl | 724 +++++++++++++++++++++++++++++++ arch/arm/lib/crypto/sha256-ce.S | 123 ++++++ arch/arm/lib/crypto/sha256.c | 64 +++ 19 files changed, 926 insertions(+), 1159 deletions(-) delete mode 100644 arch/arm/crypto/sha2-ce-core.S delete mode 100644 arch/arm/crypto/sha2-ce-glue.c delete mode 100644 arch/arm/crypto/sha256-armv4.pl delete mode 100644 arch/arm/crypto/sha256_glue.c delete mode 100644 arch/arm/crypto/sha256_glue.h delete mode 100644 arch/arm/crypto/sha256_neon_glue.c create mode 100644 arch/arm/lib/crypto/sha256-armv4.pl create mode 100644 arch/arm/lib/crypto/sha256-ce.S create mode 100644 arch/arm/lib/crypto/sha256.c diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index e81a5d6c1c20..c6792c0256a6 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -364,7 +364,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_SHA1_ARM_NEON=m -CONFIG_CRYPTO_SHA256_ARM=m CONFIG_CRYPTO_SHA512_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m CONFIG_CRYPTO_CHACHA20_NEON=m diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig index 275ddf7a3a14..4ec21f477c63 100644 --- a/arch/arm/configs/milbeaut_m10v_defconfig +++ b/arch/arm/configs/milbeaut_m10v_defconfig @@ -101,7 +101,6 @@ CONFIG_CRYPTO_SEQIV=m CONFIG_CRYPTO_GHASH_ARM_CE=m CONFIG_CRYPTO_SHA1_ARM_NEON=m CONFIG_CRYPTO_SHA1_ARM_CE=m -CONFIG_CRYPTO_SHA2_ARM_CE=m CONFIG_CRYPTO_SHA512_ARM=m CONFIG_CRYPTO_AES_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ad037c175fdb..96178acedad0 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1301,7 +1301,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_GHASH_ARM_CE=m CONFIG_CRYPTO_SHA1_ARM_NEON=m CONFIG_CRYPTO_SHA1_ARM_CE=m -CONFIG_CRYPTO_SHA2_ARM_CE=m CONFIG_CRYPTO_SHA512_ARM=m CONFIG_CRYPTO_AES_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 75b326bc7830..317f977e509e 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -697,7 +697,6 @@ CONFIG_SECURITY=y CONFIG_CRYPTO_MICHAEL_MIC=y CONFIG_CRYPTO_GHASH_ARM_CE=m CONFIG_CRYPTO_SHA1_ARM_NEON=m -CONFIG_CRYPTO_SHA256_ARM=m CONFIG_CRYPTO_SHA512_ARM=m CONFIG_CRYPTO_AES_ARM=m CONFIG_CRYPTO_AES_ARM_BS=m diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 24fca8608554..56be85752909 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -660,7 +660,6 @@ CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_DEFLATE=y CONFIG_CRYPTO_LZO=y CONFIG_CRYPTO_SHA1_ARM=m -CONFIG_CRYPTO_SHA256_ARM=m CONFIG_CRYPTO_SHA512_ARM=m CONFIG_CRYPTO_AES_ARM=m CONFIG_FONTS=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index 1f889d6bab77..7efb9a8596e4 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -93,27 +93,6 @@ config CRYPTO_SHA1_ARM_CE Architecture: arm using ARMv8 Crypto Extensions -config CRYPTO_SHA2_ARM_CE - tristate "Hash functions: SHA-224 and SHA-256 (ARMv8 Crypto Extensions)" - depends on KERNEL_MODE_NEON - select CRYPTO_SHA256_ARM - select CRYPTO_HASH - help - SHA-224 and SHA-256 secure hash algorithms (FIPS 180) - - Architecture: arm using - - ARMv8 Crypto Extensions - -config CRYPTO_SHA256_ARM - tristate "Hash functions: SHA-224 and SHA-256 (NEON)" - select CRYPTO_HASH - depends on !CPU_V7M - help - SHA-224 and SHA-256 secure hash algorithms (FIPS 180) - - Architecture: arm using - - NEON (Advanced SIMD) extensions - config CRYPTO_SHA512_ARM tristate "Hash functions: SHA-384 and SHA-512 (NEON)" select CRYPTO_HASH diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index ecabe6603e08..8479137c6e80 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -7,7 +7,6 @@ obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o -obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o @@ -15,20 +14,16 @@ obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o -obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o aes-arm-y := aes-cipher-core.o aes-cipher-glue.o aes-arm-bs-y := aes-neonbs-core.o aes-neonbs-glue.o sha1-arm-y := sha1-armv4-large.o sha1_glue.o sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o -sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o -sha256-arm-y := sha256-core.o sha256_glue.o $(sha256-arm-neon-y) sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o sha512-arm-y := sha512-core.o sha512-glue.o $(sha512-arm-neon-y) blake2b-neon-y := blake2b-neon-core.o blake2b-neon-glue.o sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o -sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o @@ -40,9 +35,8 @@ quiet_cmd_perl = PERL $@ $(obj)/%-core.S: $(src)/%-armv4.pl $(call cmd,perl) -clean-files += sha256-core.S sha512-core.S +clean-files += sha512-core.S aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 -AFLAGS_sha256-core.o += $(aflags-thumb2-y) AFLAGS_sha512-core.o += $(aflags-thumb2-y) diff --git a/arch/arm/crypto/sha2-ce-core.S b/arch/arm/crypto/sha2-ce-core.S deleted file mode 100644 index b6369d2440a1..000000000000 --- a/arch/arm/crypto/sha2-ce-core.S +++ /dev/null @@ -1,123 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * sha2-ce-core.S - SHA-224/256 secure hash using ARMv8 Crypto Extensions - * - * Copyright (C) 2015 Linaro Ltd. - * Author: Ard Biesheuvel - */ - -#include -#include - - .text - .arch armv8-a - .fpu crypto-neon-fp-armv8 - - k0 .req q7 - k1 .req q8 - rk .req r3 - - ta0 .req q9 - ta1 .req q10 - tb0 .req q10 - tb1 .req q9 - - dga .req q11 - dgb .req q12 - - dg0 .req q13 - dg1 .req q14 - dg2 .req q15 - - .macro add_only, ev, s0 - vmov dg2, dg0 - .ifnb \s0 - vld1.32 {k\ev}, [rk, :128]! - .endif - sha256h.32 dg0, dg1, tb\ev - sha256h2.32 dg1, dg2, tb\ev - .ifnb \s0 - vadd.u32 ta\ev, q\s0, k\ev - .endif - .endm - - .macro add_update, ev, s0, s1, s2, s3 - sha256su0.32 q\s0, q\s1 - add_only \ev, \s1 - sha256su1.32 q\s0, q\s2, q\s3 - .endm - - .align 6 -.Lsha256_rcon: - .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 - .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 - .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 - .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 - .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc - .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da - .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 - .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 - .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 - .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 - .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 - .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 - .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 - .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 - .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 - .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 - - /* - * void sha2_ce_transform(struct sha256_state *sst, u8 const *src, - int blocks); - */ -ENTRY(sha2_ce_transform) - /* load state */ - vld1.32 {dga-dgb}, [r0] - - /* load input */ -0: vld1.32 {q0-q1}, [r1]! - vld1.32 {q2-q3}, [r1]! - subs r2, r2, #1 - -#ifndef CONFIG_CPU_BIG_ENDIAN - vrev32.8 q0, q0 - vrev32.8 q1, q1 - vrev32.8 q2, q2 - vrev32.8 q3, q3 -#endif - - /* load first round constant */ - adr rk, .Lsha256_rcon - vld1.32 {k0}, [rk, :128]! - - vadd.u32 ta0, q0, k0 - vmov dg0, dga - vmov dg1, dgb - - add_update 1, 0, 1, 2, 3 - add_update 0, 1, 2, 3, 0 - add_update 1, 2, 3, 0, 1 - add_update 0, 3, 0, 1, 2 - add_update 1, 0, 1, 2, 3 - add_update 0, 1, 2, 3, 0 - add_update 1, 2, 3, 0, 1 - add_update 0, 3, 0, 1, 2 - add_update 1, 0, 1, 2, 3 - add_update 0, 1, 2, 3, 0 - add_update 1, 2, 3, 0, 1 - add_update 0, 3, 0, 1, 2 - - add_only 1, 1 - add_only 0, 2 - add_only 1, 3 - add_only 0 - - /* update state */ - vadd.u32 dga, dga, dg0 - vadd.u32 dgb, dgb, dg1 - bne 0b - - /* store new state */ - vst1.32 {dga-dgb}, [r0] - bx lr -ENDPROC(sha2_ce_transform) diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c deleted file mode 100644 index 1e9d16f79678..000000000000 --- a/arch/arm/crypto/sha2-ce-glue.c +++ /dev/null @@ -1,87 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions - * - * Copyright (C) 2015 Linaro Ltd - */ - -#include -#include -#include -#include -#include -#include -#include - -MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions"); -MODULE_AUTHOR("Ard Biesheuvel "); -MODULE_LICENSE("GPL v2"); - -asmlinkage void sha2_ce_transform(struct crypto_sha256_state *sst, - u8 const *src, int blocks); - -static int sha2_ce_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - int remain; - - kernel_neon_begin(); - remain = sha256_base_do_update_blocks(desc, data, len, - sha2_ce_transform); - kernel_neon_end(); - return remain; -} - -static int sha2_ce_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - kernel_neon_begin(); - sha256_base_do_finup(desc, data, len, sha2_ce_transform); - kernel_neon_end(); - return sha256_base_finish(desc, out); -} - -static struct shash_alg algs[] = { { - .init = sha224_base_init, - .update = sha2_ce_update, - .finup = sha2_ce_finup, - .descsize = sizeof(struct crypto_sha256_state), - .digestsize = SHA224_DIGEST_SIZE, - .base = { - .cra_name = "sha224", - .cra_driver_name = "sha224-ce", - .cra_priority = 300, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}, { - .init = sha256_base_init, - .update = sha2_ce_update, - .finup = sha2_ce_finup, - .descsize = sizeof(struct crypto_sha256_state), - .digestsize = SHA256_DIGEST_SIZE, - .base = { - .cra_name = "sha256", - .cra_driver_name = "sha256-ce", - .cra_priority = 300, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -} }; - -static int __init sha2_ce_mod_init(void) -{ - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); -} - -static void __exit sha2_ce_mod_fini(void) -{ - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); -} - -module_cpu_feature_match(SHA2, sha2_ce_mod_init); -module_exit(sha2_ce_mod_fini); diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl deleted file mode 100644 index f3a2b54efd4e..000000000000 --- a/arch/arm/crypto/sha256-armv4.pl +++ /dev/null @@ -1,724 +0,0 @@ -#!/usr/bin/env perl -# SPDX-License-Identifier: GPL-2.0 - -# This code is taken from the OpenSSL project but the author (Andy Polyakov) -# has relicensed it under the GPLv2. Therefore this program is free software; -# you can redistribute it and/or modify it under the terms of the GNU General -# Public License version 2 as published by the Free Software Foundation. -# -# The original headers, including the original license headers, are -# included below for completeness. - -# ==================================================================== -# Written by Andy Polyakov for the OpenSSL -# project. The module is, however, dual licensed under OpenSSL and -# CRYPTOGAMS licenses depending on where you obtain it. For further -# details see https://www.openssl.org/~appro/cryptogams/. -# ==================================================================== - -# SHA256 block procedure for ARMv4. May 2007. - -# Performance is ~2x better than gcc 3.4 generated code and in "abso- -# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per -# byte [on single-issue Xscale PXA250 core]. - -# July 2010. -# -# Rescheduling for dual-issue pipeline resulted in 22% improvement on -# Cortex A8 core and ~20 cycles per processed byte. - -# February 2011. -# -# Profiler-assisted and platform-specific optimization resulted in 16% -# improvement on Cortex A8 core and ~15.4 cycles per processed byte. - -# September 2013. -# -# Add NEON implementation. On Cortex A8 it was measured to process one -# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon -# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only -# code (meaning that latter performs sub-optimally, nothing was done -# about it). - -# May 2014. -# -# Add ARMv8 code path performing at 2.0 cpb on Apple A7. - -while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} -open STDOUT,">$output"; - -$ctx="r0"; $t0="r0"; -$inp="r1"; $t4="r1"; -$len="r2"; $t1="r2"; -$T1="r3"; $t3="r3"; -$A="r4"; -$B="r5"; -$C="r6"; -$D="r7"; -$E="r8"; -$F="r9"; -$G="r10"; -$H="r11"; -@V=($A,$B,$C,$D,$E,$F,$G,$H); -$t2="r12"; -$Ktbl="r14"; - -@Sigma0=( 2,13,22); -@Sigma1=( 6,11,25); -@sigma0=( 7,18, 3); -@sigma1=(17,19,10); - -sub BODY_00_15 { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___ if ($i<16); -#if __ARM_ARCH__>=7 - @ ldr $t1,[$inp],#4 @ $i -# if $i==15 - str $inp,[sp,#17*4] @ make room for $t4 -# endif - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) -# ifndef __ARMEB__ - rev $t1,$t1 -# endif -#else - @ ldrb $t1,[$inp,#3] @ $i - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - ldrb $t2,[$inp,#2] - ldrb $t0,[$inp,#1] - orr $t1,$t1,$t2,lsl#8 - ldrb $t2,[$inp],#4 - orr $t1,$t1,$t0,lsl#16 -# if $i==15 - str $inp,[sp,#17*4] @ make room for $t4 -# endif - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` - orr $t1,$t1,$t2,lsl#24 - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) -#endif -___ -$code.=<<___; - ldr $t2,[$Ktbl],#4 @ *K256++ - add $h,$h,$t1 @ h+=X[i] - str $t1,[sp,#`$i%16`*4] - eor $t1,$f,$g - add $h,$h,$t0,ror#$Sigma1[0] @ h+=Sigma1(e) - and $t1,$t1,$e - add $h,$h,$t2 @ h+=K256[i] - eor $t1,$t1,$g @ Ch(e,f,g) - eor $t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]` - add $h,$h,$t1 @ h+=Ch(e,f,g) -#if $i==31 - and $t2,$t2,#0xff - cmp $t2,#0xf2 @ done? -#endif -#if $i<15 -# if __ARM_ARCH__>=7 - ldr $t1,[$inp],#4 @ prefetch -# else - ldrb $t1,[$inp,#3] -# endif - eor $t2,$a,$b @ a^b, b^c in next round -#else - ldr $t1,[sp,#`($i+2)%16`*4] @ from future BODY_16_xx - eor $t2,$a,$b @ a^b, b^c in next round - ldr $t4,[sp,#`($i+15)%16`*4] @ from future BODY_16_xx -#endif - eor $t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]` @ Sigma0(a) - and $t3,$t3,$t2 @ (b^c)&=(a^b) - add $d,$d,$h @ d+=h - eor $t3,$t3,$b @ Maj(a,b,c) - add $h,$h,$t0,ror#$Sigma0[0] @ h+=Sigma0(a) - @ add $h,$h,$t3 @ h+=Maj(a,b,c) -___ - ($t2,$t3)=($t3,$t2); -} - -sub BODY_16_XX { -my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; - -$code.=<<___; - @ ldr $t1,[sp,#`($i+1)%16`*4] @ $i - @ ldr $t4,[sp,#`($i+14)%16`*4] - mov $t0,$t1,ror#$sigma0[0] - add $a,$a,$t2 @ h+=Maj(a,b,c) from the past - mov $t2,$t4,ror#$sigma1[0] - eor $t0,$t0,$t1,ror#$sigma0[1] - eor $t2,$t2,$t4,ror#$sigma1[1] - eor $t0,$t0,$t1,lsr#$sigma0[2] @ sigma0(X[i+1]) - ldr $t1,[sp,#`($i+0)%16`*4] - eor $t2,$t2,$t4,lsr#$sigma1[2] @ sigma1(X[i+14]) - ldr $t4,[sp,#`($i+9)%16`*4] - - add $t2,$t2,$t0 - eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` @ from BODY_00_15 - add $t1,$t1,$t2 - eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) - add $t1,$t1,$t4 @ X[i] -___ - &BODY_00_15(@_); -} - -$code=<<___; -#ifndef __KERNEL__ -# include "arm_arch.h" -#else -# define __ARM_ARCH__ __LINUX_ARM_ARCH__ -# define __ARM_MAX_ARCH__ 7 -#endif - -.text -#if __ARM_ARCH__<7 -.code 32 -#else -.syntax unified -# ifdef __thumb2__ -.thumb -# else -.code 32 -# endif -#endif - -.type K256,%object -.align 5 -K256: -.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 -.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 -.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 -.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 -.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc -.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da -.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 -.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 -.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 -.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 -.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 -.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 -.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 -.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 -.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 -.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 -.size K256,.-K256 -.word 0 @ terminator -#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) -.LOPENSSL_armcap: -.word OPENSSL_armcap_P-sha256_block_data_order -#endif -.align 5 - -.global sha256_block_data_order -.type sha256_block_data_order,%function -sha256_block_data_order: -.Lsha256_block_data_order: -#if __ARM_ARCH__<7 - sub r3,pc,#8 @ sha256_block_data_order -#else - adr r3,.Lsha256_block_data_order -#endif -#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) - ldr r12,.LOPENSSL_armcap - ldr r12,[r3,r12] @ OPENSSL_armcap_P - tst r12,#ARMV8_SHA256 - bne .LARMv8 - tst r12,#ARMV7_NEON - bne .LNEON -#endif - add $len,$inp,$len,lsl#6 @ len to point at the end of inp - stmdb sp!,{$ctx,$inp,$len,r4-r11,lr} - ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H} - sub $Ktbl,r3,#256+32 @ K256 - sub sp,sp,#16*4 @ alloca(X[16]) -.Loop: -# if __ARM_ARCH__>=7 - ldr $t1,[$inp],#4 -# else - ldrb $t1,[$inp,#3] -# endif - eor $t3,$B,$C @ magic - eor $t2,$t2,$t2 -___ -for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } -$code.=".Lrounds_16_xx:\n"; -for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); } -$code.=<<___; -#if __ARM_ARCH__>=7 - ite eq @ Thumb2 thing, sanity check in ARM -#endif - ldreq $t3,[sp,#16*4] @ pull ctx - bne .Lrounds_16_xx - - add $A,$A,$t2 @ h+=Maj(a,b,c) from the past - ldr $t0,[$t3,#0] - ldr $t1,[$t3,#4] - ldr $t2,[$t3,#8] - add $A,$A,$t0 - ldr $t0,[$t3,#12] - add $B,$B,$t1 - ldr $t1,[$t3,#16] - add $C,$C,$t2 - ldr $t2,[$t3,#20] - add $D,$D,$t0 - ldr $t0,[$t3,#24] - add $E,$E,$t1 - ldr $t1,[$t3,#28] - add $F,$F,$t2 - ldr $inp,[sp,#17*4] @ pull inp - ldr $t2,[sp,#18*4] @ pull inp+len - add $G,$G,$t0 - add $H,$H,$t1 - stmia $t3,{$A,$B,$C,$D,$E,$F,$G,$H} - cmp $inp,$t2 - sub $Ktbl,$Ktbl,#256 @ rewind Ktbl - bne .Loop - - add sp,sp,#`16+3`*4 @ destroy frame -#if __ARM_ARCH__>=5 - ldmia sp!,{r4-r11,pc} -#else - ldmia sp!,{r4-r11,lr} - tst lr,#1 - moveq pc,lr @ be binary compatible with V4, yet - bx lr @ interoperable with Thumb ISA:-) -#endif -.size sha256_block_data_order,.-sha256_block_data_order -___ -###################################################################### -# NEON stuff -# -{{{ -my @X=map("q$_",(0..3)); -my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25"); -my $Xfer=$t4; -my $j=0; - -sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; } -sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; } - -sub AUTOLOAD() # thunk [simplified] x86-style perlasm -{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./; - my $arg = pop; - $arg = "#$arg" if ($arg*1 eq $arg); - $code .= "\t$opcode\t".join(',',@_,$arg)."\n"; -} - -sub Xupdate() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e,$f,$g,$h); - - &vext_8 ($T0,@X[0],@X[1],4); # X[1..4] - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vext_8 ($T1,@X[2],@X[3],4); # X[9..12] - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T2,$T0,$sigma0[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += X[9..12] - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T1,$T0,$sigma0[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T2,$T0,32-$sigma0[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T3,$T0,$sigma0[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T1,$T1,$T2); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T3,$T0,32-$sigma0[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T1,$T1,$T3); # sigma0(X[1..4]) - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T5,&Dhi(@X[3]),$sigma1[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += sigma0(X[1..4]) - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); # sigma1(X[14..15]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15]) - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[0]); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T5,&Dlo(@X[0]),$sigma1[2]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); - eval(shift(@insns)); - eval(shift(@insns)); - &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_32 ("{$T0}","[$Ktbl,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[1]); - eval(shift(@insns)); - eval(shift(@insns)); - &veor ($T5,$T5,$T4); # sigma1(X[16..17]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 (&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17]) - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 ($T0,$T0,@X[0]); - while($#insns>=2) { eval(shift(@insns)); } - &vst1_32 ("{$T0}","[$Xfer,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - - push(@X,shift(@X)); # "rotate" X[] -} - -sub Xpreload() -{ use integer; - my $body = shift; - my @insns = (&$body,&$body,&$body,&$body); - my ($a,$b,$c,$d,$e,$f,$g,$h); - - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vld1_32 ("{$T0}","[$Ktbl,:128]!"); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vrev32_8 (@X[0],@X[0]); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - eval(shift(@insns)); - &vadd_i32 ($T0,$T0,@X[0]); - foreach (@insns) { eval; } # remaining instructions - &vst1_32 ("{$T0}","[$Xfer,:128]!"); - - push(@X,shift(@X)); # "rotate" X[] -} - -sub body_00_15 () { - ( - '($a,$b,$c,$d,$e,$f,$g,$h)=@V;'. - '&add ($h,$h,$t1)', # h+=X[i]+K[i] - '&eor ($t1,$f,$g)', - '&eor ($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))', - '&add ($a,$a,$t2)', # h+=Maj(a,b,c) from the past - '&and ($t1,$t1,$e)', - '&eor ($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))', # Sigma1(e) - '&eor ($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))', - '&eor ($t1,$t1,$g)', # Ch(e,f,g) - '&add ($h,$h,$t2,"ror#$Sigma1[0]")', # h+=Sigma1(e) - '&eor ($t2,$a,$b)', # a^b, b^c in next round - '&eor ($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))', # Sigma0(a) - '&add ($h,$h,$t1)', # h+=Ch(e,f,g) - '&ldr ($t1,sprintf "[sp,#%d]",4*(($j+1)&15)) if (($j&15)!=15);'. - '&ldr ($t1,"[$Ktbl]") if ($j==15);'. - '&ldr ($t1,"[sp,#64]") if ($j==31)', - '&and ($t3,$t3,$t2)', # (b^c)&=(a^b) - '&add ($d,$d,$h)', # d+=h - '&add ($h,$h,$t0,"ror#$Sigma0[0]");'. # h+=Sigma0(a) - '&eor ($t3,$t3,$b)', # Maj(a,b,c) - '$j++; unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);' - ) -} - -$code.=<<___; -#if __ARM_MAX_ARCH__>=7 -.arch armv7-a -.fpu neon - -.global sha256_block_data_order_neon -.type sha256_block_data_order_neon,%function -.align 4 -sha256_block_data_order_neon: -.LNEON: - stmdb sp!,{r4-r12,lr} - - sub $H,sp,#16*4+16 - adr $Ktbl,.Lsha256_block_data_order - sub $Ktbl,$Ktbl,#.Lsha256_block_data_order-K256 - bic $H,$H,#15 @ align for 128-bit stores - mov $t2,sp - mov sp,$H @ alloca - add $len,$inp,$len,lsl#6 @ len to point at the end of inp - - vld1.8 {@X[0]},[$inp]! - vld1.8 {@X[1]},[$inp]! - vld1.8 {@X[2]},[$inp]! - vld1.8 {@X[3]},[$inp]! - vld1.32 {$T0},[$Ktbl,:128]! - vld1.32 {$T1},[$Ktbl,:128]! - vld1.32 {$T2},[$Ktbl,:128]! - vld1.32 {$T3},[$Ktbl,:128]! - vrev32.8 @X[0],@X[0] @ yes, even on - str $ctx,[sp,#64] - vrev32.8 @X[1],@X[1] @ big-endian - str $inp,[sp,#68] - mov $Xfer,sp - vrev32.8 @X[2],@X[2] - str $len,[sp,#72] - vrev32.8 @X[3],@X[3] - str $t2,[sp,#76] @ save original sp - vadd.i32 $T0,$T0,@X[0] - vadd.i32 $T1,$T1,@X[1] - vst1.32 {$T0},[$Xfer,:128]! - vadd.i32 $T2,$T2,@X[2] - vst1.32 {$T1},[$Xfer,:128]! - vadd.i32 $T3,$T3,@X[3] - vst1.32 {$T2},[$Xfer,:128]! - vst1.32 {$T3},[$Xfer,:128]! - - ldmia $ctx,{$A-$H} - sub $Xfer,$Xfer,#64 - ldr $t1,[sp,#0] - eor $t2,$t2,$t2 - eor $t3,$B,$C - b .L_00_48 - -.align 4 -.L_00_48: -___ - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); - &Xupdate(\&body_00_15); -$code.=<<___; - teq $t1,#0 @ check for K256 terminator - ldr $t1,[sp,#0] - sub $Xfer,$Xfer,#64 - bne .L_00_48 - - ldr $inp,[sp,#68] - ldr $t0,[sp,#72] - sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl - teq $inp,$t0 - it eq - subeq $inp,$inp,#64 @ avoid SEGV - vld1.8 {@X[0]},[$inp]! @ load next input block - vld1.8 {@X[1]},[$inp]! - vld1.8 {@X[2]},[$inp]! - vld1.8 {@X[3]},[$inp]! - it ne - strne $inp,[sp,#68] - mov $Xfer,sp -___ - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); - &Xpreload(\&body_00_15); -$code.=<<___; - ldr $t0,[$t1,#0] - add $A,$A,$t2 @ h+=Maj(a,b,c) from the past - ldr $t2,[$t1,#4] - ldr $t3,[$t1,#8] - ldr $t4,[$t1,#12] - add $A,$A,$t0 @ accumulate - ldr $t0,[$t1,#16] - add $B,$B,$t2 - ldr $t2,[$t1,#20] - add $C,$C,$t3 - ldr $t3,[$t1,#24] - add $D,$D,$t4 - ldr $t4,[$t1,#28] - add $E,$E,$t0 - str $A,[$t1],#4 - add $F,$F,$t2 - str $B,[$t1],#4 - add $G,$G,$t3 - str $C,[$t1],#4 - add $H,$H,$t4 - str $D,[$t1],#4 - stmia $t1,{$E-$H} - - ittte ne - movne $Xfer,sp - ldrne $t1,[sp,#0] - eorne $t2,$t2,$t2 - ldreq sp,[sp,#76] @ restore original sp - itt ne - eorne $t3,$B,$C - bne .L_00_48 - - ldmia sp!,{r4-r12,pc} -.size sha256_block_data_order_neon,.-sha256_block_data_order_neon -#endif -___ -}}} -###################################################################### -# ARMv8 stuff -# -{{{ -my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2)); -my @MSG=map("q$_",(8..11)); -my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15)); -my $Ktbl="r3"; - -$code.=<<___; -#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) - -# ifdef __thumb2__ -# define INST(a,b,c,d) .byte c,d|0xc,a,b -# else -# define INST(a,b,c,d) .byte a,b,c,d -# endif - -.type sha256_block_data_order_armv8,%function -.align 5 -sha256_block_data_order_armv8: -.LARMv8: - vld1.32 {$ABCD,$EFGH},[$ctx] -# ifdef __thumb2__ - adr $Ktbl,.LARMv8 - sub $Ktbl,$Ktbl,#.LARMv8-K256 -# else - adrl $Ktbl,K256 -# endif - add $len,$inp,$len,lsl#6 @ len to point at the end of inp - -.Loop_v8: - vld1.8 {@MSG[0]-@MSG[1]},[$inp]! - vld1.8 {@MSG[2]-@MSG[3]},[$inp]! - vld1.32 {$W0},[$Ktbl]! - vrev32.8 @MSG[0],@MSG[0] - vrev32.8 @MSG[1],@MSG[1] - vrev32.8 @MSG[2],@MSG[2] - vrev32.8 @MSG[3],@MSG[3] - vmov $ABCD_SAVE,$ABCD @ offload - vmov $EFGH_SAVE,$EFGH - teq $inp,$len -___ -for($i=0;$i<12;$i++) { -$code.=<<___; - vld1.32 {$W1},[$Ktbl]! - vadd.i32 $W0,$W0,@MSG[0] - sha256su0 @MSG[0],@MSG[1] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - sha256su1 @MSG[0],@MSG[2],@MSG[3] -___ - ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG)); -} -$code.=<<___; - vld1.32 {$W1},[$Ktbl]! - vadd.i32 $W0,$W0,@MSG[0] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - vld1.32 {$W0},[$Ktbl]! - vadd.i32 $W1,$W1,@MSG[1] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - vld1.32 {$W1},[$Ktbl] - vadd.i32 $W0,$W0,@MSG[2] - sub $Ktbl,$Ktbl,#256-16 @ rewind - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W0 - sha256h2 $EFGH,$abcd,$W0 - - vadd.i32 $W1,$W1,@MSG[3] - vmov $abcd,$ABCD - sha256h $ABCD,$EFGH,$W1 - sha256h2 $EFGH,$abcd,$W1 - - vadd.i32 $ABCD,$ABCD,$ABCD_SAVE - vadd.i32 $EFGH,$EFGH,$EFGH_SAVE - it ne - bne .Loop_v8 - - vst1.32 {$ABCD,$EFGH},[$ctx] - - ret @ bx lr -.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8 -#endif -___ -}}} -$code.=<<___; -.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by " -.align 2 -#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) -.comm OPENSSL_armcap_P,4,4 -#endif -___ - -open SELF,$0; -while() { - next if (/^#!/); - last if (!s/^#/@/ and !/^$/); - print; -} -close SELF; - -{ my %opcode = ( - "sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40, - "sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 ); - - sub unsha256 { - my ($mnemonic,$arg)=@_; - - if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) { - my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19) - |(($2&7)<<17)|(($2&8)<<4) - |(($3&7)<<1) |(($3&8)<<2); - # since ARMv7 instructions are always encoded little-endian. - # correct solution is to use .inst directive, but older - # assemblers don't implement it:-( - sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s", - $word&0xff,($word>>8)&0xff, - ($word>>16)&0xff,($word>>24)&0xff, - $mnemonic,$arg; - } - } -} - -foreach (split($/,$code)) { - - s/\`([^\`]*)\`/eval $1/geo; - - s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo; - - s/\bret\b/bx lr/go or - s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4 - - print $_,"\n"; -} - -close STDOUT; # enforce flush diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c deleted file mode 100644 index d04c4e6bae6d..000000000000 --- a/arch/arm/crypto/sha256_glue.c +++ /dev/null @@ -1,107 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Glue code for the SHA256 Secure Hash Algorithm assembly implementation - * using optimized ARM assembler and NEON instructions. - * - * Copyright © 2015 Google Inc. - * - * This file is based on sha256_ssse3_glue.c: - * Copyright (C) 2013 Intel Corporation - * Author: Tim Chen - */ - -#include -#include -#include -#include -#include -#include - -#include "sha256_glue.h" - -asmlinkage void sha256_block_data_order(struct crypto_sha256_state *state, - const u8 *data, int num_blks); - -static int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - /* make sure casting to sha256_block_fn() is safe */ - BUILD_BUG_ON(offsetof(struct crypto_sha256_state, state) != 0); - - return sha256_base_do_update_blocks(desc, data, len, - sha256_block_data_order); -} - -static int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - sha256_base_do_finup(desc, data, len, sha256_block_data_order); - return sha256_base_finish(desc, out); -} - -static struct shash_alg algs[] = { { - .digestsize = SHA256_DIGEST_SIZE, - .init = sha256_base_init, - .update = crypto_sha256_arm_update, - .finup = crypto_sha256_arm_finup, - .descsize = sizeof(struct crypto_sha256_state), - .base = { - .cra_name = "sha256", - .cra_driver_name = "sha256-asm", - .cra_priority = 150, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}, { - .digestsize = SHA224_DIGEST_SIZE, - .init = sha224_base_init, - .update = crypto_sha256_arm_update, - .finup = crypto_sha256_arm_finup, - .descsize = sizeof(struct crypto_sha256_state), - .base = { - .cra_name = "sha224", - .cra_driver_name = "sha224-asm", - .cra_priority = 150, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA224_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -} }; - -static int __init sha256_mod_init(void) -{ - int res = crypto_register_shashes(algs, ARRAY_SIZE(algs)); - - if (res < 0) - return res; - - if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) { - res = crypto_register_shashes(sha256_neon_algs, - ARRAY_SIZE(sha256_neon_algs)); - - if (res < 0) - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); - } - - return res; -} - -static void __exit sha256_mod_fini(void) -{ - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); - - if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) - crypto_unregister_shashes(sha256_neon_algs, - ARRAY_SIZE(sha256_neon_algs)); -} - -module_init(sha256_mod_init); -module_exit(sha256_mod_fini); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm (ARM), including NEON"); - -MODULE_ALIAS_CRYPTO("sha256"); diff --git a/arch/arm/crypto/sha256_glue.h b/arch/arm/crypto/sha256_glue.h deleted file mode 100644 index 9881c9a115d1..000000000000 --- a/arch/arm/crypto/sha256_glue.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CRYPTO_SHA256_GLUE_H -#define _CRYPTO_SHA256_GLUE_H - -#include - -extern struct shash_alg sha256_neon_algs[2]; - -#endif /* _CRYPTO_SHA256_GLUE_H */ diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c deleted file mode 100644 index 76eb3cdc21c9..000000000000 --- a/arch/arm/crypto/sha256_neon_glue.c +++ /dev/null @@ -1,75 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Glue code for the SHA256 Secure Hash Algorithm assembly implementation - * using NEON instructions. - * - * Copyright © 2015 Google Inc. - * - * This file is based on sha512_neon_glue.c: - * Copyright © 2014 Jussi Kivilinna - */ - -#include -#include -#include -#include -#include -#include - -#include "sha256_glue.h" - -asmlinkage void sha256_block_data_order_neon( - struct crypto_sha256_state *digest, const u8 *data, int num_blks); - -static int crypto_sha256_neon_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - int remain; - - kernel_neon_begin(); - remain = sha256_base_do_update_blocks(desc, data, len, - sha256_block_data_order_neon); - kernel_neon_end(); - return remain; -} - -static int crypto_sha256_neon_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - kernel_neon_begin(); - sha256_base_do_finup(desc, data, len, sha256_block_data_order_neon); - kernel_neon_end(); - return sha256_base_finish(desc, out); -} - -struct shash_alg sha256_neon_algs[] = { { - .digestsize = SHA256_DIGEST_SIZE, - .init = sha256_base_init, - .update = crypto_sha256_neon_update, - .finup = crypto_sha256_neon_finup, - .descsize = sizeof(struct crypto_sha256_state), - .base = { - .cra_name = "sha256", - .cra_driver_name = "sha256-neon", - .cra_priority = 250, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}, { - .digestsize = SHA224_DIGEST_SIZE, - .init = sha224_base_init, - .update = crypto_sha256_neon_update, - .finup = crypto_sha256_neon_finup, - .descsize = sizeof(struct crypto_sha256_state), - .base = { - .cra_name = "sha224", - .cra_driver_name = "sha224-neon", - .cra_priority = 250, - .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | - CRYPTO_AHASH_ALG_FINUP_MAX, - .cra_blocksize = SHA224_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -} }; diff --git a/arch/arm/lib/crypto/.gitignore b/arch/arm/lib/crypto/.gitignore index 0d47d4f21c6d..12d74d8b03d0 100644 --- a/arch/arm/lib/crypto/.gitignore +++ b/arch/arm/lib/crypto/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only poly1305-core.S +sha256-core.S diff --git a/arch/arm/lib/crypto/Kconfig b/arch/arm/lib/crypto/Kconfig index e8444fd0aae3..9f3ff30f4032 100644 --- a/arch/arm/lib/crypto/Kconfig +++ b/arch/arm/lib/crypto/Kconfig @@ -22,3 +22,9 @@ config CRYPTO_POLY1305_ARM tristate default CRYPTO_LIB_POLY1305 select CRYPTO_ARCH_HAVE_LIB_POLY1305 + +config CRYPTO_SHA256_ARM + tristate + depends on !CPU_V7M + default CRYPTO_LIB_SHA256 + select CRYPTO_ARCH_HAVE_LIB_SHA256 diff --git a/arch/arm/lib/crypto/Makefile b/arch/arm/lib/crypto/Makefile index 4c042a4c77ed..431f77c3ff6f 100644 --- a/arch/arm/lib/crypto/Makefile +++ b/arch/arm/lib/crypto/Makefile @@ -10,13 +10,17 @@ chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o poly1305-arm-y := poly1305-core.o poly1305-glue.o +obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o +sha256-arm-y := sha256.o sha256-core.o +sha256-arm-$(CONFIG_KERNEL_MODE_NEON) += sha256-ce.o + quiet_cmd_perl = PERL $@ cmd_perl = $(PERL) $(<) > $(@) $(obj)/%-core.S: $(src)/%-armv4.pl $(call cmd,perl) -clean-files += poly1305-core.S +clean-files += poly1305-core.S sha256-core.S aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 @@ -24,3 +28,5 @@ aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5 poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7 AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y) + +AFLAGS_sha256-core.o += $(aflags-thumb2-y) diff --git a/arch/arm/lib/crypto/sha256-armv4.pl b/arch/arm/lib/crypto/sha256-armv4.pl new file mode 100644 index 000000000000..f3a2b54efd4e --- /dev/null +++ b/arch/arm/lib/crypto/sha256-armv4.pl @@ -0,0 +1,724 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 + +# This code is taken from the OpenSSL project but the author (Andy Polyakov) +# has relicensed it under the GPLv2. Therefore this program is free software; +# you can redistribute it and/or modify it under the terms of the GNU General +# Public License version 2 as published by the Free Software Foundation. +# +# The original headers, including the original license headers, are +# included below for completeness. + +# ==================================================================== +# Written by Andy Polyakov for the OpenSSL +# project. The module is, however, dual licensed under OpenSSL and +# CRYPTOGAMS licenses depending on where you obtain it. For further +# details see https://www.openssl.org/~appro/cryptogams/. +# ==================================================================== + +# SHA256 block procedure for ARMv4. May 2007. + +# Performance is ~2x better than gcc 3.4 generated code and in "abso- +# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per +# byte [on single-issue Xscale PXA250 core]. + +# July 2010. +# +# Rescheduling for dual-issue pipeline resulted in 22% improvement on +# Cortex A8 core and ~20 cycles per processed byte. + +# February 2011. +# +# Profiler-assisted and platform-specific optimization resulted in 16% +# improvement on Cortex A8 core and ~15.4 cycles per processed byte. + +# September 2013. +# +# Add NEON implementation. On Cortex A8 it was measured to process one +# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon +# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only +# code (meaning that latter performs sub-optimally, nothing was done +# about it). + +# May 2014. +# +# Add ARMv8 code path performing at 2.0 cpb on Apple A7. + +while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} +open STDOUT,">$output"; + +$ctx="r0"; $t0="r0"; +$inp="r1"; $t4="r1"; +$len="r2"; $t1="r2"; +$T1="r3"; $t3="r3"; +$A="r4"; +$B="r5"; +$C="r6"; +$D="r7"; +$E="r8"; +$F="r9"; +$G="r10"; +$H="r11"; +@V=($A,$B,$C,$D,$E,$F,$G,$H); +$t2="r12"; +$Ktbl="r14"; + +@Sigma0=( 2,13,22); +@Sigma1=( 6,11,25); +@sigma0=( 7,18, 3); +@sigma1=(17,19,10); + +sub BODY_00_15 { +my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; + +$code.=<<___ if ($i<16); +#if __ARM_ARCH__>=7 + @ ldr $t1,[$inp],#4 @ $i +# if $i==15 + str $inp,[sp,#17*4] @ make room for $t4 +# endif + eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` + add $a,$a,$t2 @ h+=Maj(a,b,c) from the past + eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) +# ifndef __ARMEB__ + rev $t1,$t1 +# endif +#else + @ ldrb $t1,[$inp,#3] @ $i + add $a,$a,$t2 @ h+=Maj(a,b,c) from the past + ldrb $t2,[$inp,#2] + ldrb $t0,[$inp,#1] + orr $t1,$t1,$t2,lsl#8 + ldrb $t2,[$inp],#4 + orr $t1,$t1,$t0,lsl#16 +# if $i==15 + str $inp,[sp,#17*4] @ make room for $t4 +# endif + eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` + orr $t1,$t1,$t2,lsl#24 + eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) +#endif +___ +$code.=<<___; + ldr $t2,[$Ktbl],#4 @ *K256++ + add $h,$h,$t1 @ h+=X[i] + str $t1,[sp,#`$i%16`*4] + eor $t1,$f,$g + add $h,$h,$t0,ror#$Sigma1[0] @ h+=Sigma1(e) + and $t1,$t1,$e + add $h,$h,$t2 @ h+=K256[i] + eor $t1,$t1,$g @ Ch(e,f,g) + eor $t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]` + add $h,$h,$t1 @ h+=Ch(e,f,g) +#if $i==31 + and $t2,$t2,#0xff + cmp $t2,#0xf2 @ done? +#endif +#if $i<15 +# if __ARM_ARCH__>=7 + ldr $t1,[$inp],#4 @ prefetch +# else + ldrb $t1,[$inp,#3] +# endif + eor $t2,$a,$b @ a^b, b^c in next round +#else + ldr $t1,[sp,#`($i+2)%16`*4] @ from future BODY_16_xx + eor $t2,$a,$b @ a^b, b^c in next round + ldr $t4,[sp,#`($i+15)%16`*4] @ from future BODY_16_xx +#endif + eor $t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]` @ Sigma0(a) + and $t3,$t3,$t2 @ (b^c)&=(a^b) + add $d,$d,$h @ d+=h + eor $t3,$t3,$b @ Maj(a,b,c) + add $h,$h,$t0,ror#$Sigma0[0] @ h+=Sigma0(a) + @ add $h,$h,$t3 @ h+=Maj(a,b,c) +___ + ($t2,$t3)=($t3,$t2); +} + +sub BODY_16_XX { +my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_; + +$code.=<<___; + @ ldr $t1,[sp,#`($i+1)%16`*4] @ $i + @ ldr $t4,[sp,#`($i+14)%16`*4] + mov $t0,$t1,ror#$sigma0[0] + add $a,$a,$t2 @ h+=Maj(a,b,c) from the past + mov $t2,$t4,ror#$sigma1[0] + eor $t0,$t0,$t1,ror#$sigma0[1] + eor $t2,$t2,$t4,ror#$sigma1[1] + eor $t0,$t0,$t1,lsr#$sigma0[2] @ sigma0(X[i+1]) + ldr $t1,[sp,#`($i+0)%16`*4] + eor $t2,$t2,$t4,lsr#$sigma1[2] @ sigma1(X[i+14]) + ldr $t4,[sp,#`($i+9)%16`*4] + + add $t2,$t2,$t0 + eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` @ from BODY_00_15 + add $t1,$t1,$t2 + eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e) + add $t1,$t1,$t4 @ X[i] +___ + &BODY_00_15(@_); +} + +$code=<<___; +#ifndef __KERNEL__ +# include "arm_arch.h" +#else +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 +#endif + +.text +#if __ARM_ARCH__<7 +.code 32 +#else +.syntax unified +# ifdef __thumb2__ +.thumb +# else +.code 32 +# endif +#endif + +.type K256,%object +.align 5 +K256: +.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 +.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 +.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 +.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 +.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc +.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da +.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 +.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 +.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 +.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 +.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 +.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 +.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 +.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 +.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 +.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 +.size K256,.-K256 +.word 0 @ terminator +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.LOPENSSL_armcap: +.word OPENSSL_armcap_P-sha256_block_data_order +#endif +.align 5 + +.global sha256_block_data_order +.type sha256_block_data_order,%function +sha256_block_data_order: +.Lsha256_block_data_order: +#if __ARM_ARCH__<7 + sub r3,pc,#8 @ sha256_block_data_order +#else + adr r3,.Lsha256_block_data_order +#endif +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) + ldr r12,.LOPENSSL_armcap + ldr r12,[r3,r12] @ OPENSSL_armcap_P + tst r12,#ARMV8_SHA256 + bne .LARMv8 + tst r12,#ARMV7_NEON + bne .LNEON +#endif + add $len,$inp,$len,lsl#6 @ len to point at the end of inp + stmdb sp!,{$ctx,$inp,$len,r4-r11,lr} + ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H} + sub $Ktbl,r3,#256+32 @ K256 + sub sp,sp,#16*4 @ alloca(X[16]) +.Loop: +# if __ARM_ARCH__>=7 + ldr $t1,[$inp],#4 +# else + ldrb $t1,[$inp,#3] +# endif + eor $t3,$B,$C @ magic + eor $t2,$t2,$t2 +___ +for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); } +$code.=".Lrounds_16_xx:\n"; +for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); } +$code.=<<___; +#if __ARM_ARCH__>=7 + ite eq @ Thumb2 thing, sanity check in ARM +#endif + ldreq $t3,[sp,#16*4] @ pull ctx + bne .Lrounds_16_xx + + add $A,$A,$t2 @ h+=Maj(a,b,c) from the past + ldr $t0,[$t3,#0] + ldr $t1,[$t3,#4] + ldr $t2,[$t3,#8] + add $A,$A,$t0 + ldr $t0,[$t3,#12] + add $B,$B,$t1 + ldr $t1,[$t3,#16] + add $C,$C,$t2 + ldr $t2,[$t3,#20] + add $D,$D,$t0 + ldr $t0,[$t3,#24] + add $E,$E,$t1 + ldr $t1,[$t3,#28] + add $F,$F,$t2 + ldr $inp,[sp,#17*4] @ pull inp + ldr $t2,[sp,#18*4] @ pull inp+len + add $G,$G,$t0 + add $H,$H,$t1 + stmia $t3,{$A,$B,$C,$D,$E,$F,$G,$H} + cmp $inp,$t2 + sub $Ktbl,$Ktbl,#256 @ rewind Ktbl + bne .Loop + + add sp,sp,#`16+3`*4 @ destroy frame +#if __ARM_ARCH__>=5 + ldmia sp!,{r4-r11,pc} +#else + ldmia sp!,{r4-r11,lr} + tst lr,#1 + moveq pc,lr @ be binary compatible with V4, yet + bx lr @ interoperable with Thumb ISA:-) +#endif +.size sha256_block_data_order,.-sha256_block_data_order +___ +###################################################################### +# NEON stuff +# +{{{ +my @X=map("q$_",(0..3)); +my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25"); +my $Xfer=$t4; +my $j=0; + +sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; } +sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; } + +sub AUTOLOAD() # thunk [simplified] x86-style perlasm +{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./; + my $arg = pop; + $arg = "#$arg" if ($arg*1 eq $arg); + $code .= "\t$opcode\t".join(',',@_,$arg)."\n"; +} + +sub Xupdate() +{ use integer; + my $body = shift; + my @insns = (&$body,&$body,&$body,&$body); + my ($a,$b,$c,$d,$e,$f,$g,$h); + + &vext_8 ($T0,@X[0],@X[1],4); # X[1..4] + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + &vext_8 ($T1,@X[2],@X[3],4); # X[9..12] + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T2,$T0,$sigma0[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += X[9..12] + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T1,$T0,$sigma0[2]); + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T2,$T0,32-$sigma0[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T3,$T0,$sigma0[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T1,$T1,$T2); + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T3,$T0,32-$sigma0[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T1,$T1,$T3); # sigma0(X[1..4]) + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T5,&Dhi(@X[3]),$sigma1[2]); + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += sigma0(X[1..4]) + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T5,$T5,$T4); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T5,$T5,$T4); # sigma1(X[14..15]) + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 (&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15]) + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[0]); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T5,&Dlo(@X[0]),$sigma1[2]); + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T5,$T5,$T4); + eval(shift(@insns)); + eval(shift(@insns)); + &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &vld1_32 ("{$T0}","[$Ktbl,:128]!"); + eval(shift(@insns)); + eval(shift(@insns)); + &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[1]); + eval(shift(@insns)); + eval(shift(@insns)); + &veor ($T5,$T5,$T4); # sigma1(X[16..17]) + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 (&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17]) + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 ($T0,$T0,@X[0]); + while($#insns>=2) { eval(shift(@insns)); } + &vst1_32 ("{$T0}","[$Xfer,:128]!"); + eval(shift(@insns)); + eval(shift(@insns)); + + push(@X,shift(@X)); # "rotate" X[] +} + +sub Xpreload() +{ use integer; + my $body = shift; + my @insns = (&$body,&$body,&$body,&$body); + my ($a,$b,$c,$d,$e,$f,$g,$h); + + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + &vld1_32 ("{$T0}","[$Ktbl,:128]!"); + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + &vrev32_8 (@X[0],@X[0]); + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + eval(shift(@insns)); + &vadd_i32 ($T0,$T0,@X[0]); + foreach (@insns) { eval; } # remaining instructions + &vst1_32 ("{$T0}","[$Xfer,:128]!"); + + push(@X,shift(@X)); # "rotate" X[] +} + +sub body_00_15 () { + ( + '($a,$b,$c,$d,$e,$f,$g,$h)=@V;'. + '&add ($h,$h,$t1)', # h+=X[i]+K[i] + '&eor ($t1,$f,$g)', + '&eor ($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))', + '&add ($a,$a,$t2)', # h+=Maj(a,b,c) from the past + '&and ($t1,$t1,$e)', + '&eor ($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))', # Sigma1(e) + '&eor ($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))', + '&eor ($t1,$t1,$g)', # Ch(e,f,g) + '&add ($h,$h,$t2,"ror#$Sigma1[0]")', # h+=Sigma1(e) + '&eor ($t2,$a,$b)', # a^b, b^c in next round + '&eor ($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))', # Sigma0(a) + '&add ($h,$h,$t1)', # h+=Ch(e,f,g) + '&ldr ($t1,sprintf "[sp,#%d]",4*(($j+1)&15)) if (($j&15)!=15);'. + '&ldr ($t1,"[$Ktbl]") if ($j==15);'. + '&ldr ($t1,"[sp,#64]") if ($j==31)', + '&and ($t3,$t3,$t2)', # (b^c)&=(a^b) + '&add ($d,$d,$h)', # d+=h + '&add ($h,$h,$t0,"ror#$Sigma0[0]");'. # h+=Sigma0(a) + '&eor ($t3,$t3,$b)', # Maj(a,b,c) + '$j++; unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);' + ) +} + +$code.=<<___; +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + +.global sha256_block_data_order_neon +.type sha256_block_data_order_neon,%function +.align 4 +sha256_block_data_order_neon: +.LNEON: + stmdb sp!,{r4-r12,lr} + + sub $H,sp,#16*4+16 + adr $Ktbl,.Lsha256_block_data_order + sub $Ktbl,$Ktbl,#.Lsha256_block_data_order-K256 + bic $H,$H,#15 @ align for 128-bit stores + mov $t2,sp + mov sp,$H @ alloca + add $len,$inp,$len,lsl#6 @ len to point at the end of inp + + vld1.8 {@X[0]},[$inp]! + vld1.8 {@X[1]},[$inp]! + vld1.8 {@X[2]},[$inp]! + vld1.8 {@X[3]},[$inp]! + vld1.32 {$T0},[$Ktbl,:128]! + vld1.32 {$T1},[$Ktbl,:128]! + vld1.32 {$T2},[$Ktbl,:128]! + vld1.32 {$T3},[$Ktbl,:128]! + vrev32.8 @X[0],@X[0] @ yes, even on + str $ctx,[sp,#64] + vrev32.8 @X[1],@X[1] @ big-endian + str $inp,[sp,#68] + mov $Xfer,sp + vrev32.8 @X[2],@X[2] + str $len,[sp,#72] + vrev32.8 @X[3],@X[3] + str $t2,[sp,#76] @ save original sp + vadd.i32 $T0,$T0,@X[0] + vadd.i32 $T1,$T1,@X[1] + vst1.32 {$T0},[$Xfer,:128]! + vadd.i32 $T2,$T2,@X[2] + vst1.32 {$T1},[$Xfer,:128]! + vadd.i32 $T3,$T3,@X[3] + vst1.32 {$T2},[$Xfer,:128]! + vst1.32 {$T3},[$Xfer,:128]! + + ldmia $ctx,{$A-$H} + sub $Xfer,$Xfer,#64 + ldr $t1,[sp,#0] + eor $t2,$t2,$t2 + eor $t3,$B,$C + b .L_00_48 + +.align 4 +.L_00_48: +___ + &Xupdate(\&body_00_15); + &Xupdate(\&body_00_15); + &Xupdate(\&body_00_15); + &Xupdate(\&body_00_15); +$code.=<<___; + teq $t1,#0 @ check for K256 terminator + ldr $t1,[sp,#0] + sub $Xfer,$Xfer,#64 + bne .L_00_48 + + ldr $inp,[sp,#68] + ldr $t0,[sp,#72] + sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl + teq $inp,$t0 + it eq + subeq $inp,$inp,#64 @ avoid SEGV + vld1.8 {@X[0]},[$inp]! @ load next input block + vld1.8 {@X[1]},[$inp]! + vld1.8 {@X[2]},[$inp]! + vld1.8 {@X[3]},[$inp]! + it ne + strne $inp,[sp,#68] + mov $Xfer,sp +___ + &Xpreload(\&body_00_15); + &Xpreload(\&body_00_15); + &Xpreload(\&body_00_15); + &Xpreload(\&body_00_15); +$code.=<<___; + ldr $t0,[$t1,#0] + add $A,$A,$t2 @ h+=Maj(a,b,c) from the past + ldr $t2,[$t1,#4] + ldr $t3,[$t1,#8] + ldr $t4,[$t1,#12] + add $A,$A,$t0 @ accumulate + ldr $t0,[$t1,#16] + add $B,$B,$t2 + ldr $t2,[$t1,#20] + add $C,$C,$t3 + ldr $t3,[$t1,#24] + add $D,$D,$t4 + ldr $t4,[$t1,#28] + add $E,$E,$t0 + str $A,[$t1],#4 + add $F,$F,$t2 + str $B,[$t1],#4 + add $G,$G,$t3 + str $C,[$t1],#4 + add $H,$H,$t4 + str $D,[$t1],#4 + stmia $t1,{$E-$H} + + ittte ne + movne $Xfer,sp + ldrne $t1,[sp,#0] + eorne $t2,$t2,$t2 + ldreq sp,[sp,#76] @ restore original sp + itt ne + eorne $t3,$B,$C + bne .L_00_48 + + ldmia sp!,{r4-r12,pc} +.size sha256_block_data_order_neon,.-sha256_block_data_order_neon +#endif +___ +}}} +###################################################################### +# ARMv8 stuff +# +{{{ +my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2)); +my @MSG=map("q$_",(8..11)); +my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15)); +my $Ktbl="r3"; + +$code.=<<___; +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) + +# ifdef __thumb2__ +# define INST(a,b,c,d) .byte c,d|0xc,a,b +# else +# define INST(a,b,c,d) .byte a,b,c,d +# endif + +.type sha256_block_data_order_armv8,%function +.align 5 +sha256_block_data_order_armv8: +.LARMv8: + vld1.32 {$ABCD,$EFGH},[$ctx] +# ifdef __thumb2__ + adr $Ktbl,.LARMv8 + sub $Ktbl,$Ktbl,#.LARMv8-K256 +# else + adrl $Ktbl,K256 +# endif + add $len,$inp,$len,lsl#6 @ len to point at the end of inp + +.Loop_v8: + vld1.8 {@MSG[0]-@MSG[1]},[$inp]! + vld1.8 {@MSG[2]-@MSG[3]},[$inp]! + vld1.32 {$W0},[$Ktbl]! + vrev32.8 @MSG[0],@MSG[0] + vrev32.8 @MSG[1],@MSG[1] + vrev32.8 @MSG[2],@MSG[2] + vrev32.8 @MSG[3],@MSG[3] + vmov $ABCD_SAVE,$ABCD @ offload + vmov $EFGH_SAVE,$EFGH + teq $inp,$len +___ +for($i=0;$i<12;$i++) { +$code.=<<___; + vld1.32 {$W1},[$Ktbl]! + vadd.i32 $W0,$W0,@MSG[0] + sha256su0 @MSG[0],@MSG[1] + vmov $abcd,$ABCD + sha256h $ABCD,$EFGH,$W0 + sha256h2 $EFGH,$abcd,$W0 + sha256su1 @MSG[0],@MSG[2],@MSG[3] +___ + ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG)); +} +$code.=<<___; + vld1.32 {$W1},[$Ktbl]! + vadd.i32 $W0,$W0,@MSG[0] + vmov $abcd,$ABCD + sha256h $ABCD,$EFGH,$W0 + sha256h2 $EFGH,$abcd,$W0 + + vld1.32 {$W0},[$Ktbl]! + vadd.i32 $W1,$W1,@MSG[1] + vmov $abcd,$ABCD + sha256h $ABCD,$EFGH,$W1 + sha256h2 $EFGH,$abcd,$W1 + + vld1.32 {$W1},[$Ktbl] + vadd.i32 $W0,$W0,@MSG[2] + sub $Ktbl,$Ktbl,#256-16 @ rewind + vmov $abcd,$ABCD + sha256h $ABCD,$EFGH,$W0 + sha256h2 $EFGH,$abcd,$W0 + + vadd.i32 $W1,$W1,@MSG[3] + vmov $abcd,$ABCD + sha256h $ABCD,$EFGH,$W1 + sha256h2 $EFGH,$abcd,$W1 + + vadd.i32 $ABCD,$ABCD,$ABCD_SAVE + vadd.i32 $EFGH,$EFGH,$EFGH_SAVE + it ne + bne .Loop_v8 + + vst1.32 {$ABCD,$EFGH},[$ctx] + + ret @ bx lr +.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8 +#endif +___ +}}} +$code.=<<___; +.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by " +.align 2 +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.comm OPENSSL_armcap_P,4,4 +#endif +___ + +open SELF,$0; +while() { + next if (/^#!/); + last if (!s/^#/@/ and !/^$/); + print; +} +close SELF; + +{ my %opcode = ( + "sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40, + "sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 ); + + sub unsha256 { + my ($mnemonic,$arg)=@_; + + if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) { + my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19) + |(($2&7)<<17)|(($2&8)<<4) + |(($3&7)<<1) |(($3&8)<<2); + # since ARMv7 instructions are always encoded little-endian. + # correct solution is to use .inst directive, but older + # assemblers don't implement it:-( + sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s", + $word&0xff,($word>>8)&0xff, + ($word>>16)&0xff,($word>>24)&0xff, + $mnemonic,$arg; + } + } +} + +foreach (split($/,$code)) { + + s/\`([^\`]*)\`/eval $1/geo; + + s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo; + + s/\bret\b/bx lr/go or + s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4 + + print $_,"\n"; +} + +close STDOUT; # enforce flush diff --git a/arch/arm/lib/crypto/sha256-ce.S b/arch/arm/lib/crypto/sha256-ce.S new file mode 100644 index 000000000000..ac2c9b01b22d --- /dev/null +++ b/arch/arm/lib/crypto/sha256-ce.S @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sha256-ce.S - SHA-224/256 secure hash using ARMv8 Crypto Extensions + * + * Copyright (C) 2015 Linaro Ltd. + * Author: Ard Biesheuvel + */ + +#include +#include + + .text + .arch armv8-a + .fpu crypto-neon-fp-armv8 + + k0 .req q7 + k1 .req q8 + rk .req r3 + + ta0 .req q9 + ta1 .req q10 + tb0 .req q10 + tb1 .req q9 + + dga .req q11 + dgb .req q12 + + dg0 .req q13 + dg1 .req q14 + dg2 .req q15 + + .macro add_only, ev, s0 + vmov dg2, dg0 + .ifnb \s0 + vld1.32 {k\ev}, [rk, :128]! + .endif + sha256h.32 dg0, dg1, tb\ev + sha256h2.32 dg1, dg2, tb\ev + .ifnb \s0 + vadd.u32 ta\ev, q\s0, k\ev + .endif + .endm + + .macro add_update, ev, s0, s1, s2, s3 + sha256su0.32 q\s0, q\s1 + add_only \ev, \s1 + sha256su1.32 q\s0, q\s2, q\s3 + .endm + + .align 6 +.Lsha256_rcon: + .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 + .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 + .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 + .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 + .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc + .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da + .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 + .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 + .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 + .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 + .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 + .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 + .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 + .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 + .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 + .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 + + /* + * void sha256_ce_transform(u32 state[SHA256_STATE_WORDS], + * const u8 *data, size_t nblocks); + */ +ENTRY(sha256_ce_transform) + /* load state */ + vld1.32 {dga-dgb}, [r0] + + /* load input */ +0: vld1.32 {q0-q1}, [r1]! + vld1.32 {q2-q3}, [r1]! + subs r2, r2, #1 + +#ifndef CONFIG_CPU_BIG_ENDIAN + vrev32.8 q0, q0 + vrev32.8 q1, q1 + vrev32.8 q2, q2 + vrev32.8 q3, q3 +#endif + + /* load first round constant */ + adr rk, .Lsha256_rcon + vld1.32 {k0}, [rk, :128]! + + vadd.u32 ta0, q0, k0 + vmov dg0, dga + vmov dg1, dgb + + add_update 1, 0, 1, 2, 3 + add_update 0, 1, 2, 3, 0 + add_update 1, 2, 3, 0, 1 + add_update 0, 3, 0, 1, 2 + add_update 1, 0, 1, 2, 3 + add_update 0, 1, 2, 3, 0 + add_update 1, 2, 3, 0, 1 + add_update 0, 3, 0, 1, 2 + add_update 1, 0, 1, 2, 3 + add_update 0, 1, 2, 3, 0 + add_update 1, 2, 3, 0, 1 + add_update 0, 3, 0, 1, 2 + + add_only 1, 1 + add_only 0, 2 + add_only 1, 3 + add_only 0 + + /* update state */ + vadd.u32 dga, dga, dg0 + vadd.u32 dgb, dgb, dg1 + bne 0b + + /* store new state */ + vst1.32 {dga-dgb}, [r0] + bx lr +ENDPROC(sha256_ce_transform) diff --git a/arch/arm/lib/crypto/sha256.c b/arch/arm/lib/crypto/sha256.c new file mode 100644 index 000000000000..3a8dfc304807 --- /dev/null +++ b/arch/arm/lib/crypto/sha256.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SHA-256 optimized for ARM + * + * Copyright 2025 Google LLC + */ +#include +#include +#include +#include +#include + +asmlinkage void sha256_block_data_order(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks); +asmlinkage void sha256_block_data_order_neon(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks); +asmlinkage void sha256_ce_transform(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce); + +void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks) +{ + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && + static_branch_likely(&have_neon) && crypto_simd_usable()) { + kernel_neon_begin(); + if (static_branch_likely(&have_ce)) + sha256_ce_transform(state, data, nblocks); + else + sha256_block_data_order_neon(state, data, nblocks); + kernel_neon_end(); + } else { + sha256_block_data_order(state, data, nblocks); + } +} +EXPORT_SYMBOL(sha256_blocks_arch); + +bool sha256_is_arch_optimized(void) +{ + /* We always can use at least the ARM scalar implementation. */ + return true; +} +EXPORT_SYMBOL(sha256_is_arch_optimized); + +static int __init sha256_arm_mod_init(void) +{ + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) { + static_branch_enable(&have_neon); + if (elf_hwcap2 & HWCAP2_SHA2) + static_branch_enable(&have_ce); + } + return 0; +} +arch_initcall(sha256_arm_mod_init); + +static void __exit sha256_arm_mod_exit(void) +{ +} +module_exit(sha256_arm_mod_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SHA-256 optimized for ARM"); -- cgit v1.2.3