From patchwork Thu May 29 18:05:22 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 31145 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-pd0-f199.google.com (mail-pd0-f199.google.com [209.85.192.199]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id 3E552203E6 for ; Thu, 29 May 2014 18:05:39 +0000 (UTC) Received: by mail-pd0-f199.google.com with SMTP id fp1sf44152pdb.6 for ; Thu, 29 May 2014 11:05:38 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:delivered-to:from:to:cc:subject :date:message-id:in-reply-to:references:x-original-sender :x-original-authentication-results:precedence:mailing-list:list-id :list-post:list-help:list-archive:list-unsubscribe; bh=QkUaEkCm/c0e9sUG+qcxpcpghkZdI4YxdlG2rdFsU0o=; b=QDpXYYA3XeR0uaVje06VrMPk2Ywcy6KCzHc4K4B79ZL4ozhO9gemJxGazglC7ZAFFM XoPZKb3VZAjf02yMrNdbBQyamAjhbZW9lyHpmr/SMERFgOcofnq9bRVPL83jXKNb8jl5 vfPT0WbX4MCmk61TMTMz3aXFZXPNRYRO4FKYKq6Sd2VSH25Viiqd0/pFsm9f/Ipujdmj fdqaE/ETEXXFkt8cUNanuSaMsHNGnf/QASlkoWiOphVW7qR0n4hQLZz5hxDjolJHjMOU xrswRNrzFeXVE+TQd6d82CCtLpUu292en90+SWWwZdlmGCMfnT+nn/yQz8HBpdwqHaL2 +hMQ== X-Gm-Message-State: ALoCoQnVZ57UOPHmBJ7NWN8P3JS2mVgzyHSrnE0zfVXApWUm2Hkcz5Ha/638oWXAO3kqDhVLDHQ+ X-Received: by 10.67.4.170 with SMTP id cf10mr2529033pad.31.1401386738375; Thu, 29 May 2014 11:05:38 -0700 (PDT) MIME-Version: 1.0 X-BeenThere: patchwork-forward@linaro.org Received: by 10.140.40.74 with SMTP id w68ls704465qgw.53.gmail; Thu, 29 May 2014 11:05:38 -0700 (PDT) X-Received: by 10.58.195.231 with SMTP id ih7mr8320152vec.32.1401386738172; Thu, 29 May 2014 11:05:38 -0700 (PDT) Received: from mail-ve0-f171.google.com (mail-ve0-f171.google.com [209.85.128.171]) by mx.google.com with ESMTPS id x1si1119413vep.70.2014.05.29.11.05.38 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Thu, 29 May 2014 11:05:38 -0700 (PDT) Received-SPF: pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.128.171 as permitted sender) client-ip=209.85.128.171; Received: by mail-ve0-f171.google.com with SMTP id oz11so825788veb.16 for ; Thu, 29 May 2014 11:05:38 -0700 (PDT) X-Received: by 10.220.44.141 with SMTP id a13mr2741484vcf.71.1401386738055; Thu, 29 May 2014 11:05:38 -0700 (PDT) X-Forwarded-To: patchwork-forward@linaro.org X-Forwarded-For: patch@linaro.org patchwork-forward@linaro.org Delivered-To: patches@linaro.org Received: by 10.220.221.72 with SMTP id ib8csp48368vcb; Thu, 29 May 2014 11:05:37 -0700 (PDT) X-Received: by 10.180.92.69 with SMTP id ck5mr13953548wib.15.1401386737078; Thu, 29 May 2014 11:05:37 -0700 (PDT) Received: from mnementh.archaic.org.uk (mnementh.archaic.org.uk. [2001:8b0:1d0::1]) by mx.google.com with ESMTPS id m2si3635965wiz.34.2014.05.29.11.05.32 for (version=TLSv1.2 cipher=RC4-SHA bits=128/128); Thu, 29 May 2014 11:05:33 -0700 (PDT) Received-SPF: none (google.com: pm215@archaic.org.uk does not designate permitted sender hosts) client-ip=2001:8b0:1d0::1; Received: from pm215 by mnementh.archaic.org.uk with local (Exim 4.80) (envelope-from ) id 1Wq4hg-0006uQ-9Y; Thu, 29 May 2014 19:05:24 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Cc: patches@linaro.org, Ard Biesheuvel , =?UTF-8?q?Alex=20Benn=C3=A9e?= Subject: [PATCH 1/3] target-arm: add support for v8 SHA1 and SHA256 instructions Date: Thu, 29 May 2014 19:05:22 +0100 Message-Id: <1401386724-26529-2-git-send-email-peter.maydell@linaro.org> X-Mailer: git-send-email 1.7.10.4 In-Reply-To: <1401386724-26529-1-git-send-email-peter.maydell@linaro.org> References: <1401386724-26529-1-git-send-email-peter.maydell@linaro.org> X-Removed-Original-Auth: Dkim didn't pass. X-Original-Sender: peter.maydell@linaro.org X-Original-Authentication-Results: mx.google.com; spf=pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.128.171 as permitted sender) smtp.mail=patch+caf_=patchwork-forward=linaro.org@linaro.org Precedence: list Mailing-list: list patchwork-forward@linaro.org; contact patchwork-forward+owners@linaro.org List-ID: X-Google-Group-Id: 836684582541 List-Post: , List-Help: , List-Archive: List-Unsubscribe: , From: Ard Biesheuvel This adds support for the SHA1 and SHA256 instructions that are available on some v8 implementations of Aarch32. Signed-off-by: Ard Biesheuvel [PMM: * rebase * fix bad indent * add a missing UNDEF check for Q!=1 in the 3-reg SHA1/SHA256 case * use g_assert_not_reached() * don't re-extract bit 6 for the 2-reg-misc encodings * set the ELF HWCAP2 bits for the new features ] Signed-off-by: Peter Maydell --- linux-user/elfload.c | 2 + target-arm/cpu.c | 2 + target-arm/cpu.h | 2 + target-arm/crypto_helper.c | 257 +++++++++++++++++++++++++++++++++++++++++++-- target-arm/helper.h | 9 ++ target-arm/translate.c | 84 +++++++++++++++ 6 files changed, 349 insertions(+), 7 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 995f999..9bda262 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -468,6 +468,8 @@ static uint32_t get_elf_hwcap2(void) uint32_t hwcaps = 0; GET_FEATURE(ARM_FEATURE_V8_AES, ARM_HWCAP2_ARM_AES); + GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP2_ARM_SHA1); + GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP2_ARM_SHA2); GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP2_ARM_CRC32); return hwcaps; } diff --git a/target-arm/cpu.c b/target-arm/cpu.c index 794dcb9..753f6cb 100644 --- a/target-arm/cpu.c +++ b/target-arm/cpu.c @@ -317,6 +317,8 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) set_feature(env, ARM_FEATURE_ARM_DIV); set_feature(env, ARM_FEATURE_LPAE); set_feature(env, ARM_FEATURE_V8_AES); + set_feature(env, ARM_FEATURE_V8_SHA1); + set_feature(env, ARM_FEATURE_V8_SHA256); } if (arm_feature(env, ARM_FEATURE_V7)) { set_feature(env, ARM_FEATURE_VAPA); diff --git a/target-arm/cpu.h b/target-arm/cpu.h index 8d04385..a8fc2ec 100644 --- a/target-arm/cpu.h +++ b/target-arm/cpu.h @@ -635,6 +635,8 @@ enum arm_features { ARM_FEATURE_CBAR_RO, /* has cp15 CBAR and it is read-only */ ARM_FEATURE_EL2, /* has EL2 Virtualization support */ ARM_FEATURE_EL3, /* has EL3 Secure monitor support */ + ARM_FEATURE_V8_SHA1, /* implements SHA1 part of v8 Crypto Extensions */ + ARM_FEATURE_V8_SHA256, /* implements SHA256 part of v8 Crypto Extensions */ }; static inline int arm_feature(CPUARMState *env, int feature) diff --git a/target-arm/crypto_helper.c b/target-arm/crypto_helper.c index d8898ed..3e4b5f7 100644 --- a/target-arm/crypto_helper.c +++ b/target-arm/crypto_helper.c @@ -1,7 +1,7 @@ /* * crypto_helper.c - emulate v8 Crypto Extensions instructions * - * Copyright (C) 2013 Linaro Ltd + * Copyright (C) 2013 - 2014 Linaro Ltd * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -15,9 +15,9 @@ #include "exec/exec-all.h" #include "exec/helper-proto.h" -union AES_STATE { +union CRYPTO_STATE { uint8_t bytes[16]; - uint32_t cols[4]; + uint32_t words[4]; uint64_t l[2]; }; @@ -99,11 +99,11 @@ void HELPER(crypto_aese)(CPUARMState *env, uint32_t rd, uint32_t rm, /* ShiftRows permutation vector for decryption */ { 0, 13, 10, 7, 4, 1, 14, 11, 8, 5, 2, 15, 12, 9, 6, 3 }, }; - union AES_STATE rk = { .l = { + union CRYPTO_STATE rk = { .l = { float64_val(env->vfp.regs[rm]), float64_val(env->vfp.regs[rm + 1]) } }; - union AES_STATE st = { .l = { + union CRYPTO_STATE st = { .l = { float64_val(env->vfp.regs[rd]), float64_val(env->vfp.regs[rd + 1]) } }; @@ -260,7 +260,7 @@ void HELPER(crypto_aesmc)(CPUARMState *env, uint32_t rd, uint32_t rm, 0x92b479a7, 0x99b970a9, 0x84ae6bbb, 0x8fa362b5, 0xbe805d9f, 0xb58d5491, 0xa89a4f83, 0xa397468d, } }; - union AES_STATE st = { .l = { + union CRYPTO_STATE st = { .l = { float64_val(env->vfp.regs[rm]), float64_val(env->vfp.regs[rm + 1]) } }; @@ -269,7 +269,7 @@ void HELPER(crypto_aesmc)(CPUARMState *env, uint32_t rd, uint32_t rm, assert(decrypt < 2); for (i = 0; i < 16; i += 4) { - st.cols[i >> 2] = cpu_to_le32( + st.words[i >> 2] = cpu_to_le32( mc[decrypt][st.bytes[i]] ^ rol32(mc[decrypt][st.bytes[i + 1]], 8) ^ rol32(mc[decrypt][st.bytes[i + 2]], 16) ^ @@ -279,3 +279,246 @@ void HELPER(crypto_aesmc)(CPUARMState *env, uint32_t rd, uint32_t rm, env->vfp.regs[rd] = make_float64(st.l[0]); env->vfp.regs[rd + 1] = make_float64(st.l[1]); } + +/* + * SHA-1 logical functions + */ + +static uint32_t cho(uint32_t x, uint32_t y, uint32_t z) +{ + return (x & (y ^ z)) ^ z; +} + +static uint32_t par(uint32_t x, uint32_t y, uint32_t z) +{ + return x ^ y ^ z; +} + +static uint32_t maj(uint32_t x, uint32_t y, uint32_t z) +{ + return (x & y) | ((x | y) & z); +} + +void HELPER(crypto_sha1_3reg)(CPUARMState *env, uint32_t rd, uint32_t rn, + uint32_t rm, uint32_t op) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE n = { .l = { + float64_val(env->vfp.regs[rn]), + float64_val(env->vfp.regs[rn + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + + if (op == 3) { /* sha1su0 */ + d.l[0] ^= d.l[1] ^ m.l[0]; + d.l[1] ^= n.l[0] ^ m.l[1]; + } else { + int i; + + for (i = 0; i < 4; i++) { + uint32_t t; + + switch (op) { + case 0: /* sha1c */ + t = cho(d.words[1], d.words[2], d.words[3]); + break; + case 1: /* sha1p */ + t = par(d.words[1], d.words[2], d.words[3]); + break; + case 2: /* sha1m */ + t = maj(d.words[1], d.words[2], d.words[3]); + break; + default: + g_assert_not_reached(); + } + t += rol32(d.words[0], 5) + n.words[0] + m.words[i]; + + n.words[0] = d.words[3]; + d.words[3] = d.words[2]; + d.words[2] = ror32(d.words[1], 2); + d.words[1] = d.words[0]; + d.words[0] = t; + } + } + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} + +void HELPER(crypto_sha1h)(CPUARMState *env, uint32_t rd, uint32_t rm) +{ + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + + m.words[0] = ror32(m.words[0], 2); + m.words[1] = m.words[2] = m.words[3] = 0; + + env->vfp.regs[rd] = make_float64(m.l[0]); + env->vfp.regs[rd + 1] = make_float64(m.l[1]); +} + +void HELPER(crypto_sha1su1)(CPUARMState *env, uint32_t rd, uint32_t rm) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + + d.words[0] = rol32(d.words[0] ^ m.words[1], 1); + d.words[1] = rol32(d.words[1] ^ m.words[2], 1); + d.words[2] = rol32(d.words[2] ^ m.words[3], 1); + d.words[3] = rol32(d.words[3] ^ d.words[0], 1); + + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} + +/* + * The SHA-256 logical functions, according to + * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf + */ + +static uint32_t S0(uint32_t x) +{ + return ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22); +} + +static uint32_t S1(uint32_t x) +{ + return ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25); +} + +static uint32_t s0(uint32_t x) +{ + return ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3); +} + +static uint32_t s1(uint32_t x) +{ + return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10); +} + +void HELPER(crypto_sha256h)(CPUARMState *env, uint32_t rd, uint32_t rn, + uint32_t rm) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE n = { .l = { + float64_val(env->vfp.regs[rn]), + float64_val(env->vfp.regs[rn + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + int i; + + for (i = 0; i < 4; i++) { + uint32_t t = cho(n.words[0], n.words[1], n.words[2]) + n.words[3] + + S1(n.words[0]) + m.words[i]; + + n.words[3] = n.words[2]; + n.words[2] = n.words[1]; + n.words[1] = n.words[0]; + n.words[0] = d.words[3] + t; + + t += maj(d.words[0], d.words[1], d.words[2]) + S0(d.words[0]); + + d.words[3] = d.words[2]; + d.words[2] = d.words[1]; + d.words[1] = d.words[0]; + d.words[0] = t; + } + + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} + +void HELPER(crypto_sha256h2)(CPUARMState *env, uint32_t rd, uint32_t rn, + uint32_t rm) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE n = { .l = { + float64_val(env->vfp.regs[rn]), + float64_val(env->vfp.regs[rn + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + int i; + + for (i = 0; i < 4; i++) { + uint32_t t = cho(d.words[0], d.words[1], d.words[2]) + d.words[3] + + S1(d.words[0]) + m.words[i]; + + d.words[3] = d.words[2]; + d.words[2] = d.words[1]; + d.words[1] = d.words[0]; + d.words[0] = n.words[3 - i] + t; + } + + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} + +void HELPER(crypto_sha256su0)(CPUARMState *env, uint32_t rd, uint32_t rm) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + + d.words[0] += s0(d.words[1]); + d.words[1] += s0(d.words[2]); + d.words[2] += s0(d.words[3]); + d.words[3] += s0(m.words[0]); + + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} + +void HELPER(crypto_sha256su1)(CPUARMState *env, uint32_t rd, uint32_t rn, + uint32_t rm) +{ + union CRYPTO_STATE d = { .l = { + float64_val(env->vfp.regs[rd]), + float64_val(env->vfp.regs[rd + 1]) + } }; + union CRYPTO_STATE n = { .l = { + float64_val(env->vfp.regs[rn]), + float64_val(env->vfp.regs[rn + 1]) + } }; + union CRYPTO_STATE m = { .l = { + float64_val(env->vfp.regs[rm]), + float64_val(env->vfp.regs[rm + 1]) + } }; + + d.words[0] += s1(m.words[2]) + n.words[1]; + d.words[1] += s1(m.words[3]) + n.words[2]; + d.words[2] += s1(d.words[0]) + n.words[3]; + d.words[3] += s1(d.words[1]) + m.words[0]; + + env->vfp.regs[rd] = make_float64(d.l[0]); + env->vfp.regs[rd + 1] = make_float64(d.l[1]); +} diff --git a/target-arm/helper.h b/target-arm/helper.h index b63fd0f..113b09d 100644 --- a/target-arm/helper.h +++ b/target-arm/helper.h @@ -512,6 +512,15 @@ DEF_HELPER_3(neon_qzip32, void, env, i32, i32) DEF_HELPER_4(crypto_aese, void, env, i32, i32, i32) DEF_HELPER_4(crypto_aesmc, void, env, i32, i32, i32) +DEF_HELPER_5(crypto_sha1_3reg, void, env, i32, i32, i32, i32) +DEF_HELPER_3(crypto_sha1h, void, env, i32, i32) +DEF_HELPER_3(crypto_sha1su1, void, env, i32, i32) + +DEF_HELPER_4(crypto_sha256h, void, env, i32, i32, i32) +DEF_HELPER_4(crypto_sha256h2, void, env, i32, i32, i32) +DEF_HELPER_3(crypto_sha256su0, void, env, i32, i32) +DEF_HELPER_4(crypto_sha256su1, void, env, i32, i32, i32) + DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_2(dc_zva, void, env, i64) diff --git a/target-arm/translate.c b/target-arm/translate.c index 7f6fcd6..ab3713d 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -4775,6 +4775,7 @@ static void gen_neon_narrow_op(int op, int u, int size, #define NEON_3R_VPMIN 21 #define NEON_3R_VQDMULH_VQRDMULH 22 #define NEON_3R_VPADD 23 +#define NEON_3R_SHA 24 /* SHA1C,SHA1P,SHA1M,SHA1SU0,SHA256H{2},SHA256SU1 */ #define NEON_3R_VFM 25 /* VFMA, VFMS : float fused multiply-add */ #define NEON_3R_FLOAT_ARITH 26 /* float VADD, VSUB, VPADD, VABD */ #define NEON_3R_FLOAT_MULTIPLY 27 /* float VMLA, VMLS, VMUL */ @@ -4808,6 +4809,7 @@ static const uint8_t neon_3r_sizes[] = { [NEON_3R_VPMIN] = 0x7, [NEON_3R_VQDMULH_VQRDMULH] = 0x6, [NEON_3R_VPADD] = 0x7, + [NEON_3R_SHA] = 0xf, /* size field encodes op type */ [NEON_3R_VFM] = 0x5, /* size bit 1 encodes op */ [NEON_3R_FLOAT_ARITH] = 0x5, /* size bit 1 encodes op */ [NEON_3R_FLOAT_MULTIPLY] = 0x5, /* size bit 1 encodes op */ @@ -4841,6 +4843,7 @@ static const uint8_t neon_3r_sizes[] = { #define NEON_2RM_VCEQ0 18 #define NEON_2RM_VCLE0 19 #define NEON_2RM_VCLT0 20 +#define NEON_2RM_SHA1H 21 #define NEON_2RM_VABS 22 #define NEON_2RM_VNEG 23 #define NEON_2RM_VCGT0_F 24 @@ -4857,6 +4860,7 @@ static const uint8_t neon_3r_sizes[] = { #define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */ #define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */ #define NEON_2RM_VSHLL 38 +#define NEON_2RM_SHA1SU1 39 /* Includes SHA256SU0 */ #define NEON_2RM_VRINTN 40 #define NEON_2RM_VRINTX 41 #define NEON_2RM_VRINTA 42 @@ -4917,6 +4921,7 @@ static const uint8_t neon_2rm_sizes[] = { [NEON_2RM_VCEQ0] = 0x7, [NEON_2RM_VCLE0] = 0x7, [NEON_2RM_VCLT0] = 0x7, + [NEON_2RM_SHA1H] = 0x4, [NEON_2RM_VABS] = 0x7, [NEON_2RM_VNEG] = 0x7, [NEON_2RM_VCGT0_F] = 0x4, @@ -4933,6 +4938,7 @@ static const uint8_t neon_2rm_sizes[] = { [NEON_2RM_VMOVN] = 0x7, [NEON_2RM_VQMOVN] = 0x7, [NEON_2RM_VSHLL] = 0x7, + [NEON_2RM_SHA1SU1] = 0x4, [NEON_2RM_VRINTN] = 0x4, [NEON_2RM_VRINTX] = 0x4, [NEON_2RM_VRINTA] = 0x4, @@ -5010,6 +5016,49 @@ static int disas_neon_data_insn(CPUARMState * env, DisasContext *s, uint32_t ins if (q && ((rd | rn | rm) & 1)) { return 1; } + /* + * The SHA-1/SHA-256 3-register instructions require special treatment + * here, as their size field is overloaded as an op type selector, and + * they all consume their input in a single pass. + */ + if (op == NEON_3R_SHA) { + if (!q) { + return 1; + } + if (!u) { /* SHA-1 */ + if (!arm_feature(env, ARM_FEATURE_V8_SHA1)) { + return 1; + } + tmp = tcg_const_i32(rd); + tmp2 = tcg_const_i32(rn); + tmp3 = tcg_const_i32(rm); + tmp4 = tcg_const_i32(size); + gen_helper_crypto_sha1_3reg(cpu_env, tmp, tmp2, tmp3, tmp4); + tcg_temp_free_i32(tmp4); + } else { /* SHA-256 */ + if (!arm_feature(env, ARM_FEATURE_V8_SHA256) || size == 3) { + return 1; + } + tmp = tcg_const_i32(rd); + tmp2 = tcg_const_i32(rn); + tmp3 = tcg_const_i32(rm); + switch (size) { + case 0: + gen_helper_crypto_sha256h(cpu_env, tmp, tmp2, tmp3); + break; + case 1: + gen_helper_crypto_sha256h2(cpu_env, tmp, tmp2, tmp3); + break; + case 2: + gen_helper_crypto_sha256su1(cpu_env, tmp, tmp2, tmp3); + break; + } + } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); + return 0; + } if (size == 3 && op != NEON_3R_LOGIC) { /* 64-bit element instructions. */ for (pass = 0; pass < (q ? 2 : 1); pass++) { @@ -6485,6 +6534,41 @@ static int disas_neon_data_insn(CPUARMState * env, DisasContext *s, uint32_t ins tcg_temp_free_i32(tmp2); tcg_temp_free_i32(tmp3); break; + case NEON_2RM_SHA1H: + if (!arm_feature(env, ARM_FEATURE_V8_SHA1) + || ((rm | rd) & 1)) { + return 1; + } + tmp = tcg_const_i32(rd); + tmp2 = tcg_const_i32(rm); + + gen_helper_crypto_sha1h(cpu_env, tmp, tmp2); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + break; + case NEON_2RM_SHA1SU1: + if ((rm | rd) & 1) { + return 1; + } + /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */ + if (q) { + if (!arm_feature(env, ARM_FEATURE_V8_SHA256)) { + return 1; + } + } else if (!arm_feature(env, ARM_FEATURE_V8_SHA1)) { + return 1; + } + tmp = tcg_const_i32(rd); + tmp2 = tcg_const_i32(rm); + if (q) { + gen_helper_crypto_sha256su0(cpu_env, tmp, tmp2); + } else { + gen_helper_crypto_sha1su1(cpu_env, tmp, tmp2); + } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + break; default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) {