[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v2] target-arm: add support for v8 AES instructions
|
From: |
Ard Biesheuvel |
|
Subject: |
[Qemu-devel] [PATCH v2] target-arm: add support for v8 AES instructions |
|
Date: |
Thu, 5 Dec 2013 18:54:38 +0100 |
This adds support for the AESE/AESD/AESMC/AESIMC instructions that
are available on some v8 implementations of Aarch32.
Signed-off-by: Ard Biesheuvel <address@hidden>
---
Changes since v1:
- refactored AES code:
* use precomputed lookup tables for AESMC and AESIMC
* squash leaf functions add_sub_shift() and mix_columns() into callers
- rebased onto upstream master
- added missing tcg_free_temp()'s and other review suggestions by PMM
target-arm/Makefile.objs | 1 +
target-arm/cpu.c | 1 +
target-arm/cpu.h | 1 +
target-arm/crypto_helper.c | 281 +++++++++++++++++++++++++++++++++++++++++++++
target-arm/helper.h | 3 +
target-arm/translate.c | 26 +++++
6 files changed, 313 insertions(+)
create mode 100644 target-arm/crypto_helper.c
diff --git a/target-arm/Makefile.objs b/target-arm/Makefile.objs
index 356fbfc..f428b5b 100644
--- a/target-arm/Makefile.objs
+++ b/target-arm/Makefile.objs
@@ -6,3 +6,4 @@ obj-y += translate.o op_helper.o helper.o cpu.o
obj-y += neon_helper.o iwmmxt_helper.o
obj-y += gdbstub.o
obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o gdbstub64.o
+obj-y += crypto_helper.o
diff --git a/target-arm/cpu.c b/target-arm/cpu.c
index d40f2a7..11a82db 100644
--- a/target-arm/cpu.c
+++ b/target-arm/cpu.c
@@ -241,6 +241,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error
**errp)
set_feature(env, ARM_FEATURE_V7);
set_feature(env, ARM_FEATURE_ARM_DIV);
set_feature(env, ARM_FEATURE_LPAE);
+ set_feature(env, ARM_FEATURE_V8_AES);
}
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 9f110f1..6dbac97 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -465,6 +465,7 @@ enum arm_features {
ARM_FEATURE_LPAE, /* has Large Physical Address Extension */
ARM_FEATURE_V8,
ARM_FEATURE_AARCH64, /* supports 64 bit mode */
+ ARM_FEATURE_V8_AES, /* implements AES 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
new file mode 100644
index 0000000..f94be69
--- /dev/null
+++ b/target-arm/crypto_helper.c
@@ -0,0 +1,281 @@
+/*
+ * crypto_helper.c - emulate v8 Crypto Extensions instructions
+ *
+ * Copyright (C) 2013 Linaro Ltd <address@hidden>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ */
+
+#include <stdlib.h>
+
+#include "cpu.h"
+#include "exec/exec-all.h"
+#include "helper.h"
+
+union AES_STATE {
+ uint8_t bytes[16];
+ uint32_t cols[4];
+ uint64_t l[2];
+};
+
+void HELPER(crypto_aese)(CPUARMState *env, uint32_t rd, uint32_t rm,
+ uint32_t decrypt)
+{
+ static uint8_t const sbox[][256] = { {
+ /* S-box for encryption */
+ 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5,
+ 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
+ 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0,
+ 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
+ 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc,
+ 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
+ 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a,
+ 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
+ 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0,
+ 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
+ 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b,
+ 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
+ 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85,
+ 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
+ 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5,
+ 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
+ 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17,
+ 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
+ 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88,
+ 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
+ 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c,
+ 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
+ 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9,
+ 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
+ 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6,
+ 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
+ 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e,
+ 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
+ 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94,
+ 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
+ 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68,
+ 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+ }, {
+ /* S-box for decryption */
+ 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38,
+ 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
+ 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87,
+ 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
+ 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d,
+ 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
+ 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2,
+ 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
+ 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16,
+ 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
+ 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda,
+ 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
+ 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a,
+ 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
+ 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02,
+ 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
+ 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea,
+ 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
+ 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85,
+ 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
+ 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89,
+ 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
+ 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20,
+ 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
+ 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31,
+ 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
+ 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d,
+ 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
+ 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0,
+ 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
+ 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26,
+ 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+ } };
+ static uint8_t const shift[][16] = {
+ /* ShiftRows permutation vector for encryption */
+ { 0, 5, 10, 15, 4, 9, 14, 3, 8, 13, 2, 7, 12, 1, 6, 11 },
+ /* 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 = {
+ float64_val(env->vfp.regs[rm]),
+ float64_val(env->vfp.regs[rm + 1])
+ } };
+ union AES_STATE st = { .l = {
+ float64_val(env->vfp.regs[rd]),
+ float64_val(env->vfp.regs[rd + 1])
+ } };
+ int i;
+
+ assert(decrypt < 2);
+
+ /* xor state vector with round key */
+ rk.l[0] ^= st.l[0];
+ rk.l[1] ^= st.l[1];
+
+ /* combine ShiftRows operation and sbox substitution */
+ for (i = 0; i < 16; i++) {
+ st.bytes[i] = sbox[decrypt][rk.bytes[shift[decrypt][i]]];
+ }
+
+ env->vfp.regs[rd] = make_float64(st.l[0]);
+ env->vfp.regs[rd + 1] = make_float64(st.l[1]);
+}
+
+void HELPER(crypto_aesmc)(CPUARMState *env, uint32_t rd, uint32_t rm,
+ uint32_t decrypt)
+{
+ static uint32_t const mc[][256] = { {
+ /* MixColumns lookup table */
+ 0x00000000, 0x03010102, 0x06020204, 0x05030306,
+ 0x0c040408, 0x0f05050a, 0x0a06060c, 0x0907070e,
+ 0x18080810, 0x1b090912, 0x1e0a0a14, 0x1d0b0b16,
+ 0x140c0c18, 0x170d0d1a, 0x120e0e1c, 0x110f0f1e,
+ 0x30101020, 0x33111122, 0x36121224, 0x35131326,
+ 0x3c141428, 0x3f15152a, 0x3a16162c, 0x3917172e,
+ 0x28181830, 0x2b191932, 0x2e1a1a34, 0x2d1b1b36,
+ 0x241c1c38, 0x271d1d3a, 0x221e1e3c, 0x211f1f3e,
+ 0x60202040, 0x63212142, 0x66222244, 0x65232346,
+ 0x6c242448, 0x6f25254a, 0x6a26264c, 0x6927274e,
+ 0x78282850, 0x7b292952, 0x7e2a2a54, 0x7d2b2b56,
+ 0x742c2c58, 0x772d2d5a, 0x722e2e5c, 0x712f2f5e,
+ 0x50303060, 0x53313162, 0x56323264, 0x55333366,
+ 0x5c343468, 0x5f35356a, 0x5a36366c, 0x5937376e,
+ 0x48383870, 0x4b393972, 0x4e3a3a74, 0x4d3b3b76,
+ 0x443c3c78, 0x473d3d7a, 0x423e3e7c, 0x413f3f7e,
+ 0xc0404080, 0xc3414182, 0xc6424284, 0xc5434386,
+ 0xcc444488, 0xcf45458a, 0xca46468c, 0xc947478e,
+ 0xd8484890, 0xdb494992, 0xde4a4a94, 0xdd4b4b96,
+ 0xd44c4c98, 0xd74d4d9a, 0xd24e4e9c, 0xd14f4f9e,
+ 0xf05050a0, 0xf35151a2, 0xf65252a4, 0xf55353a6,
+ 0xfc5454a8, 0xff5555aa, 0xfa5656ac, 0xf95757ae,
+ 0xe85858b0, 0xeb5959b2, 0xee5a5ab4, 0xed5b5bb6,
+ 0xe45c5cb8, 0xe75d5dba, 0xe25e5ebc, 0xe15f5fbe,
+ 0xa06060c0, 0xa36161c2, 0xa66262c4, 0xa56363c6,
+ 0xac6464c8, 0xaf6565ca, 0xaa6666cc, 0xa96767ce,
+ 0xb86868d0, 0xbb6969d2, 0xbe6a6ad4, 0xbd6b6bd6,
+ 0xb46c6cd8, 0xb76d6dda, 0xb26e6edc, 0xb16f6fde,
+ 0x907070e0, 0x937171e2, 0x967272e4, 0x957373e6,
+ 0x9c7474e8, 0x9f7575ea, 0x9a7676ec, 0x997777ee,
+ 0x887878f0, 0x8b7979f2, 0x8e7a7af4, 0x8d7b7bf6,
+ 0x847c7cf8, 0x877d7dfa, 0x827e7efc, 0x817f7ffe,
+ 0x9b80801b, 0x98818119, 0x9d82821f, 0x9e83831d,
+ 0x97848413, 0x94858511, 0x91868617, 0x92878715,
+ 0x8388880b, 0x80898909, 0x858a8a0f, 0x868b8b0d,
+ 0x8f8c8c03, 0x8c8d8d01, 0x898e8e07, 0x8a8f8f05,
+ 0xab90903b, 0xa8919139, 0xad92923f, 0xae93933d,
+ 0xa7949433, 0xa4959531, 0xa1969637, 0xa2979735,
+ 0xb398982b, 0xb0999929, 0xb59a9a2f, 0xb69b9b2d,
+ 0xbf9c9c23, 0xbc9d9d21, 0xb99e9e27, 0xba9f9f25,
+ 0xfba0a05b, 0xf8a1a159, 0xfda2a25f, 0xfea3a35d,
+ 0xf7a4a453, 0xf4a5a551, 0xf1a6a657, 0xf2a7a755,
+ 0xe3a8a84b, 0xe0a9a949, 0xe5aaaa4f, 0xe6abab4d,
+ 0xefacac43, 0xecadad41, 0xe9aeae47, 0xeaafaf45,
+ 0xcbb0b07b, 0xc8b1b179, 0xcdb2b27f, 0xceb3b37d,
+ 0xc7b4b473, 0xc4b5b571, 0xc1b6b677, 0xc2b7b775,
+ 0xd3b8b86b, 0xd0b9b969, 0xd5baba6f, 0xd6bbbb6d,
+ 0xdfbcbc63, 0xdcbdbd61, 0xd9bebe67, 0xdabfbf65,
+ 0x5bc0c09b, 0x58c1c199, 0x5dc2c29f, 0x5ec3c39d,
+ 0x57c4c493, 0x54c5c591, 0x51c6c697, 0x52c7c795,
+ 0x43c8c88b, 0x40c9c989, 0x45caca8f, 0x46cbcb8d,
+ 0x4fcccc83, 0x4ccdcd81, 0x49cece87, 0x4acfcf85,
+ 0x6bd0d0bb, 0x68d1d1b9, 0x6dd2d2bf, 0x6ed3d3bd,
+ 0x67d4d4b3, 0x64d5d5b1, 0x61d6d6b7, 0x62d7d7b5,
+ 0x73d8d8ab, 0x70d9d9a9, 0x75dadaaf, 0x76dbdbad,
+ 0x7fdcdca3, 0x7cdddda1, 0x79dedea7, 0x7adfdfa5,
+ 0x3be0e0db, 0x38e1e1d9, 0x3de2e2df, 0x3ee3e3dd,
+ 0x37e4e4d3, 0x34e5e5d1, 0x31e6e6d7, 0x32e7e7d5,
+ 0x23e8e8cb, 0x20e9e9c9, 0x25eaeacf, 0x26ebebcd,
+ 0x2fececc3, 0x2cededc1, 0x29eeeec7, 0x2aefefc5,
+ 0x0bf0f0fb, 0x08f1f1f9, 0x0df2f2ff, 0x0ef3f3fd,
+ 0x07f4f4f3, 0x04f5f5f1, 0x01f6f6f7, 0x02f7f7f5,
+ 0x13f8f8eb, 0x10f9f9e9, 0x15fafaef, 0x16fbfbed,
+ 0x1ffcfce3, 0x1cfdfde1, 0x19fefee7, 0x1affffe5,
+ }, {
+ /* Inverse MixColumns lookup table */
+ 0x00000000, 0x0b0d090e, 0x161a121c, 0x1d171b12,
+ 0x2c342438, 0x27392d36, 0x3a2e3624, 0x31233f2a,
+ 0x58684870, 0x5365417e, 0x4e725a6c, 0x457f5362,
+ 0x745c6c48, 0x7f516546, 0x62467e54, 0x694b775a,
+ 0xb0d090e0, 0xbbdd99ee, 0xa6ca82fc, 0xadc78bf2,
+ 0x9ce4b4d8, 0x97e9bdd6, 0x8afea6c4, 0x81f3afca,
+ 0xe8b8d890, 0xe3b5d19e, 0xfea2ca8c, 0xf5afc382,
+ 0xc48cfca8, 0xcf81f5a6, 0xd296eeb4, 0xd99be7ba,
+ 0x7bbb3bdb, 0x70b632d5, 0x6da129c7, 0x66ac20c9,
+ 0x578f1fe3, 0x5c8216ed, 0x41950dff, 0x4a9804f1,
+ 0x23d373ab, 0x28de7aa5, 0x35c961b7, 0x3ec468b9,
+ 0x0fe75793, 0x04ea5e9d, 0x19fd458f, 0x12f04c81,
+ 0xcb6bab3b, 0xc066a235, 0xdd71b927, 0xd67cb029,
+ 0xe75f8f03, 0xec52860d, 0xf1459d1f, 0xfa489411,
+ 0x9303e34b, 0x980eea45, 0x8519f157, 0x8e14f859,
+ 0xbf37c773, 0xb43ace7d, 0xa92dd56f, 0xa220dc61,
+ 0xf66d76ad, 0xfd607fa3, 0xe07764b1, 0xeb7a6dbf,
+ 0xda595295, 0xd1545b9b, 0xcc434089, 0xc74e4987,
+ 0xae053edd, 0xa50837d3, 0xb81f2cc1, 0xb31225cf,
+ 0x82311ae5, 0x893c13eb, 0x942b08f9, 0x9f2601f7,
+ 0x46bde64d, 0x4db0ef43, 0x50a7f451, 0x5baafd5f,
+ 0x6a89c275, 0x6184cb7b, 0x7c93d069, 0x779ed967,
+ 0x1ed5ae3d, 0x15d8a733, 0x08cfbc21, 0x03c2b52f,
+ 0x32e18a05, 0x39ec830b, 0x24fb9819, 0x2ff69117,
+ 0x8dd64d76, 0x86db4478, 0x9bcc5f6a, 0x90c15664,
+ 0xa1e2694e, 0xaaef6040, 0xb7f87b52, 0xbcf5725c,
+ 0xd5be0506, 0xdeb30c08, 0xc3a4171a, 0xc8a91e14,
+ 0xf98a213e, 0xf2872830, 0xef903322, 0xe49d3a2c,
+ 0x3d06dd96, 0x360bd498, 0x2b1ccf8a, 0x2011c684,
+ 0x1132f9ae, 0x1a3ff0a0, 0x0728ebb2, 0x0c25e2bc,
+ 0x656e95e6, 0x6e639ce8, 0x737487fa, 0x78798ef4,
+ 0x495ab1de, 0x4257b8d0, 0x5f40a3c2, 0x544daacc,
+ 0xf7daec41, 0xfcd7e54f, 0xe1c0fe5d, 0xeacdf753,
+ 0xdbeec879, 0xd0e3c177, 0xcdf4da65, 0xc6f9d36b,
+ 0xafb2a431, 0xa4bfad3f, 0xb9a8b62d, 0xb2a5bf23,
+ 0x83868009, 0x888b8907, 0x959c9215, 0x9e919b1b,
+ 0x470a7ca1, 0x4c0775af, 0x51106ebd, 0x5a1d67b3,
+ 0x6b3e5899, 0x60335197, 0x7d244a85, 0x7629438b,
+ 0x1f6234d1, 0x146f3ddf, 0x097826cd, 0x02752fc3,
+ 0x335610e9, 0x385b19e7, 0x254c02f5, 0x2e410bfb,
+ 0x8c61d79a, 0x876cde94, 0x9a7bc586, 0x9176cc88,
+ 0xa055f3a2, 0xab58faac, 0xb64fe1be, 0xbd42e8b0,
+ 0xd4099fea, 0xdf0496e4, 0xc2138df6, 0xc91e84f8,
+ 0xf83dbbd2, 0xf330b2dc, 0xee27a9ce, 0xe52aa0c0,
+ 0x3cb1477a, 0x37bc4e74, 0x2aab5566, 0x21a65c68,
+ 0x10856342, 0x1b886a4c, 0x069f715e, 0x0d927850,
+ 0x64d90f0a, 0x6fd40604, 0x72c31d16, 0x79ce1418,
+ 0x48ed2b32, 0x43e0223c, 0x5ef7392e, 0x55fa3020,
+ 0x01b79aec, 0x0aba93e2, 0x17ad88f0, 0x1ca081fe,
+ 0x2d83bed4, 0x268eb7da, 0x3b99acc8, 0x3094a5c6,
+ 0x59dfd29c, 0x52d2db92, 0x4fc5c080, 0x44c8c98e,
+ 0x75ebf6a4, 0x7ee6ffaa, 0x63f1e4b8, 0x68fcedb6,
+ 0xb1670a0c, 0xba6a0302, 0xa77d1810, 0xac70111e,
+ 0x9d532e34, 0x965e273a, 0x8b493c28, 0x80443526,
+ 0xe90f427c, 0xe2024b72, 0xff155060, 0xf418596e,
+ 0xc53b6644, 0xce366f4a, 0xd3217458, 0xd82c7d56,
+ 0x7a0ca137, 0x7101a839, 0x6c16b32b, 0x671bba25,
+ 0x5638850f, 0x5d358c01, 0x40229713, 0x4b2f9e1d,
+ 0x2264e947, 0x2969e049, 0x347efb5b, 0x3f73f255,
+ 0x0e50cd7f, 0x055dc471, 0x184adf63, 0x1347d66d,
+ 0xcadc31d7, 0xc1d138d9, 0xdcc623cb, 0xd7cb2ac5,
+ 0xe6e815ef, 0xede51ce1, 0xf0f207f3, 0xfbff0efd,
+ 0x92b479a7, 0x99b970a9, 0x84ae6bbb, 0x8fa362b5,
+ 0xbe805d9f, 0xb58d5491, 0xa89a4f83, 0xa397468d,
+ } };
+ union AES_STATE st = { .l = {
+ float64_val(env->vfp.regs[rm]),
+ float64_val(env->vfp.regs[rm + 1])
+ } };
+ int i;
+
+ assert(decrypt < 2);
+
+ for (i = 0; i < 16; i += 4) {
+ st.cols[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) ^
+ rol32(mc[decrypt][st.bytes[i + 3]], 24));
+ }
+
+ env->vfp.regs[rd] = make_float64(st.l[0]);
+ env->vfp.regs[rd + 1] = make_float64(st.l[1]);
+}
diff --git a/target-arm/helper.h b/target-arm/helper.h
index cac9564..dd1543f 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -458,4 +458,7 @@ DEF_HELPER_3(neon_qzip8, void, env, i32, i32)
DEF_HELPER_3(neon_qzip16, void, env, i32, i32)
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)
+
#include "exec/def-helper.h"
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 5f003e7..265f178 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4407,6 +4407,8 @@ static const uint8_t neon_3r_sizes[] = {
#define NEON_2RM_VREV16 2
#define NEON_2RM_VPADDL 4
#define NEON_2RM_VPADDL_U 5
+#define NEON_2RM_AESE 6 /* Includes AESD */
+#define NEON_2RM_AESMC 7 /* Includes AESIMC */
#define NEON_2RM_VCLS 8
#define NEON_2RM_VCLZ 9
#define NEON_2RM_VCNT 10
@@ -4464,6 +4466,8 @@ static const uint8_t neon_2rm_sizes[] = {
[NEON_2RM_VREV16] = 0x1,
[NEON_2RM_VPADDL] = 0x7,
[NEON_2RM_VPADDL_U] = 0x7,
+ [NEON_2RM_AESE] = 0x1,
+ [NEON_2RM_AESMC] = 0x1,
[NEON_2RM_VCLS] = 0x7,
[NEON_2RM_VCLZ] = 0x7,
[NEON_2RM_VCNT] = 0x1,
@@ -5986,6 +5990,28 @@ 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_AESE: case NEON_2RM_AESMC:
+ if (!arm_feature(env, ARM_FEATURE_V8_AES)
+ || ((rm | rd) & 1)) {
+ return 1;
+ }
+ tmp = tcg_const_i32(rd);
+ tmp2 = tcg_const_i32(rm);
+
+ /* Bit 6 is the lowest opcode bit; it distinguishes
between
+ * encryption (AESE/AESMC) and decryption (AESD/AESIMC)
+ */
+ tmp3 = tcg_const_i32(extract32(insn, 6, 1));
+
+ if (op == NEON_2RM_AESE) {
+ gen_helper_crypto_aese(cpu_env, tmp, tmp2, tmp3);
+ } else {
+ gen_helper_crypto_aesmc(cpu_env, tmp, tmp2, tmp3);
+ }
+ tcg_temp_free_i32(tmp);
+ tcg_temp_free_i32(tmp2);
+ tcg_temp_free_i32(tmp3);
+ break;
default:
elementwise:
for (pass = 0; pass < (q ? 4 : 2); pass++) {
--
1.8.3.2
- [Qemu-devel] [PATCH v2] target-arm: add support for v8 AES instructions,
Ard Biesheuvel <=