arch-arm: AArch32 Crypto AES

This patch implements the AArch32 AES instructions
from the Crypto extension.

Change-Id: I51e6deda748b0c26135bcfe9d0c7128f3af91f3d
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Matt Horsnell <matt.horsnell@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13248
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>

diff --git a/src/arch/arm/insts/crypto.cc b/src/arch/arm/insts/crypto.cc
index e5a4612bc4f76a80dd8707825b96c27c7b34e382..76f803c19f79a6485e580e686f6a6614d3bea4df 100644 (file)
--- a/src/arch/arm/insts/crypto.cc
+++ b/src/arch/arm/insts/crypto.cc
@@ -46,6 +46,234 @@
 
 namespace ArmISA {
 
+const uint8_t
+Crypto::aesSBOX[256] = {
+    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
+};
+
+const uint8_t
+Crypto::aesInvSBOX[256] = {
+    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
+};
+
+const uint8_t
+Crypto::aesFFLOG[256] = {
+    0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68,
+    0x33, 0xee, 0xdf, 0x03, 0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef,
+    0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1, 0x7d, 0xc2, 0x1d, 0xb5,
+    0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
+    0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45,
+    0x35, 0x93, 0xda, 0x8e, 0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94,
+    0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38, 0x66, 0xdd, 0xfd, 0x30,
+    0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
+    0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54,
+    0xfa, 0x85, 0x3d, 0xba, 0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca,
+    0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57, 0xaf, 0x58, 0xa8, 0x50,
+    0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
+    0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0,
+    0x9c, 0xa9, 0x51, 0xa0, 0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec,
+    0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7, 0xcc, 0xbb, 0x3e, 0x5a,
+    0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
+    0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd,
+    0x37, 0x3f, 0x5b, 0xd1, 0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47,
+    0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab, 0x44, 0x11, 0x92, 0xd9,
+    0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
+    0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80,
+    0xc0, 0xf7, 0x70, 0x07
+};
+
+const uint8_t
+Crypto::aesFFEXP[256] = {
+    0x01, 0x03, 0x05, 0x0f, 0x11, 0x33, 0x55, 0xff, 0x1a, 0x2e, 0x72, 0x96,
+    0xa1, 0xf8, 0x13, 0x35, 0x5f, 0xe1, 0x38, 0x48, 0xd8, 0x73, 0x95, 0xa4,
+    0xf7, 0x02, 0x06, 0x0a, 0x1e, 0x22, 0x66, 0xaa, 0xe5, 0x34, 0x5c, 0xe4,
+    0x37, 0x59, 0xeb, 0x26, 0x6a, 0xbe, 0xd9, 0x70, 0x90, 0xab, 0xe6, 0x31,
+    0x53, 0xf5, 0x04, 0x0c, 0x14, 0x3c, 0x44, 0xcc, 0x4f, 0xd1, 0x68, 0xb8,
+    0xd3, 0x6e, 0xb2, 0xcd, 0x4c, 0xd4, 0x67, 0xa9, 0xe0, 0x3b, 0x4d, 0xd7,
+    0x62, 0xa6, 0xf1, 0x08, 0x18, 0x28, 0x78, 0x88, 0x83, 0x9e, 0xb9, 0xd0,
+    0x6b, 0xbd, 0xdc, 0x7f, 0x81, 0x98, 0xb3, 0xce, 0x49, 0xdb, 0x76, 0x9a,
+    0xb5, 0xc4, 0x57, 0xf9, 0x10, 0x30, 0x50, 0xf0, 0x0b, 0x1d, 0x27, 0x69,
+    0xbb, 0xd6, 0x61, 0xa3, 0xfe, 0x19, 0x2b, 0x7d, 0x87, 0x92, 0xad, 0xec,
+    0x2f, 0x71, 0x93, 0xae, 0xe9, 0x20, 0x60, 0xa0, 0xfb, 0x16, 0x3a, 0x4e,
+    0xd2, 0x6d, 0xb7, 0xc2, 0x5d, 0xe7, 0x32, 0x56, 0xfa, 0x15, 0x3f, 0x41,
+    0xc3, 0x5e, 0xe2, 0x3d, 0x47, 0xc9, 0x40, 0xc0, 0x5b, 0xed, 0x2c, 0x74,
+    0x9c, 0xbf, 0xda, 0x75, 0x9f, 0xba, 0xd5, 0x64, 0xac, 0xef, 0x2a, 0x7e,
+    0x82, 0x9d, 0xbc, 0xdf, 0x7a, 0x8e, 0x89, 0x80, 0x9b, 0xb6, 0xc1, 0x58,
+    0xe8, 0x23, 0x65, 0xaf, 0xea, 0x25, 0x6f, 0xb1, 0xc8, 0x43, 0xc5, 0x54,
+    0xfc, 0x1f, 0x21, 0x63, 0xa5, 0xf4, 0x07, 0x09, 0x1b, 0x2d, 0x77, 0x99,
+    0xb0, 0xcb, 0x46, 0xca, 0x45, 0xcf, 0x4a, 0xde, 0x79, 0x8b, 0x86, 0x91,
+    0xa8, 0xe3, 0x3e, 0x42, 0xc6, 0x51, 0xf3, 0x0e, 0x12, 0x36, 0x5a, 0xee,
+    0x29, 0x7b, 0x8d, 0x8c, 0x8f, 0x8a, 0x85, 0x94, 0xa7, 0xf2, 0x0d, 0x17,
+    0x39, 0x4b, 0xdd, 0x7c, 0x84, 0x97, 0xa2, 0xfd, 0x1c, 0x24, 0x6c, 0xb4,
+    0xc7, 0x52, 0xf6, 0x01
+};
+
+const uint8_t
+Crypto::aesSHIFT[16] = {
+    0, 5, 10, 15, 4, 9, 14, 3,
+    8, 13, 2, 7, 12, 1, 6, 11
+};
+
+const uint8_t
+Crypto::aesINVSHIFT[16] = {
+    0, 13, 10, 7, 4, 1, 14, 11,
+    8, 5, 2, 15, 12, 9, 6, 3
+};
+
+uint8_t
+Crypto::aesFFMul(uint8_t a, uint8_t b)
+{
+    unsigned int log_prod;
+
+    if ((a ==0)|| (b == 0)) return 0;
+
+    log_prod = (aesFFLOG[a] + aesFFLOG[b]);
+
+    if(log_prod > 0xff)
+        log_prod = log_prod - 0xff;
+
+    return aesFFEXP[log_prod];
+}
+
+void
+Crypto::aesSubBytes(uint8_t *output, uint8_t *input)
+{
+    for (int i = 0; i < 16; ++i) {
+        output[i] = aesSBOX[input[i]];
+    }
+}
+
+void
+Crypto::aesInvSubBytes(uint8_t *output, uint8_t *input)
+{
+    for (int i = 0; i < 16; ++i) {
+        output[i] = aesInvSBOX[input[i]];
+    }
+}
+
+void
+Crypto::aesShiftRows(uint8_t *output, uint8_t *input)
+{
+    for (int i = 0; i < 16; ++i) {
+        output[i] = input[aesSHIFT[i]];
+    }
+}
+
+void
+Crypto::aesInvShiftRows(uint8_t *output, uint8_t *input)
+{
+    for (int i = 0; i < 16; ++i) {
+        output[i] = input[aesINVSHIFT[i]];
+    }
+}
+
+void
+Crypto::aesAddRoundKey(uint8_t *output, uint8_t *input,
+                    uint8_t *key)
+{
+    for (int i = 0; i < 16; ++i) {
+        output[i] = input[i] ^ key[i];
+    }
+}
+
+void
+Crypto::aesMixColumns(uint8_t *output, uint8_t *input)
+{
+    for (int j = 0; j < 4; ++j) {
+        int row0 = (j * 4);
+        int row1 = row0 + 1;
+        int row2 = row0 + 2;
+        int row3 = row0 + 3;
+        uint8_t t1 = input[row0] ^ input[row1] ^
+                           input[row2] ^ input[row3];
+
+        output[row1] = input[row1] ^ t1 ^ aesFFMul2(input[row1] ^ input[row2]);
+        output[row2] = input[row2] ^ t1 ^ aesFFMul2(input[row2] ^ input[row3]);
+        output[row3] = input[row3] ^ t1 ^ aesFFMul2(input[row3] ^ input[row0]);
+        output[row0] = input[row0] ^ t1 ^ aesFFMul2(input[row0] ^ input[row1]);
+    }
+}
+
+void
+Crypto::aesInvMixColumns(uint8_t *output, uint8_t *input)
+{
+    for (int j = 0; j < 4; ++j) {
+        for (int i = 0; i < 4; ++i) {
+            int index0 = (j * 4) + i;
+            int index1 = (j * 4) + ((i + 1) % 4);
+            int index2 = (j * 4) + ((i + 2) % 4);
+            int index3 = (j * 4) + ((i + 3) % 4);
+            output [index0] =
+                aesFFMul(0x0e, input[index0]) ^ aesFFMul(0x0b, input[index1]) ^
+                aesFFMul(0x0d, input[index2]) ^ aesFFMul(0x09, input[index3]);
+            }
+    }
+}
+
+void
+Crypto::aesEncrypt(uint8_t *output, uint8_t *input,
+                    uint8_t *key)
+{
+    uint8_t temp1[16];
+    uint8_t temp2[16];
+    aesAddRoundKey(&temp1[0], input, key);
+    aesShiftRows(&temp2[0], &temp1[0]);
+    aesSubBytes(output, &temp2[0]);
+}
+
+void
+Crypto::aesDecrypt(uint8_t *output, uint8_t *input,
+                    uint8_t *key)
+{
+    uint8_t temp1[16];
+    uint8_t temp2[16];
+    aesAddRoundKey(&temp1[0], input, key);
+    aesInvShiftRows(&temp2[0], &temp1[0]);
+    aesInvSubBytes(output, &temp2[0]);
+}
+
 void
 Crypto::sha256Op(
     uint32_t *X,

diff --git a/src/arch/arm/insts/crypto.hh b/src/arch/arm/insts/crypto.hh
index c89ace04a786c5a55840a4e3cf9f81f921e1ed66..021c519cdd9202b0b9d06d1af82fe979c2125d87 100644 (file)
--- a/src/arch/arm/insts/crypto.hh
+++ b/src/arch/arm/insts/crypto.hh
@@ -52,6 +52,41 @@ class Crypto
         MAJORITY
     };
 
+    /** Look up table for subByttes transformation */
+    static const uint8_t aesSBOX[256];
+
+    /** Look up table for inverse subBytes transformation */
+    static const uint8_t aesInvSBOX[256];
+
+    static const uint8_t aesSHIFT[16];
+    static const uint8_t aesINVSHIFT[16];
+
+    /**
+     * Look up table for Finite Field logarithm where the base
+     * is the element {03} in the field G(256)
+     */
+    static const uint8_t aesFFLOG[256];
+
+    /**
+     * Look up table for {03}^X where {03} and X are elements
+     * in the filed G(256)
+     */
+    static const uint8_t aesFFEXP[256];
+
+    /** Finite field multiplication of two elements in the field G(256) */
+    uint8_t aesFFMul(uint8_t a, uint8_t b);
+
+    uint8_t aesFFMul2(uint8_t a)
+    {
+        return ((a & 0x80) ? ((a << 1) ^ 0x1b) : (a << 1));
+    }
+
+    void aesSubBytes(uint8_t *output, uint8_t *input);
+    void aesInvSubBytes(uint8_t *output, uint8_t *input);
+    void aesShiftRows(uint8_t *output, uint8_t *input);
+    void aesInvShiftRows(uint8_t *output, uint8_t *input);
+    void aesAddRoundKey(uint8_t *output, uint8_t *input, uint8_t *key);
+
     uint32_t ror(uint32_t x, uint8_t shift)
     {
         return (x >> shift) | (x << (32 - shift));
@@ -92,6 +127,10 @@ class Crypto
     void store1Reg(uint8_t *output, uint32_t *X);
 
   public:
+    void aesMixColumns(uint8_t *output, uint8_t *input);
+    void aesInvMixColumns(uint8_t *output, uint8_t *input);
+    void aesEncrypt(uint8_t *output, uint8_t *input, uint8_t *key);
+    void aesDecrypt(uint8_t *output, uint8_t *input, uint8_t *key);
     void sha256H(uint8_t *output, uint8_t *input, uint8_t *input2);
     void sha256H2(uint8_t *output, uint8_t *input, uint8_t *input2);
     void sha256Su0(uint8_t *output, uint8_t *input);

diff --git a/src/arch/arm/isa/formats/fp.isa b/src/arch/arm/isa/formats/fp.isa
index 26abc659f27761b7766f44db40f048239eaa0762..77a33e6fe33f870368e06e80085126f8d55997eb 100644 (file)
--- a/src/arch/arm/isa/formats/fp.isa
+++ b/src/arch/arm/isa/formats/fp.isa
@@ -1476,6 +1476,18 @@ let {{
               case 0x5:
                 return decodeNeonUTwoMiscSReg<NVpaddlD, NVpaddlQ>(
                         q, size, machInst, vd, vm);
+              case 0x6:
+                if (q == 0) {
+                    return new AESE(machInst, vd, vd, vm);
+                } else {
+                    return new AESD(machInst, vd, vd, vm);
+                }
+              case 0x7:
+                if (q == 0) {
+                    return new AESMC(machInst, vd, vm);
+                } else {
+                    return new AESIMC(machInst, vd, vm);
+                }
               case 0x8:
                 return decodeNeonSTwoMiscReg<NVclsD, NVclsQ>(
                         q, size, machInst, vd, vm);

diff --git a/src/arch/arm/isa/insts/crypto.isa b/src/arch/arm/isa/insts/crypto.isa
index cdc0293a4f1fbfa1f65418636e8fa6275e202780..20ba4c486af212efbe17361c7b5ed347f3dc5013 100644 (file)
--- a/src/arch/arm/isa/insts/crypto.isa
+++ b/src/arch/arm/isa/insts/crypto.isa
@@ -136,6 +136,11 @@ let {{
         decoder_output += RegRegImmOpConstructor.subst(cryptoiop)
         exec_output += CryptoPredOpExecute.subst(cryptoiop)
 
+    aeseCode = "crypto.aesEncrypt(output, input, input2);"
+    aesdCode = "crypto.aesDecrypt(output, input, input2);"
+    aesmcCode = "crypto.aesMixColumns(output, input);"
+    aesimcCode = "crypto.aesInvMixColumns(output, input);"
+
     sha1_cCode = "crypto.sha1C(output, input, input2);"
     sha1_pCode = "crypto.sha1P(output, input, input2);"
     sha1_mCode = "crypto.sha1M(output, input, input2);"
@@ -148,6 +153,16 @@ let {{
     sha256_su0Code = "crypto.sha256Su0(output, input);"
     sha256_su1Code = "crypto.sha256Su1(output, input, input2);"
 
+    aes_enabled = cryptoEnabledCheckCode % { "mask" : 0xF0 }
+    cryptoRegRegRegInst("aese", "AESE", "SimdAesOp",
+                        aes_enabled, aeseCode)
+    cryptoRegRegRegInst("aesd", "AESD", "SimdAesOp",
+                        aes_enabled, aesdCode)
+    cryptoRegRegInst("aesmc", "AESMC", "SimdAesMixOp",
+                     aes_enabled, aesmcCode)
+    cryptoRegRegInst("aesimc", "AESIMC", "SimdAesMixOp",
+                     aes_enabled, aesimcCode)
+
     sha1_enabled = cryptoEnabledCheckCode % { "mask" : 0xF00 }
     cryptoRegRegRegInst("sha1c", "SHA1C", "SimdSha1HashOp",
                         sha1_enabled, sha1_cCode)

diff --git a/src/cpu/FuncUnit.py b/src/cpu/FuncUnit.py
index e985a648a7e441cd96ffa60d61242bd05167bab7..a408de3ab6650c830813d036dd76f4ffede89575 100644 (file)
--- a/src/cpu/FuncUnit.py
+++ b/src/cpu/FuncUnit.py
@@ -50,9 +50,10 @@ class OpClass(Enum):
             'SimdSqrt', 'SimdFloatAdd', 'SimdFloatAlu', 'SimdFloatCmp',
             'SimdFloatCvt', 'SimdFloatDiv', 'SimdFloatMisc', 'SimdFloatMult',
             'SimdFloatMultAcc', 'SimdFloatSqrt',
-            'SimdSha1Hash', 'SimdSha1Hash2', 'SimdSha256Hash',
-            'SimdSha256Hash2', 'SimdShaSigma2', 'SimdShaSigma3',
-            'MemRead', 'MemWrite', 'FloatMemRead', 'FloatMemWrite',
+            'SimdAes', 'SimdAesMix', 'SimdSha1Hash', 'SimdSha1Hash2',
+            'SimdSha256Hash', 'SimdSha256Hash2', 'SimdShaSigma2',
+            'SimdShaSigma3', 'MemRead', 'MemWrite',
+            'FloatMemRead', 'FloatMemWrite',
             'IprAccess', 'InstPrefetch']
 
 class OpDesc(SimObject):

diff --git a/src/cpu/op_class.hh b/src/cpu/op_class.hh
index a4cadb96e927e7dae8921f0815ee8620b386ff3d..1bb88e1cd584324a9c2c92ca910aede84cec56f2 100644 (file)
--- a/src/cpu/op_class.hh
+++ b/src/cpu/op_class.hh
@@ -83,6 +83,8 @@ static const OpClass SimdFloatMiscOp = Enums::SimdFloatMisc;
 static const OpClass SimdFloatMultOp = Enums::SimdFloatMult;
 static const OpClass SimdFloatMultAccOp = Enums::SimdFloatMultAcc;
 static const OpClass SimdFloatSqrtOp = Enums::SimdFloatSqrt;
+static const OpClass SimdAesOp = Enums::SimdAes;
+static const OpClass SimdAesMixOp = Enums::SimdAesMix;
 static const OpClass SimdSha1HashOp = Enums::SimdSha1Hash;
 static const OpClass SimdSha1Hash2Op = Enums::SimdSha1Hash2;
 static const OpClass SimdSha256HashOp = Enums::SimdSha256Hash;