Added AES-NI cpu extension support ([DYNAREC] too, using AES extension if available)

1 files changed, 187 insertions, 0 deletions

diff --git a/src/emu/x64run660f.c b/src/emu/x64run660f.c
index 5eee4f56..2c6a364c 100644
--- a/src/emu/x64run660f.c
+++ b/src/emu/x64run660f.c
@@ -22,6 +22,27 @@
 

 #include "modrm.h"

 

+static uint8_t ff_mult(uint8_t a, uint8_t b)

+{

+	int retval = 0;

+

+	for(int i = 0; i < 8; i++) {

+		if((b & 1) == 1) 

+			retval ^= a;

+		

+		if((a & 0x80)) {

+			a <<= 1;

+			a  ^= 0x1b;

+		} else {

+			a <<= 1;

+		}

+		

+		b >>= 1;

+	}

+	

+	return retval;

+}

+

 int Run660F(x64emu_t *emu, rex_t rex)

 {

     uint8_t opcode;

@@ -36,6 +57,49 @@ int Run660F(x64emu_t *emu, rex_t rex)
     reg64_t *oped, *opgd;

     sse_regs_t *opex, *opgx, eax1, *opex2;

     mmx87_regs_t *opem, *opgm;

+    // AES opcodes constants

+                            //   A0 B1 C2 D3 E4 F5 G6 H7 I8 J9 Ka Lb Mc Nd Oe Pf

+                            //   A  F  K  P  E  J  O  D  I  N  C  H  M  B  G  L

+    const uint8_t shiftrows[] = {0, 5,10,15, 4, 9,14, 3, 8,13, 2, 7,12, 1, 6,11};

+    const uint8_t subbytes[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,

+    };

+                            //   A0 B1 C2 D3 E4 F5 G6 H7 I8 J9 Ka Lb Mc Nd Oe Pf

+                            //   A  N  K  H  E  B  O  L  I  F  C  P  M  J  G  D

+    const uint8_t invshiftrows[] = {0,13,10, 7, 4, 1,14,11, 8, 5, 2,15,12, 9, 6, 3};

+    const uint8_t invsubbytes[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,

+    };

 

     opcode = F8;

 

@@ -365,6 +429,108 @@ int Run660F(x64emu_t *emu, rex_t rex)
                     GX->sq[i] = EX->sd[i];

                 break;

 

+            case 0xDB:  /* AESIMC Gx, Ex */

+                nextop = F8;

+                GETEX(0);

+                GETGX;

+                //STATE ← InvMixColumns( STATE );

+                if (EX == GX) {

+                    for(int i=0; i<16; ++i)

+                        eax1.ub[i] = EX->ub[i];

+                    for(int j=0; j<4; ++j) {

+                        GX->ub[0+j*4] = ff_mult(0x0E, eax1.ub[0+j*4]) ^ ff_mult(0x0B, eax1.ub[1+j*4]) ^ ff_mult(0x0D, eax1.ub[2+j*4]) ^ ff_mult(0x09, eax1.ub[3+j*4]);

+                        GX->ub[1+j*4] = ff_mult(0x09, eax1.ub[0+j*4]) ^ ff_mult(0x0E, eax1.ub[1+j*4]) ^ ff_mult(0x0B, eax1.ub[2+j*4]) ^ ff_mult(0x0D, eax1.ub[3+j*4]);

+                        GX->ub[2+j*4] = ff_mult(0x0D, eax1.ub[0+j*4]) ^ ff_mult(0x09, eax1.ub[1+j*4]) ^ ff_mult(0x0E, eax1.ub[2+j*4]) ^ ff_mult(0x0B, eax1.ub[3+j*4]);

+                        GX->ub[3+j*4] = ff_mult(0x0B, eax1.ub[0+j*4]) ^ ff_mult(0x0D, eax1.ub[1+j*4]) ^ ff_mult(0x09, eax1.ub[2+j*4]) ^ ff_mult(0x0E, eax1.ub[3+j*4]);

+                    }

+                } else {

+                    for(int j=0; j<4; ++j) {

+                        GX->ub[0+j*4] = ff_mult(0x0E, EX->ub[0+j*4]) ^ ff_mult(0x0B, EX->ub[1+j*4]) ^ ff_mult(0x0D, EX->ub[2+j*4]) ^ ff_mult(0x09, EX->ub[3+j*4]);

+                        GX->ub[1+j*4] = ff_mult(0x09, EX->ub[0+j*4]) ^ ff_mult(0x0E, EX->ub[1+j*4]) ^ ff_mult(0x0B, EX->ub[2+j*4]) ^ ff_mult(0x0D, EX->ub[3+j*4]);

+                        GX->ub[2+j*4] = ff_mult(0x0D, EX->ub[0+j*4]) ^ ff_mult(0x09, EX->ub[1+j*4]) ^ ff_mult(0x0E, EX->ub[2+j*4]) ^ ff_mult(0x0B, EX->ub[3+j*4]);

+                        GX->ub[3+j*4] = ff_mult(0x0B, EX->ub[0+j*4]) ^ ff_mult(0x0D, EX->ub[1+j*4]) ^ ff_mult(0x09, EX->ub[2+j*4]) ^ ff_mult(0x0E, EX->ub[3+j*4]);

+                    }

+                }

+                break;

+            case 0xDC:  /* AESENC Gx, Ex */

+                nextop = F8;

+                GETEX(0);

+                GETGX;

+                //STATE ← SRC1;

+                //RoundKey ← SRC2;

+                //STATE ← ShiftRows( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = GX->ub[shiftrows[i]];

+                //STATE ← SubBytes( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = subbytes[eax1.ub[i]];

+                //STATE ← MixColumns( STATE );

+                for(int j=0; j<4; ++j) {

+                    GX->ub[0+j*4] = ff_mult(0x02, eax1.ub[0+j*4]) ^ ff_mult(0x03, eax1.ub[1+j*4]) ^               eax1.ub[2+j*4]  ^               eax1.ub[3+j*4] ;

+                    GX->ub[1+j*4] =               eax1.ub[0+j*4]  ^ ff_mult(0x02, eax1.ub[1+j*4]) ^ ff_mult(0x03, eax1.ub[2+j*4]) ^               eax1.ub[3+j*4] ;

+                    GX->ub[2+j*4] =               eax1.ub[0+j*4]  ^               eax1.ub[1+j*4]  ^ ff_mult(0x02, eax1.ub[2+j*4]) ^ ff_mult(0x03, eax1.ub[3+j*4]);

+                    GX->ub[3+j*4] = ff_mult(0x03, eax1.ub[0+j*4]) ^               eax1.ub[1+j*4]  ^               eax1.ub[2+j*4]  ^ ff_mult(0x02, eax1.ub[3+j*4]);

+                }

+                //DEST[127:0] ← STATE XOR RoundKey;

+                GX->q[0] ^= EX->q[0];

+                GX->q[1] ^= EX->q[1];

+                break;

+            case 0xDD:  /* AESENCLAST Gx, Ex */

+                nextop = F8;

+                GETEX(0);

+                GETGX;

+                //STATE ← SRC1;

+                //RoundKey ← SRC2;

+                //STATE ← ShiftRows( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = GX->ub[shiftrows[i]];

+                //STATE ← SubBytes( STATE );

+                for(int i=0; i<16; ++i)

+                    GX->ub[i] = subbytes[eax1.ub[i]];

+                //DEST[127:0] ← STATE XOR RoundKey;

+                GX->q[0] ^= EX->q[0];

+                GX->q[1] ^= EX->q[1];

+                break;

+            case 0xDE:  /* AESDEC Gx, Ex */

+                nextop = F8;

+                GETEX(0);

+                GETGX;

+                //STATE ← SRC1;

+                //RoundKey ← SRC2;

+                //STATE ← InvShiftRows( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = GX->ub[invshiftrows[i]];

+                //STATE ← InvSubBytes( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = invsubbytes[eax1.ub[i]];

+                //STATE ← InvMixColumns( STATE );

+                for(int j=0; j<4; ++j) {

+                    GX->ub[0+j*4] = ff_mult(0x0E, eax1.ub[0+j*4]) ^ ff_mult(0x0B, eax1.ub[1+j*4]) ^ ff_mult(0x0D, eax1.ub[2+j*4]) ^ ff_mult(0x09, eax1.ub[3+j*4]);

+                    GX->ub[1+j*4] = ff_mult(0x09, eax1.ub[0+j*4]) ^ ff_mult(0x0E, eax1.ub[1+j*4]) ^ ff_mult(0x0B, eax1.ub[2+j*4]) ^ ff_mult(0x0D, eax1.ub[3+j*4]);

+                    GX->ub[2+j*4] = ff_mult(0x0D, eax1.ub[0+j*4]) ^ ff_mult(0x09, eax1.ub[1+j*4]) ^ ff_mult(0x0E, eax1.ub[2+j*4]) ^ ff_mult(0x0B, eax1.ub[3+j*4]);

+                    GX->ub[3+j*4] = ff_mult(0x0B, eax1.ub[0+j*4]) ^ ff_mult(0x0D, eax1.ub[1+j*4]) ^ ff_mult(0x09, eax1.ub[2+j*4]) ^ ff_mult(0x0E, eax1.ub[3+j*4]);

+                }

+                //DEST[127:0] ← STATE XOR RoundKey;

+                GX->q[0] ^= EX->q[0];

+                GX->q[1] ^= EX->q[1];

+                break;

+            case 0xDF:  /* AESDECLAST Gx, Ex */

+                nextop = F8;

+                GETEX(0);

+                GETGX;

+                //STATE ← SRC1;

+                //RoundKey ← SRC2;

+                //STATE ← InvShiftRows( STATE );

+                for(int i=0; i<16; ++i)

+                    eax1.ub[i] = GX->ub[invshiftrows[i]];

+                //STATE ← InvSubBytes( STATE );

+                for(int i=0; i<16; ++i)

+                    GX->ub[i] = invsubbytes[eax1.ub[i]];

+                //DEST[127:0] ← STATE XOR RoundKey;

+                GX->q[0] ^= EX->q[0];

+                GX->q[1] ^= EX->q[1];

+                break;

+

             default:

                 return 1;

         }

@@ -476,6 +642,27 @@ int Run660F(x64emu_t *emu, rex_t rex)
                         GX->ud[i] = 0;

                 break;

 

+            case 0xDF:      // AESKEYGENASSIST Gx, Ex, u8

+                nextop = F8;

+                GETEX(1);

+                GETGX;

+                tmp32u = F8;

+                for (int i = 4; i < 8; ++i)

+                    GX->ub[i] = subbytes[EX->ub[i]];

+                for (int i = 12; i < 16; ++i)

+                    GX->ub[i] = subbytes[EX->ub[i]];

+                GX->ud[0] = GX->ud[1];

+                tmp8u = GX->ub[4];

+                GX->ud[1] = GX->ud[1] >> 8;

+                GX->ub[7] = tmp8u;

+                GX->ud[1] ^= tmp32u;

+                GX->ud[2] = GX->ud[3];

+                tmp8u = GX->ub[12];

+                GX->ud[3] = GX->ud[3] >> 8;

+                GX->ub[15] = tmp8u;

+                GX->ud[3] ^= tmp32u;

+                break;

+

             default:

                 return 1;

         }