Refactor AES Instructions

index e79c707..a4044f5 100644
@@ -23,6 +23,9 @@ void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
 		     const unsigned long length, const AES_KEY *key,
 		     unsigned char *ivec, const int enc);
 
+extern const uint8_t AES_sbox[256];
+extern const uint8_t AES_isbox[256];
+
 /*
 AES_Te0[x] = S [x].[02, 01, 01, 03];
 AES_Te1[x] = S [x].[03, 02, 01, 01];

76 lines not on this page · raw message

index a4044f5..c45bc57 100644
@@ -26,6 +26,10 @@ void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
 extern const uint8_t AES_sbox[256];
 extern const uint8_t AES_isbox[256];
 
+/* AES ShiftRows and InvShiftRows */
+extern const uint8_t AES_shifts[16];
+extern const uint8_t AES_ishifts[16];
+
 /*
 AES_Te0[x] = S [x].[02, 01, 01, 03];
 AES_Te1[x] = S [x].[03, 02, 01, 01];

index eeb644b..c26cf55 100644
@@ -108,6 +108,14 @@ const uint8_t AES_isbox[256] = {
     0xE1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0C, 0x7D,
 };
 
+const uint8_t AES_shifts[16] = {
+    0, 5, 10, 15, 4, 9, 14, 3, 8, 13, 2, 7, 12, 1, 6, 11
+};
+
+const uint8_t AES_ishifts[16] = {
+    0, 13, 10, 7, 4, 1, 14, 11, 8, 5, 2, 15, 12, 9, 6, 3
+};
+
 /*
 AES_Te0[x] = S [x].[02, 01, 01, 03];
 AES_Te1[x] = S [x].[03, 02, 01, 01];

index c45bc57..c106660 100644
@@ -30,6 +30,13 @@ extern const uint8_t AES_isbox[256];
 extern const uint8_t AES_shifts[16];
 extern const uint8_t AES_ishifts[16];
 
+/* AES InvMixColumns */
+/* AES_imc[x][0] = [x].[0e, 09, 0d, 0b]; */
+/* AES_imc[x][1] = [x].[0b, 0e, 09, 0d]; */
+/* AES_imc[x][2] = [x].[0d, 0b, 0e, 09]; */
+/* AES_imc[x][3] = [x].[09, 0d, 0b, 0e]; */
+extern const uint32_t AES_imc[256][4];
+
 /*
 AES_Te0[x] = S [x].[02, 01, 01, 03];
 AES_Te1[x] = S [x].[03, 02, 01, 01];

271 lines not on this page · raw message

index eb24b5f..886e0a8 100644
@@ -17,6 +17,9 @@
  * You should have received a copy of the GNU Lesser General Public
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
+
+#include "qemu/aes.h"
+
 #if SHIFT == 0
 #define Reg MMXReg
 #define XMM_ONLY(...)

@@ -2204,15 +2207,6 @@ void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     d->Q(1) = resh;
 }
 
-/* AES-NI op helpers */
-static const uint8_t aes_shifts[16] = {
-    0, 5, 10, 15, 4, 9, 14, 3, 8, 13, 2, 7, 12, 1, 6, 11
-};
-
-static const uint8_t aes_ishifts[16] = {
-    0, 13, 10, 7, 4, 1, 14, 11, 8, 5, 2, 15, 12, 9, 6, 3
-};
-
 void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
     int i;

@@ -2220,10 +2214,10 @@ void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg rk = *s;
 
     for (i = 0 ; i < 4 ; i++) {
-        d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(aes_ishifts[4*i+0])] ^
-                                    AES_Td1[st.B(aes_ishifts[4*i+1])] ^
-                                    AES_Td2[st.B(aes_ishifts[4*i+2])] ^
-                                    AES_Td3[st.B(aes_ishifts[4*i+3])]);
+        d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4*i+0])] ^
+                                    AES_Td1[st.B(AES_ishifts[4*i+1])] ^
+                                    AES_Td2[st.B(AES_ishifts[4*i+2])] ^
+                                    AES_Td3[st.B(AES_ishifts[4*i+3])]);
     }
 }
 

@@ -2234,7 +2228,7 @@ void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg rk = *s;
 
     for (i = 0; i < 16; i++) {
-        d->B(i) = rk.B(i) ^ (AES_Td4[st.B(aes_ishifts[i])] & 0xff);
+        d->B(i) = rk.B(i) ^ (AES_Td4[st.B(AES_ishifts[i])] & 0xff);
     }
 }
 

@@ -2245,10 +2239,10 @@ void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg rk = *s;
 
     for (i = 0 ; i < 4 ; i++) {
-        d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(aes_shifts[4*i+0])] ^
-                                    AES_Te1[st.B(aes_shifts[4*i+1])] ^
-                                    AES_Te2[st.B(aes_shifts[4*i+2])] ^
-                                    AES_Te3[st.B(aes_shifts[4*i+3])]);
+        d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4*i+0])] ^
+                                    AES_Te1[st.B(AES_shifts[4*i+1])] ^
+                                    AES_Te2[st.B(AES_shifts[4*i+2])] ^
+                                    AES_Te3[st.B(AES_shifts[4*i+3])]);
     }
 }
 

@@ -2259,7 +2253,7 @@ void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg rk = *s;
 
     for (i = 0; i < 16; i++) {
-        d->B(i) = rk.B(i) ^ (AES_Te4[st.B(aes_shifts[i])] & 0xff);
+        d->B(i) = rk.B(i) ^ (AES_Te4[st.B(AES_shifts[i])] & 0xff);
     }
 
 }

index f94be69..9dc0c8e 100644
@@ -14,6 +14,7 @@
 #include "cpu.h"
 #include "exec/exec-all.h"
 #include "helper.h"
+#include "qemu/aes.h"
 
 union AES_STATE {
     uint8_t    bytes[16];

@@ -24,81 +25,9 @@ union AES_STATE {
 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 },
-    };
+    static uint8_t const *sbox[2] = { AES_sbox, AES_isbox };
+    static uint8_t const *shift[2] = { AES_shifts, AES_ishifts };
+
     union AES_STATE rk = { .l = {
         float64_val(env->vfp.regs[rm]),
         float64_val(env->vfp.regs[rm + 1])

index 582d8ac..c7d8cb6 100644
@@ -19,6 +19,7 @@
 #include "cpu.h"
 #include "qemu/host-utils.h"
 #include "helper.h"
+#include "qemu/aes.h"
 
 #include "helper_regs.h"
 /*****************************************************************************/

@@ -396,9 +397,13 @@ target_ulong helper_602_mfrom(target_ulong arg)
 #if defined(HOST_WORDS_BIGENDIAN)
 #define HI_IDX 0
 #define LO_IDX 1
+#define AVRB(i) u8[i]
+#define AVRW(i) u32[i]
 #else
 #define HI_IDX 1
 #define LO_IDX 0
+#define AVRB(i) u8[15-(i)]
+#define AVRW(i) u32[3-(i)]
 #endif
 
 #if defined(HOST_WORDS_BIGENDIAN)

@@ -2338,284 +2343,63 @@ uint32_t helper_bcdsub(ppc_avr_t *r,  ppc_avr_t *a, ppc_avr_t *b, uint32_t ps)
     return helper_bcdadd(r, a, &bcopy, ps);
 }
 
-static uint8_t SBOX[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,
-};
-
-static void SubBytes(ppc_avr_t *r, ppc_avr_t *a)
-{
-    int i;
-    VECTOR_FOR_INORDER_I(i, u8) {
-        r->u8[i] = SBOX[a->u8[i]];
-    }
-}
-
-static uint8_t InvSBOX[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,
-};
-
-static void InvSubBytes(ppc_avr_t *r, ppc_avr_t *a)
+void helper_vsbox(ppc_avr_t *r, ppc_avr_t *a)
 {
     int i;
     VECTOR_FOR_INORDER_I(i, u8) {
-        r->u8[i] = InvSBOX[a->u8[i]];
+        r->u8[i] = AES_sbox[a->u8[i]];
     }
 }
 
-static uint8_t ROTL8(uint8_t x, int n)
-{
-    return (x << n) | (x >> (8-n));
-}
-
-static inline int BIT8(uint8_t x, int n)
-{
-    return (x & (0x80 >> n)) != 0;
-}
-
-static uint8_t GFx02(uint8_t x)
-{
-    return ROTL8(x, 1) ^ (BIT8(x, 0) ? 0x1A : 0);
-}
-
-static uint8_t GFx03(uint8_t x)
-{
-    return x ^ ROTL8(x, 1) ^ (BIT8(x, 0) ? 0x1A : 0);
-}
-
-static uint8_t GFx09(uint8_t x)
-{
-    uint8_t term2 = ROTL8(x, 3);
-    uint8_t term3 = (BIT8(x, 0) ? 0x68 : 0) | (BIT8(x, 1) ? 0x14 : 0) |
-                    (BIT8(x, 2) ? 0x02 : 0);
-    uint8_t term4 = (BIT8(x, 1) ? 0x20 : 0) | (BIT8(x, 2) ? 0x18 : 0);
-    return x ^ term2 ^ term3 ^ term4;
-}
-
-static uint8_t GFx0B(uint8_t x)
-{
-    uint8_t term2 = ROTL8(x, 1);
-    uint8_t term3 = (x << 3) | (BIT8(x, 0) ? 0x06 : 0) |
-                    (BIT8(x, 2) ? 0x01 : 0);
-    uint8_t term4 = (BIT8(x, 0) ? 0x70 : 0) | (BIT8(x, 1) ? 0x06 : 0) |
-                    (BIT8(x, 2) ? 0x08 : 0);
-    uint8_t term5 = (BIT8(x, 1) ? 0x30 : 0) | (BIT8(x, 2) ? 0x02 : 0);
-    uint8_t term6 = BIT8(x, 2) ? 0x10 : 0;
-    return x ^ term2 ^ term3 ^ term4 ^ term5 ^ term6;
-}
-
-static uint8_t GFx0D(uint8_t x)
-{
-    uint8_t term2 = ROTL8(x, 2);
-    uint8_t term3 = (x << 3) | (BIT8(x, 1) ? 0x04 : 0) |
-                    (BIT8(x, 2) ? 0x03 : 0);
-    uint8_t term4 = (BIT8(x, 0) ? 0x58 : 0) | (BIT8(x, 1) ? 0x20 : 0);
-    uint8_t term5 = (BIT8(x, 1) ? 0x08 : 0) | (BIT8(x, 2) ? 0x10 : 0);
-    uint8_t term6 = BIT8(x, 2) ? 0x08 : 0;
-    return x ^ term2 ^ term3 ^ term4 ^ term5 ^ term6;
-}
-
-static uint8_t GFx0E(uint8_t x)
-{
-    uint8_t term1 = ROTL8(x, 1);
-    uint8_t term2 = (x << 2) | (BIT8(x, 2) ? 0x02 : 0) |
-                    (BIT8(x, 1) ? 0x01 : 0);
-    uint8_t term3 = (x << 3) | (BIT8(x, 1) ? 0x04 : 0) |
-                    (BIT8(x, 2) ? 0x01 : 0);
-    uint8_t term4 = (BIT8(x, 0) ? 0x40 : 0) | (BIT8(x, 1) ? 0x28 : 0) |
-                    (BIT8(x, 2) ? 0x10 : 0);
-    uint8_t term5 = (BIT8(x, 2) ? 0x08 : 0);
-    return term1 ^ term2 ^ term3 ^ term4 ^ term5;
-}
-
-#if defined(HOST_WORDS_BIGENDIAN)
-#define MCB(x, i, b) ((x)->u8[(i)*4 + (b)])
-#else
-#define MCB(x, i, b) ((x)->u8[15 - ((i)*4 + (b))])
-#endif
-
-static void MixColumns(ppc_avr_t *r, ppc_avr_t *x)
+void helper_vcipher(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
     int i;
-    for (i = 0; i < 4; i++) {
-        MCB(r, i, 0) = GFx02(MCB(x, i, 0)) ^ GFx03(MCB(x, i, 1)) ^
-                       MCB(x, i, 2) ^ MCB(x, i, 3);
-        MCB(r, i, 1) = MCB(x, i, 0) ^ GFx02(MCB(x, i, 1)) ^
-                       GFx03(MCB(x, i, 2)) ^ MCB(x, i, 3);
-        MCB(r, i, 2) = MCB(x, i, 0) ^ MCB(x, i, 1) ^
-                       GFx02(MCB(x, i, 2)) ^ GFx03(MCB(x, i, 3));
-        MCB(r, i, 3) = GFx03(MCB(x, i, 0)) ^ MCB(x, i, 1) ^
-                       MCB(x, i, 2) ^ GFx02(MCB(x, i, 3));
-    }
-}
 
-static void InvMixColumns(ppc_avr_t *r, ppc_avr_t *x)
-{
-    int i;
-    for (i = 0; i < 4; i++) {
-        MCB(r, i, 0) = GFx0E(MCB(x, i, 0)) ^ GFx0B(MCB(x, i, 1)) ^
-                       GFx0D(MCB(x, i, 2)) ^ GFx09(MCB(x, i, 3));
-        MCB(r, i, 1) = GFx09(MCB(x, i, 0)) ^ GFx0E(MCB(x, i, 1)) ^
-                       GFx0B(MCB(x, i, 2)) ^ GFx0D(MCB(x, i, 3));
-        MCB(r, i, 2) = GFx0D(MCB(x, i, 0)) ^ GFx09(MCB(x, i, 1)) ^
-                       GFx0E(MCB(x, i, 2)) ^ GFx0B(MCB(x, i, 3));
-        MCB(r, i, 3) = GFx0B(MCB(x, i, 0)) ^ GFx0D(MCB(x, i, 1)) ^
-                       GFx09(MCB(x, i, 2)) ^ GFx0E(MCB(x, i, 3));
+    VECTOR_FOR_INORDER_I(i, u32) {
+        r->AVRW(i) = b->AVRW(i) ^
+            (AES_Te0[a->AVRB(AES_shifts[4*i + 0])] ^
+             AES_Te1[a->AVRB(AES_shifts[4*i + 1])] ^
+             AES_Te2[a->AVRB(AES_shifts[4*i + 2])] ^
+             AES_Te3[a->AVRB(AES_shifts[4*i + 3])]);
     }
 }
 
-static void ShiftRows(ppc_avr_t *r, ppc_avr_t *x)
-{
-    MCB(r, 0, 0) = MCB(x, 0, 0);
-    MCB(r, 1, 0) = MCB(x, 1, 0);
-    MCB(r, 2, 0) = MCB(x, 2, 0);
-    MCB(r, 3, 0) = MCB(x, 3, 0);
-
-    MCB(r, 0, 1) = MCB(x, 1, 1);
-    MCB(r, 1, 1) = MCB(x, 2, 1);
-    MCB(r, 2, 1) = MCB(x, 3, 1);
-    MCB(r, 3, 1) = MCB(x, 0, 1);
-
-    MCB(r, 0, 2) = MCB(x, 2, 2);
-    MCB(r, 1, 2) = MCB(x, 3, 2);
-    MCB(r, 2, 2) = MCB(x, 0, 2);
-    MCB(r, 3, 2) = MCB(x, 1, 2);
-
-    MCB(r, 0, 3) = MCB(x, 3, 3);
-    MCB(r, 1, 3) = MCB(x, 0, 3);
-    MCB(r, 2, 3) = MCB(x, 1, 3);
-    MCB(r, 3, 3) = MCB(x, 2, 3);
-}
-
-static void InvShiftRows(ppc_avr_t *r, ppc_avr_t *x)
-{
-    MCB(r, 0, 0) = MCB(x, 0, 0);
-    MCB(r, 1, 0) = MCB(x, 1, 0);
-    MCB(r, 2, 0) = MCB(x, 2, 0);
-    MCB(r, 3, 0) = MCB(x, 3, 0);
-
-    MCB(r, 0, 1) = MCB(x, 3, 1);
-    MCB(r, 1, 1) = MCB(x, 0, 1);
-    MCB(r, 2, 1) = MCB(x, 1, 1);
-    MCB(r, 3, 1) = MCB(x, 2, 1);
-
-    MCB(r, 0, 2) = MCB(x, 2, 2);
-    MCB(r, 1, 2) = MCB(x, 3, 2);
-    MCB(r, 2, 2) = MCB(x, 0, 2);
-    MCB(r, 3, 2) = MCB(x, 1, 2);
-
-    MCB(r, 0, 3) = MCB(x, 1, 3);
-    MCB(r, 1, 3) = MCB(x, 2, 3);
-    MCB(r, 2, 3) = MCB(x, 3, 3);
-    MCB(r, 3, 3) = MCB(x, 0, 3);
-}
-
-#undef MCB
-
-void helper_vsbox(ppc_avr_t *r, ppc_avr_t *a)
-{
-    SubBytes(r, a);
-}
-
-void helper_vcipher(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-{
-    ppc_avr_t vtemp1, vtemp2, vtemp3;
-    SubBytes(&vtemp1, a);
-    ShiftRows(&vtemp2, &vtemp1);
-    MixColumns(&vtemp3, &vtemp2);
-    r->u64[0] = vtemp3.u64[0] ^ b->u64[0];
-    r->u64[1] = vtemp3.u64[1] ^ b->u64[1];
-}
-
 void helper_vcipherlast(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
-    ppc_avr_t vtemp1, vtemp2;
-    SubBytes(&vtemp1, a);
-    ShiftRows(&vtemp2, &vtemp1);
-    r->u64[0] = vtemp2.u64[0] ^ b->u64[0];
-    r->u64[1] = vtemp2.u64[1] ^ b->u64[1];
+    int i;
+
+    VECTOR_FOR_INORDER_I(i, u8) {
+        r->AVRB(i) = b->AVRB(i) ^ (AES_Te4[a->AVRB(AES_shifts[i])] & 0xFF);
+    }
 }
 
 void helper_vncipher(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
     /* This differs from what is written in ISA V2.07.  The RTL is */
     /* incorrect and will be fixed in V2.07B.                      */
-    ppc_avr_t vtemp1, vtemp2, vtemp3;
-    InvShiftRows(&vtemp1, a);
-    InvSubBytes(&vtemp2, &vtemp1);
-    vtemp3.u64[0] = vtemp2.u64[0] ^ b->u64[0];
-    vtemp3.u64[1] = vtemp2.u64[1] ^ b->u64[1];
-    InvMixColumns(r, &vtemp3);
+    int i;
+    ppc_avr_t tmp;
+
+    VECTOR_FOR_INORDER_I(i, u8) {
+        tmp.AVRB(i) = b->AVRB(i) ^ AES_isbox[a->AVRB(AES_ishifts[i])];
+    }
+
+    VECTOR_FOR_INORDER_I(i, u32) {
+        r->AVRW(i) =
+            AES_imc[tmp.AVRB(4*i + 0)][0] ^
+            AES_imc[tmp.AVRB(4*i + 1)][1] ^
+            AES_imc[tmp.AVRB(4*i + 2)][2] ^
+            AES_imc[tmp.AVRB(4*i + 3)][3];
+    }
 }
 
 void helper_vncipherlast(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
-    ppc_avr_t vtemp1, vtemp2;
-    InvShiftRows(&vtemp1, a);
-    InvSubBytes(&vtemp2, &vtemp1);
-    r->u64[0] = vtemp2.u64[0] ^ b->u64[0];
-    r->u64[1] = vtemp2.u64[1] ^ b->u64[1];
+    int i;
+
+    VECTOR_FOR_INORDER_I(i, u8) {
+        r->AVRB(i) = b->AVRB(i) ^ (AES_Td4[a->AVRB(AES_ishifts[i])] & 0xFF);
+    }
 }
 
 #define ROTRu32(v, n) (((v) >> (n)) | ((v) << (32-n)))