[Qemu-devel] [PATCH 3/3] target-i386: add AES-NI instructions

[Aurelien Jarno <aurelien@aurel32.net>]

Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
---
 target-i386/cpu.c            |    6 +-
 target-i386/ops_sse.h        |  188 ++++++++++++++++++++++++++++++++++++++++++
 target-i386/ops_sse_header.h |    6 ++
 target-i386/translate.c      |    7 ++
 4 files changed, 204 insertions(+), 3 deletions(-)

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 5941d40..321d945 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -390,13 +390,13 @@ typedef struct x86_def_t {
 #define TCG_EXT_FEATURES (CPUID_EXT_SSE3 | CPUID_EXT_PCLMULQDQ | \
           CPUID_EXT_MONITOR | CPUID_EXT_SSSE3 | CPUID_EXT_CX16 | \
           CPUID_EXT_SSE41 | CPUID_EXT_SSE42 | CPUID_EXT_POPCNT | \
-          CPUID_EXT_MOVBE | CPUID_EXT_HYPERVISOR)
+          CPUID_EXT_MOVBE | CPUID_EXT_AES | CPUID_EXT_HYPERVISOR)
           /* missing:
           CPUID_EXT_DTES64, CPUID_EXT_DSCPL, CPUID_EXT_VMX, CPUID_EXT_SMX,
           CPUID_EXT_EST, CPUID_EXT_TM2, CPUID_EXT_CID, CPUID_EXT_FMA,
           CPUID_EXT_XTPR, CPUID_EXT_PDCM, CPUID_EXT_PCID, CPUID_EXT_DCA,
-          CPUID_EXT_X2APIC, CPUID_EXT_TSC_DEADLINE_TIMER, CPUID_EXT_AES,
-          CPUID_EXT_XSAVE, CPUID_EXT_OSXSAVE, CPUID_EXT_AVX, CPUID_EXT_F16C,
+          CPUID_EXT_X2APIC, CPUID_EXT_TSC_DEADLINE_TIMER, CPUID_EXT_XSAVE,
+          CPUID_EXT_OSXSAVE, CPUID_EXT_AVX, CPUID_EXT_F16C,
           CPUID_EXT_RDRAND */
 #define TCG_EXT2_FEATURES ((TCG_FEATURES & CPUID_EXT2_AMD_ALIASES) | \
           CPUID_EXT2_NX | CPUID_EXT2_MMXEXT | CPUID_EXT2_RDTSCP | \
diff --git a/target-i386/ops_sse.h b/target-i386/ops_sse.h
index 2ee5b8d..05b9842 100644
--- a/target-i386/ops_sse.h
+++ b/target-i386/ops_sse.h
@@ -2203,6 +2203,194 @@ void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     d->Q(0) = resl;
     d->Q(1) = resh;
 }
+
+/* AES-NI op helpers */
+static const uint8_t aes_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 const uint8_t aes_inv_sbox[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 inline void aes_subreg(Reg *d, const uint8_t s[256])
+{
+    int i;
+
+    for (i = 0; i < 16; i++) {
+        d->B(i) = s[d->B(i)];
+    }
+}
+
+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_inv_shifts[16] = {
+    0, 13, 10, 7, 4, 1, 14, 11, 8, 5, 2, 15, 12, 9, 6, 3
+};
+
+static inline void aes_shiftrows(Reg *a, const uint8_t s[16])
+{
+    int i;
+    Reg tmp = *a;
+
+    for (i = 0 ; i < 16 ; i++) {
+        a->B(i) = tmp.B(s[i]);
+    }
+}
+
+const uint8_t aes_mix[4] = {
+    2, 3, 1, 1
+};
+
+const uint8_t aes_inv_mix[4] = {
+    14, 11, 13, 9
+};
+
+static inline uint8_t aes_ffmul(uint8_t a, uint8_t b)
+{
+    uint8_t res = 0;
+
+    while (b) {
+        if (b & 1) {
+            res ^= a;
+        }
+        a = (a << 1) ^ (a & 0x80 ? 0x1b : 0x00);
+        b >>= 1;
+    }
+    return res;
+}
+
+static inline void aes_mixcolumns(Reg *a, const uint8_t m[4])
+{
+    int i, j, k;
+    Reg tmp = *a;
+
+    for (i = 0; i < 4; i += 1) {
+        for (j = 0; j < 4; j += 1) {
+            a->B(i * 4 + j) = 0;
+            for (k = 0; k < 4; k += 1) {
+                a->B(i * 4 + j) ^= aes_ffmul(m[(k - j) & 3], tmp.B(i * 4 + k));
+            }
+        }
+    }
+}
+
+void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    aes_shiftrows(d, aes_inv_shifts);
+    aes_subreg(d, aes_inv_sbox);
+    aes_mixcolumns(d, aes_inv_mix);
+    d->Q(0) ^= s->Q(0);
+    d->Q(1) ^= s->Q(1);
+}
+
+void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    aes_shiftrows(d, aes_inv_shifts);
+    aes_subreg(d, aes_inv_sbox);
+    d->Q(0) ^= s->Q(0);
+    d->Q(1) ^= s->Q(1);
+}
+
+void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    aes_shiftrows(d, aes_shifts);
+    aes_subreg(d, aes_sbox);
+    aes_mixcolumns(d, aes_mix);
+    d->Q(0) ^= s->Q(0);
+    d->Q(1) ^= s->Q(1);
+}
+
+void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    aes_shiftrows(d, aes_shifts);
+    aes_subreg(d, aes_sbox);
+    d->Q(0) ^= s->Q(0);
+    d->Q(1) ^= s->Q(1);
+}
+
+void glue(helper_aesimc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+    *d = *s;
+    aes_mixcolumns(d, aes_inv_mix);
+}
+
+void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+                                          uint32_t ctrl)
+{
+    int i;
+
+    for (i = 0 ; i < 4 ; i++) {
+        d->B(i) = aes_sbox[s->B(i + 4)];
+        d->B(i + 8) = aes_sbox[s->B(i + 12)];
+    }
+    d->L(1) = (d->L(0) << 24 | d->L(0) >> 8) ^ ctrl;
+    d->L(3) = (d->L(2) << 24 | d->L(2) >> 8) ^ ctrl;
+}
 #endif
 
 #undef SHIFT
diff --git a/target-i386/ops_sse_header.h b/target-i386/ops_sse_header.h
index 2842233..a68c7cc 100644
--- a/target-i386/ops_sse_header.h
+++ b/target-i386/ops_sse_header.h
@@ -338,6 +338,12 @@ DEF_HELPER_3(popcnt, tl, env, tl, i32)
 
 /* AES-NI op helpers */
 #if SHIFT == 1
+DEF_HELPER_3(glue(aesdec, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_3(glue(aesdeclast, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_3(glue(aesenc, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_3(glue(aesenclast, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_3(glue(aesimc, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_4(glue(aeskeygenassist, SUFFIX), void, env, Reg, Reg, i32)
 DEF_HELPER_4(glue(pclmulqdq, SUFFIX), void, env, Reg, Reg, i32)
 #endif
 
diff --git a/target-i386/translate.c b/target-i386/translate.c
index d649e99..233f24f 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -3149,6 +3149,7 @@ struct SSEOpHelper_eppi {
 #define SSE41_SPECIAL { { NULL, SSE_SPECIAL }, CPUID_EXT_SSE41 }
 #define PCLMULQDQ_OP(x) { { NULL, gen_helper_ ## x ## _xmm }, \
         CPUID_EXT_PCLMULQDQ }
+#define AESNI_OP(x) { { NULL, gen_helper_ ## x ## _xmm }, CPUID_EXT_AES }
 
 static const struct SSEOpHelper_epp sse_op_table6[256] = {
     [0x00] = SSSE3_OP(pshufb),
@@ -3197,6 +3198,11 @@ static const struct SSEOpHelper_epp sse_op_table6[256] = {
     [0x3f] = SSE41_OP(pmaxud),
     [0x40] = SSE41_OP(pmulld),
     [0x41] = SSE41_OP(phminposuw),
+    [0xdb] = AESNI_OP(aesimc),
+    [0xdc] = AESNI_OP(aesenc),
+    [0xdd] = AESNI_OP(aesenclast),
+    [0xde] = AESNI_OP(aesdec),
+    [0xdf] = AESNI_OP(aesdeclast),
 };
 
 static const struct SSEOpHelper_eppi sse_op_table7[256] = {
@@ -3223,6 +3229,7 @@ static const struct SSEOpHelper_eppi sse_op_table7[256] = {
     [0x61] = SSE42_OP(pcmpestri),
     [0x62] = SSE42_OP(pcmpistrm),
     [0x63] = SSE42_OP(pcmpistri),
+    [0xdf] = AESNI_OP(aeskeygenassist),
 };
 
 static void gen_sse(CPUX86State *env, DisasContext *s, int b,
-- 
1.7.10.4