[Qemu-devel] [PATCH 45/57] target-i386: Implement MOVBE

[Richard Henderson]

Signed-off-by: Richard Henderson <address@hidden>
---
 target-i386/cpu.c       |  16 +++++--
 target-i386/translate.c | 122 ++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 110 insertions(+), 28 deletions(-)

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 376d4c8..776b670 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -382,10 +382,15 @@ typedef struct x86_def_t {
           CPUID_VME, CPUID_DTS, CPUID_SS, CPUID_HT, CPUID_TM, CPUID_PBE */
 #define TCG_EXT_FEATURES (CPUID_EXT_SSE3 | CPUID_EXT_MONITOR | \
           CPUID_EXT_SSSE3 | CPUID_EXT_CX16 | CPUID_EXT_POPCNT | \
-          CPUID_EXT_HYPERVISOR)
+          CPUID_EXT_MOVBE | CPUID_EXT_HYPERVISOR)
           /* missing:
-          CPUID_EXT_DTES64, CPUID_EXT_DSCPL, CPUID_EXT_VMX, CPUID_EXT_EST,
-          CPUID_EXT_TM2, CPUID_EXT_XTPR, CPUID_EXT_PDCM, CPUID_EXT_XSAVE */
+          CPUID_EXT_PCLMULQDQ, 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_SSE41, CPUID_EXT_SSE42,
+          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_RDRAND */
 #define TCG_EXT2_FEATURES ((TCG_FEATURES & CPUID_EXT2_AMD_ALIASES) | \
           CPUID_EXT2_NX | CPUID_EXT2_MMXEXT | CPUID_EXT2_RDTSCP | \
           CPUID_EXT2_3DNOW | CPUID_EXT2_3DNOWEXT)
@@ -395,6 +400,11 @@ typedef struct x86_def_t {
           CPUID_EXT3_CR8LEG | CPUID_EXT3_ABM | CPUID_EXT3_SSE4A)
 #define TCG_SVM_FEATURES 0
 #define TCG_7_0_EBX_FEATURES (CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_SMAP)
+          /* missing:
+          CPUID_7_0_EBX_FSGSBASE, CPUID_7_0_EBX_BMI1, CPUID_7_0_EBX_HLE,
+          CPUID_7_0_EBX_AVX2, CPUID_7_0_EBX_BMI2, CPUID_7_0_EBX_ERMS,
+          CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM, CPUID_7_0_EBX_RDSEED,
+          CPUID_7_0_EBX_ADX */
 
 /* maintains list of cpu model definitions
  */
diff --git a/target-i386/translate.c b/target-i386/translate.c
index a9cb60b..cee6095 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -3842,11 +3842,13 @@ static void gen_sse(CPUX86State *env, DisasContext *s, 
int b,
             reg = ((modrm >> 3) & 7) | rex_r;
             gen_op_mov_reg_T0(OT_LONG, reg);
             break;
+
         case 0x138:
-            if (s->prefix & PREFIX_REPNZ)
-                goto crc32;
         case 0x038:
             b = modrm;
+            if ((b & 0xf0) == 0xf0) {
+                goto do_0f_38_fx;
+            }
             modrm = cpu_ldub_code(env, s->pc++);
             rm = modrm & 7;
             reg = ((modrm >> 3) & 7) | rex_r;
@@ -3919,36 +3921,106 @@ static void gen_sse(CPUX86State *env, DisasContext *s, 
int b,
                 set_cc_op(s, CC_OP_EFLAGS);
             }
             break;
-        case 0x338: /* crc32 */
-        crc32:
-            b = modrm;
+
+        case 0x238:
+        case 0x338:
+        do_0f_38_fx:
+            /* Various integer extensions at 0f 38 f[0-f].  */
+            b = modrm | (b1 << 8);
             modrm = cpu_ldub_code(env, s->pc++);
             reg = ((modrm >> 3) & 7) | rex_r;
 
-            if (b != 0xf0 && b != 0xf1)
-                goto illegal_op;
-            if (!(s->cpuid_ext_features & CPUID_EXT_SSE42))
-                goto illegal_op;
+            switch (b) {
+            case 0x3f0: /* crc32 Gd,Eb */
+            case 0x3f1: /* crc32 Gd,Ey */
+            do_crc32:
+                if (!(s->cpuid_ext_features & CPUID_EXT_SSE42)) {
+                    goto illegal_op;
+                }
+                if ((b & 0xff) == 0xf0) {
+                    ot = OT_BYTE;
+                } else if (s->dflag != 2) {
+                    ot = (s->prefix & PREFIX_DATA ? OT_WORD : OT_LONG);
+                } else {
+                    ot = OT_QUAD;
+                }
 
-            if (b == 0xf0)
-                ot = OT_BYTE;
-            else if (b == 0xf1 && s->dflag != 2)
-                if (s->prefix & PREFIX_DATA)
-                    ot = OT_WORD;
-                else
-                    ot = OT_LONG;
-            else
-                ot = OT_QUAD;
+                gen_op_mov_TN_reg(OT_LONG, 0, reg);
+                tcg_gen_trunc_tl_i32(cpu_tmp2_i32, cpu_T[0]);
+                gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
+                gen_helper_crc32(cpu_T[0], cpu_tmp2_i32,
+                                 cpu_T[0], tcg_const_i32(8 << ot));
 
-            gen_op_mov_TN_reg(OT_LONG, 0, reg);
-            tcg_gen_trunc_tl_i32(cpu_tmp2_i32, cpu_T[0]);
-            gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
-            gen_helper_crc32(cpu_T[0], cpu_tmp2_i32,
-                             cpu_T[0], tcg_const_i32(8 << ot));
+                ot = (s->dflag == 2) ? OT_QUAD : OT_LONG;
+                gen_op_mov_reg_T0(ot, reg);
+                break;
 
-            ot = (s->dflag == 2) ? OT_QUAD : OT_LONG;
-            gen_op_mov_reg_T0(ot, reg);
+            case 0x1f0: /* crc32 or movbe */
+            case 0x1f1:
+                /* For these insns, the f3 prefix is supposed to have priority
+                   over the 66 prefix, but that's not what we implement above
+                   setting b1.  */
+                if (s->prefix & PREFIX_REPNZ) {
+                    goto do_crc32;
+                }
+                /* FALLTHRU */
+            case 0x0f0: /* movbe Gy,My */
+            case 0x0f1: /* movbe My,Gy */
+                if (!(s->cpuid_ext_features & CPUID_EXT_MOVBE)) {
+                    goto illegal_op;
+                }
+                if (s->dflag != 2) {
+                    ot = (s->prefix & PREFIX_DATA ? OT_WORD : OT_LONG);
+                } else {
+                    ot = OT_QUAD;
+                }
+
+                /* Load the data incoming to the bswap.  Note that the TCG
+                   implementation of bswap requires the input be zero
+                   extended.  In the case of the loads, we simply know that
+                   gen_op_ld_v via gen_ldst_modrm does that already.  */
+                if ((b & 1) == 0) {
+                    gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
+                } else {
+                    switch (ot) {
+                    case OT_WORD:
+                        tcg_gen_ext16u_tl(cpu_T[0], cpu_regs[reg]);
+                        break;
+                    default:
+                        tcg_gen_ext32u_tl(cpu_T[0], cpu_regs[reg]);
+                        break;
+                    case OT_QUAD:
+                        tcg_gen_mov_tl(cpu_T[0], cpu_regs[reg]);
+                        break;
+                    }
+                }
+
+                switch (ot) {
+                case OT_WORD:
+                    tcg_gen_bswap16_tl(cpu_T[0], cpu_T[0]);
+                    break;
+                default:
+                    tcg_gen_bswap32_tl(cpu_T[0], cpu_T[0]);
+                    break;
+#ifdef TARGET_X86_64
+                case OT_QUAD:
+                    tcg_gen_bswap64_tl(cpu_T[0], cpu_T[0]);
+                    break;
+#endif
+                }
+
+                if ((b & 1) == 0) {
+                    gen_op_mov_reg_T0(ot, reg);
+                } else {
+                    gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 1);
+                }
+                break;
+
+            default:
+                goto illegal_op;
+            }
             break;
+
         case 0x03a:
         case 0x13a:
             b = modrm;
-- 
1.7.11.7