tcg: implement real ext_i32_i64 and extu_i32_i64 ops

Implement real ext_i32_i64 and extu_i32_i64 ops. They ensure that a
32-bit value is always converted to a 64-bit value and not propagated
through the register allocator or the optimizer.

Cc: Andrzej Zaborowski <balrogg@gmail.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Blue Swirl <blauwirbel@gmail.com>
Cc: Stefan Weil <sw@weilnetz.de>
Acked-by: Claudio Fontana <claudio.fontana@huawei.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>

10 files changed, 45 insertions, 10 deletions

diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
index b7ec4f5..7f7ab7e 100644
--- a/tcg/aarch64/tcg-target.c
+++ b/tcg/aarch64/tcg-target.c
@@ -1556,6 +1556,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ext16s_i32:
         tcg_out_sxt(s, ext, MO_16, a0, a1);
         break;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         tcg_out_sxt(s, TCG_TYPE_I64, MO_32, a0, a1);
         break;
@@ -1567,6 +1568,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ext16u_i32:
         tcg_out_uxt(s, MO_16, a0, a1);
         break;
+    case INDEX_op_extu_i32_i64:
     case INDEX_op_ext32u_i64:
         tcg_out_movr(s, TCG_TYPE_I32, a0, a1);
         break;
@@ -1712,6 +1714,8 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
     { INDEX_op_ext8u_i64, { "r", "r" } },
     { INDEX_op_ext16u_i64, { "r", "r" } },
     { INDEX_op_ext32u_i64, { "r", "r" } },
+    { INDEX_op_ext_i32_i64, { "r", "r" } },
+    { INDEX_op_extu_i32_i64, { "r", "r" } },
 
     { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
     { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
index 887f22f..7648f7e 100644
--- a/tcg/i386/tcg-target.c
+++ b/tcg/i386/tcg-target.c
@@ -2064,9 +2064,11 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_bswap64_i64:
         tcg_out_bswap64(s, args[0]);
         break;
+    case INDEX_op_extu_i32_i64:
     case INDEX_op_ext32u_i64:
         tcg_out_ext32u(s, args[0], args[1]);
         break;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         tcg_out_ext32s(s, args[0], args[1]);
         break;
@@ -2201,6 +2203,9 @@ static const TCGTargetOpDef x86_op_defs[] = {
     { INDEX_op_ext16u_i64, { "r", "r" } },
     { INDEX_op_ext32u_i64, { "r", "r" } },
 
+    { INDEX_op_ext_i32_i64, { "r", "r" } },
+    { INDEX_op_extu_i32_i64, { "r", "r" } },
+
     { INDEX_op_deposit_i64, { "Q", "0", "Q" } },
     { INDEX_op_movcond_i64, { "r", "r", "re", "r", "0" } },
 
diff --git a/tcg/ia64/tcg-target.c b/tcg/ia64/tcg-target.c
index 81cb9f7..71e79cf 100644
--- a/tcg/ia64/tcg-target.c
+++ b/tcg/ia64/tcg-target.c
@@ -2148,9 +2148,11 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ext16u_i64:
         tcg_out_ext(s, OPC_ZXT2_I29, args[0], args[1]);
         break;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         tcg_out_ext(s, OPC_SXT4_I29, args[0], args[1]);
         break;
+    case INDEX_op_extu_i32_i64:
     case INDEX_op_ext32u_i64:
         tcg_out_ext(s, OPC_ZXT4_I29, args[0], args[1]);
         break;
@@ -2301,6 +2303,8 @@ static const TCGTargetOpDef ia64_op_defs[] = {
     { INDEX_op_ext16u_i64, { "r", "rZ"} },
     { INDEX_op_ext32s_i64, { "r", "rZ"} },
     { INDEX_op_ext32u_i64, { "r", "rZ"} },
+    { INDEX_op_ext_i32_i64, { "r", "rZ" } },
+    { INDEX_op_extu_i32_i64, { "r", "rZ" } },
 
     { INDEX_op_bswap16_i64, { "r", "rZ" } },
     { INDEX_op_bswap32_i64, { "r", "rZ" } },
diff --git a/tcg/ppc/tcg-target.c b/tcg/ppc/tcg-target.c
index 2b6eafa..31fa25c 100644
--- a/tcg/ppc/tcg-target.c
+++ b/tcg/ppc/tcg-target.c
@@ -2200,12 +2200,16 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
     case INDEX_op_ext16s_i64:
         c = EXTSH;
         goto gen_ext;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         c = EXTSW;
         goto gen_ext;
     gen_ext:
         tcg_out32(s, c | RS(args[1]) | RA(args[0]));
         break;
+    case INDEX_op_extu_i32_i64:
+        tcg_out_ext32u(s, args[0], args[1]);
+        break;
 
     case INDEX_op_setcond_i32:
         tcg_out_setcond(s, TCG_TYPE_I32, args[3], args[0], args[1], args[2],
@@ -2482,6 +2486,8 @@ static const TCGTargetOpDef ppc_op_defs[] = {
     { INDEX_op_ext8s_i64, { "r", "r" } },
     { INDEX_op_ext16s_i64, { "r", "r" } },
     { INDEX_op_ext32s_i64, { "r", "r" } },
+    { INDEX_op_ext_i32_i64, { "r", "r" } },
+    { INDEX_op_extu_i32_i64, { "r", "r" } },
     { INDEX_op_bswap16_i64, { "r", "r" } },
     { INDEX_op_bswap32_i64, { "r", "r" } },
     { INDEX_op_bswap64_i64, { "r", "r" } },
diff --git a/tcg/s390/tcg-target.c b/tcg/s390/tcg-target.c
index aa718ec..96c3d65 100644
--- a/tcg/s390/tcg-target.c
+++ b/tcg/s390/tcg-target.c
@@ -2090,6 +2090,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ext16s_i64:
         tgen_ext16s(s, TCG_TYPE_I64, args[0], args[1]);
         break;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         tgen_ext32s(s, args[0], args[1]);
         break;
@@ -2099,6 +2100,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ext16u_i64:
         tgen_ext16u(s, TCG_TYPE_I64, args[0], args[1]);
         break;
+    case INDEX_op_extu_i32_i64:
     case INDEX_op_ext32u_i64:
         tgen_ext32u(s, args[0], args[1]);
         break;
@@ -2251,6 +2253,9 @@ static const TCGTargetOpDef s390_op_defs[] = {
     { INDEX_op_ext32s_i64, { "r", "r" } },
     { INDEX_op_ext32u_i64, { "r", "r" } },
 
+    { INDEX_op_ext_i32_i64, { "r", "r" } },
+    { INDEX_op_extu_i32_i64, { "r", "r" } },
+
     { INDEX_op_bswap16_i64, { "r", "r" } },
     { INDEX_op_bswap32_i64, { "r", "r" } },
     { INDEX_op_bswap64_i64, { "r", "r" } },
diff --git a/tcg/sparc/tcg-target.c b/tcg/sparc/tcg-target.c
index b23032b..fe75af0 100644
--- a/tcg/sparc/tcg-target.c
+++ b/tcg/sparc/tcg-target.c
@@ -1407,9 +1407,11 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_divu_i64:
         c = ARITH_UDIVX;
         goto gen_arith;
+    case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
         tcg_out_arithi(s, a0, a1, 0, SHIFT_SRA);
         break;
+    case INDEX_op_extu_i32_i64:
     case INDEX_op_ext32u_i64:
         tcg_out_arithi(s, a0, a1, 0, SHIFT_SRL);
         break;
@@ -1531,8 +1533,10 @@ static const TCGTargetOpDef sparc_op_defs[] = {
     { INDEX_op_neg_i64, { "R", "RJ" } },
     { INDEX_op_not_i64, { "R", "RJ" } },
 
-    { INDEX_op_ext32s_i64, { "R", "r" } },
-    { INDEX_op_ext32u_i64, { "R", "r" } },
+    { INDEX_op_ext32s_i64, { "R", "R" } },
+    { INDEX_op_ext32u_i64, { "R", "R" } },
+    { INDEX_op_ext_i32_i64, { "R", "r" } },
+    { INDEX_op_extu_i32_i64, { "R", "r" } },
     { INDEX_op_trunc_shr_i64_i32,  { "r", "R" } },
 
     { INDEX_op_brcond_i64, { "RZ", "RJ" } },
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index 0e79fd1..7114315 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1770,9 +1770,8 @@ void tcg_gen_extu_i32_i64(TCGv_i64 ret, TCGv_i32 arg)
         tcg_gen_mov_i32(TCGV_LOW(ret), arg);
         tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
     } else {
-        /* Note: we assume the target supports move between
-           32 and 64 bit registers.  */
-        tcg_gen_ext32u_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+        tcg_gen_op2(&tcg_ctx, INDEX_op_extu_i32_i64,
+                    GET_TCGV_I64(ret), GET_TCGV_I32(arg));
     }
 }
 
@@ -1782,9 +1781,8 @@ void tcg_gen_ext_i32_i64(TCGv_i64 ret, TCGv_i32 arg)
         tcg_gen_mov_i32(TCGV_LOW(ret), arg);
         tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
     } else {
-        /* Note: we assume the target supports move between
-           32 and 64 bit registers.  */
-        tcg_gen_ext32s_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+        tcg_gen_op2(&tcg_ctx, INDEX_op_ext_i32_i64,
+                    GET_TCGV_I64(ret), GET_TCGV_I32(arg));
     }
 }
 
diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h
index 4a34f43..f721a5a 100644
--- a/tcg/tcg-opc.h
+++ b/tcg/tcg-opc.h
@@ -138,6 +138,9 @@ DEF(rotl_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
 DEF(rotr_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
 DEF(deposit_i64, 1, 2, 2, IMPL64 | IMPL(TCG_TARGET_HAS_deposit_i64))
 
+/* size changing ops */
+DEF(ext_i32_i64, 1, 1, 0, IMPL64)
+DEF(extu_i32_i64, 1, 1, 0, IMPL64)
 DEF(trunc_shr_i64_i32, 1, 1, 1,
     IMPL(TCG_TARGET_HAS_trunc_shr_i64_i32)
     | (TCG_TARGET_REG_BITS == 32 ? TCG_OPF_NOT_PRESENT : 0))
diff --git a/tcg/tci/tcg-target.c b/tcg/tci/tcg-target.c
index 83472db..bbb54d4 100644
--- a/tcg/tci/tcg-target.c
+++ b/tcg/tci/tcg-target.c
@@ -210,6 +210,8 @@ static const TCGTargetOpDef tcg_target_op_defs[] = {
 #if TCG_TARGET_HAS_ext32u_i64
     { INDEX_op_ext32u_i64, { R, R } },
 #endif
+    { INDEX_op_ext_i32_i64, { R, R } },
+    { INDEX_op_extu_i32_i64, { R, R } },
 #if TCG_TARGET_HAS_bswap16_i64
     { INDEX_op_bswap16_i64, { R, R } },
 #endif
@@ -701,6 +703,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
     case INDEX_op_ext16u_i64:   /* Optional (TCG_TARGET_HAS_ext16u_i64). */
     case INDEX_op_ext32s_i64:   /* Optional (TCG_TARGET_HAS_ext32s_i64). */
     case INDEX_op_ext32u_i64:   /* Optional (TCG_TARGET_HAS_ext32u_i64). */
+    case INDEX_op_ext_i32_i64:
+    case INDEX_op_extu_i32_i64:
 #endif /* TCG_TARGET_REG_BITS == 64 */
     case INDEX_op_neg_i32:      /* Optional (TCG_TARGET_HAS_neg_i32). */
     case INDEX_op_not_i32:      /* Optional (TCG_TARGET_HAS_not_i32). */
diff --git a/tci.c b/tci.c
index 8444948..3d6d177 100644
--- a/tci.c
+++ b/tci.c
@@ -1033,18 +1033,20 @@ uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr)
 #endif
 #if TCG_TARGET_HAS_ext32s_i64
         case INDEX_op_ext32s_i64:
+#endif
+        case INDEX_op_ext_i32_i64:
             t0 = *tb_ptr++;
             t1 = tci_read_r32s(&tb_ptr);
             tci_write_reg64(t0, t1);
             break;
-#endif
 #if TCG_TARGET_HAS_ext32u_i64
         case INDEX_op_ext32u_i64:
+#endif
+        case INDEX_op_extu_i32_i64:
             t0 = *tb_ptr++;
             t1 = tci_read_r32(&tb_ptr);
             tci_write_reg64(t0, t1);
             break;
-#endif
 #if TCG_TARGET_HAS_bswap16_i64
         case INDEX_op_bswap16_i64:
             TODO();