[Qemu-devel] [PATCH v4 14/33] tcg-aarch64: Handle zero as first argument to sub

[Richard Henderson]

In order to properly handle neg, as generated by TCG generic code.

Signed-off-by: Richard Henderson <r...@twiddle.net>
---
 tcg/aarch64/tcg-target.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
index 5b4eeee..08a0cc4 100644
--- a/tcg/aarch64/tcg-target.c
+++ b/tcg/aarch64/tcg-target.c
@@ -114,6 +114,7 @@ static inline void patch_reloc(uint8_t *code_ptr, int type,
 #define TCG_CT_CONST_IS32 0x100
 #define TCG_CT_CONST_AIMM 0x200
 #define TCG_CT_CONST_LIMM 0x400
+#define TCG_CT_CONST_ZERO 0x800
 
 /* parse target specific constraints */
 static int target_parse_constraint(TCGArgConstraint *ct,
@@ -147,6 +148,9 @@ static int target_parse_constraint(TCGArgConstraint *ct,
     case 'L': /* Valid for logical immediate.  */
         ct->ct |= TCG_CT_CONST_LIMM;
         break;
+    case 'Z': /* zero */
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
     default:
         return -1;
     }
@@ -198,6 +202,9 @@ static int tcg_target_const_match(tcg_target_long val,
     if ((ct & TCG_CT_CONST_LIMM) && is_limm(val)) {
         return 1;
     }
+    if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    }
 
     return 0;
 }
@@ -1186,6 +1193,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     TCGArg a2 = args[2];
     int c2 = const_args[2];
 
+    /* Some operands are defined with "rZ" constraint, a register or
+       the zero register.  These need not actually test args[I] == 0.  */
+#define REG0(I)  (const_args[I] ? TCG_REG_XZR : (TCGReg)args[I])
+
     switch (opc) {
     case INDEX_op_exit_tb:
         tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
@@ -1255,9 +1266,16 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         /* FALLTHRU */
     case INDEX_op_sub_i64:
         if (c2) {
-            tcg_out_addsubi(s, ext, a0, a1, -a2);
+            /* Arithmetic immediate instructions use Xn|sp, and thus
+               we cannot encode the zero register if tcg optimization
+               is turned off and both A1 and A2 are constants.  */
+            if (const_args[1]) {
+                tcg_out_movi(s, ext ? TCG_TYPE_I64 : TCG_TYPE_I32, a0, -a2);
+            } else {
+                tcg_out_addsubi(s, ext, a0, a1, -a2);
+            }
         } else {
-            tcg_fmt_Rdnm(s, INSN_SUB, ext, a0, a1, a2);
+            tcg_fmt_Rdnm(s, INSN_SUB, ext, a0, REG0(1), a2);
         }
         break;
 
@@ -1481,6 +1499,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         /* Opcode not implemented.  */
         tcg_abort();
     }
+
+#undef REG0
 }
 
 static const TCGTargetOpDef aarch64_op_defs[] = {
@@ -1518,8 +1538,8 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
 
     { INDEX_op_add_i32, { "r", "r", "rwA" } },
     { INDEX_op_add_i64, { "r", "r", "rA" } },
-    { INDEX_op_sub_i32, { "r", "r", "rwA" } },
-    { INDEX_op_sub_i64, { "r", "r", "rA" } },
+    { INDEX_op_sub_i32, { "r", "rZ", "rwA" } },
+    { INDEX_op_sub_i64, { "r", "rZ", "rA" } },
     { INDEX_op_mul_i32, { "r", "r", "r" } },
     { INDEX_op_mul_i64, { "r", "r", "r" } },
     { INDEX_op_and_i32, { "r", "r", "rwL" } },
-- 
1.8.3.1