[PATCH v4 09/36] tcg/i386: Add TCG_TARGET_CALL_{RET,ARG}_I128

[Richard Henderson]

Fill in the parameters for the host ABI for Int128.
Adjust tcg_target_call_oarg_reg for _WIN64, and
tcg_out_call for i386 sysv.  Allow TCG_TYPE_V128
stores without AVX enabled.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/i386/tcg-target.h     | 10 ++++++++++
 tcg/i386/tcg-target.c.inc | 30 +++++++++++++++++++++++++++++-
 2 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 7edb7f1d9a..9e0e82d80a 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -100,6 +100,16 @@ typedef enum {
 #endif
 #define TCG_TARGET_CALL_ARG_I32      TCG_CALL_ARG_NORMAL
 #define TCG_TARGET_CALL_ARG_I64      TCG_CALL_ARG_NORMAL
+#if defined(_WIN64)
+# define TCG_TARGET_CALL_ARG_I128    TCG_CALL_ARG_BY_REF
+# define TCG_TARGET_CALL_RET_I128    TCG_CALL_RET_BY_VEC
+#elif TCG_TARGET_REG_BITS == 64
+# define TCG_TARGET_CALL_ARG_I128    TCG_CALL_ARG_NORMAL
+# define TCG_TARGET_CALL_RET_I128    TCG_CALL_RET_NORMAL
+#else
+# define TCG_TARGET_CALL_ARG_I128    TCG_CALL_ARG_NORMAL
+# define TCG_TARGET_CALL_RET_I128    TCG_CALL_RET_BY_REF
+#endif
 
 extern bool have_bmi1;
 extern bool have_popcnt;
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index ab6881a4f3..c96b5a6f43 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -115,6 +115,11 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind 
kind, int slot)
     case TCG_CALL_RET_NORMAL:
         tcg_debug_assert(slot >= 0 && slot <= 1);
         return slot ? TCG_REG_EDX : TCG_REG_EAX;
+#ifdef _WIN64
+    case TCG_CALL_RET_BY_VEC:
+        tcg_debug_assert(slot == 0);
+        return TCG_REG_XMM0;
+#endif
     default:
         g_assert_not_reached();
     }
@@ -1188,9 +1193,16 @@ static void tcg_out_st(TCGContext *s, TCGType type, 
TCGReg arg,
          * The gvec infrastructure is asserts that v128 vector loads
          * and stores use a 16-byte aligned offset.  Validate that the
          * final pointer is aligned by using an insn that will SIGSEGV.
+         *
+         * This specific instance is also used by TCG_CALL_RET_BY_VEC,
+         * for _WIN64, which must have SSE2 but may not have AVX.
          */
         tcg_debug_assert(arg >= 16);
-        tcg_out_vex_modrm_offset(s, OPC_MOVDQA_WxVx, arg, 0, arg1, arg2);
+        if (have_avx1) {
+            tcg_out_vex_modrm_offset(s, OPC_MOVDQA_WxVx, arg, 0, arg1, arg2);
+        } else {
+            tcg_out_modrm_offset(s, OPC_MOVDQA_WxVx, arg, arg1, arg2);
+        }
         break;
     case TCG_TYPE_V256:
         /*
@@ -1677,6 +1689,22 @@ static void tcg_out_call(TCGContext *s, const 
tcg_insn_unit *dest,
                          const TCGHelperInfo *info)
 {
     tcg_out_branch(s, 1, dest);
+
+#ifndef _WIN32
+    if (TCG_TARGET_REG_BITS == 32 && info->out_kind == TCG_CALL_RET_BY_REF) {
+        /*
+         * The sysv i386 abi for struct return places a reference as the
+         * first argument of the stack, and pops that argument with the
+         * return statement.  Since we want to retain the aligned stack
+         * pointer for the callee, we do not want to actually push that
+         * argument before the call but rely on the normal store to the
+         * stack slot.  But we do need to compensate for the pop in order
+         * to reset our correct stack pointer value.
+         * Pushing a garbage value back onto the stack is quickest.
+         */
+        tcg_out_push(s, TCG_REG_EAX);
+    }
+#endif
 }
 
 static void tcg_out_jmp(TCGContext *s, const tcg_insn_unit *dest)
-- 
2.34.1