tcg/i386: Convert tcg_out_qemu_st_slow_path

Use tcg_out_st_helper_args.  This eliminates the use of a tail call to
the store helper.  This may or may not be an improvement, depending on
the call/return branch prediction of the host microarchitecture.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 4 insertions, 53 deletions

diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 3508b9cc6c..a01bfad773 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -1854,11 +1854,8 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
  */
 static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
 {
-    MemOpIdx oi = l->oi;
-    MemOp opc = get_memop(oi);
-    MemOp s_bits = opc & MO_SIZE;
+    MemOp opc = get_memop(l->oi);
     tcg_insn_unit **label_ptr = &l->label_ptr[0];
-    TCGReg retaddr;
 
     /* resolve label address */
     tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4);
@@ -1866,56 +1863,10 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
         tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4);
     }
 
-    if (TCG_TARGET_REG_BITS == 32) {
-        int ofs = 0;
-
-        tcg_out_st(s, TCG_TYPE_PTR, TCG_AREG0, TCG_REG_ESP, ofs);
-        ofs += 4;
-
-        tcg_out_st(s, TCG_TYPE_I32, l->addrlo_reg, TCG_REG_ESP, ofs);
-        ofs += 4;
-
-        if (TARGET_LONG_BITS == 64) {
-            tcg_out_st(s, TCG_TYPE_I32, l->addrhi_reg, TCG_REG_ESP, ofs);
-            ofs += 4;
-        }
-
-        tcg_out_st(s, TCG_TYPE_I32, l->datalo_reg, TCG_REG_ESP, ofs);
-        ofs += 4;
-
-        if (s_bits == MO_64) {
-            tcg_out_st(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_ESP, ofs);
-            ofs += 4;
-        }
-
-        tcg_out_sti(s, TCG_TYPE_I32, oi, TCG_REG_ESP, ofs);
-        ofs += 4;
-
-        retaddr = TCG_REG_EAX;
-        tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
-        tcg_out_st(s, TCG_TYPE_PTR, retaddr, TCG_REG_ESP, ofs);
-    } else {
-        tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
-        tcg_out_mov(s, TCG_TYPE_TL, tcg_target_call_iarg_regs[1],
-                    l->addrlo_reg);
-        tcg_out_mov(s, (s_bits == MO_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
-                    tcg_target_call_iarg_regs[2], l->datalo_reg);
-        tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[3], oi);
-
-        if (ARRAY_SIZE(tcg_target_call_iarg_regs) > 4) {
-            retaddr = tcg_target_call_iarg_regs[4];
-            tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
-        } else {
-            retaddr = TCG_REG_RAX;
-            tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
-            tcg_out_st(s, TCG_TYPE_PTR, retaddr, TCG_REG_ESP,
-                       TCG_TARGET_CALL_STACK_OFFSET);
-        }
-    }
+    tcg_out_st_helper_args(s, l, &ldst_helper_param);
+    tcg_out_branch(s, 1, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
 
-    /* "Tail call" to the helper, with the return address back inline.  */
-    tcg_out_push(s, retaddr);
-    tcg_out_jmp(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    tcg_out_jmp(s, l->raddr);
     return true;
 }
 #else