tcg/aarch64: Implement goto_ptr

Measurements:

                      SPECint06 (test set), x86_64-linux-user. Host: APM 64-bit ARMv8 (Atlas/A57) @ 2.4 GHz

 1.45x +-+-------------------------------------------------------------------------------------------------------------+-+
       |                                      *****                                                                      |
       |      +++                             *   *                                                    +goto-ptr         |
  1.4x +-+...*****............................*...*....................................................................+-+
       |     *+++*                            *   *                            +++                                       |
 1.35x +-+...*...*............................*...*...........................*****....................................+-+
       |     *   *                            *   *                           *+++*                                      |
       |     *   *                            *   *                           *   *                                      |
  1.3x +-+...*...*............................*...*...........................*...*....................................+-+
       |     *   *                            *   *                           *   *                                      |
       |     *   *                            *   *                           *   *                    *****             |
 1.25x +-+...*...*...........*****............*...*...........................*...*............*****...*...*...........+-+
       |     *   *           *   *            *   *                           *   *            *+++*   *   *             |
  1.2x +-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...........+-+
       |     *   *           *   *            *   *                           *   *            *   *   *   *             |
       |     *   *           *   *            *   *                           *   *            *   *   *   *   *****     |
 1.15x +-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...*...*...+-+
       |     *   *           *   *            *   *                           *   *    +++     *   *   *   *   *   *     |
       |     *   *           *   *            *   *                           *   *   *****    *   *   *   *   *   *     |
  1.1x +-+...*...*...........*...*....*****...*...*...*****...................*...*...*...*....*...*...*...*...*...*...+-+
       |     *   *           *   *    *   *   *   *   *   *                   *   *   *   *    *   *   *   *   *   *     |
 1.05x +-+...*...*...........*...*....*...*...*...*...*...*...................*...*...*...*....*...*...*...*...*...*...+-+
       |     *   *   *****   *   *    *   *   *   *   *   *                   *   *   *   *    *   *   *   *   *   *     |
       |     *   *   *   *   *   *    *   *   *   *   *   *   *****   *****   *   *   *   *    *   *   *   *   *   *     |
    1x +-+---*****---*****---*****----*****---*****---*****---*****---*****---*****---*****----*****---*****---*****---+-+
          astar   bzip2     gcc    gobmk h264ref   hmmlibquantum     mcf omnetpperlbench    sjenxalancbmk   hmean
  png: http://imgur.com/en9HE8LTested-by: NEmilio G. Cota <cota@braap.org>
Reviewed-by: NAurelien Jarno <aurelien@aurel32.net>
Signed-off-by: NRichard Henderson <rth@twiddle.net>

tcg/aarch64/tcg-target.h

@@ -77,7 +77,7 @@ typedef enum {
 #define TCG_TARGET_HAS_mulsh_i32        0
 #define TCG_TARGET_HAS_extrl_i64_i32    0
 #define TCG_TARGET_HAS_extrh_i64_i32    0
-#define TCG_TARGET_HAS_goto_ptr         0
+#define TCG_TARGET_HAS_goto_ptr         1
 
 #define TCG_TARGET_HAS_div_i64          1
 #define TCG_TARGET_HAS_rem_i64          1

tcg/aarch64/tcg-target.inc.c

@@ -1357,8 +1357,13 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     switch (opc) {
     case INDEX_op_exit_tb:
-        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
-        tcg_out_goto(s, tb_ret_addr);
+        /* Reuse the zeroing that exists for goto_ptr.  */
+        if (a0 == 0) {
+            tcg_out_goto(s, s->code_gen_epilogue);
+        } else {
+            tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
+            tcg_out_goto(s, tb_ret_addr);
+        }
         break;
 
     case INDEX_op_goto_tb:
@@ -1374,6 +1379,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         s->tb_jmp_reset_offset[a0] = tcg_current_code_size(s);
         break;
 
+    case INDEX_op_goto_ptr:
+        tcg_out_insn(s, 3207, BR, a0);
+        break;
+
     case INDEX_op_br:
         tcg_out_goto_label(s, arg_label(a0));
         break;
@@ -1735,6 +1744,7 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
     { INDEX_op_exit_tb, { } },
     { INDEX_op_goto_tb, { } },
     { INDEX_op_br, { } },
+    { INDEX_op_goto_ptr, { "r" } },
 
     { INDEX_op_ld8u_i32, { "r", "r" } },
     { INDEX_op_ld8s_i32, { "r", "r" } },
@@ -1942,6 +1952,14 @@ static void tcg_target_qemu_prologue(TCGContext *s)
     tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
     tcg_out_insn(s, 3207, BR, tcg_target_call_iarg_regs[1]);
 
+    /*
+     * Return path for goto_ptr. Set return value to 0, a-la exit_tb,
+     * and fall through to the rest of the epilogue.
+     */
+    s->code_gen_epilogue = s->code_ptr;
+    tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_X0, 0);
+
+    /* TB epilogue */
     tb_ret_addr = s->code_ptr;
 
     /* Remove TCG locals stack space.  */