1 files changed, 36 insertions, 18 deletions

diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index e75a6d4943..9f5cb66718 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -329,11 +329,6 @@ static const uint8_t tcg_cond_to_arm_cond[] = {
     [TCG_COND_GTU] = COND_HI,
 };
 
-static inline void tcg_out_bx(TCGContext *s, int cond, int rn)
-{
-    tcg_out32(s, (cond << 28) | 0x012fff10 | rn);
-}
-
 static inline void tcg_out_b(TCGContext *s, int cond, int32_t offset)
 {
     tcg_out32(s, (cond << 28) | 0x0a000000 |
@@ -402,6 +397,18 @@ static inline void tcg_out_mov_reg(TCGContext *s, int cond, int rd, int rm)
     }
 }
 
+static inline void tcg_out_bx(TCGContext *s, int cond, TCGReg rn)
+{
+    /* Unless the C portion of QEMU is compiled as thumb, we don't
+       actually need true BX semantics; merely a branch to an address
+       held in a register.  */
+    if (use_armv5t_instructions) {
+        tcg_out32(s, (cond << 28) | 0x012fff10 | rn);
+    } else {
+        tcg_out_mov_reg(s, cond, TCG_REG_PC, rn);
+    }
+}
+
 static inline void tcg_out_dat_imm(TCGContext *s,
                 int cond, int opc, int rd, int rn, int im)
 {
@@ -977,7 +984,7 @@ static inline void tcg_out_st8(TCGContext *s, int cond,
  * with the code buffer limited to 16MB we wouldn't need the long case.
  * But we also use it for the tail-call to the qemu_ld/st helpers, which does.
  */
-static inline void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr)
+static void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr)
 {
     intptr_t addri = (intptr_t)addr;
     ptrdiff_t disp = tcg_pcrel_diff(s, addr);
@@ -987,15 +994,9 @@ static inline void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr)
         return;
     }
 
+    assert(use_armv5t_instructions || (addri & 1) == 0);
     tcg_out_movi32(s, cond, TCG_REG_TMP, addri);
-    if (use_armv5t_instructions) {
-        tcg_out_bx(s, cond, TCG_REG_TMP);
-    } else {
-        if (addri & 1) {
-            tcg_abort();
-        }
-        tcg_out_mov_reg(s, cond, TCG_REG_PC, TCG_REG_TMP);
-    }
+    tcg_out_bx(s, cond, TCG_REG_TMP);
 }
 
 /* The call case is mostly used for helpers - so it's not unreasonable
@@ -1654,8 +1655,14 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     switch (opc) {
     case INDEX_op_exit_tb:
-        tcg_out_movi32(s, COND_AL, TCG_REG_R0, args[0]);
-        tcg_out_goto(s, COND_AL, tb_ret_addr);
+        /* Reuse the zeroing that exists for goto_ptr.  */
+        a0 = args[0];
+        if (a0 == 0) {
+            tcg_out_goto(s, COND_AL, s->code_gen_epilogue);
+        } else {
+            tcg_out_movi32(s, COND_AL, TCG_REG_R0, args[0]);
+            tcg_out_goto(s, COND_AL, tb_ret_addr);
+        }
         break;
     case INDEX_op_goto_tb:
         if (s->tb_jmp_insn_offset) {
@@ -1670,6 +1677,9 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         }
         s->tb_jmp_reset_offset[args[0]] = tcg_current_code_size(s);
         break;
+    case INDEX_op_goto_ptr:
+        tcg_out_bx(s, COND_AL, args[0]);
+        break;
     case INDEX_op_br:
         tcg_out_goto_label(s, COND_AL, arg_label(args[0]));
         break;
@@ -1960,6 +1970,7 @@ static const TCGTargetOpDef arm_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" } },
@@ -2135,9 +2146,16 @@ 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_bx(s, COND_AL, tcg_target_call_iarg_regs[1]);
-    tb_ret_addr = s->code_ptr;
 
-    /* Epilogue.  We branch here via tb_ret_addr.  */
+    /*
+     * 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_PTR, TCG_REG_R0, 0);
+
+    /* TB epilogue */
+    tb_ret_addr = s->code_ptr;
     tcg_out_dat_rI(s, COND_AL, ARITH_ADD, TCG_REG_CALL_STACK,
                    TCG_REG_CALL_STACK, stack_addend, 1);