Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-tcg-20210306' into staging

TCI build fix and cleanup
Streamline tb_lookup
Fixes for tcg/aarch64

# gpg: Signature made Sat 06 Mar 2021 21:34:46 GMT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-tcg-20210306: (27 commits)
  accel/tcg: Precompute curr_cflags into cpu->tcg_cflags
  include/exec: lightly re-arrange TranslationBlock
  accel/tcg: drop the use of CF_HASH_MASK and rename params
  accel/tcg: move CF_CLUSTER calculation to curr_cflags
  accel/tcg: rename tb_lookup__cpu_state and hoist state extraction
  tcg/tci: Merge mov, not and neg operations
  tcg/tci: Merge bswap operations
  tcg/tci: Merge extension operations
  tcg/tci: Merge basic arithmetic operations
  tcg/tci: Reduce use of tci_read_r64
  tcg/tci: Remove tci_read_r32s
  tcg/tci: Remove tci_read_r32
  tcg/tci: Remove tci_read_r16s
  tcg/tci: Remove tci_read_r16
  tcg/tci: Remove tci_read_r8s
  tcg/tci: Remove tci_read_r8
  tcg/tci: Merge identical cases in generation (load/store opcodes)
  tcg/tci: Merge identical cases in generation (conditional opcodes)
  tcg/tci: Merge identical cases in generation (deposit opcode)
  tcg/tci: Merge identical cases in generation (exchange opcodes)
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 73 insertions, 131 deletions

diff --git a/tcg/tci/tcg-target.c.inc b/tcg/tci/tcg-target.c.inc
index feac4659cc..c79f9c32d8 100644
--- a/tcg/tci/tcg-target.c.inc
+++ b/tcg/tci/tcg-target.c.inc
@@ -380,6 +380,18 @@ static inline void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg)
     old_code_ptr[1] = s->code_ptr - old_code_ptr;
 }
 
+#if TCG_TARGET_REG_BITS == 64
+# define CASE_32_64(x) \
+        case glue(glue(INDEX_op_, x), _i64): \
+        case glue(glue(INDEX_op_, x), _i32):
+# define CASE_64(x) \
+        case glue(glue(INDEX_op_, x), _i64):
+#else
+# define CASE_32_64(x) \
+        case glue(glue(INDEX_op_, x), _i32):
+# define CASE_64(x)
+#endif
+
 static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
                        const int *const_args)
 {
@@ -391,6 +403,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
     case INDEX_op_exit_tb:
         tcg_out64(s, args[0]);
         break;
+
     case INDEX_op_goto_tb:
         if (s->tb_jmp_insn_offset) {
             /* Direct jump method. */
@@ -404,15 +417,18 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         }
         set_jmp_reset_offset(s, args[0]);
         break;
+
     case INDEX_op_br:
         tci_out_label(s, arg_label(args[0]));
         break;
-    case INDEX_op_setcond_i32:
+
+    CASE_32_64(setcond)
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
         tcg_out_r(s, args[2]);
         tcg_out8(s, args[3]);   /* condition */
         break;
+
 #if TCG_TARGET_REG_BITS == 32
     case INDEX_op_setcond2_i32:
         /* setcond2_i32 cond, t0, t1_low, t1_high, t2_low, t2_high */
@@ -423,95 +439,54 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         tcg_out_r(s, args[4]);
         tcg_out8(s, args[5]);   /* condition */
         break;
-#elif TCG_TARGET_REG_BITS == 64
-    case INDEX_op_setcond_i64:
-        tcg_out_r(s, args[0]);
-        tcg_out_r(s, args[1]);
-        tcg_out_r(s, args[2]);
-        tcg_out8(s, args[3]);   /* condition */
-        break;
 #endif
-    case INDEX_op_ld8u_i32:
-    case INDEX_op_ld8s_i32:
-    case INDEX_op_ld16u_i32:
-    case INDEX_op_ld16s_i32:
+
+    CASE_32_64(ld8u)
+    CASE_32_64(ld8s)
+    CASE_32_64(ld16u)
+    CASE_32_64(ld16s)
     case INDEX_op_ld_i32:
-    case INDEX_op_st8_i32:
-    case INDEX_op_st16_i32:
+    CASE_64(ld32u)
+    CASE_64(ld32s)
+    CASE_64(ld)
+    CASE_32_64(st8)
+    CASE_32_64(st16)
     case INDEX_op_st_i32:
-    case INDEX_op_ld8u_i64:
-    case INDEX_op_ld8s_i64:
-    case INDEX_op_ld16u_i64:
-    case INDEX_op_ld16s_i64:
-    case INDEX_op_ld32u_i64:
-    case INDEX_op_ld32s_i64:
-    case INDEX_op_ld_i64:
-    case INDEX_op_st8_i64:
-    case INDEX_op_st16_i64:
-    case INDEX_op_st32_i64:
-    case INDEX_op_st_i64:
+    CASE_64(st32)
+    CASE_64(st)
         stack_bounds_check(args[1], args[2]);
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
         tcg_debug_assert(args[2] == (int32_t)args[2]);
         tcg_out32(s, args[2]);
         break;
-    case INDEX_op_add_i32:
-    case INDEX_op_sub_i32:
-    case INDEX_op_mul_i32:
-    case INDEX_op_and_i32:
-    case INDEX_op_andc_i32:     /* Optional (TCG_TARGET_HAS_andc_i32). */
-    case INDEX_op_eqv_i32:      /* Optional (TCG_TARGET_HAS_eqv_i32). */
-    case INDEX_op_nand_i32:     /* Optional (TCG_TARGET_HAS_nand_i32). */
-    case INDEX_op_nor_i32:      /* Optional (TCG_TARGET_HAS_nor_i32). */
-    case INDEX_op_or_i32:
-    case INDEX_op_orc_i32:      /* Optional (TCG_TARGET_HAS_orc_i32). */
-    case INDEX_op_xor_i32:
-    case INDEX_op_shl_i32:
-    case INDEX_op_shr_i32:
-    case INDEX_op_sar_i32:
-    case INDEX_op_rotl_i32:     /* Optional (TCG_TARGET_HAS_rot_i32). */
-    case INDEX_op_rotr_i32:     /* Optional (TCG_TARGET_HAS_rot_i32). */
-        tcg_out_r(s, args[0]);
-        tcg_out_r(s, args[1]);
-        tcg_out_r(s, args[2]);
-        break;
-    case INDEX_op_deposit_i32:  /* Optional (TCG_TARGET_HAS_deposit_i32). */
-        tcg_out_r(s, args[0]);
-        tcg_out_r(s, args[1]);
-        tcg_out_r(s, args[2]);
-        tcg_debug_assert(args[3] <= UINT8_MAX);
-        tcg_out8(s, args[3]);
-        tcg_debug_assert(args[4] <= UINT8_MAX);
-        tcg_out8(s, args[4]);
-        break;
 
-#if TCG_TARGET_REG_BITS == 64
-    case INDEX_op_add_i64:
-    case INDEX_op_sub_i64:
-    case INDEX_op_mul_i64:
-    case INDEX_op_and_i64:
-    case INDEX_op_andc_i64:     /* Optional (TCG_TARGET_HAS_andc_i64). */
-    case INDEX_op_eqv_i64:      /* Optional (TCG_TARGET_HAS_eqv_i64). */
-    case INDEX_op_nand_i64:     /* Optional (TCG_TARGET_HAS_nand_i64). */
-    case INDEX_op_nor_i64:      /* Optional (TCG_TARGET_HAS_nor_i64). */
-    case INDEX_op_or_i64:
-    case INDEX_op_orc_i64:      /* Optional (TCG_TARGET_HAS_orc_i64). */
-    case INDEX_op_xor_i64:
-    case INDEX_op_shl_i64:
-    case INDEX_op_shr_i64:
-    case INDEX_op_sar_i64:
-    case INDEX_op_rotl_i64:     /* Optional (TCG_TARGET_HAS_rot_i64). */
-    case INDEX_op_rotr_i64:     /* Optional (TCG_TARGET_HAS_rot_i64). */
-    case INDEX_op_div_i64:      /* Optional (TCG_TARGET_HAS_div_i64). */
-    case INDEX_op_divu_i64:     /* Optional (TCG_TARGET_HAS_div_i64). */
-    case INDEX_op_rem_i64:      /* Optional (TCG_TARGET_HAS_div_i64). */
-    case INDEX_op_remu_i64:     /* Optional (TCG_TARGET_HAS_div_i64). */
+    CASE_32_64(add)
+    CASE_32_64(sub)
+    CASE_32_64(mul)
+    CASE_32_64(and)
+    CASE_32_64(or)
+    CASE_32_64(xor)
+    CASE_32_64(andc)     /* Optional (TCG_TARGET_HAS_andc_*). */
+    CASE_32_64(orc)      /* Optional (TCG_TARGET_HAS_orc_*). */
+    CASE_32_64(eqv)      /* Optional (TCG_TARGET_HAS_eqv_*). */
+    CASE_32_64(nand)     /* Optional (TCG_TARGET_HAS_nand_*). */
+    CASE_32_64(nor)      /* Optional (TCG_TARGET_HAS_nor_*). */
+    CASE_32_64(shl)
+    CASE_32_64(shr)
+    CASE_32_64(sar)
+    CASE_32_64(rotl)     /* Optional (TCG_TARGET_HAS_rot_*). */
+    CASE_32_64(rotr)     /* Optional (TCG_TARGET_HAS_rot_*). */
+    CASE_32_64(div)      /* Optional (TCG_TARGET_HAS_div_*). */
+    CASE_32_64(divu)     /* Optional (TCG_TARGET_HAS_div_*). */
+    CASE_32_64(rem)      /* Optional (TCG_TARGET_HAS_div_*). */
+    CASE_32_64(remu)     /* Optional (TCG_TARGET_HAS_div_*). */
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
         tcg_out_r(s, args[2]);
         break;
-    case INDEX_op_deposit_i64:  /* Optional (TCG_TARGET_HAS_deposit_i64). */
+
+    CASE_32_64(deposit)  /* Optional (TCG_TARGET_HAS_deposit_*). */
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
         tcg_out_r(s, args[2]);
@@ -520,45 +495,31 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         tcg_debug_assert(args[4] <= UINT8_MAX);
         tcg_out8(s, args[4]);
         break;
-    case INDEX_op_brcond_i64:
+
+    CASE_32_64(brcond)
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
         tcg_out8(s, args[2]);           /* condition */
         tci_out_label(s, arg_label(args[3]));
         break;
-    case INDEX_op_bswap16_i64:  /* Optional (TCG_TARGET_HAS_bswap16_i64). */
-    case INDEX_op_bswap32_i64:  /* Optional (TCG_TARGET_HAS_bswap32_i64). */
-    case INDEX_op_bswap64_i64:  /* Optional (TCG_TARGET_HAS_bswap64_i64). */
-    case INDEX_op_not_i64:      /* Optional (TCG_TARGET_HAS_not_i64). */
-    case INDEX_op_neg_i64:      /* Optional (TCG_TARGET_HAS_neg_i64). */
-    case INDEX_op_ext8s_i64:    /* Optional (TCG_TARGET_HAS_ext8s_i64). */
-    case INDEX_op_ext8u_i64:    /* Optional (TCG_TARGET_HAS_ext8u_i64). */
-    case INDEX_op_ext16s_i64:   /* Optional (TCG_TARGET_HAS_ext16s_i64). */
-    case INDEX_op_ext16u_i64:   /* Optional (TCG_TARGET_HAS_ext16u_i64). */
-    case INDEX_op_ext32s_i64:   /* Optional (TCG_TARGET_HAS_ext32s_i64). */
-    case INDEX_op_ext32u_i64:   /* Optional (TCG_TARGET_HAS_ext32u_i64). */
-    case INDEX_op_ext_i32_i64:
-    case INDEX_op_extu_i32_i64:
-#endif /* TCG_TARGET_REG_BITS == 64 */
-    case INDEX_op_neg_i32:      /* Optional (TCG_TARGET_HAS_neg_i32). */
-    case INDEX_op_not_i32:      /* Optional (TCG_TARGET_HAS_not_i32). */
-    case INDEX_op_ext8s_i32:    /* Optional (TCG_TARGET_HAS_ext8s_i32). */
-    case INDEX_op_ext16s_i32:   /* Optional (TCG_TARGET_HAS_ext16s_i32). */
-    case INDEX_op_ext8u_i32:    /* Optional (TCG_TARGET_HAS_ext8u_i32). */
-    case INDEX_op_ext16u_i32:   /* Optional (TCG_TARGET_HAS_ext16u_i32). */
-    case INDEX_op_bswap16_i32:  /* Optional (TCG_TARGET_HAS_bswap16_i32). */
-    case INDEX_op_bswap32_i32:  /* Optional (TCG_TARGET_HAS_bswap32_i32). */
-        tcg_out_r(s, args[0]);
-        tcg_out_r(s, args[1]);
-        break;
-    case INDEX_op_div_i32:      /* Optional (TCG_TARGET_HAS_div_i32). */
-    case INDEX_op_divu_i32:     /* Optional (TCG_TARGET_HAS_div_i32). */
-    case INDEX_op_rem_i32:      /* Optional (TCG_TARGET_HAS_div_i32). */
-    case INDEX_op_remu_i32:     /* Optional (TCG_TARGET_HAS_div_i32). */
+
+    CASE_32_64(neg)      /* Optional (TCG_TARGET_HAS_neg_*). */
+    CASE_32_64(not)      /* Optional (TCG_TARGET_HAS_not_*). */
+    CASE_32_64(ext8s)    /* Optional (TCG_TARGET_HAS_ext8s_*). */
+    CASE_32_64(ext8u)    /* Optional (TCG_TARGET_HAS_ext8u_*). */
+    CASE_32_64(ext16s)   /* Optional (TCG_TARGET_HAS_ext16s_*). */
+    CASE_32_64(ext16u)   /* Optional (TCG_TARGET_HAS_ext16u_*). */
+    CASE_64(ext32s)      /* Optional (TCG_TARGET_HAS_ext32s_i64). */
+    CASE_64(ext32u)      /* Optional (TCG_TARGET_HAS_ext32u_i64). */
+    CASE_64(ext_i32)
+    CASE_64(extu_i32)
+    CASE_32_64(bswap16)  /* Optional (TCG_TARGET_HAS_bswap16_*). */
+    CASE_32_64(bswap32)  /* Optional (TCG_TARGET_HAS_bswap32_*). */
+    CASE_64(bswap64)     /* Optional (TCG_TARGET_HAS_bswap64_i64). */
         tcg_out_r(s, args[0]);
         tcg_out_r(s, args[1]);
-        tcg_out_r(s, args[2]);
         break;
+
 #if TCG_TARGET_REG_BITS == 32
     case INDEX_op_add2_i32:
     case INDEX_op_sub2_i32:
@@ -584,31 +545,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         tcg_out_r(s, args[3]);
         break;
 #endif
-    case INDEX_op_brcond_i32:
-        tcg_out_r(s, args[0]);
-        tcg_out_r(s, args[1]);
-        tcg_out8(s, args[2]);           /* condition */
-        tci_out_label(s, arg_label(args[3]));
-        break;
+
     case INDEX_op_qemu_ld_i32:
-        tcg_out_r(s, *args++);
-        tcg_out_r(s, *args++);
-        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
-            tcg_out_r(s, *args++);
-        }
-        tcg_out_i(s, *args++);
-        break;
-    case INDEX_op_qemu_ld_i64:
-        tcg_out_r(s, *args++);
-        if (TCG_TARGET_REG_BITS == 32) {
-            tcg_out_r(s, *args++);
-        }
-        tcg_out_r(s, *args++);
-        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
-            tcg_out_r(s, *args++);
-        }
-        tcg_out_i(s, *args++);
-        break;
     case INDEX_op_qemu_st_i32:
         tcg_out_r(s, *args++);
         tcg_out_r(s, *args++);
@@ -617,6 +555,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         }
         tcg_out_i(s, *args++);
         break;
+
+    case INDEX_op_qemu_ld_i64:
     case INDEX_op_qemu_st_i64:
         tcg_out_r(s, *args++);
         if (TCG_TARGET_REG_BITS == 32) {
@@ -628,8 +568,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
         }
         tcg_out_i(s, *args++);
         break;
+
     case INDEX_op_mb:
         break;
+
     case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
     case INDEX_op_mov_i64:
     case INDEX_op_call:     /* Always emitted via tcg_out_call.  */