[PATCH v4 14/30] tcg/loongarch64: Implement bswap{16,32,64} ops

[WANG Xuerui]

Signed-off-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     | 10 +++++-----
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 46b4f54562..ce6843b408 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -519,6 +519,33 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_opc_bstrins_d(s, a0, a2, args[3], args[3] + args[4] - 1);
         break;
 
+    case INDEX_op_bswap16_i32:
+    case INDEX_op_bswap16_i64:
+        tcg_out_opc_revb_2h(s, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tcg_out_ext16s(s, a0, a0);
+        } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext16u(s, a0, a0);
+        }
+        break;
+
+    case INDEX_op_bswap32_i32:
+        /* All 32-bit values are computed sign-extended in the register.  */
+        a2 = TCG_BSWAP_OS;
+        /* fallthrough */
+    case INDEX_op_bswap32_i64:
+        tcg_out_opc_revb_2w(s, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tcg_out_ext32s(s, a0, a0);
+        } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext32u(s, a0, a0);
+        }
+        break;
+
+    case INDEX_op_bswap64_i64:
+        tcg_out_opc_revb_d(s, a0, a1);
+        break;
+
     case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
     case INDEX_op_mov_i64:
     default:
@@ -550,6 +577,11 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
     case INDEX_op_not_i64:
     case INDEX_op_extract_i32:
     case INDEX_op_extract_i64:
+    case INDEX_op_bswap16_i32:
+    case INDEX_op_bswap16_i64:
+    case INDEX_op_bswap32_i32:
+    case INDEX_op_bswap32_i64:
+    case INDEX_op_bswap64_i64:
         return C_O1_I1(r, r);
 
     case INDEX_op_andc_i32:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 084d635a8e..02d17d2f6d 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -111,8 +111,8 @@ typedef enum {
 #define TCG_TARGET_HAS_ext16s_i32       1
 #define TCG_TARGET_HAS_ext8u_i32        1
 #define TCG_TARGET_HAS_ext16u_i32       1
-#define TCG_TARGET_HAS_bswap16_i32      0
-#define TCG_TARGET_HAS_bswap32_i32      0
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
 #define TCG_TARGET_HAS_not_i32          1
 #define TCG_TARGET_HAS_neg_i32          0
 #define TCG_TARGET_HAS_andc_i32         1
@@ -146,9 +146,9 @@ typedef enum {
 #define TCG_TARGET_HAS_ext8u_i64        1
 #define TCG_TARGET_HAS_ext16u_i64       1
 #define TCG_TARGET_HAS_ext32u_i64       1
-#define TCG_TARGET_HAS_bswap16_i64      0
-#define TCG_TARGET_HAS_bswap32_i64      0
-#define TCG_TARGET_HAS_bswap64_i64      0
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
 #define TCG_TARGET_HAS_not_i64          1
 #define TCG_TARGET_HAS_neg_i64          0
 #define TCG_TARGET_HAS_andc_i64         1
-- 
2.33.0