tcg/mips: Support bswap flags in tcg_out_bswap32

Merge tcg_out_bswap32 and tcg_out_bswap32s.
Use the flags in the internal uses for loads and stores.

For mips32r2 bswap32 with zero-extension, standardize on
WSBH+ROTR+DEXT.  This is the same number of insns as the
previous DSBH+DSHD+DSRL but fits in better with the flags check.

Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 16 insertions, 23 deletions

diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index a9f9f52..bf0eb84 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -579,27 +579,20 @@ static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub)
     tcg_debug_assert(ok);
 }
 
-static void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg)
+static void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg, int flags)
 {
     if (use_mips32r2_instructions) {
         tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
         tcg_out_opc_sa(s, OPC_ROTR, ret, ret, 16);
+        if (flags & TCG_BSWAP_OZ) {
+            tcg_out_opc_bf(s, OPC_DEXT, ret, ret, 31, 0);
+        }
     } else {
-        tcg_out_bswap_subr(s, bswap32_addr);
-        /* delay slot -- never omit the insn, like tcg_out_mov might.  */
-        tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
-        tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
-    }
-}
-
-static void tcg_out_bswap32u(TCGContext *s, TCGReg ret, TCGReg arg)
-{
-    if (use_mips32r2_instructions) {
-        tcg_out_opc_reg(s, OPC_DSBH, ret, 0, arg);
-        tcg_out_opc_reg(s, OPC_DSHD, ret, 0, ret);
-        tcg_out_dsrl(s, ret, ret, 32);
-    } else {
-        tcg_out_bswap_subr(s, bswap32u_addr);
+        if (flags & TCG_BSWAP_OZ) {
+            tcg_out_bswap_subr(s, bswap32u_addr);
+        } else {
+            tcg_out_bswap_subr(s, bswap32_addr);
+        }
         /* delay slot -- never omit the insn, like tcg_out_mov might.  */
         tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
         tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
@@ -1381,7 +1374,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         if (TCG_TARGET_REG_BITS == 64 && is_64) {
             if (use_mips32r2_instructions) {
                 tcg_out_opc_imm(s, OPC_LWU, lo, base, 0);
-                tcg_out_bswap32u(s, lo, lo);
+                tcg_out_bswap32(s, lo, lo, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
             } else {
                 tcg_out_bswap_subr(s, bswap32u_addr);
                 /* delay slot */
@@ -1394,7 +1387,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
     case MO_SL | MO_BSWAP:
         if (use_mips32r2_instructions) {
             tcg_out_opc_imm(s, OPC_LW, lo, base, 0);
-            tcg_out_bswap32(s, lo, lo);
+            tcg_out_bswap32(s, lo, lo, 0);
         } else {
             tcg_out_bswap_subr(s, bswap32_addr);
             /* delay slot */
@@ -1520,7 +1513,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         break;
 
     case MO_32 | MO_BSWAP:
-        tcg_out_bswap32(s, TCG_TMP3, lo);
+        tcg_out_bswap32(s, TCG_TMP3, lo, 0);
         lo = TCG_TMP3;
         /* FALLTHRU */
     case MO_32:
@@ -1539,9 +1532,9 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP0, base, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP1, base, 4);
         } else {
-            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? lo : hi);
+            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? lo : hi, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP3, base, 0);
-            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? hi : lo);
+            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? hi : lo, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP3, base, 4);
         }
         break;
@@ -1946,10 +1939,10 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_bswap16(s, a0, a1, a2);
         break;
     case INDEX_op_bswap32_i32:
-        tcg_out_bswap32(s, a0, a1);
+        tcg_out_bswap32(s, a0, a1, 0);
         break;
     case INDEX_op_bswap32_i64:
-        tcg_out_bswap32u(s, a0, a1);
+        tcg_out_bswap32(s, a0, a1, a2);
         break;
     case INDEX_op_bswap64_i64:
         tcg_out_bswap64(s, a0, a1);