target/mips: Support R5900 three-operand MULT and MULTU instructions

The three-operand MULT and MULTU are the only R5900-specific
instructions emitted by GCC 7.3. The R5900 also implements the three-
operand MADD and MADDU instructions, but they are omitted in QEMU for
now since they are absent in programs compiled by current GCC versions.

Likewise, the R5900-specific pipeline 1 instruction variants MULT1,
MULTU1, DIV1, DIVU1, MADD1, MADDU1, MFHI1, MFLO1, MTHI1 and MTLO1
are omitted here as well.

Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Fredrik Noring <noring@nocrew.org>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>

diff --git a/target/mips/translate.c b/target/mips/translate.c
index 1c0400c4ae7e667d30f685c0d2145fc47585740c..3dc6d80ce174f196f932588be9bb38f4105272d3 100644 (file)
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -4766,6 +4766,78 @@ static void gen_muldiv(DisasContext *ctx, uint32_t opc,
     tcg_temp_free(t1);
 }
 
+/*
+ * These MULT and MULTU instructions implemented in for example the
+ * Toshiba/Sony R5900 and the Toshiba TX19, TX39 and TX79 core
+ * architectures are special three-operand variants with the syntax
+ *
+ *     MULT[U] rd, rs, rt
+ *
+ * such that
+ *
+ *     (rd, LO, HI) <- rs * rt
+ *
+ * where the low-order 32-bits of the result is placed into both the
+ * GPR rd and the special register LO. The high-order 32-bits of the
+ * result is placed into the special register HI.
+ *
+ * If the GPR rd is omitted in assembly language, it is taken to be 0,
+ * which is the zero register that always reads as 0.
+ */
+static void gen_mul_txx9(DisasContext *ctx, uint32_t opc,
+                         int rd, int rs, int rt)
+{
+    TCGv t0 = tcg_temp_new();
+    TCGv t1 = tcg_temp_new();
+    int acc = 0;
+
+    gen_load_gpr(t0, rs);
+    gen_load_gpr(t1, rt);
+
+    switch (opc) {
+    case OPC_MULT:
+        {
+            TCGv_i32 t2 = tcg_temp_new_i32();
+            TCGv_i32 t3 = tcg_temp_new_i32();
+            tcg_gen_trunc_tl_i32(t2, t0);
+            tcg_gen_trunc_tl_i32(t3, t1);
+            tcg_gen_muls2_i32(t2, t3, t2, t3);
+            if (rd) {
+                tcg_gen_ext_i32_tl(cpu_gpr[rd], t2);
+            }
+            tcg_gen_ext_i32_tl(cpu_LO[acc], t2);
+            tcg_gen_ext_i32_tl(cpu_HI[acc], t3);
+            tcg_temp_free_i32(t2);
+            tcg_temp_free_i32(t3);
+        }
+        break;
+    case OPC_MULTU:
+        {
+            TCGv_i32 t2 = tcg_temp_new_i32();
+            TCGv_i32 t3 = tcg_temp_new_i32();
+            tcg_gen_trunc_tl_i32(t2, t0);
+            tcg_gen_trunc_tl_i32(t3, t1);
+            tcg_gen_mulu2_i32(t2, t3, t2, t3);
+            if (rd) {
+                tcg_gen_ext_i32_tl(cpu_gpr[rd], t2);
+            }
+            tcg_gen_ext_i32_tl(cpu_LO[acc], t2);
+            tcg_gen_ext_i32_tl(cpu_HI[acc], t3);
+            tcg_temp_free_i32(t2);
+            tcg_temp_free_i32(t3);
+        }
+        break;
+    default:
+        MIPS_INVAL("mul TXx9");
+        generate_exception_end(ctx, EXCP_RI);
+        goto out;
+    }
+
+ out:
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+
 static void gen_mul_vr54xx (DisasContext *ctx, uint32_t opc,
                             int rd, int rs, int rt)
 {
@@ -23490,6 +23562,8 @@ static void decode_opc_special_legacy(CPUMIPSState *env, DisasContext *ctx)
             check_insn(ctx, INSN_VR54XX);
             op1 = MASK_MUL_VR54XX(ctx->opcode);
             gen_mul_vr54xx(ctx, op1, rd, rs, rt);
+        } else if (ctx->insn_flags & INSN_R5900) {
+            gen_mul_txx9(ctx, op1, rd, rs, rt);
         } else {
             gen_muldiv(ctx, op1, rd & 3, rs, rt);
         }