target-xtensa: add FP registers

There are 16 32-bit FP registers (f0 - f15), control and status user
registers (fcr, fsr).

See ISA, 4.3.10 for more details.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>

gdbstub.c

@@ -1696,6 +1696,10 @@ static int cpu_gdb_read_register(CPUXtensaState *env, uint8_t *mem_buf, int n)
         GET_REG32(env->uregs[reg->targno & 0xff]);
         break;
 
+    case 4: /*f*/
+        GET_REG32(float32_val(env->fregs[reg->targno & 0x0f]));
+        break;
+
     case 8: /*a*/
         GET_REG32(env->regs[reg->targno & 0x0f]);
         break;
@@ -1736,6 +1740,10 @@ static int cpu_gdb_write_register(CPUXtensaState *env, uint8_t *mem_buf, int n)
         env->uregs[reg->targno & 0xff] = tmp;
         break;
 
+    case 4: /*f*/
+        env->fregs[reg->targno & 0x0f] = make_float32(tmp);
+        break;
+
     case 8: /*a*/
         env->regs[reg->targno & 0x0f] = tmp;
         break;

target-xtensa/cpu.h

@@ -36,6 +36,7 @@
 #include "config.h"
 #include "qemu-common.h"
 #include "cpu-defs.h"
+#include "fpu/softfloat.h"
 
 #define TARGET_HAS_ICE 1
 
@@ -325,6 +326,8 @@ typedef struct CPUXtensaState {
     uint32_t sregs[256];
     uint32_t uregs[256];
     uint32_t phys_regs[MAX_NAREG];
+    float32 fregs[16];
+    float_status fp_status;
 
     xtensa_tlb_entry itlb[7][MAX_TLB_WAY_SIZE];
     xtensa_tlb_entry dtlb[10][MAX_TLB_WAY_SIZE];

target-xtensa/helper.h

@@ -36,4 +36,6 @@ DEF_HELPER_3(wsr_ibreaka, void, env, i32, i32)
 DEF_HELPER_3(wsr_dbreaka, void, env, i32, i32)
 DEF_HELPER_3(wsr_dbreakc, void, env, i32, i32)
 
+DEF_HELPER_2(wur_fcr, void, env, i32)
+
 #include "def-helper.h"

target-xtensa/op_helper.c

@@ -771,3 +771,16 @@ void HELPER(wsr_dbreakc)(CPUXtensaState *env, uint32_t i, uint32_t v)
     }
     env->sregs[DBREAKC + i] = v;
 }
+
+void HELPER(wur_fcr)(CPUXtensaState *env, uint32_t v)
+{
+    static const int rounding_mode[] = {
+        float_round_nearest_even,
+        float_round_to_zero,
+        float_round_up,
+        float_round_down,
+    };
+
+    env->uregs[FCR] = v & 0xfffff07f;
+    set_float_rounding_mode(rounding_mode[v & 3], &env->fp_status);
+}

target-xtensa/translate.c

@@ -70,6 +70,7 @@ typedef struct DisasContext {
 static TCGv_ptr cpu_env;
 static TCGv_i32 cpu_pc;
 static TCGv_i32 cpu_R[16];
+static TCGv_i32 cpu_FR[16];
 static TCGv_i32 cpu_SR[256];
 static TCGv_i32 cpu_UR[256];
 
@@ -155,6 +156,12 @@ void xtensa_translate_init(void)
         "ar8", "ar9", "ar10", "ar11",
         "ar12", "ar13", "ar14", "ar15",
     };
+    static const char * const fregnames[] = {
+        "f0", "f1", "f2", "f3",
+        "f4", "f5", "f6", "f7",
+        "f8", "f9", "f10", "f11",
+        "f12", "f13", "f14", "f15",
+    };
     int i;
 
     cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");
@@ -167,6 +174,12 @@ void xtensa_translate_init(void)
                 regnames[i]);
     }
 
+    for (i = 0; i < 16; i++) {
+        cpu_FR[i] = tcg_global_mem_new_i32(TCG_AREG0,
+                offsetof(CPUXtensaState, fregs[i]),
+                fregnames[i]);
+    }
+
     for (i = 0; i < 256; ++i) {
         if (sregnames[i]) {
             cpu_SR[i] = tcg_global_mem_new_i32(TCG_AREG0,
@@ -692,6 +705,23 @@ static void gen_wsr(DisasContext *dc, uint32_t sr, TCGv_i32 s)
     }
 }
 
+static void gen_wur(uint32_t ur, TCGv_i32 s)
+{
+    switch (ur) {
+    case FCR:
+        gen_helper_wur_fcr(cpu_env, s);
+        break;
+
+    case FSR:
+        tcg_gen_andi_i32(cpu_UR[ur], s, 0xffffff80);
+        break;
+
+    default:
+        tcg_gen_mov_i32(cpu_UR[ur], s);
+        break;
+    }
+}
+
 static void gen_load_store_alignment(DisasContext *dc, int shift,
         TCGv_i32 addr, bool no_hw_alignment)
 {
@@ -1761,13 +1791,11 @@ static void disas_xtensa_insn(DisasContext *dc)
 
             case 15: /*WUR*/
                 gen_window_check1(dc, RRR_T);
-                {
+                if (uregnames[RSR_SR]) {
-                    if (uregnames[RSR_SR]) {
+                    gen_wur(RSR_SR, cpu_R[RRR_T]);
-                        tcg_gen_mov_i32(cpu_UR[RSR_SR], cpu_R[RRR_T]);
+                } else {
-                    } else {
+                    qemu_log("WUR %d not implemented, ", RSR_SR);
-                        qemu_log("WUR %d not implemented, ", RSR_SR);
+                    TBD();
-                        TBD();
-                    }
                 }
                 break;
 
@@ -2730,6 +2758,16 @@ void cpu_dump_state(CPUXtensaState *env, FILE *f, fprintf_function cpu_fprintf,
         cpu_fprintf(f, "AR%02d=%08x%c", i, env->phys_regs[i],
                 (i % 4) == 3 ? '\n' : ' ');
     }
+
+    if (xtensa_option_enabled(env->config, XTENSA_OPTION_FP_COPROCESSOR)) {
+        cpu_fprintf(f, "\n");
+
+        for (i = 0; i < 16; ++i) {
+            cpu_fprintf(f, "F%02d=%08x (%+10.8e)%c", i,
+                    float32_val(env->fregs[i]),
+                    *(float *)&env->fregs[i], (i % 2) == 1 ? '\n' : ' ');
+        }
+    }
 }
 
 void restore_state_to_opc(CPUXtensaState *env, TranslationBlock *tb, int pc_pos)