- Add FTOU, CRCN, FTOHP, and HPTOF insns

-----BEGIN PGP SIGNATURE-----
 
 iQJTBAABCgA9FiEEbmNqfoPy3Qz6bm43CtLGOWtpyhQFAmUWb2sfHGtiYXN0aWFu
 QG1haWwudW5pLXBhZGVyYm9ybi5kZQAKCRAK0sY5a2nKFPn0D/0S+Zth2okyfe6H
 YdoFB49PWlcafIvZHr1TDswp3LvSDnrjHLJfEW1Gx3mtDkw+/7uid0eMTQ8sDlxJ
 t7spJdZDZ5dkm+9K5MzGkW0zo0jDY6kbS1A3HJRPcpJJJk4zBBL1K4KC1FBUD6IK
 7n41f5vExgWhIhOgZmT9WTMbBfh73/+Cu8h6M9RAI1VI0O6N5jOETpKTBFsPOx+A
 Kd429cB1c9QeAj0iEXdMn2/Xg2cAII86jrOcYkLYltxir/r6Cia9hfp/F6OXpcZI
 QqKzn11djvbCCL7m9OXhuI3ZP+TIcX7QOabSstfghHlNG1qs/RkXwIRqKHsfRXNG
 nywBTjwIDSiZ4cbZVJ6OjXxbU9OBRkmDgh+SYEVMlFi4E+t3WeTMC8gxUsjfITpK
 JXFoduN2P0yKRjkWQ2OSQ7xX4StFPikXBH1eC8RNnW4IY00wMiJ0tM/0+j+qJLLM
 Ft/bceIZhnGs+axN0jF1EtR03uLZ0kmy3YqsH/KnBnufrag3ytpC/kAtl9Scd6m+
 N4pAT9cfgxqXv/yXAKGupoNPwPGvvSKV6XQTJt2Hn7PBadHWlvlBkgYqGIejpHDM
 x9EghA8o4q5rTu9zTqBv36bOHJEDbJhmq5dYqJTS/q1ORjnWQQsLxv+6XGN3wrbb
 OuexPdD8fH3mWrjeJJ3KDKojOYyGyg==
 =gUyL
 -----END PGP SIGNATURE-----

Merge tag 'pull-tricore-20230929' of https://github.com/bkoppelmann/qemu into staging

- Add FTOU, CRCN, FTOHP, and HPTOF insns

# -----BEGIN PGP SIGNATURE-----
#
# iQJTBAABCgA9FiEEbmNqfoPy3Qz6bm43CtLGOWtpyhQFAmUWb2sfHGtiYXN0aWFu
# QG1haWwudW5pLXBhZGVyYm9ybi5kZQAKCRAK0sY5a2nKFPn0D/0S+Zth2okyfe6H
# YdoFB49PWlcafIvZHr1TDswp3LvSDnrjHLJfEW1Gx3mtDkw+/7uid0eMTQ8sDlxJ
# t7spJdZDZ5dkm+9K5MzGkW0zo0jDY6kbS1A3HJRPcpJJJk4zBBL1K4KC1FBUD6IK
# 7n41f5vExgWhIhOgZmT9WTMbBfh73/+Cu8h6M9RAI1VI0O6N5jOETpKTBFsPOx+A
# Kd429cB1c9QeAj0iEXdMn2/Xg2cAII86jrOcYkLYltxir/r6Cia9hfp/F6OXpcZI
# QqKzn11djvbCCL7m9OXhuI3ZP+TIcX7QOabSstfghHlNG1qs/RkXwIRqKHsfRXNG
# nywBTjwIDSiZ4cbZVJ6OjXxbU9OBRkmDgh+SYEVMlFi4E+t3WeTMC8gxUsjfITpK
# JXFoduN2P0yKRjkWQ2OSQ7xX4StFPikXBH1eC8RNnW4IY00wMiJ0tM/0+j+qJLLM
# Ft/bceIZhnGs+axN0jF1EtR03uLZ0kmy3YqsH/KnBnufrag3ytpC/kAtl9Scd6m+
# N4pAT9cfgxqXv/yXAKGupoNPwPGvvSKV6XQTJt2Hn7PBadHWlvlBkgYqGIejpHDM
# x9EghA8o4q5rTu9zTqBv36bOHJEDbJhmq5dYqJTS/q1ORjnWQQsLxv+6XGN3wrbb
# OuexPdD8fH3mWrjeJJ3KDKojOYyGyg==
# =gUyL
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 29 Sep 2023 02:32:11 EDT
# gpg:                using RSA key 6E636A7E83F2DD0CFA6E6E370AD2C6396B69CA14
# gpg:                issuer "kbastian@mail.uni-paderborn.de"
# gpg: Good signature from "Bastian Koppelmann <kbastian@mail.uni-paderborn.de>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6E63 6A7E 83F2 DD0C FA6E  6E37 0AD2 C639 6B69 CA14

* tag 'pull-tricore-20230929' of https://github.com/bkoppelmann/qemu:
  target/tricore: Change effective address (ea) to target_ulong
  target/tricore: Remove CSFRs from cpu.h
  tests/tcg: Reset result register after each test
  hw/tricore: Log failing test in testdevice
  tests/tcg/tricore: Extended and non-extened regs now match
  target/tricore: Fix FTOUZ being ISA v1.3.1 up
  target/tricore: Replace cpu_*_code with translator_*
  target/tricore: Swap src and dst reg for RCRR_INSERT
  target/tricore: Fix RCPW/RRPW_INSERT insns for width = 0
  target/tricore: Implement hptof insn
  target/tricore: Implement ftohp insn
  target/tricore: Clarify special case for FTOUZ insn
  target/tricore: Implement FTOU insn
  target/tricore: Correctly handle FPU RM from PSW
  target/tricore: Implement CRCN insn
  tests/tcg/tricore: Bump cpu to tc37x

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

hw/tricore/tricore_testdevice.c

@@ -16,6 +16,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "hw/qdev-properties.h"
 #include "hw/tricore/tricore_testdevice.h"
@@ -23,6 +24,9 @@
 static void tricore_testdevice_write(void *opaque, hwaddr offset,
                                       uint64_t value, unsigned size)
 {
+    if (value != 0) {
+        qemu_log_mask(LOG_GUEST_ERROR, "Test %" PRIu64 " failed!\n", value);
+    }
     exit(value);
 }
 

target/tricore/cpu.h

@@ -30,150 +30,25 @@ typedef struct CPUArchState {
     /* GPR Register */
     uint32_t gpr_a[16];
     uint32_t gpr_d[16];
-    /* CSFR Register */
-    uint32_t PCXI;
 /* Frequently accessed PSW_USB bits are stored separately for efficiency.
        This contains all the other bits.  Use psw_{read,write} to access
        the whole PSW.  */
     uint32_t PSW;
-
+    /* PSW flag cache for faster execution */
-    /* PSW flag cache for faster execution
-    */
     uint32_t PSW_USB_C;
     uint32_t PSW_USB_V;   /* Only if bit 31 set, then flag is set  */
     uint32_t PSW_USB_SV;  /* Only if bit 31 set, then flag is set  */
     uint32_t PSW_USB_AV;  /* Only if bit 31 set, then flag is set. */
     uint32_t PSW_USB_SAV; /* Only if bit 31 set, then flag is set. */
 
-    uint32_t PC;
+#define R(ADDR, NAME, FEATURE) uint32_t NAME;
-    uint32_t SYSCON;
+#define A(ADDR, NAME, FEATURE) uint32_t NAME;
-    uint32_t CPU_ID;
+#define E(ADDR, NAME, FEATURE) uint32_t NAME;
-    uint32_t CORE_ID;
+#include "csfr.h.inc"
-    uint32_t BIV;
+#undef R
-    uint32_t BTV;
+#undef A
-    uint32_t ISP;
+#undef E
-    uint32_t ICR;
-    uint32_t FCX;
-    uint32_t LCX;
-    uint32_t COMPAT;
 
-    /* Mem Protection Register */
-    uint32_t DPR0_0L;
-    uint32_t DPR0_0U;
-    uint32_t DPR0_1L;
-    uint32_t DPR0_1U;
-    uint32_t DPR0_2L;
-    uint32_t DPR0_2U;
-    uint32_t DPR0_3L;
-    uint32_t DPR0_3U;
-
-    uint32_t DPR1_0L;
-    uint32_t DPR1_0U;
-    uint32_t DPR1_1L;
-    uint32_t DPR1_1U;
-    uint32_t DPR1_2L;
-    uint32_t DPR1_2U;
-    uint32_t DPR1_3L;
-    uint32_t DPR1_3U;
-
-    uint32_t DPR2_0L;
-    uint32_t DPR2_0U;
-    uint32_t DPR2_1L;
-    uint32_t DPR2_1U;
-    uint32_t DPR2_2L;
-    uint32_t DPR2_2U;
-    uint32_t DPR2_3L;
-    uint32_t DPR2_3U;
-
-    uint32_t DPR3_0L;
-    uint32_t DPR3_0U;
-    uint32_t DPR3_1L;
-    uint32_t DPR3_1U;
-    uint32_t DPR3_2L;
-    uint32_t DPR3_2U;
-    uint32_t DPR3_3L;
-    uint32_t DPR3_3U;
-
-    uint32_t CPR0_0L;
-    uint32_t CPR0_0U;
-    uint32_t CPR0_1L;
-    uint32_t CPR0_1U;
-    uint32_t CPR0_2L;
-    uint32_t CPR0_2U;
-    uint32_t CPR0_3L;
-    uint32_t CPR0_3U;
-
-    uint32_t CPR1_0L;
-    uint32_t CPR1_0U;
-    uint32_t CPR1_1L;
-    uint32_t CPR1_1U;
-    uint32_t CPR1_2L;
-    uint32_t CPR1_2U;
-    uint32_t CPR1_3L;
-    uint32_t CPR1_3U;
-
-    uint32_t CPR2_0L;
-    uint32_t CPR2_0U;
-    uint32_t CPR2_1L;
-    uint32_t CPR2_1U;
-    uint32_t CPR2_2L;
-    uint32_t CPR2_2U;
-    uint32_t CPR2_3L;
-    uint32_t CPR2_3U;
-
-    uint32_t CPR3_0L;
-    uint32_t CPR3_0U;
-    uint32_t CPR3_1L;
-    uint32_t CPR3_1U;
-    uint32_t CPR3_2L;
-    uint32_t CPR3_2U;
-    uint32_t CPR3_3L;
-    uint32_t CPR3_3U;
-
-    uint32_t DPM0;
-    uint32_t DPM1;
-    uint32_t DPM2;
-    uint32_t DPM3;
-
-    uint32_t CPM0;
-    uint32_t CPM1;
-    uint32_t CPM2;
-    uint32_t CPM3;
-
-    /* Memory Management Registers */
-    uint32_t MMU_CON;
-    uint32_t MMU_ASI;
-    uint32_t MMU_TVA;
-    uint32_t MMU_TPA;
-    uint32_t MMU_TPX;
-    uint32_t MMU_TFA;
-    /* {1.3.1 only */
-    uint32_t BMACON;
-    uint32_t SMACON;
-    uint32_t DIEAR;
-    uint32_t DIETR;
-    uint32_t CCDIER;
-    uint32_t MIECON;
-    uint32_t PIEAR;
-    uint32_t PIETR;
-    uint32_t CCPIER;
-    /*} */
-    /* Debug Registers */
-    uint32_t DBGSR;
-    uint32_t EXEVT;
-    uint32_t CREVT;
-    uint32_t SWEVT;
-    uint32_t TR0EVT;
-    uint32_t TR1EVT;
-    uint32_t DMS;
-    uint32_t DCX;
-    uint32_t DBGTCR;
-    uint32_t CCTRL;
-    uint32_t CCNT;
-    uint32_t ICNT;
-    uint32_t M1CNT;
-    uint32_t M2CNT;
-    uint32_t M3CNT;
     /* Floating Point Registers */
     float_status fp_status;
 

target/tricore/fpu_helper.c

@@ -373,6 +373,80 @@ uint32_t helper_ftoi(CPUTriCoreState *env, uint32_t arg)
     return (uint32_t)result;
 }
 
+uint32_t helper_hptof(CPUTriCoreState *env, uint32_t arg)
+{
+    float16 f_arg = make_float16(arg);
+    uint32_t result = 0;
+    int32_t flags = 0;
+
+    /*
+     * if we have any NAN we need to move the top 2 and lower 8 input mantissa
+     * bits to the top 2 and lower 8 output mantissa bits respectively.
+     * Softfloat on the other hand uses the top 10 mantissa bits.
+     */
+    if (float16_is_any_nan(f_arg)) {
+        if (float16_is_signaling_nan(f_arg, &env->fp_status)) {
+            flags |= float_flag_invalid;
+        }
+        result = 0;
+        result = float32_set_sign(result, f_arg >> 15);
+        result = deposit32(result, 23, 8, 0xff);
+        result = deposit32(result, 21, 2, extract32(f_arg, 8, 2));
+        result = deposit32(result, 0, 8, extract32(f_arg, 0, 8));
+    } else {
+        set_flush_inputs_to_zero(0, &env->fp_status);
+        result = float16_to_float32(f_arg, true, &env->fp_status);
+        set_flush_inputs_to_zero(1, &env->fp_status);
+        flags = f_get_excp_flags(env);
+    }
+
+    if (flags) {
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+
+    return result;
+}
+
+uint32_t helper_ftohp(CPUTriCoreState *env, uint32_t arg)
+{
+    float32 f_arg = make_float32(arg);
+    uint32_t result = 0;
+    int32_t flags = 0;
+
+    /*
+     * if we have any NAN we need to move the top 2 and lower 8 input mantissa
+     * bits to the top 2 and lower 8 output mantissa bits respectively.
+     * Softfloat on the other hand uses the top 10 mantissa bits.
+     */
+    if (float32_is_any_nan(f_arg)) {
+        if (float32_is_signaling_nan(f_arg, &env->fp_status)) {
+            flags |= float_flag_invalid;
+        }
+        result = float16_set_sign(result, arg >> 31);
+        result = deposit32(result, 10, 5, 0x1f);
+        result = deposit32(result, 8, 2, extract32(arg, 21, 2));
+        result = deposit32(result, 0, 8, extract32(arg, 0, 8));
+        if (extract32(result, 0, 10) == 0) {
+            result |= (1 << 8);
+        }
+    } else {
+        set_flush_to_zero(0, &env->fp_status);
+        result = float32_to_float16(f_arg, true, &env->fp_status);
+        set_flush_to_zero(1, &env->fp_status);
+        flags = f_get_excp_flags(env);
+    }
+
+    if (flags) {
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+
+    return result;
+}
+
 uint32_t helper_itof(CPUTriCoreState *env, uint32_t arg)
 {
     float32 f_result;
@@ -429,6 +503,38 @@ uint32_t helper_ftoiz(CPUTriCoreState *env, uint32_t arg)
     return result;
 }
 
+uint32_t helper_ftou(CPUTriCoreState *env, uint32_t arg)
+{
+    float32 f_arg = make_float32(arg);
+    uint32_t result;
+    int32_t flags = 0;
+
+    result = float32_to_uint32(f_arg, &env->fp_status);
+
+    flags = f_get_excp_flags(env);
+    if (flags & float_flag_invalid) {
+        flags &= ~float_flag_inexact;
+        if (float32_is_any_nan(f_arg)) {
+            result = 0;
+        }
+    /*
+     * we need to check arg < 0.0 before rounding as TriCore needs to raise
+     * float_flag_invalid as well. For instance, when we have a negative
+     * exponent and sign, softfloat would only raise float_flat_inexact.
+     */
+    } else if (float32_lt_quiet(f_arg, 0, &env->fp_status)) {
+        flags = float_flag_invalid;
+        result = 0;
+    }
+
+    if (flags) {
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+    return result;
+}
+
 uint32_t helper_ftouz(CPUTriCoreState *env, uint32_t arg)
 {
     float32 f_arg = make_float32(arg);
@@ -443,6 +549,11 @@ uint32_t helper_ftouz(CPUTriCoreState *env, uint32_t arg)
         if (float32_is_any_nan(f_arg)) {
             result = 0;
         }
+    /*
+     * we need to check arg < 0.0 before rounding as TriCore needs to raise
+     * float_flag_invalid as well. For instance, when we have a negative
+     * exponent and sign, softfloat would only raise float_flat_inexact.
+     */
     } else if (float32_lt_quiet(f_arg, 0, &env->fp_status)) {
         flags = float_flag_invalid;
         result = 0;

target/tricore/helper.c

@@ -120,16 +120,31 @@ void tricore_cpu_list(void)
 
 void fpu_set_state(CPUTriCoreState *env)
 {
-    set_float_rounding_mode(env->PSW & MASK_PSW_FPU_RM, &env->fp_status);
+    switch (extract32(env->PSW, 24, 2)) {
+    case 0:
+        set_float_rounding_mode(float_round_nearest_even, &env->fp_status);
+        break;
+    case 1:
+        set_float_rounding_mode(float_round_up, &env->fp_status);
+        break;
+    case 2:
+        set_float_rounding_mode(float_round_down, &env->fp_status);
+        break;
+    case 3:
+        set_float_rounding_mode(float_round_to_zero, &env->fp_status);
+        break;
+    }
+
     set_flush_inputs_to_zero(1, &env->fp_status);
     set_flush_to_zero(1, &env->fp_status);
+    set_float_detect_tininess(float_tininess_before_rounding, &env->fp_status);
     set_default_nan_mode(1, &env->fp_status);
 }
 
 uint32_t psw_read(CPUTriCoreState *env)
 {
     /* clear all USB bits */
-    env->PSW &= 0x6ffffff;
+    env->PSW &= 0x7ffffff;
     /* now set them from the cache */
     env->PSW |= ((env->PSW_USB_C != 0) << 31);
     env->PSW |= ((env->PSW_USB_V   & (1 << 31))  >> 1);

target/tricore/helper.h

@@ -111,9 +111,12 @@ DEF_HELPER_4(fmsub, i32, env, i32, i32, i32)
 DEF_HELPER_3(fcmp, i32, env, i32, i32)
 DEF_HELPER_2(qseed, i32, env, i32)
 DEF_HELPER_2(ftoi, i32, env, i32)
+DEF_HELPER_2(ftohp, i32, env, i32)
+DEF_HELPER_2(hptof, i32, env, i32)
 DEF_HELPER_2(itof, i32, env, i32)
 DEF_HELPER_2(utof, i32, env, i32)
 DEF_HELPER_2(ftoiz, i32, env, i32)
+DEF_HELPER_2(ftou, i32, env, i32)
 DEF_HELPER_2(ftouz, i32, env, i32)
 DEF_HELPER_2(updfl, void, env, i32)
 /* dvinit */
@@ -134,6 +137,7 @@ DEF_HELPER_FLAGS_5(mulr_h, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32, i32, i32)
 DEF_HELPER_FLAGS_2(crc32b, TCG_CALL_NO_RWG_SE, i32, i32, i32)
 DEF_HELPER_FLAGS_2(crc32_be, TCG_CALL_NO_RWG_SE, i32, i32, i32)
 DEF_HELPER_FLAGS_2(crc32_le, TCG_CALL_NO_RWG_SE, i32, i32, i32)
+DEF_HELPER_FLAGS_3(crcn, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
 DEF_HELPER_FLAGS_2(shuffle, TCG_CALL_NO_RWG_SE, i32, i32, i32)
 /* CSA */
 DEF_HELPER_2(call, void, env, i32)

target/tricore/op_helper.c

@@ -2308,6 +2308,69 @@ uint32_t helper_crc32_le(uint32_t arg0, uint32_t arg1)
     return crc32(arg1, buf, 4);
 }
 
+static uint32_t crc_div(uint32_t crc_in, uint32_t data, uint32_t gen,
+                        uint32_t n, uint32_t m)
+{
+    uint32_t i;
+
+    data = data << n;
+    for (i = 0; i < m; i++) {
+        if (crc_in & (1u << (n - 1))) {
+            crc_in <<= 1;
+            if (data & (1u << (m - 1))) {
+                crc_in++;
+            }
+            crc_in ^= gen;
+        } else {
+            crc_in <<= 1;
+            if (data & (1u << (m - 1))) {
+                crc_in++;
+            }
+        }
+        data <<= 1;
+    }
+
+    return crc_in;
+}
+
+uint32_t helper_crcn(uint32_t arg0, uint32_t arg1, uint32_t arg2)
+{
+    uint32_t crc_out, crc_in;
+    uint32_t n = extract32(arg0, 12, 4) + 1;
+    uint32_t gen = extract32(arg0, 16, n);
+    uint32_t inv = extract32(arg0, 9, 1);
+    uint32_t le = extract32(arg0, 8, 1);
+    uint32_t m = extract32(arg0, 0, 3) + 1;
+    uint32_t data = extract32(arg1, 0, m);
+    uint32_t seed = extract32(arg2, 0, n);
+
+    if (le == 1) {
+        if (m == 0) {
+            data = 0;
+        } else {
+            data = revbit32(data) >> (32 - m);
+        }
+    }
+
+    if (inv == 1) {
+        seed = ~seed;
+    }
+
+    if (m > n) {
+        crc_in = (data >> (m - n)) ^ seed;
+    } else {
+        crc_in = (data << (n - m)) ^ seed;
+    }
+
+    crc_out = crc_div(crc_in, data, gen, n, m);
+
+    if (inv) {
+        crc_out = ~crc_out;
+    }
+
+    return extract32(crc_out, 0, n);
+}
+
 uint32_t helper_shuffle(uint32_t arg0, uint32_t arg1)
 {
     uint32_t resb;
@@ -2395,7 +2458,7 @@ static bool cdc_zero(target_ulong *psw)
     return count == 0;
 }
 
-static void save_context_upper(CPUTriCoreState *env, int ea)
+static void save_context_upper(CPUTriCoreState *env, target_ulong ea)
 {
     cpu_stl_data(env, ea, env->PCXI);
     cpu_stl_data(env, ea+4, psw_read(env));
@@ -2415,7 +2478,7 @@ static void save_context_upper(CPUTriCoreState *env, int ea)
     cpu_stl_data(env, ea+60, env->gpr_d[15]);
 }
 
-static void save_context_lower(CPUTriCoreState *env, int ea)
+static void save_context_lower(CPUTriCoreState *env, target_ulong ea)
 {
     cpu_stl_data(env, ea, env->PCXI);
     cpu_stl_data(env, ea+4, env->gpr_a[11]);
@@ -2435,7 +2498,7 @@ static void save_context_lower(CPUTriCoreState *env, int ea)
     cpu_stl_data(env, ea+60, env->gpr_d[7]);
 }
 
-static void restore_context_upper(CPUTriCoreState *env, int ea,
+static void restore_context_upper(CPUTriCoreState *env, target_ulong ea,
                                   target_ulong *new_PCXI, target_ulong *new_PSW)
 {
     *new_PCXI = cpu_ldl_data(env, ea);
@@ -2456,7 +2519,7 @@ static void restore_context_upper(CPUTriCoreState *env, int ea,
     env->gpr_d[15] = cpu_ldl_data(env, ea+60);
 }
 
-static void restore_context_lower(CPUTriCoreState *env, int ea,
+static void restore_context_lower(CPUTriCoreState *env, target_ulong ea,
                                   target_ulong *ra, target_ulong *pcxi)
 {
     *pcxi = cpu_ldl_data(env, ea);
@@ -2700,26 +2763,26 @@ void helper_rfm(CPUTriCoreState *env)
     }
 }
 
-void helper_ldlcx(CPUTriCoreState *env, uint32_t ea)
+void helper_ldlcx(CPUTriCoreState *env, target_ulong ea)
 {
     uint32_t dummy;
     /* insn doesn't load PCXI and RA */
     restore_context_lower(env, ea, &dummy, &dummy);
 }
 
-void helper_lducx(CPUTriCoreState *env, uint32_t ea)
+void helper_lducx(CPUTriCoreState *env, target_ulong ea)
 {
     uint32_t dummy;
     /* insn doesn't load PCXI and PSW */
     restore_context_upper(env, ea, &dummy, &dummy);
 }
 
-void helper_stlcx(CPUTriCoreState *env, uint32_t ea)
+void helper_stlcx(CPUTriCoreState *env, target_ulong ea)
 {
     save_context_lower(env, ea);
 }
 
-void helper_stucx(CPUTriCoreState *env, uint32_t ea)
+void helper_stucx(CPUTriCoreState *env, target_ulong ea)
 {
     save_context_upper(env, ea);
 }

target/tricore/translate.c

@@ -5310,8 +5310,11 @@ static void decode_rcpw_insert(DisasContext *ctx)
         }
         break;
     case OPC2_32_RCPW_INSERT:
+        /* tcg_gen_deposit_tl() does not handle the case of width = 0 */
+        if (width == 0) {
+            tcg_gen_mov_tl(cpu_gpr_d[r2], cpu_gpr_d[r1]);
         /* if pos + width > 32 undefined result */
-        if (pos + width <= 32) {
+        } else if (pos + width <= 32) {
             temp = tcg_constant_i32(const4);
             tcg_gen_deposit_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], temp, pos, width);
         }
@@ -6260,6 +6263,20 @@ static void decode_rr_divide(DisasContext *ctx)
     case OPC2_32_RR_DIV_F:
         gen_helper_fdiv(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1], cpu_gpr_d[r2]);
         break;
+    case OPC2_32_RR_FTOHP:
+        if (has_feature(ctx, TRICORE_FEATURE_162)) {
+            gen_helper_ftohp(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
+        break;
+   case OPC2_32_RR_HPTOF:
+        if (has_feature(ctx, TRICORE_FEATURE_162)) {
+            gen_helper_hptof(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
+        break;
     case OPC2_32_RR_CMP_F:
         gen_helper_fcmp(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1], cpu_gpr_d[r2]);
         break;
@@ -6269,8 +6286,15 @@ static void decode_rr_divide(DisasContext *ctx)
     case OPC2_32_RR_ITOF:
         gen_helper_itof(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
         break;
+    case OPC2_32_RR_FTOU:
+        gen_helper_ftou(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        break;
     case OPC2_32_RR_FTOUZ:
-        gen_helper_ftouz(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        if (has_feature(ctx, TRICORE_FEATURE_131)) {
+            gen_helper_ftouz(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
         break;
     case OPC2_32_RR_UPDFL:
         gen_helper_updfl(cpu_env, cpu_gpr_d[r1]);
@@ -6554,7 +6578,10 @@ static void decode_rrpw_extract_insert(DisasContext *ctx)
 
         break;
     case OPC2_32_RRPW_INSERT:
-        if (pos + width <= 32) {
+        /* tcg_gen_deposit_tl() does not handle the case of width = 0 */
+        if (width == 0) {
+            tcg_gen_mov_tl(cpu_gpr_d[r3], cpu_gpr_d[r1]);
+        } else if (pos + width <= 32) {
             tcg_gen_deposit_tl(cpu_gpr_d[r3], cpu_gpr_d[r1], cpu_gpr_d[r2],
                                pos, width);
         }
@@ -6669,6 +6696,14 @@ static void decode_rrr_divide(DisasContext *ctx)
         gen_helper_pack(cpu_gpr_d[r4], cpu_PSW_C, cpu_gpr_d[r3],
                         cpu_gpr_d[r3+1], cpu_gpr_d[r1]);
         break;
+    case OPC2_32_RRR_CRCN:
+        if (has_feature(ctx, TRICORE_FEATURE_162)) {
+            gen_helper_crcn(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r2],
+                            cpu_gpr_d[r3]);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
+        break;
     case OPC2_32_RRR_ADD_F:
         gen_helper_fadd(cpu_gpr_d[r4], cpu_env, cpu_gpr_d[r1], cpu_gpr_d[r3]);
         break;
@@ -8192,12 +8227,12 @@ static void decode_32Bit_opc(DisasContext *ctx)
         temp2 = tcg_temp_new(); /* width*/
         temp3 = tcg_temp_new(); /* pos */
 
-        CHECK_REG_PAIR(r3);
+        CHECK_REG_PAIR(r2);
 
-        tcg_gen_andi_tl(temp2, cpu_gpr_d[r3+1], 0x1f);
+        tcg_gen_andi_tl(temp2, cpu_gpr_d[r2 + 1], 0x1f);
-        tcg_gen_andi_tl(temp3, cpu_gpr_d[r3], 0x1f);
+        tcg_gen_andi_tl(temp3, cpu_gpr_d[r2], 0x1f);
 
-        gen_insert(cpu_gpr_d[r2], cpu_gpr_d[r1], temp, temp2, temp3);
+        gen_insert(cpu_gpr_d[r3], cpu_gpr_d[r1], temp, temp2, temp3);
         break;
 /* RCRW Format */
     case OPCM_32_RCRW_MASK_INSERT:
@@ -8367,7 +8402,7 @@ static bool insn_crosses_page(CPUTriCoreState *env, DisasContext *ctx)
      * 4 bytes from the page boundary, so we cross the page if the first
      * 16 bits indicate that this is a 32 bit insn.
      */
-    uint16_t insn = cpu_lduw_code(env, ctx->base.pc_next);
+    uint16_t insn = translator_lduw(env, &ctx->base, ctx->base.pc_next);
 
     return !tricore_insn_is_16bit(insn);
 }
@@ -8380,14 +8415,15 @@ static void tricore_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
     uint16_t insn_lo;
     bool is_16bit;
 
-    insn_lo = cpu_lduw_code(env, ctx->base.pc_next);
+    insn_lo = translator_lduw(env, &ctx->base, ctx->base.pc_next);
     is_16bit = tricore_insn_is_16bit(insn_lo);
     if (is_16bit) {
         ctx->opcode = insn_lo;
         ctx->pc_succ_insn = ctx->base.pc_next + 2;
         decode_16Bit_opc(ctx);
     } else {
-        uint32_t insn_hi = cpu_lduw_code(env, ctx->base.pc_next + 2);
+        uint32_t insn_hi = translator_lduw(env, &ctx->base,
+                                           ctx->base.pc_next + 2);
         ctx->opcode = insn_hi << 16 | insn_lo;
         ctx->pc_succ_insn = ctx->base.pc_next + 4;
         decode_32Bit_opc(ctx);

target/tricore/tricore-opcodes.h

@@ -1152,6 +1152,8 @@ enum {
     OPC2_32_RR_ITOF                              = 0x14,
     OPC2_32_RR_CMP_F                             = 0x00,
     OPC2_32_RR_FTOIZ                             = 0x13,
+    OPC2_32_RR_FTOHP                             = 0x25, /* 1.6.2 only */
+    OPC2_32_RR_HPTOF                             = 0x24, /* 1.6.2 only */
     OPC2_32_RR_FTOQ31                            = 0x11,
     OPC2_32_RR_FTOQ31Z                           = 0x18,
     OPC2_32_RR_FTOU                              = 0x12,
@@ -1247,6 +1249,7 @@ enum {
     OPC2_32_RRR_SUB_F                            = 0x03,
     OPC2_32_RRR_MADD_F                           = 0x06,
     OPC2_32_RRR_MSUB_F                           = 0x07,
+    OPC2_32_RRR_CRCN                             = 0x01, /* 1.6.2 up */
 };
 /*
  * RRR1 Format

tests/tcg/tricore/Makefile.softmmu-target

@@ -9,11 +9,15 @@ CFLAGS = -mtc162 -c -I$(TESTS_PATH)
 TESTS += test_abs.asm.tst
 TESTS += test_bmerge.asm.tst
 TESTS += test_clz.asm.tst
+TESTS += test_crcn.asm.tst
 TESTS += test_dextr.asm.tst
 TESTS += test_dvstep.asm.tst
 TESTS += test_fadd.asm.tst
 TESTS += test_fmul.asm.tst
+TESTS += test_ftohp.asm.tst
 TESTS += test_ftoi.asm.tst
+TESTS += test_ftou.asm.tst
+TESTS += test_hptof.asm.tst
 TESTS += test_imask.asm.tst
 TESTS += test_insert.asm.tst
 TESTS += test_ld_bu.asm.tst
@@ -25,7 +29,7 @@ TESTS += test_muls.asm.tst
 TESTS += test_boot_to_main.c.tst
 TESTS += test_context_save_areas.c.tst
 
-QEMU_OPTS += -M tricore_testboard -cpu tc27x -nographic -kernel
+QEMU_OPTS += -M tricore_testboard -cpu tc37x -nographic -kernel
 
 %.pS: $(ASM_TESTS_PATH)/%.S
 	$(CC) -E -o $@ $<

tests/tcg/tricore/asm/macros.h

@@ -12,31 +12,31 @@
 #define TESTDEV_ADDR 0xf0000000
 /* Register definitions */
 #define DREG_RS1 %d0
-#define DREG_RS2 %d1
+#define DREG_RS2 %d2
-#define DREG_RS3 %d2
+#define DREG_RS3 %d4
-#define DREG_CALC_RESULT %d3
+#define DREG_CALC_RESULT %d5
-#define DREG_CALC_PSW %d4
+#define DREG_CALC_PSW %d6
-#define DREG_CORRECT_PSW %d5
+#define DREG_CORRECT_PSW %d7
-#define DREG_TEMP_LI %d10
+#define DREG_TEMP_LI %d13
-#define DREG_TEMP %d11
+#define DREG_TEMP %d14
-#define DREG_TEST_NUM %d14
+#define DREG_TEST_NUM %d8
-#define DREG_CORRECT_RESULT %d15
+#define DREG_CORRECT_RESULT %d9
-#define DREG_CORRECT_RESULT_2 %d13
+#define DREG_CORRECT_RESULT_2 %d10
 
 #define AREG_ADDR %a0
 #define AREG_CORRECT_RESULT %a3
 
 #define DREG_DEV_ADDR %a15
 
-#define EREG_RS1 %e6
+#define EREG_RS1 %e0
-#define EREG_RS1_LO %d6
+#define EREG_RS1_LO %d0
-#define EREG_RS1_HI %d7
+#define EREG_RS1_HI %d1
-#define EREG_RS2 %e8
+#define EREG_RS2 %e2
-#define EREG_RS2_LO %d8
+#define EREG_RS2_LO %d2
-#define EREG_RS2_HI %d9
+#define EREG_RS2_HI %d3
-#define EREG_CALC_RESULT %e8
+#define EREG_CALC_RESULT %e6
-#define EREG_CALC_RESULT_HI %d9
+#define EREG_CALC_RESULT_LO %d6
-#define EREG_CALC_RESULT_LO %d8
+#define EREG_CALC_RESULT_HI %d7
 #define EREG_CORRECT_RESULT_LO %d0
 #define EREG_CORRECT_RESULT_HI %d1
 
@@ -46,7 +46,8 @@ test_ ## num:                                     \
     code;                                         \
     LI(DREG_CORRECT_RESULT, correct)              \
     mov DREG_TEST_NUM, num;                       \
-    jne testreg, DREG_CORRECT_RESULT, fail        \
+    jne testreg, DREG_CORRECT_RESULT, fail;       \
+    mov testreg, 0
 
 #define TEST_CASE_E(num, correct_lo, correct_hi, code...)  \
 test_ ## num:                                              \
@@ -161,6 +162,30 @@ test_ ## num:                                                    \
     insn DREG_CALC_RESULT, DREG_RS1, imm1, DREG_RS2, imm2;   \
     )
 
+#define TEST_D_DDII(insn, num, result, rs1, rs2, imm1, imm2) \
+    TEST_CASE(num, DREG_CALC_RESULT, result,                 \
+    LI(DREG_RS1, rs1);                                       \
+    LI(DREG_RS2, rs2);                                       \
+    rstv;                                                    \
+    insn DREG_CALC_RESULT, DREG_RS1, DREG_RS2, imm1, imm2;   \
+    )
+
+#define TEST_D_DIE(insn, num, result, rs1, imm1, rs2_lo, rs2_hi)\
+    TEST_CASE(num, DREG_CALC_RESULT, result,                    \
+    LI(DREG_RS1, rs1);                                          \
+    LI(EREG_RS2_LO, rs2_lo);                                    \
+    LI(EREG_RS2_HI, rs2_hi);                                    \
+    rstv;                                                       \
+    insn DREG_CALC_RESULT, DREG_RS1, imm1, EREG_RS2;            \
+    )
+
+#define TEST_D_DIII(insn, num, result, rs1, imm1, imm2, imm3)\
+    TEST_CASE(num, DREG_CALC_RESULT, result,                 \
+    LI(DREG_RS1, rs1);                                       \
+    rstv;                                                    \
+    insn DREG_CALC_RESULT, DREG_RS1, imm1, imm2, imm3;       \
+    )
+
 #define TEST_E_ED(insn, num, res_hi, res_lo, rs1_hi, rs1_lo, rs2) \
     TEST_CASE_E(num, res_lo, res_hi,                              \
     LI(EREG_RS1_LO, rs1_lo);                                      \

tests/tcg/tricore/asm/test_crcn.S

@@ -0,0 +1,9 @@
+#include "macros.h"
+.text
+.global _start
+_start:
+#                insn num    result   rs1    rs2     rs3
+#                 |     |      |      |       |       |
+    TEST_D_DDD(crcn, 1, 0x00002bed, 0x0, 0xa10ddeed, 0x0)
+
+    TEST_PASSFAIL

tests/tcg/tricore/asm/test_ftohp.S

@@ -0,0 +1,14 @@
+#include "macros.h"
+.text
+.global _start
+_start:
+    TEST_D_D(ftohp, 1, 0xffff, 0xffffffff)
+    TEST_D_D(ftohp, 2, 0xfc00, 0xff800000)
+    TEST_D_D(ftohp, 3, 0x7c00, 0x7f800000)
+    TEST_D_D(ftohp, 4, 0x0, 0x0)
+    TEST_D_D(ftohp, 5, 0x5, 0x34a43580)
+
+    #TEST_D_D_PSW(ftohp, 6, 0x400, 0x8c000b80, 0x387fee74)
+
+    TEST_PASSFAIL
+

tests/tcg/tricore/asm/test_ftou.S

@@ -0,0 +1,12 @@
+#include "macros.h"
+.text
+.global _start
+_start:
+    TEST_D_D(ftou, 1, 0x00000000, 0x1733f6c2)
+    TEST_D_D(ftou, 2, 0x00000000, 0x2c9d9cdc)
+    TEST_D_D(ftou, 3, 0xffffffff, 0x56eb7395)
+    TEST_D_D(ftou, 4, 0x79900800, 0x4ef32010)
+    TEST_D_D(ftou, 5, 0x0353f510, 0x4c54fd44)
+
+    TEST_PASSFAIL
+

tests/tcg/tricore/asm/test_hptof.S

@@ -0,0 +1,12 @@
+#include "macros.h"
+.text
+.global _start
+_start:
+    TEST_D_D(hptof, 1, 0xba190000, 0xcc0e90c8)
+    TEST_D_D(hptof, 2, 0x3eaea000, 0x8be23575)
+    TEST_D_D(hptof, 3, 0xc33b8000, 0xcc48d9dc)
+    TEST_D_D(hptof, 4, 0x43e2a000, 0xaef95f15)
+    TEST_D_D(hptof, 5, 0x3d55e000, 0x04932aaf)
+
+    TEST_PASSFAIL
+

tests/tcg/tricore/asm/test_insert.S

@@ -6,4 +6,18 @@ _start:
 #                 |     |      |            |       |     |    |
     TEST_D_DIDI(insert, 1, 0x7fffffff, 0xffffffff, 0xa, 0x10, 0x8)
 
+#                insn num    result        rs1    imm1   imm2 imm3
+#                 |     |      |            |       |     |    |
+    TEST_D_DIII(insert, 2, 0xd38fe370, 0xd38fe370, 0x4, 0x4 , 0x0)
+    TEST_D_DIII(insert, 3, 0xd38fe374, 0xd38fe370, 0x4, 0x0 , 0x4)
+
+#                insn  num   result       rs1         rs2      pos  width
+#                 |     |      |           |           |        |    |
+    TEST_D_DDII(insert, 4, 0x03c1e53c, 0x03c1e53c, 0x45821385, 0x7 ,0x0)
+
+#                insn num   result       rs1     imm1      rs2_h       rs2_l
+#                 |    |      |           |        |         |           |
+    TEST_D_DIE(insert, 5, 0xe30c308d, 0xe30c308d ,0x3 , 0x00000000 ,0x00000000)
+    TEST_D_DIE(insert, 6, 0x669b0120, 0x669b2820 ,0x2 , 0x5530a1c7 ,0x3a2b0f67)
+
     TEST_PASSFAIL