Merge tag 'pull-tricore-20230928' of https://github.com/bkoppelmann/qemu

 into staging

- Add FTOU, CRCN, FTOHP, and HPTOF insns
- Add test for arithmetic TriCore insns

# -----BEGIN PGP SIGNATURE-----
#
# iQJTBAABCgA9FiEEbmNqfoPy3Qz6bm43CtLGOWtpyhQFAmUVPVgfHGtiYXN0aWFu
# QG1haWwudW5pLXBhZGVyYm9ybi5kZQAKCRAK0sY5a2nKFFzmD/9iWljlOkYEH/pe
# AJXi08MAFtVxZ7b5pkv4a/oMVy+/RtqXnTLqsh3RChby0YNaY9t4ySXCDk9n1E7c
# zrJ6dPzJ7MhNSOz9Hz0uHYZrY9ZVKsjr6GT/VMy1QcHm5z47gzNn0NwJ9WVImr4R
# Dv80PYcMueP08LHO81tACSV0ppxcg1WgRV+onyX9BgZVbdh51JS313OvtUfvvwyC
# pBxzzyZccXkLlzm0ObcEUbTCJ+fGOJ3jwHwBIEaEZFujdmBU2sM8+BTV0FgyvwH/
# 2JuM1GlKxef2lT9JInfzbwturtaKCj4uBhtw7Jvj69rQlIbal+m0AYAbr20xWCiD
# DPt6UeO9xFy+2LvjxQFv3iAFSjRvdQwYTnnq/on8LQ4y+m7fZ2a0Utl8OZlj/pX8
# 0LDPspC10aSxzqBYqkjTaahzGZbZmLapV4eAwrHNHa3JnOGk45paOJFX2JnPB1gB
# T2O8Mc738I1M6qPQzSMrM8y7xlRi97kUpF5BLfYUdjNpUVb03KIK9aEq74paAU+a
# IZTwE7U+8jn7ZEzFwMRIu0rg+bFi1ZlMmvDZm9kbBHQwoZ5xPoyEIoITlXw4B/Kk
# vg2bLz6SH+tzu9DLcoWg7FupxNE3VOtJgkGXCN2tkYoJwDE9wjVpGYJ1anW+fTZN
# J8/iunffflAyaLkRh5hi5iklvHqOeA==
# =3Fk7
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 28 Sep 2023 04:46:16 EDT
# gpg:                using RSA key 6E636A7E83F2DD0CFA6E6E370AD2C6396B69CA14
# gpg:                issuer "kbastian@mail.uni-paderborn.de"
# gpg: Can't check signature: No public key

* tag 'pull-tricore-20230928' of https://github.com/bkoppelmann/qemu: (21 commits)
  target/tricore: Change effective address (ea) to target_ulong
  target/tricore: Remove CSFRs from cpu.h
  tests/tcg/tricore: Add test from 'shuffle' to 'xor.t'
  tests/tcg/tricore: Add test from 'max' to 'shas'
  tests/tcg/tricore: Add test from 'dextr' to 'lt'
  tests/tcg/tricore: Add test from 'and' to 'csub'
  tests/tcg/tricore: Add test for all arith insns up to addx
  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
  ...

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

hw/tricore/tricore_testdevice.c

@@ -16,13 +16,17 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "hw/qdev-properties.h"
 #include "hw/tricore/tricore_testdevice.h"
 
 static void tricore_testdevice_write(void *opaque, hwaddr offset,
                                       uint64_t value, unsigned size)
 {
+    if (value != 0) {
+        qemu_log_mask(LOG_GUEST_ERROR, "Test %ld 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;
-    uint32_t SYSCON;
-    uint32_t CPU_ID;
-    uint32_t CORE_ID;
-    uint32_t BIV;
-    uint32_t BTV;
-    uint32_t ISP;
-    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;
+#define R(ADDR, NAME, FEATURE) uint32_t NAME;
+#define A(ADDR, NAME, FEATURE) uint32_t NAME;
+#define E(ADDR, NAME, FEATURE) uint32_t NAME;
+#include "csfr.h.inc"
+#undef R
+#undef A
+#undef E
+
     /* 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)