[PATCH v4 01/17] scripts: introduce scripts/update-aarch64-cpu-sysregs-header.py

[Eric Auger <eric.auger@redhat.com>]

Introduce a script that takes as input the Registers.json file
delivered in the AARCHMRS Features Model downloadable from the
Arm Developer A-Profile Architecture Exploration Tools page:
https://developer.arm.com/Architectures/A-Profile%20Architecture#Downloads
and outputs the list of ID regs in target/arm/cpu-sysregs.h.inc
under the form of DEF(<name>, <op0>, <op1>, <crn>, <crm>, <op2>).

We only care about IDregs with opcodes satisfying:
op0 = 3, op1 = {0,1,3}, crn = 0, crm within [0, 7], op2 within [0, 7]

Signed-off-by: Eric Auger <eric.auger@redhat.com>
[CH: note correct op1 range, don't skip CCSIDR]
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Message-ID: <20251208163751.611186-2-eric.auger@redhat.com>
---
 scripts/update-aarch64-cpu-sysregs-header.py | 134 +++++++++++++++++++
 1 file changed, 134 insertions(+)
 create mode 100755 scripts/update-aarch64-cpu-sysregs-header.py

diff --git a/scripts/update-aarch64-cpu-sysregs-header.py b/scripts/update-aarch64-cpu-sysregs-header.py
new file mode 100755
index 0000000000..8c337147dd
--- /dev/null
+++ b/scripts/update-aarch64-cpu-sysregs-header.py
@@ -0,0 +1,134 @@
+#!/usr/bin/env python3
+
+# This script takes as input the Registers.json file delivered in
+# the AARCHMRS Features Model downloadable from the Arm Developer
+# A-Profile Architecture Exploration Tools page:
+# https://developer.arm.com/Architectures/A-Profile%20Architecture#Downloads
+# and outputs the list of ID regs in target/arm/cpu-sysregs.h.inc
+# under the form of DEF(<name>, <op0>, <op1>, <crn>, <crm>, <op2>)
+#
+# Copyright (C) 2026 Red Hat, Inc.
+#
+# Authors: Eric Auger <eric.auger@redhat.com>
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+
+import json
+import os
+import sys
+
+# Some regs have op code values like 000x, 001x. Anyway we don't need
+# them. Besides some regs are undesired in the generated file such as
+# VMPIDR_EL2 and VPIDR_EL2 which are outside of the IDreg scope we
+# are interested in and are tricky to decode as their system accessor
+# refer to MPIDR_EL1/MIDR_EL1 respectively
+
+skiplist = ['ALLINT', 'PM', 'S1_', 'S3_', 'SVCR', \
+            'VMPIDR_EL2', 'VPIDR_EL2']
+
+# returns the int value of a given @opcode for a reg @encoding
+def get_opcode(encoding, opcode):
+    fvalue = encoding.get(opcode)
+    if fvalue:
+        value = fvalue.get('value')
+        if isinstance(value, str):
+            value = value.strip("'")
+            value = int(value, 2)
+            return value
+    return -1
+
+def extract_idregs_from_registers_json(filename):
+    """
+    Load a Registers.json file and extract all ID registers, decode their
+    opcode and dump the information in target/arm/cpu-sysregs.h.inc
+
+    Args:
+        filename (str): The path to the Registers.json
+    returns:
+        idregs: list of ID regs and their encoding
+    """
+    if not os.path.exists(filename):
+        print(f"Error: {filename} could not be found!")
+        return {}
+
+    try:
+        with open(filename, 'r') as f:
+            register_data = json.load(f)
+
+    except json.JSONDecodeError:
+        print(f"Could not decode json from '{filename}'!")
+        return {}
+    except Exception as e:
+        print(f"Unexpected error while reading {filename}: {e}")
+        return {}
+
+    registers = [r for r in register_data if isinstance(r, dict) and \
+                r.get('_type') == 'Register']
+
+    idregs = {}
+
+    for register in registers:
+        reg_name = register.get('name')
+
+        is_skipped = any(term in (reg_name or "").upper() for term in skiplist)
+
+        if reg_name and not is_skipped:
+            accessors = register.get('accessors', [])
+
+            for accessor in accessors:
+                type = accessor.get('_type')
+                if type in ['Accessors.SystemAccessor']:
+                    encoding_list = accessor.get('encoding')
+
+                    if isinstance(encoding_list, list) and encoding_list and \
+                       isinstance(encoding_list[0], dict):
+                        encoding_wrapper = encoding_list[0]
+                        encoding_source = encoding_wrapper.get('encodings', \
+                                                               encoding_wrapper)
+
+                        if isinstance(encoding_source, dict):
+                                op0 = get_opcode(encoding_source, 'op0')
+                                op1 = get_opcode(encoding_source, 'op1')
+                                op2 = get_opcode(encoding_source, 'op2')
+                                crn = get_opcode(encoding_source, 'CRn')
+                                crm = get_opcode(encoding_source, 'CRm')
+                                encoding_str=f"{op0} {op1} {crn} {crm} {op2}"
+
+                # ID regs are assumed within this scope
+                if op0 == 3 and (op1 == 0 or op1 == 1 or op1 == 3) and \
+                   crn == 0 and (crm >= 0 and crm <= 7) and (op2 >= 0 and op2 <= 7):
+                    idregs[reg_name] = encoding_str
+
+    return idregs
+
+if __name__ == "__main__":
+    # Single arg expected: the path to the Registers.json file
+    if len(sys.argv) < 2:
+        print("Usage: python scripts/update-aarch64-cpu-sysregs-header.py "
+              "<path_to_registers_json>")
+        sys.exit(1)
+    else:
+        json_file_path = sys.argv[1]
+
+    extracted_registers = extract_idregs_from_registers_json(json_file_path)
+
+    if extracted_registers:
+        output_list = extracted_registers.items()
+
+        # Sort by register name
+        sorted_output = sorted(output_list, key=lambda item: item[0])
+
+        # format lines as DEF(<name>, <op0>, <op1>, <crn>, <crm>, <op2>)
+        final_output = ""
+        for reg_name, encoding in sorted_output:
+            reformatted_encoding = encoding.replace(" ", ", ")
+            final_output += f"DEF({reg_name}, {reformatted_encoding})\n"
+
+        with open("target/arm/cpu-sysregs.h.inc", 'w') as f:
+            f.write("/* SPDX-License-Identifier: GPL-2.0-or-later */\n\n")
+            f.write("/* This file is autogenerated by ")
+            f.write("scripts/update-aarch64-cpu-sysregs-header.py */\n")
+            f.write("/* DEF(<name>, <op0>, <op1>, <crn>, <crm>, <op2>) */\n\n")
+            f.write(final_output)
+        print("updated target/arm/cpu-sysregs.h.inc")
-- 
2.53.0