diff options
| author | blasty <blasty@local> | 2026-08-07 14:08:12 +0200 |
|---|---|---|
| committer | blasty <blasty@local> | 2026-08-07 14:08:12 +0200 |
| commit | ecc58d7725db6d4929ae3e299dea4f0202a81946 (patch) | |
| tree | 896884021fe91ccff747af7aec52d210130a06f5 /idatui/codemode_client.py | |
| parent | codemode: rename takes a LIST of edits per category, not just one (diff) | |
| download | ida-tui-ecc58d7725db6d4929ae3e299dea4f0202a81946.tar.gz ida-tui-ecc58d7725db6d4929ae3e299dea4f0202a81946.tar.xz ida-tui-ecc58d7725db6d4929ae3e299dea4f0202a81946.zip | |
codemode: three defects the A/B benchmark found in the decompiler path
Benchmarking the port against master op-by-op (rather than only asking whether
tests pass) turned up three real bugs, all in the most user-visible path:
opening pseudocode.
1. decompile was doing decomp_map's job. It called the full per-column line
map purely to fill in each line's /*0xEA*/ anchor. The tool ida-tui was
written against takes ONE get_line_item at column 0 per line; the port took
one per COLUMN, i.e. thousands of get_line_item+dstr() calls per function
instead of one per line. Every pseudocode open cost the same as opening the
split view. Carried the real implementation over: 1888ms -> 53ms.
2. decomp_map used the pre-optimisation line map. Ours memoises obj_id -> ea
for the whole function (commit 853d90c: dstr() was 79% of the tool, and
consecutive columns report the same ctree item), the port's did not.
1925ms -> 287ms.
3. _idatui_compact imported ida_pro_mcp on every call. Under Code Mode that
package is not installed in the database process, so the import failed every
time -- and a FAILED import is never cached, so each one re-searched the
whole of sys.path: 422 failed imports per pc_nums call, which was most of
its runtime. 1428ms -> 257ms.
The same bug was a correctness bug hiding behind the perf bug: the fallback
path collapsed whitespace INSIDE string literals, where the real function
preserves it. Pseudocode columns are served in those coordinates, so on any
line containing a string with two spaces, every literal's mark and every
reformat would have been placed on the wrong column. It never fired on
master because ida_pro_mcp is installed there. Now calls the byte-identical
module-level shim directly, with the deviation from the extracted original
documented in place.
Narrow verification: decomp/split_view/opfmt/follow/comment/structs scenarios,
72 passed, 0 failed. Full gate running separately.
Diffstat (limited to 'idatui/codemode_client.py')
| -rw-r--r-- | idatui/codemode_client.py | 65 |
1 files changed, 8 insertions, 57 deletions
diff --git a/idatui/codemode_client.py b/idatui/codemode_client.py index 5e8089b..3bf01cc 100644 --- a/idatui/codemode_client.py +++ b/idatui/codemode_client.py @@ -171,24 +171,6 @@ def _script(args: dict[str, Any], body: str) -> str: return f"import json\na = json.loads({encoded!r})\n{dedent(body).strip()}\n" -_DECOMP_MAP_HELPER = r''' -def line_map(cfunc): - import ida_hexrays - answer = [] - for sl in cfunc.get_pseudocode(): - tagged, eas, seen = sl.line, [], set() - for x in range(len(tagged) + 1): - head = ida_hexrays.ctree_item_t(); item = ida_hexrays.ctree_item_t(); tail = ida_hexrays.ctree_item_t() - if not cfunc.get_line_item(tagged, x, False, head, item, tail): continue - text = item.dstr() or "" - try: ea = int(text.split(": ", 1)[0], 16) - except (ValueError, IndexError): continue - if ea not in seen: seen.add(ea); eas.append(ea) - answer.append(eas) - return answer -''' - - _OPERATIONS: dict[str, str] = { "list_funcs": r''' import fnmatch @@ -812,45 +794,6 @@ result } -_OPERATIONS["decompile"] = _DECOMP_MAP_HELPER + r''' -ea = int(str(a["addr"]), 16) -fn = db.functions.get_at(ea) -if fn is None: - result = {"error": f"no function at {ea:#x}"} -else: - pseudo = db.pseudocode.decompile(fn) - mapping = line_map(pseudo.raw_cfunc) - plain = pseudo.to_text() - marked = [line + (f" /*0x{eas[0]:X}*/" if eas else "") - for line, eas in zip(plain, mapping)] - import ida_name - refs, seen = [], set() - for expr in pseudo.find_objects(): - target = int(expr.obj_ea) - if target in seen or not (db.is_valid_ea(target) or db.is_private_ea(target)): continue - seen.add(target) - name = expr.obj_name or ida_name.get_name(target) or "" - try: string = db.bytes.get_string_at(target) if db.is_valid_ea(target) else None - except Exception: string = None - refs.append({"addr": hex(target), "name": name, "string": string}) - result = {"addr": hex(int(fn.start_ea)), "code": "\n".join(marked), "refs": refs} -result -''' - -_OPERATIONS["decomp_map"] = _DECOMP_MAP_HELPER + r''' -ea = int(str(a["addr"]), 16) -fn = db.functions.get_at(ea) -if fn is None: - result = {"error": f"no function at {ea:#x}"} -else: - pseudo = db.pseudocode.decompile(fn) - mapping = line_map(pseudo.raw_cfunc) - result = {"addr": hex(int(fn.start_ea)), - "lines": [{"ea": hex(eas[0]) if eas else None, - "eas": [hex(item) for item in eas]} for eas in mapping]} -result -''' - _OPERATIONS["define_code_run"] = r''' import ida_bytes, ida_idp, ida_segment, ida_ua, idaapi ea, limit = int(str(a["addr"]), 16), max(1, min(int(a.get("limit", 20000)), 200000)) @@ -877,6 +820,7 @@ else: result ''' + _OPERATIONS["define_func_run"] = r''' import ida_bytes, ida_funcs, ida_segment ea = int(str(a["addr"]), 16) @@ -901,6 +845,7 @@ else: result ''' + _OPERATIONS["set_thumb"] = r''' import ida_bytes, ida_ida, ida_idp, ida_segment, ida_segregs ea = int(str(a["addr"]), 16); treg = ida_idp.str2reg("T") @@ -926,6 +871,7 @@ else: result ''' + _OPERATIONS["thumb_scan"] = r''' import ida_bytes, ida_funcs, ida_idp, ida_segment, ida_segregs, ida_ua lo, hi = int(str(a["start"]), 16), int(str(a["end"]), 16) @@ -950,6 +896,7 @@ result = {"start": hex(lo), "end": hex(hi), "found": found, "applied": applied, result ''' + _OPERATIONS["decomp_error"] = r''' import ida_hexrays, ida_ida ea = int(str(a["addr"]), 16); fn = db.functions.get_at(ea) @@ -1016,6 +963,10 @@ _OPERATIONS["op_format"] = _remote_op( 'op_format(addr=a["addr"], mode=a.get("mode", "cycle"),' ' col=int(a.get("col", -1)), n=int(a.get("n", -1)))') _OPERATIONS["pc_nums"] = _remote_op('pc_nums(addr=a["addr"])') +_OPERATIONS["decompile"] = _remote_op( + 'decompile(addr=a["addr"],' + ' include_addresses=bool(a.get("include_addresses", True)))') +_OPERATIONS["decomp_map"] = _remote_op('decomp_map(addr=a["addr"])') _OPERATIONS["pc_num_format"] = _remote_op( 'pc_num_format(addr=a["addr"], mode=a.get("mode", "cycle"),' ' line=int(a.get("line", -1)), col=int(a.get("col", -1)),' |
