diff options
| author | blasty <blasty@local> | 2026-07-26 09:30:12 +0200 |
|---|---|---|
| committer | blasty <blasty@local> | 2026-07-26 09:30:12 +0200 |
| commit | 4e65c3ba16b13c3bb042830b020788a745cee9a9 (patch) | |
| tree | 791b3a94aec4e57801377943088a1dc0870704b4 | |
| parent | listing: make every undefined byte its own row, so you can carve anywhere (diff) | |
| download | ida-tui-4e65c3ba16b13c3bb042830b020788a745cee9a9.tar.gz ida-tui-4e65c3ba16b13c3bb042830b020788a745cee9a9.tar.xz ida-tui-4e65c3ba16b13c3bb042830b020788a745cee9a9.zip | |
listing: `c` disassembles until something stops it
One instruction per keypress means pressing `c` once per opcode for the length
of a routine, which on a raw image is the whole job. IDA's `c` runs; ours now
does too.
New define_code_run tool: create instructions consecutively and report why it
stopped — 'undecodable' (bytes aren't an instruction), 'flow' (control flow ends
here), 'defined' (ran into existing code/data), 'segment' or 'limit'. It loops
inside the worker; from the client this would be one round trip per instruction,
minutes on a real image.
Stops AT a ret rather than past it: beyond the end of a routine the bytes are
usually padding or data, and running on turns a clean carve into something you
have to undo by hand. Stopping at already-defined items is the same principle —
undefining someone's existing work to keep a speculative run going isn't a trade
the user asked for.
The ret test is ida_idp.is_ret_insn, NOT canonical features: on AArch64
insn.get_canon_feature() returns 0 for RET, so a CF_STOP check silently never
fires and the run walks straight through the end of the function. Verified
against a live IDA before relying on it.
`c` on something already defined now says "already defined @ addr" instead of
claiming the instruction failed to be created — count==0 from a run means two
very different things.
Also: the result message survives the reload. Defining an item rebuilds the view,
and the reload's own cursor handler had the last word, so every edit reported
itself as "ROM @ 0x4040 [listing]". A one-shot _flash is handed to whichever
status write lands first after the edit. (Third time this clobber pattern has
turned up: split view, the no-functions hint, now this.)
Verified: nop/nop/nop/ret at 0x4040 -> "defined 4 instructions (0x4040–0x4050) —
control flow ends here", with 0x4050 left as an undefined byte. Starting on
existing code -> no-op. Random bytes -> stops at the first that won't decode.
tests: +4 blob UI (runs to the end of flow, stops at the ret, doesn't touch the
junk after it, and the status reports it). 22/0 blob, 202/0 scenarios, 30/0
project UI.
| -rw-r--r-- | idatui/app.py | 42 | ||||
| -rw-r--r-- | idatui/domain.py | 16 | ||||
| -rw-r--r-- | server/patch_server.py | 74 | ||||
| -rw-r--r-- | tests/test_blob_ui.py | 18 |
4 files changed, 147 insertions, 3 deletions
diff --git a/idatui/app.py b/idatui/app.py index 4cf0ee0..90678d3 100644 --- a/idatui/app.py +++ b/idatui/app.py @@ -3338,6 +3338,7 @@ class IdaTui(App): self._hops: list[str] = [] # binaries a navigation crossed FROM self._load_for_label = None # project binary the dialog is for self._no_functions = False # analysis produced nothing at all + self._flash: str | None = None # message a pending reload must keep self._pending_switch = None # switch waiting on that answer self._nav_seq = 0 # bumped per navigation; drops stale ones # None = teardown wasn't an explicit quit (crash/kill): save defensively. @@ -5407,7 +5408,28 @@ class IdaTui(App): "undef": "undefined", "string": "made string"}[kind] try: if kind == "code": - self.program.define_code(ea) + # Keep going until something stops it: one instruction is rarely + # what you want, and on a raw image it means pressing `c` once + # per opcode for the length of a function. + r = self.program.define_code_run(ea) + n, why = int(r.get("count", 0)), r.get("stopped", "") + if n == 0 and why == "defined": + # Already code/data here — a no-op, not a failure. Saying + # "failed to create instruction" for it would be a lie. + self.app.call_from_thread( + self._status, f"already defined @ {ea:#x}") + return + if n == 0: + raise IDAToolError("define_code", + f"@ {ea:#x}: Failed to create instruction") + end = int(str(r.get("end", hex(ea))), 0) + reason = {"undecodable": "hit bytes that don't decode", + "flow": "control flow ends here", + "defined": "ran into existing code/data", + "segment": "end of segment", + "limit": "instruction limit"}.get(why, why) + verb = (f"defined {n} instruction{'s' if n != 1 else ''} " + f"({ea:#x}\u2013{end:#x}) \u2014 {reason}") elif kind == "func": self.program.define_func(ea) elif kind == "string": @@ -5438,7 +5460,12 @@ class IdaTui(App): def _edit_item_done(self, verb: str, ea: int) -> None: self._dirty = True - self._status(f"{verb} @ {ea:#x} (Ctrl+S to save)") + # Defining an item reloads the view, and that reload writes its own + # status when it lands — after this one. Hand the message over as a + # flash so the result of the edit is what you actually read, instead of + # "ROM @ 0x4040 [listing]" every time. + self._flash = f"{verb} @ {ea:#x} (Ctrl+S to save)" + self._status(self._flash) @work(thread=True, exclusive=True, group="save") def _save(self) -> None: @@ -6038,6 +6065,10 @@ class IdaTui(App): self._goto_ea(msg.va, push=True) def _status_for_cur(self, mode: str) -> None: + flash, self._flash = self._flash, None + if flash: + self._status(flash) # the edit that caused this reload wins + return if self._cur is not None: self._status(f"{self._cur.name} @ {self._cur.ea:#x} [{mode}]") @@ -6274,6 +6305,13 @@ class IdaTui(App): return ea = msg.ea if ea is not None: + # A pending flash (the result of an edit that caused this reload) + # outranks the idle hint: the cursor lands here as part of the + # reload, so this handler would otherwise always have the last word. + flash, self._flash = self._flash, None + if flash: + self._status(flash) + return sec = self.program.section_of(ea) if self.program else None self._status(f"{sec or '?'} @ {ea:#x} [listing] " "(c code · p func · u undefine · Enter follow)") diff --git a/idatui/domain.py b/idatui/domain.py index 846af89..e4fbec9 100644 --- a/idatui/domain.py +++ b/idatui/domain.py @@ -1366,6 +1366,22 @@ class Program: if res.get("error"): raise IDAToolError("define_code", f"@ {ea:#x}: {res['error']}") + def define_code_run(self, ea: int, limit: int = 20000) -> dict: + """Disassemble consecutively from ``ea`` until something stops it. + + Falls back to a single instruction when the worker predates the tool, so + an old worker degrades to the previous behaviour instead of failing. + """ + try: + r = self.client.call("define_code_run", addr=hex(ea), limit=int(limit)) + except IDAToolError: + self.define_code(ea) + return {"count": 1, "stopped": "single", "end": hex(ea)} + if not isinstance(r, dict) or r.get("error"): + raise IDAToolError("define_code_run", + f"@ {ea:#x}: {(r or {}).get('error', 'failed')}") + return r + def define_func(self, ea: int) -> None: """Create a function starting at ``ea`` (IDA's 'p').""" res = self._first_result( diff --git a/server/patch_server.py b/server/patch_server.py index 0e43ea5..4c806a7 100644 --- a/server/patch_server.py +++ b/server/patch_server.py @@ -768,6 +768,80 @@ def list_linkage( "ordinal": int(ordinal)}) return {"imports": imports, "exports": exports, "n_imports": len(imports), "n_exports": len(exports)} + +@tool +@idasync +def define_code_run( + addr: Annotated[str, "Address to start disassembling from"], + limit: Annotated[int, "Max instructions to create (safety stop)"] = 20000, +) -> dict: + """Disassemble CONSECUTIVELY from ``addr`` until something stops it, the way + IDA's 'c' does — one instruction is rarely what you want when carving a raw + image. Returns {start,end,count,stopped} where ``stopped`` says why: + 'undecodable' (bytes aren't an instruction), 'flow' (the last instruction + doesn't fall through, e.g. RET/B), 'defined' (ran into existing code/data), + 'segment' (hit the end) or 'limit'. + + Runs in-process: doing this from the client would be one round trip per + instruction, which is minutes on a real firmware image.""" + import ida_bytes + import ida_idp + import ida_segment + import ida_ua + import idaapi + + try: + ea = parse_address(addr) + except Exception as e: + return {"addr": str(addr), "error": str(e), "count": 0} + + seg = ida_segment.getseg(ea) + if not seg: + return {"addr": str(addr), "error": "no segment", "count": 0} + hi = seg.end_ea + try: + limit = max(1, min(int(limit), 200000)) + except (TypeError, ValueError): + limit = 20000 + + start, count, stopped = ea, 0, "limit" + while count < limit: + if ea >= hi: + stopped = "segment" + break + flags = ida_bytes.get_flags(ea) + if ida_bytes.is_code(flags) or ida_bytes.is_data(flags): + # Already defined: stop rather than clobber. Undefining someone's + # existing work to keep a speculative run going is not a trade the + # user asked for. + stopped = "defined" + break + n = ida_ua.create_insn(ea) + if n <= 0: + stopped = "undecodable" + break + count += 1 + # Stop where control flow stops. Past a RET the next bytes are usually + # padding or a new function's data, and running on turns a clean carve + # into a mess that has to be undone by hand. + # + # Ask ida_idp.is_ret_insn, NOT the canonical feature bits: on AArch64 + # get_canon_feature() returns 0 for RET, so a CF_STOP test silently never + # fires and the run walks straight through the end of the routine. + insn = ida_ua.insn_t() + if ida_ua.decode_insn(insn, ea) > 0: + try: + is_ret = ida_idp.is_ret_insn(insn) + except Exception: + is_ret = False + if is_ret or (insn.get_canon_feature() & idaapi.CF_STOP): + ea += n + stopped = "flow" + break + ea += n + + return {"start": hex(start), "end": hex(ea), "count": count, + "stopped": stopped} ''' SNIPPET = f"{BEGIN}\n{BODY.strip()}\n{END}\n" diff --git a/tests/test_blob_ui.py b/tests/test_blob_ui.py index 400c9ab..9161f44 100644 --- a/tests/test_blob_ui.py +++ b/tests/test_blob_ui.py @@ -55,7 +55,7 @@ async def run() -> int: planted = 0x40 # file offset -> ea 0x4040 for k, insn in enumerate((0xD503201F, # nop 0xD503201F, # nop - 0xD65F03C0)): # ret + 0xD65F03C0)): # ret <- the run must stop here data[planted + k * 4:planted + k * 4 + 4] = insn.to_bytes(4, "little") blob = os.path.join(tmp, "rnd.bin") with open(blob, "wb") as f: @@ -141,6 +141,22 @@ async def run() -> int: f"kind={h.kind if h else None} text={h.text if h else None!r}") if h is not None and h.kind == "code": print(f" carved {target:#x}: {h.text}") + # `c` runs until something stops it, like IDA — one instruction + # at a time means pressing it once per opcode for the length of + # a routine. We planted nop/nop/nop/ret, so it must take all + # four and stop AT the ret, not run on into the random bytes + # after it. + run = [m.get(m.index_of_ea(target + k * 4)) for k in range(3)] + check("`c` keeps going until control flow ends", + all(x is not None and x.kind == "code" for x in run), + f"{[(hex(x.ea), x.kind) for x in run if x]}") + check("and stops at the ret instead of running into junk", + m.get(m.index_of_ea(target + 12)).kind == "unknown", + f"{m.get(m.index_of_ea(target + 12)).text!r}") + status = str(app.query_one("#status", Static).render()) + check("the status reports what the run did", + "3 instructions" in status and "control flow" in status, + status[:80]) check("the carved row spans the instruction, not one byte", h.size == 4, f"size={h.size}") check("bytes before it stay individually addressable", |
