5152d0c9f7
Foundation for replacing fold's dead/abstract binary encoder with a real
SSA P-Code frontend. Verified root-cause gap: serializeBinaryIR() emits only
data-discovery nodes (sections/strings/imports/exports); the control-flow
BinaryExprKind values (BasicBlock/CallSite/...) are never constructed, so the
Z3-BB encoder's encodable filter is always empty and encodeBinaryBBs never
runs — hence 0 binary Z3 findings. The P-Code pipeline supersedes that path.
Phase 0 — docs/internal/ghidra-pcode-integration-research.md: P-Code opcode
core, the decompiler C++ embedding API (LoadImage/SleighArchitecture/Funcdata),
the CORE+DECCORE+SLEIGH source sets, no-bison finding, and pypcode as build
reference.
Phase 1 — vendored Ghidra decompiler at pinned commit (Ghidra_12.1_build,
7e89d94e34...) under third_party/ghidra-decompiler/ (cpp + AArch64 specs +
Apache-2.0 LICENSE + VENDOR.md + .gitignore for build artifacts). Validated by
hand on this clang-21/macOS toolchain:
- full SSA engine (CORE+DECCORE+SLEIGH, 80 files incl. heritage/funcdata/
action) compiles clean, -std=c++11 -O2, NO BFD, NO bison (generated
parsers are committed upstream; ruleparse isn't in the lib set);
- sleigh compiler builds; AArch64 .slaspec -> .sla compiles;
- tools/pcode_dump.cpp (custom LoadImage, no BFD) lifts the real arm64
sym._div_by_zero_direct to correct P-Code: `mov w9,#0 -> COPY(const 0)`,
`sdiv -> INT_SDIV(w8,w9)` — divisor zero-ness explicit in the data flow,
so the Phase-3 encoder proves div-by-zero trivially, multi-arch.
Not yet meson-wired (next step) and no fold-side IR/encoder yet (Phase 2-3);
this commit is the validated vendor + smoke tool.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
75 lines
2.9 KiB
C++
75 lines
2.9 KiB
C++
/* ###
|
|
* IP: GHIDRA
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
#ifndef __PREFERSPLIT_HH__
|
|
#define __PREFERSPLIT_HH__
|
|
|
|
#include "varnode.hh"
|
|
|
|
namespace ghidra {
|
|
|
|
class Funcdata; // Forward declaration
|
|
|
|
extern ElementId ELEM_PREFERSPLIT; ///< Marshaling element \<prefersplit>
|
|
|
|
struct PreferSplitRecord {
|
|
VarnodeData storage;
|
|
int4 splitoffset; // Number of initial bytes (in address order) to split into first piece
|
|
bool operator<(const PreferSplitRecord &op2) const;
|
|
};
|
|
|
|
class PreferSplitManager {
|
|
class SplitInstance {
|
|
friend class PreferSplitManager;
|
|
int4 splitoffset;
|
|
Varnode *vn;
|
|
Varnode *hi; // Most significant piece
|
|
Varnode *lo; // Least significant piece
|
|
public:
|
|
SplitInstance(Varnode *v,int4 off) { vn = v; splitoffset = off; hi = (Varnode *)0; lo = (Varnode *)0; }
|
|
};
|
|
Funcdata *data;
|
|
const vector<PreferSplitRecord> *records;
|
|
vector<PcodeOp *> tempsplits; // Copies of temporaries that need additional splitting
|
|
void fillinInstance(SplitInstance *inst,bool bigendian,bool sethi,bool setlo);
|
|
void createCopyOps(SplitInstance *ininst,SplitInstance *outinst,PcodeOp *op,bool istemp);
|
|
bool testDefiningCopy(SplitInstance *inst,PcodeOp *def,bool &istemp);
|
|
void splitDefiningCopy(SplitInstance *inst,PcodeOp *def,bool istemp);
|
|
bool testReadingCopy(SplitInstance *inst,PcodeOp *readop,bool &istemp);
|
|
void splitReadingCopy(SplitInstance *inst,PcodeOp *readop,bool istemp);
|
|
bool testZext(SplitInstance *inst,PcodeOp *op);
|
|
void splitZext(SplitInstance *inst,PcodeOp *op);
|
|
bool testPiece(SplitInstance *inst,PcodeOp *op);
|
|
void splitPiece(SplitInstance *inst,PcodeOp *op);
|
|
bool testSubpiece(SplitInstance *inst,PcodeOp *op);
|
|
void splitSubpiece(SplitInstance *inst,PcodeOp *op);
|
|
bool testLoad(SplitInstance *inst,PcodeOp *op);
|
|
void splitLoad(SplitInstance *inst,PcodeOp *op);
|
|
bool testStore(SplitInstance *inst,PcodeOp *op);
|
|
void splitStore(SplitInstance *inst,PcodeOp *op);
|
|
bool splitVarnode(SplitInstance *inst);
|
|
void splitRecord(const PreferSplitRecord &rec);
|
|
bool testTemporary(SplitInstance *inst);
|
|
void splitTemporary(SplitInstance *inst);
|
|
public:
|
|
void init(Funcdata *fd,const vector<PreferSplitRecord> *rec);
|
|
const PreferSplitRecord *findRecord(Varnode *vn) const;
|
|
static void initialize(vector<PreferSplitRecord> &records);
|
|
void split(void);
|
|
void splitAdditional(void);
|
|
};
|
|
|
|
} // End namespace ghidra
|
|
#endif
|