1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
| //===- BoundsChecking.cpp - Instrumentation for run-time bounds checking --===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Instrumentation/BoundsChecking.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetFolder.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/Value.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include <cstdint>
#include <vector>
using namespace llvm;
#define DEBUG_TYPE "bounds-checking"
static cl::opt<bool> SingleTrapBB("bounds-checking-single-trap",
cl::desc("Use one trap block per function"));
STATISTIC(ChecksAdded, "Bounds checks added");
STATISTIC(ChecksSkipped, "Bounds checks skipped");
STATISTIC(ChecksUnable, "Bounds checks unable to add");
using BuilderTy = IRBuilder<TargetFolder>;
/// Gets the conditions under which memory accessing instructions will overflow.
///
/// \p Ptr is the pointer that will be read/written, and \p InstVal is either
/// the result from the load or the value being stored. It is used to determine
/// the size of memory block that is touched.
///
/// Returns the condition under which the access will overflow.
static Value *getBoundsCheckCond(Value *Ptr, Value *InstVal,
const DataLayout &DL, TargetLibraryInfo &TLI,
ObjectSizeOffsetEvaluator &ObjSizeEval,
BuilderTy &IRB, ScalarEvolution &SE) {
uint64_t NeededSize = DL.getTypeStoreSize(InstVal->getType());
LLVM_DEBUG(dbgs() << "Instrument " << *Ptr << " for " << Twine(NeededSize)
<< " bytes\n");
SizeOffsetEvalType SizeOffset = ObjSizeEval.compute(Ptr);
if (!ObjSizeEval.bothKnown(SizeOffset)) {
++ChecksUnable;
return nullptr;
}
Value *Size = SizeOffset.first;
Value *Offset = SizeOffset.second;
ConstantInt *SizeCI = dyn_cast<ConstantInt>(Size);
Type *IntTy = DL.getIntPtrType(Ptr->getType());
Value *NeededSizeVal = ConstantInt::get(IntTy, NeededSize);
auto SizeRange = SE.getUnsignedRange(SE.getSCEV(Size));
auto OffsetRange = SE.getUnsignedRange(SE.getSCEV(Offset));
auto NeededSizeRange = SE.getUnsignedRange(SE.getSCEV(NeededSizeVal));
// three checks are required to ensure safety:
// . Offset >= 0 (since the offset is given from the base ptr)
// . Size >= Offset (unsigned)
// . Size - Offset >= NeededSize (unsigned)
//
// optimization: if Size >= 0 (signed), skip 1st check
// FIXME: add NSW/NUW here? -- we dont care if the subtraction overflows
Value *ObjSize = IRB.CreateSub(Size, Offset);
Value *Cmp2 = SizeRange.getUnsignedMin().uge(OffsetRange.getUnsignedMax())
? ConstantInt::getFalse(Ptr->getContext())
: IRB.CreateICmpULT(Size, Offset);
Value *Cmp3 = SizeRange.sub(OffsetRange)
.getUnsignedMin()
.uge(NeededSizeRange.getUnsignedMax())
? ConstantInt::getFalse(Ptr->getContext())
: IRB.CreateICmpULT(ObjSize, NeededSizeVal);
Value *Or = IRB.CreateOr(Cmp2, Cmp3);
if ((!SizeCI || SizeCI->getValue().slt(0)) &&
!SizeRange.getSignedMin().isNonNegative()) {
Value *Cmp1 = IRB.CreateICmpSLT(Offset, ConstantInt::get(IntTy, 0));
Or = IRB.CreateOr(Cmp1, Or);
}
return Or;
}
/// Adds run-time bounds checks to memory accessing instructions.
///
/// \p Or is the condition that should guard the trap.
///
/// \p GetTrapBB is a callable that returns the trap BB to use on failure.
template <typename GetTrapBBT>
static void insertBoundsCheck(Value *Or, BuilderTy IRB, GetTrapBBT GetTrapBB) {
// check if the comparison is always false
ConstantInt *C = dyn_cast_or_null<ConstantInt>(Or);
if (C) {
++ChecksSkipped;
// If non-zero, nothing to do.
if (!C->getZExtValue())
return;
}
++ChecksAdded;
BasicBlock::iterator SplitI = IRB.GetInsertPoint();
BasicBlock *OldBB = SplitI->getParent();
BasicBlock *Cont = OldBB->splitBasicBlock(SplitI);
OldBB->getTerminator()->eraseFromParent();
if (C) {
// If we have a constant zero, unconditionally branch.
// FIXME: We should really handle this differently to bypass the splitting
// the block.
BranchInst::Create(GetTrapBB(IRB), OldBB);
return;
}
// Create the conditional branch.
BranchInst::Create(GetTrapBB(IRB), Cont, Or, OldBB);
}
static bool addBoundsChecking(Function &F, TargetLibraryInfo &TLI,
ScalarEvolution &SE) {
const DataLayout &DL = F.getParent()->getDataLayout();
ObjectSizeOpts EvalOpts;
EvalOpts.RoundToAlign = true;
ObjectSizeOffsetEvaluator ObjSizeEval(DL, &TLI, F.getContext(), EvalOpts);
// check HANDLE_MEMORY_INST in include/llvm/Instruction.def for memory
// touching instructions
SmallVector<std::pair<Instruction *, Value *>, 4> TrapInfo;
for (Instruction &I : instructions(F)) {
Value *Or = nullptr;
BuilderTy IRB(I.getParent(), BasicBlock::iterator(&I), TargetFolder(DL));
if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
Or = getBoundsCheckCond(LI->getPointerOperand(), LI, DL, TLI,
ObjSizeEval, IRB, SE);
} else if (StoreInst *SI = dyn_cast<StoreInst>(&I)) {
Or = getBoundsCheckCond(SI->getPointerOperand(), SI->getValueOperand(),
DL, TLI, ObjSizeEval, IRB, SE);
} else if (AtomicCmpXchgInst *AI = dyn_cast<AtomicCmpXchgInst>(&I)) {
Or = getBoundsCheckCond(AI->getPointerOperand(), AI->getCompareOperand(),
DL, TLI, ObjSizeEval, IRB, SE);
} else if (AtomicRMWInst *AI = dyn_cast<AtomicRMWInst>(&I)) {
Or = getBoundsCheckCond(AI->getPointerOperand(), AI->getValOperand(), DL,
TLI, ObjSizeEval, IRB, SE);
}
if (Or)
TrapInfo.push_back(std::make_pair(&I, Or));
}
// Create a trapping basic block on demand using a callback. Depending on
// flags, this will either create a single block for the entire function or
// will create a fresh block every time it is called.
BasicBlock *TrapBB = nullptr;
auto GetTrapBB = [&TrapBB](BuilderTy &IRB) {
if (TrapBB && SingleTrapBB)
return TrapBB;
Function *Fn = IRB.GetInsertBlock()->getParent();
// FIXME: This debug location doesn't make a lot of sense in the
// `SingleTrapBB` case.
auto DebugLoc = IRB.getCurrentDebugLocation();
IRBuilder<>::InsertPointGuard Guard(IRB);
TrapBB = BasicBlock::Create(Fn->getContext(), "trap", Fn);
IRB.SetInsertPoint(TrapBB);
auto *F = Intrinsic::getDeclaration(Fn->getParent(), Intrinsic::trap);
CallInst *TrapCall = IRB.CreateCall(F, {});
TrapCall->setDoesNotReturn();
TrapCall->setDoesNotThrow();
TrapCall->setDebugLoc(DebugLoc);
IRB.CreateUnreachable();
return TrapBB;
};
// Add the checks.
for (const auto &Entry : TrapInfo) {
Instruction *Inst = Entry.first;
BuilderTy IRB(Inst->getParent(), BasicBlock::iterator(Inst), TargetFolder(DL));
insertBoundsCheck(Entry.second, IRB, GetTrapBB);
}
return !TrapInfo.empty();
}
PreservedAnalyses BoundsCheckingPass::run(Function &F, FunctionAnalysisManager &AM) {
auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
auto &SE = AM.getResult<ScalarEvolutionAnalysis>(F);
if (!addBoundsChecking(F, TLI, SE))
return PreservedAnalyses::all();
return PreservedAnalyses::none();
}
namespace {
struct BoundsCheckingLegacyPass : public FunctionPass {
static char ID;
BoundsCheckingLegacyPass() : FunctionPass(ID) {
initializeBoundsCheckingLegacyPassPass(*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &F) override {
auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
auto &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE();
return addBoundsChecking(F, TLI, SE);
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<TargetLibraryInfoWrapperPass>();
AU.addRequired<ScalarEvolutionWrapperPass>();
}
};
} // namespace
char BoundsCheckingLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(BoundsCheckingLegacyPass, "bounds-checking",
"Run-time bounds checking", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(BoundsCheckingLegacyPass, "bounds-checking",
"Run-time bounds checking", false, false)
FunctionPass *llvm::createBoundsCheckingLegacyPass() {
return new BoundsCheckingLegacyPass();
}
|