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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
|
//===- PreISelIntrinsicLowering.cpp - Pre-ISel intrinsic lowering pass ----===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This pass implements IR lowering for the llvm.memcpy, llvm.memmove,
// llvm.memset, llvm.load.relative and llvm.objc.* intrinsics.
//
//===----------------------------------------------------------------------===//
#include "llvm/CodeGen/PreISelIntrinsicLowering.h"
#include "llvm/Analysis/ObjCARCInstKind.h"
#include "llvm/Analysis/ObjCARCUtil.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/Utils/LowerMemIntrinsics.h"
using namespace llvm;
/// Threshold to leave statically sized memory intrinsic calls. Calls of known
/// size larger than this will be expanded by the pass. Calls of unknown or
/// lower size will be left for expansion in codegen.
static cl::opt<int64_t> MemIntrinsicExpandSizeThresholdOpt(
"mem-intrinsic-expand-size",
cl::desc("Set minimum mem intrinsic size to expand in IR"), cl::init(-1),
cl::Hidden);
namespace {
struct PreISelIntrinsicLowering {
const TargetMachine &TM;
const function_ref<TargetTransformInfo &(Function &)> LookupTTI;
/// If this is true, assume it's preferably to leave memory intrinsic calls
/// for replacement with a library call later. Otherwise this depends on
/// TargetLoweringInfo availability of the corresponding function.
const bool UseMemIntrinsicLibFunc;
explicit PreISelIntrinsicLowering(
const TargetMachine &TM_,
function_ref<TargetTransformInfo &(Function &)> LookupTTI_,
bool UseMemIntrinsicLibFunc_ = true)
: TM(TM_), LookupTTI(LookupTTI_),
UseMemIntrinsicLibFunc(UseMemIntrinsicLibFunc_) {}
static bool shouldExpandMemIntrinsicWithSize(Value *Size,
const TargetTransformInfo &TTI);
bool expandMemIntrinsicUses(Function &F) const;
bool lowerIntrinsics(Module &M) const;
};
} // namespace
static bool lowerLoadRelative(Function &F) {
if (F.use_empty())
return false;
bool Changed = false;
Type *Int32Ty = Type::getInt32Ty(F.getContext());
for (Use &U : llvm::make_early_inc_range(F.uses())) {
auto CI = dyn_cast<CallInst>(U.getUser());
if (!CI || CI->getCalledOperand() != &F)
continue;
IRBuilder<> B(CI);
Value *OffsetPtr =
B.CreatePtrAdd(CI->getArgOperand(0), CI->getArgOperand(1));
Value *OffsetI32 = B.CreateAlignedLoad(Int32Ty, OffsetPtr, Align(4));
Value *ResultPtr = B.CreatePtrAdd(CI->getArgOperand(0), OffsetI32);
CI->replaceAllUsesWith(ResultPtr);
CI->eraseFromParent();
Changed = true;
}
return Changed;
}
// ObjCARC has knowledge about whether an obj-c runtime function needs to be
// always tail-called or never tail-called.
static CallInst::TailCallKind getOverridingTailCallKind(const Function &F) {
objcarc::ARCInstKind Kind = objcarc::GetFunctionClass(&F);
if (objcarc::IsAlwaysTail(Kind))
return CallInst::TCK_Tail;
else if (objcarc::IsNeverTail(Kind))
return CallInst::TCK_NoTail;
return CallInst::TCK_None;
}
static bool lowerObjCCall(Function &F, const char *NewFn,
bool setNonLazyBind = false) {
assert(IntrinsicInst::mayLowerToFunctionCall(F.getIntrinsicID()) &&
"Pre-ISel intrinsics do lower into regular function calls");
if (F.use_empty())
return false;
// If we haven't already looked up this function, check to see if the
// program already contains a function with this name.
Module *M = F.getParent();
FunctionCallee FCache = M->getOrInsertFunction(NewFn, F.getFunctionType());
if (Function *Fn = dyn_cast<Function>(FCache.getCallee())) {
Fn->setLinkage(F.getLinkage());
if (setNonLazyBind && !Fn->isWeakForLinker()) {
// If we have Native ARC, set nonlazybind attribute for these APIs for
// performance.
Fn->addFnAttr(Attribute::NonLazyBind);
}
}
CallInst::TailCallKind OverridingTCK = getOverridingTailCallKind(F);
for (Use &U : llvm::make_early_inc_range(F.uses())) {
auto *CB = cast<CallBase>(U.getUser());
if (CB->getCalledFunction() != &F) {
objcarc::ARCInstKind Kind = objcarc::getAttachedARCFunctionKind(CB);
(void)Kind;
assert((Kind == objcarc::ARCInstKind::RetainRV ||
Kind == objcarc::ARCInstKind::UnsafeClaimRV) &&
"use expected to be the argument of operand bundle "
"\"clang.arc.attachedcall\"");
U.set(FCache.getCallee());
continue;
}
auto *CI = cast<CallInst>(CB);
assert(CI->getCalledFunction() && "Cannot lower an indirect call!");
IRBuilder<> Builder(CI->getParent(), CI->getIterator());
SmallVector<Value *, 8> Args(CI->args());
SmallVector<llvm::OperandBundleDef, 1> BundleList;
CI->getOperandBundlesAsDefs(BundleList);
CallInst *NewCI = Builder.CreateCall(FCache, Args, BundleList);
NewCI->setName(CI->getName());
// Try to set the most appropriate TailCallKind based on both the current
// attributes and the ones that we could get from ObjCARC's special
// knowledge of the runtime functions.
//
// std::max respects both requirements of notail and tail here:
// * notail on either the call or from ObjCARC becomes notail
// * tail on either side is stronger than none, but not notail
CallInst::TailCallKind TCK = CI->getTailCallKind();
NewCI->setTailCallKind(std::max(TCK, OverridingTCK));
// Transfer the 'returned' attribute from the intrinsic to the call site.
// By applying this only to intrinsic call sites, we avoid applying it to
// non-ARC explicit calls to things like objc_retain which have not been
// auto-upgraded to use the intrinsics.
unsigned Index;
if (F.getAttributes().hasAttrSomewhere(Attribute::Returned, &Index) &&
Index)
NewCI->addParamAttr(Index - AttributeList::FirstArgIndex,
Attribute::Returned);
if (!CI->use_empty())
CI->replaceAllUsesWith(NewCI);
CI->eraseFromParent();
}
return true;
}
// TODO: Should refine based on estimated number of accesses (e.g. does it
// require splitting based on alignment)
bool PreISelIntrinsicLowering::shouldExpandMemIntrinsicWithSize(
Value *Size, const TargetTransformInfo &TTI) {
ConstantInt *CI = dyn_cast<ConstantInt>(Size);
if (!CI)
return true;
uint64_t Threshold = MemIntrinsicExpandSizeThresholdOpt.getNumOccurrences()
? MemIntrinsicExpandSizeThresholdOpt
: TTI.getMaxMemIntrinsicInlineSizeThreshold();
uint64_t SizeVal = CI->getZExtValue();
// Treat a threshold of 0 as a special case to force expansion of all
// intrinsics, including size 0.
return SizeVal > Threshold || Threshold == 0;
}
static bool canEmitLibcall(const TargetMachine &TM, Function *F,
RTLIB::Libcall LC) {
// TODO: Should this consider the address space of the memcpy?
const TargetLowering *TLI = TM.getSubtargetImpl(*F)->getTargetLowering();
return TLI->getLibcallName(LC) != nullptr;
}
// TODO: Handle atomic memcpy and memcpy.inline
// TODO: Pass ScalarEvolution
bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
Intrinsic::ID ID = F.getIntrinsicID();
bool Changed = false;
for (User *U : llvm::make_early_inc_range(F.users())) {
Instruction *Inst = cast<Instruction>(U);
switch (ID) {
case Intrinsic::memcpy: {
auto *Memcpy = cast<MemCpyInst>(Inst);
Function *ParentFunc = Memcpy->getFunction();
const TargetTransformInfo &TTI = LookupTTI(*ParentFunc);
if (shouldExpandMemIntrinsicWithSize(Memcpy->getLength(), TTI)) {
if (UseMemIntrinsicLibFunc &&
canEmitLibcall(TM, ParentFunc, RTLIB::MEMCPY))
break;
// TODO: For optsize, emit the loop into a separate function
expandMemCpyAsLoop(Memcpy, TTI);
Changed = true;
Memcpy->eraseFromParent();
}
break;
}
case Intrinsic::memmove: {
auto *Memmove = cast<MemMoveInst>(Inst);
Function *ParentFunc = Memmove->getFunction();
const TargetTransformInfo &TTI = LookupTTI(*ParentFunc);
if (shouldExpandMemIntrinsicWithSize(Memmove->getLength(), TTI)) {
if (UseMemIntrinsicLibFunc &&
canEmitLibcall(TM, ParentFunc, RTLIB::MEMMOVE))
break;
if (expandMemMoveAsLoop(Memmove, TTI)) {
Changed = true;
Memmove->eraseFromParent();
}
}
break;
}
case Intrinsic::memset: {
auto *Memset = cast<MemSetInst>(Inst);
Function *ParentFunc = Memset->getFunction();
const TargetTransformInfo &TTI = LookupTTI(*ParentFunc);
if (shouldExpandMemIntrinsicWithSize(Memset->getLength(), TTI)) {
if (UseMemIntrinsicLibFunc &&
canEmitLibcall(TM, ParentFunc, RTLIB::MEMSET))
break;
expandMemSetAsLoop(Memset);
Changed = true;
Memset->eraseFromParent();
}
break;
}
default:
llvm_unreachable("unhandled intrinsic");
}
}
return Changed;
}
bool PreISelIntrinsicLowering::lowerIntrinsics(Module &M) const {
bool Changed = false;
for (Function &F : M) {
switch (F.getIntrinsicID()) {
default:
break;
case Intrinsic::memcpy:
case Intrinsic::memmove:
case Intrinsic::memset:
Changed |= expandMemIntrinsicUses(F);
break;
case Intrinsic::load_relative:
Changed |= lowerLoadRelative(F);
break;
case Intrinsic::objc_autorelease:
Changed |= lowerObjCCall(F, "objc_autorelease");
break;
case Intrinsic::objc_autoreleasePoolPop:
Changed |= lowerObjCCall(F, "objc_autoreleasePoolPop");
break;
case Intrinsic::objc_autoreleasePoolPush:
Changed |= lowerObjCCall(F, "objc_autoreleasePoolPush");
break;
case Intrinsic::objc_autoreleaseReturnValue:
Changed |= lowerObjCCall(F, "objc_autoreleaseReturnValue");
break;
case Intrinsic::objc_copyWeak:
Changed |= lowerObjCCall(F, "objc_copyWeak");
break;
case Intrinsic::objc_destroyWeak:
Changed |= lowerObjCCall(F, "objc_destroyWeak");
break;
case Intrinsic::objc_initWeak:
Changed |= lowerObjCCall(F, "objc_initWeak");
break;
case Intrinsic::objc_loadWeak:
Changed |= lowerObjCCall(F, "objc_loadWeak");
break;
case Intrinsic::objc_loadWeakRetained:
Changed |= lowerObjCCall(F, "objc_loadWeakRetained");
break;
case Intrinsic::objc_moveWeak:
Changed |= lowerObjCCall(F, "objc_moveWeak");
break;
case Intrinsic::objc_release:
Changed |= lowerObjCCall(F, "objc_release", true);
break;
case Intrinsic::objc_retain:
Changed |= lowerObjCCall(F, "objc_retain", true);
break;
case Intrinsic::objc_retainAutorelease:
Changed |= lowerObjCCall(F, "objc_retainAutorelease");
break;
case Intrinsic::objc_retainAutoreleaseReturnValue:
Changed |= lowerObjCCall(F, "objc_retainAutoreleaseReturnValue");
break;
case Intrinsic::objc_retainAutoreleasedReturnValue:
Changed |= lowerObjCCall(F, "objc_retainAutoreleasedReturnValue");
break;
case Intrinsic::objc_retainBlock:
Changed |= lowerObjCCall(F, "objc_retainBlock");
break;
case Intrinsic::objc_storeStrong:
Changed |= lowerObjCCall(F, "objc_storeStrong");
break;
case Intrinsic::objc_storeWeak:
Changed |= lowerObjCCall(F, "objc_storeWeak");
break;
case Intrinsic::objc_unsafeClaimAutoreleasedReturnValue:
Changed |= lowerObjCCall(F, "objc_unsafeClaimAutoreleasedReturnValue");
break;
case Intrinsic::objc_retainedObject:
Changed |= lowerObjCCall(F, "objc_retainedObject");
break;
case Intrinsic::objc_unretainedObject:
Changed |= lowerObjCCall(F, "objc_unretainedObject");
break;
case Intrinsic::objc_unretainedPointer:
Changed |= lowerObjCCall(F, "objc_unretainedPointer");
break;
case Intrinsic::objc_retain_autorelease:
Changed |= lowerObjCCall(F, "objc_retain_autorelease");
break;
case Intrinsic::objc_sync_enter:
Changed |= lowerObjCCall(F, "objc_sync_enter");
break;
case Intrinsic::objc_sync_exit:
Changed |= lowerObjCCall(F, "objc_sync_exit");
break;
}
}
return Changed;
}
namespace {
class PreISelIntrinsicLoweringLegacyPass : public ModulePass {
public:
static char ID;
PreISelIntrinsicLoweringLegacyPass() : ModulePass(ID) {}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<TargetTransformInfoWrapperPass>();
AU.addRequired<TargetPassConfig>();
}
bool runOnModule(Module &M) override {
auto LookupTTI = [this](Function &F) -> TargetTransformInfo & {
return this->getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
};
const auto &TM = getAnalysis<TargetPassConfig>().getTM<TargetMachine>();
PreISelIntrinsicLowering Lowering(TM, LookupTTI);
return Lowering.lowerIntrinsics(M);
}
};
} // end anonymous namespace
char PreISelIntrinsicLoweringLegacyPass::ID;
INITIALIZE_PASS_BEGIN(PreISelIntrinsicLoweringLegacyPass,
"pre-isel-intrinsic-lowering",
"Pre-ISel Intrinsic Lowering", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetPassConfig)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_END(PreISelIntrinsicLoweringLegacyPass,
"pre-isel-intrinsic-lowering",
"Pre-ISel Intrinsic Lowering", false, false)
ModulePass *llvm::createPreISelIntrinsicLoweringPass() {
return new PreISelIntrinsicLoweringLegacyPass();
}
PreservedAnalyses PreISelIntrinsicLoweringPass::run(Module &M,
ModuleAnalysisManager &AM) {
auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
auto LookupTTI = [&FAM](Function &F) -> TargetTransformInfo & {
return FAM.getResult<TargetIRAnalysis>(F);
};
PreISelIntrinsicLowering Lowering(TM, LookupTTI);
if (!Lowering.lowerIntrinsics(M))
return PreservedAnalyses::all();
else
return PreservedAnalyses::none();
}
|