aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm12/lib/Analysis/Loads.cpp
blob: 8f373f70f216c68acbaa9a41d9ce598ad15fa92e (plain) (blame)
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
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
//===- Loads.cpp - Local load analysis ------------------------------------===//
//
// 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 file defines simple local analyses for load instructions.
//
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/Loads.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CaptureTracking.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/GlobalAlias.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/Statepoint.h"

using namespace llvm;

static bool isAligned(const Value *Base, const APInt &Offset, Align Alignment,
                      const DataLayout &DL) {
  Align BA = Base->getPointerAlignment(DL);
  const APInt APAlign(Offset.getBitWidth(), Alignment.value());
  assert(APAlign.isPowerOf2() && "must be a power of 2!");
  return BA >= Alignment && !(Offset & (APAlign - 1));
}

/// Test if V is always a pointer to allocated and suitably aligned memory for
/// a simple load or store.
static bool isDereferenceableAndAlignedPointer(
    const Value *V, Align Alignment, const APInt &Size, const DataLayout &DL,
    const Instruction *CtxI, const DominatorTree *DT,
    SmallPtrSetImpl<const Value *> &Visited, unsigned MaxDepth) {
  assert(V->getType()->isPointerTy() && "Base must be pointer");

  // Recursion limit.
  if (MaxDepth-- == 0)
    return false;

  // Already visited?  Bail out, we've likely hit unreachable code.
  if (!Visited.insert(V).second)
    return false;

  // Note that it is not safe to speculate into a malloc'd region because
  // malloc may return null.

  // bitcast instructions are no-ops as far as dereferenceability is concerned.
  if (const BitCastOperator *BC = dyn_cast<BitCastOperator>(V)) {
    if (BC->getSrcTy()->isPointerTy())
      return isDereferenceableAndAlignedPointer(
          BC->getOperand(0), Alignment, Size, DL, CtxI, DT, Visited, MaxDepth);
  }

  bool CheckForNonNull = false;
  APInt KnownDerefBytes(Size.getBitWidth(),
                        V->getPointerDereferenceableBytes(DL, CheckForNonNull));
  if (KnownDerefBytes.getBoolValue() && KnownDerefBytes.uge(Size))
    if (!CheckForNonNull || isKnownNonZero(V, DL, 0, nullptr, CtxI, DT)) {
      // As we recursed through GEPs to get here, we've incrementally checked
      // that each step advanced by a multiple of the alignment. If our base is
      // properly aligned, then the original offset accessed must also be.
      Type *Ty = V->getType();
      assert(Ty->isSized() && "must be sized");
      APInt Offset(DL.getTypeStoreSizeInBits(Ty), 0);
      return isAligned(V, Offset, Alignment, DL);
    }

  // For GEPs, determine if the indexing lands within the allocated object.
  if (const GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
    const Value *Base = GEP->getPointerOperand();

    APInt Offset(DL.getIndexTypeSizeInBits(GEP->getType()), 0);
    if (!GEP->accumulateConstantOffset(DL, Offset) || Offset.isNegative() ||
        !Offset.urem(APInt(Offset.getBitWidth(), Alignment.value()))
             .isMinValue())
      return false;

    // If the base pointer is dereferenceable for Offset+Size bytes, then the
    // GEP (== Base + Offset) is dereferenceable for Size bytes.  If the base
    // pointer is aligned to Align bytes, and the Offset is divisible by Align
    // then the GEP (== Base + Offset == k_0 * Align + k_1 * Align) is also
    // aligned to Align bytes.

    // Offset and Size may have different bit widths if we have visited an
    // addrspacecast, so we can't do arithmetic directly on the APInt values.
    return isDereferenceableAndAlignedPointer(
        Base, Alignment, Offset + Size.sextOrTrunc(Offset.getBitWidth()), DL,
        CtxI, DT, Visited, MaxDepth);
  }

  // For gc.relocate, look through relocations
  if (const GCRelocateInst *RelocateInst = dyn_cast<GCRelocateInst>(V))
    return isDereferenceableAndAlignedPointer(
      RelocateInst->getDerivedPtr(), Alignment, Size, DL, CtxI, DT, Visited, MaxDepth);

  if (const AddrSpaceCastInst *ASC = dyn_cast<AddrSpaceCastInst>(V))
    return isDereferenceableAndAlignedPointer(ASC->getOperand(0), Alignment,
                                              Size, DL, CtxI, DT, Visited, MaxDepth);

  if (const auto *Call = dyn_cast<CallBase>(V)) {
    if (auto *RP = getArgumentAliasingToReturnedPointer(Call, true))
      return isDereferenceableAndAlignedPointer(RP, Alignment, Size, DL, CtxI,
                                                DT, Visited, MaxDepth);

    // If we have a call we can't recurse through, check to see if this is an
    // allocation function for which we can establish an minimum object size.
    // Such a minimum object size is analogous to a deref_or_null attribute in
    // that we still need to prove the result non-null at point of use.
    // NOTE: We can only use the object size as a base fact as we a) need to
    // prove alignment too, and b) don't want the compile time impact of a
    // separate recursive walk.
    ObjectSizeOpts Opts;
    // TODO: It may be okay to round to align, but that would imply that
    // accessing slightly out of bounds was legal, and we're currently
    // inconsistent about that.  For the moment, be conservative.
    Opts.RoundToAlign = false;
    Opts.NullIsUnknownSize = true;
    uint64_t ObjSize;
    // TODO: Plumb through TLI so that malloc routines and such working.
    if (getObjectSize(V, ObjSize, DL, nullptr, Opts)) {
      APInt KnownDerefBytes(Size.getBitWidth(), ObjSize);
      if (KnownDerefBytes.getBoolValue() && KnownDerefBytes.uge(Size) &&
          isKnownNonZero(V, DL, 0, nullptr, CtxI, DT) &&
          // TODO: We're currently inconsistent about whether deref(N) is a
          // global fact or a point in time fact.  Once D61652 eventually
          // lands, this check will be restricted to the point in time
          // variant. For that variant, we need to prove that object hasn't
          // been conditionally freed before ontext instruction - if it has, we
          // might be hoisting over the inverse conditional and creating a
          // dynamic use after free. 
          !PointerMayBeCapturedBefore(V, true, true, CtxI, DT, true)) {
        // As we recursed through GEPs to get here, we've incrementally
        // checked that each step advanced by a multiple of the alignment. If
        // our base is properly aligned, then the original offset accessed
        // must also be. 
        Type *Ty = V->getType();
        assert(Ty->isSized() && "must be sized");
        APInt Offset(DL.getTypeStoreSizeInBits(Ty), 0);
        return isAligned(V, Offset, Alignment, DL);
      }
    }
  }

  // If we don't know, assume the worst.
  return false;
}

bool llvm::isDereferenceableAndAlignedPointer(const Value *V, Align Alignment,
                                              const APInt &Size,
                                              const DataLayout &DL,
                                              const Instruction *CtxI,
                                              const DominatorTree *DT) {
  // Note: At the moment, Size can be zero.  This ends up being interpreted as
  // a query of whether [Base, V] is dereferenceable and V is aligned (since
  // that's what the implementation happened to do).  It's unclear if this is
  // the desired semantic, but at least SelectionDAG does exercise this case.

  SmallPtrSet<const Value *, 32> Visited;
  return ::isDereferenceableAndAlignedPointer(V, Alignment, Size, DL, CtxI, DT,
                                              Visited, 16);
}

bool llvm::isDereferenceableAndAlignedPointer(const Value *V, Type *Ty,
                                              MaybeAlign MA,
                                              const DataLayout &DL,
                                              const Instruction *CtxI,
                                              const DominatorTree *DT) {
  // For unsized types or scalable vectors we don't know exactly how many bytes
  // are dereferenced, so bail out.
  if (!Ty->isSized() || isa<ScalableVectorType>(Ty))
    return false;

  // When dereferenceability information is provided by a dereferenceable
  // attribute, we know exactly how many bytes are dereferenceable. If we can
  // determine the exact offset to the attributed variable, we can use that
  // information here.

  // Require ABI alignment for loads without alignment specification
  const Align Alignment = DL.getValueOrABITypeAlignment(MA, Ty);
  APInt AccessSize(DL.getPointerTypeSizeInBits(V->getType()),
                   DL.getTypeStoreSize(Ty));
  return isDereferenceableAndAlignedPointer(V, Alignment, AccessSize, DL, CtxI,
                                            DT);
}

bool llvm::isDereferenceablePointer(const Value *V, Type *Ty,
                                    const DataLayout &DL,
                                    const Instruction *CtxI,
                                    const DominatorTree *DT) {
  return isDereferenceableAndAlignedPointer(V, Ty, Align(1), DL, CtxI, DT);
}

/// Test if A and B will obviously have the same value.
///
/// This includes recognizing that %t0 and %t1 will have the same
/// value in code like this:
/// \code
///   %t0 = getelementptr \@a, 0, 3
///   store i32 0, i32* %t0
///   %t1 = getelementptr \@a, 0, 3
///   %t2 = load i32* %t1
/// \endcode
///
static bool AreEquivalentAddressValues(const Value *A, const Value *B) {
  // Test if the values are trivially equivalent.
  if (A == B)
    return true;

  // Test if the values come from identical arithmetic instructions.
  // Use isIdenticalToWhenDefined instead of isIdenticalTo because
  // this function is only used when one address use dominates the
  // other, which means that they'll always either have the same
  // value or one of them will have an undefined value.
  if (isa<BinaryOperator>(A) || isa<CastInst>(A) || isa<PHINode>(A) ||
      isa<GetElementPtrInst>(A))
    if (const Instruction *BI = dyn_cast<Instruction>(B))
      if (cast<Instruction>(A)->isIdenticalToWhenDefined(BI))
        return true;

  // Otherwise they may not be equivalent.
  return false;
}

bool llvm::isDereferenceableAndAlignedInLoop(LoadInst *LI, Loop *L,
                                             ScalarEvolution &SE,
                                             DominatorTree &DT) {
  auto &DL = LI->getModule()->getDataLayout();
  Value *Ptr = LI->getPointerOperand();

  APInt EltSize(DL.getIndexTypeSizeInBits(Ptr->getType()),
                DL.getTypeStoreSize(LI->getType()).getFixedSize());
  const Align Alignment = LI->getAlign();

  Instruction *HeaderFirstNonPHI = L->getHeader()->getFirstNonPHI();

  // If given a uniform (i.e. non-varying) address, see if we can prove the
  // access is safe within the loop w/o needing predication.
  if (L->isLoopInvariant(Ptr))
    return isDereferenceableAndAlignedPointer(Ptr, Alignment, EltSize, DL,
                                              HeaderFirstNonPHI, &DT);

  // Otherwise, check to see if we have a repeating access pattern where we can
  // prove that all accesses are well aligned and dereferenceable.
  auto *AddRec = dyn_cast<SCEVAddRecExpr>(SE.getSCEV(Ptr));
  if (!AddRec || AddRec->getLoop() != L || !AddRec->isAffine())
    return false;
  auto* Step = dyn_cast<SCEVConstant>(AddRec->getStepRecurrence(SE));
  if (!Step)
    return false;
  // TODO: generalize to access patterns which have gaps
  if (Step->getAPInt() != EltSize)
    return false;

  auto TC = SE.getSmallConstantMaxTripCount(L);
  if (!TC)
    return false;

  const APInt AccessSize = TC * EltSize;

  auto *StartS = dyn_cast<SCEVUnknown>(AddRec->getStart());
  if (!StartS)
    return false;
  assert(SE.isLoopInvariant(StartS, L) && "implied by addrec definition");
  Value *Base = StartS->getValue();

  // For the moment, restrict ourselves to the case where the access size is a
  // multiple of the requested alignment and the base is aligned.
  // TODO: generalize if a case found which warrants
  if (EltSize.urem(Alignment.value()) != 0)
    return false;
  return isDereferenceableAndAlignedPointer(Base, Alignment, AccessSize, DL,
                                            HeaderFirstNonPHI, &DT);
}

/// Check if executing a load of this pointer value cannot trap.
///
/// If DT and ScanFrom are specified this method performs context-sensitive
/// analysis and returns true if it is safe to load immediately before ScanFrom.
///
/// If it is not obviously safe to load from the specified pointer, we do
/// a quick local scan of the basic block containing \c ScanFrom, to determine
/// if the address is already accessed.
///
/// This uses the pointee type to determine how many bytes need to be safe to
/// load from the pointer.
bool llvm::isSafeToLoadUnconditionally(Value *V, Align Alignment, APInt &Size,
                                       const DataLayout &DL,
                                       Instruction *ScanFrom,
                                       const DominatorTree *DT) {
  // If DT is not specified we can't make context-sensitive query
  const Instruction* CtxI = DT ? ScanFrom : nullptr;
  if (isDereferenceableAndAlignedPointer(V, Alignment, Size, DL, CtxI, DT))
    return true;

  if (!ScanFrom)
    return false;

  if (Size.getBitWidth() > 64)
    return false;
  const uint64_t LoadSize = Size.getZExtValue();

  // Otherwise, be a little bit aggressive by scanning the local block where we
  // want to check to see if the pointer is already being loaded or stored
  // from/to.  If so, the previous load or store would have already trapped,
  // so there is no harm doing an extra load (also, CSE will later eliminate
  // the load entirely).
  BasicBlock::iterator BBI = ScanFrom->getIterator(),
                       E = ScanFrom->getParent()->begin();

  // We can at least always strip pointer casts even though we can't use the
  // base here.
  V = V->stripPointerCasts();

  while (BBI != E) {
    --BBI;

    // If we see a free or a call which may write to memory (i.e. which might do
    // a free) the pointer could be marked invalid.
    if (isa<CallInst>(BBI) && BBI->mayWriteToMemory() &&
        !isa<DbgInfoIntrinsic>(BBI))
      return false;

    Value *AccessedPtr;
    Type *AccessedTy;
    Align AccessedAlign;
    if (LoadInst *LI = dyn_cast<LoadInst>(BBI)) {
      // Ignore volatile loads. The execution of a volatile load cannot
      // be used to prove an address is backed by regular memory; it can,
      // for example, point to an MMIO register.
      if (LI->isVolatile())
        continue;
      AccessedPtr = LI->getPointerOperand();
      AccessedTy = LI->getType();
      AccessedAlign = LI->getAlign();
    } else if (StoreInst *SI = dyn_cast<StoreInst>(BBI)) {
      // Ignore volatile stores (see comment for loads).
      if (SI->isVolatile())
        continue;
      AccessedPtr = SI->getPointerOperand();
      AccessedTy = SI->getValueOperand()->getType();
      AccessedAlign = SI->getAlign();
    } else
      continue;

    if (AccessedAlign < Alignment)
      continue;

    // Handle trivial cases.
    if (AccessedPtr == V &&
        LoadSize <= DL.getTypeStoreSize(AccessedTy))
      return true;

    if (AreEquivalentAddressValues(AccessedPtr->stripPointerCasts(), V) &&
        LoadSize <= DL.getTypeStoreSize(AccessedTy))
      return true;
  }
  return false;
}

bool llvm::isSafeToLoadUnconditionally(Value *V, Type *Ty, Align Alignment,
                                       const DataLayout &DL,
                                       Instruction *ScanFrom,
                                       const DominatorTree *DT) {
  APInt Size(DL.getIndexTypeSizeInBits(V->getType()), DL.getTypeStoreSize(Ty));
  return isSafeToLoadUnconditionally(V, Alignment, Size, DL, ScanFrom, DT);
}

  /// DefMaxInstsToScan - the default number of maximum instructions
/// to scan in the block, used by FindAvailableLoadedValue().
/// FindAvailableLoadedValue() was introduced in r60148, to improve jump
/// threading in part by eliminating partially redundant loads.
/// At that point, the value of MaxInstsToScan was already set to '6'
/// without documented explanation.
cl::opt<unsigned>
llvm::DefMaxInstsToScan("available-load-scan-limit", cl::init(6), cl::Hidden,
  cl::desc("Use this to specify the default maximum number of instructions "
           "to scan backward from a given instruction, when searching for "
           "available loaded value"));

Value *llvm::FindAvailableLoadedValue(LoadInst *Load,
                                      BasicBlock *ScanBB,
                                      BasicBlock::iterator &ScanFrom,
                                      unsigned MaxInstsToScan,
                                      AAResults *AA, bool *IsLoad,
                                      unsigned *NumScanedInst) {
  // Don't CSE load that is volatile or anything stronger than unordered.
  if (!Load->isUnordered())
    return nullptr;

  return FindAvailablePtrLoadStore(
      Load->getPointerOperand(), Load->getType(), Load->isAtomic(), ScanBB,
      ScanFrom, MaxInstsToScan, AA, IsLoad, NumScanedInst);
}

// Check if the load and the store have the same base, constant offsets and
// non-overlapping access ranges.
static bool AreNonOverlapSameBaseLoadAndStore(
    Value *LoadPtr, Type *LoadTy, Value *StorePtr, Type *StoreTy,
    const DataLayout &DL) {
  APInt LoadOffset(DL.getTypeSizeInBits(LoadPtr->getType()), 0);
  APInt StoreOffset(DL.getTypeSizeInBits(StorePtr->getType()), 0);
  Value *LoadBase = LoadPtr->stripAndAccumulateConstantOffsets(
      DL, LoadOffset, /* AllowNonInbounds */ false);
  Value *StoreBase = StorePtr->stripAndAccumulateConstantOffsets(
      DL, StoreOffset, /* AllowNonInbounds */ false);
  if (LoadBase != StoreBase)
    return false;
  auto LoadAccessSize = LocationSize::precise(DL.getTypeStoreSize(LoadTy));
  auto StoreAccessSize = LocationSize::precise(DL.getTypeStoreSize(StoreTy));
  ConstantRange LoadRange(LoadOffset,
                          LoadOffset + LoadAccessSize.toRaw());
  ConstantRange StoreRange(StoreOffset,
                           StoreOffset + StoreAccessSize.toRaw());
  return LoadRange.intersectWith(StoreRange).isEmptySet();
}

Value *llvm::FindAvailablePtrLoadStore(Value *Ptr, Type *AccessTy,
                                       bool AtLeastAtomic, BasicBlock *ScanBB,
                                       BasicBlock::iterator &ScanFrom,
                                       unsigned MaxInstsToScan,
                                       AAResults *AA, bool *IsLoadCSE,
                                       unsigned *NumScanedInst) {
  if (MaxInstsToScan == 0)
    MaxInstsToScan = ~0U;

  const DataLayout &DL = ScanBB->getModule()->getDataLayout();
  Value *StrippedPtr = Ptr->stripPointerCasts();

  while (ScanFrom != ScanBB->begin()) {
    // We must ignore debug info directives when counting (otherwise they
    // would affect codegen).
    Instruction *Inst = &*--ScanFrom;
    if (isa<DbgInfoIntrinsic>(Inst))
      continue;

    // Restore ScanFrom to expected value in case next test succeeds
    ScanFrom++;

    if (NumScanedInst)
      ++(*NumScanedInst);

    // Don't scan huge blocks.
    if (MaxInstsToScan-- == 0)
      return nullptr;

    --ScanFrom;
    // If this is a load of Ptr, the loaded value is available.
    // (This is true even if the load is volatile or atomic, although
    // those cases are unlikely.)
    if (LoadInst *LI = dyn_cast<LoadInst>(Inst))
      if (AreEquivalentAddressValues(
              LI->getPointerOperand()->stripPointerCasts(), StrippedPtr) &&
          CastInst::isBitOrNoopPointerCastable(LI->getType(), AccessTy, DL)) {

        // We can value forward from an atomic to a non-atomic, but not the
        // other way around.
        if (LI->isAtomic() < AtLeastAtomic)
          return nullptr;

        if (IsLoadCSE)
            *IsLoadCSE = true;
        return LI;
      }

    // Try to get the store size for the type.
    auto AccessSize = LocationSize::precise(DL.getTypeStoreSize(AccessTy));

    if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
      Value *StorePtr = SI->getPointerOperand()->stripPointerCasts();
      // If this is a store through Ptr, the value is available!
      // (This is true even if the store is volatile or atomic, although
      // those cases are unlikely.)
      if (AreEquivalentAddressValues(StorePtr, StrippedPtr) &&
          CastInst::isBitOrNoopPointerCastable(SI->getValueOperand()->getType(),
                                               AccessTy, DL)) {

        // We can value forward from an atomic to a non-atomic, but not the
        // other way around.
        if (SI->isAtomic() < AtLeastAtomic)
          return nullptr;

        if (IsLoadCSE)
          *IsLoadCSE = false;
        return SI->getOperand(0);
      }

      // If both StrippedPtr and StorePtr reach all the way to an alloca or
      // global and they are different, ignore the store. This is a trivial form
      // of alias analysis that is important for reg2mem'd code.
      if ((isa<AllocaInst>(StrippedPtr) || isa<GlobalVariable>(StrippedPtr)) &&
          (isa<AllocaInst>(StorePtr) || isa<GlobalVariable>(StorePtr)) &&
          StrippedPtr != StorePtr)
        continue;

      if (!AA) {
        // When AA isn't available, but if the load and the store have the same
        // base, constant offsets and non-overlapping access ranges, ignore the
        // store. This is a simple form of alias analysis that is used by the
        // inliner. FIXME: use BasicAA if possible.
        if (AreNonOverlapSameBaseLoadAndStore(
                Ptr, AccessTy, SI->getPointerOperand(),
                SI->getValueOperand()->getType(), DL))
          continue;
      } else {
        // If we have alias analysis and it says the store won't modify the
        // loaded value, ignore the store.
        if (!isModSet(AA->getModRefInfo(SI, StrippedPtr, AccessSize)))
          continue;
      }

      // Otherwise the store that may or may not alias the pointer, bail out.
      ++ScanFrom;
      return nullptr;
    }

    // If this is some other instruction that may clobber Ptr, bail out.
    if (Inst->mayWriteToMemory()) {
      // If alias analysis claims that it really won't modify the load,
      // ignore it.
      if (AA && !isModSet(AA->getModRefInfo(Inst, StrippedPtr, AccessSize)))
        continue;

      // May modify the pointer, bail out.
      ++ScanFrom;
      return nullptr;
    }
  }

  // Got to the start of the block, we didn't find it, but are done for this
  // block.
  return nullptr;
}

bool llvm::canReplacePointersIfEqual(Value *A, Value *B, const DataLayout &DL,
                                     Instruction *CtxI) {
  Type *Ty = A->getType();
  assert(Ty == B->getType() && Ty->isPointerTy() &&
         "values must have matching pointer types");

  // NOTE: The checks in the function are incomplete and currently miss illegal
  // cases! The current implementation is a starting point and the
  // implementation should be made stricter over time.
  if (auto *C = dyn_cast<Constant>(B)) {
    // Do not allow replacing a pointer with a constant pointer, unless it is
    // either null or at least one byte is dereferenceable.
    APInt OneByte(DL.getPointerTypeSizeInBits(Ty), 1);
    return C->isNullValue() ||
           isDereferenceableAndAlignedPointer(B, Align(1), OneByte, DL, CtxI);
  }

  return true;
}