[IR] Change representation of getelementptr inrange (#84341)

As part of the migration to ptradd
(https://discourse.llvm.org/t/rfc-replacing-getelementptr-with-ptradd/68699),
we need to change the representation of the `inrange` attribute, which
is used for vtable splitting.

Currently, inrange is specified as follows:

```
getelementptr inbounds ({ [4 x ptr], [4 x ptr] }, ptr @vt, i64 0, inrange i32 1, i64 2)
```

The `inrange` is placed on a GEP index, and all accesses must be "in
range" of that index. The new representation is as follows:

```
getelementptr inbounds inrange(-16, 16) ({ [4 x ptr], [4 x ptr] }, ptr @vt, i64 0, i32 1, i64 2)
```

This specifies which offsets are "in range" of the GEP result. The new
representation will continue working when canonicalizing to ptradd
representation:

```
getelementptr inbounds inrange(-16, 16) (i8, ptr @vt, i64 48)
```

The inrange offsets are relative to the return value of the GEP. An
alternative design could make them relative to the source pointer
instead. The result-relative format was chosen on the off-chance that we
want to extend support to non-constant GEPs in the future, in which case
this variant is more expressive.

This implementation "upgrades" the old inrange representation in bitcode
by simply dropping it. This is a very niche feature, and I don't think
trying to upgrade it is worthwhile. Let me know if you disagree.

1 files changed, 19 insertions, 24 deletions

diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp
index 6b2e88d..6139b5b 100644
--- a/llvm/lib/Analysis/ConstantFolding.cpp
+++ b/llvm/lib/Analysis/ConstantFolding.cpp
@@ -828,7 +828,7 @@ Constant *SymbolicallyEvaluateBinop(unsigned Opc, Constant *Op0, Constant *Op1,
 /// that they aren't implicitly casted by the getelementptr.
 Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef<Constant *> Ops,
                          Type *ResultTy, bool InBounds,
-                         std::optional<unsigned> InRangeIndex,
+                         std::optional<ConstantRange> InRange,
                          const DataLayout &DL, const TargetLibraryInfo *TLI) {
   Type *IntIdxTy = DL.getIndexType(ResultTy);
   Type *IntIdxScalarTy = IntIdxTy->getScalarType();
@@ -856,8 +856,8 @@ Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef<Constant *> Ops,
   if (!Any)
     return nullptr;
 
-  Constant *C = ConstantExpr::getGetElementPtr(
-      SrcElemTy, Ops[0], NewIdxs, InBounds, InRangeIndex);
+  Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ops[0], NewIdxs,
+                                               InBounds, InRange);
   return ConstantFoldConstant(C, DL, TLI);
 }
 
@@ -866,7 +866,6 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
                                   ArrayRef<Constant *> Ops,
                                   const DataLayout &DL,
                                   const TargetLibraryInfo *TLI) {
-  const GEPOperator *InnermostGEP = GEP;
   bool InBounds = GEP->isInBounds();
 
   Type *SrcElemTy = GEP->getSourceElementType();
@@ -875,9 +874,8 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
   if (!SrcElemTy->isSized() || isa<ScalableVectorType>(SrcElemTy))
     return nullptr;
 
-  if (Constant *C = CastGEPIndices(SrcElemTy, Ops, ResTy,
-                                   GEP->isInBounds(), GEP->getInRangeIndex(),
-                                   DL, TLI))
+  if (Constant *C = CastGEPIndices(SrcElemTy, Ops, ResTy, GEP->isInBounds(),
+                                   GEP->getInRange(), DL, TLI))
     return C;
 
   Constant *Ptr = Ops[0];
@@ -896,9 +894,12 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
       DL.getIndexedOffsetInType(
           SrcElemTy, ArrayRef((Value *const *)Ops.data() + 1, Ops.size() - 1)));
 
+  std::optional<ConstantRange> InRange = GEP->getInRange();
+  if (InRange)
+    InRange = InRange->sextOrTrunc(BitWidth);
+
   // If this is a GEP of a GEP, fold it all into a single GEP.
   while (auto *GEP = dyn_cast<GEPOperator>(Ptr)) {
-    InnermostGEP = GEP;
     InBounds &= GEP->isInBounds();
 
     SmallVector<Value *, 4> NestedOps(llvm::drop_begin(GEP->operands()));
@@ -913,6 +914,14 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
     if (!AllConstantInt)
       break;
 
+    // TODO: Try to intersect two inrange attributes?
+    if (!InRange) {
+      InRange = GEP->getInRange();
+      if (InRange)
+        // Adjust inrange by offset until now.
+        InRange = InRange->sextOrTrunc(BitWidth).subtract(Offset);
+    }
+
     Ptr = cast<Constant>(GEP->getOperand(0));
     SrcElemTy = GEP->getSourceElementType();
     Offset += APInt(BitWidth, DL.getIndexedOffsetInType(SrcElemTy, NestedOps));
@@ -971,21 +980,8 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
     NewIdxs.push_back(ConstantInt::get(
         Type::getIntNTy(Ptr->getContext(), Index.getBitWidth()), Index));
 
-  // Preserve the inrange index from the innermost GEP if possible. We must
-  // have calculated the same indices up to and including the inrange index.
-  std::optional<unsigned> InRangeIndex;
-  if (std::optional<unsigned> LastIRIndex = InnermostGEP->getInRangeIndex())
-    if (SrcElemTy == InnermostGEP->getSourceElementType() &&
-        NewIdxs.size() > *LastIRIndex) {
-      InRangeIndex = LastIRIndex;
-      for (unsigned I = 0; I <= *LastIRIndex; ++I)
-        if (NewIdxs[I] != InnermostGEP->getOperand(I + 1))
-          return nullptr;
-    }
-
-  // Create a GEP.
   return ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs, InBounds,
-                                        InRangeIndex);
+                                        InRange);
 }
 
 /// Attempt to constant fold an instruction with the
@@ -1033,8 +1029,7 @@ Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, unsigned Opcode,
       return C;
 
     return ConstantExpr::getGetElementPtr(SrcElemTy, Ops[0], Ops.slice(1),
-                                          GEP->isInBounds(),
-                                          GEP->getInRangeIndex());
+                                          GEP->isInBounds(), GEP->getInRange());
   }
 
   if (auto *CE = dyn_cast<ConstantExpr>(InstOrCE)) {