[ConstFold] Support opaque pointers in constexpr GEPs

[nikic]

Summary

Support opaque pointers in SymbolicallyEvaluateGEP by using the value type of a GlobalValue base or falling back to i8 if there isn't one. We don't unconditionally generate i8 GEPs here because that would lose inrange, and because some optimizations on globals currently rely on GEP types (e.g. the globals SROA mentioned in the comment).

llvm/lib/Analysis/ConstantFolding.cpp

Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
   }
 
   // Otherwise form a regular getelementptr. Recompute the indices so that
   // we eliminate over-indexing of the notional static type array bounds.
   // This makes it easy to determine if the getelementptr is "inbounds".
   // Also, this helps GlobalOpt do SROA on GlobalVariables.
   SmallVector<Constant *, 32> NewIdxs;
   Type *Ty = PTy;
+
+  // For GEPs of GlobalValues, use the value type even for opaque pointers.
+  // Otherwise use an i8 GEP.
+  if (auto *GV = dyn_cast<GlobalValue>(Ptr))
+    SrcElemTy = GV->getValueType();
+  else if (!PTy->isOpaque())
     SrcElemTy = PTy->getElementType();
+  else
+    SrcElemTy = Type::getInt8Ty(Ptr->getContext());
 
   do {
     if (!Ty->isStructTy()) {
       if (Ty->isPointerTy()) {
         // The only pointer indexing we'll do is on the first index of the GEP.
         if (!NewIdxs.empty())
           break;
 
if (SrcElemTy == InnermostGEP->getSourceElementType() &&
       for (unsigned I = 0; I <= *LastIRIndex; ++I)
         if (NewIdxs[I] != InnermostGEP->getOperand(I + 1))
           return nullptr;
     }
 
   // Create a GEP.
   Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs,
                                                InBounds, InRangeIndex);
-  assert(C->getType()->getPointerElementType() == Ty &&
+  assert(cast<PointerType>(C->getType())->isOpaqueOrPointeeTypeMatches(Ty) &&
          "Computed GetElementPtr has unexpected type!");
 
   // If we ended up indexing a member with a type that doesn't match
   // the type of what the original indices indexed, add a cast.
   if (C->getType() != ResTy)
     C = FoldBitCast(C, ResTy, DL);
 
   return C;

llvm/test/Transforms/InstCombine/force-opaque-ptr.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -instcombine -force-opaque-pointers < %s | FileCheck %s
+
+@g = global [16 x i16] zeroinitializer
+
+define ptr @gep_constexpr_gv_1() {
+; CHECK-LABEL: @gep_constexpr_gv_1(
+; CHECK-NEXT:    ret ptr getelementptr inbounds ([16 x i16], ptr @g, i64 0, i64 10)
+;
+  ret ptr getelementptr([16 x i16], ptr @g, i64 0, i64 10)
+}
+
+define ptr @gep_constexpr_gv_2() {
+; CHECK-LABEL: @gep_constexpr_gv_2(
+; CHECK-NEXT:    ret ptr getelementptr inbounds ([16 x i16], ptr @g, i64 0, i64 12)
+;
+  ret ptr getelementptr(i32, ptr getelementptr([16 x i16], ptr @g, i64 0, i64 10), i64 1)
+}
+
+; Silly expression to get an inttoptr that does not combine with the GEP.
+define ptr @gep_constexpr_inttoptr() {
+; CHECK-LABEL: @gep_constexpr_inttoptr(
+; CHECK-NEXT:    ret ptr getelementptr (i8, ptr inttoptr (i64 mul (i64 ptrtoint (ptr @g to i64), i64 2) to ptr), i64 20)
+;
+  ret ptr getelementptr([16 x i16], ptr inttoptr (i64 mul (i64 ptrtoint ([16 x i16]* @g to i64), i64 2) to ptr), i64 0, i64 10)
+}