[CIR][NFC] Upstream LValueBaseInfo handling (#134928)

Previous implementations that used the cir::LValue class omitted hanling
of the LValueBaseInfo class, which tracks information about the basis
for the LValue's alignment. As more code was upstreamed from the
incubator, we were accumulating technical debt by adding more places
where this wasn't handled correctly. This change puts the interfaces in
place to track this information.

The information being tracked isn't used yet, so no functional change is
intended. The tracking is being added now because it will become more
difficult to add it as more features are implemented.

8 files changed, 89 insertions, 30 deletions

diff --git a/clang/include/clang/CIR/MissingFeatures.h b/clang/include/clang/CIR/MissingFeatures.h
index a180c19..3188429 100644
--- a/clang/include/clang/CIR/MissingFeatures.h
+++ b/clang/include/clang/CIR/MissingFeatures.h
@@ -108,11 +108,11 @@ struct MissingFeatures {
   static bool cgFPOptionsRAII() { return false; }
   static bool metaDataNode() { return false; }
   static bool fastMathFlags() { return false; }
-  static bool lvalueBaseInfo() { return false; }
   static bool alignCXXRecordDecl() { return false; }
   static bool setNonGC() { return false; }
   static bool incrementProfileCounter() { return false; }
   static bool insertBuiltinUnpredictable() { return false; }
+  static bool objCGC() { return false; }
 
   // Missing types
   static bool dataMemberType() { return false; }
diff --git a/clang/lib/CIR/CodeGen/CIRGenDecl.cpp b/clang/lib/CIR/CodeGen/CIRGenDecl.cpp
index d0eb648..b8e72f2 100644
--- a/clang/lib/CIR/CodeGen/CIRGenDecl.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenDecl.cpp
@@ -146,7 +146,7 @@ void CIRGenFunction::emitAutoVarInit(
   // its removal/optimization to the CIR lowering.
   if (!constant || isa<CXXTemporaryObjectExpr>(init)) {
     initializeWhatIsTechnicallyUninitialized(addr);
-    LValue lv = LValue::makeAddr(addr, type);
+    LValue lv = makeAddrLValue(addr, type, AlignmentSource::Decl);
     emitExprAsInit(init, &d, lv);
     // In case lv has uses it means we indeed initialized something
     // out of it while trying to build the expression, mark it as such.
@@ -165,7 +165,7 @@ void CIRGenFunction::emitAutoVarInit(
   assert(typedConstant && "expected typed attribute");
   if (!emission.IsConstantAggregate) {
     // For simple scalar/complex initialization, store the value directly.
-    LValue lv = LValue::makeAddr(addr, type);
+    LValue lv = makeAddrLValue(addr, type);
     assert(init && "expected initializer");
     mlir::Location initLoc = getLoc(init->getSourceRange());
     // lv.setNonGC(true);
diff --git a/clang/lib/CIR/CodeGen/CIRGenExpr.cpp b/clang/lib/CIR/CodeGen/CIRGenExpr.cpp
index 441d841..4b6652a 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExpr.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExpr.cpp
@@ -28,7 +28,8 @@ using namespace cir;
 
 /// Given an expression of pointer type, try to
 /// derive a more accurate bound on the alignment of the pointer.
-Address CIRGenFunction::emitPointerWithAlignment(const Expr *expr) {
+Address CIRGenFunction::emitPointerWithAlignment(const Expr *expr,
+                                                 LValueBaseInfo *baseInfo) {
   // We allow this with ObjC object pointers because of fragile ABIs.
   assert(expr->getType()->isPointerType() ||
          expr->getType()->isObjCObjectPointerType());
@@ -164,7 +165,8 @@ Address CIRGenFunction::emitPointerWithAlignment(const Expr *expr) {
 
   // Otherwise, use the alignment of the type.
   return makeNaturalAddressForPointer(
-      emitScalarExpr(expr), expr->getType()->getPointeeType(), CharUnits());
+      emitScalarExpr(expr), expr->getType()->getPointeeType(), CharUnits(),
+      /*forPointeeType=*/true, baseInfo);
 }
 
 void CIRGenFunction::emitStoreThroughLValue(RValue src, LValue dst,
@@ -300,7 +302,7 @@ LValue CIRGenFunction::emitDeclRefLValue(const DeclRefExpr *e) {
       cgm.errorNYI(vd->getSourceRange(), "emitDeclRefLValue: static local");
     }
 
-    return LValue::makeAddr(addr, ty);
+    return makeAddrLValue(addr, ty, AlignmentSource::Type);
   }
 
   cgm.errorNYI(e->getSourceRange(), "emitDeclRefLValue: unhandled decl type");
@@ -338,9 +340,9 @@ LValue CIRGenFunction::emitUnaryOpLValue(const UnaryOperator *e) {
     QualType t = e->getSubExpr()->getType()->getPointeeType();
     assert(!t.isNull() && "CodeGenFunction::EmitUnaryOpLValue: Illegal type");
 
-    assert(!cir::MissingFeatures::lvalueBaseInfo());
     assert(!cir::MissingFeatures::opTBAA());
-    Address addr = emitPointerWithAlignment(e->getSubExpr());
+    LValueBaseInfo baseInfo;
+    Address addr = emitPointerWithAlignment(e->getSubExpr(), &baseInfo);
 
     // Tag 'load' with deref attribute.
     // FIXME: This misses some derefence cases and has problematic interactions
@@ -350,7 +352,7 @@ LValue CIRGenFunction::emitUnaryOpLValue(const UnaryOperator *e) {
       loadOp.setIsDerefAttr(mlir::UnitAttr::get(&getMLIRContext()));
     }
 
-    LValue lv = LValue::makeAddr(addr, t);
+    LValue lv = makeAddrLValue(addr, t, baseInfo);
     assert(!cir::MissingFeatures::addressSpace());
     assert(!cir::MissingFeatures::setNonGC());
     return lv;
diff --git a/clang/lib/CIR/CodeGen/CIRGenExprAggregate.cpp b/clang/lib/CIR/CodeGen/CIRGenExprAggregate.cpp
index 36da63d..368a6cb 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExprAggregate.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExprAggregate.cpp
@@ -130,7 +130,7 @@ void AggExprEmitter::emitArrayInit(Address destPtr, cir::ArrayType arrayTy,
     }
 
     const Address address = Address(element, cirElementType, elementAlign);
-    const LValue elementLV = LValue::makeAddr(address, elementType);
+    const LValue elementLV = cgf.makeAddrLValue(address, elementType);
     emitInitializationToLValue(args[i], elementLV);
   }
 
@@ -157,7 +157,7 @@ void AggExprEmitter::emitArrayInit(Address destPtr, cir::ArrayType arrayTy,
     const Address tmpAddr = cgf.createTempAlloca(
         cirElementPtrType, cgf.getPointerAlign(), loc, "arrayinit.temp",
         /*insertIntoFnEntryBlock=*/false);
-    LValue tmpLV = LValue::makeAddr(tmpAddr, elementPtrType);
+    LValue tmpLV = cgf.makeAddrLValue(tmpAddr, elementPtrType);
     cgf.emitStoreThroughLValue(RValue::get(element), tmpLV);
 
     // TODO(CIR): Replace this part later with cir::DoWhileOp
@@ -166,7 +166,7 @@ void AggExprEmitter::emitArrayInit(Address destPtr, cir::ArrayType arrayTy,
           builder.createLoad(loc, tmpAddr.getPointer());
 
       // Emit the actual filler expression.
-      const LValue elementLV = LValue::makeAddr(
+      const LValue elementLV = cgf.makeAddrLValue(
           Address(currentElement, cirElementType, elementAlign), elementType);
 
       if (arrayFiller)
diff --git a/clang/lib/CIR/CodeGen/CIRGenFunction.h b/clang/lib/CIR/CodeGen/CIRGenFunction.h
index b1bfb55..6ffa106 100644
--- a/clang/lib/CIR/CodeGen/CIRGenFunction.h
+++ b/clang/lib/CIR/CodeGen/CIRGenFunction.h
@@ -242,12 +242,23 @@ public:
   /// been signed, and the returned Address will have the pointer authentication
   /// information needed to authenticate the signed pointer.
   Address makeNaturalAddressForPointer(mlir::Value ptr, QualType t,
-                                       CharUnits alignment) {
+                                       CharUnits alignment,
+                                       bool forPointeeType = false,
+                                       LValueBaseInfo *baseInfo = nullptr) {
     if (alignment.isZero())
-      alignment = cgm.getNaturalTypeAlignment(t);
+      alignment = cgm.getNaturalTypeAlignment(t, baseInfo);
     return Address(ptr, convertTypeForMem(t), alignment);
   }
 
+  LValue makeAddrLValue(Address addr, QualType ty,
+                        AlignmentSource source = AlignmentSource::Type) {
+    return makeAddrLValue(addr, ty, LValueBaseInfo(source));
+  }
+
+  LValue makeAddrLValue(Address addr, QualType ty, LValueBaseInfo baseInfo) {
+    return LValue::makeAddr(addr, ty, baseInfo);
+  }
+
   cir::FuncOp generateCode(clang::GlobalDecl gd, cir::FuncOp fn,
                            cir::FuncType funcType);
 
@@ -523,7 +534,8 @@ public:
   /// into the address of a local variable.  In such a case, it's quite
   /// reasonable to just ignore the returned alignment when it isn't from an
   /// explicit source.
-  Address emitPointerWithAlignment(const clang::Expr *expr);
+  Address emitPointerWithAlignment(const clang::Expr *expr,
+                                   LValueBaseInfo *baseInfo);
 
   mlir::LogicalResult emitReturnStmt(const clang::ReturnStmt &s);
 
diff --git a/clang/lib/CIR/CodeGen/CIRGenModule.cpp b/clang/lib/CIR/CodeGen/CIRGenModule.cpp
index 78d995b..d2259a9 100644
--- a/clang/lib/CIR/CodeGen/CIRGenModule.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenModule.cpp
@@ -74,18 +74,20 @@ CIRGenModule::CIRGenModule(mlir::MLIRContext &mlirContext,
                      builder.getStringAttr(getTriple().str()));
 }
 
-CharUnits CIRGenModule::getNaturalTypeAlignment(QualType t) {
+CharUnits CIRGenModule::getNaturalTypeAlignment(QualType t,
+                                                LValueBaseInfo *baseInfo) {
   assert(!cir::MissingFeatures::opTBAA());
 
-  // FIXME: This duplicates logic in ASTContext::getTypeAlignIfKnown. But
-  // that doesn't return the information we need to compute BaseInfo.
+  // FIXME: This duplicates logic in ASTContext::getTypeAlignIfKnown, but
+  // that doesn't return the information we need to compute baseInfo.
 
   // Honor alignment typedef attributes even on incomplete types.
   // We also honor them straight for C++ class types, even as pointees;
   // there's an expressivity gap here.
   if (const auto *tt = t->getAs<TypedefType>()) {
     if (unsigned align = tt->getDecl()->getMaxAlignment()) {
-      assert(!cir::MissingFeatures::lvalueBaseInfo());
+      if (baseInfo)
+        *baseInfo = LValueBaseInfo(AlignmentSource::AttributedType);
       return astContext.toCharUnitsFromBits(align);
     }
   }
@@ -99,13 +101,15 @@ CharUnits CIRGenModule::getNaturalTypeAlignment(QualType t) {
     // ASTContext::getTypeAlignIfKnown, but nothing uses the alignment if the
     // type is incomplete, so it's impossible to test. We could try to reuse
     // getTypeAlignIfKnown, but that doesn't return the information we need
-    // to set BaseInfo.  So just ignore the possibility that the alignment is
+    // to set baseInfo.  So just ignore the possibility that the alignment is
     // greater than one.
-    assert(!cir::MissingFeatures::lvalueBaseInfo());
+    if (baseInfo)
+      *baseInfo = LValueBaseInfo(AlignmentSource::Type);
     return CharUnits::One();
   }
 
-  assert(!cir::MissingFeatures::lvalueBaseInfo());
+  if (baseInfo)
+    *baseInfo = LValueBaseInfo(AlignmentSource::Type);
 
   CharUnits alignment;
   if (t.getQualifiers().hasUnaligned()) {
diff --git a/clang/lib/CIR/CodeGen/CIRGenModule.h b/clang/lib/CIR/CodeGen/CIRGenModule.h
index 66e9faa..fe39244 100644
--- a/clang/lib/CIR/CodeGen/CIRGenModule.h
+++ b/clang/lib/CIR/CodeGen/CIRGenModule.h
@@ -16,6 +16,7 @@
 #include "CIRGenBuilder.h"
 #include "CIRGenTypeCache.h"
 #include "CIRGenTypes.h"
+#include "CIRGenValue.h"
 
 #include "clang/AST/CharUnits.h"
 #include "clang/CIR/Dialect/IR/CIRDialect.h"
@@ -91,7 +92,8 @@ public:
 
   /// FIXME: this could likely be a common helper and not necessarily related
   /// with codegen.
-  clang::CharUnits getNaturalTypeAlignment(clang::QualType t);
+  clang::CharUnits getNaturalTypeAlignment(clang::QualType t,
+                                           LValueBaseInfo *baseInfo);
 
   void emitTopLevelDecl(clang::Decl *decl);
 
diff --git a/clang/lib/CIR/CodeGen/CIRGenValue.h b/clang/lib/CIR/CodeGen/CIRGenValue.h
index 68aecc6..1b702daa 100644
--- a/clang/lib/CIR/CodeGen/CIRGenValue.h
+++ b/clang/lib/CIR/CodeGen/CIRGenValue.h
@@ -75,6 +75,28 @@ enum class AlignmentSource {
   Type
 };
 
+/// Given that the base address has the given alignment source, what's
+/// our confidence in the alignment of the field?
+static inline AlignmentSource getFieldAlignmentSource(AlignmentSource source) {
+  // For now, we don't distinguish fields of opaque pointers from
+  // top-level declarations, but maybe we should.
+  return AlignmentSource::Decl;
+}
+
+class LValueBaseInfo {
+  AlignmentSource alignSource;
+
+public:
+  explicit LValueBaseInfo(AlignmentSource source = AlignmentSource::Type)
+      : alignSource(source) {}
+  AlignmentSource getAlignmentSource() const { return alignSource; }
+  void setAlignmentSource(AlignmentSource source) { alignSource = source; }
+
+  void mergeForCast(const LValueBaseInfo &info) {
+    setAlignmentSource(info.getAlignmentSource());
+  }
+};
+
 class LValue {
   enum {
     Simple,       // This is a normal l-value, use getAddress().
@@ -87,13 +109,26 @@ class LValue {
   clang::QualType type;
   clang::Qualifiers quals;
 
+  // The alignment to use when accessing this lvalue. (For vector elements,
+  // this is the alignment of the whole vector)
+  unsigned alignment;
   mlir::Value v;
   mlir::Type elementType;
+  LValueBaseInfo baseInfo;
 
-  void initialize(clang::QualType type, clang::Qualifiers quals) {
-    assert(!cir::MissingFeatures::lvalueBaseInfo());
+  void initialize(clang::QualType type, clang::Qualifiers quals,
+                  clang::CharUnits alignment, LValueBaseInfo baseInfo) {
+    assert((!alignment.isZero() || type->isIncompleteType()) &&
+           "initializing l-value with zero alignment!");
     this->type = type;
     this->quals = quals;
+    const unsigned maxAlign = 1U << 31;
+    this->alignment = alignment.getQuantity() <= maxAlign
+                          ? alignment.getQuantity()
+                          : maxAlign;
+    assert(this->alignment == alignment.getQuantity() &&
+           "Alignment exceeds allowed max!");
+    this->baseInfo = baseInfo;
   }
 
 public:
@@ -108,9 +143,9 @@ public:
   mlir::Value getPointer() const { return v; }
 
   clang::CharUnits getAlignment() const {
-    // TODO: Handle alignment
-    return clang::CharUnits::One();
+    return clang::CharUnits::fromQuantity(alignment);
   }
+  void setAlignment(clang::CharUnits a) { alignment = a.getQuantity(); }
 
   Address getAddress() const {
     return Address(getPointer(), elementType, getAlignment());
@@ -118,13 +153,17 @@ public:
 
   const clang::Qualifiers &getQuals() const { return quals; }
 
-  static LValue makeAddr(Address address, clang::QualType t) {
+  static LValue makeAddr(Address address, clang::QualType t,
+                         LValueBaseInfo baseInfo) {
+    // Classic codegen sets the objc gc qualifier here. That requires an
+    // ASTContext, which is passed in from CIRGenFunction::makeAddrLValue.
+    assert(!cir::MissingFeatures::objCGC());
+
     LValue r;
     r.lvType = Simple;
     r.v = address.getPointer();
     r.elementType = address.getElementType();
-    r.initialize(t, t.getQualifiers());
-    assert(!cir::MissingFeatures::lvalueBaseInfo());
+    r.initialize(t, t.getQualifiers(), address.getAlignment(), baseInfo);
     return r;
   }
 };