[Local] replaceAllDbgUsesWith: Update debug values before RAUW

The replaceAllDbgUsesWith utility helps passes preserve debug info when
replacing one value with another.

This improves upon the existing insertReplacementDbgValues API by:

- Updating debug intrinsics in-place, while preventing use-before-def of
  the replacement value.
- Falling back to salvageDebugInfo when a replacement can't be made.
- Moving the responsibiliy for rewriting llvm.dbg.* DIExpressions into
  common utility code.

Along with the API change, this teaches replaceAllDbgUsesWith how to
create DIExpressions for three basic integer and pointer conversions:

- The no-op conversion. Applies when the values have the same width, or
  have bit-for-bit compatible pointer representations.
- Truncation. Applies when the new value is wider than the old one.
- Zero/sign extension. Applies when the new value is narrower than the
  old one.

Testing:

- check-llvm, check-clang, a stage2 `-g -O3` build of clang,
  regression/unit testing.
- This resolves a number of mis-sized dbg.value diagnostics from
  Debugify.

Differential Revision: https://reviews.llvm.org/D48676

llvm-svn: 336451

llvm/include/llvm/IR/DebugInfoMetadata.h

@@ -778,6 +778,12 @@ class DIBasicType : public DIType {
 
   unsigned getEncoding() const { return Encoding; }
 
+  enum class Signedness { Signed, Unsigned };
+
+  /// Return the signedness of this type, or None if this type is neither
+  /// signed nor unsigned.
+  Optional<Signedness> getSignedness() const;
+
   static bool classof(const Metadata *MD) {
     return MD->getMetadataID() == DIBasicTypeKind;
   }
@@ -2206,6 +2212,14 @@ class DIVariable : public DINode {
   /// Determines the size of the variable's type.
   Optional<uint64_t> getSizeInBits() const;
 
+  /// Return the signedness of this variable's type, or None if this type is
+  /// neither signed nor unsigned.
+  Optional<DIBasicType::Signedness> getSignedness() const {
+    if (auto *BT = dyn_cast<DIBasicType>(getType().resolve()))
+      return BT->getSignedness();
+    return None;
+  }
+
   StringRef getFilename() const {
     if (auto *F = getFile())
       return F->getFilename();
@@ -2312,6 +2326,11 @@ class DIExpression : public MDNode {
     ///
     /// Return the number of elements in the operand (1 + args).
     unsigned getSize() const;
+
+    /// Append the elements of this operand to \p V.
+    void appendToVector(SmallVectorImpl<uint64_t> &V) const {
+      V.append(getSize(), *get());
+    }
   };
 
   /// An iterator for expression operands.
@@ -2425,6 +2444,13 @@ class DIExpression : public MDNode {
                                       SmallVectorImpl<uint64_t> &Ops,
                                       bool StackValue = false);
 
+  /// Convert \p DIExpr into a stack value if it isn't one already by appending
+  /// DW_OP_deref if needed, and applying \p Ops to the resulting expression.
+  /// If \p DIExpr is a fragment, the returned expression will contain the same
+  /// fragment.
+  static DIExpression *appendToStack(const DIExpression *DIExpr,
+                                     ArrayRef<uint64_t> Ops);
+
   /// Create a DIExpression to describe one part of an aggregate variable that
   /// is fragmented across multiple Values. The DW_OP_LLVM_fragment operation
   /// will be appended to the elements of \c Expr. If \c Expr already contains

llvm/include/llvm/IR/Type.h

@@ -208,6 +208,9 @@ class Type {
     return getScalarType()->isIntegerTy(BitWidth);
   }
 
+  /// Return true if this is an integer type or a pointer type.
+  bool isIntOrPtrTy() const { return isIntegerTy() || isPointerTy(); }
+
   /// True if this is an instance of FunctionType.
   bool isFunctionTy() const { return getTypeID() == FunctionTyID; }
 

llvm/include/llvm/Transforms/Utils/Local.h

@@ -329,27 +329,27 @@ bool replaceDbgDeclareForAlloca(AllocaInst *AI, Value *NewAllocaAddress,
 void replaceDbgValueForAlloca(AllocaInst *AI, Value *NewAllocaAddress,
                               DIBuilder &Builder, int Offset = 0);
 
-/// Assuming the instruction \p I is going to be deleted, attempt to salvage any
-/// dbg.value intrinsics referring to \p I by rewriting its effect into a
-/// DIExpression.
-void salvageDebugInfo(Instruction &I);
-
-/// Assuming the value \p From is going to be deleted, insert replacement
-/// dbg.value intrinsics for each debug user of \p From. The newly-inserted
-/// dbg.values refer to \p To instead of \p From. Each replacement dbg.value
-/// has the same location and variable as the debug user it replaces, has a
-/// DIExpression determined by the result of \p RewriteExpr applied to an old
-/// debug user of \p From, and is placed before \p InsertBefore. If
-/// \p RewriteExpr returns nullptr, no replacement for the specified debug
-/// user is emitted.
-void insertReplacementDbgValues(
-    Value &From, Value &To, Instruction &InsertBefore,
-    function_ref<DIExpression *(DbgInfoIntrinsic &OldDII)> RewriteExpr);
-
-/// An overload of insertReplacementDbgValues() for the common case where
-/// the replacement dbg.values have the same DIExpressions as the originals.
-void insertReplacementDbgValues(Value &From, Value &To,
-                                Instruction &InsertBefore);
+/// Assuming the instruction \p I is going to be deleted, attempt to salvage
+/// debug users of \p I by writing the effect of \p I in a DIExpression.
+/// Returns true if any debug users were updated.
+bool salvageDebugInfo(Instruction &I);
+
+/// Point debug users of \p From to \p To or salvage them. Use this function
+/// only when replacing all uses of \p From with \p To, with a guarantee that
+/// \p From is going to be deleted.
+///
+/// Follow these rules to prevent use-before-def of \p To:
+///   . If \p To is a linked Instruction, set \p DomPoint to \p To.
+///   . If \p To is an unlinked Instruction, set \p DomPoint to the Instruction
+///     \p To will be inserted after.
+///   . If \p To is not an Instruction (e.g a Constant), the choice of
+///     \p DomPoint is arbitrary. Pick \p From for simplicity.
+///
+/// If a debug user cannot be preserved without reordering variable updates or
+/// introducing a use-before-def, it is either salvaged (\ref salvageDebugInfo)
+/// or deleted. Returns true if any debug users were updated.
+bool replaceAllDbgUsesWith(Instruction &From, Value &To, Instruction &DomPoint,
+                           DominatorTree &DT);
 
 /// Remove all instructions from a basic block other than it's terminator
 /// and any present EH pad instructions.

llvm/lib/CodeGen/AsmPrinter/DwarfExpression.cpp

@@ -357,6 +357,9 @@ void DwarfExpression::addExpression(DIExpressionCursor &&ExprCursor,
     case dwarf::DW_OP_shl:
     case dwarf::DW_OP_shr:
     case dwarf::DW_OP_shra:
+    case dwarf::DW_OP_lit0:
+    case dwarf::DW_OP_not:
+    case dwarf::DW_OP_dup:
       emitOp(Op->getOp());
       break;
     case dwarf::DW_OP_deref:

llvm/lib/IR/DebugInfoMetadata.cpp

@@ -283,6 +283,19 @@ DIBasicType *DIBasicType::getImpl(LLVMContext &Context, unsigned Tag,
                        Ops);
 }
 
+Optional<DIBasicType::Signedness> DIBasicType::getSignedness() const {
+  switch (getEncoding()) {
+  case dwarf::DW_ATE_signed:
+  case dwarf::DW_ATE_signed_char:
+    return Signedness::Signed;
+  case dwarf::DW_ATE_unsigned:
+  case dwarf::DW_ATE_unsigned_char:
+    return Signedness::Unsigned;
+  default:
+    return None;
+  }
+}
+
 DIDerivedType *DIDerivedType::getImpl(
     LLVMContext &Context, unsigned Tag, MDString *Name, Metadata *File,
     unsigned Line, Metadata *Scope, Metadata *BaseType, uint64_t SizeInBits,
@@ -733,6 +746,9 @@ bool DIExpression::isValid() const {
     case dwarf::DW_OP_shra:
     case dwarf::DW_OP_deref:
     case dwarf::DW_OP_xderef:
+    case dwarf::DW_OP_lit0:
+    case dwarf::DW_OP_not:
+    case dwarf::DW_OP_dup:
       break;
     }
   }
@@ -826,6 +842,42 @@ DIExpression *DIExpression::prependOpcodes(const DIExpression *Expr,
   return DIExpression::get(Expr->getContext(), Ops);
 }
 
+DIExpression *DIExpression::appendToStack(const DIExpression *Expr,
+                                          ArrayRef<uint64_t> Ops) {
+  assert(Expr && !Ops.empty() && "Can't append ops to this expression");
+
+  // Append a DW_OP_deref after Expr's current op list if it's non-empty and
+  // has no DW_OP_stack_value.
+  //
+  // Match .* DW_OP_stack_value (DW_OP_LLVM_fragment A B)?.
+  Optional<FragmentInfo> FI = Expr->getFragmentInfo();
+  unsigned DropUntilStackValue = FI.hasValue() ? 3 : 0;
+  bool NeedsDeref =
+      (Expr->getNumElements() > DropUntilStackValue) &&
+      (Expr->getElements().drop_back(DropUntilStackValue).back() !=
+       dwarf::DW_OP_stack_value);
+
+  // Copy Expr's current op list, add a DW_OP_deref if needed, and ensure that
+  // a DW_OP_stack_value is present.
+  SmallVector<uint64_t, 16> NewOps;
+  for (auto Op : Expr->expr_ops()) {
+    if (Op.getOp() == dwarf::DW_OP_stack_value ||
+        Op.getOp() == dwarf::DW_OP_LLVM_fragment)
+      break;
+    Op.appendToVector(NewOps);
+  }
+  if (NeedsDeref)
+    NewOps.push_back(dwarf::DW_OP_deref);
+  NewOps.append(Ops.begin(), Ops.end());
+  NewOps.push_back(dwarf::DW_OP_stack_value);
+
+  // If Expr is a fragment, make the new expression a fragment as well.
+  if (FI)
+    NewOps.append(
+        {dwarf::DW_OP_LLVM_fragment, FI->OffsetInBits, FI->SizeInBits});
+  return DIExpression::get(Expr->getContext(), NewOps);
+}
+
 Optional<DIExpression *> DIExpression::createFragmentExpression(
     const DIExpression *Expr, unsigned OffsetInBits, unsigned SizeInBits) {
   SmallVector<uint64_t, 8> Ops;

llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp

@@ -268,11 +268,9 @@ Instruction *InstCombiner::commonCastTransforms(CastInst &CI) {
       // the second cast (CI). CSrc will then have a good chance of being dead.
       auto *Ty = CI.getType();
       auto *Res = CastInst::Create(NewOpc, CSrc->getOperand(0), Ty);
-      // Replace debug users of the eliminable cast by emitting debug values
-      // which refer to the new cast.
-      if (Ty->isIntegerTy() || Ty->isPointerTy())
-        // TODO: Support floats and vectors (see DW_OP_convert, fragment).
-        insertReplacementDbgValues(*CSrc, *Res, *std::next(CI.getIterator()));
+      // Point debug users of the dying cast to the new one.
+      if (CSrc->hasOneUse())
+        replaceAllDbgUsesWith(*CSrc, *Res, CI, DT);
       return Res;
     }
   }
@@ -1079,16 +1077,10 @@ Instruction *InstCombiner::visitZExt(ZExtInst &CI) {
     Value *Res = EvaluateInDifferentType(Src, DestTy, false);
     assert(Res->getType() == DestTy);
 
-    // When DestTy is integer, try to preserve any debug values referring
-    // to the zext being replaced.
-    // TODO: This should work for vectors as well, possibly via the use
-    // of DWARF fragments.
-    if (DestTy->isIntegerTy()) {
-      insertReplacementDbgValues(
-          *Src, *Res, CI, [](DbgInfoIntrinsic &OldDII) -> DIExpression * {
-            return OldDII.getExpression();
-          });
-    }
+    // Preserve debug values referring to Src if the zext is its last use.
+    if (auto *SrcOp = dyn_cast<Instruction>(Src))
+      if (SrcOp->hasOneUse())
+        replaceAllDbgUsesWith(*SrcOp, *Res, CI, DT);
 
     uint32_t SrcBitsKept = SrcTy->getScalarSizeInBits()-BitsToClear;
     uint32_t DestBitSize = DestTy->getScalarSizeInBits();