PR32382: Fix emitting complex DWARF expressions.

The DWARF specification knows 3 kinds of non-empty simple location
descriptions:
1. Register location descriptions
  - describe a variable in a register
  - consist of only a DW_OP_reg
2. Memory location descriptions
  - describe the address of a variable
3. Implicit location descriptions
  - describe the value of a variable
  - end with DW_OP_stack_value & friends

The existing DwarfExpression code is pretty much ignorant of these
restrictions. This used to not matter because we only emitted very
short expressions that we happened to get right by accident.  This
patch makes DwarfExpression aware of the rules defined by the DWARF
standard and now chooses the right kind of location description for
each expression being emitted.

This would have been an NFC commit (for the existing testsuite) if not
for the way that clang describes captured block variables. Based on
how the previous code in LLVM emitted locations, DW_OP_deref
operations that should have come at the end of the expression are put
at its beginning. Fixing this means changing the semantics of
DIExpression, so this patch bumps the version number of DIExpression
and implements a bitcode upgrade.

There are two major changes in this patch:

I had to fix the semantics of dbg.declare for describing function
arguments. After this patch a dbg.declare always takes the *address*
of a variable as the first argument, even if the argument is not an
alloca.

When lowering a DBG_VALUE, the decision of whether to emit a register
location description or a memory location description depends on the
MachineLocation — register machine locations may get promoted to
memory locations based on their DIExpression. (Future) optimization
passes that want to salvage implicit debug location for variables may
do so by appending a DW_OP_stack_value. For example:
  DBG_VALUE, [RBP-8]                        --> DW_OP_fbreg -8
  DBG_VALUE, RAX                            --> DW_OP_reg0 +0
  DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0

All testcases that were modified were regenerated from clang. I also
added source-based testcases for each of these to the debuginfo-tests
repository over the last week to make sure that no synchronized bugs
slip in. The debuginfo-tests compile from source and run the debugger.

https://bugs.llvm.org/show_bug.cgi?id=32382
<rdar://problem/31205000>

Differential Revision: https://reviews.llvm.org/D31439

llvm-svn: 300522

4 files changed, 58 insertions, 8 deletions

diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index 2de6bccf751..6d727ce8334 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -2631,6 +2631,7 @@ Error BitcodeReader::globalCleanup() {
 
   // Look for intrinsic functions which need to be upgraded at some point
   for (Function &F : *TheModule) {
+    MDLoader->upgradeDebugIntrinsics(F);
     Function *NewFn;
     if (UpgradeIntrinsicFunction(&F, NewFn))
       UpgradedIntrinsics[&F] = NewFn;
diff --git a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
index 274dfe89cce..d089684a052 100644
--- a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
+++ b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
@@ -54,6 +54,7 @@
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/ModuleSummaryIndex.h"
@@ -452,6 +453,7 @@ class MetadataLoader::MetadataLoaderImpl {
   bool StripTBAA = false;
   bool HasSeenOldLoopTags = false;
   bool NeedUpgradeToDIGlobalVariableExpression = false;
+  bool NeedDeclareExpressionUpgrade = false;
 
   /// True if metadata is being parsed for a module being ThinLTO imported.
   bool IsImporting = false;
@@ -511,6 +513,26 @@ class MetadataLoader::MetadataLoaderImpl {
     }
   }
 
+  /// Remove a leading DW_OP_deref from DIExpressions in a dbg.declare that
+  /// describes a function argument.
+  void upgradeDeclareExpressions(Function &F) {
+    if (!NeedDeclareExpressionUpgrade)
+      return;
+
+    for (auto &BB : F)
+      for (auto &I : BB)
+        if (auto *DDI = dyn_cast<DbgDeclareInst>(&I))
+          if (auto *DIExpr = DDI->getExpression())
+            if (DIExpr->startsWithDeref() &&
+                dyn_cast_or_null<Argument>(DDI->getAddress())) {
+              SmallVector<uint64_t, 8> Ops;
+              Ops.append(std::next(DIExpr->elements_begin()),
+                         DIExpr->elements_end());
+              auto *E = DIExpression::get(Context, Ops);
+              DDI->setOperand(2, MetadataAsValue::get(Context, E));
+            }
+  }
+
   void upgradeDebugInfo() {
     upgradeCUSubprograms();
     upgradeCUVariables();
@@ -565,6 +587,7 @@ public:
 
   unsigned size() const { return MetadataList.size(); }
   void shrinkTo(unsigned N) { MetadataList.shrinkTo(N); }
+  void upgradeDebugIntrinsics(Function &F) { upgradeDeclareExpressions(F); }
 };
 
 static Error error(const Twine &Message) {
@@ -1520,12 +1543,32 @@ Error MetadataLoader::MetadataLoaderImpl::parseOneMetadata(
       return error("Invalid record");
 
     IsDistinct = Record[0] & 1;
-    bool HasOpFragment = Record[0] & 2;
+    uint64_t Version = Record[0] >> 1;
     auto Elts = MutableArrayRef<uint64_t>(Record).slice(1);
-    if (!HasOpFragment)
-      if (unsigned N = Elts.size())
-        if (N >= 3 && Elts[N - 3] == dwarf::DW_OP_bit_piece)
-          Elts[N - 3] = dwarf::DW_OP_LLVM_fragment;
+    unsigned N = Elts.size();
+    // Perform various upgrades.
+    switch (Version) {
+    case 0:
+      if (N >= 3 && Elts[N - 3] == dwarf::DW_OP_bit_piece)
+        Elts[N - 3] = dwarf::DW_OP_LLVM_fragment;
+      LLVM_FALLTHROUGH;
+    case 1:
+      // Move DW_OP_deref to the end.
+      if (N && Elts[0] == dwarf::DW_OP_deref) {
+        auto End = Elts.end();
+        if (Elts.size() >= 3 && *std::prev(End, 3) == dwarf::DW_OP_LLVM_fragment)
+          End = std::prev(End, 3);
+        std::move(std::next(Elts.begin()), End, Elts.begin());
+        *std::prev(End) = dwarf::DW_OP_deref;
+      }
+      NeedDeclareExpressionUpgrade = true;
+      LLVM_FALLTHROUGH;
+    case 2:
+      // Up-to-date!
+      break;
+    default:
+      return error("Invalid record");
+    }
 
     MetadataList.assignValue(
         GET_OR_DISTINCT(DIExpression, (Context, makeArrayRef(Record).slice(1))),
@@ -1858,3 +1901,7 @@ bool MetadataLoader::isStrippingTBAA() { return Pimpl->isStrippingTBAA(); }
 
 unsigned MetadataLoader::size() const { return Pimpl->size(); }
 void MetadataLoader::shrinkTo(unsigned N) { return Pimpl->shrinkTo(N); }
+
+void MetadataLoader::upgradeDebugIntrinsics(Function &F) {
+  return Pimpl->upgradeDebugIntrinsics(F);
+}
diff --git a/llvm/lib/Bitcode/Reader/MetadataLoader.h b/llvm/lib/Bitcode/Reader/MetadataLoader.h
index 442dfc94e4e..f23dcc06cc9 100644
--- a/llvm/lib/Bitcode/Reader/MetadataLoader.h
+++ b/llvm/lib/Bitcode/Reader/MetadataLoader.h
@@ -79,6 +79,9 @@ public:
 
   unsigned size() const;
   void shrinkTo(unsigned N);
+
+  /// Perform bitcode upgrades on llvm.dbg.* calls.
+  void upgradeDebugIntrinsics(Function &F);
 };
 }
 
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index ee1b70da8ab..1d3cde2f5dd 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -1771,9 +1771,8 @@ void ModuleBitcodeWriter::writeDIExpression(const DIExpression *N,
                                             SmallVectorImpl<uint64_t> &Record,
                                             unsigned Abbrev) {
   Record.reserve(N->getElements().size() + 1);
-
-  const uint64_t HasOpFragmentFlag = 1 << 1;
-  Record.push_back((uint64_t)N->isDistinct() | HasOpFragmentFlag);
+  const uint64_t Version = 2 << 1;
+  Record.push_back((uint64_t)N->isDistinct() | Version);
   Record.append(N->elements_begin(), N->elements_end());
 
   Stream.EmitRecord(bitc::METADATA_EXPRESSION, Record, Abbrev);