Reapply "[dwarfdump] Add support for dumping accelerator tables."

This reverts commit r221842 which was a revert of r221836 and of the
test parts of r221837.

This new version fixes an UB bug pointed out by David (along with
addressing some other review comments), makes some dumping more
resilient to broken input data and forces the accelerator tables
to be dumped in the tests where we use them (this decision is
platform specific otherwise).

llvm-svn: 222003
diff --git a/llvm/lib/DebugInfo/CMakeLists.txt b/llvm/lib/DebugInfo/CMakeLists.txt
index 61a3fb0..81fc84d 100644
--- a/llvm/lib/DebugInfo/CMakeLists.txt
+++ b/llvm/lib/DebugInfo/CMakeLists.txt
@@ -1,6 +1,7 @@
 add_llvm_library(LLVMDebugInfo
   DIContext.cpp
   DWARFAbbreviationDeclaration.cpp
+  DWARFAcceleratorTable.cpp
   DWARFCompileUnit.cpp
   DWARFContext.cpp
   DWARFDebugAbbrev.cpp
diff --git a/llvm/lib/DebugInfo/DWARFAcceleratorTable.cpp b/llvm/lib/DebugInfo/DWARFAcceleratorTable.cpp
new file mode 100644
index 0000000..4b844e9
--- /dev/null
+++ b/llvm/lib/DebugInfo/DWARFAcceleratorTable.cpp
@@ -0,0 +1,116 @@
+#include "DWARFAcceleratorTable.h"
+
+#include "llvm/Support/Dwarf.h"
+#include "llvm/Support/Format.h"
+#include "llvm/Support/raw_ostream.h"
+
+namespace llvm {
+
+bool DWARFAcceleratorTable::extract() {
+  uint32_t Offset = 0;
+
+  // Check that we can at least read the header.
+  if (!AccelSection.isValidOffset(offsetof(Header, HeaderDataLength)+4))
+    return false;
+
+  Hdr.Magic = AccelSection.getU32(&Offset);
+  Hdr.Version = AccelSection.getU16(&Offset);
+  Hdr.HashFunction = AccelSection.getU16(&Offset);
+  Hdr.NumBuckets = AccelSection.getU32(&Offset);
+  Hdr.NumHashes = AccelSection.getU32(&Offset);
+  Hdr.HeaderDataLength = AccelSection.getU32(&Offset);
+
+  // Check that we can read all the hashes and offsets from the
+  // section (see SourceLevelDebugging.rst for the structure of the index).
+  if (!AccelSection.isValidOffset(sizeof(Hdr) + Hdr.HeaderDataLength +
+                                  Hdr.NumBuckets*4 + Hdr.NumHashes*8))
+    return false;
+
+  HdrData.DIEOffsetBase = AccelSection.getU32(&Offset);
+  uint32_t NumAtoms = AccelSection.getU32(&Offset);
+
+  for (unsigned i = 0; i < NumAtoms; ++i) {
+    uint16_t AtomType = AccelSection.getU16(&Offset);
+    DWARFFormValue AtomForm(AccelSection.getU16(&Offset));
+    HdrData.Atoms.push_back(std::make_pair(AtomType, AtomForm));
+  }
+
+  return true;
+}
+
+void DWARFAcceleratorTable::dump(raw_ostream &OS) {
+  // Dump the header.
+  OS << "Magic = " << format("0x%08x", Hdr.Magic) << '\n'
+     << "Version = " << format("0x%04x", Hdr.Version) << '\n'
+     << "Hash function = " << format("0x%08x", Hdr.HashFunction) << '\n'
+     << "Bucket count = " << Hdr.NumBuckets << '\n'
+     << "Hashes count = " << Hdr.NumHashes << '\n'
+     << "HeaderData length = " << Hdr.HeaderDataLength << '\n'
+     << "DIE offset base = " << HdrData.DIEOffsetBase << '\n'
+     << "Number of atoms = " << HdrData.Atoms.size() << '\n';
+
+  unsigned i = 0;
+  for (const auto &Atom: HdrData.Atoms) {
+    OS << format("Atom[%d] Type: ", i++);
+    if (const char *TypeString = dwarf::AtomTypeString(Atom.first))
+      OS << TypeString;
+    else
+      OS << format("DW_ATOM_Unknown_0x%x", Atom.first);
+    OS << " Form: ";
+    if (const char *FormString = dwarf::FormEncodingString(Atom.second.getForm()))
+      OS << FormString;
+    else
+      OS << format("DW_FORM_Unknown_0x%x", Atom.second.getForm());
+    OS << '\n';
+  }
+
+  // Now go through the actual tables and dump them.
+  uint32_t Offset = sizeof(Hdr) + Hdr.HeaderDataLength;
+  unsigned HashesBase = Offset + Hdr.NumBuckets * 4;
+  unsigned OffsetsBase = HashesBase + Hdr.NumHashes * 4;
+
+  for (unsigned Bucket = 0; Bucket < Hdr.NumBuckets; ++Bucket) {
+    unsigned Index = AccelSection.getU32(&Offset);
+
+    OS << format("Bucket[%d]\n", Bucket);
+    if (Index == UINT32_MAX) {
+      OS << "  EMPTY\n";
+      continue;
+    }
+
+    for (unsigned HashIdx = Index; HashIdx < Hdr.NumHashes; ++HashIdx) {
+      unsigned HashOffset = HashesBase + HashIdx*4;
+      unsigned OffsetsOffset = OffsetsBase + HashIdx*4;
+      uint32_t Hash = AccelSection.getU32(&HashOffset);
+
+      if (Hash % Hdr.NumBuckets != Bucket)
+        break;
+
+      unsigned DataOffset = AccelSection.getU32(&OffsetsOffset);
+      OS << format("  Hash = 0x%08x Offset = 0x%08x\n", Hash, DataOffset);
+      if (!AccelSection.isValidOffset(DataOffset)) {
+        OS << "    Invalid section offset\n";
+        continue;
+      }
+      while (unsigned StringOffset = AccelSection.getU32(&DataOffset)) {
+        OS << format("    Name: %08x \"%s\"\n", StringOffset,
+                     StringSection.getCStr(&StringOffset));
+        unsigned NumData = AccelSection.getU32(&DataOffset);
+        for (unsigned Data = 0; Data < NumData; ++Data) {
+          OS << format("    Data[%d] => ", Data);
+          unsigned i = 0;
+          for (auto &Atom : HdrData.Atoms) {
+            OS << format("{Atom[%d]: ", i++);
+            if (Atom.second.extractValue(AccelSection, &DataOffset, nullptr))
+              Atom.second.dump(OS, nullptr);
+            else
+              OS << "Error extracting the value";
+            OS << "} ";
+          }
+          OS << '\n';
+        }
+      }
+    }
+  }
+}
+}
diff --git a/llvm/lib/DebugInfo/DWARFAcceleratorTable.h b/llvm/lib/DebugInfo/DWARFAcceleratorTable.h
new file mode 100644
index 0000000..bb25917
--- /dev/null
+++ b/llvm/lib/DebugInfo/DWARFAcceleratorTable.h
@@ -0,0 +1,38 @@
+
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/DebugInfo/DWARFFormValue.h"
+
+#include <cstdint>
+
+namespace llvm {
+
+class DWARFAcceleratorTable {
+
+  struct Header {
+    uint32_t Magic;
+    uint16_t Version;
+    uint16_t HashFunction;
+    uint32_t NumBuckets;
+    uint32_t NumHashes;
+    uint32_t HeaderDataLength;
+  };
+
+  struct HeaderData {
+    typedef uint16_t AtomType;
+    uint32_t DIEOffsetBase;
+    SmallVector<std::pair<AtomType, DWARFFormValue>, 1> Atoms;
+  };
+
+  struct Header Hdr;
+  struct HeaderData HdrData;
+  DataExtractor AccelSection;
+  DataExtractor StringSection;
+public:
+  DWARFAcceleratorTable(DataExtractor AccelSection, DataExtractor StringSection)
+    : AccelSection(AccelSection), StringSection(StringSection) {}
+
+  bool extract();
+  void dump(raw_ostream &OS);
+};
+
+}
diff --git a/llvm/lib/DebugInfo/DWARFContext.cpp b/llvm/lib/DebugInfo/DWARFContext.cpp
index aa86f6a..845718d 100644
--- a/llvm/lib/DebugInfo/DWARFContext.cpp
+++ b/llvm/lib/DebugInfo/DWARFContext.cpp
@@ -9,6 +9,7 @@
 
 #include "DWARFContext.h"
 #include "DWARFDebugArangeSet.h"
+#include "DWARFAcceleratorTable.h"
 
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringSwitch.h"
@@ -59,6 +60,17 @@
   }
 }
 
+static void dumpAccelSection(raw_ostream &OS, StringRef Name, StringRef Data,
+                             StringRef StringSection, bool LittleEndian) {
+  DataExtractor AccelSection(Data, LittleEndian, 0);
+  DataExtractor StrData(StringSection, LittleEndian, 0);
+  OS << "\n." << Name << " contents:\n";
+  DWARFAcceleratorTable Accel(AccelSection, StrData);
+  if (!Accel.extract())
+    return;
+  Accel.dump(OS);
+}
+
 void DWARFContext::dump(raw_ostream &OS, DIDumpType DumpType) {
   if (DumpType == DIDT_All || DumpType == DIDT_Abbrev) {
     OS << ".debug_abbrev contents:\n";
@@ -218,6 +230,22 @@
       OS << format("%8.8x\n", strOffsetExt.getU32(&offset));
     }
   }
+
+  if (DumpType == DIDT_All || DumpType == DIDT_AppleNames)
+    dumpAccelSection(OS, "apple_names", getAppleNamesSection(),
+                     getStringSection(), isLittleEndian());
+
+  if (DumpType == DIDT_All || DumpType == DIDT_AppleTypes)
+    dumpAccelSection(OS, "apple_types", getAppleTypesSection(),
+                     getStringSection(), isLittleEndian());
+
+  if (DumpType == DIDT_All || DumpType == DIDT_AppleNamespaces)
+    dumpAccelSection(OS, "apple_namespaces", getAppleNamespacesSection(),
+                     getStringSection(), isLittleEndian());
+
+  if (DumpType == DIDT_All || DumpType == DIDT_AppleObjC)
+    dumpAccelSection(OS, "apple_objc", getAppleObjCSection(),
+                     getStringSection(), isLittleEndian());
 }
 
 const DWARFDebugAbbrev *DWARFContext::getDebugAbbrev() {
@@ -565,6 +593,11 @@
             .Case("debug_str.dwo", &StringDWOSection)
             .Case("debug_str_offsets.dwo", &StringOffsetDWOSection)
             .Case("debug_addr", &AddrSection)
+            .Case("apple_names", &AppleNamesSection)
+            .Case("apple_types", &AppleTypesSection)
+            .Case("apple_namespaces", &AppleNamespacesSection)
+            .Case("apple_namespac", &AppleNamespacesSection)
+            .Case("apple_objc", &AppleObjCSection)
             // Any more debug info sections go here.
             .Default(nullptr);
     if (SectionData) {
diff --git a/llvm/lib/DebugInfo/DWARFContext.h b/llvm/lib/DebugInfo/DWARFContext.h
index c4586b0..926f7c3 100644
--- a/llvm/lib/DebugInfo/DWARFContext.h
+++ b/llvm/lib/DebugInfo/DWARFContext.h
@@ -192,6 +192,10 @@
   virtual StringRef getStringOffsetDWOSection() = 0;
   virtual StringRef getRangeDWOSection() = 0;
   virtual StringRef getAddrSection() = 0;
+  virtual StringRef getAppleNamesSection() = 0;
+  virtual StringRef getAppleTypesSection() = 0;
+  virtual StringRef getAppleNamespacesSection() = 0;
+  virtual StringRef getAppleObjCSection() = 0;
 
   static bool isSupportedVersion(unsigned version) {
     return version == 2 || version == 3 || version == 4;
@@ -236,6 +240,10 @@
   StringRef StringOffsetDWOSection;
   StringRef RangeDWOSection;
   StringRef AddrSection;
+  StringRef AppleNamesSection;
+  StringRef AppleTypesSection;
+  StringRef AppleNamespacesSection;
+  StringRef AppleObjCSection;
 
   SmallVector<SmallString<32>, 4> UncompressedSections;
 
@@ -256,6 +264,10 @@
   StringRef getPubTypesSection() override { return PubTypesSection; }
   StringRef getGnuPubNamesSection() override { return GnuPubNamesSection; }
   StringRef getGnuPubTypesSection() override { return GnuPubTypesSection; }
+  StringRef getAppleNamesSection() override { return AppleNamesSection; }
+  StringRef getAppleTypesSection() override { return AppleTypesSection; }
+  StringRef getAppleNamespacesSection() override { return AppleNamespacesSection; }
+  StringRef getAppleObjCSection() override { return AppleObjCSection; }
 
   // Sections for DWARF5 split dwarf proposal.
   const DWARFSection &getInfoDWOSection() override { return InfoDWOSection; }