Add FileWriter to GSYM and encode/decode functions to AddressRange and AddressRanges

The full GSYM patch started with: https://reviews.llvm.org/D53379

This patch add the ability to encode data using the new llvm::gsym::FileWriter class.

FileWriter is a simplified binary data writer class that doesn't require targets, target definitions, architectures, or require any other optional compile time libraries to be enabled via the build process. This class needs the ability to seek to different spots in the binary data that it produces to fix up offsets and sizes in GSYM data. It currently uses std::ostream over llvm::raw_ostream because llvm::raw_ostream doesn't support seeking which is required when encoding and decoding GSYM data.

AddressRange objects are encoded and decoded to be relative to a base address. This will be the FunctionInfo's start address if the AddressRange is directly contained in a FunctionInfo, or a base address of the containing parent AddressRange or AddressRanges. This allows address ranges to be efficiently encoded using ULEB128 encodings as we encode the offset and size of each range instead of full addresses. This also makes encoded addresses easy to relocate as we just need to relocate one base address.

Differential Revision: https://reviews.llvm.org/D63828

llvm-svn: 369587

3 files changed, 115 insertions, 0 deletions

diff --git a/llvm/lib/DebugInfo/GSYM/CMakeLists.txt b/llvm/lib/DebugInfo/GSYM/CMakeLists.txt
index fc37d560e61..dce0ed69cd0 100644
--- a/llvm/lib/DebugInfo/GSYM/CMakeLists.txt
+++ b/llvm/lib/DebugInfo/GSYM/CMakeLists.txt
@@ -1,4 +1,5 @@
 add_llvm_library(LLVMDebugInfoGSYM
+  FileWriter.cpp
   FunctionInfo.cpp
   InlineInfo.cpp
   Range.cpp
diff --git a/llvm/lib/DebugInfo/GSYM/FileWriter.cpp b/llvm/lib/DebugInfo/GSYM/FileWriter.cpp
new file mode 100644
index 00000000000..4b30dcb60a7
--- /dev/null
+++ b/llvm/lib/DebugInfo/GSYM/FileWriter.cpp
@@ -0,0 +1,78 @@
+//===- FileWriter.cpp -------------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/GSYM/FileWriter.h"
+#include "llvm/Support/LEB128.h"
+#include "llvm/Support/raw_ostream.h"
+#include <cassert>
+
+using namespace llvm;
+using namespace gsym;
+
+FileWriter::~FileWriter() { OS.flush(); }
+
+void FileWriter::writeSLEB(int64_t S) {
+  uint8_t Bytes[32];
+  auto Length = encodeSLEB128(S, Bytes);
+  assert(Length < sizeof(Bytes));
+  OS.write(reinterpret_cast<const char *>(Bytes), Length);
+}
+
+void FileWriter::writeULEB(uint64_t U) {
+  uint8_t Bytes[32];
+  auto Length = encodeULEB128(U, Bytes);
+  assert(Length < sizeof(Bytes));
+  OS.write(reinterpret_cast<const char *>(Bytes), Length);
+}
+
+void FileWriter::writeU8(uint8_t U) {
+  OS.write(reinterpret_cast<const char *>(&U), sizeof(U));
+}
+
+void FileWriter::writeU16(uint16_t U) {
+  const uint16_t Swapped = support::endian::byte_swap(U, ByteOrder);
+  OS.write(reinterpret_cast<const char *>(&Swapped), sizeof(Swapped));
+}
+
+void FileWriter::writeU32(uint32_t U) {
+  const uint32_t Swapped = support::endian::byte_swap(U, ByteOrder);
+  OS.write(reinterpret_cast<const char *>(&Swapped), sizeof(Swapped));
+}
+
+void FileWriter::writeU64(uint64_t U) {
+  const uint64_t Swapped = support::endian::byte_swap(U, ByteOrder);
+  OS.write(reinterpret_cast<const char *>(&Swapped), sizeof(Swapped));
+}
+
+void FileWriter::fixup32(uint32_t U, uint64_t Offset) {
+  const uint32_t Swapped = support::endian::byte_swap(U, ByteOrder);
+  OS.pwrite(reinterpret_cast<const char *>(&Swapped), sizeof(Swapped),
+            Offset);
+}
+
+void FileWriter::writeData(llvm::ArrayRef<uint8_t> Data) {
+  OS.write(reinterpret_cast<const char *>(Data.data()), Data.size());
+}
+
+void FileWriter::writeNullTerminated(llvm::StringRef Str) {
+  OS << Str << '\0';
+}
+
+uint64_t FileWriter::tell() {
+  return OS.tell();
+}
+
+void FileWriter::alignTo(size_t Align) {
+  off_t Offset = OS.tell();
+  off_t AlignedOffset = (Offset + Align - 1) / Align * Align;
+  if (AlignedOffset == Offset)
+    return;
+  off_t PadCount = AlignedOffset - Offset;
+  OS.write_zeros(PadCount);
+}
diff --git a/llvm/lib/DebugInfo/GSYM/Range.cpp b/llvm/lib/DebugInfo/GSYM/Range.cpp
index ca61984dacb..f4d31f328a2 100644
--- a/llvm/lib/DebugInfo/GSYM/Range.cpp
+++ b/llvm/lib/DebugInfo/GSYM/Range.cpp
@@ -8,6 +8,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/DebugInfo/GSYM/Range.h"
+#include "llvm/DebugInfo/GSYM/FileWriter.h"
+#include "llvm/Support/DataExtractor.h"
 #include <algorithm>
 #include <inttypes.h>
 
@@ -53,3 +55,37 @@ raw_ostream &llvm::gsym::operator<<(raw_ostream &OS, const AddressRanges &AR) {
   }
   return OS;
 }
+
+void AddressRange::encode(FileWriter &O, uint64_t BaseAddr) const {
+  assert(Start >= BaseAddr);
+  O.writeULEB(Start - BaseAddr);
+  O.writeULEB(size());
+}
+
+void AddressRange::decode(DataExtractor &Data, uint64_t BaseAddr,
+                          uint64_t &Offset) {
+  const uint64_t AddrOffset = Data.getULEB128(&Offset);
+  const uint64_t Size = Data.getULEB128(&Offset);
+  const uint64_t StartAddr = BaseAddr + AddrOffset;
+  Start = StartAddr;
+  End = StartAddr + Size;
+}
+
+void AddressRanges::encode(FileWriter &O, uint64_t BaseAddr) const {
+  O.writeULEB(Ranges.size());
+  if (Ranges.empty())
+    return;
+  for (auto Range : Ranges)
+    Range.encode(O, BaseAddr);
+}
+
+void AddressRanges::decode(DataExtractor &Data, uint64_t BaseAddr,
+                           uint64_t &Offset) {
+  clear();
+  uint64_t NumRanges = Data.getULEB128(&Offset);
+  if (NumRanges == 0)
+    return;
+  Ranges.resize(NumRanges);
+  for (auto &Range : Ranges)
+    Range.decode(Data, BaseAddr, Offset);
+}