[lit] Refactor test execution logic into lit.run.Run.

[oota-llvm.git] / tools / llvm-symbolizer / LLVMSymbolize.cpp

diff --git a/tools/llvm-symbolizer/LLVMSymbolize.cpp b/tools/llvm-symbolizer/LLVMSymbolize.cpp
index dfcbacfbe63dcb8cfa753df187b40fd7f6ab2e35..45c86641d8a046f59d459e345007e978cedfb2d1 100644 (file)
--- a/tools/llvm-symbolizer/LLVMSymbolize.cpp
+++ b/tools/llvm-symbolizer/LLVMSymbolize.cpp
@@ -13,12 +13,17 @@
 
 #include "LLVMSymbolize.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Config/config.h"
 #include "llvm/Object/MachO.h"
 #include "llvm/Support/Casting.h"
+#include "llvm/Support/Compression.h"
+#include "llvm/Support/DataExtractor.h"
 #include "llvm/Support/FileSystem.h"
+#include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 
 #include <sstream>
+#include <stdlib.h>
 
 namespace llvm {
 namespace symbolize {
@@ -74,6 +79,9 @@ ModuleInfo::ModuleInfo(ObjectFile *Obj, DIContext *DICtx)
     StringRef SymbolName;
     if (error(si->getName(SymbolName)))
       continue;
+    // Mach-O symbol table names have leading underscore, skip it.
+    if (Module->isMachO() && SymbolName.size() > 0 && SymbolName[0] == '_')
+      SymbolName = SymbolName.drop_front();
     // FIXME: If a function has alias, there are two entries in symbol table
     // with same address size. Make sure we choose the correct one.
     SymbolMapTy &M = SymbolType == SymbolRef::ST_Function ? Functions : Objects;
@@ -199,6 +207,8 @@ std::string LLVMSymbolizer::symbolizeData(const std::string &ModuleName,
 void LLVMSymbolizer::flush() {
   DeleteContainerSeconds(Modules);
   DeleteContainerPointers(ParsedBinariesAndObjects);
+  BinaryForPath.clear();
+  ObjectFileForArch.clear();
 }
 
 static std::string getDarwinDWARFResourceForPath(const std::string &Path) {
@@ -210,6 +220,81 @@ static std::string getDarwinDWARFResourceForPath(const std::string &Path) {
   return ResourceName.str();
 }
 
+static bool checkFileCRC(StringRef Path, uint32_t CRCHash) {
+  OwningPtr<MemoryBuffer> MB;
+  if (MemoryBuffer::getFileOrSTDIN(Path, MB))
+    return false;
+  return !zlib::isAvailable() || CRCHash == zlib::crc32(MB->getBuffer());
+}
+
+static bool findDebugBinary(const std::string &OrigPath,
+                            const std::string &DebuglinkName, uint32_t CRCHash,
+                            std::string &Result) {
+  std::string OrigRealPath = OrigPath;
+#if defined(HAVE_REALPATH)
+  if (char *RP = realpath(OrigPath.c_str(), NULL)) {
+    OrigRealPath = RP;
+    free(RP);
+  }
+#endif
+  SmallString<16> OrigDir(OrigRealPath);
+  llvm::sys::path::remove_filename(OrigDir);
+  SmallString<16> DebugPath = OrigDir;
+  // Try /path/to/original_binary/debuglink_name
+  llvm::sys::path::append(DebugPath, DebuglinkName);
+  if (checkFileCRC(DebugPath, CRCHash)) {
+    Result = DebugPath.str();
+    return true;
+  }
+  // Try /path/to/original_binary/.debug/debuglink_name
+  DebugPath = OrigRealPath;
+  llvm::sys::path::append(DebugPath, ".debug", DebuglinkName);
+  if (checkFileCRC(DebugPath, CRCHash)) {
+    Result = DebugPath.str();
+    return true;
+  }
+  // Try /usr/lib/debug/path/to/original_binary/debuglink_name
+  DebugPath = "/usr/lib/debug";
+  llvm::sys::path::append(DebugPath, llvm::sys::path::relative_path(OrigDir),
+                          DebuglinkName);
+  if (checkFileCRC(DebugPath, CRCHash)) {
+    Result = DebugPath.str();
+    return true;
+  }
+  return false;
+}
+
+static bool getGNUDebuglinkContents(const Binary *Bin, std::string &DebugName,
+                                    uint32_t &CRCHash) {
+  const ObjectFile *Obj = dyn_cast<ObjectFile>(Bin);
+  if (!Obj)
+    return false;
+  error_code EC;
+  for (section_iterator I = Obj->begin_sections(), E = Obj->end_sections();
+       I != E; I.increment(EC)) {
+    StringRef Name;
+    I->getName(Name);
+    Name = Name.substr(Name.find_first_not_of("._"));
+    if (Name == "gnu_debuglink") {
+      StringRef Data;
+      I->getContents(Data);
+      DataExtractor DE(Data, Obj->isLittleEndian(), 0);
+      uint32_t Offset = 0;
+      if (const char *DebugNameStr = DE.getCStr(&Offset)) {
+        // 4-byte align the offset.
+        Offset = (Offset + 3) & ~0x3;
+        if (DE.isValidOffsetForDataOfSize(Offset, 4)) {
+          DebugName = DebugNameStr;
+          CRCHash = DE.getU32(&Offset);
+          return true;
+        }
+      }
+      break;
+    }
+  }
+  return false;
+}
+
 LLVMSymbolizer::BinaryPair
 LLVMSymbolizer::getOrCreateBinary(const std::string &Path) {
   BinaryMapTy::iterator I = BinaryForPath.find(Path);
@@ -236,6 +321,18 @@ LLVMSymbolizer::getOrCreateBinary(const std::string &Path) {
         ParsedBinariesAndObjects.push_back(DbgBin);
       }
     }
+    // Try to locate the debug binary using .gnu_debuglink section.
+    if (DbgBin == 0) {
+      std::string DebuglinkName;
+      uint32_t CRCHash;
+      std::string DebugBinaryPath;
+      if (getGNUDebuglinkContents(Bin, DebuglinkName, CRCHash) &&
+          findDebugBinary(Path, DebuglinkName, CRCHash, DebugBinaryPath) &&
+          !error(createBinary(DebugBinaryPath, ParsedDbgBinary))) {
+        DbgBin = ParsedDbgBinary.take();
+        ParsedBinariesAndObjects.push_back(DbgBin);
+      }
+    }
   }
   if (DbgBin == 0)
     DbgBin = Bin;
@@ -273,10 +370,14 @@ LLVMSymbolizer::getOrCreateModuleInfo(const std::string &ModuleName) {
     return I->second;
   std::string BinaryName = ModuleName;
   std::string ArchName = Opts.DefaultArch;
-  size_t ColonPos = ModuleName.find(':');
+  size_t ColonPos = ModuleName.find_last_of(':');
+  // Verify that substring after colon form a valid arch name.
   if (ColonPos != std::string::npos) {
-    BinaryName = ModuleName.substr(0, ColonPos);
-    ArchName = ModuleName.substr(ColonPos + 1);
+    std::string ArchStr = ModuleName.substr(ColonPos + 1);
+    if (Triple(ArchStr).getArch() != Triple::UnknownArch) {
+      BinaryName = ModuleName.substr(0, ColonPos);
+      ArchName = ArchStr;
+    }
   }
   BinaryPair Binaries = getOrCreateBinary(BinaryName);
   ObjectFile *Obj = getObjectFileFromBinary(Binaries.first, ArchName);