[llvm-symbolizer] -print-source-context-lines option to print source code around the line.

[samsonov]

tools/llvm-symbolizer/llvm-symbolizer.cpp

218

This will be confusing: first you will print several blocks with function/file/lineno, and then several blocks with source code. Shouldn't they be interchanged? Probably source code printing can be implemented in DIPrinter.

[aizatsky]

review

[aizatsky]

ptal

[aizatsky]

nits

[aizatsky]

nits

[aizatsky]

nits

[samsonov]

tools/llvm-symbolizer/llvm-symbolizer.cpp

218

So, what are the drawbacks of printing source file contents from DIPrinter? We changed llvm-symbolizer to be agnostic of the way DILineInfo / DIInliningInfo is represented: and pass it directly from producer to printer, and now we return to manually writing all these loops.

Keeping that in DIPrinter would also let you write unit tests for that functionality, if needed.

[aizatsky]

moved context functionality into printer.

[aizatsky]

nits

[aizatsky]

nits

[samsonov]

LGTM (but switch to line_iterator if it's convenient).

lib/DebugInfo/Symbolize/DIPrinter.cpp

46 ↗

(On Diff #44348)

Can you use include/llvm/Support/LineIterator.h instead of splitting file manually?

[aizatsky]

using line iterator.

test/lit.cfg

 # Add site-specific substitutions.
 config.substitutions.append( ('%gold', config.gold_executable) )
 config.substitutions.append( ('%ld64', config.ld64_executable) )
 config.substitutions.append( ('%go', config.go_executable) )
 config.substitutions.append( ('%llvmshlibdir', config.llvm_shlib_dir) )
 config.substitutions.append( ('%shlibext', config.llvm_shlib_ext) )
 config.substitutions.append( ('%exeext', config.llvm_exe_ext) )
 config.substitutions.append( ('%python', config.python_executable) )
+config.substitutions.append( ('%host_cc', config.host_cc) )
 
 # OCaml substitutions.
 # Support tests for both native and bytecode builds.
 config.substitutions.append( ('%ocamlc',
     "%s ocamlc -cclib -L%s %s" %
         (config.ocamlfind_executable, llvm_lib_dir, config.ocaml_flags)) )
 if config.have_ocamlopt in ('1', 'TRUE'):
     config.substitutions.append( ('%ocamlopt',
for pattern in [r"\bbugpoint\b(?!-)",
                 r"\bllvm-profdata\b",
                 r"\bllvm-ranlib\b",
                 r"\bllvm-readobj\b",
                 r"\bllvm-rtdyld\b",
                 r"\bllvm-size\b",
                 r"\bllvm-split\b",
                 r"\bllvm-tblgen\b",
                 r"\bllvm-c-test\b",
+                NOJUNK + r"\bllvm-symbolizer\b",
                 NOJUNK + r"\bopt\b",
                 r"\bFileCheck\b",
                 r"\bobj2yaml\b",
                 NOJUNK + r"\bsancov\b",
                 r"\byaml2obj\b",
                 r"\byaml-bench\b",
                 r"\bverify-uselistorder\b",
                 # Handle these specially as they are strings searched

test/tools/llvm-symbolizer/print_context.c

+// REQUIRES: x86_64-linux
+// RUN: %host_cc -O0 -g %s -o %t 2>&1
+// RUN: %t 2>&1 | llvm-symbolizer -print-source-context-lines=5 -obj=%t | FileCheck %s --check-prefix=CHECK
+
+#include <stdio.h>
+
+int inc(int a) {
+  return a + 1;
+}
+
+int main() {
+  printf("%p\n", inc);
+  return 0;
+}
+
+// CHECK: inc
+// CHECK: print_context.c:7
+// CHECK: 5  : #include
+// CHECK: 6  :
+// CHECK: 7 >: int inc
+// CHECK: 8  :   return
+// CHECK: 9  : }

tools/llvm-symbolizer/llvm-symbolizer.cpp

 static cl::opt<bool>
     ClPrintAddress("print-address", cl::init(false),
                    cl::desc("Show address before line information"));
 
 static cl::opt<bool>
     ClPrettyPrint("pretty-print", cl::init(false),
                   cl::desc("Make the output more human friendly"));
 
+static cl::opt<int> ClPrintSourceContextLines(
+    "print-source-context-lines", cl::init(0),
+    cl::desc("Print N number of source file context"));
+
 static bool error(std::error_code ec) {
   if (!ec)
     return false;
   errs() << "LLVMSymbolizer: error reading file: " << ec.message() << ".\n";
   return true;
 }
 
 static bool parseCommand(bool &IsData, std::string &ModuleName,
if (ClBinaryName == "") {
     ModuleName = ClBinaryName;
   }
   // Skip delimiters and parse module offset.
   pos += strspn(pos, kDelimiters);
   int offset_length = strcspn(pos, kDelimiters);
   return !StringRef(pos, offset_length).getAsInteger(0, ModuleOffset);
 }
 
+static void printContextIfNeeded(std::string FileName, uint32_t Line) {
+  if (ClPrintSourceContextLines <= 0)
+    return;
+
+  ErrorOr<std::unique_ptr<MemoryBuffer>> BufOrErr =
+      MemoryBuffer::getFile(FileName);
+  if (!BufOrErr)
+    return;
+
+  std::unique_ptr<MemoryBuffer> Buf = std::move(BufOrErr.get());
+  StringRef FileContent = Buf->getBuffer();
+
+  size_t FirstLine = std::max(1u, Line - ClPrintSourceContextLines / 2);
+  size_t LastLine = FirstLine + ClPrintSourceContextLines;
+  size_t MaxLineNumberWidth = std::ceil(std::log10(LastLine));
+
+  size_t LineStart = 0;
+  for (uint32_t I = 0; LineStart != StringRef::npos && I <= LastLine; ++I) {
+    size_t LineEnd = FileContent.find_first_of("\n", LineStart);
+    if (I + 1 >= FirstLine && I < LastLine) {
+      outs() << format_decimal(I + 1, MaxLineNumberWidth);
+      if (I + 1 == Line) {
+        outs() << " >: ";
+      } else {
+        outs() << "  : ";
+      }
+      outs() << FileContent.substr(LineStart, LineEnd - LineStart) << "\n";
+    }
+    LineStart = FileContent.find_first_not_of("\r", LineEnd + 1);
+  }
+}
+
 int main(int argc, char **argv) {
   // Print stack trace if we signal out.
   sys::PrintStackTraceOnErrorSignal();
   PrettyStackTraceProgram X(argc, argv);
   llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
 
   llvm::sys::InitializeCOMRAII COM(llvm::sys::COMThreadingMode::MultiThreaded);
 
if (ClPrintAddress) {
       StringRef Delimiter = (ClPrettyPrint == true) ? ": " : "\n";
       outs() << Delimiter;
     }
     if (IsData) {
       auto ResOrErr = Symbolizer.symbolizeData(ModuleName, ModuleOffset);
       Printer << (error(ResOrErr.getError()) ? DIGlobal() : ResOrErr.get());
     } else if (ClPrintInlining) {
       auto ResOrErr = Symbolizer.symbolizeInlinedCode(ModuleName, ModuleOffset);
-      Printer << (error(ResOrErr.getError()) ? DIInliningInfo()
-                                             : ResOrErr.get());
+      auto DebugInfo =
+          error(ResOrErr.getError()) ? DIInliningInfo() : ResOrErr.get();
+      if (DebugInfo.getNumberOfFrames() > 0) {
+        for (uint32_t I = 0; I < DebugInfo.getNumberOfFrames(); ++I) {
+          const auto &Frame = DebugInfo.getFrame(I);
+          Printer.printName(Frame, I > 0);
+          printContextIfNeeded(Frame.FileName, Frame.Line);
+        }
+      } else
+        Printer << DebugInfo;
     } else {
       auto ResOrErr = Symbolizer.symbolizeCode(ModuleName, ModuleOffset);
-      Printer << (error(ResOrErr.getError()) ? DILineInfo() : ResOrErr.get());
+      auto DebugInfo =
+          (error(ResOrErr.getError()) ? DILineInfo() : ResOrErr.get());
+      Printer << DebugInfo;
+      printContextIfNeeded(DebugInfo.FileName, DebugInfo.Line);
     }
     outs() << "\n";
     outs().flush();
   }
 
   return 0;
 }