[Debuginfod] Flag-determine debuginfod lookups in llvm-symbolizer.

[mysterymath]

Summary

This change adds a pair of flags controlling whether llvm-symbolizer
attempts debuginfod lookups. Lookups are attempted if --debuginfod is
passed and disabled if --no-debuginfod is passed.

The default behavior is made more nuanced: debuginfod lookups are now
only attempted if an HTTP client is compiled in and at least one backing
debuginfod URL was configured via environment variable. Previously,
debuginfod lookups would always be attempted, even if there were no
chance that they could succeed.

[mysterymath]

Update from parent.

[mysterymath]

Add test.

[dblaikie]

(general direction looks good - thanks for CC'ing me on these, btw, @phosek - I'll likely chime in if/where I have concerns, but might leave review to you/others otherwise, if that's OK - if you have particular questions you'd like me to weigh in on, or want my explicit approval, just let me know & I'm happy to provide it - otherwise happy just to ride along/keep an eye on it all)

[mysterymath]

Update from parent.

[phosek]

LGTM

llvm/tools/llvm-symbolizer/llvm-symbolizer.cpp

292–295

This is just a nit, but I find that having the comment here not followed by any code a bit confusing, especially since it's referring to logic inside main. I'd slightly prefer just inlining this function together with these comments into main.

[mysterymath]

• Merge with upstream.

llvm/tools/llvm-symbolizer/llvm-symbolizer.cpp

292–295

This needed a bit more logic to merge with the other debuginfod changes, but I did rearrange it so the comment corresponds to an explicit return false.

llvm/docs/CommandGuide/llvm-symbolizer.rst

.. option:: --basenames, -s
   Print just the file's name without any directories, instead of the
   absolute path.
 
 .. option:: --build-id
 
   Look up the object using the given build ID, specified as a hexadecimal
   string. Mutually exclusive with :option:`--obj`.
 
+.. option:: --debuginfod, --no-debuginfod
+
+  Whether or not to try debuginfod lookups for debug binaries. Unless specified,
+  debuginfod is only enabled if libcurl was compiled in (``LLVM_ENABLE_CURL``)
+  and at least one server URL was provided by the environment variable
+  ``DEBUGINFOD_URLS``.
+
 .. _llvm-symbolizer-opt-C:
 
 .. option:: --demangle, -C
 
   Print demangled function names, if the names are mangled (e.g. the mangled
   name `_Z3bazv` becomes `baz()`, whilst the non-mangled name `foz` is printed
   as is). Defaults to true.
 

llvm/test/tools/llvm-symbolizer/debuginfod.test

 # determined by the debuginfod client's caching scheme, so it is manually
 # specified here as llvmcache-98...19
 RUN: llvm-objcopy --keep-section=.debug_info %p/Inputs/addr.exe \
 RUN:   %t/llvmcache-9800707741016212219
 
 # The symbolizer should call the debuginfod client library, which finds the
 # debuginfo placed in the cache, enabling symbolization of the address.
 RUN: env DEBUGINFOD_CACHE_PATH=%t llvm-symbolizer \
-RUN:   --obj=%t/addr.exe 0x40054d | FileCheck %s --check-prefix=FOUND
+RUN:   --obj=%t/addr.exe 0x40054d --debuginfod | \
+RUN:   FileCheck %s --check-prefix=FOUND
 FOUND: {{[/\]+}}tmp{{[/\]+}}x.c:14:0
 
 # This should also work if the build ID is provided.
 RUN: env DEBUGINFOD_CACHE_PATH=%t llvm-symbolizer \
 RUN:   --build-id=127da749021c1fc1a58cba734a1f542cbe2b7ce4 0x40054d | \
 RUN:   FileCheck %s --check-prefix=FOUND
+
+# The symbolizer shouldn't call the debuginfod library by default with no URLs.
+RUN: env DEBUGINFOD_CACHE_PATH=%t llvm-symbolizer --print-address \
+RUN:   --obj=%t/addr.exe 0x40054d | FileCheck %s --check-prefix=NOTFOUND

llvm/tools/llvm-symbolizer/Opts.td

 
 def addresses : F<"addresses", "Show address before line information">;
 defm adjust_vma
     : Eq<"adjust-vma", "Add specified offset to object file addresses">,
       MetaVarName<"<offset>">;
 def basenames : Flag<["--"], "basenames">, HelpText<"Strip directory names from paths">;
 defm build_id : Eq<"build-id", "Build ID used to look up the object file">;
 defm debug_file_directory : Eq<"debug-file-directory", "Path to directory where to look for debug files">, MetaVarName<"<dir>">;
+defm debuginfod : B<"debuginfod", "Use debuginfod to find debug binaries", "Don't use debuginfod to find debug binaries">;
 defm default_arch
     : Eq<"default-arch", "Default architecture (for multi-arch objects)">,
       Group<grp_mach_o>;
 defm demangle : B<"demangle", "Demangle function names", "Don't demangle function names">;
 def functions : F<"functions", "Print function name for a given address">;
 def functions_EQ : Joined<["--"], "functions=">, HelpText<"Print function name for a given address">, Values<"none,short,linkage">;
 def help : F<"help", "Display this help">;
 defm dwp : Eq<"dwp", "Path to DWP file to be use for any split CUs">, MetaVarName<"<file>">;

llvm/tools/llvm-symbolizer/llvm-symbolizer.cpp

 
 #include "Opts.inc"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Config/config.h"
 #include "llvm/DebugInfo/Symbolize/DIPrinter.h"
 #include "llvm/DebugInfo/Symbolize/Symbolize.h"
 #include "llvm/Debuginfod/DIFetcher.h"
+#include "llvm/Debuginfod/Debuginfod.h"
 #include "llvm/Debuginfod/HTTPClient.h"
 #include "llvm/Option/Arg.h"
 #include "llvm/Option/ArgList.h"
 #include "llvm/Option/Option.h"
 #include "llvm/Support/COM.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/FileSystem.h"

 SmallVector<uint8_t> parseBuildIDArg(const opt::InputArgList &Args, int ID) {
   if (const opt::Arg *A = Args.getLastArg(ID)) {
     StringRef V(A->getValue());
     std::string Bytes;
     if (!tryGetFromHex(V, Bytes)) {
       errs() << A->getSpelling() + ": expected a build ID, but got '" + V +
                     "'\n";
       exit(1);
     }
     ArrayRef<uint8_t> BuildID(reinterpret_cast<const uint8_t *>(Bytes.data()),
                               Bytes.size());
     return SmallVector<uint8_t>(BuildID.begin(), BuildID.end());
   }
   return {};
 }
 
+ExitOnError ExitOnErr;
+
+static bool shouldUseDebuginfodByDefault(ArrayRef<uint8_t> BuildID) {
+  // If the user explicitly specified a build ID, the usual way to find it is
+  // debuginfod.
+  if (!BuildID.empty())
+    return true;
+
+  // A debuginfod lookup could succeed if a HTTP client is available and at
+  // least one backing URL is configured.
+  if (HTTPClient::isAvailable() &&
+      !ExitOnErr(getDefaultDebuginfodUrls()).empty())
+    return true;
+
+  // A debuginfod lookup could also succeed if something were present in the
+  // cache directory, but it would be surprising to enable debuginfod on this
+  // basis alone. To use existing caches in an "offline" fashion, the debuginfod
+  // flag must be set.
+  return false;
+}
+
 int main(int argc, char **argv) {
   InitLLVM X(argc, argv);
   sys::InitializeCOMRAII COM(sys::COMThreadingMode::MultiThreaded);
 
   bool IsAddr2Line = sys::path::stem(argv[0]).contains("addr2line");
   BumpPtrAllocator A;
   StringSaver Saver(A);
   SymbolizerOptTable Tbl;
#endif
   if (Args.hasArg(OPT_build_id_EQ) && Args.hasArg(OPT_obj_EQ)) {
     errs() << "error: cannot specify both --build-id and --obj\n";
     return EXIT_FAILURE;
   }
   SmallVector<uint8_t> BuildID = parseBuildIDArg(Args, OPT_build_id_EQ);
 
   LLVMSymbolizer Symbolizer(Opts);
 
+  if (Args.hasFlag(OPT_debuginfod, OPT_no_debuginfod,
+                   shouldUseDebuginfodByDefault(BuildID))) {
     // Look up symbols using the debuginfod client.
     Symbolizer.addDIFetcher(std::make_unique<DebuginfodDIFetcher>());
     // The HTTPClient must be initialized for use by the debuginfod client.
     HTTPClient::initialize();
+  }
 
   std::unique_ptr<DIPrinter> Printer;
   if (Style == OutputStyle::GNU)
     Printer = std::make_unique<GNUPrinter>(outs(), errs(), Config);
   else if (Style == OutputStyle::JSON)
     Printer = std::make_unique<JSONPrinter>(outs(), Config);
   else
     Printer = std::make_unique<LLVMPrinter>(outs(), errs(), Config);