[GCOV] Add options to filter files which must be instrumented.

calixteman · calixteman · commit c6fabeac11b9 · 2018-11-12T09:01:43.000Z
Summary: When making code coverage, a lot of files (like the ones coming from /usr/include) are removed when post-processing gcno/gcda so finally they doen't need to be instrumented nor to appear in gcno/gcda. The goal of the patch is to be able to filter the files we want to instrument, there are several advantages to do that: - improve speed (no overhead due to instrumentation on files we don't care) - reduce gcno/gcda size - it gives the possibility to easily instrument only few files (e.g. ones modified in a patch) without changing the build system - need to accept this patch to be enabled in clang: https://reviews.llvm.org/D52034 Reviewers: marco-c, vsk Reviewed By: marco-c Subscribers: llvm-commits, sylvestre.ledru Differential Revision: https://reviews.llvm.org/D52033 llvm-svn: 346641
diff --git a/llvm/include/llvm/Transforms/Instrumentation.h b/llvm/include/llvm/Transforms/Instrumentation.h
@@ -77,6 +77,12 @@ struct GCOVOptions {
   // Emit the exit block immediately after the start block, rather than after
   // all of the function body's blocks.
   bool ExitBlockBeforeBody;
+
+  // Regexes separated by a semi-colon to filter the files to instrument.
+  std::string Filter;
+
+  // Regexes separated by a semi-colon to filter the files to not instrument.
+  std::string Exclude;
 };
 
 ModulePass *createGCOVProfilerPass(const GCOVOptions &Options =
diff --git a/llvm/lib/Transforms/Instrumentation/GCOVProfiling.cpp b/llvm/lib/Transforms/Instrumentation/GCOVProfiling.cpp
@@ -36,6 +36,7 @@
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
+#include "llvm/Support/Regex.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/Instrumentation.h"
 #include "llvm/Transforms/Instrumentation/GCOVProfiler.h"
@@ -96,6 +97,11 @@ class GCOVProfiler {
   // profiling runtime to emit .gcda files when run.
   bool emitProfileArcs();
 
+  bool isFunctionInstrumented(const Function &F);
+  std::vector<Regex> createRegexesFromString(StringRef RegexesStr);
+  static bool doesFilenameMatchARegex(StringRef Filename,
+                                      std::vector<Regex> &Regexes);
+
   // Get pointers to the functions in the runtime library.
   Constant *getStartFileFunc();
   Constant *getEmitFunctionFunc();
@@ -125,6 +131,9 @@ class GCOVProfiler {
   const TargetLibraryInfo *TLI;
   LLVMContext *Ctx;
   SmallVector<std::unique_ptr<GCOVFunction>, 16> Funcs;
+  std::vector<Regex> FilterRe;
+  std::vector<Regex> ExcludeRe;
+  StringMap<bool> InstrumentedFiles;
 };
 
 class GCOVProfilerLegacyPass : public ModulePass {
@@ -423,6 +432,72 @@ namespace {
   };
 }
 
+// RegexesStr is a string containing differents regex separated by a semi-colon.
+// For example "foo\..*$;bar\..*$".
+std::vector<Regex> GCOVProfiler::createRegexesFromString(StringRef RegexesStr) {
+  std::vector<Regex> Regexes;
+  while (!RegexesStr.empty()) {
+    std::pair<StringRef, StringRef> HeadTail = RegexesStr.split(';');
+    if (!HeadTail.first.empty()) {
+      Regex Re(HeadTail.first);
+      std::string Err;
+      if (!Re.isValid(Err)) {
+        Ctx->emitError(Twine("Regex ") + HeadTail.first +
+                       " is not valid: " + Err);
+      }
+      Regexes.emplace_back(std::move(Re));
+    }
+    RegexesStr = HeadTail.second;
+  }
+  return Regexes;
+}
+
+bool GCOVProfiler::doesFilenameMatchARegex(StringRef Filename,
+                                           std::vector<Regex> &Regexes) {
+  for (Regex &Re : Regexes) {
+    if (Re.match(Filename)) {
+      return true;
+    }
+  }
+  return false;
+}
+
+bool GCOVProfiler::isFunctionInstrumented(const Function &F) {
+  if (FilterRe.empty() && ExcludeRe.empty()) {
+    return true;
+  }
+  const StringRef Filename = F.getSubprogram()->getFilename();
+  auto It = InstrumentedFiles.find(Filename);
+  if (It != InstrumentedFiles.end()) {
+    return It->second;
+  }
+
+  SmallString<256> RealPath;
+  StringRef RealFilename;
+
+  // Path can be
+  // /usr/lib/gcc/x86_64-linux-gnu/8/../../../../include/c++/8/bits/*.h so for
+  // such a case we must get the real_path.
+  if (sys::fs::real_path(Filename, RealPath)) {
+    // real_path can fail with path like "foo.c".
+    RealFilename = Filename;
+  } else {
+    RealFilename = RealPath;
+  }
+
+  bool ShouldInstrument;
+  if (FilterRe.empty()) {
+    ShouldInstrument = !doesFilenameMatchARegex(RealFilename, ExcludeRe);
+  } else if (ExcludeRe.empty()) {
+    ShouldInstrument = doesFilenameMatchARegex(RealFilename, FilterRe);
+  } else {
+    ShouldInstrument = doesFilenameMatchARegex(RealFilename, FilterRe) &&
+                       !doesFilenameMatchARegex(RealFilename, ExcludeRe);
+  }
+  InstrumentedFiles[Filename] = ShouldInstrument;
+  return ShouldInstrument;
+}
+
 std::string GCOVProfiler::mangleName(const DICompileUnit *CU,
                                      GCovFileType OutputType) {
   bool Notes = OutputType == GCovFileType::GCNO;
@@ -472,6 +547,9 @@ bool GCOVProfiler::runOnModule(Module &M, const TargetLibraryInfo &TLI) {
 
   AddFlushBeforeForkAndExec();
 
+  FilterRe = createRegexesFromString(Options.Filter);
+  ExcludeRe = createRegexesFromString(Options.Exclude);
+
   if (Options.EmitNotes) emitProfileNotes();
   if (Options.EmitData) return emitProfileArcs();
   return false;
@@ -589,7 +667,8 @@ void GCOVProfiler::emitProfileNotes() {
     for (auto &F : M->functions()) {
       DISubprogram *SP = F.getSubprogram();
       if (!SP) continue;
-      if (!functionHasLines(F)) continue;
+      if (!functionHasLines(F) || !isFunctionInstrumented(F))
+        continue;
       // TODO: Functions using scope-based EH are currently not supported.
       if (isUsingScopeBasedEH(F)) continue;
 
@@ -673,7 +752,8 @@ bool GCOVProfiler::emitProfileArcs() {
     for (auto &F : M->functions()) {
       DISubprogram *SP = F.getSubprogram();
       if (!SP) continue;
-      if (!functionHasLines(F)) continue;
+      if (!functionHasLines(F) || !isFunctionInstrumented(F))
+        continue;
       // TODO: Functions using scope-based EH are currently not supported.
       if (isUsingScopeBasedEH(F)) continue;
       if (!Result) Result = true;
