[ThinLTO] Handle bitcode without function summary sections gracefully

Summary:
Several fixes to the handling of bitcode files without function summary
sections so that they are skipped during ThinLTO processing in llvm-lto
and the gold plugin when appropriate instead of aborting.

1 Don't assert when trying to add a FunctionInfo that doesn't have
  a summary attached.
2 Skip FunctionInfo structures that don't have attached function summary
  sections when trying to create the combined function summary.
3 In both llvm-lto and gold-plugin, check whether a bitcode file has
  a function summary section before trying to parse the index, and skip
  the bitcode file if it does not.
4 Fix hasFunctionSummaryInMemBuffer in BitcodeReader, which had a bug
  where we returned to early while looking for the summary section.

Also added llvm-lto and gold-plugin based tests for cases where we
don't have function summaries in the bitcode file. I verified that
either the first couple fixes described above are enough to avoid the
crashes, or fixes 1,3,4. But have combined them all here for added
robustness.

Reviewers: joker.eph

Subscribers: llvm-commits, joker.eph

Differential Revision: http://reviews.llvm.org/D14903

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@253796 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/IR/FunctionInfo.h b/include/llvm/IR/FunctionInfo.h
index e265ad3709637b5a8bd2d1b964cf3bd1153e1060..55f9ed88f1cd67240e2470dfceb1189bf702d557 100644 (file)
--- a/include/llvm/IR/FunctionInfo.h
+++ b/include/llvm/IR/FunctionInfo.h
@@ -196,8 +196,10 @@ public:
 
   /// Add a function info for a function of the given name.
   void addFunctionInfo(StringRef FuncName, std::unique_ptr<FunctionInfo> Info) {
-    if (ExportingModule) {
-      assert(Info->functionSummary());
+    // Update the HasExportedFunctions flag, but only if we had a function
+    // summary (i.e. we aren't parsing them lazily or have a bitcode file
+    // without a function summary section).
+    if (ExportingModule && Info->functionSummary()) {
       if (ExportingModule->getModuleIdentifier() ==
           Info->functionSummary()->modulePath())
         HasExportedFunctions = true;

diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp
index 9d907773cb369fb2cc0b5d95c4fa1847adfe2b88..11c9b131da7059387605ee0c57822f50ecf1c14d 100644 (file)
--- a/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -5566,12 +5566,14 @@ std::error_code FunctionIndexBitcodeReader::parseModule() {
 
     case BitstreamEntry::SubBlock:
       if (CheckFuncSummaryPresenceOnly) {
-        if (Entry.ID == bitc::FUNCTION_SUMMARY_BLOCK_ID)
+        if (Entry.ID == bitc::FUNCTION_SUMMARY_BLOCK_ID) {
           SeenFuncSummary = true;
+          // No need to parse the rest since we found the summary.
+          return std::error_code();
+        }
         if (Stream.SkipBlock())
           return error("Invalid record");
-        // No need to parse the rest since we found the summary.
-        return std::error_code();
+        continue;
       }
       switch (Entry.ID) {
       default: // Skip unknown content.

diff --git a/lib/IR/FunctionInfo.cpp b/lib/IR/FunctionInfo.cpp
index d26c7a4e9a03be5a37e297e3a9b50025f21bcca5..17a67bcf04721a2668f7f8eea98320eebac94070 100644 (file)
--- a/lib/IR/FunctionInfo.cpp
+++ b/lib/IR/FunctionInfo.cpp
@@ -31,6 +31,10 @@ void FunctionInfoIndex::mergeFrom(std::unique_ptr<FunctionInfoIndex> Other,
     assert(List.size() == 1);
     std::unique_ptr<FunctionInfo> Info = std::move(List.front());
 
+    // Skip if there was no function summary section.
+    if (!Info->functionSummary())
+      continue;
+
     // Add the module path string ref for this module if we haven't already
     // saved a reference to it.
     if (ModPath.empty())

diff --git a/test/Linker/funcimport.ll b/test/Linker/funcimport.ll
index dad9b95bb9fa770238c875d3f7f41b019151167f..d6aa0502f260f1849069508d17c19c18e7c5b323 100644 (file)
--- a/test/Linker/funcimport.ll
+++ b/test/Linker/funcimport.ll
@@ -1,3 +1,10 @@
+; First ensure that the ThinLTO handling in llvm-link and llvm-lto handles
+; bitcode without function summary sections gracefully.
+; RUN: llvm-as %s -o %t.bc
+; RUN: llvm-as %p/Inputs/funcimport.ll -o %t2.bc
+; RUN: llvm-link %t.bc -functionindex=%t.bc -S
+; RUN: llvm-lto -thinlto -o %t3 %t.bc %t2.bc
+
 ; Do setup work for all below tests: generate bitcode and combined index
 ; RUN: llvm-as -function-summary %s -o %t.bc
 ; RUN: llvm-as -function-summary %p/Inputs/funcimport.ll -o %t2.bc

diff --git a/test/tools/gold/X86/thinlto.ll b/test/tools/gold/X86/thinlto.ll
index b24e4af80bfaf46846fd2879bfa6c56f4df6deda..97def3d7a14de1c25cff81272d308f61013f6edc 100644 (file)
--- a/test/tools/gold/X86/thinlto.ll
+++ b/test/tools/gold/X86/thinlto.ll
@@ -1,3 +1,11 @@
+; First ensure that the ThinLTO handling in the gold plugin handles
+; bitcode without function summary sections gracefully.
+; RUN: llvm-as %s -o %t.o
+; RUN: llvm-as %p/Inputs/thinlto.ll -o %t2.o
+; RUN: %gold -plugin %llvmshlibdir/LLVMgold.so \
+; RUN:    --plugin-opt=thinlto \
+; RUN:    -shared %t.o %t2.o -o %t3
+
 ; RUN: llvm-as -function-summary %s -o %t.o
 ; RUN: llvm-as -function-summary %p/Inputs/thinlto.ll -o %t2.o
 

diff --git a/tools/gold/gold-plugin.cpp b/tools/gold/gold-plugin.cpp
index 77e4b83223c6d597dcea0cba261698e8d6b9131d..672c4e3580da71c58117a3672ba3e602cb1dc004 100644 (file)
--- a/tools/gold/gold-plugin.cpp
+++ b/tools/gold/gold-plugin.cpp
@@ -620,6 +620,13 @@ getFunctionIndexForFile(claimed_file &F, ld_plugin_input_file &Info) {
 
   MemoryBufferRef BufferRef(StringRef((const char *)View, Info.filesize),
                             Info.name);
+
+  // Don't bother trying to build an index if there is no summary information
+  // in this bitcode file.
+  if (!object::FunctionIndexObjectFile::hasFunctionSummaryInMemBuffer(
+          BufferRef, diagnosticHandler))
+    return std::unique_ptr<FunctionInfoIndex>(nullptr);
+
   ErrorOr<std::unique_ptr<object::FunctionIndexObjectFile>> ObjOrErr =
       object::FunctionIndexObjectFile::create(BufferRef, diagnosticHandler);
 
@@ -911,6 +918,11 @@ static ld_plugin_status allSymbolsReadHook(raw_fd_ostream *ApiFile) {
 
       std::unique_ptr<FunctionInfoIndex> Index =
           getFunctionIndexForFile(F, File);
+
+      // Skip files without a function summary.
+      if (!Index)
+        continue;
+
       CombinedIndex.mergeFrom(std::move(Index), ++NextModuleId);
     }
 

diff --git a/tools/llvm-lto/llvm-lto.cpp b/tools/llvm-lto/llvm-lto.cpp
index aac82d31a366f8b1b745d7c65cf99b881368e655..e580a5df57824d022b3cd1f45667453576b13597 100644 (file)
--- a/tools/llvm-lto/llvm-lto.cpp
+++ b/tools/llvm-lto/llvm-lto.cpp
@@ -192,24 +192,27 @@ static int listSymbols(StringRef Command, const TargetOptions &Options) {
 
 /// Parse the function index out of an IR file and return the function
 /// index object if found, or nullptr if not.
-static std::unique_ptr<FunctionInfoIndex>
-getFunctionIndexForFile(StringRef Path, std::string &Error,
+static ErrorOr<std::unique_ptr<FunctionInfoIndex>>
+getFunctionIndexForFile(StringRef Path,
                         DiagnosticHandlerFunction DiagnosticHandler) {
   std::unique_ptr<MemoryBuffer> Buffer;
   ErrorOr<std::unique_ptr<MemoryBuffer>> BufferOrErr =
       MemoryBuffer::getFile(Path);
-  if (std::error_code EC = BufferOrErr.getError()) {
-    Error = EC.message();
-    return nullptr;
-  }
+  if (std::error_code EC = BufferOrErr.getError())
+    return EC;
   Buffer = std::move(BufferOrErr.get());
+
+  // Don't bother trying to build an index if there is no summary information
+  // in this bitcode file.
+  if (!object::FunctionIndexObjectFile::hasFunctionSummaryInMemBuffer(
+          Buffer->getMemBufferRef(), DiagnosticHandler))
+    return std::unique_ptr<FunctionInfoIndex>(nullptr);
+
   ErrorOr<std::unique_ptr<object::FunctionIndexObjectFile>> ObjOrErr =
       object::FunctionIndexObjectFile::create(Buffer->getMemBufferRef(),
                                               DiagnosticHandler);
-  if (std::error_code EC = ObjOrErr.getError()) {
-    Error = EC.message();
-    return nullptr;
-  }
+  if (std::error_code EC = ObjOrErr.getError())
+    return EC;
   return (*ObjOrErr)->takeIndex();
 }
 
@@ -221,14 +224,18 @@ static int createCombinedFunctionIndex(StringRef Command) {
   FunctionInfoIndex CombinedIndex;
   uint64_t NextModuleId = 0;
   for (auto &Filename : InputFilenames) {
-    std::string Error;
-    std::unique_ptr<FunctionInfoIndex> Index =
-        getFunctionIndexForFile(Filename, Error, diagnosticHandler);
-    if (!Index) {
+    ErrorOr<std::unique_ptr<FunctionInfoIndex>> IndexOrErr =
+        getFunctionIndexForFile(Filename, diagnosticHandler);
+    if (std::error_code EC = IndexOrErr.getError()) {
+      std::string Error = EC.message();
       errs() << Command << ": error loading file '" << Filename
              << "': " << Error << "\n";
       return 1;
     }
+    std::unique_ptr<FunctionInfoIndex> Index = std::move(IndexOrErr.get());
+    // Skip files without a function summary.
+    if (!Index)
+      continue;
     CombinedIndex.mergeFrom(std::move(Index), ++NextModuleId);
   }
   std::error_code EC;