Add a flag to remap manglings when reading profile data information.

This can be used to preserve profiling information across codebase
changes that have widespread impact on mangled names, but across which
most profiling data should still be usable. For example, when switching
from libstdc++ to libc++, or from the old libstdc++ ABI to the new ABI,
or even from a 32-bit to a 64-bit build.

The user can provide a remapping file specifying parts of mangled names
that should be treated as equivalent (eg, std::__1 should be treated as
equivalent to std::__cxx11), and profile data will be treated as
applying to a particular function if its name is equivalent to the name
of a function in the profile data under the provided equivalences. See
the documentation change for a description of how this is configured.

Remapping is supported for both sample-based profiling and instruction
profiling. We do not support remapping indirect branch target
information, but all other profile data should be remapped
appropriately.

Support is only added for the new pass manager. If someone wants to also
add support for this for the old pass manager, doing so should be
straightforward.

This is the LLVM side of Clang r344199.

Reviewers: davidxl, tejohnson, dlj, erik.pilkington

Subscribers: mehdi_amini, steven_wu, dexonsmith, llvm-commits

Differential Revision: https://reviews.llvm.org/D51249

llvm-svn: 344200

2 files changed, 55 insertions, 16 deletions

diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
index 182202fda05..4a69a0c2806 100644
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -96,6 +96,13 @@ static cl::opt<std::string> SampleProfileFile(
     "sample-profile-file", cl::init(""), cl::value_desc("filename"),
     cl::desc("Profile file loaded by -sample-profile"), cl::Hidden);
 
+// The named file contains a set of transformations that may have been applied
+// to the symbol names between the program from which the sample data was
+// collected and the current program's symbols.
+static cl::opt<std::string> SampleProfileRemappingFile(
+    "sample-profile-remapping-file", cl::init(""), cl::value_desc("filename"),
+    cl::desc("Profile remapping file loaded by -sample-profile"), cl::Hidden);
+
 static cl::opt<unsigned> SampleProfileMaxPropagateIterations(
     "sample-profile-max-propagate-iterations", cl::init(100),
     cl::desc("Maximum number of iterations to go through when propagating "
@@ -183,12 +190,12 @@ private:
 class SampleProfileLoader {
 public:
   SampleProfileLoader(
-      StringRef Name, bool IsThinLTOPreLink,
+      StringRef Name, StringRef RemapName, bool IsThinLTOPreLink,
       std::function<AssumptionCache &(Function &)> GetAssumptionCache,
       std::function<TargetTransformInfo &(Function &)> GetTargetTransformInfo)
       : GetAC(std::move(GetAssumptionCache)),
         GetTTI(std::move(GetTargetTransformInfo)), Filename(Name),
-        IsThinLTOPreLink(IsThinLTOPreLink) {}
+        RemappingFilename(RemapName), IsThinLTOPreLink(IsThinLTOPreLink) {}
 
   bool doInitialization(Module &M);
   bool runOnModule(Module &M, ModuleAnalysisManager *AM,
@@ -282,6 +289,9 @@ protected:
   /// Name of the profile file to load.
   std::string Filename;
 
+  /// Name of the profile remapping file to load.
+  std::string RemappingFilename;
+
   /// Flag indicating whether the profile input loaded successfully.
   bool ProfileIsValid = false;
 
@@ -311,13 +321,14 @@ public:
 
   SampleProfileLoaderLegacyPass(StringRef Name = SampleProfileFile,
                                 bool IsThinLTOPreLink = false)
-      : ModulePass(ID), SampleLoader(Name, IsThinLTOPreLink,
-                                     [&](Function &F) -> AssumptionCache & {
-                                       return ACT->getAssumptionCache(F);
-                                     },
-                                     [&](Function &F) -> TargetTransformInfo & {
-                                       return TTIWP->getTTI(F);
-                                     }) {
+      : ModulePass(ID),
+        SampleLoader(Name, SampleProfileRemappingFile, IsThinLTOPreLink,
+                     [&](Function &F) -> AssumptionCache & {
+                       return ACT->getAssumptionCache(F);
+                     },
+                     [&](Function &F) -> TargetTransformInfo & {
+                       return TTIWP->getTTI(F);
+                     }) {
     initializeSampleProfileLoaderLegacyPassPass(
         *PassRegistry::getPassRegistry());
   }
@@ -1515,11 +1526,26 @@ bool SampleProfileLoader::doInitialization(Module &M) {
   Reader = std::move(ReaderOrErr.get());
   Reader->collectFuncsToUse(M);
   ProfileIsValid = (Reader->read() == sampleprof_error::success);
+
+  if (!RemappingFilename.empty()) {
+    // Apply profile remappings to the loaded profile data if requested.
+    // For now, we only support remapping symbols encoded using the Itanium
+    // C++ ABI's name mangling scheme.
+    ReaderOrErr = SampleProfileReaderItaniumRemapper::create(
+        RemappingFilename, Ctx, std::move(Reader));
+    if (std::error_code EC = ReaderOrErr.getError()) {
+      std::string Msg = "Could not open profile remapping file: " + EC.message();
+      Ctx.diagnose(DiagnosticInfoSampleProfile(Filename, Msg));
+      return false;
+    }
+    Reader = std::move(ReaderOrErr.get());
+    ProfileIsValid = (Reader->read() == sampleprof_error::success);
+  }
   return true;
 }
 
 ModulePass *llvm::createSampleProfileLoaderPass() {
-  return new SampleProfileLoaderLegacyPass(SampleProfileFile);
+  return new SampleProfileLoaderLegacyPass();
 }
 
 ModulePass *llvm::createSampleProfileLoaderPass(StringRef Name) {
@@ -1612,6 +1638,8 @@ PreservedAnalyses SampleProfileLoaderPass::run(Module &M,
 
   SampleProfileLoader SampleLoader(
       ProfileFileName.empty() ? SampleProfileFile : ProfileFileName,
+      ProfileRemappingFileName.empty() ? SampleProfileRemappingFile
+                                       : ProfileRemappingFileName,
       IsThinLTOPreLink, GetAssumptionCache, GetTTI);
 
   SampleLoader.doInitialization(M);
diff --git a/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp b/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
index 307b7eaa219..ac851f660d9 100644
--- a/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
+++ b/llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp
@@ -141,6 +141,11 @@ static cl::opt<std::string>
                        cl::value_desc("filename"),
                        cl::desc("Specify the path of profile data file. This is"
                                 "mainly for test purpose."));
+static cl::opt<std::string> PGOTestProfileRemappingFile(
+    "pgo-test-profile-remapping-file", cl::init(""), cl::Hidden,
+    cl::value_desc("filename"),
+    cl::desc("Specify the path of profile remapping file. This is mainly for "
+             "test purpose."));
 
 // Command line option to disable value profiling. The default is false:
 // i.e. value profiling is enabled by default. This is for debug purpose.
@@ -1429,13 +1434,14 @@ PreservedAnalyses PGOInstrumentationGen::run(Module &M,
 }
 
 static bool annotateAllFunctions(
-    Module &M, StringRef ProfileFileName,
+    Module &M, StringRef ProfileFileName, StringRef ProfileRemappingFileName,
     function_ref<BranchProbabilityInfo *(Function &)> LookupBPI,
     function_ref<BlockFrequencyInfo *(Function &)> LookupBFI) {
   LLVM_DEBUG(dbgs() << "Read in profile counters: ");
   auto &Ctx = M.getContext();
   // Read the counter array from file.
-  auto ReaderOrErr = IndexedInstrProfReader::create(ProfileFileName);
+  auto ReaderOrErr =
+      IndexedInstrProfReader::create(ProfileFileName, ProfileRemappingFileName);
   if (Error E = ReaderOrErr.takeError()) {
     handleAllErrors(std::move(E), [&](const ErrorInfoBase &EI) {
       Ctx.diagnose(
@@ -1529,10 +1535,14 @@ static bool annotateAllFunctions(
   return true;
 }
 
-PGOInstrumentationUse::PGOInstrumentationUse(std::string Filename)
-    : ProfileFileName(std::move(Filename)) {
+PGOInstrumentationUse::PGOInstrumentationUse(std::string Filename,
+                                             std::string RemappingFilename)
+    : ProfileFileName(std::move(Filename)),
+      ProfileRemappingFileName(std::move(RemappingFilename)) {
   if (!PGOTestProfileFile.empty())
     ProfileFileName = PGOTestProfileFile;
+  if (!PGOTestProfileRemappingFile.empty())
+    ProfileRemappingFileName = PGOTestProfileRemappingFile;
 }
 
 PreservedAnalyses PGOInstrumentationUse::run(Module &M,
@@ -1547,7 +1557,8 @@ PreservedAnalyses PGOInstrumentationUse::run(Module &M,
     return &FAM.getResult<BlockFrequencyAnalysis>(F);
   };
 
-  if (!annotateAllFunctions(M, ProfileFileName, LookupBPI, LookupBFI))
+  if (!annotateAllFunctions(M, ProfileFileName, ProfileRemappingFileName,
+                            LookupBPI, LookupBFI))
     return PreservedAnalyses::all();
 
   return PreservedAnalyses::none();
@@ -1564,7 +1575,7 @@ bool PGOInstrumentationUseLegacyPass::runOnModule(Module &M) {
     return &this->getAnalysis<BlockFrequencyInfoWrapperPass>(F).getBFI();
   };
 
-  return annotateAllFunctions(M, ProfileFileName, LookupBPI, LookupBFI);
+  return annotateAllFunctions(M, ProfileFileName, "", LookupBPI, LookupBFI);
 }
 
 static std::string getSimpleNodeName(const BasicBlock *Node) {