[SampleFDO] Add profile remapping support for profile on-demand loading used

by ExtBinary format profile

Profile on-demand loading was added for ExtBinary format profile in rL374233,
but currently profile on-demand loading doesn't work well with profile
remapping. The patch adds the support.

Suppose a function in the current module has outline instance in the profile.
The function name in the module is different from the name of the outline
instance, but remapper knows the two names are equal. When loading profile
on-demand, the outline instance has to be loaded with remapper's help.

At the same time SampleProfileReaderItaniumRemapper is changed from a proxy
of SampleProfileReader to a helper member in SampleProfileReader.

Differential Revision: https://reviews.llvm.org/D68901

llvm-svn: 375295

1 files changed, 83 insertions, 37 deletions

diff --git a/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
index cf3e56728e2..001aafce7bf 100644
--- a/llvm/lib/ProfileData/SampleProfReader.cpp
+++ b/llvm/lib/ProfileData/SampleProfReader.cpp
@@ -191,7 +191,7 @@ static bool ParseLine(const StringRef &Input, bool &IsCallsite, uint32_t &Depth,
 /// the expected format.
 ///
 /// \returns true if the file was loaded successfully, false otherwise.
-std::error_code SampleProfileReaderText::read() {
+std::error_code SampleProfileReaderText::readImpl() {
   line_iterator LineIt(*Buffer, /*SkipBlanks=*/true, '#');
   sampleprof_error Result = sampleprof_error::success;
 
@@ -461,7 +461,7 @@ SampleProfileReaderBinary::readFuncProfile(const uint8_t *Start) {
   return sampleprof_error::success;
 }
 
-std::error_code SampleProfileReaderBinary::read() {
+std::error_code SampleProfileReaderBinary::readImpl() {
   while (!at_eof()) {
     if (std::error_code EC = readFuncProfile(Data))
       return EC;
@@ -540,15 +540,23 @@ std::error_code SampleProfileReaderExtBinary::readFuncProfiles() {
     return sampleprof_error::success;
   }
 
-  for (auto Name : FuncsToUse) {
-    auto iter = FuncOffsetTable.find(Name);
-    if (iter == FuncOffsetTable.end())
+  if (Remapper) {
+    for (auto Name : FuncsToUse) {
+      Remapper->insert(Name);
+    }
+  }
+
+  for (auto NameOffset : FuncOffsetTable) {
+    auto FuncName = NameOffset.first;
+    if (!FuncsToUse.count(FuncName) &&
+        (!Remapper || !Remapper->exist(FuncName)))
       continue;
-    const uint8_t *FuncProfileAddr = Start + iter->second;
+    const uint8_t *FuncProfileAddr = Start + NameOffset.second;
     assert(FuncProfileAddr < End && "out of LBRProfile section");
     if (std::error_code EC = readFuncProfile(FuncProfileAddr))
       return EC;
   }
+
   Data = End;
   return sampleprof_error::success;
 }
@@ -593,7 +601,7 @@ std::error_code SampleProfileReaderExtBinaryBase::decompressSection(
   return sampleprof_error::success;
 }
 
-std::error_code SampleProfileReaderExtBinaryBase::read() {
+std::error_code SampleProfileReaderExtBinaryBase::readImpl() {
   const uint8_t *BufStart =
       reinterpret_cast<const uint8_t *>(Buffer->getBufferStart());
 
@@ -635,7 +643,7 @@ std::error_code SampleProfileReaderExtBinaryBase::read() {
   return sampleprof_error::success;
 }
 
-std::error_code SampleProfileReaderCompactBinary::read() {
+std::error_code SampleProfileReaderCompactBinary::readImpl() {
   std::vector<uint64_t> OffsetsToUse;
   if (UseAllFuncs) {
     for (auto FuncEntry : FuncOffsetTable) {
@@ -1184,7 +1192,7 @@ std::error_code SampleProfileReaderGCC::readOneFunctionProfile(
 ///
 /// This format is generated by the Linux Perf conversion tool at
 /// https://github.com/google/autofdo.
-std::error_code SampleProfileReaderGCC::read() {
+std::error_code SampleProfileReaderGCC::readImpl() {
   // Read the string table.
   if (std::error_code EC = readNameTable())
     return EC;
@@ -1201,38 +1209,31 @@ bool SampleProfileReaderGCC::hasFormat(const MemoryBuffer &Buffer) {
   return Magic == "adcg*704";
 }
 
-std::error_code SampleProfileReaderItaniumRemapper::read() {
-  // If the underlying data is in compact format, we can't remap it because
+void SampleProfileReaderItaniumRemapper::applyRemapping(LLVMContext &Ctx) {
+  // If the reader is in compact format, we can't remap it because
   // we don't know what the original function names were.
-  if (getFormat() == SPF_Compact_Binary) {
+  if (Reader.getFormat() == SPF_Compact_Binary) {
     Ctx.diagnose(DiagnosticInfoSampleProfile(
-        Buffer->getBufferIdentifier(),
+        Reader.getBuffer()->getBufferIdentifier(),
         "Profile data remapping cannot be applied to profile data "
         "in compact format (original mangled names are not available).",
         DS_Warning));
-    return sampleprof_error::success;
-  }
-
-  if (Error E = Remappings.read(*Buffer)) {
-    handleAllErrors(
-        std::move(E), [&](const SymbolRemappingParseError &ParseError) {
-          reportError(ParseError.getLineNum(), ParseError.getMessage());
-        });
-    return sampleprof_error::malformed;
+    return;
   }
 
-  for (auto &Sample : getProfiles())
-    if (auto Key = Remappings.insert(Sample.first()))
+  assert(Remappings && "should be initialized while creating remapper");
+  for (auto &Sample : Reader.getProfiles())
+    if (auto Key = Remappings->insert(Sample.first()))
       SampleMap.insert({Key, &Sample.second});
 
-  return sampleprof_error::success;
+  RemappingApplied = true;
 }
 
 FunctionSamples *
 SampleProfileReaderItaniumRemapper::getSamplesFor(StringRef Fname) {
-  if (auto Key = Remappings.lookup(Fname))
+  if (auto Key = Remappings->lookup(Fname))
     return SampleMap.lookup(Key);
-  return SampleProfileReader::getSamplesFor(Fname);
+  return nullptr;
 }
 
 /// Prepare a memory buffer for the contents of \p Filename.
@@ -1258,13 +1259,16 @@ setupMemoryBuffer(const Twine &Filename) {
 ///
 /// \param C The LLVM context to use to emit diagnostics.
 ///
+/// \param RemapFilename The file used for profile remapping.
+///
 /// \returns an error code indicating the status of the created reader.
 ErrorOr<std::unique_ptr<SampleProfileReader>>
-SampleProfileReader::create(const Twine &Filename, LLVMContext &C) {
+SampleProfileReader::create(const std::string Filename, LLVMContext &C,
+                            const std::string RemapFilename) {
   auto BufferOrError = setupMemoryBuffer(Filename);
   if (std::error_code EC = BufferOrError.getError())
     return EC;
-  return create(BufferOrError.get(), C);
+  return create(BufferOrError.get(), C, RemapFilename);
 }
 
 /// Create a sample profile remapper from the given input, to remap the
@@ -1272,20 +1276,48 @@ SampleProfileReader::create(const Twine &Filename, LLVMContext &C) {
 ///
 /// \param Filename The file to open.
 ///
-/// \param C The LLVM context to use to emit diagnostics.
+/// \param Reader The profile reader the remapper is going to be applied to.
 ///
-/// \param Underlying The underlying profile data reader to remap.
+/// \param C The LLVM context to use to emit diagnostics.
 ///
 /// \returns an error code indicating the status of the created reader.
-ErrorOr<std::unique_ptr<SampleProfileReader>>
-SampleProfileReaderItaniumRemapper::create(
-    const Twine &Filename, LLVMContext &C,
-    std::unique_ptr<SampleProfileReader> Underlying) {
+ErrorOr<std::unique_ptr<SampleProfileReaderItaniumRemapper>>
+SampleProfileReaderItaniumRemapper::create(const std::string Filename,
+                                           SampleProfileReader &Reader,
+                                           LLVMContext &C) {
   auto BufferOrError = setupMemoryBuffer(Filename);
   if (std::error_code EC = BufferOrError.getError())
     return EC;
+  return create(BufferOrError.get(), Reader, C);
+}
+
+/// Create a sample profile remapper from the given input, to remap the
+/// function names in the given profile data.
+///
+/// \param B The memory buffer to create the reader from (assumes ownership).
+///
+/// \param C The LLVM context to use to emit diagnostics.
+///
+/// \param Reader The profile reader the remapper is going to be applied to.
+///
+/// \returns an error code indicating the status of the created reader.
+ErrorOr<std::unique_ptr<SampleProfileReaderItaniumRemapper>>
+SampleProfileReaderItaniumRemapper::create(std::unique_ptr<MemoryBuffer> &B,
+                                           SampleProfileReader &Reader,
+                                           LLVMContext &C) {
+  auto Remappings = std::make_unique<SymbolRemappingReader>();
+  if (Error E = Remappings->read(*B.get())) {
+    handleAllErrors(
+        std::move(E), [&](const SymbolRemappingParseError &ParseError) {
+          C.diagnose(DiagnosticInfoSampleProfile(B->getBufferIdentifier(),
+                                                 ParseError.getLineNum(),
+                                                 ParseError.getMessage()));
+        });
+    return sampleprof_error::malformed;
+  }
+
   return std::make_unique<SampleProfileReaderItaniumRemapper>(
-      std::move(BufferOrError.get()), C, std::move(Underlying));
+      std::move(B), std::move(Remappings), Reader);
 }
 
 /// Create a sample profile reader based on the format of the input data.
@@ -1294,9 +1326,12 @@ SampleProfileReaderItaniumRemapper::create(
 ///
 /// \param C The LLVM context to use to emit diagnostics.
 ///
+/// \param RemapFilename The file used for profile remapping.
+///
 /// \returns an error code indicating the status of the created reader.
 ErrorOr<std::unique_ptr<SampleProfileReader>>
-SampleProfileReader::create(std::unique_ptr<MemoryBuffer> &B, LLVMContext &C) {
+SampleProfileReader::create(std::unique_ptr<MemoryBuffer> &B, LLVMContext &C,
+                            const std::string RemapFilename) {
   std::unique_ptr<SampleProfileReader> Reader;
   if (SampleProfileReaderRawBinary::hasFormat(*B))
     Reader.reset(new SampleProfileReaderRawBinary(std::move(B), C));
@@ -1311,6 +1346,17 @@ SampleProfileReader::create(std::unique_ptr<MemoryBuffer> &B, LLVMContext &C) {
   else
     return sampleprof_error::unrecognized_format;
 
+  if (!RemapFilename.empty()) {
+    auto ReaderOrErr =
+        SampleProfileReaderItaniumRemapper::create(RemapFilename, *Reader, C);
+    if (std::error_code EC = ReaderOrErr.getError()) {
+      std::string Msg = "Could not create remapper: " + EC.message();
+      C.diagnose(DiagnosticInfoSampleProfile(RemapFilename, Msg));
+      return EC;
+    }
+    Reader->Remapper = std::move(ReaderOrErr.get());
+  }
+
   FunctionSamples::Format = Reader->getFormat();
   if (std::error_code EC = Reader->readHeader()) {
     return EC;