[Coverage] Store compilation dir separately in coverage mapping

We currently always store absolute filenames in coverage mapping.  This
is problematic for several reasons. It poses a problem for distributed
compilation as source location might vary across machines.  We are also
duplicating the path prefix potentially wasting space.

This change modifies how we store filenames in coverage mapping. Rather
than absolute paths, it stores the compilation directory and file paths
as given to the compiler, either relative or absolute. Later when
reading the coverage mapping information, we recombine relative paths
with the working directory. This approach is similar to handling
ofDW_AT_comp_dir in DWARF.

Finally, we also provide a new option, -fprofile-compilation-dir akin
to -fdebug-compilation-dir which can be used to manually override the
compilation directory which is useful in distributed compilation cases.

Differential Revision: https://reviews.llvm.org/D95753

1 files changed, 54 insertions, 41 deletions

diff --git a/llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp b/llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp
index 1acdcb4..942f8e7 100644
--- a/llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp
+++ b/llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp
@@ -97,9 +97,7 @@ Error RawCoverageReader::readString(StringRef &Result) {
   return Error::success();
 }
 
-Error RawCoverageFilenamesReader::read(
-    CovMapVersion Version,
-    BinaryCoverageReader::DecompressedData &Decompressed) {
+Error RawCoverageFilenamesReader::read(CovMapVersion Version) {
   uint64_t NumFilenames;
   if (auto Err = readSize(NumFilenames))
     return Err;
@@ -107,7 +105,7 @@ Error RawCoverageFilenamesReader::read(
     return make_error<CoverageMapError>(coveragemap_error::malformed);
 
   if (Version < CovMapVersion::Version4)
-    return readUncompressed(NumFilenames);
+    return readUncompressed(Version, NumFilenames);
 
   // The uncompressed length may exceed the size of the encoded filenames.
   // Skip size validation.
@@ -124,11 +122,8 @@ Error RawCoverageFilenamesReader::read(
       return make_error<CoverageMapError>(
           coveragemap_error::decompression_failed);
 
-    // Allocate memory for the decompressed filenames. Transfer ownership of
-    // the memory to BinaryCoverageReader.
-    auto DecompressedStorage = std::make_unique<SmallVector<char, 0>>();
-    SmallVectorImpl<char> &StorageBuf = *DecompressedStorage.get();
-    Decompressed.push_back(std::move(DecompressedStorage));
+    // Allocate memory for the decompressed filenames.
+    SmallVector<char, 0> StorageBuf;
 
     // Read compressed filenames.
     StringRef CompressedFilenames = Data.substr(0, CompressedLen);
@@ -143,19 +138,40 @@ Error RawCoverageFilenamesReader::read(
 
     StringRef UncompressedFilenames(StorageBuf.data(), StorageBuf.size());
     RawCoverageFilenamesReader Delegate(UncompressedFilenames, Filenames);
-    return Delegate.readUncompressed(NumFilenames);
+    return Delegate.readUncompressed(Version, NumFilenames);
   }
 
-  return readUncompressed(NumFilenames);
+  return readUncompressed(Version, NumFilenames);
 }
 
-Error RawCoverageFilenamesReader::readUncompressed(uint64_t NumFilenames) {
+Error RawCoverageFilenamesReader::readUncompressed(CovMapVersion Version,
+                                                   uint64_t NumFilenames) {
   // Read uncompressed filenames.
-  for (size_t I = 0; I < NumFilenames; ++I) {
-    StringRef Filename;
-    if (auto Err = readString(Filename))
+  if (Version < CovMapVersion::Version6) {
+    for (size_t I = 0; I < NumFilenames; ++I) {
+      StringRef Filename;
+      if (auto Err = readString(Filename))
+        return Err;
+      Filenames.push_back(Filename.str());
+    }
+  } else {
+    StringRef CWD;
+    if (auto Err = readString(CWD))
       return Err;
-    Filenames.push_back(Filename);
+    Filenames.push_back(CWD.str());
+
+    for (size_t I = 1; I < NumFilenames; ++I) {
+      StringRef Filename;
+      if (auto Err = readString(Filename))
+        return Err;
+      if (sys::path::is_absolute(Filename)) {
+        Filenames.push_back(Filename.str());
+      } else {
+        SmallString<256> P(CWD);
+        llvm::sys::path::append(P, Filename);
+        Filenames.push_back(static_cast<std::string>(P));
+      }
+    }
   }
   return Error::success();
 }
@@ -481,9 +497,8 @@ struct CovMapFuncRecordReader {
   //
   // Returns a pointer to the next \c CovHeader if it exists, or to an address
   // greater than \p CovEnd if not.
-  virtual Expected<const char *>
-  readCoverageHeader(const char *CovBuf, const char *CovBufEnd,
-                     BinaryCoverageReader::DecompressedData &Decompressed) = 0;
+  virtual Expected<const char *> readCoverageHeader(const char *CovBuf,
+                                                    const char *CovBufEnd) = 0;
 
   // Read function records.
   //
@@ -505,7 +520,7 @@ struct CovMapFuncRecordReader {
   static Expected<std::unique_ptr<CovMapFuncRecordReader>>
   get(CovMapVersion Version, InstrProfSymtab &P,
       std::vector<BinaryCoverageReader::ProfileMappingRecord> &R,
-      std::vector<StringRef> &F);
+      std::vector<std::string> &F);
 };
 
 // A class for reading coverage mapping function records for a module.
@@ -519,7 +534,7 @@ class VersionedCovMapFuncRecordReader : public CovMapFuncRecordReader {
   // in \c Records.
   DenseMap<NameRefType, size_t> FunctionRecords;
   InstrProfSymtab &ProfileNames;
-  std::vector<StringRef> &Filenames;
+  std::vector<std::string> &Filenames;
   std::vector<BinaryCoverageReader::ProfileMappingRecord> &Records;
 
   // Maps a hash of the filenames in a TU to a \c FileRange. The range
@@ -579,14 +594,13 @@ public:
   VersionedCovMapFuncRecordReader(
       InstrProfSymtab &P,
       std::vector<BinaryCoverageReader::ProfileMappingRecord> &R,
-      std::vector<StringRef> &F)
+      std::vector<std::string> &F)
       : ProfileNames(P), Filenames(F), Records(R) {}
 
   ~VersionedCovMapFuncRecordReader() override = default;
 
-  Expected<const char *> readCoverageHeader(
-      const char *CovBuf, const char *CovBufEnd,
-      BinaryCoverageReader::DecompressedData &Decompressed) override {
+  Expected<const char *> readCoverageHeader(const char *CovBuf,
+                                            const char *CovBufEnd) override {
     using namespace support;
 
     if (CovBuf + sizeof(CovMapHeader) > CovBufEnd)
@@ -615,7 +629,7 @@ public:
     size_t FilenamesBegin = Filenames.size();
     StringRef FilenameRegion(CovBuf, FilenamesSize);
     RawCoverageFilenamesReader Reader(FilenameRegion, Filenames);
-    if (auto Err = Reader.read(Version, Decompressed))
+    if (auto Err = Reader.read(Version))
       return std::move(Err);
     CovBuf += FilenamesSize;
     FilenameRange FileRange(FilenamesBegin, Filenames.size() - FilenamesBegin);
@@ -721,7 +735,7 @@ template <class IntPtrT, support::endianness Endian>
 Expected<std::unique_ptr<CovMapFuncRecordReader>> CovMapFuncRecordReader::get(
     CovMapVersion Version, InstrProfSymtab &P,
     std::vector<BinaryCoverageReader::ProfileMappingRecord> &R,
-    std::vector<StringRef> &F) {
+    std::vector<std::string> &F) {
   using namespace coverage;
 
   switch (Version) {
@@ -732,6 +746,7 @@ Expected<std::unique_ptr<CovMapFuncRecordReader>> CovMapFuncRecordReader::get(
   case CovMapVersion::Version3:
   case CovMapVersion::Version4:
   case CovMapVersion::Version5:
+  case CovMapVersion::Version6:
     // Decompress the name data.
     if (Error E = P.create(P.getNameData()))
       return std::move(E);
@@ -747,6 +762,9 @@ Expected<std::unique_ptr<CovMapFuncRecordReader>> CovMapFuncRecordReader::get(
     else if (Version == CovMapVersion::Version5)
       return std::make_unique<VersionedCovMapFuncRecordReader<
           CovMapVersion::Version5, IntPtrT, Endian>>(P, R, F);
+    else if (Version == CovMapVersion::Version6)
+      return std::make_unique<VersionedCovMapFuncRecordReader<
+          CovMapVersion::Version6, IntPtrT, Endian>>(P, R, F);
   }
   llvm_unreachable("Unsupported version");
 }
@@ -755,8 +773,7 @@ template <typename T, support::endianness Endian>
 static Error readCoverageMappingData(
     InstrProfSymtab &ProfileNames, StringRef CovMap, StringRef FuncRecords,
     std::vector<BinaryCoverageReader::ProfileMappingRecord> &Records,
-    std::vector<StringRef> &Filenames,
-    BinaryCoverageReader::DecompressedData &Decompressed) {
+    std::vector<std::string> &Filenames) {
   using namespace coverage;
 
   // Read the records in the coverage data section.
@@ -782,8 +799,7 @@ static Error readCoverageMappingData(
     // header.
     //
     // Return a pointer to the next coverage header.
-    auto NextOrErr =
-        Reader->readCoverageHeader(CovBuf, CovBufEnd, Decompressed);
+    auto NextOrErr = Reader->readCoverageHeader(CovBuf, CovBufEnd);
     if (auto E = NextOrErr.takeError())
       return E;
     CovBuf = NextOrErr.get();
@@ -810,25 +826,23 @@ BinaryCoverageReader::createCoverageReaderFromBuffer(
     if (Error E =
             readCoverageMappingData<uint32_t, support::endianness::little>(
                 Reader->ProfileNames, Coverage, FuncRecordsRef,
-                Reader->MappingRecords, Reader->Filenames,
-                Reader->Decompressed))
+                Reader->MappingRecords, Reader->Filenames))
       return std::move(E);
   } else if (BytesInAddress == 4 && Endian == support::endianness::big) {
     if (Error E = readCoverageMappingData<uint32_t, support::endianness::big>(
             Reader->ProfileNames, Coverage, FuncRecordsRef,
-            Reader->MappingRecords, Reader->Filenames, Reader->Decompressed))
+            Reader->MappingRecords, Reader->Filenames))
       return std::move(E);
   } else if (BytesInAddress == 8 && Endian == support::endianness::little) {
     if (Error E =
             readCoverageMappingData<uint64_t, support::endianness::little>(
                 Reader->ProfileNames, Coverage, FuncRecordsRef,
-                Reader->MappingRecords, Reader->Filenames,
-                Reader->Decompressed))
+                Reader->MappingRecords, Reader->Filenames))
       return std::move(E);
   } else if (BytesInAddress == 8 && Endian == support::endianness::big) {
     if (Error E = readCoverageMappingData<uint64_t, support::endianness::big>(
             Reader->ProfileNames, Coverage, FuncRecordsRef,
-            Reader->MappingRecords, Reader->Filenames, Reader->Decompressed))
+            Reader->MappingRecords, Reader->Filenames))
       return std::move(E);
   } else
     return make_error<CoverageMapError>(coveragemap_error::malformed);
@@ -1075,10 +1089,9 @@ Error BinaryCoverageReader::readNextRecord(CoverageMappingRecord &Record) {
   Expressions.clear();
   MappingRegions.clear();
   auto &R = MappingRecords[CurrentRecord];
-  RawCoverageMappingReader Reader(
-      R.CoverageMapping,
-      makeArrayRef(Filenames).slice(R.FilenamesBegin, R.FilenamesSize),
-      FunctionsFilenames, Expressions, MappingRegions);
+  auto F = makeArrayRef(Filenames).slice(R.FilenamesBegin, R.FilenamesSize);
+  RawCoverageMappingReader Reader(R.CoverageMapping, F, FunctionsFilenames,
+                                  Expressions, MappingRegions);
   if (auto Err = Reader.read())
     return Err;