[clang][serialization] Blobify IMPORTS strings and signatures (#116095)

This PR changes a part of the PCM format to store string-like things in
the blob attached to a record instead of VBR6-encoding them into the
record itself. Applied to the `IMPORTS` section (which is very hot),
this speeds up dependency scanning by 2.8%.

1 files changed, 52 insertions, 56 deletions

diff --git a/clang/lib/Serialization/GlobalModuleIndex.cpp b/clang/lib/Serialization/GlobalModuleIndex.cpp
index 9c48712..4b920fc 100644
--- a/clang/lib/Serialization/GlobalModuleIndex.cpp
+++ b/clang/lib/Serialization/GlobalModuleIndex.cpp
@@ -614,62 +614,58 @@ llvm::Error GlobalModuleIndexBuilder::loadModuleFile(FileEntryRef File) {
     unsigned Code = MaybeCode.get();
 
     // Handle module dependencies.
-    if (State == ControlBlock && Code == IMPORTS) {
-      // Load each of the imported PCH files.
-      unsigned Idx = 0, N = Record.size();
-      while (Idx < N) {
-        // Read information about the AST file.
-
-        // Skip the imported kind
-        ++Idx;
-
-        // Skip if it is standard C++ module
-        ++Idx;
-
-        // Skip the import location
-        ++Idx;
-
-        // Load stored size/modification time.
-        off_t StoredSize = (off_t)Record[Idx++];
-        time_t StoredModTime = (time_t)Record[Idx++];
-
-        // Skip the stored signature.
-        // FIXME: we could read the signature out of the import and validate it.
-        auto FirstSignatureByte = Record.begin() + Idx;
-        ASTFileSignature StoredSignature = ASTFileSignature::create(
-            FirstSignatureByte, FirstSignatureByte + ASTFileSignature::size);
-        Idx += ASTFileSignature::size;
-
-        // Skip the module name (currently this is only used for prebuilt
-        // modules while here we are only dealing with cached).
-        Idx += Record[Idx] + 1;
-
-        // Retrieve the imported file name.
-        unsigned Length = Record[Idx++];
-        SmallString<128> ImportedFile(Record.begin() + Idx,
-                                      Record.begin() + Idx + Length);
-        Idx += Length;
-
-        // Find the imported module file.
-        auto DependsOnFile =
-            FileMgr.getOptionalFileRef(ImportedFile, /*OpenFile=*/false,
-                                       /*CacheFailure=*/false);
-
-        if (!DependsOnFile)
-          return llvm::createStringError(std::errc::bad_file_descriptor,
-                                         "imported file \"%s\" not found",
-                                         ImportedFile.c_str());
-
-        // Save the information in ImportedModuleFileInfo so we can verify after
-        // loading all pcms.
-        ImportedModuleFiles.insert(std::make_pair(
-            *DependsOnFile, ImportedModuleFileInfo(StoredSize, StoredModTime,
-                                                   StoredSignature)));
-
-        // Record the dependency.
-        unsigned DependsOnID = getModuleFileInfo(*DependsOnFile).ID;
-        getModuleFileInfo(File).Dependencies.push_back(DependsOnID);
-      }
+    if (State == ControlBlock && Code == IMPORT) {
+      unsigned Idx = 0;
+      // Read information about the AST file.
+
+      // Skip the imported kind
+      ++Idx;
+
+      // Skip the import location
+      ++Idx;
+
+      // Skip the module name (currently this is only used for prebuilt
+      // modules while here we are only dealing with cached).
+      Blob = Blob.substr(Record[Idx++]);
+
+      // Skip if it is standard C++ module
+      ++Idx;
+
+      // Load stored size/modification time.
+      off_t StoredSize = (off_t)Record[Idx++];
+      time_t StoredModTime = (time_t)Record[Idx++];
+
+      // Skip the stored signature.
+      // FIXME: we could read the signature out of the import and validate it.
+      StringRef SignatureBytes = Blob.substr(0, ASTFileSignature::size);
+      auto StoredSignature = ASTFileSignature::create(SignatureBytes.begin(),
+                                                      SignatureBytes.end());
+      Blob = Blob.substr(ASTFileSignature::size);
+
+      // Retrieve the imported file name.
+      unsigned Length = Record[Idx++];
+      StringRef ImportedFile = Blob.substr(0, Length);
+      Blob = Blob.substr(Length);
+
+      // Find the imported module file.
+      auto DependsOnFile =
+          FileMgr.getOptionalFileRef(ImportedFile, /*OpenFile=*/false,
+                                     /*CacheFailure=*/false);
+
+      if (!DependsOnFile)
+        return llvm::createStringError(std::errc::bad_file_descriptor,
+                                       "imported file \"%s\" not found",
+                                       std::string(ImportedFile).c_str());
+
+      // Save the information in ImportedModuleFileInfo so we can verify after
+      // loading all pcms.
+      ImportedModuleFiles.insert(std::make_pair(
+          *DependsOnFile, ImportedModuleFileInfo(StoredSize, StoredModTime,
+                                                 StoredSignature)));
+
+      // Record the dependency.
+      unsigned DependsOnID = getModuleFileInfo(*DependsOnFile).ID;
+      getModuleFileInfo(File).Dependencies.push_back(DependsOnID);
 
       continue;
     }