[clang][modules][deps] Avoid checks for relocated modules

Currently, `ASTReader` performs some checks to diagnose relocated modules. This can add quite a bit of overhead to the scanner: it requires looking up, parsing and resolving module maps for all transitively loaded module files (and all the module maps encountered in the search paths on the way). Most of those checks are not really useful in the scanner anyway, since it uses strict context hash and immutable filesystem, which prevent those scenarios in the first place.

This can speed up scanning by up to 30%.

Depends on D150292.

Reviewed By: benlangmuir

Differential Revision: https://reviews.llvm.org/D150320

(cherry picked from commit 227f719)

Author: jansvoboda11

clang/include/clang/Lex/PreprocessorOptions.h

@@ -80,6 +80,9 @@ class PreprocessorOptions {
   std::vector<std::string> Includes;
   std::vector<std::string> MacroIncludes;
 
+  /// Perform extra checks when loading PCM files for mutable file systems.
+  bool ModulesCheckRelocated = true;
+
   /// Initialize the preprocessor with the compiler and target specific
   /// predefines.
   bool UsePredefines = true;

clang/lib/Serialization/ASTReader.cpp

@@ -2949,6 +2949,9 @@ ASTReader::ReadControlBlock(ModuleFile &F,
       BaseDirectoryAsWritten = Blob;
       assert(!F.ModuleName.empty() &&
              "MODULE_DIRECTORY found before MODULE_NAME");
+      F.BaseDirectory = std::string(Blob);
+      if (!PP.getPreprocessorOpts().ModulesCheckRelocated)
+        break;
       // If we've already loaded a module map file covering this module, we may
       // have a better path for it (relative to the current build).
       Module *M = PP.getHeaderSearchInfo().lookupModule(
@@ -2970,8 +2973,6 @@ ASTReader::ReadControlBlock(ModuleFile &F,
           }
         }
         F.BaseDirectory = std::string(M->Directory->getName());
-      } else {
-        F.BaseDirectory = std::string(Blob);
       }
       break;
     }
@@ -3949,7 +3950,8 @@ ASTReader::ReadModuleMapFileBlock(RecordData &Record, ModuleFile &F,
   // usable header search context.
   assert(!F.ModuleName.empty() &&
          "MODULE_NAME should come before MODULE_MAP_FILE");
-  if (F.Kind == MK_ImplicitModule && ModuleMgr.begin()->Kind != MK_MainFile) {
+  if (PP.getPreprocessorOpts().ModulesCheckRelocated &&
+      F.Kind == MK_ImplicitModule && ModuleMgr.begin()->Kind != MK_MainFile) {
     // An implicitly-loaded module file should have its module listed in some
     // module map file that we've already loaded.
     Module *M =

clang/lib/Tooling/DependencyScanning/DependencyScanningWorker.cpp

@@ -432,6 +432,9 @@ class DependencyScanningAction : public tooling::ToolAction {
     // context hashing.
     ScanInstance.getHeaderSearchOpts().ModulesStrictContextHash = true;
 
+    // Avoid some checks and module map parsing when loading PCM files.
+    ScanInstance.getPreprocessorOpts().ModulesCheckRelocated = false;
+
     std::unique_ptr<FrontendAction> Action;
 
     if (ModuleName)

clang/test/ClangScanDeps/header-search-pruning-transitive.c

@@ -72,8 +72,8 @@ module X { header "X.h" }
 // CHECK:            ],
 // CHECK-NEXT:       "context-hash": "[[HASH_X:.*]]",
 // CHECK-NEXT:       "file-deps": [
-// CHECK-NEXT:         "[[PREFIX]]/./X.h",
-// CHECK-NEXT:         "[[PREFIX]]/./module.modulemap"
+// CHECK-NEXT:         "[[PREFIX]]/X.h",
+// CHECK-NEXT:         "[[PREFIX]]/module.modulemap"
 // CHECK-NEXT:       ],
 // CHECK-NEXT:       "name": "X"
 // CHECK-NEXT:     },
@@ -84,11 +84,11 @@ module X { header "X.h" }
 // CHECK:            ],
 // CHECK-NEXT:       "context-hash": "[[HASH_Y_WITH_A]]",
 // CHECK-NEXT:       "file-deps": [
-// CHECK-NEXT:         "[[PREFIX]]/./Y.h",
-// CHECK-NEXT:         "[[PREFIX]]/./a/a.h",
-// CHECK-NEXT:         "[[PREFIX]]/./begin/begin.h",
-// CHECK-NEXT:         "[[PREFIX]]/./end/end.h",
-// CHECK-NEXT:         "[[PREFIX]]/./module.modulemap"
+// CHECK-NEXT:         "[[PREFIX]]/Y.h",
+// CHECK-NEXT:         "[[PREFIX]]/a/a.h",
+// CHECK-NEXT:         "[[PREFIX]]/begin/begin.h",
+// CHECK-NEXT:         "[[PREFIX]]/end/end.h",
+// CHECK-NEXT:         "[[PREFIX]]/module.modulemap"
 // CHECK-NEXT:       ],
 // CHECK-NEXT:       "name": "Y"
 // CHECK-NEXT:     }
@@ -126,8 +126,8 @@ module X { header "X.h" }
 // also has a different context hash from the first version of module X.
 // CHECK-NOT:        "context-hash": "[[HASH_X]]",
 // CHECK:            "file-deps": [
-// CHECK-NEXT:         "[[PREFIX]]/./X.h",
-// CHECK-NEXT:         "[[PREFIX]]/./module.modulemap"
+// CHECK-NEXT:         "[[PREFIX]]/X.h",
+// CHECK-NEXT:         "[[PREFIX]]/module.modulemap"
 // CHECK-NEXT:       ],
 // CHECK-NEXT:       "name": "X"
 // CHECK-NEXT:     },
@@ -138,10 +138,10 @@ module X { header "X.h" }
 // CHECK:            ],
 // CHECK-NEXT:       "context-hash": "[[HASH_Y_WITHOUT_A]]",
 // CHECK-NEXT:       "file-deps": [
-// CHECK-NEXT:         "[[PREFIX]]/./Y.h",
-// CHECK-NEXT:         "[[PREFIX]]/./begin/begin.h",
-// CHECK-NEXT:         "[[PREFIX]]/./end/end.h",
-// CHECK-NEXT:         "[[PREFIX]]/./module.modulemap"
+// CHECK-NEXT:         "[[PREFIX]]/Y.h",
+// CHECK-NEXT:         "[[PREFIX]]/begin/begin.h",
+// CHECK-NEXT:         "[[PREFIX]]/end/end.h",
+// CHECK-NEXT:         "[[PREFIX]]/module.modulemap"
 // CHECK-NEXT:       ],
 // CHECK-NEXT:       "name": "Y"
 // CHECK-NEXT:     }