[clang][modules] Stop eagerly reading files with diagnostic pragmas

clang/include/clang/Serialization/ASTBitCodes.h

@@ -41,7 +41,7 @@ namespace serialization {
 /// Version 4 of AST files also requires that the version control branch and
 /// revision match exactly, since there is no backward compatibility of
 /// AST files at this time.
-const unsigned VERSION_MAJOR = 29;
+const unsigned VERSION_MAJOR = 30;
 
 /// AST file minor version number supported by this version of
 /// Clang.

clang/lib/Serialization/ASTReader.cpp

@@ -6604,17 +6604,15 @@ void ASTReader::ReadPragmaDiagnosticMappings(DiagnosticsEngine &Diag) {
     while (NumLocations--) {
       assert(Idx < Record.size() &&
              "Invalid data, missing pragma diagnostic states");
-      SourceLocation Loc = ReadSourceLocation(F, Record[Idx++]);
-      auto IDAndOffset = SourceMgr.getDecomposedLoc(Loc);
-      assert(IDAndOffset.first.isValid() && "invalid FileID for transition");
-      assert(IDAndOffset.second == 0 && "not a start location for a FileID");
+      FileID FID = ReadFileID(F, Record, Idx);
+      assert(FID.isValid() && "invalid FileID for transition");
       unsigned Transitions = Record[Idx++];
 
       // Note that we don't need to set up Parent/ParentOffset here, because
       // we won't be changing the diagnostic state within imported FileIDs
       // (other than perhaps appending to the main source file, which has no
       // parent).
-      auto &F = Diag.DiagStatesByLoc.Files[IDAndOffset.first];
+      auto &F = Diag.DiagStatesByLoc.Files[FID];
       F.StateTransitions.reserve(F.StateTransitions.size() + Transitions);
       for (unsigned I = 0; I != Transitions; ++I) {
         unsigned Offset = Record[Idx++];

clang/lib/Serialization/ASTWriter.cpp

@@ -3131,9 +3131,7 @@ void ASTWriter::WritePragmaDiagnosticMappings(const DiagnosticsEngine &Diag,
       continue;
     ++NumLocations;
 
-    SourceLocation Loc = Diag.SourceMgr->getComposedLoc(FileIDAndFile.first, 0);
-    assert(!Loc.isInvalid() && "start loc for valid FileID is invalid");
-    AddSourceLocation(Loc, Record);
+    AddFileID(FileIDAndFile.first, Record);
 
     Record.push_back(FileIDAndFile.second.StateTransitions.size());
     for (auto &StatePoint : FileIDAndFile.second.StateTransitions) {

clang/test/Modules/home-is-cwd-search-paths.c

@@ -0,0 +1,34 @@
+// This test demonstrates how -fmodule-map-file-home-is-cwd with -fmodules-embed-all-files
+// extend the importer search paths by relying on the side effects of pragma diagnostic
+// mappings deserialization.
+
+// RUN: rm -rf %t
+// RUN: split-file %s %t
+
+//--- dir1/a.modulemap
+module a { header "a.h" }
+//--- dir1/a.h
+#include "search.h"
+// The first compilation is configured such that -I search does contain the search.h header.
+//--- dir1/search/search.h
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wparentheses"
+#pragma clang diagnostic pop
+// RUN: cd %t/dir1 && %clang_cc1 -fmodules -I search \
+// RUN:   -emit-module -fmodule-name=a a.modulemap -o %t/a.pcm \
+// RUN:   -fmodules-embed-all-files -fmodule-map-file-home-is-cwd
+
+//--- dir2/b.modulemap
+module b { header "b.h" }
+//--- dir2/b.h
+#include "search.h" // expected-error{{'search.h' file not found}}
+// The second compilation is configured such that -I search is an empty directory.
+// However, since b.pcm simply embeds the headers as "search/search.h", this compilation
+// ends up seeing it too. This relies solely on ASTReader::ReadPragmaDiagnosticMappings()
+// eagerly reading the corresponding INPUT_FILE record before header search happens.
+// Removing the eager deserialization makes this header invisible and so does removing
+// the pragma directives.
+// RUN: mkdir %t/dir2/search
+// RUN: cd %t/dir2 && %clang_cc1 -fmodules -I search \
+// RUN:   -emit-module -fmodule-name=b b.modulemap -o %t/b.pcm \
+// RUN:   -fmodule-file=%t/a.pcm -verify