[CodeView] Add full repro to LF_BUILDINFO record

This patch adds some missing information to the LF_BUILDINFO which allows for rebuilding an .OBJ without any external dependency but the .OBJ itself (other than the compiler executable).

Some tools need this information to reproduce a build without any knowledge of the build system. The LF_BUILDINFO therefore stores a full path to the compiler, the PWD (which is the CWD at program startup), a relative or absolute path to the TU, and the full CC1 command line. The command line needs to be freestanding (not depend on any environment variable). In the same way, MSVC doesn't store the provided command-line, but an expanded version (somehow their equivalent of CC1) which is also freestanding.

For more information see PR36198 and D43002.

Differential Revision: https://reviews.llvm.org/D80833

Author: aganea

clang/test/CodeGen/debug-info-codeview-buildinfo.c

@@ -0,0 +1,24 @@
+// RUN: %clang_cl /c /Z7 /Fo%t.obj -- %s
+// RUN: llvm-pdbutil dump --types %t.obj | FileCheck %s
+// RUN: %clang_cl /c /Z7 %s /Fo%t.obj -fdebug-compilation-dir .
+// RUN: llvm-pdbutil dump --types %t.obj | FileCheck %s --check-prefix RELATIVE
+
+int main() { return 42; }
+
+// CHECK:                       Types (.debug$T)
+// CHECK: ============================================================
+// CHECK: 0x[[PWD:.+]] | LF_STRING_ID [size = {{.+}}] ID: <no type>, String: [[PWDVAL:.+]]
+// CHECK: 0x[[FILEPATH:.+]] | LF_STRING_ID [size = {{.+}}] ID: <no type>, String: [[FILEPATHVAL:.+[\\/]debug-info-codeview-buildinfo.c]]
+// CHECK: 0x[[TOOL:.+]] | LF_STRING_ID [size = {{.+}}] ID: <no type>, String: [[TOOLVAL:.+[\\/]clang.*]]
+// CHECK: 0x[[CMDLINE:.+]] | LF_STRING_ID [size = {{.+}}] ID: <no type>, String: "-cc1
+// CHECK: 0x{{.+}} | LF_BUILDINFO [size = {{.+}}]
+// CHECK:          0x[[PWD]]: `[[PWDVAL]]`
+// CHECK:          0x[[TOOL]]: `[[TOOLVAL]]`
+// CHECK:          0x[[FILEPATH]]: `[[FILEPATHVAL]]`
+// CHECK:          <no type>: ``
+// CHECK:          0x[[CMDLINE]]: `"-cc1
+
+// RELATIVE:                       Types (.debug$T)
+// RELATIVE: ============================================================
+// RELATIVE: 0x{{.+}} | LF_BUILDINFO [size = {{.+}}]
+// RELATIVE:          0x{{.+}}: `.`

lld/COFF/PDB.cpp

@@ -250,6 +250,72 @@ static void addTypeInfo(pdb::TpiStreamBuilder &tpiBuilder,
   });
 }
 
+// LF_BUILDINFO records might contain relative paths, and we want to make them
+// absolute. We do this remapping only after the type records were merged,
+// because the full types graph isn't known during merging. In addition, we plan
+// to multi-thread the type merging, and the change below needs to be done
+// atomically, single-threaded.
+
+// A complication could arise when a LF_STRING_ID record already exists with the
+// same content as the new absolutized path. In that case, we simply redirect
+// LF_BUILDINFO's CurrentDirectory index to reference the existing LF_STRING_ID
+// record.
+
+static void remapBuildInfo(TypeCollection &idTable) {
+  SimpleTypeSerializer s;
+  idTable.ForEachRecord([&](TypeIndex ti, const CVType &type) {
+    if (type.kind() != LF_BUILDINFO)
+      return;
+    BuildInfoRecord bi;
+    cantFail(TypeDeserializer::deserializeAs(const_cast<CVType &>(type), bi));
+
+    auto makeAbsoluteRecord =
+        [&](BuildInfoRecord::BuildInfoArg recordType) -> Optional<TypeIndex> {
+      TypeIndex recordTi = bi.getArgs()[recordType];
+      if (recordTi.isNoneType())
+        return None;
+      CVType recordRef = idTable.getType(recordTi);
+
+      StringIdRecord record;
+      cantFail(TypeDeserializer::deserializeAs(recordRef, record));
+
+      SmallString<128> abolutizedPath(record.getString());
+      pdbMakeAbsolute(abolutizedPath);
+
+      if (abolutizedPath == record.getString())
+        return None; // The path is already absolute.
+
+      record.String = abolutizedPath;
+      ArrayRef<uint8_t> recordData = s.serialize(record);
+
+      // Replace the previous LF_STRING_ID record
+      if (!idTable.replaceType(recordTi, CVType(recordData),
+                               /*Stabilize=*/true))
+        return recordTi;
+      return None;
+    };
+
+    Optional<TypeIndex> curDirTI =
+        makeAbsoluteRecord(BuildInfoRecord::CurrentDirectory);
+    Optional<TypeIndex> buildToolTI =
+        makeAbsoluteRecord(BuildInfoRecord::BuildTool);
+
+    if (curDirTI || buildToolTI) {
+      // This new record is already there. We don't want duplicates, so
+      // re-serialize the BuildInfoRecord instead.
+      if (curDirTI)
+        bi.ArgIndices[BuildInfoRecord::CurrentDirectory] = *curDirTI;
+      if (buildToolTI)
+        bi.ArgIndices[BuildInfoRecord::BuildTool] = *buildToolTI;
+
+      ArrayRef<uint8_t> biData = s.serialize(bi);
+      bool r = idTable.replaceType(ti, CVType(biData), /*Stabilize=*/true);
+      assert(r && "Didn't expect two build records pointing to the same OBJ!");
+      (void)r;
+    }
+  });
+}
+
 static bool remapTypeIndex(TypeIndex &ti, ArrayRef<TypeIndex> typeIndexMap) {
   if (ti.isSimple())
     return true;
@@ -988,6 +1054,9 @@ void PDBLinker::addObjectsToPDB() {
   builder.getStringTableBuilder().setStrings(pdbStrTab);
   t1.stop();
 
+  // Remap the contents of the LF_BUILDINFO record.
+  remapBuildInfo(tMerger.getIDTable());
+
   // Construct TPI and IPI stream contents.
   ScopedTimer t2(tpiStreamLayoutTimer);
   addTypeInfo(builder.getTpiBuilder(), tMerger.getTypeTable());