[llvm] [CGData] llvm-cgdata (PR #89884)

[Ellis Hoag via llvm-commits]

================
@@ -0,0 +1,174 @@
+//===- CodeGenDataReader.cpp ----------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains support for reading codegen data.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGenData/CodeGenDataReader.h"
+#include "llvm/CodeGenData/OutlinedHashTreeRecord.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+#define DEBUG_TYPE "cg-data-reader"
+
+using namespace llvm;
+
+namespace llvm {
+
+static Expected<std::unique_ptr<MemoryBuffer>>
+setupMemoryBuffer(const Twine &Filename, vfs::FileSystem &FS) {
+  auto BufferOrErr = Filename.str() == "-" ? MemoryBuffer::getSTDIN()
+                                           : FS.getBufferForFile(Filename);
+  if (std::error_code EC = BufferOrErr.getError())
+    return errorCodeToError(EC);
+  return std::move(BufferOrErr.get());
+}
+
+Error CodeGenDataReader::mergeFromObjectFile(
+    const object::ObjectFile *Obj,
+    OutlinedHashTreeRecord &GlobalOutlineRecord) {
+  Triple TT = Obj->makeTriple();
+  auto CGOutLineName =
+      getCodeGenDataSectionName(CG_outline, TT.getObjectFormat(), false);
+
+  for (auto &Section : Obj->sections()) {
+    Expected<StringRef> NameOrErr = Section.getName();
+    if (!NameOrErr)
+      return NameOrErr.takeError();
+    Expected<StringRef> ContentsOrErr = Section.getContents();
+    if (!ContentsOrErr)
+      return ContentsOrErr.takeError();
+    auto *Data = reinterpret_cast<const unsigned char *>(ContentsOrErr->data());
+    auto *EndData = Data + ContentsOrErr->size();
+
+    if (*NameOrErr == CGOutLineName) {
+      // In case dealing with an executable that has concatenaed cgdata,
+      // we want to merge them into a single cgdata.
+      // Although it's not a typical workflow, we support this scenario.
+      while (Data != EndData) {
+        OutlinedHashTreeRecord LocalOutlineRecord;
+        LocalOutlineRecord.deserialize(Data);
+        GlobalOutlineRecord.merge(LocalOutlineRecord);
+      }
+    }
+    // TODO: Add support for other cgdata sections.
+  }
+
+  return Error::success();
+}
+
+Error IndexedCodeGenDataReader::read() {
+  using namespace support;
+
+  // The smallest header with the version 1 is 24 bytes
+  const unsigned MinHeaderSize = 24;
+  if (DataBuffer->getBufferSize() < MinHeaderSize)
+    return error(cgdata_error::bad_header);
+
+  auto *Start =
+      reinterpret_cast<const unsigned char *>(DataBuffer->getBufferStart());
+  auto *End =
+      reinterpret_cast<const unsigned char *>(DataBuffer->getBufferEnd());
+  auto HeaderOr = IndexedCGData::Header::readFromBuffer(Start);
+  if (!HeaderOr)
+    return HeaderOr.takeError();
+  Header = HeaderOr.get();
----------------
ellishg wrote:

You could also refactor some checks of `Expected` above to use `moveInto()`, but I'm not sure if it will help readability. I'll leave it up to you.

https://github.com/llvm/llvm-project/pull/89884