[CGData] LLD for MachO

lld/MachO/Config.h

@@ -210,6 +210,7 @@ struct Configuration {
   std::vector<SectionAlign> sectionAlignments;
   std::vector<SegmentProtection> segmentProtections;
   bool ltoDebugPassManager = false;
+  llvm::StringRef codegenDataGeneratePath;
   bool csProfileGenerate = false;
   llvm::StringRef csProfilePath;
   bool pgoWarnMismatch;

lld/MachO/Driver.cpp

@@ -36,6 +36,7 @@
 #include "llvm/ADT/StringRef.h"
 #include "llvm/BinaryFormat/MachO.h"
 #include "llvm/BinaryFormat/Magic.h"
+#include "llvm/CGData/CodeGenDataWriter.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Object/Archive.h"
@@ -1322,6 +1323,38 @@ static void gatherInputSections() {
   }
 }
 
+static void codegenDataGenerate() {
+  TimeTraceScope timeScope("Generating codegen data");
+
+  OutlinedHashTreeRecord globalOutlineRecord;
+  for (ConcatInputSection *isec : inputSections) {
+    if (isec->getSegName() == segment_names::data &&
+        isec->getName() == section_names::outlinedHashTree) {
+      // Read outlined hash tree from each section
+      OutlinedHashTreeRecord localOutlineRecord;
+      auto *data = isec->data.data();
+      localOutlineRecord.deserialize(data);
+
+      // Merge it to the global hash tree.
+      globalOutlineRecord.merge(localOutlineRecord);
+    }
+  }
+
+  CodeGenDataWriter Writer;
+  if (!globalOutlineRecord.empty())
+    Writer.addRecord(globalOutlineRecord);
+
+  std::error_code EC;
+  auto fileName = config->codegenDataGeneratePath;
+  assert(!fileName.empty());
+  raw_fd_ostream Output(fileName, EC, sys::fs::OF_None);
+  if (EC)
+    error("fail to create raw_fd_ostream");
+
+  if (auto E = Writer.write(Output))
+    error("fail to write CGData");
+}
+
 static void foldIdenticalLiterals() {
   TimeTraceScope timeScope("Fold identical literals");
   // We always create a cStringSection, regardless of whether dedupLiterals is
@@ -1759,6 +1792,8 @@ bool link(ArrayRef<const char *> argsArr, llvm::raw_ostream &stdoutOS,
     config->ignoreAutoLinkOptions.insert(arg->getValue());
   config->strictAutoLink = args.hasArg(OPT_strict_auto_link);
   config->ltoDebugPassManager = args.hasArg(OPT_lto_debug_pass_manager);
+  config->codegenDataGeneratePath =
+      args.getLastArgValue(OPT_codegen_data_generate_path);
   config->csProfileGenerate = args.hasArg(OPT_cs_profile_generate);
   config->csProfilePath = args.getLastArgValue(OPT_cs_profile_path);
   config->pgoWarnMismatch =
@@ -2103,6 +2138,10 @@ bool link(ArrayRef<const char *> argsArr, llvm::raw_ostream &stdoutOS,
     }
 
     gatherInputSections();
+
+    if (!config->codegenDataGeneratePath.empty())
+      codegenDataGenerate();
+
     if (config->callGraphProfileSort)
       priorityBuilder.extractCallGraphProfile();
 

lld/MachO/InputSection.h

@@ -354,6 +354,7 @@ constexpr const char objcMethname[] = "__objc_methname";
 constexpr const char objcNonLazyCatList[] = "__objc_nlcatlist";
 constexpr const char objcNonLazyClassList[] = "__objc_nlclslist";
 constexpr const char objcProtoList[] = "__objc_protolist";
+constexpr const char outlinedHashTree[] = "__llvm_outline";
 constexpr const char pageZero[] = "__pagezero";
 constexpr const char pointers[] = "__pointers";
 constexpr const char rebase[] = "__rebase";

lld/MachO/Options.td

@@ -162,6 +162,8 @@ def no_objc_category_merging : Flag<["-"], "no_objc_category_merging">,
     Group<grp_lld>;
 def lto_debug_pass_manager: Flag<["--"], "lto-debug-pass-manager">,
     HelpText<"Debug new pass manager">, Group<grp_lld>;
+def codegen_data_generate_path : Joined<["--"], "codegen-data-generate-path=">,
+    HelpText<"Codegen data file path">, Group<grp_lld>;
 def cs_profile_generate: Flag<["--"], "cs-profile-generate">,
     HelpText<"Perform context sensitive PGO instrumentation">, Group<grp_lld>;
 def cs_profile_path: Joined<["--"], "cs-profile-path=">,

lld/test/MachO/cgdata-generate.s

@@ -0,0 +1,94 @@
+# UNSUPPORTED: system-windows
+# REQUIRES: aarch64
+
+# RUN: rm -rf %t; split-file %s %t
+
+# Synthesize raw cgdata without the header (24 byte) from the indexed cgdata.
+# RUN: llvm-cgdata --convert --format binary %t/raw-1.cgtext -o %t/raw-1.cgdata
+# RUN: od -t x1 -j 24 -An %t/raw-1.cgdata | tr -d '\n\r\t' | sed 's/ \+/ /g; s/^ *//; s/ *$//; s/ /,0x/g; s/^/0x/' > %t/raw-1-bytes.txt
+# RUN: sed "s/<RAW_1_BYTES>/$(cat %t/raw-1-bytes.txt)/g" %t/merge-1-template.s > %t/merge-1.s
+# RUN: llvm-cgdata --convert --format binary %t/raw-2.cgtext -o %t/raw-2.cgdata
+# RUN: od -t x1 -j 24 -An %t/raw-2.cgdata | tr -d '\n\r\t' | sed 's/ \+/ /g; s/^ *//; s/ *$//; s/ /,0x/g; s/^/0x/' > %t/raw-2-bytes.txt
+# RUN: sed "s/<RAW_2_BYTES>/$(cat %t/raw-2-bytes.txt)/g" %t/merge-2-template.s > %t/merge-2.s
+
+# RUN: llvm-mc -filetype obj -triple arm64-apple-darwin %t/merge-1.s -o %t/merge-1.o
+# RUN: llvm-mc -filetype obj -triple arm64-apple-darwin %t/merge-2.s -o %t/merge-2.o
+# RUN: llvm-mc -filetype obj -triple arm64-apple-darwin %t/main.s -o %t/main.o
+
+# This checks if the codegen data from the linker is identical to the merged codegen data
+# from each object file, which is obtained using the llvm-cgdata tool.
+# RUN: %no-arg-lld -dylib -arch arm64 -platform_version ios 14.0 15.0 -o %t/out \
+# RUN: %t/merge-1.o %t/merge-2.o %t/main.o --codegen-data-generate-path=%t/out-cgdata
+# RUN: llvm-cgdata --merge %t/merge-1.o %t/merge-2.o %t/main.o -o %t/merge-cgdata
+# RUN: diff %t/out-cgdata %t/merge-cgdata
+
+# Merge order doesn't matter. `main.o` is dropped due to missing __llvm_outline.
+# RUN: llvm-cgdata --merge %t/merge-2.o %t/merge-1.o -o %t/merge-cgdata-shuffle
+# RUN: diff %t/out-cgdata %t/merge-cgdata-shuffle
+
+# We can also generate the merged codegen data from the executable that is not dead-stripped.
+# RUN: llvm-objdump -h %t/out| FileCheck %s
+CHECK: __llvm_outline
+# RUN: llvm-cgdata --merge %t/out -o %t/merge-cgdata-exe
+# RUN: diff %t/merge-cgdata-exe %t/merge-cgdata
+
+# Dead-strip will remove __llvm_outline sections from the final executable.
+# But the codeden data is still correctly produced from the linker.
+# RUN: %no-arg-lld -dylib -arch arm64 -platform_version ios 14.0 15.0 -o %t/out-strip \
+# RUN: %t/merge-1.o %t/merge-2.o %t/main.o -dead_strip --codegen-data-generate-path=%t/out-cgdata-strip
+# RUN: llvm-cgdata --merge %t/merge-1.o %t/merge-2.o %t/main.o -o %t/merge-cgdata-strip
+# RUN: diff %t/out-cgdata-strip %t/merge-cgdata-strip
+# RUN: diff %t/out-cgdata-strip %t/merge-cgdata
+
+# Ensure no __llvm_outline section remains in the executable.
+# RUN: llvm-objdump -h %t/out-strip | FileCheck %s --check-prefix=STRIP
+STRIP-NOT: __llvm_outline
+
+#--- raw-1.cgtext
+:outlined_hash_tree
+0:
+  Hash:            0x0
+  Terminals:       0
+  SuccessorIds:    [ 1 ]
+1:
+  Hash:            0x1
+  Terminals:       0
+  SuccessorIds:    [ 2 ]
+2:
+  Hash:            0x2
+  Terminals:       4
+  SuccessorIds:    [  ]
+...
+
+#--- merge-1-template.s
+.section __DATA,__llvm_outline
+_data:
+.byte <RAW_1_BYTES>
+
+#--- raw-2.cgtext
+:outlined_hash_tree
+0:
+  Hash:            0x0
+  Terminals:       0
+  SuccessorIds:    [ 1 ]
+1:
+  Hash:            0x1
+  Terminals:       0
+  SuccessorIds:    [ 2 ]
+2:
+  Hash:            0x3
+  Terminals:       5
+  SuccessorIds:    [  ]
+...
+
+#--- merge-2-template.s
+.section __DATA,__llvm_outline
+_data:
+.byte <RAW_2_BYTES>
+
+#--- main.s
+.globl _main
+
+.text
+_main:
+  ret