[Lldb-commits] [clang] [lldb] [llvm] [BOLT][DWARF] Fix handling of DWARF5 DWP (PR #72729)

Alexander Yermolovich via lldb-commits lldb-commits at lists.llvm.org
Fri Nov 17 16:45:36 PST 2023


https://github.com/ayermolo created https://github.com/llvm/llvm-project/pull/72729

Fixed handling of DWP as input. Before BOLT crashed. Now it will write out
correct CU, and all the TUs. Potential future improvement is to scan all the TUs
used in this CU, and only include those.

>From 80adaca72cf869f8735d7a3684a8d64bc438e5b6 Mon Sep 17 00:00:00 2001
From: Amir Ayupov <aaupov at meta.com>
Date: Tue, 1 Jun 2021 11:37:41 -0700
Subject: [PATCH 1/3] Rebase: [Facebook] Add clang driver options to test debug
 info and BOLT

Summary:
This is an essential piece of infrastructure for us to be
continuously testing debug info with BOLT. We can't only make changes
to a test repo because we need to change debuginfo tests to call BOLT,
hence, this diff needs to sit in our opensource repo. But when upstreaming
to LLVM, this should be kept BOLT-only outside of LLVM. When upstreaming,
we need to git diff and check all folders that are being modified by our
commits and discard this one (and leave as an internal diff).

To test BOLT in debuginfo tests, configure it with -DLLVM_TEST_BOLT=ON.
Then run check-lldb and check-debuginfo.

Manual rebase conflict history:
https://phabricator.intern.facebook.com/D29205224
https://phabricator.intern.facebook.com/D29564078
https://phabricator.intern.facebook.com/D33289118
https://phabricator.intern.facebook.com/D34957174
https://phabricator.intern.facebook.com/D35317341

Test Plan:
tested locally
Configured with:
-DLLVM_ENABLE_PROJECTS="clang;lld;lldb;compiler-rt;bolt;debuginfo-tests"
-DLLVM_TEST_BOLT=ON
Ran test suite with:
ninja check-debuginfo
ninja check-lldb

Reviewers: maks, #llvm-bolt

Reviewed By: maks

Subscribers: ayermolo, phabricatorlinter

Differential Revision: https://phabricator.intern.facebook.com/D46256657

Tasks: T92898286
---
 clang/include/clang/Driver/Options.td  |  4 ++++
 clang/lib/Driver/ToolChains/Gnu.cpp    | 29 ++++++++++++++++++++++++++
 cross-project-tests/lit.cfg.py         | 14 ++++++++++++-
 cross-project-tests/lit.site.cfg.py.in |  4 ++++
 lldb/test/API/lit.cfg.py               |  5 +++++
 lldb/test/API/lit.site.cfg.py.in       |  8 +++++++
 lldb/test/Shell/helper/toolchain.py    |  5 +++++
 lldb/test/Shell/lit.site.cfg.py.in     |  9 ++++++++
 llvm/CMakeLists.txt                    |  4 ++++
 9 files changed, 81 insertions(+), 1 deletion(-)

diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 811550416110b3d..31ad86bc098ec63 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -5178,6 +5178,10 @@ def pg : Flag<["-"], "pg">, HelpText<"Enable mcount instrumentation">,
   MarshallingInfoFlag<CodeGenOpts<"InstrumentForProfiling">>;
 def pipe : Flag<["-", "--"], "pipe">,
   HelpText<"Use pipes between commands, when possible">;
+// Facebook T92898286
+def post_link_optimize : Flag<["--"], "post-link-optimize">,
+  HelpText<"Apply post-link optimizations using BOLT">;
+// End Facebook T92898286
 def prebind__all__twolevel__modules : Flag<["-"], "prebind_all_twolevel_modules">;
 def prebind : Flag<["-"], "prebind">;
 def preload : Flag<["-"], "preload">;
diff --git a/clang/lib/Driver/ToolChains/Gnu.cpp b/clang/lib/Driver/ToolChains/Gnu.cpp
index ba95ce9c5a28153..bf55d90f6dc704b 100644
--- a/clang/lib/Driver/ToolChains/Gnu.cpp
+++ b/clang/lib/Driver/ToolChains/Gnu.cpp
@@ -666,12 +666,41 @@ void tools::gnutools::Linker::ConstructJob(Compilation &C, const JobAction &JA,
     }
   }
 
+  // Facebook T92898286
+  if (Args.hasArg(options::OPT_post_link_optimize))
+    CmdArgs.push_back("-q");
+  // End Facebook T92898286
+
   Args.AddAllArgs(CmdArgs, options::OPT_T);
 
   const char *Exec = Args.MakeArgString(ToolChain.GetLinkerPath());
   C.addCommand(std::make_unique<Command>(JA, *this,
                                          ResponseFileSupport::AtFileCurCP(),
                                          Exec, CmdArgs, Inputs, Output));
+  // Facebook T92898286
+  if (!Args.hasArg(options::OPT_post_link_optimize) || !Output.isFilename())
+    return;
+
+  const char *MvExec = Args.MakeArgString(ToolChain.GetProgramPath("mv"));
+  ArgStringList MoveCmdArgs;
+  MoveCmdArgs.push_back(Output.getFilename());
+  const char *PreBoltBin =
+      Args.MakeArgString(Twine(Output.getFilename()) + ".pre-bolt");
+  MoveCmdArgs.push_back(PreBoltBin);
+  C.addCommand(std::make_unique<Command>(JA, *this, ResponseFileSupport::None(),
+                                         MvExec, MoveCmdArgs, std::nullopt));
+
+  ArgStringList BoltCmdArgs;
+  const char *BoltExec =
+      Args.MakeArgString(ToolChain.GetProgramPath("llvm-bolt"));
+  BoltCmdArgs.push_back(PreBoltBin);
+  BoltCmdArgs.push_back("-reorder-blocks=reverse");
+  BoltCmdArgs.push_back("-update-debug-sections");
+  BoltCmdArgs.push_back("-o");
+  BoltCmdArgs.push_back(Output.getFilename());
+  C.addCommand(std::make_unique<Command>(JA, *this, ResponseFileSupport::None(),
+                                         BoltExec, BoltCmdArgs, std::nullopt));
+  // End Facebook T92898286
 }
 
 void tools::gnutools::Assembler::ConstructJob(Compilation &C,
diff --git a/cross-project-tests/lit.cfg.py b/cross-project-tests/lit.cfg.py
index 774c4eaf4d976b2..619634578dfe609 100644
--- a/cross-project-tests/lit.cfg.py
+++ b/cross-project-tests/lit.cfg.py
@@ -84,7 +84,13 @@ def get_required_attr(config, attr_name):
 # use_clang() and use_lld() respectively, so set them to "", if needed.
 if not hasattr(config, "clang_src_dir"):
     config.clang_src_dir = ""
-llvm_config.use_clang(required=("clang" in config.llvm_enabled_projects))
+# Facebook T92898286
+should_test_bolt = get_required_attr(config, "llvm_test_bolt")
+if should_test_bolt:
+    llvm_config.use_clang(required=("clang" in config.llvm_enabled_projects), additional_flags=["--post-link-optimize"])
+else:
+    llvm_config.use_clang(required=("clang" in config.llvm_enabled_projects))
+# End Facebook T92898286
 
 if not hasattr(config, "lld_src_dir"):
     config.lld_src_dir = ""
@@ -293,3 +299,9 @@ def get_clang_default_dwarf_version_string(triple):
 # Allow 'REQUIRES: XXX-registered-target' in tests.
 for arch in config.targets_to_build:
     config.available_features.add(arch.lower() + "-registered-target")
+
+# Facebook T92898286
+# Ensure the user's PYTHONPATH is included.
+if "PYTHONPATH" in os.environ:
+    config.environment["PYTHONPATH"] = os.environ["PYTHONPATH"]
+# End Facebook T92898286
diff --git a/cross-project-tests/lit.site.cfg.py.in b/cross-project-tests/lit.site.cfg.py.in
index 39458dfc79afd2a..2d53cd377f0330d 100644
--- a/cross-project-tests/lit.site.cfg.py.in
+++ b/cross-project-tests/lit.site.cfg.py.in
@@ -21,6 +21,10 @@ config.mlir_src_root = "@MLIR_SOURCE_DIR@"
 
 config.llvm_use_sanitizer = "@LLVM_USE_SANITIZER@"
 
+# Facebook T92898286
+config.llvm_test_bolt = lit.util.pythonize_bool("@LLVM_TEST_BOLT@")
+# End Facebook T92898286
+
 import lit.llvm
 lit.llvm.initialize(lit_config, config)
 
diff --git a/lldb/test/API/lit.cfg.py b/lldb/test/API/lit.cfg.py
index 8b35e8b2a217cf7..3c0c6baa6f55d8a 100644
--- a/lldb/test/API/lit.cfg.py
+++ b/lldb/test/API/lit.cfg.py
@@ -244,6 +244,11 @@ def delete_module_cache(path):
 if is_configured("lldb_framework_dir"):
     dotest_cmd += ["--framework", config.lldb_framework_dir]
 
+# Facebook T92898286
+if is_configured("llvm_test_bolt"):
+    dotest_cmd += ["-E", '"--post-link-optimize"']
+# End Facebook T92898286
+
 if (
     "lldb-repro-capture" in config.available_features
     or "lldb-repro-replay" in config.available_features
diff --git a/lldb/test/API/lit.site.cfg.py.in b/lldb/test/API/lit.site.cfg.py.in
index 053331dc4881f77..1da91d8fb5508ce 100644
--- a/lldb/test/API/lit.site.cfg.py.in
+++ b/lldb/test/API/lit.site.cfg.py.in
@@ -1,5 +1,9 @@
 @LIT_SITE_CFG_IN_HEADER@
 
+#Facebook T92898286
+import lit.util
+#End Facebook T92898286
+
 config.llvm_src_root = "@LLVM_SOURCE_DIR@"
 config.llvm_obj_root = "@LLVM_BINARY_DIR@"
 config.llvm_tools_dir = lit_config.substitute("@LLVM_TOOLS_DIR@")
@@ -39,6 +43,10 @@ config.libcxx_include_target_dir = "@LIBCXX_GENERATED_INCLUDE_TARGET_DIR@"
 config.lldb_module_cache = os.path.join("@LLDB_TEST_MODULE_CACHE_LLDB@", "lldb-api")
 config.clang_module_cache = os.path.join("@LLDB_TEST_MODULE_CACHE_CLANG@", "lldb-api")
 
+# Facebook T92898286
+config.llvm_test_bolt = lit.util.pythonize_bool("@LLVM_TEST_BOLT@")
+# End Facebook T92898286
+
 # Plugins
 lldb_build_intel_pt = '@LLDB_BUILD_INTEL_PT@'
 if lldb_build_intel_pt == '1':
diff --git a/lldb/test/Shell/helper/toolchain.py b/lldb/test/Shell/helper/toolchain.py
index 255955fc70d8c41..7b7be06643166df 100644
--- a/lldb/test/Shell/helper/toolchain.py
+++ b/lldb/test/Shell/helper/toolchain.py
@@ -165,6 +165,11 @@ def use_support_substitutions(config):
     if config.cmake_sysroot:
         host_flags += ["--sysroot={}".format(config.cmake_sysroot)]
 
+    # Facebook T92898286
+    if config.llvm_test_bolt:
+        host_flags += ["--post-link-optimize"]
+    # End Facebook T92898286
+
     host_flags = " ".join(host_flags)
     config.substitutions.append(("%clang_host", "%clang " + host_flags))
     config.substitutions.append(("%clangxx_host", "%clangxx " + host_flags))
diff --git a/lldb/test/Shell/lit.site.cfg.py.in b/lldb/test/Shell/lit.site.cfg.py.in
index 736dfc335732b5a..3b4d99aa076a455 100644
--- a/lldb/test/Shell/lit.site.cfg.py.in
+++ b/lldb/test/Shell/lit.site.cfg.py.in
@@ -1,5 +1,10 @@
 @LIT_SITE_CFG_IN_HEADER@
 
+#Facebook T92898286
+import lit.util
+#End Facebook T92898286
+
+
 config.llvm_src_root = "@LLVM_SOURCE_DIR@"
 config.llvm_obj_root = "@LLVM_BINARY_DIR@"
 config.llvm_tools_dir = lit_config.substitute("@LLVM_TOOLS_DIR@")
@@ -30,6 +35,10 @@ config.lldb_system_debugserver = @LLDB_USE_SYSTEM_DEBUGSERVER@
 config.lldb_module_cache = os.path.join("@LLDB_TEST_MODULE_CACHE_LLDB@", "lldb-shell")
 config.clang_module_cache = os.path.join("@LLDB_TEST_MODULE_CACHE_CLANG@", "lldb-shell")
 
+# Facebook T92898286
+config.llvm_test_bolt = lit.util.pythonize_bool("@LLVM_TEST_BOLT@")
+# End Facebook T92898286
+
 import lit.llvm
 lit.llvm.initialize(lit_config, config)
 
diff --git a/llvm/CMakeLists.txt b/llvm/CMakeLists.txt
index 1c983165b2ef003..cba26c7a617fa4a 100644
--- a/llvm/CMakeLists.txt
+++ b/llvm/CMakeLists.txt
@@ -685,6 +685,10 @@ set(LLVM_LIB_FUZZING_ENGINE "" CACHE PATH
 option(LLVM_USE_SPLIT_DWARF
   "Use -gsplit-dwarf when compiling llvm and --gdb-index when linking." OFF)
 
+# Facebook T92898286
+option(LLVM_TEST_BOLT "Enable BOLT testing in non-BOLT tests that use clang" OFF)
+# End Facebook T92898286
+
 # Define an option controlling whether we should build for 32-bit on 64-bit
 # platforms, where supported.
 if( CMAKE_SIZEOF_VOID_P EQUAL 8 AND NOT (WIN32 OR ${CMAKE_SYSTEM_NAME} MATCHES "AIX"))

>From 3c7a1e685be4ec0c1c3c3b59751291cc2c5af3a9 Mon Sep 17 00:00:00 2001
From: Rafael Auler <rafaelauler at fb.com>
Date: Thu, 5 Aug 2021 14:17:07 -0700
Subject: [PATCH 2/3] Rebase: [Facebook] [MC] Introduce NeverAlign fragment
 type

Summary:
Introduce NeverAlign fragment type.

The intended usage of this fragment is to insert it before a pair of
macro-op fusion eligible instructions. NeverAlign fragment ensures that
the next fragment (first instruction in the pair) does not end at a
given alignment boundary by emitting a minimal size nop if necessary.

In effect, it ensures that a pair of macro-fusible instructions is not
split by a given alignment boundary, which is a precondition for
macro-op fusion in modern Intel Cores (64B = cache line size, see Intel
Architecture Optimization Reference Manual, 2.3.2.1 Legacy Decode
Pipeline: Macro-Fusion).

This patch introduces functionality used by BOLT when emitting code with
MacroFusion alignment already in place.

The use case is different from BoundaryAlign and instruction bundling:
- BoundaryAlign can be extended to perform the desired alignment for the
first instruction in the macro-op fusion pair (D101817). However, this
approach has higher overhead due to reliance on relaxation as
BoundaryAlign requires in the general case - see
https://reviews.llvm.org/D97982#2710638.
- Instruction bundling: the intent of NeverAlign fragment is to prevent
the first instruction in a pair ending at a given alignment boundary, by
inserting at most one minimum size nop. It's OK if either instruction
crosses the cache line. Padding both instructions using bundles to not
cross the alignment boundary would result in excessive padding. There's
no straightforward way to request instruction bundling to avoid a given
end alignment for the first instruction in the bundle.

LLVM: https://reviews.llvm.org/D97982

Manual rebase conflict history:
https://phabricator.intern.facebook.com/D30142613

Test Plan: sandcastle

Reviewers: #llvm-bolt

Subscribers: phabricatorlinter

Differential Revision: https://phabricator.intern.facebook.com/D31361547
---
 bolt/lib/Core/BinaryEmitter.cpp               |   1 +
 llvm/include/llvm/MC/MCFragment.h             |  22 ++
 llvm/include/llvm/MC/MCObjectStreamer.h       |   2 +
 llvm/include/llvm/MC/MCStreamer.h             |   6 +
 llvm/lib/MC/MCAssembler.cpp                   | 118 ++++++----
 llvm/lib/MC/MCFragment.cpp                    |  12 +
 llvm/lib/MC/MCObjectStreamer.cpp              |   5 +
 llvm/lib/MC/MCStreamer.cpp                    |   2 +
 .../lib/Target/X86/AsmParser/X86AsmParser.cpp |  24 ++
 llvm/test/MC/X86/directive-avoid_end_align.s  | 208 ++++++++++++++++++
 10 files changed, 363 insertions(+), 37 deletions(-)
 create mode 100644 llvm/test/MC/X86/directive-avoid_end_align.s

diff --git a/bolt/lib/Core/BinaryEmitter.cpp b/bolt/lib/Core/BinaryEmitter.cpp
index fb1bf530c1974aa..82fbd8c0f67b215 100644
--- a/bolt/lib/Core/BinaryEmitter.cpp
+++ b/bolt/lib/Core/BinaryEmitter.cpp
@@ -482,6 +482,7 @@ void BinaryEmitter::emitFunctionBody(BinaryFunction &BF, FunctionFragment &FF,
         // This assumes the second instruction in the macro-op pair will get
         // assigned to its own MCRelaxableFragment. Since all JCC instructions
         // are relaxable, we should be safe.
+        Streamer.emitNeverAlignCodeAtEnd(/*Alignment to avoid=*/64, *BC.STI);
       }
 
       if (!EmitCodeOnly) {
diff --git a/llvm/include/llvm/MC/MCFragment.h b/llvm/include/llvm/MC/MCFragment.h
index efe44b0b6917e10..5f515399ad445a8 100644
--- a/llvm/include/llvm/MC/MCFragment.h
+++ b/llvm/include/llvm/MC/MCFragment.h
@@ -33,6 +33,7 @@ class MCFragment : public ilist_node_with_parent<MCFragment, MCSection> {
 public:
   enum FragmentType : uint8_t {
     FT_Align,
+    FT_NeverAlign,
     FT_Data,
     FT_CompactEncodedInst,
     FT_Fill,
@@ -344,6 +345,27 @@ class MCAlignFragment : public MCFragment {
   }
 };
 
+class MCNeverAlignFragment : public MCFragment {
+  /// The alignment the end of the next fragment should avoid.
+  unsigned Alignment;
+
+  /// When emitting Nops some subtargets have specific nop encodings.
+  const MCSubtargetInfo &STI;
+
+public:
+  MCNeverAlignFragment(unsigned Alignment, const MCSubtargetInfo &STI,
+                       MCSection *Sec = nullptr)
+      : MCFragment(FT_NeverAlign, false, Sec), Alignment(Alignment), STI(STI) {}
+
+  unsigned getAlignment() const { return Alignment; }
+
+  const MCSubtargetInfo &getSubtargetInfo() const { return STI; }
+
+  static bool classof(const MCFragment *F) {
+    return F->getKind() == MCFragment::FT_NeverAlign;
+  }
+};
+
 class MCFillFragment : public MCFragment {
   uint8_t ValueSize;
   /// Value to use for filling bytes.
diff --git a/llvm/include/llvm/MC/MCObjectStreamer.h b/llvm/include/llvm/MC/MCObjectStreamer.h
index 5e5b4b315017095..3c6fd9301647db7 100644
--- a/llvm/include/llvm/MC/MCObjectStreamer.h
+++ b/llvm/include/llvm/MC/MCObjectStreamer.h
@@ -157,6 +157,8 @@ class MCObjectStreamer : public MCStreamer {
                             unsigned MaxBytesToEmit = 0) override;
   void emitCodeAlignment(Align ByteAlignment, const MCSubtargetInfo *STI,
                          unsigned MaxBytesToEmit = 0) override;
+  void emitNeverAlignCodeAtEnd(unsigned ByteAlignment,
+                               const MCSubtargetInfo &STI) override;
   void emitValueToOffset(const MCExpr *Offset, unsigned char Value,
                          SMLoc Loc) override;
   void emitDwarfLocDirective(unsigned FileNo, unsigned Line, unsigned Column,
diff --git a/llvm/include/llvm/MC/MCStreamer.h b/llvm/include/llvm/MC/MCStreamer.h
index 3bf2d22e182353f..87691a6ec0e08dd 100644
--- a/llvm/include/llvm/MC/MCStreamer.h
+++ b/llvm/include/llvm/MC/MCStreamer.h
@@ -885,6 +885,12 @@ class MCStreamer {
   virtual void emitCodeAlignment(Align Alignment, const MCSubtargetInfo *STI,
                                  unsigned MaxBytesToEmit = 0);
 
+  /// If the end of the fragment following this NeverAlign fragment ever gets
+  /// aligned to \p ByteAlignment, this fragment emits a single nop before the
+  /// following fragment to break this end-alignment.
+  virtual void emitNeverAlignCodeAtEnd(unsigned ByteAlignment,
+                                       const MCSubtargetInfo &STI);
+
   /// Emit some number of copies of \p Value until the byte offset \p
   /// Offset is reached.
   ///
diff --git a/llvm/lib/MC/MCAssembler.cpp b/llvm/lib/MC/MCAssembler.cpp
index 901a66f156663f8..15c8b016fef6094 100644
--- a/llvm/lib/MC/MCAssembler.cpp
+++ b/llvm/lib/MC/MCAssembler.cpp
@@ -297,6 +297,43 @@ bool MCAssembler::evaluateFixup(const MCAsmLayout &Layout,
   return IsResolved;
 }
 
+/// Check if the branch crosses the boundary.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment alignment requirement of the branch.
+/// \returns true if the branch cross the boundary.
+static bool mayCrossBoundary(uint64_t StartAddr, uint64_t Size,
+                             Align BoundaryAlignment) {
+  uint64_t EndAddr = StartAddr + Size;
+  return (StartAddr >> Log2(BoundaryAlignment)) !=
+         ((EndAddr - 1) >> Log2(BoundaryAlignment));
+}
+
+/// Check if the branch is against the boundary.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment alignment requirement of the branch.
+/// \returns true if the branch is against the boundary.
+static bool isAgainstBoundary(uint64_t StartAddr, uint64_t Size,
+                              Align BoundaryAlignment) {
+  uint64_t EndAddr = StartAddr + Size;
+  return (EndAddr & (BoundaryAlignment.value() - 1)) == 0;
+}
+
+/// Check if the branch needs padding.
+///
+/// \param StartAddr start address of the fused/unfused branch.
+/// \param Size size of the fused/unfused branch.
+/// \param BoundaryAlignment alignment requirement of the branch.
+/// \returns true if the branch needs padding.
+static bool needPadding(uint64_t StartAddr, uint64_t Size,
+                        Align BoundaryAlignment) {
+  return mayCrossBoundary(StartAddr, Size, BoundaryAlignment) ||
+         isAgainstBoundary(StartAddr, Size, BoundaryAlignment);
+}
+
 uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout,
                                           const MCFragment &F) const {
   assert(getBackendPtr() && "Requires assembler backend");
@@ -357,6 +394,41 @@ uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout,
     return Size;
   }
 
+  case MCFragment::FT_NeverAlign: {
+    // Disclaimer: NeverAlign fragment size depends on the size of its immediate
+    // successor, but NeverAlign need not be a MCRelaxableFragment.
+    // NeverAlign fragment size is recomputed if the successor is relaxed:
+    // - If RelaxableFragment is relaxed, it gets invalidated by marking its
+    // predecessor as LastValidFragment.
+    // - This forces the assembler to call MCAsmLayout::layoutFragment on that
+    // relaxable fragment, which in turn will always ask the predecessor to
+    // compute its size (see "computeFragmentSize(prev)" in layoutFragment).
+    //
+    // In short, the simplest way to ensure that computeFragmentSize() is sane
+    // is to establish the following rule: it should never examine fragments
+    // after the current fragment in the section. If we logically need to
+    // examine any fragment after the current fragment, we need to do that using
+    // relaxation, inside MCAssembler::layoutSectionOnce.
+    const MCNeverAlignFragment &NAF = cast<MCNeverAlignFragment>(F);
+    const MCFragment *NF = F.getNextNode();
+    uint64_t Offset = Layout.getFragmentOffset(&NAF);
+    size_t NextFragSize = 0;
+    if (const auto *NextFrag = dyn_cast<MCRelaxableFragment>(NF)) {
+      NextFragSize = NextFrag->getContents().size();
+    } else if (const auto *NextFrag = dyn_cast<MCDataFragment>(NF)) {
+      NextFragSize = NextFrag->getContents().size();
+    } else {
+      llvm_unreachable("Didn't find the expected fragment after NeverAlign");
+    }
+    // Check if the next fragment ends at the alignment we want to avoid.
+    if (isAgainstBoundary(Offset, NextFragSize, Align(NAF.getAlignment()))) {
+      // Avoid this alignment by introducing minimum nop.
+      assert(getBackend().getMinimumNopSize() != NAF.getAlignment());
+      return getBackend().getMinimumNopSize();
+    }
+    return 0;
+  }
+
   case MCFragment::FT_Org: {
     const MCOrgFragment &OF = cast<MCOrgFragment>(F);
     MCValue Value;
@@ -580,6 +652,15 @@ static void writeFragment(raw_ostream &OS, const MCAssembler &Asm,
     break;
   }
 
+  case MCFragment::FT_NeverAlign: {
+    const MCNeverAlignFragment &NAF = cast<MCNeverAlignFragment>(F);
+    if (!Asm.getBackend().writeNopData(OS, FragmentSize,
+                                       &NAF.getSubtargetInfo()))
+      report_fatal_error("unable to write nop sequence of " +
+                         Twine(FragmentSize) + " bytes");
+    break;
+  }
+
   case MCFragment::FT_Data:
     ++stats::EmittedDataFragments;
     OS << cast<MCDataFragment>(F).getContents();
@@ -1046,43 +1127,6 @@ bool MCAssembler::relaxLEB(MCAsmLayout &Layout, MCLEBFragment &LF) {
   return OldSize != LF.getContents().size();
 }
 
-/// Check if the branch crosses the boundary.
-///
-/// \param StartAddr start address of the fused/unfused branch.
-/// \param Size size of the fused/unfused branch.
-/// \param BoundaryAlignment alignment requirement of the branch.
-/// \returns true if the branch cross the boundary.
-static bool mayCrossBoundary(uint64_t StartAddr, uint64_t Size,
-                             Align BoundaryAlignment) {
-  uint64_t EndAddr = StartAddr + Size;
-  return (StartAddr >> Log2(BoundaryAlignment)) !=
-         ((EndAddr - 1) >> Log2(BoundaryAlignment));
-}
-
-/// Check if the branch is against the boundary.
-///
-/// \param StartAddr start address of the fused/unfused branch.
-/// \param Size size of the fused/unfused branch.
-/// \param BoundaryAlignment alignment requirement of the branch.
-/// \returns true if the branch is against the boundary.
-static bool isAgainstBoundary(uint64_t StartAddr, uint64_t Size,
-                              Align BoundaryAlignment) {
-  uint64_t EndAddr = StartAddr + Size;
-  return (EndAddr & (BoundaryAlignment.value() - 1)) == 0;
-}
-
-/// Check if the branch needs padding.
-///
-/// \param StartAddr start address of the fused/unfused branch.
-/// \param Size size of the fused/unfused branch.
-/// \param BoundaryAlignment alignment requirement of the branch.
-/// \returns true if the branch needs padding.
-static bool needPadding(uint64_t StartAddr, uint64_t Size,
-                        Align BoundaryAlignment) {
-  return mayCrossBoundary(StartAddr, Size, BoundaryAlignment) ||
-         isAgainstBoundary(StartAddr, Size, BoundaryAlignment);
-}
-
 bool MCAssembler::relaxBoundaryAlign(MCAsmLayout &Layout,
                                      MCBoundaryAlignFragment &BF) {
   // BoundaryAlignFragment that doesn't need to align any fragment should not be
diff --git a/llvm/lib/MC/MCFragment.cpp b/llvm/lib/MC/MCFragment.cpp
index 4e6459c5d6e459f..5a143a439ba9777 100644
--- a/llvm/lib/MC/MCFragment.cpp
+++ b/llvm/lib/MC/MCFragment.cpp
@@ -274,6 +274,9 @@ void MCFragment::destroy() {
     case FT_Align:
       delete cast<MCAlignFragment>(this);
       return;
+    case FT_NeverAlign:
+      delete cast<MCNeverAlignFragment>(this);
+      return;
     case FT_Data:
       delete cast<MCDataFragment>(this);
       return;
@@ -342,6 +345,9 @@ LLVM_DUMP_METHOD void MCFragment::dump() const {
   OS << "<";
   switch (getKind()) {
   case MCFragment::FT_Align: OS << "MCAlignFragment"; break;
+  case MCFragment::FT_NeverAlign:
+    OS << "MCNeverAlignFragment";
+    break;
   case MCFragment::FT_Data:  OS << "MCDataFragment"; break;
   case MCFragment::FT_CompactEncodedInst:
     OS << "MCCompactEncodedInstFragment"; break;
@@ -381,6 +387,12 @@ LLVM_DUMP_METHOD void MCFragment::dump() const {
        << " MaxBytesToEmit:" << AF->getMaxBytesToEmit() << ">";
     break;
   }
+  case MCFragment::FT_NeverAlign: {
+    const MCNeverAlignFragment *NAF = cast<MCNeverAlignFragment>(this);
+    OS << "\n       ";
+    OS << " Alignment:" << NAF->getAlignment() << ">";
+    break;
+  }
   case MCFragment::FT_Data:  {
     const auto *DF = cast<MCDataFragment>(this);
     OS << "\n       ";
diff --git a/llvm/lib/MC/MCObjectStreamer.cpp b/llvm/lib/MC/MCObjectStreamer.cpp
index 3cf7b4359cabab6..3f4fb6ca9f0ae24 100644
--- a/llvm/lib/MC/MCObjectStreamer.cpp
+++ b/llvm/lib/MC/MCObjectStreamer.cpp
@@ -659,6 +659,11 @@ void MCObjectStreamer::emitCodeAlignment(Align Alignment,
   cast<MCAlignFragment>(getCurrentFragment())->setEmitNops(true, STI);
 }
 
+void MCObjectStreamer::emitNeverAlignCodeAtEnd(unsigned ByteAlignment,
+                                               const MCSubtargetInfo &STI) {
+  insert(new MCNeverAlignFragment(ByteAlignment, STI));
+}
+
 void MCObjectStreamer::emitValueToOffset(const MCExpr *Offset,
                                          unsigned char Value,
                                          SMLoc Loc) {
diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
index 2371cb2384414b9..008852afa39cbe6 100644
--- a/llvm/lib/MC/MCStreamer.cpp
+++ b/llvm/lib/MC/MCStreamer.cpp
@@ -1237,6 +1237,8 @@ void MCStreamer::emitValueToAlignment(Align Alignment, int64_t Value,
                                       unsigned MaxBytesToEmit) {}
 void MCStreamer::emitCodeAlignment(Align Alignment, const MCSubtargetInfo *STI,
                                    unsigned MaxBytesToEmit) {}
+void MCStreamer::emitNeverAlignCodeAtEnd(unsigned ByteAlignment,
+                                         const MCSubtargetInfo &STI) {}
 void MCStreamer::emitValueToOffset(const MCExpr *Offset, unsigned char Value,
                                    SMLoc Loc) {}
 void MCStreamer::emitBundleAlignMode(Align Alignment) {}
diff --git a/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp b/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp
index 19b4ea474f5284b..414a6a9e2daba6d 100644
--- a/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp
+++ b/llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp
@@ -1152,6 +1152,7 @@ class X86AsmParser : public MCTargetAsmParser {
   bool parseDirectiveArch();
   bool parseDirectiveNops(SMLoc L);
   bool parseDirectiveEven(SMLoc L);
+  bool parseDirectiveAvoidEndAlign(SMLoc L);
   bool ParseDirectiveCode(StringRef IDVal, SMLoc L);
 
   /// CodeView FPO data directives.
@@ -4493,6 +4494,8 @@ bool X86AsmParser::ParseDirective(AsmToken DirectiveID) {
     return false;
   } else if (IDVal == ".nops")
     return parseDirectiveNops(DirectiveID.getLoc());
+  else if (IDVal == ".avoid_end_align")
+    return parseDirectiveAvoidEndAlign(DirectiveID.getLoc());
   else if (IDVal == ".even")
     return parseDirectiveEven(DirectiveID.getLoc());
   else if (IDVal == ".cv_fpo_proc")
@@ -4587,6 +4590,27 @@ bool X86AsmParser::parseDirectiveEven(SMLoc L) {
   return false;
 }
 
+/// Directive for NeverAlign fragment testing, not for general usage!
+/// parseDirectiveAvoidEndAlign
+///  ::= .avoid_end_align alignment
+bool X86AsmParser::parseDirectiveAvoidEndAlign(SMLoc L) {
+  int64_t Alignment = 0;
+  SMLoc AlignmentLoc;
+  AlignmentLoc = getTok().getLoc();
+  if (getParser().checkForValidSection() ||
+      getParser().parseAbsoluteExpression(Alignment))
+    return true;
+
+  if (getParser().parseEOL("unexpected token in directive"))
+    return true;
+
+  if (Alignment <= 0)
+    return Error(AlignmentLoc, "expected a positive alignment");
+
+  getParser().getStreamer().emitNeverAlignCodeAtEnd(Alignment, getSTI());
+  return false;
+}
+
 /// ParseDirectiveCode
 ///  ::= .code16 | .code32 | .code64
 bool X86AsmParser::ParseDirectiveCode(StringRef IDVal, SMLoc L) {
diff --git a/llvm/test/MC/X86/directive-avoid_end_align.s b/llvm/test/MC/X86/directive-avoid_end_align.s
new file mode 100644
index 000000000000000..1d748401edc12ed
--- /dev/null
+++ b/llvm/test/MC/X86/directive-avoid_end_align.s
@@ -0,0 +1,208 @@
+# RUN: llvm-mc -triple=x86_64 -filetype=obj %s | llvm-objdump --no-show-raw-insn -d - | FileCheck %s
+# RUN: not llvm-mc -triple=x86_64 --defsym ERR=1 %s -o /dev/null 2>&1 | FileCheck %s --check-prefix=ERR
+
+# avoid_end_align has no effect since test doesn't end at alignment boundary:
+.avoid_end_align 64
+# CHECK-NOT: nop
+  testl %eax, %eax
+# CHECK: testl %eax, %eax
+  je  .LBB0
+
+.fill 58, 1, 0x00
+# NeverAlign followed by MCDataFragment:
+# avoid_end_align inserts nop because `test` would end at alignment boundary:
+.avoid_end_align 64
+# CHECK: 			3e: nop
+  testl %eax, %eax
+# CHECK-NEXT: 3f: testl %eax, %eax
+  je  .LBB0
+# CHECK-NEXT: 41: je
+.LBB0:
+  retq
+
+.p2align 6
+.L0:
+.nops 57
+  int3
+# NeverAlign followed by RelaxableFragment:
+.avoid_end_align 64
+# CHECK: 			ba: nop
+  cmpl $(.L1-.L0), %eax
+# CHECK-NEXT: bb: cmpl
+  je  .L0
+# CHECK-NEXT: c1: je
+.nops 65
+.L1:
+
+###############################################################################
+# Experiment A:
+# Check that NeverAlign doesn't introduce infinite loops in layout.
+# Control:
+# 1. NeverAlign fragment is not added,
+# 2. Short formats of cmp and jcc are used (3 and 2 bytes respectively),
+# 3. cmp and jcc are placed such that to be split by 64B alignment boundary.
+# 4. jcc would be relaxed to a longer format if at least one byte is added
+#    between .L10 and je itself, e.g. by adding a NeverAlign padding byte,
+#    or relaxing cmp instruction.
+# 5. cmp would be relaxed to a longer format if at least one byte is added
+#    between .L11 and .L12, e.g. due to relaxing jcc instruction.
+.p2align 6
+# CHECK:      140: int3
+.fill 2, 1, 0xcc
+.L10:
+.nops 122
+  int3
+# CHECK:      1bc: int3
+# no avoid_end_align here
+# CHECK-NOT:  nop
+  cmp $(.L12-.L11), %eax
+# CHECK:      1bd: cmpl
+.L11:
+  je  .L10
+# CHECK-NEXT: 1c0: je
+.nops 125
+.L12:
+
+# Experiment:
+# Same setup as control, except NeverAlign fragment is added before cmp.
+# Expected effect:
+# 1. NeverAlign pads cmp+jcc by one byte since cmp and jcc are split by a 64B
+#    alignment boundary,
+# 2. This extra byte forces jcc relaxation to a longer format (Control rule #4),
+# 3. This results in an cmp relaxation (Control rule #5),
+# 4. Which in turn makes NeverAlign fragment unnecessary as cmp and jcc
+#    are no longer split by an alignment boundary (cmp crosses the boundary).
+# 5. NeverAlign padding is removed.
+# 6. cmp and jcc instruction remain in relaxed form.
+# 7. Relaxation converges, layout succeeds.
+.p2align 6
+# CHECK:      240: int3
+.fill 2, 1, 0xcc
+.L20:
+.nops 122
+  int3
+# CHECK:      2bc: int3
+.avoid_end_align 64
+# CHECK-NOT: 	nop
+  cmp $(.L22-.L21), %eax
+# CHECK-NEXT: 2bd: cmpl
+.L21:
+  je  .L20
+# CHECK-NEXT: 2c3: je
+.nops 125
+.L22:
+
+###############################################################################
+# Experiment B: similar to exp A, but we check that once NeverAlign padding is
+# removed from the layout (exp A, experiment step 5), the increased distance
+# between the symbols L33 and L34 triggers the relaxation of instruction at
+# label L32.
+#
+# Control 1: using a one-byte instruction at L33 (site of NeverAlign) leads to
+# steps 2-3 of exp A, experiment:
+# 2. This extra byte forces jcc relaxation to a longer format (Control rule #4),
+# 3. This results in an cmp relaxation (Control rule #5),
+# => short cmp under L32
+.p2align 6
+# CHECK:      380: int3
+.fill 2, 1, 0xcc
+.L30:
+.nops 122
+  int3
+# CHECK:      3fc: int3
+  hlt
+#.avoid_end_align 64
+.L33:
+  cmp $(.L32-.L31), %eax
+# CHECK:      3fe: cmpl
+.L31:
+  je  .L30
+# CHECK-NEXT: 404: je
+.nops 114
+.p2align 1
+  int3
+  int3
+# CHECK:      47c: int3
+.L34:
+.nops 9
+.L32:
+  cmp $(.L33-.L34), %eax
+# CHECK:      487: cmp
+# note that the size of cmp is 48a-487 == 3 bytes (distance is exactly -128)
+  int3
+# CHECK-NEXT: 48a: int3
+
+# Control 2: leaving out a byte at L43 (site of NeverAlign), plus
+# relaxed jcc and cmp leads to a relaxed cmp under L42 (-129 as cmp's immediate)
+.p2align 6
+# CHECK:      4c0: int3
+.fill 2, 1, 0xcc
+.L40:
+.nops 122
+  int3
+# CHECK:      53c: int3
+#  int3
+#.avoid_end_align 64
+.L43:
+  cmp $(.L42-.L41+0x100), %eax
+# CHECK:      53d: cmpl
+.L41:
+  je  .L40+0x100
+# CHECK-NEXT: 543: je
+.nops 114
+.p2align 1
+  int3
+  int3
+# CHECK:      5bc: int3
+.L44:
+.nops 9
+.L42:
+  cmp $(.L43-.L44), %eax
+# CHECK:      5c7: cmp
+# note that the size of cmp is 5cd-5c7 == 6 bytes (distance is exactly -129)
+  int3
+# CHECK-NEXT: 5cd: int3
+
+# Experiment
+# Checking if removing NeverAlign padding at L53 as a result of alignment and
+# relaxation of cmp and jcc following it (see exp A), thus reproducing the case
+# in Control 2 (getting a relaxed cmp under L52), is handled correctly.
+.p2align 6
+# CHECK:      600: int3
+.fill 2, 1, 0xcc
+.L50:
+.nops 122
+  int3
+# CHECK:      67c: int3
+.avoid_end_align 64
+.L53:
+# CHECK-NOT: 	nop
+  cmp $(.L52-.L51), %eax
+# CHECK-NEXT: 67d: cmpl
+.L51:
+  je  .L50
+# CHECK-NEXT: 683: je
+.nops 114
+.p2align 1
+  int3
+  int3
+# CHECK:      6fc: int3
+.L54:
+.nops 9
+.L52:
+  cmp $(.L53-.L54), %eax
+# CHECK:      707: cmp
+# note that the size of cmp is 70d-707 == 6 bytes (distance is exactly -129)
+  int3
+# CHECK-NEXT: 70d: int3
+
+.ifdef ERR
+# ERR: {{.*}}.s:[[#@LINE+1]]:17: error: unknown token in expression
+.avoid_end_align
+# ERR: {{.*}}.s:[[#@LINE+1]]:18: error: expected absolute expression
+.avoid_end_align x
+# ERR: {{.*}}.s:[[#@LINE+1]]:18: error: expected a positive alignment
+.avoid_end_align 0
+# ERR: {{.*}}.s:[[#@LINE+1]]:20: error: unexpected token in directive
+.avoid_end_align 64, 0
+.endif

>From 255c5d427ae30f9acd66af10452e1e7f67f2409e Mon Sep 17 00:00:00 2001
From: Alexander Yermolovich <ayermolo at meta.com>
Date: Fri, 17 Nov 2023 12:09:34 -0800
Subject: [PATCH 3/3] [BOLT][DWARF] Fix handling of DWARF5 DWP

Fixed handling of DWP as input. Before BOLT crashed. Now it will write out
correct CU, and all the TUs. Potential future improvement is to scan all the TUs
used in this CU, and only include those.
---
 bolt/include/bolt/Core/DIEBuilder.h           |   3 +-
 bolt/lib/Core/DIEBuilder.cpp                  |  17 +-
 bolt/lib/Rewrite/DWARFRewriter.cpp            |  14 +-
 .../X86/Inputs/dwarf5-df-types-dup-helper.s   | 504 ++++++++++++++++++
 .../X86/Inputs/dwarf5-df-types-dup-main.s     | 498 +++++++++++++++++
 .../X86/dwarf5-df-types-dup-dwp-input.test    |  29 +
 6 files changed, 1048 insertions(+), 17 deletions(-)
 create mode 100644 bolt/test/X86/Inputs/dwarf5-df-types-dup-helper.s
 create mode 100644 bolt/test/X86/Inputs/dwarf5-df-types-dup-main.s
 create mode 100644 bolt/test/X86/dwarf5-df-types-dup-dwp-input.test

diff --git a/bolt/include/bolt/Core/DIEBuilder.h b/bolt/include/bolt/Core/DIEBuilder.h
index fb86e59468b835a..1c5252142d4ebf5 100644
--- a/bolt/include/bolt/Core/DIEBuilder.h
+++ b/bolt/include/bolt/Core/DIEBuilder.h
@@ -273,7 +273,8 @@ class DIEBuilder {
   void buildCompileUnits(const std::vector<DWARFUnit *> &CUs);
   /// Preventing implicit conversions.
   template <class T> void buildCompileUnits(T) = delete;
-  void buildBoth();
+  /// Builds DWO Unit. For DWARF5 this includes the type units.
+  void buildDWOUnit(DWARFUnit &U);
 
   /// Returns DWARFUnitInfo for DWARFUnit
   DWARFUnitInfo &getUnitInfoByDwarfUnit(const DWARFUnit &DwarfUnit) {
diff --git a/bolt/lib/Core/DIEBuilder.cpp b/bolt/lib/Core/DIEBuilder.cpp
index 223ae714440d97d..6b33303ba553b72 100644
--- a/bolt/lib/Core/DIEBuilder.cpp
+++ b/bolt/lib/Core/DIEBuilder.cpp
@@ -193,12 +193,6 @@ void DIEBuilder::buildTypeUnits(const bool Init) {
   if (Init)
     BuilderState.reset(new State());
 
-  unsigned int CUNum = getCUNum(DwarfContext, IsDWO);
-  getState().CloneUnitCtxMap.resize(CUNum);
-  DWARFContext::unit_iterator_range CU4TURanges =
-      IsDWO ? DwarfContext->dwo_types_section_units()
-            : DwarfContext->types_section_units();
-
   const DWARFUnitIndex &TUIndex = DwarfContext->getTUIndex();
   if (!TUIndex.getRows().empty()) {
     for (auto &Row : TUIndex.getRows()) {
@@ -208,6 +202,11 @@ void DIEBuilder::buildTypeUnits(const bool Init) {
                                        true);
     }
   }
+  unsigned int CUNum = getCUNum(DwarfContext, IsDWO);
+  getState().CloneUnitCtxMap.resize(CUNum);
+  DWARFContext::unit_iterator_range CU4TURanges =
+      IsDWO ? DwarfContext->dwo_types_section_units()
+            : DwarfContext->types_section_units();
 
   getState().Type = ProcessingType::DWARF4TUs;
   for (std::unique_ptr<DWARFUnit> &DU : CU4TURanges)
@@ -278,11 +277,13 @@ void DIEBuilder::buildCompileUnits(const std::vector<DWARFUnit *> &CUs) {
     constructFromUnit(*DU);
 }
 
-void DIEBuilder::buildBoth() {
+void DIEBuilder::buildDWOUnit(DWARFUnit &U) {
   BuilderState.release();
   BuilderState = std::make_unique<State>();
   buildTypeUnits(false);
-  buildCompileUnits(false);
+  getState().Type = ProcessingType::CUs;
+  registerUnit(U, false);
+  constructFromUnit(U);
 }
 
 DIE *DIEBuilder::constructDIEFast(DWARFDie &DDie, DWARFUnit &U,
diff --git a/bolt/lib/Rewrite/DWARFRewriter.cpp b/bolt/lib/Rewrite/DWARFRewriter.cpp
index 360b82f45bd7754..3bba61724b9e542 100644
--- a/bolt/lib/Rewrite/DWARFRewriter.cpp
+++ b/bolt/lib/Rewrite/DWARFRewriter.cpp
@@ -481,7 +481,7 @@ emitUnit(DIEBuilder &DIEBldr, DIEStreamer &Streamer, DWARFUnit &Unit) {
 
 static void emitDWOBuilder(const std::string &DWOName,
                            DIEBuilder &DWODIEBuilder, DWARFRewriter &Rewriter,
-                           const DWARFUnit &SplitCU, DWARFUnit &CU,
+                           DWARFUnit &SplitCU, DWARFUnit &CU,
                            DWARFRewriter::DWPState &State,
                            DebugLocWriter &LocWriter) {
   // Populate debug_info and debug_abbrev for current dwo into StringRef.
@@ -498,17 +498,15 @@ static void emitDWOBuilder(const std::string &DWOName,
   DWARFRewriter::UnitMetaVectorType TUMetaVector;
   DWARFRewriter::UnitMeta CUMI = {0, 0, 0};
   if (SplitCU.getContext().getMaxDWOVersion() >= 5) {
-    // TODO: Handle DWP as input. Right now it will iterate over all of CUs and
-    // TUs
     for (std::unique_ptr<llvm::DWARFUnit> &CU :
          SplitCU.getContext().dwo_info_section_units()) {
+      if (!CU->isTypeUnit())
+        continue;
       DWARFRewriter::UnitMeta MI =
           emitUnit(DWODIEBuilder, *Streamer, *CU.get());
-      if (CU->isTypeUnit())
-        TUMetaVector.emplace_back(MI);
-      else
-        CUMI = MI;
+      TUMetaVector.emplace_back(MI);
     }
+    CUMI = emitUnit(DWODIEBuilder, *Streamer, SplitCU);
   } else {
     for (std::unique_ptr<llvm::DWARFUnit> &CU :
          SplitCU.getContext().dwo_compile_units())
@@ -707,7 +705,7 @@ void DWARFRewriter::updateDebugInfo() {
     // Skipping CUs that failed to load.
     if (SplitCU) {
       DIEBuilder DWODIEBuilder(&(*SplitCU)->getContext(), true);
-      DWODIEBuilder.buildBoth();
+      DWODIEBuilder.buildDWOUnit(**SplitCU);
       std::string DWOName = updateDWONameCompDir(
           *Unit, *DIEBlder, *DIEBlder->getUnitDIEbyUnit(*Unit));
 
diff --git a/bolt/test/X86/Inputs/dwarf5-df-types-dup-helper.s b/bolt/test/X86/Inputs/dwarf5-df-types-dup-helper.s
new file mode 100644
index 000000000000000..cf0bdad3bbda188
--- /dev/null
+++ b/bolt/test/X86/Inputs/dwarf5-df-types-dup-helper.s
@@ -0,0 +1,504 @@
+# clang++ -gsplit-dwarf -g2 -gdwarf-5 -gpubnames -fdebug-types-section -fdebug-compilation-dir='.'
+# header.h
+# struct Foo2a {
+#   char *c1;
+#   char *c2;
+#   char *c3;
+# };
+
+# main.cpp
+# #include "header.h"
+# int fooint;
+# struct Foo2Int {
+#    int *c1;
+#    int *c2;
+# };
+#
+# int foo() {
+#   Foo2Int fint;
+#   Foo2a f;
+#   return 0;
+# }
+
+	.text
+	.file	"helper.cpp"
+	.file	0 "." "helper.cpp" md5 0xc33186b2db66a78883b1546aace9855d
+	.globl	_Z3foov                         # -- Begin function _Z3foov
+	.p2align	4, 0x90
+	.type	_Z3foov, at function
+_Z3foov:                                # @_Z3foov
+.Lfunc_begin0:
+	.loc	0 8 0                           # helper.cpp:8:0
+	.cfi_startproc
+# %bb.0:                                # %entry
+	pushq	%rbp
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+	.cfi_def_cfa_register %rbp
+.Ltmp0:
+	.loc	0 11 3 prologue_end             # helper.cpp:11:3
+	xorl	%eax, %eax
+	.loc	0 11 3 epilogue_begin is_stmt 0 # helper.cpp:11:3
+	popq	%rbp
+	.cfi_def_cfa %rsp, 8
+	retq
+.Ltmp1:
+.Lfunc_end0:
+	.size	_Z3foov, .Lfunc_end0-_Z3foov
+	.cfi_endproc
+                                        # -- End function
+	.type	fooint, at object                  # @fooint
+	.bss
+	.globl	fooint
+	.p2align	2, 0x0
+fooint:
+	.long	0                               # 0x0
+	.size	fooint, 4
+
+	.section	.debug_info.dwo,"e", at progbits
+	.long	.Ldebug_info_dwo_end0-.Ldebug_info_dwo_start0 # Length of Unit
+.Ldebug_info_dwo_start0:
+	.short	5                               # DWARF version number
+	.byte	6                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	-3882554063269480080            # Type Signature
+	.long	31                              # Type DIE Offset
+	.byte	1                               # Abbrev [1] 0x18:0x2a DW_TAG_type_unit
+	.short	33                              # DW_AT_language
+	.long	0                               # DW_AT_stmt_list
+	.byte	2                               # Abbrev [2] 0x1f:0x19 DW_TAG_structure_type
+	.byte	5                               # DW_AT_calling_convention
+	.byte	7                               # DW_AT_name
+	.byte	16                              # DW_AT_byte_size
+	.byte	0                               # DW_AT_decl_file
+	.byte	3                               # DW_AT_decl_line
+	.byte	3                               # Abbrev [3] 0x25:0x9 DW_TAG_member
+	.byte	5                               # DW_AT_name
+	.long	56                              # DW_AT_type
+	.byte	0                               # DW_AT_decl_file
+	.byte	4                               # DW_AT_decl_line
+	.byte	0                               # DW_AT_data_member_location
+	.byte	3                               # Abbrev [3] 0x2e:0x9 DW_TAG_member
+	.byte	6                               # DW_AT_name
+	.long	56                              # DW_AT_type
+	.byte	0                               # DW_AT_decl_file
+	.byte	5                               # DW_AT_decl_line
+	.byte	8                               # DW_AT_data_member_location
+	.byte	0                               # End Of Children Mark
+	.byte	4                               # Abbrev [4] 0x38:0x5 DW_TAG_pointer_type
+	.long	61                              # DW_AT_type
+	.byte	5                               # Abbrev [5] 0x3d:0x4 DW_TAG_base_type
+	.byte	1                               # DW_AT_name
+	.byte	5                               # DW_AT_encoding
+	.byte	4                               # DW_AT_byte_size
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end0:
+	.long	.Ldebug_info_dwo_end1-.Ldebug_info_dwo_start1 # Length of Unit
+.Ldebug_info_dwo_start1:
+	.short	5                               # DWARF version number
+	.byte	6                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	1175092228111723119             # Type Signature
+	.long	31                              # Type DIE Offset
+	.byte	1                               # Abbrev [1] 0x18:0x33 DW_TAG_type_unit
+	.short	33                              # DW_AT_language
+	.long	0                               # DW_AT_stmt_list
+	.byte	2                               # Abbrev [2] 0x1f:0x22 DW_TAG_structure_type
+	.byte	5                               # DW_AT_calling_convention
+	.byte	11                              # DW_AT_name
+	.byte	24                              # DW_AT_byte_size
+	.byte	1                               # DW_AT_decl_file
+	.byte	1                               # DW_AT_decl_line
+	.byte	3                               # Abbrev [3] 0x25:0x9 DW_TAG_member
+	.byte	5                               # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	2                               # DW_AT_decl_line
+	.byte	0                               # DW_AT_data_member_location
+	.byte	3                               # Abbrev [3] 0x2e:0x9 DW_TAG_member
+	.byte	6                               # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	3                               # DW_AT_decl_line
+	.byte	8                               # DW_AT_data_member_location
+	.byte	3                               # Abbrev [3] 0x37:0x9 DW_TAG_member
+	.byte	10                              # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	4                               # DW_AT_decl_line
+	.byte	16                              # DW_AT_data_member_location
+	.byte	0                               # End Of Children Mark
+	.byte	4                               # Abbrev [4] 0x41:0x5 DW_TAG_pointer_type
+	.long	70                              # DW_AT_type
+	.byte	5                               # Abbrev [5] 0x46:0x4 DW_TAG_base_type
+	.byte	9                               # DW_AT_name
+	.byte	6                               # DW_AT_encoding
+	.byte	1                               # DW_AT_byte_size
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end1:
+	.section	.debug_abbrev,"", at progbits
+	.byte	1                               # Abbreviation Code
+	.byte	74                              # DW_TAG_skeleton_unit
+	.byte	0                               # DW_CHILDREN_no
+	.byte	16                              # DW_AT_stmt_list
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	114                             # DW_AT_str_offsets_base
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	27                              # DW_AT_comp_dir
+	.byte	37                              # DW_FORM_strx1
+	.byte	118                             # DW_AT_dwo_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	17                              # DW_AT_low_pc
+	.byte	27                              # DW_FORM_addrx
+	.byte	18                              # DW_AT_high_pc
+	.byte	6                               # DW_FORM_data4
+	.byte	115                             # DW_AT_addr_base
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	0                               # EOM(3)
+	.section	.debug_info,"", at progbits
+.Lcu_begin0:
+	.long	.Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+	.short	5                               # DWARF version number
+	.byte	4                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	.debug_abbrev                   # Offset Into Abbrev. Section
+	.quad	2142419470755914572
+	.byte	1                               # Abbrev [1] 0x14:0x14 DW_TAG_skeleton_unit
+	.long	.Lline_table_start0             # DW_AT_stmt_list
+	.long	.Lstr_offsets_base0             # DW_AT_str_offsets_base
+	.byte	0                               # DW_AT_comp_dir
+	.byte	1                               # DW_AT_dwo_name
+	.byte	1                               # DW_AT_low_pc
+	.long	.Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+	.long	.Laddr_table_base0              # DW_AT_addr_base
+.Ldebug_info_end0:
+	.section	.debug_str_offsets,"", at progbits
+	.long	12                              # Length of String Offsets Set
+	.short	5
+	.short	0
+.Lstr_offsets_base0:
+	.section	.debug_str,"MS", at progbits,1
+.Lskel_string0:
+	.asciz	"."                             # string offset=0
+.Lskel_string1:
+	.asciz	"helper.dwo"                    # string offset=2
+	.section	.debug_str_offsets,"", at progbits
+	.long	.Lskel_string0
+	.long	.Lskel_string1
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	64                              # Length of String Offsets Set
+	.short	5
+	.short	0
+	.section	.debug_str.dwo,"eMS", at progbits,1
+.Linfo_string0:
+	.asciz	"fooint"                        # string offset=0
+.Linfo_string1:
+	.asciz	"int"                           # string offset=7
+.Linfo_string2:
+	.asciz	"_Z3foov"                       # string offset=11
+.Linfo_string3:
+	.asciz	"foo"                           # string offset=19
+.Linfo_string4:
+	.asciz	"fint"                          # string offset=23
+.Linfo_string5:
+	.asciz	"c1"                            # string offset=28
+.Linfo_string6:
+	.asciz	"c2"                            # string offset=31
+.Linfo_string7:
+	.asciz	"Foo2Int"                       # string offset=34
+.Linfo_string8:
+	.asciz	"f"                             # string offset=42
+.Linfo_string9:
+	.asciz	"char"                          # string offset=44
+.Linfo_string10:
+	.asciz	"c3"                            # string offset=49
+.Linfo_string11:
+	.asciz	"Foo2a"                         # string offset=52
+.Linfo_string12:
+	.asciz	"clang version 18.0.0"          # string offset=58
+.Linfo_string13:
+	.asciz	"helper.cpp"                    # string offset=79
+.Linfo_string14:
+	.asciz	"helper.dwo"                    # string offset=90
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	0
+	.long	7
+	.long	11
+	.long	19
+	.long	23
+	.long	28
+	.long	31
+	.long	34
+	.long	42
+	.long	44
+	.long	49
+	.long	52
+	.long	58
+	.long	79
+	.long	90
+	.section	.debug_info.dwo,"e", at progbits
+	.long	.Ldebug_info_dwo_end2-.Ldebug_info_dwo_start2 # Length of Unit
+.Ldebug_info_dwo_start2:
+	.short	5                               # DWARF version number
+	.byte	5                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	2142419470755914572
+	.byte	6                               # Abbrev [6] 0x14:0x4f DW_TAG_compile_unit
+	.byte	12                              # DW_AT_producer
+	.short	33                              # DW_AT_language
+	.byte	13                              # DW_AT_name
+	.byte	14                              # DW_AT_dwo_name
+	.byte	7                               # Abbrev [7] 0x1a:0xb DW_TAG_variable
+	.byte	0                               # DW_AT_name
+	.long	37                              # DW_AT_type
+                                        # DW_AT_external
+	.byte	0                               # DW_AT_decl_file
+	.byte	2                               # DW_AT_decl_line
+	.byte	2                               # DW_AT_location
+	.byte	161
+	.byte	0
+	.byte	5                               # Abbrev [5] 0x25:0x4 DW_TAG_base_type
+	.byte	1                               # DW_AT_name
+	.byte	5                               # DW_AT_encoding
+	.byte	4                               # DW_AT_byte_size
+	.byte	8                               # Abbrev [8] 0x29:0x27 DW_TAG_subprogram
+	.byte	1                               # DW_AT_low_pc
+	.long	.Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+	.byte	1                               # DW_AT_frame_base
+	.byte	86
+	.byte	2                               # DW_AT_linkage_name
+	.byte	3                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	8                               # DW_AT_decl_line
+	.long	37                              # DW_AT_type
+                                        # DW_AT_external
+	.byte	9                               # Abbrev [9] 0x39:0xb DW_TAG_variable
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	112
+	.byte	4                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	9                               # DW_AT_decl_line
+	.long	80                              # DW_AT_type
+	.byte	9                               # Abbrev [9] 0x44:0xb DW_TAG_variable
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	88
+	.byte	8                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	10                              # DW_AT_decl_line
+	.long	89                              # DW_AT_type
+	.byte	0                               # End Of Children Mark
+	.byte	10                              # Abbrev [10] 0x50:0x9 DW_TAG_structure_type
+                                        # DW_AT_declaration
+	.quad	-3882554063269480080            # DW_AT_signature
+	.byte	10                              # Abbrev [10] 0x59:0x9 DW_TAG_structure_type
+                                        # DW_AT_declaration
+	.quad	1175092228111723119             # DW_AT_signature
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end2:
+	.section	.debug_abbrev.dwo,"e", at progbits
+	.byte	1                               # Abbreviation Code
+	.byte	65                              # DW_TAG_type_unit
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	19                              # DW_AT_language
+	.byte	5                               # DW_FORM_data2
+	.byte	16                              # DW_AT_stmt_list
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	2                               # Abbreviation Code
+	.byte	19                              # DW_TAG_structure_type
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	54                              # DW_AT_calling_convention
+	.byte	11                              # DW_FORM_data1
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	3                               # Abbreviation Code
+	.byte	13                              # DW_TAG_member
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	56                              # DW_AT_data_member_location
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	4                               # Abbreviation Code
+	.byte	15                              # DW_TAG_pointer_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	5                               # Abbreviation Code
+	.byte	36                              # DW_TAG_base_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	62                              # DW_AT_encoding
+	.byte	11                              # DW_FORM_data1
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	6                               # Abbreviation Code
+	.byte	17                              # DW_TAG_compile_unit
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	37                              # DW_AT_producer
+	.byte	37                              # DW_FORM_strx1
+	.byte	19                              # DW_AT_language
+	.byte	5                               # DW_FORM_data2
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	118                             # DW_AT_dwo_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	7                               # Abbreviation Code
+	.byte	52                              # DW_TAG_variable
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	63                              # DW_AT_external
+	.byte	25                              # DW_FORM_flag_present
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	2                               # DW_AT_location
+	.byte	24                              # DW_FORM_exprloc
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	8                               # Abbreviation Code
+	.byte	46                              # DW_TAG_subprogram
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	17                              # DW_AT_low_pc
+	.byte	27                              # DW_FORM_addrx
+	.byte	18                              # DW_AT_high_pc
+	.byte	6                               # DW_FORM_data4
+	.byte	64                              # DW_AT_frame_base
+	.byte	24                              # DW_FORM_exprloc
+	.byte	110                             # DW_AT_linkage_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	63                              # DW_AT_external
+	.byte	25                              # DW_FORM_flag_present
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	9                               # Abbreviation Code
+	.byte	52                              # DW_TAG_variable
+	.byte	0                               # DW_CHILDREN_no
+	.byte	2                               # DW_AT_location
+	.byte	24                              # DW_FORM_exprloc
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	10                              # Abbreviation Code
+	.byte	19                              # DW_TAG_structure_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	60                              # DW_AT_declaration
+	.byte	25                              # DW_FORM_flag_present
+	.byte	105                             # DW_AT_signature
+	.byte	32                              # DW_FORM_ref_sig8
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	0                               # EOM(3)
+	.section	.debug_line.dwo,"e", at progbits
+.Ltmp2:
+	.long	.Ldebug_line_end0-.Ldebug_line_start0 # unit length
+.Ldebug_line_start0:
+	.short	5
+	.byte	8
+	.byte	0
+	.long	.Lprologue_end0-.Lprologue_start0
+.Lprologue_start0:
+	.byte	1
+	.byte	1
+	.byte	1
+	.byte	-5
+	.byte	14
+	.byte	1
+	.byte	1
+	.byte	1
+	.byte	8
+	.byte	2
+	.byte	46
+	.byte	0
+	.byte	46
+	.byte	0
+	.byte	3
+	.byte	1
+	.byte	8
+	.byte	2
+	.byte	15
+	.byte	5
+	.byte	30
+	.byte	2
+	.ascii	"helper.cpp"
+	.byte	0
+	.byte	0
+	.byte	0xc3, 0x31, 0x86, 0xb2
+	.byte	0xdb, 0x66, 0xa7, 0x88
+	.byte	0x83, 0xb1, 0x54, 0x6a
+	.byte	0xac, 0xe9, 0x85, 0x5d
+	.ascii	"header.h"
+	.byte	0
+	.byte	1
+	.byte	0xfe, 0xa7, 0xbb, 0x1f
+	.byte	0x22, 0xc4, 0x7f, 0x12
+	.byte	0x9e, 0x15, 0x69, 0x5f
+	.byte	0x71, 0x37, 0xa1, 0xe7
+.Lprologue_end0:
+.Ldebug_line_end0:
+	.section	.debug_addr,"", at progbits
+	.long	.Ldebug_addr_end0-.Ldebug_addr_start0 # Length of contribution
+.Ldebug_addr_start0:
+	.short	5                               # DWARF version number
+	.byte	8                               # Address size
+	.byte	0                               # Segment selector size
+.Laddr_table_base0:
+	.quad	fooint
+	.quad	.Lfunc_begin0
+.Ldebug_addr_end0:
+	.ident	"clang version 18.0.0"
+	.section	".note.GNU-stack","", at progbits
+	.addrsig
+	.section	.debug_line,"", at progbits
+.Lline_table_start0:
diff --git a/bolt/test/X86/Inputs/dwarf5-df-types-dup-main.s b/bolt/test/X86/Inputs/dwarf5-df-types-dup-main.s
new file mode 100644
index 000000000000000..d991094cf0a0818
--- /dev/null
+++ b/bolt/test/X86/Inputs/dwarf5-df-types-dup-main.s
@@ -0,0 +1,498 @@
+# clang++ -gsplit-dwarf -g2 -gdwarf-5 -gpubnames -fdebug-types-section -fdebug-compilation-dir='.'
+# header.h
+# struct Foo2a {
+#   char *c1;
+#   char *c2;
+#   char *c3;
+# };
+
+# main.cpp
+# #include "header.h"
+# struct Foo2 {
+#  char *c1;
+# };
+# int main(int argc, char *argv[]) {
+#  Foo2 f2;
+#  Foo2a f3;
+#  return 0;
+# }
+	.text
+	.file	"main.cpp"
+	.globl	main                            # -- Begin function main
+	.p2align	4, 0x90
+	.type	main, at function
+main:                                   # @main
+.Lfunc_begin0:
+	.file	0 "." "main.cpp" md5 0x9c5cea5bb78d3fc265cd175110bfe903
+	.loc	0 5 0                           # main.cpp:5:0
+	.cfi_startproc
+# %bb.0:                                # %entry
+	pushq	%rbp
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+	.cfi_def_cfa_register %rbp
+	movl	$0, -4(%rbp)
+	movl	%edi, -8(%rbp)
+	movq	%rsi, -16(%rbp)
+.Ltmp0:
+	.loc	0 8 2 prologue_end              # main.cpp:8:2
+	xorl	%eax, %eax
+	.loc	0 8 2 epilogue_begin is_stmt 0  # main.cpp:8:2
+	popq	%rbp
+	.cfi_def_cfa %rsp, 8
+	retq
+.Ltmp1:
+.Lfunc_end0:
+	.size	main, .Lfunc_end0-main
+	.cfi_endproc
+                                        # -- End function
+	.section	.debug_info.dwo,"e", at progbits
+	.long	.Ldebug_info_dwo_end0-.Ldebug_info_dwo_start0 # Length of Unit
+.Ldebug_info_dwo_start0:
+	.short	5                               # DWARF version number
+	.byte	6                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	5322170643381124694             # Type Signature
+	.long	31                              # Type DIE Offset
+	.byte	1                               # Abbrev [1] 0x18:0x21 DW_TAG_type_unit
+	.short	33                              # DW_AT_language
+	.long	0                               # DW_AT_stmt_list
+	.byte	2                               # Abbrev [2] 0x1f:0x10 DW_TAG_structure_type
+	.byte	5                               # DW_AT_calling_convention
+	.byte	7                               # DW_AT_name
+	.byte	8                               # DW_AT_byte_size
+	.byte	0                               # DW_AT_decl_file
+	.byte	2                               # DW_AT_decl_line
+	.byte	3                               # Abbrev [3] 0x25:0x9 DW_TAG_member
+	.byte	6                               # DW_AT_name
+	.long	47                              # DW_AT_type
+	.byte	0                               # DW_AT_decl_file
+	.byte	3                               # DW_AT_decl_line
+	.byte	0                               # DW_AT_data_member_location
+	.byte	0                               # End Of Children Mark
+	.byte	4                               # Abbrev [4] 0x2f:0x5 DW_TAG_pointer_type
+	.long	52                              # DW_AT_type
+	.byte	5                               # Abbrev [5] 0x34:0x4 DW_TAG_base_type
+	.byte	4                               # DW_AT_name
+	.byte	6                               # DW_AT_encoding
+	.byte	1                               # DW_AT_byte_size
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end0:
+	.long	.Ldebug_info_dwo_end1-.Ldebug_info_dwo_start1 # Length of Unit
+.Ldebug_info_dwo_start1:
+	.short	5                               # DWARF version number
+	.byte	6                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	1175092228111723119             # Type Signature
+	.long	31                              # Type DIE Offset
+	.byte	1                               # Abbrev [1] 0x18:0x33 DW_TAG_type_unit
+	.short	33                              # DW_AT_language
+	.long	0                               # DW_AT_stmt_list
+	.byte	2                               # Abbrev [2] 0x1f:0x22 DW_TAG_structure_type
+	.byte	5                               # DW_AT_calling_convention
+	.byte	11                              # DW_AT_name
+	.byte	24                              # DW_AT_byte_size
+	.byte	1                               # DW_AT_decl_file
+	.byte	1                               # DW_AT_decl_line
+	.byte	3                               # Abbrev [3] 0x25:0x9 DW_TAG_member
+	.byte	6                               # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	2                               # DW_AT_decl_line
+	.byte	0                               # DW_AT_data_member_location
+	.byte	3                               # Abbrev [3] 0x2e:0x9 DW_TAG_member
+	.byte	9                               # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	3                               # DW_AT_decl_line
+	.byte	8                               # DW_AT_data_member_location
+	.byte	3                               # Abbrev [3] 0x37:0x9 DW_TAG_member
+	.byte	10                              # DW_AT_name
+	.long	65                              # DW_AT_type
+	.byte	1                               # DW_AT_decl_file
+	.byte	4                               # DW_AT_decl_line
+	.byte	16                              # DW_AT_data_member_location
+	.byte	0                               # End Of Children Mark
+	.byte	4                               # Abbrev [4] 0x41:0x5 DW_TAG_pointer_type
+	.long	70                              # DW_AT_type
+	.byte	5                               # Abbrev [5] 0x46:0x4 DW_TAG_base_type
+	.byte	4                               # DW_AT_name
+	.byte	6                               # DW_AT_encoding
+	.byte	1                               # DW_AT_byte_size
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end1:
+	.section	.debug_abbrev,"", at progbits
+	.byte	1                               # Abbreviation Code
+	.byte	74                              # DW_TAG_skeleton_unit
+	.byte	0                               # DW_CHILDREN_no
+	.byte	16                              # DW_AT_stmt_list
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	114                             # DW_AT_str_offsets_base
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	27                              # DW_AT_comp_dir
+	.byte	37                              # DW_FORM_strx1
+	.byte	118                             # DW_AT_dwo_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	17                              # DW_AT_low_pc
+	.byte	27                              # DW_FORM_addrx
+	.byte	18                              # DW_AT_high_pc
+	.byte	6                               # DW_FORM_data4
+	.byte	115                             # DW_AT_addr_base
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	0                               # EOM(3)
+	.section	.debug_info,"", at progbits
+.Lcu_begin0:
+	.long	.Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+	.short	5                               # DWARF version number
+	.byte	4                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	.debug_abbrev                   # Offset Into Abbrev. Section
+	.quad	5962099678818150071
+	.byte	1                               # Abbrev [1] 0x14:0x14 DW_TAG_skeleton_unit
+	.long	.Lline_table_start0             # DW_AT_stmt_list
+	.long	.Lstr_offsets_base0             # DW_AT_str_offsets_base
+	.byte	0                               # DW_AT_comp_dir
+	.byte	1                               # DW_AT_dwo_name
+	.byte	0                               # DW_AT_low_pc
+	.long	.Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+	.long	.Laddr_table_base0              # DW_AT_addr_base
+.Ldebug_info_end0:
+	.section	.debug_str_offsets,"", at progbits
+	.long	12                              # Length of String Offsets Set
+	.short	5
+	.short	0
+.Lstr_offsets_base0:
+	.section	.debug_str,"MS", at progbits,1
+.Lskel_string0:
+	.asciz	"."                             # string offset=0
+.Lskel_string1:
+	.asciz	"main.dwo"                      # string offset=2
+	.section	.debug_str_offsets,"", at progbits
+	.long	.Lskel_string0
+	.long	.Lskel_string1
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	64                              # Length of String Offsets Set
+	.short	5
+	.short	0
+	.section	.debug_str.dwo,"eMS", at progbits,1
+.Linfo_string0:
+	.asciz	"main"                          # string offset=0
+.Linfo_string1:
+	.asciz	"int"                           # string offset=5
+.Linfo_string2:
+	.asciz	"argc"                          # string offset=9
+.Linfo_string3:
+	.asciz	"argv"                          # string offset=14
+.Linfo_string4:
+	.asciz	"char"                          # string offset=19
+.Linfo_string5:
+	.asciz	"f2"                            # string offset=24
+.Linfo_string6:
+	.asciz	"c1"                            # string offset=27
+.Linfo_string7:
+	.asciz	"Foo2"                          # string offset=30
+.Linfo_string8:
+	.asciz	"f3"                            # string offset=35
+.Linfo_string9:
+	.asciz	"c2"                            # string offset=38
+.Linfo_string10:
+	.asciz	"c3"                            # string offset=41
+.Linfo_string11:
+	.asciz	"Foo2a"                         # string offset=44
+.Linfo_string12:
+	.asciz	"clang version 18.0.0"          # string offset=50
+.Linfo_string13:
+	.asciz	"main.cpp"                      # string offset=71
+.Linfo_string14:
+	.asciz	"main.dwo"                      # string offset=80
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	0
+	.long	5
+	.long	9
+	.long	14
+	.long	19
+	.long	24
+	.long	27
+	.long	30
+	.long	35
+	.long	38
+	.long	41
+	.long	44
+	.long	50
+	.long	71
+	.long	80
+	.section	.debug_info.dwo,"e", at progbits
+	.long	.Ldebug_info_dwo_end2-.Ldebug_info_dwo_start2 # Length of Unit
+.Ldebug_info_dwo_start2:
+	.short	5                               # DWARF version number
+	.byte	5                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	5962099678818150071
+	.byte	6                               # Abbrev [6] 0x14:0x67 DW_TAG_compile_unit
+	.byte	12                              # DW_AT_producer
+	.short	33                              # DW_AT_language
+	.byte	13                              # DW_AT_name
+	.byte	14                              # DW_AT_dwo_name
+	.byte	7                               # Abbrev [7] 0x1a:0x3c DW_TAG_subprogram
+	.byte	0                               # DW_AT_low_pc
+	.long	.Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+	.byte	1                               # DW_AT_frame_base
+	.byte	86
+	.byte	0                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	5                               # DW_AT_decl_line
+	.long	86                              # DW_AT_type
+                                        # DW_AT_external
+	.byte	8                               # Abbrev [8] 0x29:0xb DW_TAG_formal_parameter
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	120
+	.byte	2                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	5                               # DW_AT_decl_line
+	.long	86                              # DW_AT_type
+	.byte	8                               # Abbrev [8] 0x34:0xb DW_TAG_formal_parameter
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	112
+	.byte	3                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	5                               # DW_AT_decl_line
+	.long	90                              # DW_AT_type
+	.byte	9                               # Abbrev [9] 0x3f:0xb DW_TAG_variable
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	104
+	.byte	5                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	6                               # DW_AT_decl_line
+	.long	104                             # DW_AT_type
+	.byte	9                               # Abbrev [9] 0x4a:0xb DW_TAG_variable
+	.byte	2                               # DW_AT_location
+	.byte	145
+	.byte	80
+	.byte	8                               # DW_AT_name
+	.byte	0                               # DW_AT_decl_file
+	.byte	7                               # DW_AT_decl_line
+	.long	113                             # DW_AT_type
+	.byte	0                               # End Of Children Mark
+	.byte	5                               # Abbrev [5] 0x56:0x4 DW_TAG_base_type
+	.byte	1                               # DW_AT_name
+	.byte	5                               # DW_AT_encoding
+	.byte	4                               # DW_AT_byte_size
+	.byte	4                               # Abbrev [4] 0x5a:0x5 DW_TAG_pointer_type
+	.long	95                              # DW_AT_type
+	.byte	4                               # Abbrev [4] 0x5f:0x5 DW_TAG_pointer_type
+	.long	100                             # DW_AT_type
+	.byte	5                               # Abbrev [5] 0x64:0x4 DW_TAG_base_type
+	.byte	4                               # DW_AT_name
+	.byte	6                               # DW_AT_encoding
+	.byte	1                               # DW_AT_byte_size
+	.byte	10                              # Abbrev [10] 0x68:0x9 DW_TAG_structure_type
+                                        # DW_AT_declaration
+	.quad	5322170643381124694             # DW_AT_signature
+	.byte	10                              # Abbrev [10] 0x71:0x9 DW_TAG_structure_type
+                                        # DW_AT_declaration
+	.quad	1175092228111723119             # DW_AT_signature
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_dwo_end2:
+	.section	.debug_abbrev.dwo,"e", at progbits
+	.byte	1                               # Abbreviation Code
+	.byte	65                              # DW_TAG_type_unit
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	19                              # DW_AT_language
+	.byte	5                               # DW_FORM_data2
+	.byte	16                              # DW_AT_stmt_list
+	.byte	23                              # DW_FORM_sec_offset
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	2                               # Abbreviation Code
+	.byte	19                              # DW_TAG_structure_type
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	54                              # DW_AT_calling_convention
+	.byte	11                              # DW_FORM_data1
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	3                               # Abbreviation Code
+	.byte	13                              # DW_TAG_member
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	56                              # DW_AT_data_member_location
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	4                               # Abbreviation Code
+	.byte	15                              # DW_TAG_pointer_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	5                               # Abbreviation Code
+	.byte	36                              # DW_TAG_base_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	62                              # DW_AT_encoding
+	.byte	11                              # DW_FORM_data1
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	6                               # Abbreviation Code
+	.byte	17                              # DW_TAG_compile_unit
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	37                              # DW_AT_producer
+	.byte	37                              # DW_FORM_strx1
+	.byte	19                              # DW_AT_language
+	.byte	5                               # DW_FORM_data2
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	118                             # DW_AT_dwo_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	7                               # Abbreviation Code
+	.byte	46                              # DW_TAG_subprogram
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	17                              # DW_AT_low_pc
+	.byte	27                              # DW_FORM_addrx
+	.byte	18                              # DW_AT_high_pc
+	.byte	6                               # DW_FORM_data4
+	.byte	64                              # DW_AT_frame_base
+	.byte	24                              # DW_FORM_exprloc
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	63                              # DW_AT_external
+	.byte	25                              # DW_FORM_flag_present
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	8                               # Abbreviation Code
+	.byte	5                               # DW_TAG_formal_parameter
+	.byte	0                               # DW_CHILDREN_no
+	.byte	2                               # DW_AT_location
+	.byte	24                              # DW_FORM_exprloc
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	9                               # Abbreviation Code
+	.byte	52                              # DW_TAG_variable
+	.byte	0                               # DW_CHILDREN_no
+	.byte	2                               # DW_AT_location
+	.byte	24                              # DW_FORM_exprloc
+	.byte	3                               # DW_AT_name
+	.byte	37                              # DW_FORM_strx1
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	10                              # Abbreviation Code
+	.byte	19                              # DW_TAG_structure_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	60                              # DW_AT_declaration
+	.byte	25                              # DW_FORM_flag_present
+	.byte	105                             # DW_AT_signature
+	.byte	32                              # DW_FORM_ref_sig8
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	0                               # EOM(3)
+	.section	.debug_line.dwo,"e", at progbits
+.Ltmp2:
+	.long	.Ldebug_line_end0-.Ldebug_line_start0 # unit length
+.Ldebug_line_start0:
+	.short	5
+	.byte	8
+	.byte	0
+	.long	.Lprologue_end0-.Lprologue_start0
+.Lprologue_start0:
+	.byte	1
+	.byte	1
+	.byte	1
+	.byte	-5
+	.byte	14
+	.byte	1
+	.byte	1
+	.byte	1
+	.byte	8
+	.byte	2
+	.byte	46
+	.byte	0
+	.byte	46
+	.byte	0
+	.byte	3
+	.byte	1
+	.byte	8
+	.byte	2
+	.byte	15
+	.byte	5
+	.byte	30
+	.byte	2
+	.ascii	"main.cpp"
+	.byte	0
+	.byte	0
+	.byte	0x9c, 0x5c, 0xea, 0x5b
+	.byte	0xb7, 0x8d, 0x3f, 0xc2
+	.byte	0x65, 0xcd, 0x17, 0x51
+	.byte	0x10, 0xbf, 0xe9, 0x03
+	.ascii	"header.h"
+	.byte	0
+	.byte	1
+	.byte	0xfe, 0xa7, 0xbb, 0x1f
+	.byte	0x22, 0xc4, 0x7f, 0x12
+	.byte	0x9e, 0x15, 0x69, 0x5f
+	.byte	0x71, 0x37, 0xa1, 0xe7
+.Lprologue_end0:
+.Ldebug_line_end0:
+	.section	.debug_addr,"", at progbits
+	.long	.Ldebug_addr_end0-.Ldebug_addr_start0 # Length of contribution
+.Ldebug_addr_start0:
+	.short	5                               # DWARF version number
+	.byte	8                               # Address size
+	.byte	0                               # Segment selector size
+.Laddr_table_base0:
+	.quad	.Lfunc_begin0
+.Ldebug_addr_end0:
+	.ident	"clang version 18.0.0"
+	.section	".note.GNU-stack","", at progbits
+	.addrsig
+	.section	.debug_line,"", at progbits
+.Lline_table_start0:
diff --git a/bolt/test/X86/dwarf5-df-types-dup-dwp-input.test b/bolt/test/X86/dwarf5-df-types-dup-dwp-input.test
new file mode 100644
index 000000000000000..036d4c9168ee5aa
--- /dev/null
+++ b/bolt/test/X86/dwarf5-df-types-dup-dwp-input.test
@@ -0,0 +1,29 @@
+; RUN: rm -rf %t
+; RUN: mkdir %t
+; RUN: cd %t
+; RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-df-types-dup-main.s \
+; RUN: -split-dwarf-file=main.dwo -o main.o
+; RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-df-types-dup-helper.s \
+; RUN: -split-dwarf-file=helper.dwo -o helper.o
+; RUN: %clang %cflags -gdwarf-5 -gsplit-dwarf=split main.o helper.o -o main.exe
+; RUN: llvm-dwp -e main.exe -o main.exe.dwp
+; RUN: llvm-bolt main.exe -o main.exe.bolt --update-debug-sections
+; RUN: llvm-dwarfdump --debug-info -r 0 main.dwo.dwo | FileCheck -check-prefix=BOLT-DWO-DWO-MAIN %s
+; RUN: llvm-dwarfdump --debug-info -r 0 helper.dwo.dwo | FileCheck -check-prefix=BOLT-DWO-DWO-HELPER %s
+
+; Tests that BOLT correctly handles DWARF5 DWP file as input. Output has correct CU, and all the type units are written out.
+
+; BOLT-DWO-DWO-MAIN: debug_info.dwo
+; BOLT-DWO-DWO-MAIN-NEXT: type_signature = 0x49dc260088be7e56
+; BOLT-DWO-DWO-MAIN: type_signature = 0x104ec427d2ebea6f
+; BOLT-DWO-DWO-MAIN: type_signature = 0xca1e65a66d92b970
+; BOLT-DWO-DWO-MAIN: Compile Unit
+; BOLT-DWO-DWO-MAIN-SAME: DWO_id = 0x52bda211bf6d26b7
+; BOLT-DWO-DWO-MAIN-NOT: Compile Unit
+; BOLT-DWO-DWO-HELPER: debug_info.dwo
+; BOLT-DWO-DWO-HELPER-NEXT: type_signature = 0x49dc260088be7e56
+; BOLT-DWO-DWO-HELPER: type_signature = 0x104ec427d2ebea6f
+; BOLT-DWO-DWO-HELPER: type_signature = 0xca1e65a66d92b970
+; BOLT-DWO-DWO-HELPER: Compile Unit
+; BOLT-DWO-DWO-HELPER-SAME: DWO_id = 0x1dbb67285a49634c
+; BOLT-DWO-DWO-HELPER-NOT: Compile Unit



More information about the lldb-commits mailing list