Revert "[DWARF] Create subprogram's DIE in DISubprogram's unit"

[SureYeaah]

Summary

This reverts commit ef0dcb506300dc9644e8000c6028d14214be9d97.

This change is causing a lot of compiler crashes.

[SureYeaah]

I am trying to create a small repro for this that I can share but it would be great if we could revert this asap.

[SureYeaah]

cc: @jmorse

[jmorse]

Sure, please do revert if this is causing a crash.

I'm aware that there's a latent bug hanging around, documented in https://bugs.llvm.org/show_bug.cgi?id=37255 that could be related. (This is speculation right now).

[SureYeaah]

Here's the stacktrace from a crash:

 #0 0x00005568d4c35205 SignalHandler(int) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x5d5e205)
 #1 0x00007f00dfea89a0 __restore_rt (/usr/grte/v4/lib64/libpthread.so.0+0xf9a0)
 #2 0x00005568d2756aa0 llvm::DIE::computeOffsetsAndAbbrevs(llvm::AsmPrinter const*, llvm::DIEAbbrevSet&, unsigned int) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x387faa0)
 #3 0x00005568d2757edc llvm::DIE::computeOffsetsAndAbbrevs(llvm::AsmPrinter const*, llvm::DIEAbbrevSet&, unsigned int) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x3880edc)
 #4 0x00005568d2757edc llvm::DIE::computeOffsetsAndAbbrevs(llvm::AsmPrinter const*, llvm::DIEAbbrevSet&, unsigned int) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x3880edc)
 #5 0x00005568d178ae88 llvm::DwarfFile::computeSizeAndOffsets() (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x28b3e88)
 #6 0x00005568d1788a28 llvm::DwarfDebug::endModule() (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x28b1a28)
 #7 0x00005568d2c9f5f9 llvm::AsmPrinter::doFinalization(llvm::Module&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x3dc85f9)
 #8 0x00005568d1edae12 llvm::FPPassManager::doFinalization(llvm::Module&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x3003e12)
 #9 0x00005568d1b27ac3 llvm::legacy::PassManagerImpl::run(llvm::Module&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2c50ac3)
#10 0x00005568d1b26d20 codegen(llvm::lto::Config const&, llvm::TargetMachine*, std::__u::function<std::__u::unique_ptr<llvm::lto::NativeObjectStream, std::__u::default_delete<llvm::lto::NativeObjectStream> > (unsigned int)>, unsigned int, llvm::Module&, llvm::ModuleSummaryIndex const&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2c4fd20)
#11 0x00005568d1b2514a llvm::lto::thinBackend(llvm::lto::Config const&, unsigned int, std::__u::function<std::__u::unique_ptr<llvm::lto::NativeObjectStream, std::__u::default_delete<llvm::lto::NativeObjectStream> > (unsigned int)>, llvm::Module&, llvm::ModuleSummaryIndex const&, llvm::StringMap<std::__u::unordered_set<unsigned long, std::__u::hash<unsigned long>, std::__u::equal_to<unsigned long>, std::__u::allocator<unsigned long> >, llvm::MallocAllocator> const&, llvm::DenseMap<unsigned long, llvm::GlobalValueSummary*, llvm::DenseMapInfo<unsigned long>, llvm::detail::DenseMapPair<unsigned long, llvm::GlobalValueSummary*> > const&, llvm::MapVector<llvm::StringRef, llvm::BitcodeModule, llvm::DenseMap<llvm::StringRef, unsigned int, llvm::DenseMapInfo<llvm::StringRef>, llvm::detail::DenseMapPair<llvm::StringRef, unsigned int> >, std::__u::vector<std::__u::pair<llvm::StringRef, llvm::BitcodeModule>, std::__u::allocator<std::__u::pair<llvm::StringRef, llvm::BitcodeModule> > > >&, std::__u::vector<unsigned char, std::__u::allocator<unsigned char> > const&)::$_2::operator()(llvm::Module&, llvm::TargetMachine*, std::__u::unique_ptr<llvm::ToolOutputFile, std::__u::default_delete<llvm::ToolOutputFile> >) const (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2c4e14a)
#12 0x00005568d1b24288 llvm::lto::thinBackend(llvm::lto::Config const&, unsigned int, std::__u::function<std::__u::unique_ptr<llvm::lto::NativeObjectStream, std::__u::default_delete<llvm::lto::NativeObjectStream> > (unsigned int)>, llvm::Module&, llvm::ModuleSummaryIndex const&, llvm::StringMap<std::__u::unordered_set<unsigned long, std::__u::hash<unsigned long>, std::__u::equal_to<unsigned long>, std::__u::allocator<unsigned long> >, llvm::MallocAllocator> const&, llvm::DenseMap<unsigned long, llvm::GlobalValueSummary*, llvm::DenseMapInfo<unsigned long>, llvm::detail::DenseMapPair<unsigned long, llvm::GlobalValueSummary*> > const&, llvm::MapVector<llvm::StringRef, llvm::BitcodeModule, llvm::DenseMap<llvm::StringRef, unsigned int, llvm::DenseMapInfo<llvm::StringRef>, llvm::detail::DenseMapPair<llvm::StringRef, unsigned int> >, std::__u::vector<std::__u::pair<llvm::StringRef, llvm::BitcodeModule>, std::__u::allocator<std::__u::pair<llvm::StringRef, llvm::BitcodeModule> > > >&, std::__u::vector<unsigned char, std::__u::allocator<unsigned char> > const&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2c4d288)
#13 0x00005568d1b1e54d clang::EmitBackendOutput(clang::DiagnosticsEngine&, clang::HeaderSearchOptions const&, clang::CodeGenOptions const&, clang::TargetOptions const&, clang::LangOptions const&, llvm::DataLayout const&, llvm::Module*, clang::BackendAction, std::__u::unique_ptr<llvm::raw_pwrite_stream, std::__u::default_delete<llvm::raw_pwrite_stream> >) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2c4754d)
#14 0x00005568d189269e clang::CodeGenAction::ExecuteAction() (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x29bb69e)
#15 0x00005568d19eb395 clang::FrontendAction::Execute() (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2b14395)
#16 0x00005568d19eaa21 clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2b13a21)
#17 0x00005568d19e998c clang::ExecuteCompilerInvocation(clang::CompilerInstance*) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2b1298c)
#18 0x00005568d19dc944 cc1_main(llvm::ArrayRef<char const*>, char const*, void*) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2b05944)
#19 0x00005568d19dbdfd ExecuteCC1Tool(llvm::SmallVectorImpl<char const*>&) (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2b04dfd)
#20 0x00005568d235dcfb main (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x3486cfb)
#21 0x00007f00dfd16bbd __libc_start_main (/usr/grte/v4/lib64/libc.so.6+0x38bbd)
#22 0x00005568d1e25659 _start (third_party/crosstool/v18/llvm_unstable/toolchain/bin/clang+0x2f4e65

[jmorse]

The stack trace is exploding when enumerating child DIEs, so it seems possible that this is running into another scenario where a subprogram is referred to incorrectly across CUs, and that wouldn't be surprising. To state the obvious, we'll need a reproducer to pin down where this is coming from.

[rupprecht]

I can reproduce the issue internally as well, so I can try to reduce something.

Oddly, my initial attempts to build with an release+asserts build makes the crash disappear, so I can't say if it's the same issue as http://llvm.org/PR37255 (which is an assertion failure).

[rupprecht]

While I'm reducing the source, the minimal flags to hit this seem to be clang -g -mllvm -generate-type-units ...

Lots of compilations trigger this crash, so you may not actually need me to reduce anything, you could maybe try compiling any large codebase (clang+llvm probably works) with those flags and find something. I'm reducing https://github.com/abseil/abseil-cpp/blob/master/absl/strings/str_split.cc which is the earliest failure seen.

[jmorse]

Hi,

In D95622#2537549, @rupprecht wrote:

While I'm reducing the source, the minimal flags to hit this seem to be clang -g -mllvm -generate-type-units ...

Ah, generate-type-units is the key, I generate a bunch of assertion failures on a stage2 RelWithDebInfo build and that flag:

Unknown DIE kind
UNREACHABLE executed at /fast/fs/llvm4/llvm/lib/CodeGen/AsmPrinter/DIE.cpp:347!

I'll start digging into that, thanks for the flags.

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.h

DbgEntity *createConcreteEntity(DwarfCompileUnit &TheCU,
                                   LexicalScope &Scope,
                                   const DINode *Node,
                                   const DILocation *Location,
                                   const MCSymbol *Sym = nullptr);
 
   /// Construct a DIE for this abstract scope.
   void constructAbstractSubprogramScopeDIE(DwarfCompileUnit &SrcCU, LexicalScope *Scope);
 
+  /// Construct a DIE for the subprogram definition \p SP and return it.
+  DIE &constructSubprogramDefinitionDIE(const DISubprogram *SP);
+
   /// Construct DIEs for call site entries describing the calls in \p MF.
   void constructCallSiteEntryDIEs(const DISubprogram &SP, DwarfCompileUnit &CU,
                                   DIE &ScopeDIE, const MachineFunction &MF);
 
   template <typename DataT>
   void addAccelNameImpl(const DICompileUnit &CU, AccelTable<DataT> &AppleAccel,
                         StringRef Name, const DIE &Die);
 
public:
   uint16_t getDwarfVersion() const;
 
   /// Returns a suitable DWARF form to represent a section offset, i.e.
   /// * DW_FORM_sec_offset for DWARF version >= 4;
   /// * DW_FORM_data8 for 64-bit DWARFv3;
   /// * DW_FORM_data4 for 32-bit DWARFv3 and DWARFv2.
   dwarf::Form getDwarfSectionOffsetForm() const;
 
-  /// Construct a DIE for the subprogram definition \p SP and return it.
-  DIE &constructSubprogramDefinitionDIE(const DISubprogram *SP);
-
   /// Returns the previous CU that was being updated
   const DwarfCompileUnit *getPrevCU() const { return PrevCU; }
   void setPrevCU(const DwarfCompileUnit *PrevCU) { this->PrevCU = PrevCU; }
 
   /// Returns the entries for the .debug_loc section.
   const DebugLocStream &getDebugLocs() const { return DebugLocs; }
 
   /// Emit an entry for the debug loc section. This can be used to

llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp

 
 DIE *DwarfUnit::getOrCreateContextDIE(const DIScope *Context) {
   if (!Context || isa<DIFile>(Context))
     return &getUnitDie();
   if (auto *T = dyn_cast<DIType>(Context))
     return getOrCreateTypeDIE(T);
   if (auto *NS = dyn_cast<DINamespace>(Context))
     return getOrCreateNameSpace(NS);
-  if (auto *SP = dyn_cast<DISubprogram>(Context)) {
-    // Subprogram definitions should be created in the Unit that they specify,
-    // which might not be "this" unit when type definitions move around under
-    // LTO.
-    assert(SP->isDefinition());
-    return &DD->constructSubprogramDefinitionDIE(SP);
-  }
+  if (auto *SP = dyn_cast<DISubprogram>(Context))
+    return getOrCreateSubprogramDIE(SP);
   if (auto *M = dyn_cast<DIModule>(Context))
     return getOrCreateModule(M);
   return getDIE(Context);
 }
 
 DIE *DwarfUnit::createTypeDIE(const DICompositeType *Ty) {
   auto *Context = Ty->getScope();
   DIE *ContextDIE = getOrCreateContextDIE(Context);

llvm/test/DebugInfo/X86/subprogram-across-cus.ll

-; RUN: llc %s -mtriple=x86_64-unknown-linux-gnu -filetype=obj -o %t
-; RUN: llvm-dwarfdump -verify %t
-; RUN: llvm-dwarfdump -debug-info %t | FileCheck %s
-; RUN: rm %t
-;
-;$ cat -n 1.cpp
-;     1  struct HHH;
-;     2  HHH *zzz;
-;
-;$ cat -n 2.cpp
-;     1  void __attribute__((optnone)) __attribute__((nodebug)) f1()  { }
-;     2
-;     3  struct HHH {
-;     4    template <typename bbb>
-;     5    static int __attribute__((always_inline)) ccc() {
-;     6      f1();
-;     7    }
-;     8  };
-;     9
-;    10  int main() {
-;    11    struct local { };
-;    12    HHH::ccc<local>();
-;    13  }
-;
-; $ clang -flto -O2 -g 1.cpp 2.cpp -o a.out
-;
-; Given this input, LLVM attempts to create a DIE for subprogram "main" in the
-; wrong context. The definition of struct "HHH" is placed in the CU for 1.cpp.
-; While creating the template instance in "HHH", function "ccc" is referenced
-; via the struct local type, and "main" is created in the CU for 1.cpp, which
-; is incorrect.
-;
-; See PR48790 for more discussion and original compile commands.
-;
-; Check that there are no verifier failures, and that the SP for "main" appears
-; in the correct CU.
-; CHECK-LABEL:      DW_TAG_compile_unit
-; CHECK:              DW_AT_name ("1.cpp")
-; CHECK-NOT:          DW_AT_name ("main")
-; CHECK-LABEL:      DW_TAG_compile_unit
-; CHECK:              DW_AT_name ("2.cpp")
-; CHECK:            DW_TAG_subprogram
-; CHECK:              DW_AT_name ("main")
-
-source_filename = "ld-temp.o"
-target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-linux-gnu"
-
-; Function Attrs: noinline norecurse nounwind optnone uwtable mustprogress
-define internal fastcc void @_Z2f1v() unnamed_addr {
-entry:
-  ret void
-}
-
-; Function Attrs: norecurse noreturn nounwind uwtable mustprogress
-define dso_local i32 @main() local_unnamed_addr !dbg !17 {
-entry:
-  tail call fastcc void @_Z2f1v(), !dbg !21
-  unreachable, !dbg !21
-}
-
-!llvm.dbg.cu = !{!0, !9}
-!llvm.ident = !{!10, !10}
-!llvm.module.flags = !{!11, !12, !13, !14, !15, !16}
-
-!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !1, producer: "clang version 12.0.0 ([e-mail]:llvm/llvm-project bc9ab9a5cd6bafc5e1293f3d5d51638f8f5cd26c)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, globals: !3, splitDebugInlining: false, nameTableKind: None)
-!1 = !DIFile(filename: "1.cpp", directory: "/tmp/bees")
-!2 = !{}
-!3 = !{!4}
-!4 = !DIGlobalVariableExpression(var: !5, expr: !DIExpression())
-!5 = distinct !DIGlobalVariable(name: "zzz", scope: !0, file: !1, line: 2, type: !6, isLocal: false, isDefinition: true)
-!6 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !7, size: 64)
-!7 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "HHH", file: !8, line: 3, size: 8, flags: DIFlagTypePassByValue, elements: !2, identifier: "_ZTS3HHH")
-!8 = !DIFile(filename: "2.cpp", directory: "/tmp/bees")
-!9 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !8, producer: "clang version 12.0.0 ([e-mail]:llvm/llvm-project bc9ab9a5cd6bafc5e1293f3d5d51638f8f5cd26c)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, splitDebugInlining: false, nameTableKind: None)
-!10 = !{!"clang version 12.0.0 ([e-mail]:llvm/llvm-project bc9ab9a5cd6bafc5e1293f3d5d51638f8f5cd26c)"}
-!11 = !{i32 7, !"Dwarf Version", i32 4}
-!12 = !{i32 2, !"Debug Info Version", i32 3}
-!13 = !{i32 1, !"wchar_size", i32 4}
-!14 = !{i32 1, !"ThinLTO", i32 0}
-!15 = !{i32 1, !"EnableSplitLTOUnit", i32 1}
-!16 = !{i32 1, !"LTOPostLink", i32 1}
-!17 = distinct !DISubprogram(name: "main", scope: !8, file: !8, line: 10, type: !18, scopeLine: 10, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !9, retainedNodes: !2)
-!18 = !DISubroutineType(types: !19)
-!19 = !{!20}
-!20 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
-!21 = !DILocation(line: 6, column: 5, scope: !22, inlinedAt: !27)
-!22 = distinct !DISubprogram(name: "ccc<local>", linkageName: "_ZN3HHH3cccIZ4mainE5localEEiv", scope: !7, file: !8, line: 5, type: !18, scopeLine: 5, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagLocalToUnit | DISPFlagDefinition | DISPFlagOptimized, unit: !9, templateParams: !24, declaration: !23, retainedNodes: !2)
-!23 = !DISubprogram(name: "ccc<local>", linkageName: "_ZN3HHH3cccIZ4mainE5localEEiv", scope: !7, file: !8, line: 5, type: !18, scopeLine: 5, flags: DIFlagPrototyped | DIFlagStaticMember, spFlags: DISPFlagOptimized, templateParams: !24)
-!24 = !{!25}
-!25 = !DITemplateTypeParameter(name: "bbb", type: !26)
-!26 = !DICompositeType(tag: DW_TAG_structure_type, name: "local", scope: !17, file: !8, line: 11, size: 8, flags: DIFlagFwdDecl)
-!27 = distinct !DILocation(line: 12, column: 3, scope: !17)