[DebugInfo][DWARF] Emit Per-Function Line Table Offsets and End Sequences

Author: Alex B

llvm/include/llvm/BinaryFormat/Dwarf.def

@@ -618,6 +618,7 @@ HANDLE_DW_AT(0x3e08, LLVM_ptrauth_isa_pointer, 0, LLVM)
 HANDLE_DW_AT(0x3e09, LLVM_ptrauth_authenticates_null_values, 0, LLVM)
 HANDLE_DW_AT(0x3e0a, LLVM_ptrauth_authentication_mode, 0, LLVM)
 HANDLE_DW_AT(0x3e0b, LLVM_num_extra_inhabitants, 0, LLVM)
+HANDLE_DW_AT(0x3e0c, LLVM_stmt_sequence, 0, LLVM)
 
 // Apple extensions.
 

llvm/include/llvm/MC/MCDwarf.h

@@ -123,6 +123,9 @@ class MCDwarfLoc {
   friend class MCContext;
   friend class MCDwarfLineEntry;
 
+  // DwarfDebug::endFunctionImpl needs to construct MCDwarfLoc(IsEndOfFunction)
+  friend class DwarfDebug;
+
   MCDwarfLoc(unsigned fileNum, unsigned line, unsigned column, unsigned flags,
              unsigned isa, unsigned discriminator)
       : FileNum(fileNum), Line(line), Column(column), Flags(flags), Isa(isa),
@@ -239,7 +242,7 @@ class MCLineSection {
 
   // Add an end entry by cloning the last entry, if exists, for the section
   // the given EndLabel belongs to. The label is replaced by the given EndLabel.
-  void addEndEntry(MCSymbol *EndLabel);
+  void addEndEntry(MCSymbol *EndLabel, bool generatingFuncLineTableOffsets);
 
   using MCDwarfLineEntryCollection = std::vector<MCDwarfLineEntry>;
   using iterator = MCDwarfLineEntryCollection::iterator;

llvm/include/llvm/MC/MCStreamer.h

@@ -251,6 +251,15 @@ class MCStreamer {
   /// discussion for future inclusion.
   bool AllowAutoPadding = false;
 
+  // Flag specifying weather functions will have an offset into the line table
+  // where the line data for that function starts
+  bool GenerateFuncLineTableOffsets = false;
+
+  // Symbol that tracks the stream symbol for first line of the current function
+  // being generated. This symbol can be used to reference where the line
+  // entries for the function start in the generated line table.
+  MCSymbol *CurrentFuncFirstLineStreamSym;
+
 protected:
   MCFragment *CurFrag = nullptr;
 
@@ -313,6 +322,24 @@ class MCStreamer {
   void setAllowAutoPadding(bool v) { AllowAutoPadding = v; }
   bool getAllowAutoPadding() const { return AllowAutoPadding; }
 
+  void setGenerateFuncLineTableOffsets(bool v) {
+    GenerateFuncLineTableOffsets = v;
+  }
+  bool getGenerateFuncLineTableOffsets() const {
+    return GenerateFuncLineTableOffsets;
+  }
+
+  // Use the below functions to track the symbol that points to the current
+  // function's line info in the output stream.
+  void beginFunction() { CurrentFuncFirstLineStreamSym = nullptr; }
+  void emittedLineStreamSym(MCSymbol *StreamSym) {
+    if (!CurrentFuncFirstLineStreamSym)
+      CurrentFuncFirstLineStreamSym = StreamSym;
+  }
+  MCSymbol *getCurrentFuncFirstLineStreamSym() {
+    return CurrentFuncFirstLineStreamSym;
+  }
+
   /// When emitting an object file, create and emit a real label. When emitting
   /// textual assembly, this should do nothing to avoid polluting our output.
   virtual MCSymbol *emitCFILabel();

llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp

@@ -526,6 +526,14 @@ DIE &DwarfCompileUnit::updateSubprogramScopeDIE(const DISubprogram *SP) {
           *DD->getCurrentFunction()))
     addFlag(*SPDie, dwarf::DW_AT_APPLE_omit_frame_ptr);
 
+  if (Asm->OutStreamer->getGenerateFuncLineTableOffsets() &&
+      Asm->OutStreamer->getCurrentFuncFirstLineStreamSym()) {
+    addSectionLabel(
+        *SPDie, dwarf::DW_AT_LLVM_stmt_sequence,
+        Asm->OutStreamer->getCurrentFuncFirstLineStreamSym(),
+        Asm->getObjFileLowering().getDwarfLineSection()->getBeginSymbol());
+  }
+
   // Only include DW_AT_frame_base in full debug info
   if (!includeMinimalInlineScopes()) {
     const TargetFrameLowering *TFI = Asm->MF->getSubtarget().getFrameLowering();

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

@@ -170,6 +170,12 @@ static cl::opt<DwarfDebug::MinimizeAddrInV5> MinimizeAddrInV5Option(
                           "Stuff")),
     cl::init(DwarfDebug::MinimizeAddrInV5::Default));
 
+static cl::opt<bool> EmitFuncLineTableOffsetsOption(
+    "emit-func-debug-line-table-offsets", cl::Hidden,
+    cl::desc("Include line table offset in function's debug info and emit end "
+             "sequence after each function's line data."),
+    cl::init(false));
+
 static constexpr unsigned ULEB128PadSize = 4;
 
 void DebugLocDwarfExpression::emitOp(uint8_t Op, const char *Comment) {
@@ -441,6 +447,8 @@ DwarfDebug::DwarfDebug(AsmPrinter *A)
   Asm->OutStreamer->getContext().setDwarfVersion(DwarfVersion);
   Asm->OutStreamer->getContext().setDwarfFormat(Dwarf64 ? dwarf::DWARF64
                                                         : dwarf::DWARF32);
+  Asm->OutStreamer->setGenerateFuncLineTableOffsets(
+      EmitFuncLineTableOffsetsOption);
 }
 
 // Define out of line so we don't have to include DwarfUnit.h in DwarfDebug.h.
@@ -2222,6 +2230,10 @@ void DwarfDebug::beginFunctionImpl(const MachineFunction *MF) {
   if (SP->getUnit()->getEmissionKind() == DICompileUnit::NoDebug)
     return;
 
+  // Notify the streamer that we are beginning a function - this will reset the
+  // label pointing to the currently generated function's first line entry
+  Asm->OutStreamer->beginFunction();
+
   DwarfCompileUnit &CU = getOrCreateDwarfCompileUnit(SP->getUnit());
 
   Asm->OutStreamer->getContext().setDwarfCompileUnitID(
@@ -2250,7 +2262,8 @@ void DwarfDebug::terminateLineTable(const DwarfCompileUnit *CU) {
       getDwarfCompileUnitIDForLineTable(*CU));
   // Add the last range label for the given CU.
   LineTable.getMCLineSections().addEndEntry(
-      const_cast<MCSymbol *>(CURanges.back().End));
+      const_cast<MCSymbol *>(CURanges.back().End),
+      EmitFuncLineTableOffsetsOption);
 }
 
 void DwarfDebug::skippedNonDebugFunction() {
@@ -2343,6 +2356,21 @@ void DwarfDebug::endFunctionImpl(const MachineFunction *MF) {
   // Construct call site entries.
   constructCallSiteEntryDIEs(*SP, TheCU, ScopeDIE, *MF);
 
+  // If we're emitting line table offsets, we also need to emit an end label
+  // after all function's line entries
+  if (EmitFuncLineTableOffsetsOption) {
+    MCSymbol *LineSym = Asm->OutStreamer->getContext().createTempSymbol();
+    Asm->OutStreamer->emitLabel(LineSym);
+    MCDwarfLoc DwarfLoc(
+        1, 1, 0, DWARF2_LINE_DEFAULT_IS_STMT ? DWARF2_FLAG_IS_STMT : 0, 0, 0);
+    MCDwarfLineEntry LineEntry(LineSym, DwarfLoc);
+    Asm->OutStreamer->getContext()
+        .getMCDwarfLineTable(
+            Asm->OutStreamer->getContext().getDwarfCompileUnitID())
+        .getMCLineSections()
+        .addLineEntry(LineEntry, Asm->OutStreamer->getCurrentSectionOnly());
+  }
+
   // Clear debug info
   // Ownership of DbgVariables is a bit subtle - ScopeVariables owns all the
   // DbgVariables except those that are also in AbstractVariables (since they

llvm/lib/MC/MCDwarf.cpp

@@ -104,8 +104,17 @@ void MCDwarfLineEntry::make(MCStreamer *MCOS, MCSection *Section) {
   // Get the current .loc info saved in the context.
   const MCDwarfLoc &DwarfLoc = MCOS->getContext().getCurrentDwarfLoc();
 
+  MCSymbol *LineStreamLabel = nullptr;
+  // If functions need offsets into the generated line table, then we need to
+  // create a label referencing where the line was generated in the output
+  // stream
+  if (MCOS->getGenerateFuncLineTableOffsets()) {
+    LineStreamLabel = MCOS->getContext().createTempSymbol();
+    MCOS->emittedLineStreamSym(LineStreamLabel);
+  }
+
   // Create a (local) line entry with the symbol and the current .loc info.
-  MCDwarfLineEntry LineEntry(LineSym, DwarfLoc);
+  MCDwarfLineEntry LineEntry(LineSym, DwarfLoc, LineStreamLabel);
 
   // clear DwarfLocSeen saying the current .loc info is now used.
   MCOS->getContext().clearDwarfLocSeen();
@@ -145,7 +154,8 @@ makeStartPlusIntExpr(MCContext &Ctx, const MCSymbol &Start, int IntVal) {
   return Res;
 }
 
-void MCLineSection::addEndEntry(MCSymbol *EndLabel) {
+void MCLineSection::addEndEntry(MCSymbol *EndLabel,
+                                bool generatingFuncLineTableOffsets) {
   auto *Sec = &EndLabel->getSection();
   // The line table may be empty, which we should skip adding an end entry.
   // There are two cases:
@@ -158,8 +168,12 @@ void MCLineSection::addEndEntry(MCSymbol *EndLabel) {
   if (I != MCLineDivisions.end()) {
     auto &Entries = I->second;
     auto EndEntry = Entries.back();
-    EndEntry.setEndLabel(EndLabel);
-    Entries.push_back(EndEntry);
+    // If generatingFuncLineTableOffsets is set, then we already generated an
+    // end label at the end of the last function, so skip generating another one
+    if (!generatingFuncLineTableOffsets) {
+      EndEntry.setEndLabel(EndLabel);
+      Entries.push_back(EndEntry);
+    }
   }
 }
 

llvm/test/DebugInfo/X86/DW_AT_LLVM_stmt_seq_sec_offset.ll

@@ -0,0 +1,82 @@
+; RUN: llc -mtriple=i686-w64-mingw32 -o %t -filetype=obj %s
+; RUN: llvm-dwarfdump -v -all %t | FileCheck %s -check-prefix=NO_STMT_SEQ
+
+; RUN: llc -mtriple=i686-w64-mingw32 -o %t -filetype=obj %s -emit-func-debug-line-table-offsets
+; RUN: llvm-dwarfdump -v -all %t | FileCheck %s -check-prefix=STMT_SEQ
+
+; NO_STMT_SEQ-NOT:      DW_AT_LLVM_stmt_sequence
+
+; STMT_SEQ:   [[[ABBREV_CODE:[0-9]+]]] DW_TAG_subprogram
+; STMT_SEQ:  	       DW_AT_LLVM_stmt_sequence    DW_FORM_sec_offset
+; STMT_SEQ:   DW_TAG_subprogram [[[ABBREV_CODE]]]
+; STMT_SEQ:       DW_AT_LLVM_stmt_sequence [DW_FORM_sec_offset]	(0x00000028)
+; STMT_SEQ:   DW_AT_name {{.*}}func01
+; STMT_SEQ:   DW_TAG_subprogram [[[ABBREV_CODE]]]
+; STMT_SEQ:       DW_AT_LLVM_stmt_sequence [DW_FORM_sec_offset]	(0x00000033)
+; STMT_SEQ:   DW_AT_name {{.*}}main
+
+;; Check that the line table starts at 0x00000028 (first function)
+; STMT_SEQ:            Address            Line   Column File   ISA Discriminator OpIndex Flags
+; STMT_SEQ-NEXT:       ------------------ ------ ------ ------ --- ------------- ------- -------------
+; STMT_SEQ-NEXT:  0x00000028: 00 DW_LNE_set_address (0x00000006)
+
+;; Check that we have an 'end_sequence' just before the next function (0x00000033)
+; STMT_SEQ:            0x0000000000000006      1      0      1   0             0       0  is_stmt end_sequence
+; STMT_SEQ-NEXT: 0x00000033: 00 DW_LNE_set_address (0x00000027)
+
+;; Check that the end of the line table still has an 'end_sequence'
+; STMT_SEQ       0x00000049: 00 DW_LNE_end_sequence
+; STMT_SEQ-NEXT        0x0000000000000027      6      3      1   0             0       0  end_sequence
+
+
+; generated from:
+; clang -g -S -emit-llvm test.c -o test.ll
+; ======= test.c ======
+; int func01() {
+;   return 1;
+; }
+; int main() {
+;   return 0;
+; }
+; =====================
+
+
+; ModuleID = 'test.c'
+source_filename = "test.c"
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-apple-macosx14.0.0"
+
+; Function Attrs: noinline nounwind optnone ssp uwtable(sync)
+define i32 @func01() #0 !dbg !9 {
+  ret i32 1, !dbg !13
+}
+
+; Function Attrs: noinline nounwind optnone ssp uwtable(sync)
+define i32 @main() #0 !dbg !14 {
+  %1 = alloca i32, align 4
+  store i32 0, ptr %1, align 4
+  ret i32 0, !dbg !15
+}
+
+attributes #0 = { noinline nounwind optnone ssp uwtable(sync) "frame-pointer"="non-leaf" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="apple-m1" "target-features"="+aes,+crc,+dotprod,+fp-armv8,+fp16fml,+fullfp16,+lse,+neon,+ras,+rcpc,+rdm,+sha2,+sha3,+v8.1a,+v8.2a,+v8.3a,+v8.4a,+v8.5a,+v8a,+zcm,+zcz" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2, !3, !4, !5, !6, !7}
+!llvm.ident = !{!8}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C11, file: !1, producer: "Homebrew clang version 17.0.6", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: Apple, sysroot: "/Library/Developer/CommandLineTools/SDKs/MacOSX14.sdk", sdk: "MacOSX14.sdk")
+!1 = !DIFile(filename: "test.c", directory: "/tmp/clang_test")
+!2 = !{i32 7, !"Dwarf Version", i32 4}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = !{i32 1, !"wchar_size", i32 4}
+!5 = !{i32 8, !"PIC Level", i32 2}
+!6 = !{i32 7, !"uwtable", i32 1}
+!7 = !{i32 7, !"frame-pointer", i32 1}
+!8 = !{!"Homebrew clang version 17.0.6"}
+!9 = distinct !DISubprogram(name: "func01", scope: !1, file: !1, line: 1, type: !10, scopeLine: 1, spFlags: DISPFlagDefinition, unit: !0)
+!10 = !DISubroutineType(types: !11)
+!11 = !{!12}
+!12 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!13 = !DILocation(line: 2, column: 3, scope: !9)
+!14 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 5, type: !10, scopeLine: 5, spFlags: DISPFlagDefinition, unit: !0)
+!15 = !DILocation(line: 6, column: 3, scope: !14)