[DWARFv5] llvm-mc support for new unit header.

[probinson]

Summary

This is for running the assembler with -g (to emit DWARF describing the assembler source).

[aprantl]

Thanks, this looks good.

llvm/trunk/lib/MC/MCDwarf.cpp

static void EmitGenDwarfInfo(MCStreamer *MCOS,
   // The 4 byte total length of the information for this compilation unit, not
   // including these 4 bytes.
   const MCExpr *Length = MakeStartMinusEndExpr(*MCOS, *InfoStart, *InfoEnd, 4);
   emitAbsValue(*MCOS, Length, 4);
 
   // The 2 byte DWARF version.
   MCOS->EmitIntValue(context.getDwarfVersion(), 2);
 
+  // The DWARF v5 header has unit type, address size, abbrev offset.
+  // Earlier versions have abbrev offset, address size.
   const MCAsmInfo &AsmInfo = *context.getAsmInfo();
+  int AddrSize = AsmInfo.getPointerSize();
+  if (context.getDwarfVersion() >= 5) {
+    MCOS->EmitIntValue(dwarf::DW_UT_compile, 1);
+    MCOS->EmitIntValue(AddrSize, 1);
+  }
   // The 4 byte offset to the debug abbrevs from the start of the .debug_abbrev,
   // it is at the start of that section so this is zero.
   if (AbbrevSectionSymbol == nullptr)
     MCOS->EmitIntValue(0, 4);
   else
     MCOS->EmitSymbolValue(AbbrevSectionSymbol, 4,
                           AsmInfo.needsDwarfSectionOffsetDirective());
-
-  const MCAsmInfo *asmInfo = context.getAsmInfo();
-  int AddrSize = asmInfo->getPointerSize();
-  // The 1 byte size of an address.
+  if (context.getDwarfVersion() <= 4)
     MCOS->EmitIntValue(AddrSize, 1);
 
   // Second part: the compile_unit DIE.
 
   // The DW_TAG_compile_unit DIE abbrev (1).
   MCOS->EmitULEB128IntValue(1);
 
   // DW_AT_stmt_list, a 4 byte offset from the start of the .debug_line section,
   // which is at the start of that section so this is zero.

llvm/trunk/test/MC/ARM/dwarf-asm-multiple-sections.s

+// RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 5 -fdebug-compilation-dir=/tmp
+// RUN: llvm-dwarfdump %t | FileCheck -check-prefix DWARF -check-prefix DWARF45 %s
+// RUN: llvm-objdump -r %t | FileCheck -check-prefix RELOC -check-prefix RELOC5 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -fdebug-compilation-dir=/tmp
-// RUN: llvm-dwarfdump %t | FileCheck -check-prefix DWARF -check-prefix DWARF4 %s
-// RUN: llvm-objdump -r %t | FileCheck -check-prefix RELOC %s
+// RUN: llvm-dwarfdump %t | FileCheck -check-prefix DWARF -check-prefix DWARF45 %s
+// RUN: llvm-objdump -r %t | FileCheck -check-prefix RELOC -check-prefix RELOC4 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 3 -fdebug-compilation-dir=/tmp
 // RUN: llvm-dwarfdump %t | FileCheck -check-prefix DWARF -check-prefix DWARF3 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 2 2>&1 | FileCheck -check-prefix VERSION %s
 // RUN: not llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 1 2>&1 | FileCheck -check-prefix DWARF1 %s
-// RUN: not llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 5 2>&1 | FileCheck -check-prefix DWARF5 %s
+// RUN: not llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 6 2>&1 | FileCheck -check-prefix DWARF6 %s
   .section .text, "ax"
 a:
   mov r0, r0
 
   .section foo, "ax"
 b:
   mov r1, r1
 
 // DWARF: .debug_abbrev contents:
 // DWARF: Abbrev table for offset: 0x00000000
 // DWARF: [1] DW_TAG_compile_unit DW_CHILDREN_yes
 // DWARF3:        DW_AT_stmt_list DW_FORM_data4
-// DWARF4:        DW_AT_stmt_list DW_FORM_sec_offset
+// DWARF45:       DW_AT_stmt_list DW_FORM_sec_offset
 // DWARF3:        DW_AT_ranges    DW_FORM_data4
-// DWARF4:        DW_AT_ranges    DW_FORM_sec_offset
+// DWARF45:       DW_AT_ranges    DW_FORM_sec_offset
 // DWARF:         DW_AT_name      DW_FORM_string
 // DWARF:         DW_AT_comp_dir  DW_FORM_string
 // DWARF:         DW_AT_producer  DW_FORM_string
 // DWARF:         DW_AT_language  DW_FORM_data2
 
 // DWARF: .debug_info contents:
 // DWARF: 0x{{[0-9a-f]+}}: DW_TAG_compile_unit [1]
 // DWARF-NOT: DW_TAG_
-// DWARF3: DW_AT_ranges [DW_FORM_data4]           (0x00000000
-// DWARF4: DW_AT_ranges [DW_FORM_sec_offset]      (0x00000000
+// DWARF3:  DW_AT_ranges [DW_FORM_data4]           (0x00000000
+// DWARF45: DW_AT_ranges [DW_FORM_sec_offset]      (0x00000000
 
 // DWARF: 0x{{[0-9a-f]+}}:   DW_TAG_label [2] *
 // DWARF-NEXT: DW_AT_name [DW_FORM_string]     ("a")
 
 // DWARF: 0x{{[0-9a-f]+}}:   DW_TAG_label [2] *
 // DWARF-NEXT: DW_AT_name [DW_FORM_string]     ("b")
 
 
 // DWARF: .debug_aranges contents:
 // DWARF-NEXT: Address Range Header: length = 0x00000024, version = 0x0002, cu_offset = 0x00000000, addr_size = 0x04, seg_size = 0x00
 // DWARF-NEXT: [0x00000000 - 0x00000004)
 // DWARF-NEXT: [0x00000000 - 0x00000004)
 
 
 // DWARF: .debug_line contents:
-// DWARF:      0x0000000000000000     11      0      1   0   0  is_stmt
-// DWARF-NEXT: 0x0000000000000004     11      0      1   0   0  is_stmt end_sequence
-// DWARF-NEXT: 0x0000000000000000     15      0      1   0   0  is_stmt
-// DWARF-NEXT: 0x0000000000000004     15      0      1   0   0  is_stmt end_sequence
+// DWARF:      0x0000000000000000     14      0      1   0   0  is_stmt
+// DWARF-NEXT: 0x0000000000000004     14      0      1   0   0  is_stmt end_sequence
+// DWARF-NEXT: 0x0000000000000000     18      0      1   0   0  is_stmt
+// DWARF-NEXT: 0x0000000000000004     18      0      1   0   0  is_stmt end_sequence
 
 
 // DWARF: .debug_ranges contents:
 // DWARF: 00000000 ffffffff 00000000
 // DWARF: 00000000 00000000 00000004
 // DWARF: 00000000 ffffffff 00000000
 // DWARF: 00000000 00000000 00000004
 // DWARF: 00000000 <End of list>
 
 
 
+// Offsets are different in DWARF v5 due to different header layout.
 // RELOC: RELOCATION RECORDS FOR [.rel.debug_info]:
-// RELOC-NEXT: 00000006 R_ARM_ABS32 .debug_abbrev
-// RELOC-NEXT: 0000000c R_ARM_ABS32 .debug_line
-// RELOC-NEXT: 00000010 R_ARM_ABS32 .debug_ranges
+// RELOC4-NEXT: 00000006 R_ARM_ABS32 .debug_abbrev
+// RELOC4-NEXT: 0000000c R_ARM_ABS32 .debug_line
+// RELOC4-NEXT: 00000010 R_ARM_ABS32 .debug_ranges
+// RELOC5-NEXT: 00000008 R_ARM_ABS32 .debug_abbrev
+// RELOC5-NEXT: 0000000d R_ARM_ABS32 .debug_line
+// RELOC5-NEXT: 00000011 R_ARM_ABS32 .debug_ranges
 // RELOC-NEXT: R_ARM_ABS32 .text
 // RELOC-NEXT: R_ARM_ABS32 foo
 
 // RELOC: RELOCATION RECORDS FOR [.rel.debug_ranges]:
 // RELOC-NEXT: 00000004 R_ARM_ABS32 .text
 // RELOC-NEXT: 00000014 R_ARM_ABS32 foo
 
 // RELOC: RELOCATION RECORDS FOR [.rel.debug_aranges]:
 // RELOC-NEXT: 00000006 R_ARM_ABS32 .debug_info
 // RELOC-NEXT: 00000010 R_ARM_ABS32 .text
 // RELOC-NEXT: 00000018 R_ARM_ABS32 foo
 
 
 // VERSION: {{.*}} warning: DWARF2 only supports one section per compilation unit
 
 // DWARF1: Dwarf version 1 is not supported.
-// DWARF5: Dwarf version 5 is not supported.
+// DWARF6: Dwarf version 6 is not supported.

llvm/trunk/test/MC/ELF/gen-dwarf.s

 // RUN: llvm-mc -g -dwarf-version 2 -triple  i686-pc-linux-gnu %s -filetype=obj -o - | llvm-readobj -r | FileCheck %s
 // RUN: not llvm-mc -g -dwarf-version 1  -triple  i686-pc-linux-gnu %s -filetype=asm -o - 2>&1 | FileCheck --check-prefix=DWARF1 %s
 // RUN: llvm-mc -g -dwarf-version 2 -triple  i686-pc-linux-gnu %s -filetype=asm -o - | FileCheck --check-prefix=ASM --check-prefix=DWARF2 %s
 // RUN: llvm-mc -g -dwarf-version 3 -triple  i686-pc-linux-gnu %s -filetype=asm -o - | FileCheck --check-prefix=ASM --check-prefix=DWARF3 %s
 // RUN: llvm-mc -g -triple  i686-pc-linux-gnu %s -filetype=asm -o - | FileCheck --check-prefix=ASM --check-prefix=DWARF4 %s
-// RUN: not llvm-mc -g -dwarf-version 5  -triple  i686-pc-linux-gnu %s -filetype=asm -o - 2>&1 | FileCheck --check-prefix=DWARF5 %s
+// RUN: llvm-mc -g -dwarf-version 5  -triple  i686-pc-linux-gnu %s -filetype=asm -o - 2>&1 | FileCheck --check-prefix=DWARF5 %s
+// RUN: not llvm-mc -g -dwarf-version 6  -triple  i686-pc-linux-gnu %s -filetype=asm -o - 2>&1 | FileCheck --check-prefix=DWARF6 %s
 
 
 // Test that on ELF:
 // 1. the debug info has a relocation to debug_abbrev and one to to debug_line.
 // 2. the debug_aranges has relocations to text and debug_line.
 
 
     .text

 // CHECK-NEXT:   }
 // CHECK:      ]
 
 // First instance of the section is just to give it a label for debug_aranges to refer to
 // ASM: .section .debug_info
 
 // ASM: .section .debug_abbrev
 // ASM-NEXT: [[ABBREV_LABEL:.Ltmp[0-9]+]]
+// DWARF5: .section .debug_abbrev
+// DWARF5-NEXT: [[ABBREV_LABEL:.Ltmp[0-9]+]]
 
 // Second instance of the section has the CU
 // ASM: .section .debug_info
 // Dwarf version
 // DWARF2: .short 2
 // DWARF3: .short 3
 // DWARF4: .short 4
 // ASM-NEXT: .long [[ABBREV_LABEL]]
+// DWARF5: .short 5
+// DWARF5-NEXT: .byte 1
+// DWARF5-NEXT: .byte 4
+// DWARF5-NEXT: .long [[ABBREV_LABEL]]
+
 // First .byte 1 is the abbreviation number for the compile_unit abbrev
 // ASM: .byte 1
 // ASM-NEXT: .long [[LINE_LABEL:.L[a-z0-9]+]]
 
 // ASM: .section .debug_line
 // ASM-NEXT: [[LINE_LABEL]]
 
 // DWARF1: Dwarf version 1 is not supported.
-// DWARF5: Dwarf version 5 is not supported.
+// DWARF6: Dwarf version 6 is not supported.

llvm/trunk/tools/llvm-mc/llvm-mc.cpp

int main(int argc, char **argv) {
   MOFI.InitMCObjectFileInfo(TheTriple, PIC, CMModel, Ctx);
 
   if (SaveTempLabels)
     Ctx.setAllowTemporaryLabels(false);
 
   Ctx.setGenDwarfForAssembly(GenDwarfForAssembly);
   // Default to 4 for dwarf version.
   unsigned DwarfVersion = MCOptions.DwarfVersion ? MCOptions.DwarfVersion : 4;
-  if (DwarfVersion < 2 || DwarfVersion > 4) {
+  if (DwarfVersion < 2 || DwarfVersion > 5) {
     errs() << ProgName << ": Dwarf version " << DwarfVersion
            << " is not supported." << '\n';
     return 1;
   }
   Ctx.setDwarfVersion(DwarfVersion);
   if (!DwarfDebugFlags.empty())
     Ctx.setDwarfDebugFlags(StringRef(DwarfDebugFlags));
   if (!DwarfDebugProducer.empty())