Add support for verifying .debug_names in split DWARF for CUs and TUs. (#101775)

This patch fixes .debug_names verification for split DWARF with no type
units. It will print out an error for any name entries where we can't
locate the .dwo file. It finds the non skeleton unit and correctly
figures out the DIE offset in the .dwo file. If the non skeleton unit is
found and yet the skeleton unit has a DWO ID, an error will be emitted
showing we couldn't access the non-skeleton compile unit.

Author: clayborg

llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h

@@ -264,6 +264,9 @@ class DWARFContext : public DIContext {
   DWARFCompileUnit *getDWOCompileUnitForHash(uint64_t Hash);
   DWARFTypeUnit *getTypeUnitForHash(uint16_t Version, uint64_t Hash, bool IsDWO);
 
+  /// Return the DWARF unit that includes an offset (relative to .debug_info).
+  DWARFUnit *getUnitForOffset(uint64_t Offset);
+
   /// Return the compile unit that includes an offset (relative to .debug_info).
   DWARFCompileUnit *getCompileUnitForOffset(uint64_t Offset);
 

llvm/lib/DebugInfo/DWARF/DWARFContext.cpp

@@ -1510,9 +1510,12 @@ DWARFUnitVector &DWARFContext::getDWOUnits(bool Lazy) {
   return State->getDWOUnits(Lazy);
 }
 
+DWARFUnit *DWARFContext::getUnitForOffset(uint64_t Offset) {
+  return State->getNormalUnits().getUnitForOffset(Offset);
+}
+
 DWARFCompileUnit *DWARFContext::getCompileUnitForOffset(uint64_t Offset) {
-  return dyn_cast_or_null<DWARFCompileUnit>(
-      State->getNormalUnits().getUnitForOffset(Offset));
+  return dyn_cast_or_null<DWARFCompileUnit>(getUnitForOffset(Offset));
 }
 
 DWARFCompileUnit *DWARFContext::getCompileUnitForCodeAddress(uint64_t Address) {

llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp

@@ -1626,8 +1626,63 @@ unsigned DWARFVerifier::verifyNameIndexEntries(
       UnitOffset = NI.getCUOffset(*CUIndex);
     if (!UnitOffset)
       continue;
-    uint64_t DIEOffset = *UnitOffset + *EntryOr->getDIEUnitOffset();
-    DWARFDie DIE = DCtx.getDIEForOffset(DIEOffset);
+    // For split DWARF entries we need to make sure we find the non skeleton
+    // DWARF unit that is needed and use that's DWARF unit offset as the
+    // DIE offset to add the DW_IDX_die_offset to.
+    DWARFUnit *DU = DCtx.getUnitForOffset(*UnitOffset);
+    if (DU == nullptr || DU->getOffset() != *UnitOffset) {
+      // If we didn't find a DWARF Unit from the UnitOffset, or if the offset
+      // of the unit doesn't match exactly, report an error.
+      ErrorCategory.Report(
+          "Name Index entry contains invalid CU or TU offset", [&]() {
+            error() << formatv("Name Index @ {0:x}: Entry @ {1:x} contains an "
+                               "invalid CU or TU offset {1:x}.\n",
+                               NI.getUnitOffset(), EntryID, *UnitOffset);
+          });
+      ++NumErrors;
+      continue;
+    }
+    // This function will try to get the non skeleton unit DIE, but if it is
+    // unable to load the .dwo file from the .dwo or .dwp, it will return the
+    // unit DIE of the DWARFUnit in "DU". So we need to check if the DWARFUnit
+    // has a .dwo file, but we couldn't load it.
+
+    // FIXME: Need a follow up patch to fix usage of
+    // DWARFUnit::getNonSkeletonUnitDIE() so that it returns an empty DWARFDie
+    // if the .dwo file isn't available and clean up other uses of this function
+    // call to properly deal with it. It isn't clear that getNonSkeletonUnitDIE
+    // will return the unit DIE of DU if we aren't able to get the .dwo file,
+    // but that is what the function currently does.
+    DWARFDie NonSkeletonUnitDie = DU->getNonSkeletonUnitDIE();
+    if (DU->getDWOId() && DU->getUnitDIE() == NonSkeletonUnitDie) {
+      ErrorCategory.Report("Unable to get load .dwo file", [&]() {
+        error() << formatv("Name Index @ {0:x}: Entry @ {1:x} unable to load "
+                           ".dwo file \"{2}\" for DWARF unit @ {3:x}.\n",
+                           NI.getUnitOffset(), EntryID,
+                           dwarf::toString(DU->getUnitDIE().find(
+                               {DW_AT_dwo_name, DW_AT_GNU_dwo_name})),
+                           *UnitOffset);
+      });
+      ++NumErrors;
+      continue;
+    }
+    DWARFUnit *NonSkeletonUnit = NonSkeletonUnitDie.getDwarfUnit();
+    uint64_t DIEOffset =
+        NonSkeletonUnit->getOffset() + *EntryOr->getDIEUnitOffset();
+    const uint64_t NextUnitOffset = NonSkeletonUnit->getNextUnitOffset();
+    // DIE offsets are relative to the specified CU or TU. Make sure the DIE
+    // offsets is a valid relative offset.
+    if (DIEOffset >= NextUnitOffset) {
+      ErrorCategory.Report("NameIndex relative DIE offset too large", [&]() {
+        error() << formatv("Name Index @ {0:x}: Entry @ {1:x} references a "
+                           "DIE @ {2:x} when CU or TU ends at {3:x}.\n",
+                           NI.getUnitOffset(), EntryID, DIEOffset,
+                           NextUnitOffset);
+      });
+      continue;
+    }
+    DWARFDie DIE = NonSkeletonUnit->getDIEForOffset(DIEOffset);
+
     if (!DIE) {
       ErrorCategory.Report("NameIndex references nonexistent DIE", [&]() {
         error() << formatv("Name Index @ {0:x}: Entry @ {1:x} references a "
@@ -1637,7 +1692,12 @@ unsigned DWARFVerifier::verifyNameIndexEntries(
       ++NumErrors;
       continue;
     }
-    if (DIE.getDwarfUnit()->getOffset() != *UnitOffset) {
+    // Only compare the DIE we found's DWARFUnit offset if the DIE lives in
+    // the DWARFUnit from the DW_IDX_comp_unit or DW_IDX_type_unit. If we are
+    // using split DWARF, then the DIE's DWARFUnit doesn't need to match the
+    // skeleton unit.
+    if (DIE.getDwarfUnit() == DU &&
+        DIE.getDwarfUnit()->getOffset() != *UnitOffset) {
       ErrorCategory.Report("Name index contains mismatched CU of DIE", [&]() {
         error() << formatv(
             "Name Index @ {0:x}: Entry @ {1:x}: mismatched CU of "

llvm/test/tools/llvm-dwarfdump/Inputs/verify_split_dwarf_debug_names_exe.yaml

@@ -0,0 +1,99 @@
+--- !ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+ProgramHeaders:
+  - Type:            PT_PHDR
+    Flags:           [ PF_R ]
+    VAddr:           0x200040
+    Align:           0x8
+    Offset:          0x40
+  - Type:            PT_LOAD
+    Flags:           [ PF_R ]
+    FirstSec:        .eh_frame
+    LastSec:         .eh_frame
+    VAddr:           0x200000
+    Align:           0x1000
+    Offset:          0x0
+  - Type:            PT_LOAD
+    Flags:           [ PF_X, PF_R ]
+    FirstSec:        .text
+    LastSec:         .text
+    VAddr:           0x201160
+    Align:           0x1000
+    Offset:          0x160
+  - Type:            PT_GNU_STACK
+    Flags:           [ PF_W, PF_R ]
+    Align:           0x0
+    Offset:          0x0
+Sections:
+  - Name:            .eh_frame
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+    Address:         0x200120
+    AddressAlign:    0x8
+    Content:         1400000000000000017A5200017810011B0C0708900100001C0000001C000000201000000F00000000410E108602430D064A0C070800000000000000
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address:         0x201160
+    AddressAlign:    0x10
+    Content:         554889E5C745FC0000000031C05DC3
+  - Name:            .debug_abbrev
+    Type:            SHT_PROGBITS
+    AddressAlign:    0x1
+    Content:         014A00101772171B257625111B12067317000000
+  - Name:            .debug_info
+    Type:            SHT_PROGBITS
+    AddressAlign:    0x1
+    Content:         24000000050004080000000048DE180E7C9CA7750100000000080000000001000F00000008000000
+  - Name:            .debug_str_offsets
+    Type:            SHT_PROGBITS
+    AddressAlign:    0x1
+    Content:         0C000000050000000900000000000000
+  - Name:            .debug_names
+    Type:            SHT_PROGBITS
+    AddressAlign:    0x4
+    Content:         8800000005000000010000000000000000000000030000000300000019000000080000004C4C564D30373030000000000100000002000000030000008973880B6A7F9A7C3080880B140000000B0000001000000000000000060000000C0000000113031304190000022E031304190000032403130419000000013900000000021A0000000003350000000000
+  - Name:            .comment
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_MERGE, SHF_STRINGS ]
+    AddressAlign:    0x1
+    EntSize:         0x1
+    Content:         004C696E6B65723A204C4C442031392E302E30202868747470733A2F2F6769746875622E636F6D2F636C6179626F72672F6C6C766D2D70726F6A6563742E67697420353562313431303839356236396438653435313766366132613239373862343134623465636163332900636C616E672076657273696F6E2031392E302E30676974202868747470733A2F2F6769746875622E636F6D2F636C6179626F72672F6C6C766D2D70726F6A6563742E67697420353562313431303839356236396438653435313766366132613239373862343134623465636163332900
+  - Name:            .debug_line
+    Type:            SHT_PROGBITS
+    AddressAlign:    0x1
+    Content:         590000000500080037000000010101FB0E0D00010101010000000100000101011F010000000003011F020F051E0102000000006A7F8D4D5A8D13A0F16154AB8A56B134040000090260112000000000001605030AAE060B2E0202000101
+  - Name:            .debug_line_str
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_MERGE, SHF_STRINGS ]
+    AddressAlign:    0x1
+    EntSize:         0x1
+    Content:         2E006D61696E2E63707000
+Symbols:
+  - Name:            main.cpp
+    Type:            STT_FILE
+    Index:           SHN_ABS
+  - Name:            main
+    Type:            STT_FUNC
+    Section:         .text
+    Binding:         STB_GLOBAL
+    Value:           0x201160
+    Size:            0xF
+DWARF:
+  debug_str:
+    - main.dwo
+    - .
+    - main
+    - int
+    - Foo
+  debug_addr:
+    - Length:          0xC
+      Version:         0x5
+      AddressSize:     0x8
+      Entries:
+        - Address:         0x201160
+...

llvm/test/tools/llvm-dwarfdump/Inputs/verify_split_dwarf_debug_names_main_dwo.yaml

@@ -0,0 +1,37 @@
+--- !ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_REL
+  Machine:         EM_X86_64
+  SectionHeaderStringTable: .strtab
+Sections:
+  - Name:            .debug_str_offsets.dwo
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_EXCLUDE ]
+    AddressAlign:    0x1
+    Content:         24000000050000000000000005000000090000000B0000000D00000011000000810000008A000000
+  - Name:            .debug_str.dwo
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_EXCLUDE, SHF_MERGE, SHF_STRINGS ]
+    AddressAlign:    0x1
+    EntSize:         0x1
+    Content:         6D61696E00696E740066007800466F6F00636C616E672076657273696F6E2031392E302E30676974202868747470733A2F2F6769746875622E636F6D2F636C6179626F72672F6C6C766D2D70726F6A6563742E676974203535623134313038393562363964386534353137663661326132393738623431346234656361633329006D61696E2E637070006D61696E2E64776F00
+  - Name:            .debug_info.dwo
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_EXCLUDE ]
+    AddressAlign:    0x1
+    Content:         46000000050005080000000048DE180E7C9CA77501052100060702000F000000015600000535000000030291780200063900000000040105040505040400010603350000000002000000
+  - Name:            .debug_abbrev.dwo
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_EXCLUDE ]
+    AddressAlign:    0x1
+    Content:         01110125251305032576250000022E01111B1206401803253A0B3B0B49133F190000033400021803253A0B3B0B4913000004240003253E0B0B0B0000051301360B03250B0B3A0B3B0B0000060D00032549133A0B3B0B380B000000
+  - Type:            SectionHeaderTable
+    Sections:
+      - Name:            .strtab
+      - Name:            .debug_str_offsets.dwo
+      - Name:            .debug_str.dwo
+      - Name:            .debug_info.dwo
+      - Name:            .debug_abbrev.dwo
+...

llvm/test/tools/llvm-dwarfdump/X86/debug-names-verify-entries.s

@@ -2,8 +2,8 @@
 
 # CHECK: error: Name Index @ 0x0: Unable to get string associated with name 1.
 # CHECK: error: Name Index @ 0x0: Entry @ 0x73 contains an invalid CU index (47).
-# CHECK: error: Name Index @ 0x0: Entry @ 0x79 references a non-existing DIE @ 0x3fa.
-# CHECK: error: Name Index @ 0x0: Entry @ 0x85: mismatched CU of DIE @ 0x30: index - 0x0; debug_info - 0x1e.
+# CHECK: error: Name Index @ 0x0: Entry @ 0x79 references a DIE @ 0x3fa when CU or TU ends at 0x1e.
+# CHECK: error: Name Index @ 0x0: Entry @ 0x85 references a DIE @ 0x30 when CU or TU ends at 0x1e.
 # CHECK: error: Name Index @ 0x0: Entry @ 0x8b: mismatched Tag of DIE @ 0x17: index - DW_TAG_subprogram; debug_info - DW_TAG_variable.
 # CHECK: error: Name Index @ 0x0: Entry @ 0x91: mismatched Name of DIE @ 0x35: index - foo; debug_info - bar, _Z3bar.
 # CHECK: error: Name Index @ 0x0: Name 2 (foo): Incorrectly terminated entry list.

llvm/test/tools/llvm-dwarfdump/verify_split_dwarf_debug_names.test

@@ -0,0 +1,32 @@
+# Verify we can successfully verify .debug_names with split DWARF.
+#
+# RUN: rm -rf %t1/
+# RUN: mkdir %t1
+# RUN: yaml2obj %p/Inputs/verify_split_dwarf_debug_names_exe.yaml > %t1/a.out
+# RUN: yaml2obj %p/Inputs/verify_split_dwarf_debug_names_main_dwo.yaml > %t1/main.dwo
+# RUN: cd %t1
+# RUN: llvm-dwarfdump --verify %t1/a.out | FileCheck %s
+
+# CHECK: Verifying unit: 1 / 1
+# CHECK: Verifying dwo Units...
+# CHECK: Verifying .debug_line...
+# CHECK: Verifying .debug_str_offsets...
+# CHECK: Verifying .debug_names...
+# CHECK: No errors.
+
+# Now verify if we remove the "main.dwo" file that we get an error letting us
+# know that the .dwo file was not able to be found.
+# RUN: rm %t1/main.dwo
+# RUN: not llvm-dwarfdump --verify %t1/a.out | FileCheck --check-prefix=NODWO %s
+
+# NODWO: Verifying unit: 1 / 1
+# NODWO: Verifying dwo Units...
+# NODWO: Verifying .debug_line...
+# NODWO: Verifying .debug_str_offsets...
+# NODWO: Verifying .debug_names...
+# NODWO: error: Name Index @ 0x0: Entry @ 0x79 unable to load .dwo file "main.dwo" for DWARF unit @ 0x0.
+# NODWO: error: Name Index @ 0x0: Entry @ 0x7f unable to load .dwo file "main.dwo" for DWARF unit @ 0x0.
+# NODWO: error: Name Index @ 0x0: Entry @ 0x85 unable to load .dwo file "main.dwo" for DWARF unit @ 0x0.
+# NODWO: error: Aggregated error counts:
+# NODWO: error: Unable to get load .dwo file occurred 3 time(s).
+# NODWO: Errors detected.