[llvm] 9670a45 - libDebugInfoDWARF: Don't try to parse loclist[.dwo] headers when parsing debug_info[.dwo]

David Blaikie via llvm-commits llvm-commits at lists.llvm.org
Tue Oct 13 22:34:32 PDT 2020


Author: David Blaikie
Date: 2020-10-13T22:28:59-07:00
New Revision: 9670a45c980c371c5ece8047a00b8b2abec73823

URL: https://github.com/llvm/llvm-project/commit/9670a45c980c371c5ece8047a00b8b2abec73823
DIFF: https://github.com/llvm/llvm-project/commit/9670a45c980c371c5ece8047a00b8b2abec73823.diff

LOG: libDebugInfoDWARF: Don't try to parse loclist[.dwo] headers when parsing debug_info[.dwo]

There's no way to know whether there's a loclist contribution to parse
if there's no loclistx encoding - and if there is one, there's no need
to walk back from the loclist_base (or, uin the case of
info.dwo/loclist.dwo - starting at 0 in the contribution) to parse the
header, instead rely on the DWARF32/64 and address size in the CU
that's already available.

This would come up in split DWARF (non-split wouldn't try to read a
loclist header in the absence of a loclist_base) when one unit had
location lists and another does not (because the loclists.dwo section
would be non-empty in that case - in the case where it's empty the
parsing would silently skip).

Simplify the testing a bit, rather than needing a whole dwp, etc - by
creating a malformed loclists.dwo section (and use single file Split
DWARF) that would trip up any attempt to parse it - but no attempt
should be made.

Added: 
    llvm/test/tools/llvm-dwarfdump/X86/debug_loclists_unused_invalid.s

Modified: 
    llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
    llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
index 0b0238f7235e..369cbdc28c2e 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
@@ -209,7 +209,6 @@ class DWARFUnit {
   const DWARFDebugAbbrev *Abbrev;
   const DWARFSection *RangeSection;
   uint64_t RangeSectionBase;
-  const DWARFSection *LocSection;
   uint64_t LocSectionBase;
 
   /// Location table of this unit.
@@ -228,9 +227,6 @@ class DWARFUnit {
   /// offsets table (DWARF v5).
   Optional<StrOffsetsContributionDescriptor> StringOffsetsTableContribution;
 
-  /// A table of range lists (DWARF v5 and later).
-  Optional<DWARFListTableHeader> LoclistTableHeader;
-
   mutable const DWARFAbbreviationDeclarationSet *Abbrevs;
   llvm::Optional<object::SectionedAddress> BaseAddr;
   /// The compile unit debug information entry items.
@@ -318,10 +314,6 @@ class DWARFUnit {
     RangeSection = RS;
     RangeSectionBase = Base;
   }
-  void setLocSection(const DWARFSection *LS, uint64_t Base) {
-    LocSection = LS;
-    LocSectionBase = Base;
-  }
 
   uint64_t getLocSectionBase() const {
     return LocSectionBase;
@@ -418,14 +410,8 @@ class DWARFUnit {
   /// DW_FORM_rnglistx.
   Optional<uint64_t> getRnglistOffset(uint32_t Index);
 
-  Optional<uint64_t> getLoclistOffset(uint32_t Index) {
-    if (!LoclistTableHeader)
-      return None;
-    if (Optional<uint64_t> Off =
-            LoclistTableHeader->getOffsetEntry(LocTable->getData(), Index))
-      return *Off + getLocSectionBase();
-    return None;
-  }
+  Optional<uint64_t> getLoclistOffset(uint32_t Index);
+
   Expected<DWARFAddressRangesVector> collectAddressRanges();
 
   Expected<DWARFLocationExpressionsVector>

diff  --git a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
index 67066db15b4a..ffd7d1e62c94 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
@@ -181,31 +181,6 @@ DWARFUnit::DWARFUnit(DWARFContext &DC, const DWARFSection &Section,
       StringOffsetSection(SOS), AddrOffsetSection(AOS), isLittleEndian(LE),
       IsDWO(IsDWO), UnitVector(UnitVector) {
   clear();
-  if (IsDWO) {
-    // If we are reading a package file, we need to adjust the location list
-    // data based on the index entries.
-    StringRef Data = Header.getVersion() >= 5
-                         ? Context.getDWARFObj().getLoclistsDWOSection().Data
-                         : LocSection->Data;
-    if (auto *IndexEntry = Header.getIndexEntry())
-      if (const auto *C = IndexEntry->getContribution(
-              Header.getVersion() >= 5 ? DW_SECT_LOCLISTS : DW_SECT_EXT_LOC))
-        Data = Data.substr(C->Offset, C->Length);
-
-    DWARFDataExtractor DWARFData(Data, isLittleEndian, getAddressByteSize());
-    LocTable =
-        std::make_unique<DWARFDebugLoclists>(DWARFData, Header.getVersion());
-  } else if (Header.getVersion() >= 5) {
-    LocTable = std::make_unique<DWARFDebugLoclists>(
-        DWARFDataExtractor(Context.getDWARFObj(),
-                           Context.getDWARFObj().getLoclistsSection(),
-                           isLittleEndian, getAddressByteSize()),
-        Header.getVersion());
-  } else {
-    LocTable = std::make_unique<DWARFDebugLoc>(
-        DWARFDataExtractor(Context.getDWARFObj(), *LocSection, isLittleEndian,
-                           getAddressByteSize()));
-  }
 }
 
 DWARFUnit::~DWARFUnit() = default;
@@ -492,8 +467,8 @@ Error DWARFUnit::tryExtractDIEsIfNeeded(bool CUDieOnly) {
   // describe address ranges.
   if (getVersion() >= 5) {
     // In case of DWP, the base offset from the index has to be added.
-    uint64_t ContributionBaseOffset = 0;
     if (IsDWO) {
+      uint64_t ContributionBaseOffset = 0;
       if (auto *IndexEntry = Header.getIndexEntry())
         if (auto *Contrib = IndexEntry->getContribution(DW_SECT_RNGLISTS))
           ContributionBaseOffset = Contrib->Offset;
@@ -506,42 +481,33 @@ Error DWARFUnit::tryExtractDIEsIfNeeded(bool CUDieOnly) {
                        toSectionOffset(UnitDie.find(DW_AT_rnglists_base),
                                        DWARFListTableHeader::getHeaderSize(
                                            Header.getFormat())));
+  }
 
-    // In a split dwarf unit, there is no DW_AT_loclists_base attribute.
-    // Setting LocSectionBase to point past the table header.
-    if (IsDWO) {
-      auto &DWOSection = Context.getDWARFObj().getLoclistsDWOSection();
-      if (DWOSection.Data.empty())
-        return Error::success();
-      setLocSection(&DWOSection,
-                    DWARFListTableHeader::getHeaderSize(Header.getFormat()));
-    } else if (auto X = UnitDie.find(DW_AT_loclists_base)) {
-      setLocSection(&Context.getDWARFObj().getLoclistsSection(),
-                    toSectionOffset(X, 0));
-    } else {
-      return Error::success();
-    }
+  if (IsDWO) {
+    // If we are reading a package file, we need to adjust the location list
+    // data based on the index entries.
+    StringRef Data = Header.getVersion() >= 5
+                         ? Context.getDWARFObj().getLoclistsDWOSection().Data
+                         : Context.getDWARFObj().getLocDWOSection().Data;
+    if (auto *IndexEntry = Header.getIndexEntry())
+      if (const auto *C = IndexEntry->getContribution(
+              Header.getVersion() >= 5 ? DW_SECT_LOCLISTS : DW_SECT_EXT_LOC))
+        Data = Data.substr(C->Offset, C->Length);
 
-    if (LocSection) {
-      if (IsDWO)
-        LoclistTableHeader.emplace(".debug_loclists.dwo", "locations");
-      else
-        LoclistTableHeader.emplace(".debug_loclists", "locations");
-
-      uint64_t HeaderSize = DWARFListTableHeader::getHeaderSize(Header.getFormat());
-      uint64_t Offset = getLocSectionBase();
-      const DWARFDataExtractor &Data = LocTable->getData();
-      if (Offset < HeaderSize)
-        return createStringError(errc::invalid_argument,
-                                 "did not detect a valid"
-                                 " list table with base = 0x%" PRIx64 "\n",
-                                 Offset);
-      Offset -= HeaderSize;
-      if (Error E = LoclistTableHeader->extract(Data, &Offset))
-        return createStringError(errc::invalid_argument,
-                                 "parsing a loclist table: " +
-                                     toString(std::move(E)));
-    }
+    DWARFDataExtractor DWARFData(Data, isLittleEndian, getAddressByteSize());
+    LocTable =
+        std::make_unique<DWARFDebugLoclists>(DWARFData, Header.getVersion());
+    LocSectionBase = DWARFListTableHeader::getHeaderSize(Header.getFormat());
+  } else if (getVersion() >= 5) {
+    LocTable = std::make_unique<DWARFDebugLoclists>(
+        DWARFDataExtractor(Context.getDWARFObj(),
+                           Context.getDWARFObj().getLoclistsSection(),
+                           isLittleEndian, getAddressByteSize()),
+        getVersion());
+  } else {
+    LocTable = std::make_unique<DWARFDebugLoc>(DWARFDataExtractor(
+        Context.getDWARFObj(), Context.getDWARFObj().getLocSection(),
+        isLittleEndian, getAddressByteSize()));
   }
 
   // Don't fall back to DW_AT_GNU_ranges_base: it should be ignored for
@@ -981,3 +947,10 @@ Optional<uint64_t> DWARFUnit::getRnglistOffset(uint32_t Index) {
     return *Off + RangeSectionBase;
   return None;
 }
+
+Optional<uint64_t> DWARFUnit::getLoclistOffset(uint32_t Index) {
+  if (Optional<uint64_t> Off = llvm::DWARFListTableHeader::getOffsetEntry(
+          LocTable->getData(), LocSectionBase, getFormat(), Index))
+    return *Off + LocSectionBase;
+  return None;
+}

diff  --git a/llvm/test/tools/llvm-dwarfdump/X86/debug_loclists_unused_invalid.s b/llvm/test/tools/llvm-dwarfdump/X86/debug_loclists_unused_invalid.s
new file mode 100644
index 000000000000..5a8c9886829d
--- /dev/null
+++ b/llvm/test/tools/llvm-dwarfdump/X86/debug_loclists_unused_invalid.s
@@ -0,0 +1,230 @@
+# REQUIRES: x86-registered-target
+
+# RUN: rm -rf %t
+# RUN: mkdir %t
+# RUN: cd %t
+# RUN: llvm-mc %s -dwarf-version=5 -filetype obj -triple x86_64-pc-linux -o main.o
+# RUN: llvm-dwarfdump main.o 2>&1 | FileCheck %s
+
+# CHECK: .debug_info.dwo contents:
+# CHECK-NEXT: Compile Unit:
+# CHECK-EMPTY:
+# CHECK-NEXT: compile_unit
+
+	.text
+	.file	"main.cpp"
+	.globl	main                            # -- Begin function main
+	.p2align	4, 0x90
+	.type	main, at function
+main:                                   # @main
+.Lfunc_begin0:
+	.file	0 "/usr/local/google/home/blaikie/dev/scratch" "main.cpp" md5 0x277b2d67900f5d0f46c9638ad2528ff1
+	.loc	0 1 0                           # main.cpp:1:0
+	.cfi_startproc
+# %bb.0:                                # %entry
+	pushq	%rbp
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+	.cfi_def_cfa_register %rbp
+	xorl	%eax, %eax
+.Ltmp0:
+	.loc	0 2 1 prologue_end              # main.cpp:2:1
+	popq	%rbp
+	.cfi_def_cfa %rsp, 8
+	retq
+.Ltmp1:
+.Lfunc_end0:
+	.size	main, .Lfunc_end0-main
+	.cfi_endproc
+                                        # -- End function
+	.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
+	.ascii	"\264B"                         # DW_AT_GNU_pubnames
+	.byte	25                              # DW_FORM_flag_present
+	.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	6318074710904753300
+	.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
+                                        # DW_AT_GNU_pubnames
+	.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.o"                        # string offset=43
+	.section	.debug_str_offsets,"", at progbits
+	.long	.Lskel_string0
+	.long	.Lskel_string1
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	24                              # 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	"clang version 12.0.0 (git at github.com:llvm/llvm-project.git 9a33f027ac7d73e14ae287e78ab554142d1cbc8f)" # string offset=9
+.Linfo_string3:
+	.asciz	"main.cpp"                      # string offset=110
+.Linfo_string4:
+	.asciz	"main.s"                        # string offset=119
+	.section	.debug_str_offsets.dwo,"e", at progbits
+	.long	0
+	.long	5
+	.long	9
+	.long	110
+	.long	119
+	.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	5                               # DWARF Unit Type
+	.byte	8                               # Address Size (in bytes)
+	.long	0                               # Offset Into Abbrev. Section
+	.quad	6318074710904753300
+	.byte	1                               # Abbrev [1] 0x14:0x1a DW_TAG_compile_unit
+	.byte	2                               # DW_AT_producer
+	.short	33                              # DW_AT_language
+	.byte	3                               # DW_AT_name
+	.byte	4                               # DW_AT_dwo_name
+	.byte	2                               # Abbrev [2] 0x1a:0xf 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	1                               # DW_AT_decl_line
+	.long	41                              # DW_AT_type
+                                        # DW_AT_external
+	.byte	3                               # Abbrev [3] 0x29:0x4 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:
+	.section	.debug_abbrev.dwo,"e", at progbits
+	.byte	1                               # 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	2                               # Abbreviation Code
+	.byte	46                              # DW_TAG_subprogram
+	.byte	0                               # DW_CHILDREN_no
+	.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	3                               # 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	0                               # EOM(3)
+	.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:
+	.section	.debug_gnu_pubnames,"", at progbits
+	.long	.LpubNames_end0-.LpubNames_begin0 # Length of Public Names Info
+.LpubNames_begin0:
+	.short	2                               # DWARF Version
+	.long	.Lcu_begin0                     # Offset of Compilation Unit Info
+	.long	40                              # Compilation Unit Length
+	.long	26                              # DIE offset
+	.byte	48                              # Attributes: FUNCTION, EXTERNAL
+	.asciz	"main"                          # External Name
+	.long	0                               # End Mark
+.LpubNames_end0:
+	.section	.debug_gnu_pubtypes,"", at progbits
+	.long	.LpubTypes_end0-.LpubTypes_begin0 # Length of Public Types Info
+.LpubTypes_begin0:
+	.short	2                               # DWARF Version
+	.long	.Lcu_begin0                     # Offset of Compilation Unit Info
+	.long	40                              # Compilation Unit Length
+	.long	41                              # DIE offset
+	.byte	144                             # Attributes: TYPE, STATIC
+	.asciz	"int"                           # External Name
+	.long	0                               # End Mark
+.LpubTypes_end0:
+	.ident	"clang version 12.0.0 (git at github.com:llvm/llvm-project.git 9a33f027ac7d73e14ae287e78ab554142d1cbc8f)"
+	.section	".note.GNU-stack","", at progbits
+	.addrsig
+	.section	.debug_line,"", at progbits
+.Lline_table_start0:
+	.section	.debug_loclists.dwo,"e", at progbits
+	.byte 	0


        


More information about the llvm-commits mailing list