[DWARF/AccelTable] Remove getDIESectionOffset for DWARF v5 entries

Summary:
This method was not correct for entries in DWO files as it assumed it
could just add up the CU and DIE offsets to get the absolute DIE offset.
This is not correct for the DWO files, as here the CU offset will
reference the skeleton unit, whereas the DIE offset will be the offset
in the full unit in the DWO file.

Unfortunately, this means that we are not able to determine the absolute
DIE offset using the information in the .debug_names section alone,
which means we have to offload some of this work to the users of this
class.

To demonstrate how this can be done, I've added/fixed the ability to
lookup entries using accelerator tables in DWO files in llvm-dwarfdump.
To make this happen, I've needed to make two extra changes in other
classes:
- made the DWARFContext method to lookup a CU based on the section
  offset public. I've needed this functionality to lookup a CU, and this
  seems like a useful thing in general.
- made DWARFUnit::getDWOId call extractDIEsIfNeeded. Before this, the
  DWOId was filled in only if the root DIE happened to be parsed
  before we called the accessor. Since the lazy parsing is supposed to
  happen under the hood, calling extractDIEsIfNeeded seems appropriate.

Reviewers: JDevlieghere, aprantl, dblaikie

Subscribers: mgrang, llvm-commits

Differential Revision: https://reviews.llvm.org/D48009

llvm-svn: 334578

7 files changed, 225 insertions, 39 deletions

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFAcceleratorTable.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFAcceleratorTable.h
index 741cec3507c..1d448728338 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFAcceleratorTable.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFAcceleratorTable.h
@@ -56,12 +56,6 @@ public:
     /// in this Accelerator Entry.
     virtual Optional<uint64_t> getCUOffset() const = 0;
 
-    /// Returns the Section Offset of the Debug Info Entry associated with this
-    /// Accelerator Entry or None if the DIE offset is not recorded in this
-    /// Accelerator Entry. The returned offset is relative to the start of the
-    /// Section containing the DIE.
-    virtual Optional<uint64_t> getDIESectionOffset() const = 0;
-
     /// Returns the Tag of the Debug Info Entry associated with this
     /// Accelerator Entry or None if the Tag is not recorded in this
     /// Accelerator Entry.
@@ -130,7 +124,13 @@ public:
 
   public:
     Optional<uint64_t> getCUOffset() const override;
-    Optional<uint64_t> getDIESectionOffset() const override;
+
+    /// Returns the Section Offset of the Debug Info Entry associated with this
+    /// Accelerator Entry or None if the DIE offset is not recorded in this
+    /// Accelerator Entry. The returned offset is relative to the start of the
+    /// Section containing the DIE.
+    Optional<uint64_t> getDIESectionOffset() const;
+
     Optional<dwarf::Tag> getTag() const override;
 
     /// Returns the value of the Atom in this Accelerator Entry, if the Entry
@@ -286,7 +286,6 @@ public:
 
   public:
     Optional<uint64_t> getCUOffset() const override;
-    Optional<uint64_t> getDIESectionOffset() const override;
     Optional<dwarf::Tag> getTag() const override { return tag(); }
 
     /// Returns the Index into the Compilation Unit list of the owning Name
diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h
index 6634eedbcd0..fe7430c9f04 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFContext.h
@@ -205,6 +205,9 @@ public:
 
   DWARFCompileUnit *getDWOCompileUnitForHash(uint64_t Hash);
 
+  /// Return the compile unit that includes an offset (relative to .debug_info).
+  DWARFCompileUnit *getCompileUnitForOffset(uint32_t Offset);
+
   /// Get a DIE given an exact offset.
   DWARFDie getDIEForOffset(uint32_t Offset);
 
@@ -321,9 +324,6 @@ public:
   Error loadRegisterInfo(const object::ObjectFile &Obj);
 
 private:
-  /// Return the compile unit that includes an offset (relative to .debug_info).
-  DWARFCompileUnit *getCompileUnitForOffset(uint32_t Offset);
-
   /// Return the compile unit which contains instruction with provided
   /// address.
   DWARFCompileUnit *getCompileUnitForAddress(uint64_t Address);
diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
index b6ea11ec88e..fa98b728492 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
@@ -442,7 +442,10 @@ public:
   }
 
   const char *getCompilationDir();
-  Optional<uint64_t> getDWOId() const { return getHeader().getDWOId(); }
+  Optional<uint64_t> getDWOId() {
+    extractDIEsIfNeeded(/*CUDieOnly*/ true);
+    return getHeader().getDWOId();
+  }
   void setDWOId(uint64_t NewID) { Header.setDWOId(NewID); }
 
   /// Return a vector of address ranges resulting from a (possibly encoded)
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFAcceleratorTable.cpp b/llvm/lib/DebugInfo/DWARF/DWARFAcceleratorTable.cpp
index c2ba9e6027b..0ded97cabf2 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFAcceleratorTable.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFAcceleratorTable.cpp
@@ -556,14 +556,6 @@ Optional<uint64_t> DWARFDebugNames::Entry::getCUOffset() const {
   return NameIdx->getCUOffset(*Index);
 }
 
-Optional<uint64_t> DWARFDebugNames::Entry::getDIESectionOffset() const {
-  Optional<uint64_t> CUOff = getCUOffset();
-  Optional<uint64_t> DIEOff = getDIEUnitOffset();
-  if (CUOff && DIEOff)
-    return *CUOff + *DIEOff;
-  return None;
-}
-
 void DWARFDebugNames::Entry::dump(ScopedPrinter &W) const {
   W.printHex("Abbrev", Abbr->Code);
   W.startLine() << formatv("Tag: {0}\n", Abbr->Tag);
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp b/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
index fe44071d9a2..e456de5b103 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
@@ -1088,7 +1088,7 @@ unsigned DWARFVerifier::verifyNameIndexEntries(
       continue;
     }
     uint32_t CUOffset = NI.getCUOffset(CUIndex);
-    uint64_t DIEOffset = *EntryOr->getDIESectionOffset();
+    uint64_t DIEOffset = CUOffset + *EntryOr->getDIEUnitOffset();
     DWARFDie DIE = DCtx.getDIEForOffset(DIEOffset);
     if (!DIE) {
       error() << formatv("Name Index @ {0:x}: Entry @ {1:x} references a "
@@ -1261,9 +1261,10 @@ unsigned DWARFVerifier::verifyNameIndexCompleteness(
   // Now we know that our Die should be present in the Index. Let's check if
   // that's the case.
   unsigned NumErrors = 0;
+  uint64_t DieUnitOffset = Die.getOffset() - Die.getDwarfUnit()->getOffset();
   for (StringRef Name : EntryNames) {
-    if (none_of(NI.equal_range(Name), [&Die](const DWARFDebugNames::Entry &E) {
-          return E.getDIESectionOffset() == uint64_t(Die.getOffset());
+    if (none_of(NI.equal_range(Name), [&](const DWARFDebugNames::Entry &E) {
+          return E.getDIEUnitOffset() == DieUnitOffset;
         })) {
       error() << formatv("Name Index @ {0:x}: Entry for DIE @ {1:x} ({2}) with "
                          "name {3} missing.\n",
diff --git a/llvm/test/tools/llvm-dwarfdump/X86/debug-names-find-dwo.s b/llvm/test/tools/llvm-dwarfdump/X86/debug-names-find-dwo.s
new file mode 100644
index 00000000000..a12aa2e90f1
--- /dev/null
+++ b/llvm/test/tools/llvm-dwarfdump/X86/debug-names-find-dwo.s
@@ -0,0 +1,162 @@
+# RUN: llvm-mc -triple x86_64-pc-linux %s -filetype=obj | \
+# RUN:   llvm-dwarfdump -find=foobar - | FileCheck %s
+
+# CHECK: DW_TAG_variable
+# CHECK-NEXT: DW_AT_name ("foobar")
+
+	.text
+	.file	"<stdin>"
+	.file	1 "/tmp/cu1.c"
+	.type	foobar,@object          # @foobar
+	.comm	foobar,8,8
+	.section	.debug_str,"MS",@progbits,1
+.Lskel_string0:
+	.asciz	"foo.dwo"               # string offset=0
+.Lskel_string1:
+	.asciz	"/tmp"                  # string offset=8
+.Lskel_string2:
+	.asciz	"foobar"                # string offset=13
+	.section	.debug_loc.dwo,"",@progbits
+	.section	.debug_abbrev,"",@progbits
+	.byte	1                       # Abbreviation Code
+	.byte	17                      # DW_TAG_compile_unit
+	.byte	0                       # DW_CHILDREN_no
+	.byte	16                      # DW_AT_stmt_list
+	.byte	23                      # DW_FORM_sec_offset
+	.ascii	"\260B"                 # DW_AT_GNU_dwo_name
+	.byte	14                      # DW_FORM_strp
+	.byte	27                      # DW_AT_comp_dir
+	.byte	14                      # DW_FORM_strp
+	.ascii	"\261B"                 # DW_AT_GNU_dwo_id
+	.byte	7                       # DW_FORM_data8
+	.ascii	"\263B"                 # DW_AT_GNU_addr_base
+	.byte	23                      # DW_FORM_sec_offset
+	.byte	0                       # EOM(1)
+	.byte	0                       # EOM(2)
+	.byte	0                       # EOM(3)
+	.section	.debug_info,"",@progbits
+.Lcu_begin0:
+	.long	32                      # Length of Unit
+	.short	4                       # DWARF version number
+	.long	.debug_abbrev           # Offset Into Abbrev. Section
+	.byte	8                       # Address Size (in bytes)
+	.byte	1                       # Abbrev [1] 0xb:0x19 DW_TAG_compile_unit
+	.long	0                       # DW_AT_stmt_list
+	.long	.Lskel_string0          # DW_AT_GNU_dwo_name
+	.long	.Lskel_string1          # DW_AT_comp_dir
+	.quad	-1328675031687321003    # DW_AT_GNU_dwo_id
+	.long	.debug_addr             # DW_AT_GNU_addr_base
+	.section	.debug_ranges,"",@progbits
+	.section	.debug_macinfo,"",@progbits
+	.byte	0                       # End Of Macro List Mark
+	.section	.debug_str.dwo,"MS",@progbits,1
+.Linfo_string0:
+	.asciz	"foo.dwo"               # string offset=0
+.Linfo_string1:
+	.asciz	"clang version 7.0.0 (trunk 325496) (llvm/trunk 325732)" # string offset=8
+.Linfo_string2:
+	.asciz	"/tmp/cu1.c"            # string offset=63
+.Linfo_string3:
+	.asciz	"foobar"                # string offset=74
+	.section	.debug_str_offsets.dwo,"",@progbits
+	.long	0
+	.long	8
+	.long	63
+	.long	74
+	.section	.debug_info.dwo,"",@progbits
+	.long	34                      # Length of Unit
+	.short	4                       # DWARF version number
+	.long	0                       # Offset Into Abbrev. Section
+	.byte	8                       # Address Size (in bytes)
+	.byte	1                       # Abbrev [1] 0xb:0x1b DW_TAG_compile_unit
+	.byte	0                       # DW_AT_GNU_dwo_name
+	.byte	1                       # DW_AT_producer
+	.short	12                      # DW_AT_language
+	.byte	2                       # DW_AT_name
+	.quad	-1328675031687321003    # DW_AT_GNU_dwo_id
+	.byte	2                       # Abbrev [2] 0x19:0xb DW_TAG_variable
+	.byte	3                       # DW_AT_name
+	.long	36                      # DW_AT_type
+                                        # DW_AT_external
+	.byte	1                       # DW_AT_decl_file
+	.byte	1                       # DW_AT_decl_line
+	.byte	2                       # DW_AT_location
+	.byte	251
+	.byte	0
+	.byte	3                       # Abbrev [3] 0x24:0x1 DW_TAG_pointer_type
+	.byte	0                       # End Of Children Mark
+	.section	.debug_abbrev.dwo,"",@progbits
+	.byte	1                       # Abbreviation Code
+	.byte	17                      # DW_TAG_compile_unit
+	.byte	1                       # DW_CHILDREN_yes
+	.ascii	"\260B"                 # DW_AT_GNU_dwo_name
+	.ascii	"\202>"                 # DW_FORM_GNU_str_index
+	.byte	37                      # DW_AT_producer
+	.ascii	"\202>"                 # DW_FORM_GNU_str_index
+	.byte	19                      # DW_AT_language
+	.byte	5                       # DW_FORM_data2
+	.byte	3                       # DW_AT_name
+	.ascii	"\202>"                 # DW_FORM_GNU_str_index
+	.ascii	"\261B"                 # DW_AT_GNU_dwo_id
+	.byte	7                       # DW_FORM_data8
+	.byte	0                       # EOM(1)
+	.byte	0                       # EOM(2)
+	.byte	2                       # Abbreviation Code
+	.byte	52                      # DW_TAG_variable
+	.byte	0                       # DW_CHILDREN_no
+	.byte	3                       # DW_AT_name
+	.ascii	"\202>"                 # DW_FORM_GNU_str_index
+	.byte	73                      # DW_AT_type
+	.byte	19                      # DW_FORM_ref4
+	.byte	63                      # DW_AT_external
+	.byte	25                      # DW_FORM_flag_present
+	.byte	58                      # DW_AT_decl_file
+	.byte	11                      # DW_FORM_data1
+	.byte	59                      # DW_AT_decl_line
+	.byte	11                      # DW_FORM_data1
+	.byte	2                       # DW_AT_location
+	.byte	24                      # DW_FORM_exprloc
+	.byte	0                       # EOM(1)
+	.byte	0                       # EOM(2)
+	.byte	3                       # Abbreviation Code
+	.byte	15                      # DW_TAG_pointer_type
+	.byte	0                       # DW_CHILDREN_no
+	.byte	0                       # EOM(1)
+	.byte	0                       # EOM(2)
+	.byte	0                       # EOM(3)
+	.section	.debug_addr,"",@progbits
+	.quad	foobar
+	.section	.debug_names,"",@progbits
+	.long	.Lnames_end0-.Lnames_start0 # Header: unit length
+.Lnames_start0:
+	.short	5                       # Header: version
+	.short	0                       # Header: padding
+	.long	1                       # Header: compilation unit count
+	.long	0                       # Header: local type unit count
+	.long	0                       # Header: foreign type unit count
+	.long	1                       # Header: bucket count
+	.long	1                       # Header: name count
+	.long	.Lnames_abbrev_end0-.Lnames_abbrev_start0 # Header: abbreviation table size
+	.long	8                       # Header: augmentation string size
+	.ascii	"LLVM0700"              # Header: augmentation string
+	.long	.Lcu_begin0             # Compilation unit 0
+	.long	1                       # Bucket 0
+	.long	-35364674               # Hash in Bucket 0
+	.long	.Lskel_string2          # String in Bucket 0: foobar
+	.long	.Lnames0-.Lnames_entries0 # Offset in Bucket 0
+.Lnames_abbrev_start0:
+	.byte	52                      # Abbrev code
+	.byte	52                      # DW_TAG_variable
+	.byte	3                       # DW_IDX_die_offset
+	.byte	19                      # DW_FORM_ref4
+	.byte	0                       # End of abbrev
+	.byte	0                       # End of abbrev
+	.byte	0                       # End of abbrev list
+.Lnames_abbrev_end0:
+.Lnames_entries0:
+.Lnames0:
+	.byte	52                      # Abbreviation code
+	.long	25                      # DW_IDX_die_offset
+	.long	0                       # End of list: foobar
+	.p2align	2
+.Lnames_end0:
diff --git a/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp b/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp
index 433c681a108..d9d36625083 100644
--- a/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp
+++ b/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp
@@ -309,31 +309,60 @@ static void filterByName(const StringSet<> &Names,
 
 }
 
-template <typename AccelTable>
-static void getDIEOffset(const AccelTable &Accel, StringRef Name,
-                         SmallVectorImpl<uint64_t> &Offsets) {
-  for (const auto &Entry : Accel.equal_range(Name))
-    if (llvm::Optional<uint64_t> Off = Entry.getDIESectionOffset())
-      Offsets.push_back(*Off);
+static void getDies(DWARFContext &DICtx, const AppleAcceleratorTable &Accel,
+                    StringRef Name, SmallVectorImpl<DWARFDie> &Dies) {
+  for (const auto &Entry : Accel.equal_range(Name)) {
+    if (llvm::Optional<uint64_t> Off = Entry.getDIESectionOffset()) {
+      if (DWARFDie Die = DICtx.getDIEForOffset(*Off))
+        Dies.push_back(Die);
+    }
+  }
+}
+
+static DWARFDie toDie(const DWARFDebugNames::Entry &Entry,
+                      DWARFContext &DICtx) {
+  llvm::Optional<uint64_t> CUOff = Entry.getCUOffset();
+  llvm::Optional<uint64_t> Off = Entry.getDIEUnitOffset();
+  if (!CUOff || !Off)
+    return DWARFDie();
+
+  DWARFCompileUnit *CU = DICtx.getCompileUnitForOffset(*CUOff);
+  if (!CU)
+    return DWARFDie();
+
+  if (Optional<uint64_t> DWOId = CU->getDWOId()) {
+    // This is a skeleton unit. Look up the DIE in the DWO unit.
+    CU = DICtx.getDWOCompileUnitForHash(*DWOId);
+    if (!CU)
+      return DWARFDie();
+  }
+
+  return CU->getDIEForOffset(CU->getOffset() + *Off);
+}
+
+static void getDies(DWARFContext &DICtx, const DWARFDebugNames &Accel,
+                    StringRef Name, SmallVectorImpl<DWARFDie> &Dies) {
+  for (const auto &Entry : Accel.equal_range(Name)) {
+    if (DWARFDie Die = toDie(Entry, DICtx))
+      Dies.push_back(Die);
+  }
 }
 
 /// Print only DIEs that have a certain name.
 static void filterByAccelName(ArrayRef<std::string> Names, DWARFContext &DICtx,
                               raw_ostream &OS) {
-  SmallVector<uint64_t, 4> Offsets;
+  SmallVector<DWARFDie, 4> Dies;
   for (const auto &Name : Names) {
-    getDIEOffset(DICtx.getAppleNames(), Name, Offsets);
-    getDIEOffset(DICtx.getAppleTypes(), Name, Offsets);
-    getDIEOffset(DICtx.getAppleNamespaces(), Name, Offsets);
-    getDIEOffset(DICtx.getDebugNames(), Name, Offsets);
+    getDies(DICtx, DICtx.getAppleNames(), Name, Dies);
+    getDies(DICtx, DICtx.getAppleTypes(), Name, Dies);
+    getDies(DICtx, DICtx.getAppleNamespaces(), Name, Dies);
+    getDies(DICtx, DICtx.getDebugNames(), Name, Dies);
   }
-  llvm::sort(Offsets.begin(), Offsets.end());
-  Offsets.erase(std::unique(Offsets.begin(), Offsets.end()), Offsets.end());
+  llvm::sort(Dies.begin(), Dies.end());
+  Dies.erase(std::unique(Dies.begin(), Dies.end()), Dies.end());
 
-  for (uint64_t Off: Offsets) {
-    DWARFDie Die = DICtx.getDIEForOffset(Off);
+  for (DWARFDie Die : Dies)
     Die.dump(OS, 0, getDumpOpts());
-  }
 }
 
 /// Handle the --lookup option and dump the DIEs and line info for the given