Fix a crash when parsing incorrect DWARF

Summary:
While parsing a childless compile unit DIE we could crash if the DIE was
followed by any extra data (such as a superfluous end-of-children
marker). This happened because the break-on-depth=0 check was performed
only when parsing the null DIE, which was not correct because with a
childless root DIE, we could reach the end of the unit without ever
encountering the null DIE.

If the compile unit contribution ended directly after the CU DIE,
everything would be fine as we would terminate parsing due to reaching
EOF. However, if the contribution contained extra data (perhaps a
superfluous end-of-children marker), we would crash because we would
treat that data as the begging of another compile unit.

This fixes the crash by moving the depth=0 check to a more generic
place, and also adds a regression test.

Reviewers: clayborg, jankratochvil, JDevlieghere

Subscribers: lldb-commits

Differential Revision: https://reviews.llvm.org/D54417

llvm-svn: 346849

2 files changed, 48 insertions, 3 deletions

diff --git a/lldb/lit/SymbolFile/DWARF/childless-compile-unit.s b/lldb/lit/SymbolFile/DWARF/childless-compile-unit.s
new file mode 100644
index 00000000000..d167e0503c5
--- /dev/null
+++ b/lldb/lit/SymbolFile/DWARF/childless-compile-unit.s
@@ -0,0 +1,45 @@
+# Test that we don't crash when parsing slightly invalid DWARF.  The compile
+# unit in this file sets DW_CHILDREN_no, but it still includes an
+# end-of-children marker in its contribution.
+
+# RUN: llvm-mc -triple x86_64-pc-linux %s -filetype=obj > %t.o
+# RUN: lldb-test symbols %t.o
+
+	.section	.debug_str,"MS",@progbits,1
+.Linfo_string0:
+	.asciz	"Hand-written DWARF"
+.Linfo_string1:
+	.asciz	"-"
+.Linfo_string2:
+	.asciz	"/tmp"
+
+	.section	.debug_abbrev,"",@progbits
+	.byte	1                       # Abbreviation Code
+	.byte	17                      # DW_TAG_compile_unit
+	.byte	0                       # DW_CHILDREN_no
+	.byte	37                      # DW_AT_producer
+	.byte	14                      # DW_FORM_strp
+	.byte	19                      # DW_AT_language
+	.byte	5                       # DW_FORM_data2
+	.byte	3                       # DW_AT_name
+	.byte	14                      # DW_FORM_strp
+	.byte	27                      # DW_AT_comp_dir
+	.byte	14                      # DW_FORM_strp
+	.byte	0                       # EOM(1)
+	.byte	0                       # EOM(2)
+	.byte	0                       # EOM(3)
+
+	.section	.debug_info,"",@progbits
+.Lcu_begin0:
+	.long	.Lcu_length_end-.Lcu_length_start # Length of Unit
+.Lcu_length_start:
+	.short	4                       # DWARF version number
+	.long	.debug_abbrev           # Offset Into Abbrev. Section
+	.byte	8                       # Address Size (in bytes)
+	.byte	1                       # Abbrev [1] 0xb:0x30 DW_TAG_compile_unit
+	.long	.Linfo_string0          # DW_AT_producer
+	.short	12                      # DW_AT_language
+	.long	.Linfo_string1          # DW_AT_name
+	.long	.Linfo_string2          # DW_AT_comp_dir
+	.byte	0                       # Bogus End Of Children Mark
+.Lcu_length_end:
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp b/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
index 7236a0599e6..a7b5e3517b2 100644
--- a/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
+++ b/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
@@ -244,9 +244,6 @@ void DWARFUnit::ExtractDIEsRWLocked() {
 
       if (depth > 0)
         --depth;
-      if (depth == 0)
-        break; // We are done with this compile unit!
-
       prev_die_had_children = false;
     } else {
       die_index_stack.back() = m_die_array.size() - 1;
@@ -258,6 +255,9 @@ void DWARFUnit::ExtractDIEsRWLocked() {
       }
       prev_die_had_children = die_has_children;
     }
+
+    if (depth == 0)
+      break; // We are done with this compile unit!
   }
 
   if (!m_die_array.empty()) {