DWARF: Implement DW_AT_signature lookup for type unit support

Summary:
This patch implements the main feature of type units. When completing a
type, if we encounter a DW_AT_signature attribute, we use it's value to
lookup the complete definition of the type in the relevant type unit.

To enable this lookup, we build up a map of all type units in a symbol
file when parsing the units. Then we consult this map when resolving the
DW_AT_signature attribute.

I include add a couple of tests which exercise the type lookup feature,
including one that ensure we do something reasonable in case we fail to
lookup the type.

A lot of the ideas in this patch have been taken from D32167 and D61505.

Reviewers: clayborg, JDevlieghere, aprantl, alexshap

Subscribers: mgrang, lldb-commits

Differential Revision: https://reviews.llvm.org/D62246

llvm-svn: 361603

6 files changed, 178 insertions, 4 deletions

diff --git a/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-basic.cpp b/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-basic.cpp
index e28515269b4..defa8ba5c69 100644
--- a/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-basic.cpp
+++ b/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-basic.cpp
@@ -1,13 +1,15 @@
+enum E { e1, e2, e3 };
+enum class EC { e1, e2, e3 };
+
 struct A {
   int i;
   long l;
   float f;
   double d;
+  E e;
+  EC ec;
 };
 
-enum E { e1, e2, e3 };
-enum class EC { e1, e2, e3 };
-
-extern constexpr A a{42, 47l, 4.2f, 4.7};
+extern constexpr A a{42, 47l, 4.2f, 4.7, e1, EC::e3};
 extern constexpr E e(e2);
 extern constexpr EC ec(EC::e2);
diff --git a/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-expressions.cpp b/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-expressions.cpp
index 7bdd79d0973..fe728cf040d 100644
--- a/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-expressions.cpp
+++ b/lldb/lit/SymbolFile/DWARF/Inputs/debug-types-expressions.cpp
@@ -11,11 +11,19 @@ struct B: public A {
 namespace ns {
 struct A {
   int i = 147;
+  ::A getA();
   A();
 };
 A::A() = default;
+
+::A A::getA() {
+  ::A a;
+  a.i = i - 1;
+  return a;
 }
 
+} // namespace ns
+
 int foo(A *a) {
   return a->f();
 }
diff --git a/lldb/lit/SymbolFile/DWARF/debug-types-basic.test b/lldb/lit/SymbolFile/DWARF/debug-types-basic.test
index 468a4e8567c..bf2c9c69d1d 100644
--- a/lldb/lit/SymbolFile/DWARF/debug-types-basic.test
+++ b/lldb/lit/SymbolFile/DWARF/debug-types-basic.test
@@ -19,6 +19,8 @@ type lookup A
 # CHECK-NEXT:   long l;
 # CHECK-NEXT:   float f;
 # CHECK-NEXT:   double d;
+# CHECK-NEXT:   E e;
+# CHECK-NEXT:   EC ec;
 # CHECK-NEXT: }
 
 type lookup E
@@ -44,3 +46,9 @@ print (E) 1
 print (EC) 1
 # CHECK-LABEL: print (EC) 1
 # CHECK: (EC) $1 = e2
+
+target variable a e ec
+# CHECK-LABEL: target variable a e ec
+# CHECK: (const A) a = (i = 42, l = 47, f = 4.{{[12].*}}, d = 4.{{[67].*}}, e = e1, ec = e3)
+# CHECK: (const E) e = e2
+# CHECK: (const EC) ec = e2
diff --git a/lldb/lit/SymbolFile/DWARF/debug-types-expressions.test b/lldb/lit/SymbolFile/DWARF/debug-types-expressions.test
index db67f8a3958..da40269461a 100644
--- a/lldb/lit/SymbolFile/DWARF/debug-types-expressions.test
+++ b/lldb/lit/SymbolFile/DWARF/debug-types-expressions.test
@@ -19,6 +19,13 @@ frame variable a
 # CHECK-LABEL: frame variable a
 # CHECK: (B *) a =
 
+frame variable *a
+# CHECK-LABEL: frame variable *a
+# CHECK:      (B) *a = {
+# CHECK-NEXT:   A = (i = 47)
+# CHECK-NEXT:   j = 42
+# CHECK-NEXT: }
+
 print a->f()
 # CHECK-LABEL: print a->f()
 # CHECK: (int) $0 = 47
@@ -26,3 +33,11 @@ print a->f()
 print ns::A()
 # CHECK-LABEL: print ns::A()
 # CHECK: (ns::A) $1 = (i = 147)
+
+print ns::A().i + a->i
+# CHECK-LABEL: print ns::A().i + a->i
+# CHECK: (int) $2 = 194
+
+print ns::A().getA()
+# CHECK-LABEL: ns::A().getA()
+# CHECK: (A) $3 = (i = 146)
diff --git a/lldb/lit/SymbolFile/DWARF/debug-types-missing-signature.test b/lldb/lit/SymbolFile/DWARF/debug-types-missing-signature.test
new file mode 100644
index 00000000000..ca5c759136b
--- /dev/null
+++ b/lldb/lit/SymbolFile/DWARF/debug-types-missing-signature.test
@@ -0,0 +1,26 @@
+Create a dangling DW_AT_signature reference by stripping the debug_types
+section, and make sure lldb does something reasonable.
+RUN: %clangxx -target x86_64-pc-linux %S/Inputs/debug-types-basic.cpp \
+RUN:   -g -gdwarf-4 -fdebug-types-section -c -o %t.o
+RUN: llvm-objcopy --remove-section=.debug_types %t.o %t
+
+
+RUN: %lldb %t -b -o "type lookup A" | FileCheck --check-prefix=LOOKUPA %s
+LOOKUPA: no type was found matching 'A'
+
+RUN: %lldb %t -b -o "type lookup E" | FileCheck --check-prefix=LOOKUPE %s
+LOOKUPE: no type was found matching 'E'
+
+RUN: %lldb %t -b -o "type lookup EC" | FileCheck --check-prefix=LOOKUPEC %s
+LOOKUPEC: no type was found matching 'EC'
+
+RUN: %lldb %t -b -o "print (E) 1" 2>&1 | FileCheck --check-prefix=PRINTE %s
+PRINTE: use of undeclared identifier 'E'
+
+RUN: %lldb %t -b -o "print (EC) 1" 2>&1 | FileCheck --check-prefix=PRINTEC %s
+PRINTEC: use of undeclared identifier 'EC'
+
+RUN: %lldb %t -b -o "target variable a e ec" | FileCheck --check-prefix=VARS %s
+VARS: (const (anonymous struct)) a = {}
+VARS: (const (anonymous enum)) e = 1
+VARS: (const (anonymous enum)) ec = 1
diff --git a/lldb/lit/SymbolFile/DWARF/debug-types-signature-loop.s b/lldb/lit/SymbolFile/DWARF/debug-types-signature-loop.s
new file mode 100644
index 00000000000..d0d0fd5705a
--- /dev/null
+++ b/lldb/lit/SymbolFile/DWARF/debug-types-signature-loop.s
@@ -0,0 +1,115 @@
+# REQUIRES: lld
+
+# RUN: llvm-mc -filetype=obj -triple x86_64-pc-linux -o %t.o %s
+# RUN: ld.lld %t.o -o %t
+# RUN: %lldb %t -o "target variable e" -b | FileCheck %s
+
+# CHECK: e = <could not resolve type>
+
+        .type   e,@object               # @e
+        .section        .rodata,"a",@progbits
+        .globl  e
+        .p2align        2
+e:
+        .long   0                       # 0x0
+        .size   e, 4
+
+.Lstr_offsets_base0:
+        .section        .debug_str,"MS",@progbits,1
+.Linfo_string0:
+        .asciz  "Hand-written DWARF"
+.Linfo_string1:
+        .asciz  "a.cpp"            
+.Linfo_string3:
+        .asciz  "e"           
+.Linfo_string4:
+        .asciz  "unsigned int"
+.Linfo_string5:
+        .asciz  "e1"          
+.Linfo_string6:
+        .asciz  "E"           
+
+        .section        .debug_abbrev,"",@progbits
+        .byte   1                       # Abbreviation Code
+        .byte   65                      # DW_TAG_type_unit
+        .byte   1                       # DW_CHILDREN_yes
+        .byte   19                      # DW_AT_language
+        .byte   5                       # DW_FORM_data2
+        .byte   0                       # EOM(1)
+        .byte   0                       # EOM(2)
+        .byte   5                       # Abbreviation Code
+        .byte   17                      # DW_TAG_compile_unit
+        .byte   1                       # DW_CHILDREN_yes
+        .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   0                       # EOM(1)
+        .byte   0                       # EOM(2)
+        .byte   6                       # Abbreviation Code
+        .byte   52                      # DW_TAG_variable
+        .byte   0                       # DW_CHILDREN_no
+        .byte   3                       # DW_AT_name
+        .byte   14                      # DW_FORM_strp
+        .byte   73                      # DW_AT_type
+        .byte   19                      # DW_FORM_ref4
+        .byte   2                       # DW_AT_location
+        .byte   24                      # DW_FORM_exprloc
+        .byte   0                       # EOM(1)
+        .byte   0                       # EOM(2)
+        .byte   8                       # Abbreviation Code
+        .byte   4                       # DW_TAG_enumeration_type
+        .byte   0                       # DW_CHILDREN_no
+        .byte   60                      # DW_AT_declaration
+        .byte   25                      # DW_FORM_flag_present
+        .byte   105                     # DW_AT_signature
+        .byte   32                      # DW_FORM_ref_sig8
+        .byte   0                       # EOM(1)
+        .byte   0                       # EOM(2)
+        .byte   0                       # EOM(3)
+
+        .section        .debug_info,"",@progbits
+.Ltu_begin0:
+        .long   .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+        .short  5                       # DWARF version number
+        .byte   2                       # DWARF Unit Type
+        .byte   8                       # Address Size (in bytes)
+        .long   .debug_abbrev           # Offset Into Abbrev. Section
+        .quad   5390450678491038984     # Type Signature
+        .long   .LE-.Ltu_begin0         # Type DIE Offset
+        .byte   1                       # Abbrev [1] 0x18:0x1d DW_TAG_type_unit
+        .short  4                       # DW_AT_language
+.LE:
+        .byte   8                       # Abbrev [8] 0x23:0xd DW_TAG_enumeration_type
+                                        # DW_AT_declaration
+        .quad   5390450678491038984     # DW_AT_signature
+.Lbase:
+        .byte   0                       # End Of Children Mark
+.Ldebug_info_end0:
+
+.Lcu_begin0:
+        .long   .Ldebug_info_end1-.Ldebug_info_start1 # Length of Unit
+.Ldebug_info_start1:
+        .short  5                       # DWARF version number
+        .byte   1                       # DWARF Unit Type
+        .byte   8                       # Address Size (in bytes)
+        .long   .debug_abbrev           # Offset Into Abbrev. Section
+        .byte   5                       # Abbrev [5] 0xc:0x2c DW_TAG_compile_unit
+        .long   .Linfo_string0          # DW_AT_producer
+        .short  4                       # DW_AT_language
+        .long   .Linfo_string1          # DW_AT_name
+        .byte   6                       # Abbrev [6] 0x1e:0xb DW_TAG_variable
+        .long   .Linfo_string3          # DW_AT_name
+        .long   .LE_sig-.Lcu_begin0     # DW_AT_type
+        .byte   9                       # DW_AT_location
+        .byte   3
+        .quad   e
+.LE_sig:
+        .byte   8                       # Abbrev [8] 0x2e:0x9 DW_TAG_enumeration_type
+                                        # DW_AT_declaration
+        .quad   5390450678491038984     # DW_AT_signature
+        .byte   0                       # End Of Children Mark
+.Ldebug_info_end1: