DWARF type hashing: pointers to members

Includes a test case/FIXME demonstrating a bug/limitation in pointer to
member hashing. To be honest I'm not sure why we don't just always use
summary hashing for referenced types... but perhaps I'm missing
something.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193175 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 192 insertions, 11 deletions

diff --git a/lib/CodeGen/AsmPrinter/DIEHash.cpp b/lib/CodeGen/AsmPrinter/DIEHash.cpp
index 64a8fd50ed..9a1f966c8d 100644
--- a/lib/CodeGen/AsmPrinter/DIEHash.cpp
+++ b/lib/CodeGen/AsmPrinter/DIEHash.cpp
@@ -192,6 +192,7 @@ void DIEHash::collectAttributes(DIE *Die, DIEAttrs &Attrs) {
 void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
   const DIEValue *Value = Attr.Val;
   const DIEAbbrevData *Desc = Attr.Desc;
+  dwarf::Attribute Attribute = Desc->getAttribute();
 
   // 7.27 Step 3
   // ... An attribute that refers to another type entry T is processed as
@@ -200,14 +201,16 @@ void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
     DIE *Entry = EntryAttr->getEntry();
 
     // Step 5
-    // If the tag in Step 3 is one of ...
-    if (Tag == dwarf::DW_TAG_pointer_type ||
-        Tag == dwarf::DW_TAG_reference_type ||
-        Tag == dwarf::DW_TAG_rvalue_reference_type) {
-      // ... and the referenced type (via the DW_AT_type or DW_AT_friend
-      // attribute) ...
-      assert(Desc->getAttribute() == dwarf::DW_AT_type ||
-             Desc->getAttribute() == dwarf::DW_AT_friend);
+    // If the tag in Step 3 is one of [the below tags]
+    if ((Tag == dwarf::DW_TAG_pointer_type ||
+         Tag == dwarf::DW_TAG_reference_type ||
+         Tag == dwarf::DW_TAG_rvalue_reference_type ||
+         Tag == dwarf::DW_TAG_ptr_to_member_type) &&
+        // and the referenced type (via the [below attributes])
+        // FIXME: This seems overly restrictive, and causes hash mismatches
+        // there's a decl/def difference in the containing type of a
+        // ptr_to_member_type.
+        Attribute == dwarf::DW_AT_type) {
       // [FIXME] ... has a DW_AT_name attribute,
       // append the letter 'N'
       addULEB128('N');
@@ -238,7 +241,7 @@ void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
       // 'R' as the marker
       addULEB128('R');
 
-      addULEB128(Desc->getAttribute());
+      addULEB128(Attribute);
 
       // and use the unsigned LEB128 encoding of [the index of T in the
       // list] as the attribute value;
@@ -249,7 +252,7 @@ void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
     // otherwise, b) use the letter 'T' as a the marker, ...
     addULEB128('T');
 
-    addULEB128(Desc->getAttribute());
+    addULEB128(Attribute);
 
     // ... process the type T recursively by performing Steps 2 through 7, and
     // use the result as the attribute value.
@@ -261,7 +264,7 @@ void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
   // Other attribute values use the letter 'A' as the marker, ...
   addULEB128('A');
 
-  addULEB128(Desc->getAttribute());
+  addULEB128(Attribute);
 
   // ... and the value consists of the form code (encoded as an unsigned LEB128
   // value) followed by the encoding of the value according to the form code. To
diff --git a/unittests/CodeGen/DIEHashTest.cpp b/unittests/CodeGen/DIEHashTest.cpp
index 1ac8b3df6e..32030c1509 100644
--- a/unittests/CodeGen/DIEHashTest.cpp
+++ b/unittests/CodeGen/DIEHashTest.cpp
@@ -264,4 +264,182 @@ TEST(DIEHashTest, RValueReference) {
 
   ASSERT_EQ(0xad211c8c3b31e57ULL, MD5Res);
 }
+
+// struct foo { foo foo::*mem; };
+TEST(DIEHashTest, PtrToMember) {
+  DIE Foo(dwarf::DW_TAG_structure_type);
+  DIEInteger Eight(8);
+  Foo.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &Eight);
+  DIEString FooStr(&Eight, "foo");
+  Foo.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &FooStr);
+
+  DIE *Mem = new DIE(dwarf::DW_TAG_member);
+  DIEString MemStr(&Eight, "mem");
+  Mem->addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &MemStr);
+  DIEInteger Zero(0);
+  Mem->addValue(dwarf::DW_AT_data_member_location, dwarf::DW_FORM_data1, &Zero);
+
+  DIE PtrToFooMem(dwarf::DW_TAG_ptr_to_member_type);
+  DIEEntry FooEntry(&Foo);
+  PtrToFooMem.addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &FooEntry);
+  PtrToFooMem.addValue(dwarf::DW_AT_containing_type, dwarf::DW_FORM_ref4, &FooEntry);
+
+  DIEEntry PtrToFooMemRef(&PtrToFooMem);
+  Mem->addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &PtrToFooMemRef);
+
+  Foo.addChild(Mem);
+
+  uint64_t MD5Res = DIEHash().computeTypeSignature(&Foo);
+
+  ASSERT_EQ(0x852e0c9ff7c04ebULL, MD5Res);
+}
+
+// Check that the hash for a pointer-to-member matches regardless of whether the
+// pointed-to type is a declaration or a definition.
+//
+//   struct bar; // { };
+//   struct foo { bar foo::*mem; };
+TEST(DIEHashTest, PtrToMemberDeclDefMatch) {
+  DIEInteger Zero(0);
+  DIEInteger One(1);
+  DIEInteger Eight(8);
+  DIEString FooStr(&Eight, "foo");
+  DIEString BarStr(&Eight, "bar");
+  DIEString MemStr(&Eight, "mem");
+  uint64_t MD5ResDecl;
+  {
+    DIE Bar(dwarf::DW_TAG_structure_type);
+    Bar.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &BarStr);
+    Bar.addValue(dwarf::DW_AT_declaration, dwarf::DW_FORM_flag_present, &One);
+
+    DIE Foo(dwarf::DW_TAG_structure_type);
+    Foo.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &Eight);
+    Foo.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &FooStr);
+
+    DIE *Mem = new DIE(dwarf::DW_TAG_member);
+    Mem->addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &MemStr);
+    Mem->addValue(dwarf::DW_AT_data_member_location, dwarf::DW_FORM_data1,
+                  &Zero);
+
+    DIE PtrToFooMem(dwarf::DW_TAG_ptr_to_member_type);
+    DIEEntry BarEntry(&Bar);
+    PtrToFooMem.addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &BarEntry);
+    DIEEntry FooEntry(&Foo);
+    PtrToFooMem.addValue(dwarf::DW_AT_containing_type, dwarf::DW_FORM_ref4,
+                         &FooEntry);
+
+    DIEEntry PtrToFooMemRef(&PtrToFooMem);
+    Mem->addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &PtrToFooMemRef);
+
+    Foo.addChild(Mem);
+
+    MD5ResDecl = DIEHash().computeTypeSignature(&Foo);
+  }
+  uint64_t MD5ResDef;
+  {
+    DIE Bar(dwarf::DW_TAG_structure_type);
+    Bar.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &BarStr);
+    Bar.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &One);
+
+    DIE Foo(dwarf::DW_TAG_structure_type);
+    Foo.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &Eight);
+    Foo.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &FooStr);
+
+    DIE *Mem = new DIE(dwarf::DW_TAG_member);
+    Mem->addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &MemStr);
+    Mem->addValue(dwarf::DW_AT_data_member_location, dwarf::DW_FORM_data1,
+                  &Zero);
+
+    DIE PtrToFooMem(dwarf::DW_TAG_ptr_to_member_type);
+    DIEEntry BarEntry(&Bar);
+    PtrToFooMem.addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &BarEntry);
+    DIEEntry FooEntry(&Foo);
+    PtrToFooMem.addValue(dwarf::DW_AT_containing_type, dwarf::DW_FORM_ref4,
+                         &FooEntry);
+
+    DIEEntry PtrToFooMemRef(&PtrToFooMem);
+    Mem->addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &PtrToFooMemRef);
+
+    Foo.addChild(Mem);
+
+    MD5ResDef = DIEHash().computeTypeSignature(&Foo);
+  }
+  ASSERT_EQ(MD5ResDef, MD5ResDecl);
+}
+
+// Check that the hash for a pointer-to-member matches regardless of whether the
+// pointed-to type is a declaration or a definition.
+//
+//   struct bar; // { };
+//   struct foo { bar bar::*mem; };
+TEST(DIEHashTest, PtrToMemberDeclDefMisMatch) {
+  DIEInteger Zero(0);
+  DIEInteger One(1);
+  DIEInteger Eight(8);
+  DIEString FooStr(&Eight, "foo");
+  DIEString BarStr(&Eight, "bar");
+  DIEString MemStr(&Eight, "mem");
+  uint64_t MD5ResDecl;
+  {
+    DIE Bar(dwarf::DW_TAG_structure_type);
+    Bar.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &BarStr);
+    Bar.addValue(dwarf::DW_AT_declaration, dwarf::DW_FORM_flag_present, &One);
+
+    DIE Foo(dwarf::DW_TAG_structure_type);
+    Foo.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &Eight);
+    Foo.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &FooStr);
+
+    DIE *Mem = new DIE(dwarf::DW_TAG_member);
+    Mem->addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &MemStr);
+    Mem->addValue(dwarf::DW_AT_data_member_location, dwarf::DW_FORM_data1,
+                  &Zero);
+
+    DIE PtrToFooMem(dwarf::DW_TAG_ptr_to_member_type);
+    DIEEntry BarEntry(&Bar);
+    PtrToFooMem.addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &BarEntry);
+    PtrToFooMem.addValue(dwarf::DW_AT_containing_type, dwarf::DW_FORM_ref4,
+                         &BarEntry);
+
+    DIEEntry PtrToFooMemRef(&PtrToFooMem);
+    Mem->addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &PtrToFooMemRef);
+
+    Foo.addChild(Mem);
+
+    MD5ResDecl = DIEHash().computeTypeSignature(&Foo);
+  }
+  uint64_t MD5ResDef;
+  {
+    DIE Bar(dwarf::DW_TAG_structure_type);
+    Bar.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &BarStr);
+    Bar.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &One);
+
+    DIE Foo(dwarf::DW_TAG_structure_type);
+    Foo.addValue(dwarf::DW_AT_byte_size, dwarf::DW_FORM_data1, &Eight);
+    Foo.addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &FooStr);
+
+    DIE *Mem = new DIE(dwarf::DW_TAG_member);
+    Mem->addValue(dwarf::DW_AT_name, dwarf::DW_FORM_strp, &MemStr);
+    Mem->addValue(dwarf::DW_AT_data_member_location, dwarf::DW_FORM_data1,
+                  &Zero);
+
+    DIE PtrToFooMem(dwarf::DW_TAG_ptr_to_member_type);
+    DIEEntry BarEntry(&Bar);
+    PtrToFooMem.addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &BarEntry);
+    PtrToFooMem.addValue(dwarf::DW_AT_containing_type, dwarf::DW_FORM_ref4,
+                         &BarEntry);
+
+    DIEEntry PtrToFooMemRef(&PtrToFooMem);
+    Mem->addValue(dwarf::DW_AT_type, dwarf::DW_FORM_ref4, &PtrToFooMemRef);
+
+    Foo.addChild(Mem);
+
+    MD5ResDef = DIEHash().computeTypeSignature(&Foo);
+  }
+  // FIXME: This seems to be a bug in the DWARF type hashing specification that
+  // only uses the brief name hashing for types referenced via DW_AT_type. In
+  // this case the type is referenced via DW_AT_containing_type and full hashing
+  // causes a hash to differ when the containing type is a declaration in one TU
+  // and a definition in another.
+  ASSERT_NE(MD5ResDef, MD5ResDecl);
+}
 }