//
//===----------------------------------------------------------------------===//
-#define DEBUG_TYPE "dwarfdebug"
-
+#include "ByteStreamer.h"
#include "DIEHash.h"
-
-#include "DIE.h"
-#include "DwarfCompileUnit.h"
+#include "DwarfDebug.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/StringRef.h"
+#include "llvm/CodeGen/AsmPrinter.h"
+#include "llvm/CodeGen/DIE.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Dwarf.h"
#include "llvm/Support/Endian.h"
using namespace llvm;
+#define DEBUG_TYPE "dwarfdebug"
+
/// \brief Grabs the string in whichever attribute is passed in and returns
/// a reference to it.
static StringRef getDIEStringAttr(const DIE &Die, uint16_t Attr) {
- const SmallVectorImpl<DIEValue *> &Values = Die.getValues();
- const DIEAbbrev &Abbrevs = Die.getAbbrev();
-
// Iterate through all the attributes until we find the one we're
// looking for, if we can't find it return an empty string.
- for (size_t i = 0; i < Values.size(); ++i) {
- if (Abbrevs.getData()[i].getAttribute() == Attr) {
- DIEValue *V = Values[i];
- assert(isa<DIEString>(V) && "String requested. Not a string.");
- DIEString *S = cast<DIEString>(V);
- return S->getString();
- }
- }
+ for (const auto &V : Die.values())
+ if (V.getAttribute() == Attr)
+ return V.getDIEString().getString();
+
return StringRef("");
}
do {
uint8_t Byte = Value & 0x7f;
Value >>= 7;
- More = !((((Value == 0 ) && ((Byte & 0x40) == 0)) ||
+ More = !((((Value == 0) && ((Byte & 0x40) == 0)) ||
((Value == -1) && ((Byte & 0x40) != 0))));
if (More)
Byte |= 0x80; // Mark this byte to show that more bytes will follow.
// Collect all of the attributes for a particular DIE in single structure.
void DIEHash::collectAttributes(const DIE &Die, DIEAttrs &Attrs) {
- const SmallVectorImpl<DIEValue *> &Values = Die.getValues();
- const DIEAbbrev &Abbrevs = Die.getAbbrev();
-
#define COLLECT_ATTR(NAME) \
case dwarf::NAME: \
- Attrs.NAME.Val = Values[i]; \
- Attrs.NAME.Desc = &Abbrevs.getData()[i]; \
+ Attrs.NAME = V; \
break
- for (size_t i = 0, e = Values.size(); i != e; ++i) {
+ for (const auto &V : Die.values()) {
DEBUG(dbgs() << "Attribute: "
- << dwarf::AttributeString(Abbrevs.getData()[i].getAttribute())
+ << dwarf::AttributeString(V.getAttribute())
<< " added.\n");
- switch (Abbrevs.getData()[i].getAttribute()) {
- COLLECT_ATTR(DW_AT_name);
- COLLECT_ATTR(DW_AT_accessibility);
- COLLECT_ATTR(DW_AT_address_class);
- COLLECT_ATTR(DW_AT_allocated);
- COLLECT_ATTR(DW_AT_artificial);
- COLLECT_ATTR(DW_AT_associated);
- COLLECT_ATTR(DW_AT_binary_scale);
- COLLECT_ATTR(DW_AT_bit_offset);
- COLLECT_ATTR(DW_AT_bit_size);
- COLLECT_ATTR(DW_AT_bit_stride);
- COLLECT_ATTR(DW_AT_byte_size);
- COLLECT_ATTR(DW_AT_byte_stride);
- COLLECT_ATTR(DW_AT_const_expr);
- COLLECT_ATTR(DW_AT_const_value);
- COLLECT_ATTR(DW_AT_containing_type);
- COLLECT_ATTR(DW_AT_count);
- COLLECT_ATTR(DW_AT_data_bit_offset);
- COLLECT_ATTR(DW_AT_data_location);
- COLLECT_ATTR(DW_AT_data_member_location);
- COLLECT_ATTR(DW_AT_decimal_scale);
- COLLECT_ATTR(DW_AT_decimal_sign);
- COLLECT_ATTR(DW_AT_default_value);
- COLLECT_ATTR(DW_AT_digit_count);
- COLLECT_ATTR(DW_AT_discr);
- COLLECT_ATTR(DW_AT_discr_list);
- COLLECT_ATTR(DW_AT_discr_value);
- COLLECT_ATTR(DW_AT_encoding);
- COLLECT_ATTR(DW_AT_enum_class);
- COLLECT_ATTR(DW_AT_endianity);
- COLLECT_ATTR(DW_AT_explicit);
- COLLECT_ATTR(DW_AT_is_optional);
- COLLECT_ATTR(DW_AT_location);
- COLLECT_ATTR(DW_AT_lower_bound);
- COLLECT_ATTR(DW_AT_mutable);
- COLLECT_ATTR(DW_AT_ordering);
- COLLECT_ATTR(DW_AT_picture_string);
- COLLECT_ATTR(DW_AT_prototyped);
- COLLECT_ATTR(DW_AT_small);
- COLLECT_ATTR(DW_AT_segment);
- COLLECT_ATTR(DW_AT_string_length);
- COLLECT_ATTR(DW_AT_threads_scaled);
- COLLECT_ATTR(DW_AT_upper_bound);
- COLLECT_ATTR(DW_AT_use_location);
- COLLECT_ATTR(DW_AT_use_UTF8);
- COLLECT_ATTR(DW_AT_variable_parameter);
- COLLECT_ATTR(DW_AT_virtuality);
- COLLECT_ATTR(DW_AT_visibility);
- COLLECT_ATTR(DW_AT_vtable_elem_location);
- COLLECT_ATTR(DW_AT_type);
+ switch (V.getAttribute()) {
+ COLLECT_ATTR(DW_AT_name);
+ COLLECT_ATTR(DW_AT_accessibility);
+ COLLECT_ATTR(DW_AT_address_class);
+ COLLECT_ATTR(DW_AT_allocated);
+ COLLECT_ATTR(DW_AT_artificial);
+ COLLECT_ATTR(DW_AT_associated);
+ COLLECT_ATTR(DW_AT_binary_scale);
+ COLLECT_ATTR(DW_AT_bit_offset);
+ COLLECT_ATTR(DW_AT_bit_size);
+ COLLECT_ATTR(DW_AT_bit_stride);
+ COLLECT_ATTR(DW_AT_byte_size);
+ COLLECT_ATTR(DW_AT_byte_stride);
+ COLLECT_ATTR(DW_AT_const_expr);
+ COLLECT_ATTR(DW_AT_const_value);
+ COLLECT_ATTR(DW_AT_containing_type);
+ COLLECT_ATTR(DW_AT_count);
+ COLLECT_ATTR(DW_AT_data_bit_offset);
+ COLLECT_ATTR(DW_AT_data_location);
+ COLLECT_ATTR(DW_AT_data_member_location);
+ COLLECT_ATTR(DW_AT_decimal_scale);
+ COLLECT_ATTR(DW_AT_decimal_sign);
+ COLLECT_ATTR(DW_AT_default_value);
+ COLLECT_ATTR(DW_AT_digit_count);
+ COLLECT_ATTR(DW_AT_discr);
+ COLLECT_ATTR(DW_AT_discr_list);
+ COLLECT_ATTR(DW_AT_discr_value);
+ COLLECT_ATTR(DW_AT_encoding);
+ COLLECT_ATTR(DW_AT_enum_class);
+ COLLECT_ATTR(DW_AT_endianity);
+ COLLECT_ATTR(DW_AT_explicit);
+ COLLECT_ATTR(DW_AT_is_optional);
+ COLLECT_ATTR(DW_AT_location);
+ COLLECT_ATTR(DW_AT_lower_bound);
+ COLLECT_ATTR(DW_AT_mutable);
+ COLLECT_ATTR(DW_AT_ordering);
+ COLLECT_ATTR(DW_AT_picture_string);
+ COLLECT_ATTR(DW_AT_prototyped);
+ COLLECT_ATTR(DW_AT_small);
+ COLLECT_ATTR(DW_AT_segment);
+ COLLECT_ATTR(DW_AT_string_length);
+ COLLECT_ATTR(DW_AT_threads_scaled);
+ COLLECT_ATTR(DW_AT_upper_bound);
+ COLLECT_ATTR(DW_AT_use_location);
+ COLLECT_ATTR(DW_AT_use_UTF8);
+ COLLECT_ATTR(DW_AT_variable_parameter);
+ COLLECT_ATTR(DW_AT_virtuality);
+ COLLECT_ATTR(DW_AT_visibility);
+ COLLECT_ATTR(DW_AT_vtable_elem_location);
+ COLLECT_ATTR(DW_AT_type);
default:
break;
}
return;
}
- // otherwise, b) use the letter 'T' as a the marker, ...
+ // otherwise, b) use the letter 'T' as the marker, ...
addULEB128('T');
addULEB128(Attribute);
computeHash(Entry);
}
+// Hash all of the values in a block like set of values. This assumes that
+// all of the data is going to be added as integers.
+void DIEHash::hashBlockData(const DIE::const_value_range &Values) {
+ for (const auto &V : Values)
+ Hash.update((uint64_t)V.getDIEInteger().getValue());
+}
+
+// Hash the contents of a loclistptr class.
+void DIEHash::hashLocList(const DIELocList &LocList) {
+ HashingByteStreamer Streamer(*this);
+ DwarfDebug &DD = *AP->getDwarfDebug();
+ const DebugLocStream &Locs = DD.getDebugLocs();
+ for (const auto &Entry : Locs.getEntries(Locs.getList(LocList.getValue())))
+ DD.emitDebugLocEntry(Streamer, Entry);
+}
+
// Hash an individual attribute \param Attr based on the type of attribute and
// the form.
-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
- // follows:
- if (const DIEEntry *EntryAttr = dyn_cast<DIEEntry>(Value)) {
- hashDIEEntry(Attribute, Tag, *EntryAttr->getEntry());
- return;
+void DIEHash::hashAttribute(DIEValue Value, dwarf::Tag Tag) {
+ dwarf::Attribute Attribute = Value.getAttribute();
+
+ // Other attribute values use the letter 'A' as the marker, 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 ensure
+ // reproducibility of the signature, the set of forms used in the signature
+ // computation is limited to the following: DW_FORM_sdata, DW_FORM_flag,
+ // DW_FORM_string, and DW_FORM_block.
+
+ switch (Value.getType()) {
+ case DIEValue::isNone:
+ llvm_unreachable("Expected valid DIEValue");
+
+ // 7.27 Step 3
+ // ... An attribute that refers to another type entry T is processed as
+ // follows:
+ case DIEValue::isEntry:
+ hashDIEEntry(Attribute, Tag, Value.getDIEEntry().getEntry());
+ break;
+ case DIEValue::isInteger: {
+ addULEB128('A');
+ addULEB128(Attribute);
+ switch (Value.getForm()) {
+ case dwarf::DW_FORM_data1:
+ case dwarf::DW_FORM_data2:
+ case dwarf::DW_FORM_data4:
+ case dwarf::DW_FORM_data8:
+ case dwarf::DW_FORM_udata:
+ case dwarf::DW_FORM_sdata:
+ addULEB128(dwarf::DW_FORM_sdata);
+ addSLEB128((int64_t)Value.getDIEInteger().getValue());
+ break;
+ // DW_FORM_flag_present is just flag with a value of one. We still give it a
+ // value so just use the value.
+ case dwarf::DW_FORM_flag_present:
+ case dwarf::DW_FORM_flag:
+ addULEB128(dwarf::DW_FORM_flag);
+ addULEB128((int64_t)Value.getDIEInteger().getValue());
+ break;
+ default:
+ llvm_unreachable("Unknown integer form!");
+ }
+ break;
}
-
- // Other attribute values use the letter 'A' as the marker, ...
- addULEB128('A');
-
- 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
- // ensure reproducibility of the signature, the set of forms used in the
- // signature computation is limited to the following: DW_FORM_sdata,
- // DW_FORM_flag, DW_FORM_string, and DW_FORM_block.
- switch (Desc->getForm()) {
- case dwarf::DW_FORM_string:
- llvm_unreachable(
- "Add support for DW_FORM_string if we ever start emitting them again");
- case dwarf::DW_FORM_GNU_str_index:
- case dwarf::DW_FORM_strp:
+ case DIEValue::isString:
+ addULEB128('A');
+ addULEB128(Attribute);
addULEB128(dwarf::DW_FORM_string);
- addString(cast<DIEString>(Value)->getString());
+ addString(Value.getDIEString().getString());
break;
- case dwarf::DW_FORM_data1:
- case dwarf::DW_FORM_data2:
- case dwarf::DW_FORM_data4:
- case dwarf::DW_FORM_data8:
- case dwarf::DW_FORM_udata:
- addULEB128(dwarf::DW_FORM_sdata);
- addSLEB128((int64_t)cast<DIEInteger>(Value)->getValue());
+ case DIEValue::isBlock:
+ case DIEValue::isLoc:
+ case DIEValue::isLocList:
+ addULEB128('A');
+ addULEB128(Attribute);
+ addULEB128(dwarf::DW_FORM_block);
+ if (Value.getType() == DIEValue::isBlock) {
+ addULEB128(Value.getDIEBlock().ComputeSize(AP));
+ hashBlockData(Value.getDIEBlock().values());
+ } else if (Value.getType() == DIEValue::isLoc) {
+ addULEB128(Value.getDIELoc().ComputeSize(AP));
+ hashBlockData(Value.getDIELoc().values());
+ } else {
+ // We could add the block length, but that would take
+ // a bit of work and not add a lot of uniqueness
+ // to the hash in some way we could test.
+ hashLocList(Value.getDIELocList());
+ }
break;
- default:
- llvm_unreachable("Add support for additional forms");
+ // FIXME: It's uncertain whether or not we should handle this at the moment.
+ case DIEValue::isExpr:
+ case DIEValue::isLabel:
+ case DIEValue::isDelta:
+ case DIEValue::isTypeSignature:
+ llvm_unreachable("Add support for additional value types.");
}
}
void DIEHash::hashAttributes(const DIEAttrs &Attrs, dwarf::Tag Tag) {
#define ADD_ATTR(ATTR) \
{ \
- if (ATTR.Val != 0) \
+ if (ATTR) \
hashAttribute(ATTR, Tag); \
}
addAttributes(Die);
// Then hash each of the children of the DIE.
- for (std::vector<DIE *>::const_iterator I = Die.getChildren().begin(),
- E = Die.getChildren().end();
- I != E; ++I) {
+ for (auto &C : Die.children()) {
// 7.27 Step 7
// If C is a nested type entry or a member function entry, ...
- if (isType((*I)->getTag()) || (*I)->getTag() == dwarf::DW_TAG_subprogram) {
- StringRef Name = getDIEStringAttr(**I, dwarf::DW_AT_name);
+ if (isType(C.getTag()) || C.getTag() == dwarf::DW_TAG_subprogram) {
+ StringRef Name = getDIEStringAttr(C, dwarf::DW_AT_name);
// ... and has a DW_AT_name attribute
if (!Name.empty()) {
- hashNestedType(**I, Name);
+ hashNestedType(C, Name);
continue;
}
}
- computeHash(**I);
+ computeHash(C);
}
// Following the last (or if there are no children), append a zero byte.
// ... take the least significant 8 bytes and return those. Our MD5
// implementation always returns its results in little endian, swap bytes
// appropriately.
- return *reinterpret_cast<support::ulittle64_t *>(Result + 8);
+ return support::endian::read64le(Result + 8);
}
/// This is based on the type signature computation given in section 7.27 of the
// ... take the least significant 8 bytes and return those. Our MD5
// implementation always returns its results in little endian, swap bytes
// appropriately.
- return *reinterpret_cast<support::ulittle64_t *>(Result + 8);
+ return support::endian::read64le(Result + 8);
}
/// This is based on the type signature computation given in section 7.27 of the
// ... take the least significant 8 bytes and return those. Our MD5
// implementation always returns its results in little endian, swap bytes
// appropriately.
- return *reinterpret_cast<support::ulittle64_t *>(Result + 8);
+ return support::endian::read64le(Result + 8);
}