Reland D79501 "[DebugInfo] Fix handling DW_OP_call_ref in DWARF64 units."

With a fix to uninitialized EndOffset.

DW_OP_call_ref is the only operation that has an operand which depends
on the DWARF format. The patch fixes handling that operation in DWARF64
units.

Differential Revision: https://reviews.llvm.org/D79501

11 files changed, 110 insertions, 16 deletions

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFExpression.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFExpression.h
index 4bbff49..2892930 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFExpression.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFExpression.h
@@ -12,6 +12,8 @@
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/iterator.h"
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/Support/DataExtractor.h"
 
 namespace llvm {
@@ -88,7 +90,8 @@ public:
     uint64_t getRawOperand(unsigned Idx) { return Operands[Idx]; }
     uint64_t getOperandEndOffset(unsigned Idx) { return OperandEndOffsets[Idx]; }
     uint64_t getEndOffset() { return EndOffset; }
-    bool extract(DataExtractor Data, uint8_t AddressSize, uint64_t Offset);
+    bool extract(DataExtractor Data, uint8_t AddressSize, uint64_t Offset,
+                 Optional<dwarf::DwarfFormat> Format);
     bool isError() { return Error; }
     bool print(raw_ostream &OS, const DWARFExpression *Expr,
                const MCRegisterInfo *RegInfo, DWARFUnit *U, bool isEH);
@@ -107,7 +110,7 @@ public:
         : Expr(Expr), Offset(Offset) {
       Op.Error =
           Offset >= Expr->Data.getData().size() ||
-          !Op.extract(Expr->Data, Expr->AddressSize, Offset);
+          !Op.extract(Expr->Data, Expr->AddressSize, Offset, Expr->Format);
     }
 
   public:
@@ -115,7 +118,7 @@ public:
       Offset = Op.isError() ? Expr->Data.getData().size() : Op.EndOffset;
       Op.Error =
           Offset >= Expr->Data.getData().size() ||
-          !Op.extract(Expr->Data, Expr->AddressSize, Offset);
+          !Op.extract(Expr->Data, Expr->AddressSize, Offset, Expr->Format);
       return Op;
     }
 
@@ -127,8 +130,9 @@ public:
     friend bool operator==(const iterator &, const iterator &);
   };
 
-  DWARFExpression(DataExtractor Data, uint8_t AddressSize)
-      : Data(Data), AddressSize(AddressSize) {
+  DWARFExpression(DataExtractor Data, uint8_t AddressSize,
+                  Optional<dwarf::DwarfFormat> Format = None)
+      : Data(Data), AddressSize(AddressSize), Format(Format) {
     assert(AddressSize == 8 || AddressSize == 4 || AddressSize == 2);
   }
 
@@ -143,6 +147,7 @@ public:
 private:
   DataExtractor Data;
   uint8_t AddressSize;
+  Optional<dwarf::DwarfFormat> Format;
 };
 
 inline bool operator==(const DWARFExpression::iterator &LHS,
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index cf1e269..25b973e 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -2337,7 +2337,7 @@ void DwarfDebug::emitDebugLocEntry(ByteStreamer &Streamer,
   DWARFDataExtractor Data(StringRef(DebugLocs.getBytes(Entry).data(),
                                     DebugLocs.getBytes(Entry).size()),
                           Asm->getDataLayout().isLittleEndian(), PtrSize);
-  DWARFExpression Expr(Data, PtrSize);
+  DWARFExpression Expr(Data, PtrSize, Asm->OutContext.getDwarfFormat());
 
   using Encoding = DWARFExpression::Operation::Encoding;
   uint64_t Offset = 0;
diff --git a/llvm/lib/DWARFLinker/DWARFLinker.cpp b/llvm/lib/DWARFLinker/DWARFLinker.cpp
index 1d7ef35..fff3763 100644
--- a/llvm/lib/DWARFLinker/DWARFLinker.cpp
+++ b/llvm/lib/DWARFLinker/DWARFLinker.cpp
@@ -1008,7 +1008,8 @@ unsigned DWARFLinker::DIECloner::cloneBlockAttribute(
     DWARFUnit &OrigUnit = Unit.getOrigUnit();
     DataExtractor Data(StringRef((const char *)Bytes.data(), Bytes.size()),
                        IsLittleEndian, OrigUnit.getAddressByteSize());
-    DWARFExpression Expr(Data, OrigUnit.getAddressByteSize());
+    DWARFExpression Expr(Data, OrigUnit.getAddressByteSize(),
+                         OrigUnit.getFormParams().Format);
     cloneExpression(Data, Expr, File, Unit, Buffer);
     Bytes = Buffer;
   }
@@ -2134,7 +2135,8 @@ uint64_t DWARFLinker::DIECloner::cloneAllCompileUnits(
         DataExtractor Data(Bytes, IsLittleEndian,
                            OrigUnit.getAddressByteSize());
         cloneExpression(Data,
-                        DWARFExpression(Data, OrigUnit.getAddressByteSize()),
+                        DWARFExpression(Data, OrigUnit.getAddressByteSize(),
+                                        OrigUnit.getFormParams().Format),
                         File, *CurrentUnit, Buffer);
       };
       Emitter->emitLocationsForUnit(*CurrentUnit, DwarfContext, ProcessExpr);
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDebugFrame.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDebugFrame.cpp
index 7c1280d..5b38b29 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDebugFrame.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDebugFrame.cpp
@@ -130,6 +130,9 @@ Error CFIProgram::parse(DWARFDataExtractor Data, uint64_t *Offset,
           DataExtractor Extractor(
               Data.getData().slice(*Offset, *Offset + ExprLength),
               Data.isLittleEndian(), Data.getAddressSize());
+          // Note. We do not pass the DWARF format to DWARFExpression, because
+          // DW_OP_call_ref, the only operation which depends on the format, is
+          // prohibited in call frame instructions, see sec. 6.4.2 in DWARFv5.
           Instructions.back().Expression =
               DWARFExpression(Extractor, Data.getAddressSize());
           *Offset += ExprLength;
@@ -143,6 +146,9 @@ Error CFIProgram::parse(DWARFDataExtractor Data, uint64_t *Offset,
           DataExtractor Extractor(
               Data.getData().slice(*Offset, *Offset + BlockLength),
               Data.isLittleEndian(), Data.getAddressSize());
+          // Note. We do not pass the DWARF format to DWARFExpression, because
+          // DW_OP_call_ref, the only operation which depends on the format, is
+          // prohibited in call frame instructions, see sec. 6.4.2 in DWARFv5.
           Instructions.back().Expression =
               DWARFExpression(Extractor, Data.getAddressSize());
           *Offset += BlockLength;
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDebugLoc.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDebugLoc.cpp
index 17f0b7f..f381263 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDebugLoc.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDebugLoc.cpp
@@ -110,6 +110,10 @@ static void dumpExpression(raw_ostream &OS, ArrayRef<uint8_t> Data,
                            bool IsLittleEndian, unsigned AddressSize,
                            const MCRegisterInfo *MRI, DWARFUnit *U) {
   DWARFDataExtractor Extractor(Data, IsLittleEndian, AddressSize);
+  // Note. We do not pass any format to DWARFExpression, even if the
+  // corresponding unit is known. For now, there is only one operation,
+  // DW_OP_call_ref, which depends on the format; it is rarely used, and
+  // is unexpected in location tables.
   DWARFExpression(Extractor, AddressSize).print(OS, MRI, U);
 }
 
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
index f93f329..81a6b5d 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
@@ -79,7 +79,8 @@ static void dumpLocation(raw_ostream &OS, DWARFFormValue &FormValue,
     ArrayRef<uint8_t> Expr = *FormValue.getAsBlock();
     DataExtractor Data(StringRef((const char *)Expr.data(), Expr.size()),
                        Ctx.isLittleEndian(), 0);
-    DWARFExpression(Data, U->getAddressByteSize()).print(OS, MRI, U);
+    DWARFExpression(Data, U->getAddressByteSize(), U->getFormParams().Format)
+        .print(OS, MRI, U);
     return;
   }
 
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFExpression.cpp b/llvm/lib/DebugInfo/DWARF/DWARFExpression.cpp
index 379b88c..605236bc 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFExpression.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFExpression.cpp
@@ -8,7 +8,6 @@
 
 #include "llvm/DebugInfo/DWARF/DWARFExpression.h"
 #include "llvm/DebugInfo/DWARF/DWARFUnit.h"
-#include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Support/Format.h"
 #include <cassert>
@@ -119,7 +118,8 @@ static DWARFExpression::Operation::Description getOpDesc(unsigned OpCode) {
 }
 
 bool DWARFExpression::Operation::extract(DataExtractor Data,
-                                         uint8_t AddressSize, uint64_t Offset) {
+                                         uint8_t AddressSize, uint64_t Offset,
+                                         Optional<DwarfFormat> Format) {
   Opcode = Data.getU8(&Offset);
 
   Desc = getOpDesc(Opcode);
@@ -135,6 +135,7 @@ bool DWARFExpression::Operation::extract(DataExtractor Data,
     if (Size == Operation::SizeNA)
       break;
 
+    EndOffset = Offset;
     switch (Size & ~Operation::SignBit) {
     case Operation::Size1:
       Operands[Operand] = Data.getU8(&Offset);
@@ -158,8 +159,10 @@ bool DWARFExpression::Operation::extract(DataExtractor Data,
       Operands[Operand] = Data.getUnsigned(&Offset, AddressSize);
       break;
     case Operation::SizeRefAddr:
-      // TODO: Add support for 64-bit DWARF format.
-      Operands[Operand] = Data.getU32(&Offset);
+      if (!Format)
+        return false;
+      Operands[Operand] =
+          Data.getUnsigned(&Offset, dwarf::getDwarfOffsetByteSize(*Format));
       break;
     case Operation::SizeLEB:
       if (Signed)
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp b/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
index c7d3974..4f12878 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFVerifier.cpp
@@ -486,7 +486,8 @@ unsigned DWARFVerifier::verifyDebugInfoAttribute(const DWARFDie &Die,
       DWARFUnit *U = Die.getDwarfUnit();
       for (const auto &Entry : *Loc) {
         DataExtractor Data(toStringRef(Entry.Expr), DCtx.isLittleEndian(), 0);
-        DWARFExpression Expression(Data, U->getAddressByteSize());
+        DWARFExpression Expression(Data, U->getAddressByteSize(),
+                                   U->getFormParams().Format);
         bool Error = any_of(Expression, [](DWARFExpression::Operation &Op) {
           return Op.isError();
         });
@@ -1294,7 +1295,8 @@ static bool isVariableIndexable(const DWARFDie &Die, DWARFContext &DCtx) {
   for (const auto &Entry : *Loc) {
     DataExtractor Data(toStringRef(Entry.Expr), DCtx.isLittleEndian(),
                        U->getAddressByteSize());
-    DWARFExpression Expression(Data, U->getAddressByteSize());
+    DWARFExpression Expression(Data, U->getAddressByteSize(),
+                               U->getFormParams().Format);
     bool IsInteresting = any_of(Expression, [](DWARFExpression::Operation &Op) {
       return !Op.isError() && (Op.getCode() == DW_OP_addr ||
                                Op.getCode() == DW_OP_form_tls_address ||
diff --git a/llvm/test/DebugInfo/X86/DW_OP_call_ref_dwarf64.s b/llvm/test/DebugInfo/X86/DW_OP_call_ref_dwarf64.s
new file mode 100644
index 0000000..5031e14
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/DW_OP_call_ref_dwarf64.s
@@ -0,0 +1,42 @@
+# RUN: llvm-mc -triple x86_64 %s -filetype=obj -o %t.o
+# RUN: llvm-dwarfdump -debug-info %t.o | FileCheck %s
+# RUN: llvm-dwarfdump -verify %t.o | FileCheck %s --check-prefix=VERIFY
+
+# CHECK: DW_TAG_variable
+# CHECK-NEXT: DW_AT_location (DW_OP_call_ref 0x1100223344)
+
+# VERIFY-NOT: error: DIE contains invalid DWARF expression:
+# VERIFY: No errors.
+
+    .section .debug_abbrev,"",@progbits
+    .uleb128 1                      # Abbreviation Code
+    .uleb128 17                     # DW_TAG_compile_unit
+    .byte 1                         # DW_CHILDREN_yes
+    .byte 0                         # EOM(1)
+    .byte 0                         # EOM(2)
+    .uleb128 5                      # Abbreviation Code
+    .uleb128 52                     # DW_TAG_variable
+    .byte 0                         # DW_CHILDREN_no
+    .uleb128 2                      # DW_AT_location
+    .uleb128 24                     # DW_FORM_exprloc
+    .byte 0                         # EOM(1)
+    .byte 0                         # EOM(2)
+    .byte 0                         # EOM(3)
+
+    .section .debug_info,"",@progbits
+    .long 0xffffffff                # DWARF64 mark
+    .quad .Lcu_end-.Lcu_start       # Length of Unit
+.Lcu_start:
+    .short 5                        # DWARF version number
+    .byte 1                         # DW_UT_compile
+    .byte 8                         # Address Size
+    .quad .debug_abbrev             # Offset Into Abbrev. Section
+    .uleb128 1                      # Abbrev [1] DW_TAG_compile_unit
+    .uleb128 5                      # Abbrev [5] DW_TAG_variable
+    .byte .Lloc_end-.Lloc_begin     # DW_AT_location
+.Lloc_begin:
+    .byte 154                       # DW_OP_call_ref
+    .quad 0x1100223344              # Offset
+.Lloc_end:
+    .byte 0                         # End Of Children Mark
+.Lcu_end:
diff --git a/llvm/test/DebugInfo/X86/DW_OP_call_ref_unexpected.s b/llvm/test/DebugInfo/X86/DW_OP_call_ref_unexpected.s
new file mode 100644
index 0000000..036e044
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/DW_OP_call_ref_unexpected.s
@@ -0,0 +1,28 @@
+# RUN: llvm-mc -filetype=obj -triple=x86_64 %s -o %t.o
+# RUN: llvm-dwarfdump -debug-loc %t.o | FileCheck %s
+
+# This checks that we do not try to interpret DW_OP_call_ref if it is
+# encountered in a location table.
+
+# CHECK: .debug_loc contents:
+# CHECK-NEXT: 0x00000000:
+# CHECK-NEXT:   (0x0000000000000000, 0x0000000000000015): <decoding error>
+
+    .section .debug_loc, "", @progbits
+    .quad 0                         # Beginning address offset
+    .quad 0x15                      # Ending address offset
+    .short .LDescrEnd-.LDescrBegin  # Location description length
+.LDescrBegin:
+    .byte 0x9a                      # DW_OP_call_ref
+    .long 0xff
+.LDescrEnd:
+    .quad 0, 0                      # EOL entry
+
+# A dummy CU to provide the parser of .debug_loc with the address size.
+    .section .debug_info,"",@progbits
+    .long .LCUEnd-.LCUBegin         # Length of Unit
+.LCUBegin:
+    .short 4                        # DWARF version number
+    .long 0                         # Offset Into Abbrev. Section
+    .byte 8                         # Address Size
+.LCUEnd:
diff --git a/llvm/tools/llvm-dwarfdump/Statistics.cpp b/llvm/tools/llvm-dwarfdump/Statistics.cpp
index f1f37c9..18b4c40 100644
--- a/llvm/tools/llvm-dwarfdump/Statistics.cpp
+++ b/llvm/tools/llvm-dwarfdump/Statistics.cpp
@@ -248,7 +248,8 @@ static void collectStatsForDie(DWARFDie Die, std::string FnPrefix,
     DWARFUnit *U = Die.getDwarfUnit();
     DataExtractor Data(toStringRef(D),
                        Die.getDwarfUnit()->getContext().isLittleEndian(), 0);
-    DWARFExpression Expression(Data, U->getAddressByteSize());
+    DWARFExpression Expression(Data, U->getAddressByteSize(),
+                               U->getFormParams().Format);
     // Consider the expression containing the DW_OP_entry_value as
     // an entry value.
     return llvm::any_of(Expression, [](DWARFExpression::Operation &Op) {