llvm-project/llvm/lib/CodeGen/AsmPrinter/DwarfExpression.h

288 lines
9.7 KiB
C
Raw Normal View History

//===- llvm/CodeGen/DwarfExpression.h - Dwarf Compile Unit ------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains support for writing dwarf compile unit.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_CODEGEN_ASMPRINTER_DWARFEXPRESSION_H
#define LLVM_LIB_CODEGEN_ASMPRINTER_DWARFEXPRESSION_H
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/IR/DebugInfoMetadata.h"
#include <cassert>
#include <cstdint>
#include <iterator>
namespace llvm {
class AsmPrinter;
class APInt;
class ByteStreamer;
class DwarfUnit;
class DIELoc;
class TargetRegisterInfo;
/// Holds a DIExpression and keeps track of how many operands have been consumed
/// so far.
class DIExpressionCursor {
DIExpression::expr_op_iterator Start, End;
public:
DIExpressionCursor(const DIExpression *Expr) {
if (!Expr) {
assert(Start == End);
return;
}
Start = Expr->expr_op_begin();
End = Expr->expr_op_end();
}
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
DIExpressionCursor(ArrayRef<uint64_t> Expr)
: Start(Expr.begin()), End(Expr.end()) {}
DIExpressionCursor(const DIExpressionCursor &) = default;
/// Consume one operation.
Optional<DIExpression::ExprOperand> take() {
if (Start == End)
return None;
return *(Start++);
}
/// Consume N operations.
void consume(unsigned N) { std::advance(Start, N); }
/// Return the current operation.
Optional<DIExpression::ExprOperand> peek() const {
if (Start == End)
return None;
return *(Start);
}
/// Return the next operation.
Optional<DIExpression::ExprOperand> peekNext() const {
if (Start == End)
return None;
auto Next = Start.getNext();
if (Next == End)
return None;
return *Next;
}
/// Determine whether there are any operations left in this expression.
operator bool() const { return Start != End; }
DIExpression::expr_op_iterator begin() const { return Start; }
DIExpression::expr_op_iterator end() const { return End; }
/// Retrieve the fragment information, if any.
Optional<DIExpression::FragmentInfo> getFragmentInfo() const {
return DIExpression::getFragmentInfo(Start, End);
}
};
/// Base class containing the logic for constructing DWARF expressions
/// independently of whether they are emitted into a DIE or into a .debug_loc
/// entry.
class DwarfExpression {
protected:
/// Holds information about all subregisters comprising a register location.
struct Register {
int DwarfRegNo;
unsigned Size;
const char *Comment;
};
/// The register location, if any.
SmallVector<Register, 2> DwarfRegs;
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
/// Current Fragment Offset in Bits.
uint64_t OffsetInBits = 0;
unsigned DwarfVersion;
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
/// Sometimes we need to add a DW_OP_bit_piece to describe a subregister.
unsigned SubRegisterSizeInBits = 0;
unsigned SubRegisterOffsetInBits = 0;
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
/// The kind of location description being produced.
enum { Unknown = 0, Register, Memory, Implicit } LocationKind = Unknown;
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
/// Push a DW_OP_piece / DW_OP_bit_piece for emitting later, if one is needed
/// to represent a subregister.
void setSubRegisterPiece(unsigned SizeInBits, unsigned OffsetInBits) {
SubRegisterSizeInBits = SizeInBits;
SubRegisterOffsetInBits = OffsetInBits;
}
/// Add masking operations to stencil out a subregister.
void maskSubRegister();
/// Output a dwarf operand and an optional assembler comment.
virtual void emitOp(uint8_t Op, const char *Comment = nullptr) = 0;
/// Emit a raw signed value.
virtual void emitSigned(int64_t Value) = 0;
/// Emit a raw unsigned value.
virtual void emitUnsigned(uint64_t Value) = 0;
/// Return whether the given machine register is the frame register in the
/// current function.
virtual bool isFrameRegister(const TargetRegisterInfo &TRI, unsigned MachineReg) = 0;
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
/// Emit a DW_OP_reg operation. Note that this is only legal inside a DWARF
/// register location description.
void addReg(int DwarfReg, const char *Comment = nullptr);
/// Emit a DW_OP_breg operation.
void addBReg(int DwarfReg, int Offset);
/// Emit DW_OP_fbreg <Offset>.
void addFBReg(int Offset);
/// Emit a partial DWARF register operation.
///
/// \param MachineReg The register number.
/// \param MaxSize If the register must be composed from
/// sub-registers this is an upper bound
/// for how many bits the emitted DW_OP_piece
/// may cover.
///
/// If size and offset is zero an operation for the entire register is
/// emitted: Some targets do not provide a DWARF register number for every
/// register. If this is the case, this function will attempt to emit a DWARF
/// register by emitting a fragment of a super-register or by piecing together
/// multiple subregisters that alias the register.
///
/// \return false if no DWARF register exists for MachineReg.
bool addMachineReg(const TargetRegisterInfo &TRI, unsigned MachineReg,
unsigned MaxSize = ~1U);
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
/// Emit a DW_OP_piece or DW_OP_bit_piece operation for a variable fragment.
/// \param OffsetInBits This is an optional offset into the location that
/// is at the top of the DWARF stack.
void addOpPiece(unsigned SizeInBits, unsigned OffsetInBits = 0);
/// Emit a shift-right dwarf operation.
void addShr(unsigned ShiftBy);
/// Emit a bitwise and dwarf operation.
void addAnd(unsigned Mask);
/// Emit a DW_OP_stack_value, if supported.
///
/// The proper way to describe a constant value is DW_OP_constu <const>,
/// DW_OP_stack_value. Unfortunately, DW_OP_stack_value was not available
/// until DWARF 4, so we will continue to generate DW_OP_constu <const> for
/// DWARF 2 and DWARF 3. Technically, this is incorrect since DW_OP_const
/// <const> actually describes a value at a constant addess, not a constant
/// value. However, in the past there was no better way to describe a
/// constant value, so the producers and consumers started to rely on
/// heuristics to disambiguate the value vs. location status of the
/// expression. See PR21176 for more details.
void addStackValue();
~DwarfExpression() = default;
public:
DwarfExpression(unsigned DwarfVersion) : DwarfVersion(DwarfVersion) {}
/// This needs to be called last to commit any pending changes.
void finalize();
/// Emit a signed constant.
void addSignedConstant(int64_t Value);
/// Emit an unsigned constant.
void addUnsignedConstant(uint64_t Value);
/// Emit an unsigned constant.
void addUnsignedConstant(const APInt &Value);
bool isMemoryLocation() const { return LocationKind == Memory; }
bool isUnknownLocation() const { return LocationKind == Unknown; }
/// Lock this down to become a memory location description.
void setMemoryLocationKind() {
assert(LocationKind == Unknown);
LocationKind = Memory;
}
/// Emit a machine register location. As an optimization this may also consume
/// the prefix of a DwarfExpression if a more efficient representation for
/// combining the register location and the first operation exists.
///
/// \param FragmentOffsetInBits If this is one fragment out of a
/// fragmented
/// location, this is the offset of the
/// fragment inside the entire variable.
/// \return false if no DWARF register exists
/// for MachineReg.
bool addMachineRegExpression(const TargetRegisterInfo &TRI,
DIExpressionCursor &Expr, unsigned MachineReg,
unsigned FragmentOffsetInBits = 0);
/// Emit all remaining operations in the DIExpressionCursor.
///
/// \param FragmentOffsetInBits If this is one fragment out of multiple
/// locations, this is the offset of the
/// fragment inside the entire variable.
void addExpression(DIExpressionCursor &&Expr,
unsigned FragmentOffsetInBits = 0);
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
/// If applicable, emit an empty DW_OP_piece / DW_OP_bit_piece to advance to
/// the fragment described by \c Expr.
void addFragmentOffset(const DIExpression *Expr);
};
/// DwarfExpression implementation for .debug_loc entries.
class DebugLocDwarfExpression final : public DwarfExpression {
ByteStreamer &BS;
void emitOp(uint8_t Op, const char *Comment = nullptr) override;
void emitSigned(int64_t Value) override;
void emitUnsigned(uint64_t Value) override;
bool isFrameRegister(const TargetRegisterInfo &TRI,
unsigned MachineReg) override;
public:
DebugLocDwarfExpression(unsigned DwarfVersion, ByteStreamer &BS)
: DwarfExpression(DwarfVersion), BS(BS) {}
};
/// DwarfExpression implementation for singular DW_AT_location.
class DIEDwarfExpression final : public DwarfExpression {
const AsmPrinter &AP;
DwarfUnit &DU;
DIELoc &DIE;
void emitOp(uint8_t Op, const char *Comment = nullptr) override;
void emitSigned(int64_t Value) override;
void emitUnsigned(uint64_t Value) override;
bool isFrameRegister(const TargetRegisterInfo &TRI,
unsigned MachineReg) override;
public:
DIEDwarfExpression(const AsmPrinter &AP, DwarfUnit &DU, DIELoc &DIE);
DIELoc *finalize() {
DwarfExpression::finalize();
return &DIE;
}
};
} // end namespace llvm
#endif // LLVM_LIB_CODEGEN_ASMPRINTER_DWARFEXPRESSION_H