llvm-project/llvm/lib/CodeGen/AsmPrinter/AsmPrinterDwarf.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

327 lines
11 KiB
C++
Raw Normal View History

//===-- AsmPrinterDwarf.cpp - AsmPrinter Dwarf Support --------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the Dwarf emissions parts of AsmPrinter.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/Twine.h"
#include "llvm/BinaryFormat/Dwarf.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/DIE.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/MC/MCSection.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include <cstdint>
using namespace llvm;
#define DEBUG_TYPE "asm-printer"
//===----------------------------------------------------------------------===//
// Dwarf Emission Helper Routines
//===----------------------------------------------------------------------===//
/// EmitSLEB128 - emit the specified signed leb128 value.
void AsmPrinter::emitSLEB128(int64_t Value, const char *Desc) const {
if (isVerbose() && Desc)
OutStreamer->AddComment(Desc);
OutStreamer->emitSLEB128IntValue(Value);
}
void AsmPrinter::emitULEB128(uint64_t Value, const char *Desc,
unsigned PadTo) const {
if (isVerbose() && Desc)
OutStreamer->AddComment(Desc);
OutStreamer->emitULEB128IntValue(Value, PadTo);
}
/// Emit something like ".uleb128 Hi-Lo".
void AsmPrinter::emitLabelDifferenceAsULEB128(const MCSymbol *Hi,
const MCSymbol *Lo) const {
OutStreamer->emitAbsoluteSymbolDiffAsULEB128(Hi, Lo);
}
static const char *DecodeDWARFEncoding(unsigned Encoding) {
switch (Encoding) {
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_absptr:
return "absptr";
case dwarf::DW_EH_PE_omit:
return "omit";
case dwarf::DW_EH_PE_pcrel:
return "pcrel";
case dwarf::DW_EH_PE_uleb128:
return "uleb128";
case dwarf::DW_EH_PE_sleb128:
return "sleb128";
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_udata4:
return "udata4";
case dwarf::DW_EH_PE_udata8:
return "udata8";
case dwarf::DW_EH_PE_sdata4:
return "sdata4";
case dwarf::DW_EH_PE_sdata8:
return "sdata8";
case dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_udata4:
return "pcrel udata4";
case dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_sdata4:
return "pcrel sdata4";
case dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_udata8:
return "pcrel udata8";
case dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_sdata8:
return "pcrel sdata8";
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_udata4
:
return "indirect pcrel udata4";
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_sdata4
:
return "indirect pcrel sdata4";
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_udata8
:
return "indirect pcrel udata8";
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_pcrel | dwarf::DW_EH_PE_sdata8
:
return "indirect pcrel sdata8";
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_datarel |
dwarf::DW_EH_PE_sdata4:
return "indirect datarel sdata4";
case dwarf::DW_EH_PE_indirect | dwarf::DW_EH_PE_datarel |
dwarf::DW_EH_PE_sdata8:
return "indirect datarel sdata8";
}
2012-11-20 20:34:47 +00:00
return "<unknown encoding>";
}
/// EmitEncodingByte - Emit a .byte 42 directive that corresponds to an
/// encoding. If verbose assembly output is enabled, we output comments
/// describing the encoding. Desc is an optional string saying what the
/// encoding is specifying (e.g. "LSDA").
void AsmPrinter::emitEncodingByte(unsigned Val, const char *Desc) const {
if (isVerbose()) {
2013-12-04 22:29:02 +00:00
if (Desc)
OutStreamer->AddComment(Twine(Desc) + " Encoding = " +
Twine(DecodeDWARFEncoding(Val)));
else
OutStreamer->AddComment(Twine("Encoding = ") + DecodeDWARFEncoding(Val));
}
2012-11-20 20:34:47 +00:00
OutStreamer->emitIntValue(Val, 1);
}
/// GetSizeOfEncodedValue - Return the size of the encoding in bytes.
unsigned AsmPrinter::GetSizeOfEncodedValue(unsigned Encoding) const {
if (Encoding == dwarf::DW_EH_PE_omit)
return 0;
2012-11-20 20:34:47 +00:00
switch (Encoding & 0x07) {
2013-12-04 22:26:43 +00:00
default:
llvm_unreachable("Invalid encoded value.");
case dwarf::DW_EH_PE_absptr:
return MF->getDataLayout().getPointerSize();
2013-12-04 22:26:43 +00:00
case dwarf::DW_EH_PE_udata2:
return 2;
case dwarf::DW_EH_PE_udata4:
return 4;
case dwarf::DW_EH_PE_udata8:
return 8;
}
}
void AsmPrinter::emitTTypeReference(const GlobalValue *GV, unsigned Encoding) {
if (GV) {
const TargetLoweringObjectFile &TLOF = getObjFileLowering();
2012-11-20 20:34:47 +00:00
const MCExpr *Exp =
TLOF.getTTypeGlobalReference(GV, Encoding, TM, MMI, *OutStreamer);
OutStreamer->emitValue(Exp, GetSizeOfEncodedValue(Encoding));
} else
OutStreamer->emitIntValue(0, GetSizeOfEncodedValue(Encoding));
}
void AsmPrinter::emitDwarfSymbolReference(const MCSymbol *Label,
bool ForceOffset) const {
if (!ForceOffset) {
// On COFF targets, we have to emit the special .secrel32 directive.
if (MAI->needsDwarfSectionOffsetDirective()) {
assert(!isDwarf64() &&
"emitting DWARF64 is not implemented for COFF targets");
OutStreamer->emitCOFFSecRel32(Label, /*Offset=*/0);
return;
}
// If the format uses relocations with dwarf, refer to the symbol directly.
if (doesDwarfUseRelocationsAcrossSections()) {
OutStreamer->emitSymbolValue(Label, getDwarfOffsetByteSize());
return;
}
}
2012-11-20 20:34:47 +00:00
// Otherwise, emit it as a label difference from the start of the section.
emitLabelDifference(Label, Label->getSection().getBeginSymbol(),
getDwarfOffsetByteSize());
}
void AsmPrinter::emitDwarfStringOffset(DwarfStringPoolEntry S) const {
if (doesDwarfUseRelocationsAcrossSections()) {
assert(S.Symbol && "No symbol available");
emitDwarfSymbolReference(S.Symbol);
return;
}
// Just emit the offset directly; no need for symbol math.
OutStreamer->emitIntValue(S.Offset, getDwarfOffsetByteSize());
}
void AsmPrinter::emitDwarfOffset(const MCSymbol *Label, uint64_t Offset) const {
emitLabelPlusOffset(Label, Offset, getDwarfOffsetByteSize());
}
void AsmPrinter::emitDwarfLengthOrOffset(uint64_t Value) const {
assert(isDwarf64() || Value <= UINT32_MAX);
OutStreamer->emitIntValue(Value, getDwarfOffsetByteSize());
}
void AsmPrinter::emitDwarfUnitLength(uint64_t Length,
const Twine &Comment) const {
OutStreamer->emitDwarfUnitLength(Length, Comment);
}
MCSymbol *AsmPrinter::emitDwarfUnitLength(const Twine &Prefix,
const Twine &Comment) const {
return OutStreamer->emitDwarfUnitLength(Prefix, Comment);
}
void AsmPrinter::emitCallSiteOffset(const MCSymbol *Hi, const MCSymbol *Lo,
unsigned Encoding) const {
// The least significant 3 bits specify the width of the encoding
if ((Encoding & 0x7) == dwarf::DW_EH_PE_uleb128)
emitLabelDifferenceAsULEB128(Hi, Lo);
else
emitLabelDifference(Hi, Lo, GetSizeOfEncodedValue(Encoding));
}
void AsmPrinter::emitCallSiteValue(uint64_t Value, unsigned Encoding) const {
// The least significant 3 bits specify the width of the encoding
if ((Encoding & 0x7) == dwarf::DW_EH_PE_uleb128)
emitULEB128(Value);
else
OutStreamer->emitIntValue(Value, GetSizeOfEncodedValue(Encoding));
}
//===----------------------------------------------------------------------===//
// Dwarf Lowering Routines
//===----------------------------------------------------------------------===//
void AsmPrinter::emitCFIInstruction(const MCCFIInstruction &Inst) const {
switch (Inst.getOperation()) {
default:
llvm_unreachable("Unexpected instruction");
case MCCFIInstruction::OpDefCfaOffset:
OutStreamer->emitCFIDefCfaOffset(Inst.getOffset());
break;
case MCCFIInstruction::OpAdjustCfaOffset:
OutStreamer->emitCFIAdjustCfaOffset(Inst.getOffset());
break;
case MCCFIInstruction::OpDefCfa:
OutStreamer->emitCFIDefCfa(Inst.getRegister(), Inst.getOffset());
break;
case MCCFIInstruction::OpDefCfaRegister:
OutStreamer->emitCFIDefCfaRegister(Inst.getRegister());
break;
case MCCFIInstruction::OpLLVMDefAspaceCfa:
OutStreamer->emitCFILLVMDefAspaceCfa(Inst.getRegister(), Inst.getOffset(),
Inst.getAddressSpace());
break;
case MCCFIInstruction::OpOffset:
OutStreamer->emitCFIOffset(Inst.getRegister(), Inst.getOffset());
break;
case MCCFIInstruction::OpRegister:
OutStreamer->emitCFIRegister(Inst.getRegister(), Inst.getRegister2());
break;
case MCCFIInstruction::OpWindowSave:
OutStreamer->emitCFIWindowSave();
break;
case MCCFIInstruction::OpNegateRAState:
OutStreamer->emitCFINegateRAState();
break;
case MCCFIInstruction::OpSameValue:
OutStreamer->emitCFISameValue(Inst.getRegister());
break;
case MCCFIInstruction::OpGnuArgsSize:
OutStreamer->emitCFIGnuArgsSize(Inst.getOffset());
break;
case MCCFIInstruction::OpEscape:
OutStreamer->AddComment(Inst.getComment());
OutStreamer->emitCFIEscape(Inst.getValues());
break;
case MCCFIInstruction::OpRestore:
OutStreamer->emitCFIRestore(Inst.getRegister());
break;
case MCCFIInstruction::OpUndefined:
OutStreamer->emitCFIUndefined(Inst.getRegister());
break;
[CodeGen] Async unwind - add a pass to fix CFI information This pass inserts the necessary CFI instructions to compensate for the inconsistency of the call-frame information caused by linear (non-CGA aware) nature of the unwind tables. Unlike the `CFIInstrInserer` pass, this one almost always emits only `.cfi_remember_state`/`.cfi_restore_state`, which results in smaller unwind tables and also transparently handles custom unwind info extensions like CFA offset adjustement and save locations of SVE registers. This pass takes advantage of the constraints taht LLVM imposes on the placement of save/restore points (cf. `ShrinkWrap.cpp`): * there is a single basic block, containing the function prologue * possibly multiple epilogue blocks, where each epilogue block is complete and self-contained, i.e. CSR restore instructions (and the corresponding CFI instructions are not split across two or more blocks. * prologue and epilogue blocks are outside of any loops Thus, during execution, at the beginning and at the end of each basic block the function can be in one of two states: - "has a call frame", if the function has executed the prologue, or has not executed any epilogue - "does not have a call frame", if the function has not executed the prologue, or has executed an epilogue These properties can be computed for each basic block by a single RPO traversal. From the point of view of the unwind tables, the "has/does not have call frame" state at beginning of each block is determined by the state at the end of the previous block, in layout order. Where these states differ, we insert compensating CFI instructions, which come in two flavours: - CFI instructions, which reset the unwind table state to the initial one. This is done by a target specific hook and is expected to be trivial to implement, for example it could be: ``` .cfi_def_cfa <sp>, 0 .cfi_same_value <rN> .cfi_same_value <rN-1> ... ``` where `<rN>` are the callee-saved registers. - CFI instructions, which reset the unwind table state to the one created by the function prologue. These are the sequence: ``` .cfi_restore_state .cfi_remember_state ``` In this case we also insert a `.cfi_remember_state` after the last CFI instruction in the function prologue. Reviewed By: MaskRay, danielkiss, chill Differential Revision: https://reviews.llvm.org/D114545
2022-04-11 12:08:26 +01:00
case MCCFIInstruction::OpRememberState:
OutStreamer->emitCFIRememberState();
break;
case MCCFIInstruction::OpRestoreState:
OutStreamer->emitCFIRestoreState();
break;
}
}
void AsmPrinter::emitDwarfDIE(const DIE &Die) const {
// Emit the code (index) for the abbreviation.
if (isVerbose())
OutStreamer->AddComment("Abbrev [" + Twine(Die.getAbbrevNumber()) + "] 0x" +
Twine::utohexstr(Die.getOffset()) + ":0x" +
Twine::utohexstr(Die.getSize()) + " " +
dwarf::TagString(Die.getTag()));
emitULEB128(Die.getAbbrevNumber());
// Emit the DIE attribute values.
for (const auto &V : Die.values()) {
dwarf::Attribute Attr = V.getAttribute();
assert(V.getForm() && "Too many attributes for DIE (check abbreviation)");
if (isVerbose()) {
OutStreamer->AddComment(dwarf::AttributeString(Attr));
if (Attr == dwarf::DW_AT_accessibility)
Reapply "AsmPrinter: Change DIEValue to be stored by value" This reverts commit r238350, effectively reapplying r238349 after fixing (all?) the problems, all somehow related to how I was using `AlignedArrayCharUnion<>` inside `DIEValue`: - MSVC can only handle `sizeof()` on types, not values. Change the assert. - GCC doesn't know the `is_trivially_copyable` type trait. Instead of asserting it, add destructors. - Call placement new even when constructing POD (i.e., the pointers). - Instead of copying the char buffer, copy the casted classes. I've left in a couple of `static_assert`s that I think both MSVC and GCC know how to handle. If the bots disagree with me, I'll remove them. - Check that the constructed type is either standard layout or a pointer. This protects against a programming error: we really want the "small" `DIEValue`s to be small and simple, so don't accidentally change them not to be. - Similarly, check that the size of the buffer is no bigger than a `uint64_t` or a pointer. (I thought checking against `sizeof(uint64_t)` would be good enough, but Chandler suggested that pointers might sometimes be bigger than that in the context of sanitizers.) I've also committed r238359 in the meantime, which introduces a DIEValue.def to simplify dispatching between the various types (thanks to a review comment by David Blaikie). Without that, this commit would be almost unintelligible. Here's the original commit message: -- Change `DIEValue` to be stored/passed/etc. by value, instead of reference. It's now a discriminated union, with a `Val` field storing the actual type. The classes that used to inherit from `DIEValue` no longer do. There are two categories of these: - Small values fit in a single pointer and are stored by value. - Large values require auxiliary storage, and are stored by reference. The only non-mechanical change is to tools/dsymutil/DwarfLinker.cpp. It was relying on `DIEInteger`s being passed around by reference, so I replaced that assumption with a `PatchLocation` type that stores a safe reference to where the `DIEInteger` lives instead. This commit causes a temporary regression in memory usage, since I've left merging `DIEAbbrevData` into `DIEValue` for a follow-up commit. I measured an increase from 845 MB to 879 MB, around 3.9%. The follow-up drops it lower than the starting point, and I've only recently brought the memory this low anyway, so I'm committing these changes separately to keep them incremental. (I also considered swapping the commits, but the other one first would cause a lot more code churn.) (I'm looking at `llc` memory usage on `verify-uselistorder.lto.opt.bc`; see r236629 for details.) -- llvm-svn: 238362
2015-05-27 22:14:58 +00:00
OutStreamer->AddComment(
dwarf::AccessibilityString(V.getDIEInteger().getValue()));
}
// Emit an attribute using the defined form.
V.emitValue(this);
}
// Emit the DIE children if any.
if (Die.hasChildren()) {
for (const auto &Child : Die.children())
emitDwarfDIE(Child);
OutStreamer->AddComment("End Of Children Mark");
emitInt8(0);
}
}
void AsmPrinter::emitDwarfAbbrev(const DIEAbbrev &Abbrev) const {
// Emit the abbreviations code (base 1 index.)
emitULEB128(Abbrev.getNumber(), "Abbreviation Code");
// Emit the abbreviations data.
Abbrev.Emit(this);
}