diff options
Diffstat (limited to 'contrib/llvm-project/llvm/tools/llvm-dwarfdump')
| -rw-r--r-- | contrib/llvm-project/llvm/tools/llvm-dwarfdump/Statistics.cpp | 413 | ||||
| -rw-r--r-- | contrib/llvm-project/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp | 646 |
2 files changed, 1059 insertions, 0 deletions
diff --git a/contrib/llvm-project/llvm/tools/llvm-dwarfdump/Statistics.cpp b/contrib/llvm-project/llvm/tools/llvm-dwarfdump/Statistics.cpp new file mode 100644 index 000000000000..f26369b935cb --- /dev/null +++ b/contrib/llvm-project/llvm/tools/llvm-dwarfdump/Statistics.cpp @@ -0,0 +1,413 @@ +#include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/StringSet.h" +#include "llvm/DebugInfo/DIContext.h" +#include "llvm/DebugInfo/DWARF/DWARFContext.h" +#include "llvm/DebugInfo/DWARF/DWARFDebugLoc.h" +#include "llvm/Object/ObjectFile.h" + +#define DEBUG_TYPE "dwarfdump" +using namespace llvm; +using namespace object; + +/// Holds statistics for one function (or other entity that has a PC range and +/// contains variables, such as a compile unit). +struct PerFunctionStats { + /// Number of inlined instances of this function. + unsigned NumFnInlined = 0; + /// Number of inlined instances that have abstract origins. + unsigned NumAbstractOrigins = 0; + /// Number of variables and parameters with location across all inlined + /// instances. + unsigned TotalVarWithLoc = 0; + /// Number of constants with location across all inlined instances. + unsigned ConstantMembers = 0; + /// List of all Variables and parameters in this function. + StringSet<> VarsInFunction; + /// Compile units also cover a PC range, but have this flag set to false. + bool IsFunction = false; + /// Verify function definition has PC addresses (for detecting when + /// a function has been inlined everywhere). + bool HasPCAddresses = false; + /// Function has source location information. + bool HasSourceLocation = false; + /// Number of function parameters. + unsigned NumParams = 0; + /// Number of function parameters with source location. + unsigned NumParamSourceLocations = 0; + /// Number of function parameters with type. + unsigned NumParamTypes = 0; + /// Number of function parameters with a DW_AT_location. + unsigned NumParamLocations = 0; + /// Number of variables. + unsigned NumVars = 0; + /// Number of variables with source location. + unsigned NumVarSourceLocations = 0; + /// Number of variables wtih type. + unsigned NumVarTypes = 0; + /// Number of variables wtih DW_AT_location. + unsigned NumVarLocations = 0; +}; + +/// Holds accumulated global statistics about DIEs. +struct GlobalStats { + /// Total number of PC range bytes covered by DW_AT_locations. + unsigned ScopeBytesCovered = 0; + /// Total number of PC range bytes in each variable's enclosing scope, + /// starting from the first definition of the variable. + unsigned ScopeBytesFromFirstDefinition = 0; + /// Total number of call site entries (DW_TAG_call_site) or + /// (DW_AT_call_file & DW_AT_call_line). + unsigned CallSiteEntries = 0; + /// Total byte size of concrete functions. This byte size includes + /// inline functions contained in the concrete functions. + uint64_t FunctionSize = 0; + /// Total byte size of inlined functions. This is the total number of bytes + /// for the top inline functions within concrete functions. This can help + /// tune the inline settings when compiling to match user expectations. + uint64_t InlineFunctionSize = 0; +}; + +/// Extract the low pc from a Die. +static uint64_t getLowPC(DWARFDie Die) { + auto RangesOrError = Die.getAddressRanges(); + DWARFAddressRangesVector Ranges; + if (RangesOrError) + Ranges = RangesOrError.get(); + else + llvm::consumeError(RangesOrError.takeError()); + if (Ranges.size()) + return Ranges[0].LowPC; + return dwarf::toAddress(Die.find(dwarf::DW_AT_low_pc), 0); +} + +/// Collect debug info quality metrics for one DIE. +static void collectStatsForDie(DWARFDie Die, std::string FnPrefix, + std::string VarPrefix, uint64_t ScopeLowPC, + uint64_t BytesInScope, uint32_t InlineDepth, + StringMap<PerFunctionStats> &FnStatMap, + GlobalStats &GlobalStats) { + bool HasLoc = false; + bool HasSrcLoc = false; + bool HasType = false; + bool IsArtificial = false; + uint64_t BytesCovered = 0; + uint64_t OffsetToFirstDefinition = 0; + + if (Die.getTag() == dwarf::DW_TAG_call_site) { + GlobalStats.CallSiteEntries++; + return; + } + + if (Die.getTag() != dwarf::DW_TAG_formal_parameter && + Die.getTag() != dwarf::DW_TAG_variable && + Die.getTag() != dwarf::DW_TAG_member) { + // Not a variable or constant member. + return; + } + + if (Die.findRecursively(dwarf::DW_AT_decl_file) && + Die.findRecursively(dwarf::DW_AT_decl_line)) + HasSrcLoc = true; + + if (Die.findRecursively(dwarf::DW_AT_type)) + HasType = true; + + if (Die.find(dwarf::DW_AT_artificial)) + IsArtificial = true; + + if (Die.find(dwarf::DW_AT_const_value)) { + // This catches constant members *and* variables. + HasLoc = true; + BytesCovered = BytesInScope; + } else { + if (Die.getTag() == dwarf::DW_TAG_member) { + // Non-const member. + return; + } + // Handle variables and function arguments. + auto FormValue = Die.find(dwarf::DW_AT_location); + HasLoc = FormValue.hasValue(); + if (HasLoc) { + // Get PC coverage. + if (auto DebugLocOffset = FormValue->getAsSectionOffset()) { + auto *DebugLoc = Die.getDwarfUnit()->getContext().getDebugLoc(); + if (auto List = DebugLoc->getLocationListAtOffset(*DebugLocOffset)) { + for (auto Entry : List->Entries) + BytesCovered += Entry.End - Entry.Begin; + if (List->Entries.size()) { + uint64_t FirstDef = List->Entries[0].Begin; + uint64_t UnitOfs = getLowPC(Die.getDwarfUnit()->getUnitDIE()); + // Ranges sometimes start before the lexical scope. + if (UnitOfs + FirstDef >= ScopeLowPC) + OffsetToFirstDefinition = UnitOfs + FirstDef - ScopeLowPC; + // Or even after it. Count that as a failure. + if (OffsetToFirstDefinition > BytesInScope) + OffsetToFirstDefinition = 0; + } + } + assert(BytesInScope); + } else { + // Assume the entire range is covered by a single location. + BytesCovered = BytesInScope; + } + } + } + + // Collect PC range coverage data. + auto &FnStats = FnStatMap[FnPrefix]; + if (DWARFDie D = + Die.getAttributeValueAsReferencedDie(dwarf::DW_AT_abstract_origin)) + Die = D; + // By using the variable name + the path through the lexical block tree, the + // keys are consistent across duplicate abstract origins in different CUs. + std::string VarName = StringRef(Die.getName(DINameKind::ShortName)); + FnStats.VarsInFunction.insert(VarPrefix + VarName); + if (BytesInScope) { + FnStats.TotalVarWithLoc += (unsigned)HasLoc; + // Adjust for the fact the variables often start their lifetime in the + // middle of the scope. + BytesInScope -= OffsetToFirstDefinition; + // Turns out we have a lot of ranges that extend past the lexical scope. + GlobalStats.ScopeBytesCovered += std::min(BytesInScope, BytesCovered); + GlobalStats.ScopeBytesFromFirstDefinition += BytesInScope; + assert(GlobalStats.ScopeBytesCovered <= + GlobalStats.ScopeBytesFromFirstDefinition); + } else if (Die.getTag() == dwarf::DW_TAG_member) { + FnStats.ConstantMembers++; + } else { + FnStats.TotalVarWithLoc += (unsigned)HasLoc; + } + if (!IsArtificial) { + if (Die.getTag() == dwarf::DW_TAG_formal_parameter) { + FnStats.NumParams++; + if (HasType) + FnStats.NumParamTypes++; + if (HasSrcLoc) + FnStats.NumParamSourceLocations++; + if (HasLoc) + FnStats.NumParamLocations++; + } else if (Die.getTag() == dwarf::DW_TAG_variable) { + FnStats.NumVars++; + if (HasType) + FnStats.NumVarTypes++; + if (HasSrcLoc) + FnStats.NumVarSourceLocations++; + if (HasLoc) + FnStats.NumVarLocations++; + } + } +} + +/// Recursively collect debug info quality metrics. +static void collectStatsRecursive(DWARFDie Die, std::string FnPrefix, + std::string VarPrefix, uint64_t ScopeLowPC, + uint64_t BytesInScope, uint32_t InlineDepth, + StringMap<PerFunctionStats> &FnStatMap, + GlobalStats &GlobalStats) { + // Handle any kind of lexical scope. + const dwarf::Tag Tag = Die.getTag(); + const bool IsFunction = Tag == dwarf::DW_TAG_subprogram; + const bool IsBlock = Tag == dwarf::DW_TAG_lexical_block; + const bool IsInlinedFunction = Tag == dwarf::DW_TAG_inlined_subroutine; + if (IsFunction || IsInlinedFunction || IsBlock) { + + // Reset VarPrefix when entering a new function. + if (Die.getTag() == dwarf::DW_TAG_subprogram || + Die.getTag() == dwarf::DW_TAG_inlined_subroutine) + VarPrefix = "v"; + + // Ignore forward declarations. + if (Die.find(dwarf::DW_AT_declaration)) + return; + + // Check for call sites. + if (Die.find(dwarf::DW_AT_call_file) && Die.find(dwarf::DW_AT_call_line)) + GlobalStats.CallSiteEntries++; + + // PC Ranges. + auto RangesOrError = Die.getAddressRanges(); + if (!RangesOrError) { + llvm::consumeError(RangesOrError.takeError()); + return; + } + + auto Ranges = RangesOrError.get(); + uint64_t BytesInThisScope = 0; + for (auto Range : Ranges) + BytesInThisScope += Range.HighPC - Range.LowPC; + ScopeLowPC = getLowPC(Die); + + // Count the function. + if (!IsBlock) { + StringRef Name = Die.getName(DINameKind::LinkageName); + if (Name.empty()) + Name = Die.getName(DINameKind::ShortName); + FnPrefix = Name; + // Skip over abstract origins. + if (Die.find(dwarf::DW_AT_inline)) + return; + // We've seen an (inlined) instance of this function. + auto &FnStats = FnStatMap[Name]; + if (IsInlinedFunction) { + FnStats.NumFnInlined++; + if (Die.findRecursively(dwarf::DW_AT_abstract_origin)) + FnStats.NumAbstractOrigins++; + } + FnStats.IsFunction = true; + if (BytesInThisScope && !IsInlinedFunction) + FnStats.HasPCAddresses = true; + std::string FnName = StringRef(Die.getName(DINameKind::ShortName)); + if (Die.findRecursively(dwarf::DW_AT_decl_file) && + Die.findRecursively(dwarf::DW_AT_decl_line)) + FnStats.HasSourceLocation = true; + } + + if (BytesInThisScope) { + BytesInScope = BytesInThisScope; + if (IsFunction) + GlobalStats.FunctionSize += BytesInThisScope; + else if (IsInlinedFunction && InlineDepth == 0) + GlobalStats.InlineFunctionSize += BytesInThisScope; + } + } else { + // Not a scope, visit the Die itself. It could be a variable. + collectStatsForDie(Die, FnPrefix, VarPrefix, ScopeLowPC, BytesInScope, + InlineDepth, FnStatMap, GlobalStats); + } + + // Set InlineDepth correctly for child recursion + if (IsFunction) + InlineDepth = 0; + else if (IsInlinedFunction) + ++InlineDepth; + + // Traverse children. + unsigned LexicalBlockIndex = 0; + DWARFDie Child = Die.getFirstChild(); + while (Child) { + std::string ChildVarPrefix = VarPrefix; + if (Child.getTag() == dwarf::DW_TAG_lexical_block) + ChildVarPrefix += toHex(LexicalBlockIndex++) + '.'; + + collectStatsRecursive(Child, FnPrefix, ChildVarPrefix, ScopeLowPC, + BytesInScope, InlineDepth, FnStatMap, GlobalStats); + Child = Child.getSibling(); + } +} + +/// Print machine-readable output. +/// The machine-readable format is single-line JSON output. +/// \{ +static void printDatum(raw_ostream &OS, const char *Key, StringRef Value) { + OS << ",\"" << Key << "\":\"" << Value << '"'; + LLVM_DEBUG(llvm::dbgs() << Key << ": " << Value << '\n'); +} +static void printDatum(raw_ostream &OS, const char *Key, uint64_t Value) { + OS << ",\"" << Key << "\":" << Value; + LLVM_DEBUG(llvm::dbgs() << Key << ": " << Value << '\n'); +} +/// \} + +/// Collect debug info quality metrics for an entire DIContext. +/// +/// Do the impossible and reduce the quality of the debug info down to a few +/// numbers. The idea is to condense the data into numbers that can be tracked +/// over time to identify trends in newer compiler versions and gauge the effect +/// of particular optimizations. The raw numbers themselves are not particularly +/// useful, only the delta between compiling the same program with different +/// compilers is. +bool collectStatsForObjectFile(ObjectFile &Obj, DWARFContext &DICtx, + Twine Filename, raw_ostream &OS) { + StringRef FormatName = Obj.getFileFormatName(); + GlobalStats GlobalStats; + StringMap<PerFunctionStats> Statistics; + for (const auto &CU : static_cast<DWARFContext *>(&DICtx)->compile_units()) + if (DWARFDie CUDie = CU->getNonSkeletonUnitDIE(false)) + collectStatsRecursive(CUDie, "/", "g", 0, 0, 0, Statistics, GlobalStats); + + /// The version number should be increased every time the algorithm is changed + /// (including bug fixes). New metrics may be added without increasing the + /// version. + unsigned Version = 3; + unsigned VarParamTotal = 0; + unsigned VarParamUnique = 0; + unsigned VarParamWithLoc = 0; + unsigned NumFunctions = 0; + unsigned NumInlinedFunctions = 0; + unsigned NumFuncsWithSrcLoc = 0; + unsigned NumAbstractOrigins = 0; + unsigned ParamTotal = 0; + unsigned ParamWithType = 0; + unsigned ParamWithLoc = 0; + unsigned ParamWithSrcLoc = 0; + unsigned VarTotal = 0; + unsigned VarWithType = 0; + unsigned VarWithSrcLoc = 0; + unsigned VarWithLoc = 0; + for (auto &Entry : Statistics) { + PerFunctionStats &Stats = Entry.getValue(); + unsigned TotalVars = Stats.VarsInFunction.size() * Stats.NumFnInlined; + // Count variables in concrete out-of-line functions and in global scope. + if (Stats.HasPCAddresses || !Stats.IsFunction) + TotalVars += Stats.VarsInFunction.size(); + unsigned Constants = Stats.ConstantMembers; + VarParamWithLoc += Stats.TotalVarWithLoc + Constants; + VarParamTotal += TotalVars; + VarParamUnique += Stats.VarsInFunction.size(); + LLVM_DEBUG(for (auto &V + : Stats.VarsInFunction) llvm::dbgs() + << Entry.getKey() << ": " << V.getKey() << "\n"); + NumFunctions += Stats.IsFunction; + NumFuncsWithSrcLoc += Stats.HasSourceLocation; + NumInlinedFunctions += Stats.IsFunction * Stats.NumFnInlined; + NumAbstractOrigins += Stats.IsFunction * Stats.NumAbstractOrigins; + ParamTotal += Stats.NumParams; + ParamWithType += Stats.NumParamTypes; + ParamWithLoc += Stats.NumParamLocations; + ParamWithSrcLoc += Stats.NumParamSourceLocations; + VarTotal += Stats.NumVars; + VarWithType += Stats.NumVarTypes; + VarWithLoc += Stats.NumVarLocations; + VarWithSrcLoc += Stats.NumVarSourceLocations; + } + + // Print summary. + OS.SetBufferSize(1024); + OS << "{\"version\":" << Version; + LLVM_DEBUG(llvm::dbgs() << "Variable location quality metrics\n"; + llvm::dbgs() << "---------------------------------\n"); + printDatum(OS, "file", Filename.str()); + printDatum(OS, "format", FormatName); + printDatum(OS, "source functions", NumFunctions); + printDatum(OS, "source functions with location", NumFuncsWithSrcLoc); + printDatum(OS, "inlined functions", NumInlinedFunctions); + printDatum(OS, "inlined funcs with abstract origins", NumAbstractOrigins); + printDatum(OS, "unique source variables", VarParamUnique); + printDatum(OS, "source variables", VarParamTotal); + printDatum(OS, "variables with location", VarParamWithLoc); + printDatum(OS, "call site entries", GlobalStats.CallSiteEntries); + printDatum(OS, "scope bytes total", + GlobalStats.ScopeBytesFromFirstDefinition); + printDatum(OS, "scope bytes covered", GlobalStats.ScopeBytesCovered); + printDatum(OS, "total function size", GlobalStats.FunctionSize); + printDatum(OS, "total inlined function size", GlobalStats.InlineFunctionSize); + printDatum(OS, "total formal params", ParamTotal); + printDatum(OS, "formal params with source location", ParamWithSrcLoc); + printDatum(OS, "formal params with type", ParamWithType); + printDatum(OS, "formal params with binary location", ParamWithLoc); + printDatum(OS, "total vars", VarTotal); + printDatum(OS, "vars with source location", VarWithSrcLoc); + printDatum(OS, "vars with type", VarWithType); + printDatum(OS, "vars with binary location", VarWithLoc); + OS << "}\n"; + LLVM_DEBUG( + llvm::dbgs() << "Total Availability: " + << (int)std::round((VarParamWithLoc * 100.0) / VarParamTotal) + << "%\n"; + llvm::dbgs() << "PC Ranges covered: " + << (int)std::round((GlobalStats.ScopeBytesCovered * 100.0) / + GlobalStats.ScopeBytesFromFirstDefinition) + << "%\n"); + return true; +} diff --git a/contrib/llvm-project/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp b/contrib/llvm-project/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp new file mode 100644 index 000000000000..05a7aef67ece --- /dev/null +++ b/contrib/llvm-project/llvm/tools/llvm-dwarfdump/llvm-dwarfdump.cpp @@ -0,0 +1,646 @@ +//===-- llvm-dwarfdump.cpp - Debug info dumping utility for llvm ----------===// +// +// 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 program is a utility that works like "dwarfdump". +// +//===----------------------------------------------------------------------===// + +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringSet.h" +#include "llvm/ADT/Triple.h" +#include "llvm/DebugInfo/DIContext.h" +#include "llvm/DebugInfo/DWARF/DWARFContext.h" +#include "llvm/Object/Archive.h" +#include "llvm/Object/MachOUniversal.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/Format.h" +#include "llvm/Support/InitLLVM.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/Path.h" +#include "llvm/Support/Regex.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/ToolOutputFile.h" +#include "llvm/Support/WithColor.h" +#include "llvm/Support/raw_ostream.h" + +using namespace llvm; +using namespace object; + +/// Parser for options that take an optional offest argument. +/// @{ +struct OffsetOption { + uint64_t Val = 0; + bool HasValue = false; + bool IsRequested = false; +}; + +namespace llvm { +namespace cl { +template <> +class parser<OffsetOption> final : public basic_parser<OffsetOption> { +public: + parser(Option &O) : basic_parser(O) {} + + /// Return true on error. + bool parse(Option &O, StringRef ArgName, StringRef Arg, OffsetOption &Val) { + if (Arg == "") { + Val.Val = 0; + Val.HasValue = false; + Val.IsRequested = true; + return false; + } + if (Arg.getAsInteger(0, Val.Val)) + return O.error("'" + Arg + "' value invalid for integer argument!"); + Val.HasValue = true; + Val.IsRequested = true; + return false; + } + + enum ValueExpected getValueExpectedFlagDefault() const { + return ValueOptional; + } + + void printOptionInfo(const Option &O, size_t GlobalWidth) const { + outs() << " -" << O.ArgStr; + Option::printHelpStr(O.HelpStr, GlobalWidth, getOptionWidth(O)); + } + + void printOptionDiff(const Option &O, OffsetOption V, OptVal Default, + size_t GlobalWidth) const { + printOptionName(O, GlobalWidth); + outs() << "[=offset]"; + } + + // An out-of-line virtual method to provide a 'home' for this class. + void anchor() override {}; +}; +} // cl +} // llvm + +/// @} +/// Command line options. +/// @{ + +namespace { +using namespace cl; + +OptionCategory DwarfDumpCategory("Specific Options"); +static list<std::string> + InputFilenames(Positional, desc("<input object files or .dSYM bundles>"), + ZeroOrMore, cat(DwarfDumpCategory)); + +cl::OptionCategory SectionCategory("Section-specific Dump Options", + "These control which sections are dumped. " + "Where applicable these parameters take an " + "optional =<offset> argument to dump only " + "the entry at the specified offset."); + +static opt<bool> DumpAll("all", desc("Dump all debug info sections"), + cat(SectionCategory)); +static alias DumpAllAlias("a", desc("Alias for -all"), aliasopt(DumpAll)); + +// Options for dumping specific sections. +static unsigned DumpType = DIDT_Null; +static std::array<llvm::Optional<uint64_t>, (unsigned)DIDT_ID_Count> + DumpOffsets; +#define HANDLE_DWARF_SECTION(ENUM_NAME, ELF_NAME, CMDLINE_NAME) \ + static opt<OffsetOption> Dump##ENUM_NAME( \ + CMDLINE_NAME, desc("Dump the " ELF_NAME " section"), \ + cat(SectionCategory)); +#include "llvm/BinaryFormat/Dwarf.def" +#undef HANDLE_DWARF_SECTION + +static alias DumpDebugFrameAlias("eh-frame", desc("Alias for -debug-frame"), + NotHidden, cat(SectionCategory), + aliasopt(DumpDebugFrame)); +static list<std::string> + ArchFilters("arch", + desc("Dump debug information for the specified CPU " + "architecture only. Architectures may be specified by " + "name or by number. This option can be specified " + "multiple times, once for each desired architecture."), + cat(DwarfDumpCategory)); +static opt<bool> + Diff("diff", + desc("Emit diff-friendly output by omitting offsets and addresses."), + cat(DwarfDumpCategory)); +static list<std::string> + Find("find", + desc("Search for the exact match for <name> in the accelerator tables " + "and print the matching debug information entries. When no " + "accelerator tables are available, the slower but more complete " + "-name option can be used instead."), + value_desc("name"), cat(DwarfDumpCategory)); +static alias FindAlias("f", desc("Alias for -find."), aliasopt(Find)); +static opt<bool> IgnoreCase("ignore-case", + desc("Ignore case distinctions when searching."), + value_desc("i"), cat(DwarfDumpCategory)); +static alias IgnoreCaseAlias("i", desc("Alias for -ignore-case."), + aliasopt(IgnoreCase)); +static list<std::string> Name( + "name", + desc("Find and print all debug info entries whose name (DW_AT_name " + "attribute) matches the exact text in <pattern>. When used with the " + "the -regex option <pattern> is interpreted as a regular expression."), + value_desc("pattern"), cat(DwarfDumpCategory)); +static alias NameAlias("n", desc("Alias for -name"), aliasopt(Name)); +static opt<uint64_t> + Lookup("lookup", + desc("Lookup <address> in the debug information and print out any " + "available file, function, block and line table details."), + value_desc("address"), cat(DwarfDumpCategory)); +static opt<std::string> + OutputFilename("o", cl::init("-"), + cl::desc("Redirect output to the specified file."), + cl::value_desc("filename"), cat(DwarfDumpCategory)); +static alias OutputFilenameAlias("out-file", desc("Alias for -o."), + aliasopt(OutputFilename)); +static opt<bool> + UseRegex("regex", + desc("Treat any <pattern> strings as regular expressions when " + "searching instead of just as an exact string match."), + cat(DwarfDumpCategory)); +static alias RegexAlias("x", desc("Alias for -regex"), aliasopt(UseRegex)); +static opt<bool> + ShowChildren("show-children", + desc("Show a debug info entry's children when selectively " + "printing entries."), + cat(DwarfDumpCategory)); +static alias ShowChildrenAlias("c", desc("Alias for -show-children."), + aliasopt(ShowChildren)); +static opt<bool> + ShowParents("show-parents", + desc("Show a debug info entry's parents when selectively " + "printing entries."), + cat(DwarfDumpCategory)); +static alias ShowParentsAlias("p", desc("Alias for -show-parents."), + aliasopt(ShowParents)); +static opt<bool> + ShowForm("show-form", + desc("Show DWARF form types after the DWARF attribute types."), + cat(DwarfDumpCategory)); +static alias ShowFormAlias("F", desc("Alias for -show-form."), + aliasopt(ShowForm), cat(DwarfDumpCategory)); +static opt<unsigned> + ChildRecurseDepth("recurse-depth", + desc("Only recurse to a depth of N when displaying " + "children of debug info entries."), + cat(DwarfDumpCategory), init(-1U), value_desc("N")); +static alias ChildRecurseDepthAlias("r", desc("Alias for -recurse-depth."), + aliasopt(ChildRecurseDepth)); +static opt<unsigned> + ParentRecurseDepth("parent-recurse-depth", + desc("Only recurse to a depth of N when displaying " + "parents of debug info entries."), + cat(DwarfDumpCategory), init(-1U), value_desc("N")); +static opt<bool> + SummarizeTypes("summarize-types", + desc("Abbreviate the description of type unit entries."), + cat(DwarfDumpCategory)); +static cl::opt<bool> + Statistics("statistics", + cl::desc("Emit JSON-formatted debug info quality metrics."), + cat(DwarfDumpCategory)); +static opt<bool> Verify("verify", desc("Verify the DWARF debug info."), + cat(DwarfDumpCategory)); +static opt<bool> Quiet("quiet", desc("Use with -verify to not emit to STDOUT."), + cat(DwarfDumpCategory)); +static opt<bool> DumpUUID("uuid", desc("Show the UUID for each architecture."), + cat(DwarfDumpCategory)); +static alias DumpUUIDAlias("u", desc("Alias for -uuid."), aliasopt(DumpUUID)); +static opt<bool> Verbose("verbose", + desc("Print more low-level encoding details."), + cat(DwarfDumpCategory)); +static alias VerboseAlias("v", desc("Alias for -verbose."), aliasopt(Verbose), + cat(DwarfDumpCategory)); +static cl::extrahelp + HelpResponse("\nPass @FILE as argument to read options from FILE.\n"); +} // namespace +/// @} +//===----------------------------------------------------------------------===// + +static void error(StringRef Prefix, std::error_code EC) { + if (!EC) + return; + WithColor::error() << Prefix << ": " << EC.message() << "\n"; + exit(1); +} + +static DIDumpOptions getDumpOpts() { + DIDumpOptions DumpOpts; + DumpOpts.DumpType = DumpType; + DumpOpts.ChildRecurseDepth = ChildRecurseDepth; + DumpOpts.ParentRecurseDepth = ParentRecurseDepth; + DumpOpts.ShowAddresses = !Diff; + DumpOpts.ShowChildren = ShowChildren; + DumpOpts.ShowParents = ShowParents; + DumpOpts.ShowForm = ShowForm; + DumpOpts.SummarizeTypes = SummarizeTypes; + DumpOpts.Verbose = Verbose; + // In -verify mode, print DIEs without children in error messages. + if (Verify) + return DumpOpts.noImplicitRecursion(); + return DumpOpts; +} + +static uint32_t getCPUType(MachOObjectFile &MachO) { + if (MachO.is64Bit()) + return MachO.getHeader64().cputype; + else + return MachO.getHeader().cputype; +} + +/// Return true if the object file has not been filtered by an --arch option. +static bool filterArch(ObjectFile &Obj) { + if (ArchFilters.empty()) + return true; + + if (auto *MachO = dyn_cast<MachOObjectFile>(&Obj)) { + for (auto Arch : ArchFilters) { + // Match architecture number. + unsigned Value; + if (!StringRef(Arch).getAsInteger(0, Value)) + if (Value == getCPUType(*MachO)) + return true; + + // Match as name. + if (MachO->getArchTriple().getArch() == Triple(Arch).getArch()) + return true; + } + } + return false; +} + +using HandlerFn = std::function<bool(ObjectFile &, DWARFContext &DICtx, Twine, + raw_ostream &)>; + +/// Print only DIEs that have a certain name. +static bool filterByName(const StringSet<> &Names, DWARFDie Die, + StringRef NameRef, raw_ostream &OS) { + std::string Name = + (IgnoreCase && !UseRegex) ? NameRef.lower() : NameRef.str(); + if (UseRegex) { + // Match regular expression. + for (auto Pattern : Names.keys()) { + Regex RE(Pattern, IgnoreCase ? Regex::IgnoreCase : Regex::NoFlags); + std::string Error; + if (!RE.isValid(Error)) { + errs() << "error in regular expression: " << Error << "\n"; + exit(1); + } + if (RE.match(Name)) { + Die.dump(OS, 0, getDumpOpts()); + return true; + } + } + } else if (Names.count(Name)) { + // Match full text. + Die.dump(OS, 0, getDumpOpts()); + return true; + } + return false; +} + +/// Print only DIEs that have a certain name. +static void filterByName(const StringSet<> &Names, + DWARFContext::unit_iterator_range CUs, + raw_ostream &OS) { + for (const auto &CU : CUs) + for (const auto &Entry : CU->dies()) { + DWARFDie Die = {CU.get(), &Entry}; + if (const char *Name = Die.getName(DINameKind::ShortName)) + if (filterByName(Names, Die, Name, OS)) + continue; + if (const char *Name = Die.getName(DINameKind::LinkageName)) + filterByName(Names, Die, Name, OS); + } +} + +static void getDies(DWARFContext &DICtx, const AppleAcceleratorTable &Accel, + StringRef Name, SmallVectorImpl<DWARFDie> &Dies) { + for (const auto &Entry : Accel.equal_range(Name)) { + if (llvm::Optional<uint64_t> Off = Entry.getDIESectionOffset()) { + if (DWARFDie Die = DICtx.getDIEForOffset(*Off)) + Dies.push_back(Die); + } + } +} + +static DWARFDie toDie(const DWARFDebugNames::Entry &Entry, + DWARFContext &DICtx) { + llvm::Optional<uint64_t> CUOff = Entry.getCUOffset(); + llvm::Optional<uint64_t> Off = Entry.getDIEUnitOffset(); + if (!CUOff || !Off) + return DWARFDie(); + + DWARFCompileUnit *CU = DICtx.getCompileUnitForOffset(*CUOff); + if (!CU) + return DWARFDie(); + + if (llvm::Optional<uint64_t> DWOId = CU->getDWOId()) { + // This is a skeleton unit. Look up the DIE in the DWO unit. + CU = DICtx.getDWOCompileUnitForHash(*DWOId); + if (!CU) + return DWARFDie(); + } + + return CU->getDIEForOffset(CU->getOffset() + *Off); +} + +static void getDies(DWARFContext &DICtx, const DWARFDebugNames &Accel, + StringRef Name, SmallVectorImpl<DWARFDie> &Dies) { + for (const auto &Entry : Accel.equal_range(Name)) { + if (DWARFDie Die = toDie(Entry, DICtx)) + Dies.push_back(Die); + } +} + +/// Print only DIEs that have a certain name. +static void filterByAccelName(ArrayRef<std::string> Names, DWARFContext &DICtx, + raw_ostream &OS) { + SmallVector<DWARFDie, 4> Dies; + for (const auto &Name : Names) { + getDies(DICtx, DICtx.getAppleNames(), Name, Dies); + getDies(DICtx, DICtx.getAppleTypes(), Name, Dies); + getDies(DICtx, DICtx.getAppleNamespaces(), Name, Dies); + getDies(DICtx, DICtx.getDebugNames(), Name, Dies); + } + llvm::sort(Dies); + Dies.erase(std::unique(Dies.begin(), Dies.end()), Dies.end()); + + for (DWARFDie Die : Dies) + Die.dump(OS, 0, getDumpOpts()); +} + +/// Handle the --lookup option and dump the DIEs and line info for the given +/// address. +/// TODO: specified Address for --lookup option could relate for several +/// different sections(in case not-linked object file). llvm-dwarfdump +/// need to do something with this: extend lookup option with section +/// information or probably display all matched entries, or something else... +static bool lookup(ObjectFile &Obj, DWARFContext &DICtx, uint64_t Address, + raw_ostream &OS) { + auto DIEsForAddr = DICtx.getDIEsForAddress(Lookup); + + if (!DIEsForAddr) + return false; + + DIDumpOptions DumpOpts = getDumpOpts(); + DumpOpts.ChildRecurseDepth = 0; + DIEsForAddr.CompileUnit->dump(OS, DumpOpts); + if (DIEsForAddr.FunctionDIE) { + DIEsForAddr.FunctionDIE.dump(OS, 2, DumpOpts); + if (DIEsForAddr.BlockDIE) + DIEsForAddr.BlockDIE.dump(OS, 4, DumpOpts); + } + + // TODO: it is neccessary to set proper SectionIndex here. + // object::SectionedAddress::UndefSection works for only absolute addresses. + if (DILineInfo LineInfo = DICtx.getLineInfoForAddress( + {Lookup, object::SectionedAddress::UndefSection})) + LineInfo.dump(OS); + + return true; +} + +bool collectStatsForObjectFile(ObjectFile &Obj, DWARFContext &DICtx, + Twine Filename, raw_ostream &OS); + +static bool dumpObjectFile(ObjectFile &Obj, DWARFContext &DICtx, Twine Filename, + raw_ostream &OS) { + logAllUnhandledErrors(DICtx.loadRegisterInfo(Obj), errs(), + Filename.str() + ": "); + // The UUID dump already contains all the same information. + if (!(DumpType & DIDT_UUID) || DumpType == DIDT_All) + OS << Filename << ":\tfile format " << Obj.getFileFormatName() << '\n'; + + // Handle the --lookup option. + if (Lookup) + return lookup(Obj, DICtx, Lookup, OS); + + // Handle the --name option. + if (!Name.empty()) { + StringSet<> Names; + for (auto name : Name) + Names.insert((IgnoreCase && !UseRegex) ? StringRef(name).lower() : name); + + filterByName(Names, DICtx.normal_units(), OS); + filterByName(Names, DICtx.dwo_units(), OS); + return true; + } + + // Handle the --find option and lower it to --debug-info=<offset>. + if (!Find.empty()) { + filterByAccelName(Find, DICtx, OS); + return true; + } + + // Dump the complete DWARF structure. + DICtx.dump(OS, getDumpOpts(), DumpOffsets); + return true; +} + +static bool verifyObjectFile(ObjectFile &Obj, DWARFContext &DICtx, + Twine Filename, raw_ostream &OS) { + // Verify the DWARF and exit with non-zero exit status if verification + // fails. + raw_ostream &stream = Quiet ? nulls() : OS; + stream << "Verifying " << Filename.str() << ":\tfile format " + << Obj.getFileFormatName() << "\n"; + bool Result = DICtx.verify(stream, getDumpOpts()); + if (Result) + stream << "No errors.\n"; + else + stream << "Errors detected.\n"; + return Result; +} + +static bool handleBuffer(StringRef Filename, MemoryBufferRef Buffer, + HandlerFn HandleObj, raw_ostream &OS); + +static bool handleArchive(StringRef Filename, Archive &Arch, + HandlerFn HandleObj, raw_ostream &OS) { + bool Result = true; + Error Err = Error::success(); + for (auto Child : Arch.children(Err)) { + auto BuffOrErr = Child.getMemoryBufferRef(); + error(Filename, errorToErrorCode(BuffOrErr.takeError())); + auto NameOrErr = Child.getName(); + error(Filename, errorToErrorCode(NameOrErr.takeError())); + std::string Name = (Filename + "(" + NameOrErr.get() + ")").str(); + Result &= handleBuffer(Name, BuffOrErr.get(), HandleObj, OS); + } + error(Filename, errorToErrorCode(std::move(Err))); + + return Result; +} + +static bool handleBuffer(StringRef Filename, MemoryBufferRef Buffer, + HandlerFn HandleObj, raw_ostream &OS) { + Expected<std::unique_ptr<Binary>> BinOrErr = object::createBinary(Buffer); + error(Filename, errorToErrorCode(BinOrErr.takeError())); + + bool Result = true; + if (auto *Obj = dyn_cast<ObjectFile>(BinOrErr->get())) { + if (filterArch(*Obj)) { + std::unique_ptr<DWARFContext> DICtx = DWARFContext::create(*Obj); + Result = HandleObj(*Obj, *DICtx, Filename, OS); + } + } + else if (auto *Fat = dyn_cast<MachOUniversalBinary>(BinOrErr->get())) + for (auto &ObjForArch : Fat->objects()) { + std::string ObjName = + (Filename + "(" + ObjForArch.getArchFlagName() + ")").str(); + if (auto MachOOrErr = ObjForArch.getAsObjectFile()) { + auto &Obj = **MachOOrErr; + if (filterArch(Obj)) { + std::unique_ptr<DWARFContext> DICtx = DWARFContext::create(Obj); + Result &= HandleObj(Obj, *DICtx, ObjName, OS); + } + continue; + } else + consumeError(MachOOrErr.takeError()); + if (auto ArchiveOrErr = ObjForArch.getAsArchive()) { + error(ObjName, errorToErrorCode(ArchiveOrErr.takeError())); + Result &= handleArchive(ObjName, *ArchiveOrErr.get(), HandleObj, OS); + continue; + } else + consumeError(ArchiveOrErr.takeError()); + } + else if (auto *Arch = dyn_cast<Archive>(BinOrErr->get())) + Result = handleArchive(Filename, *Arch, HandleObj, OS); + return Result; +} + +static bool handleFile(StringRef Filename, HandlerFn HandleObj, + raw_ostream &OS) { + ErrorOr<std::unique_ptr<MemoryBuffer>> BuffOrErr = + MemoryBuffer::getFileOrSTDIN(Filename); + error(Filename, BuffOrErr.getError()); + std::unique_ptr<MemoryBuffer> Buffer = std::move(BuffOrErr.get()); + return handleBuffer(Filename, *Buffer, HandleObj, OS); +} + +/// If the input path is a .dSYM bundle (as created by the dsymutil tool), +/// replace it with individual entries for each of the object files inside the +/// bundle otherwise return the input path. +static std::vector<std::string> expandBundle(const std::string &InputPath) { + std::vector<std::string> BundlePaths; + SmallString<256> BundlePath(InputPath); + // Normalize input path. This is necessary to accept `bundle.dSYM/`. + sys::path::remove_dots(BundlePath); + // Manually open up the bundle to avoid introducing additional dependencies. + if (sys::fs::is_directory(BundlePath) && + sys::path::extension(BundlePath) == ".dSYM") { + std::error_code EC; + sys::path::append(BundlePath, "Contents", "Resources", "DWARF"); + for (sys::fs::directory_iterator Dir(BundlePath, EC), DirEnd; + Dir != DirEnd && !EC; Dir.increment(EC)) { + const std::string &Path = Dir->path(); + sys::fs::file_status Status; + EC = sys::fs::status(Path, Status); + error(Path, EC); + switch (Status.type()) { + case sys::fs::file_type::regular_file: + case sys::fs::file_type::symlink_file: + case sys::fs::file_type::type_unknown: + BundlePaths.push_back(Path); + break; + default: /*ignore*/; + } + } + error(BundlePath, EC); + } + if (!BundlePaths.size()) + BundlePaths.push_back(InputPath); + return BundlePaths; +} + +int main(int argc, char **argv) { + InitLLVM X(argc, argv); + + llvm::InitializeAllTargetInfos(); + llvm::InitializeAllTargetMCs(); + + HideUnrelatedOptions({&DwarfDumpCategory, &SectionCategory, &ColorCategory}); + cl::ParseCommandLineOptions( + argc, argv, + "pretty-print DWARF debug information in object files" + " and debug info archives.\n"); + + // FIXME: Audit interactions between these two options and make them + // compatible. + if (Diff && Verbose) { + WithColor::error() << "incompatible arguments: specifying both -diff and " + "-verbose is currently not supported"; + return 0; + } + + std::error_code EC; + ToolOutputFile OutputFile(OutputFilename, EC, sys::fs::OF_None); + error("Unable to open output file" + OutputFilename, EC); + // Don't remove output file if we exit with an error. + OutputFile.keep(); + + bool OffsetRequested = false; + + // Defaults to dumping all sections, unless brief mode is specified in which + // case only the .debug_info section in dumped. +#define HANDLE_DWARF_SECTION(ENUM_NAME, ELF_NAME, CMDLINE_NAME) \ + if (Dump##ENUM_NAME.IsRequested) { \ + DumpType |= DIDT_##ENUM_NAME; \ + if (Dump##ENUM_NAME.HasValue) { \ + DumpOffsets[DIDT_ID_##ENUM_NAME] = Dump##ENUM_NAME.Val; \ + OffsetRequested = true; \ + } \ + } +#include "llvm/BinaryFormat/Dwarf.def" +#undef HANDLE_DWARF_SECTION + if (DumpUUID) + DumpType |= DIDT_UUID; + if (DumpAll) + DumpType = DIDT_All; + if (DumpType == DIDT_Null) { + if (Verbose) + DumpType = DIDT_All; + else + DumpType = DIDT_DebugInfo; + } + + // Unless dumping a specific DIE, default to --show-children. + if (!ShowChildren && !Verify && !OffsetRequested && Name.empty() && Find.empty()) + ShowChildren = true; + + // Defaults to a.out if no filenames specified. + if (InputFilenames.empty()) + InputFilenames.push_back("a.out"); + + // Expand any .dSYM bundles to the individual object files contained therein. + std::vector<std::string> Objects; + for (const auto &F : InputFilenames) { + auto Objs = expandBundle(F); + Objects.insert(Objects.end(), Objs.begin(), Objs.end()); + } + + if (Verify) { + // If we encountered errors during verify, exit with a non-zero exit status. + if (!all_of(Objects, [&](std::string Object) { + return handleFile(Object, verifyObjectFile, OutputFile.os()); + })) + return 1; + } else if (Statistics) + for (auto Object : Objects) + handleFile(Object, collectStatsForObjectFile, OutputFile.os()); + else + for (auto Object : Objects) + handleFile(Object, dumpObjectFile, OutputFile.os()); + + return EXIT_SUCCESS; +} |