summaryrefslogtreecommitdiff
path: root/source/Plugins/ObjectFile/Breakpad
diff options
context:
space:
mode:
Diffstat (limited to 'source/Plugins/ObjectFile/Breakpad')
-rw-r--r--source/Plugins/ObjectFile/Breakpad/BreakpadRecords.cpp411
-rw-r--r--source/Plugins/ObjectFile/Breakpad/BreakpadRecords.h163
-rw-r--r--source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp197
-rw-r--r--source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h16
4 files changed, 603 insertions, 184 deletions
diff --git a/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.cpp b/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.cpp
new file mode 100644
index 000000000000..d489eaf11115
--- /dev/null
+++ b/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.cpp
@@ -0,0 +1,411 @@
+//===-- BreakpadRecords.cpp ----------------------------------- -*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "Plugins/ObjectFile/Breakpad/BreakpadRecords.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/StringSwitch.h"
+#include "llvm/Support/Endian.h"
+#include "llvm/Support/FormatVariadic.h"
+
+using namespace lldb_private;
+using namespace lldb_private::breakpad;
+
+namespace {
+enum class Token { Unknown, Module, Info, CodeID, File, Func, Public, Stack, CFI, Init };
+}
+
+template<typename T>
+static T stringTo(llvm::StringRef Str);
+
+template <> Token stringTo<Token>(llvm::StringRef Str) {
+ return llvm::StringSwitch<Token>(Str)
+ .Case("MODULE", Token::Module)
+ .Case("INFO", Token::Info)
+ .Case("CODE_ID", Token::CodeID)
+ .Case("FILE", Token::File)
+ .Case("FUNC", Token::Func)
+ .Case("PUBLIC", Token::Public)
+ .Case("STACK", Token::Stack)
+ .Case("CFI", Token::CFI)
+ .Case("INIT", Token::Init)
+ .Default(Token::Unknown);
+}
+
+template <>
+llvm::Triple::OSType stringTo<llvm::Triple::OSType>(llvm::StringRef Str) {
+ using llvm::Triple;
+ return llvm::StringSwitch<Triple::OSType>(Str)
+ .Case("Linux", Triple::Linux)
+ .Case("mac", Triple::MacOSX)
+ .Case("windows", Triple::Win32)
+ .Default(Triple::UnknownOS);
+}
+
+template <>
+llvm::Triple::ArchType stringTo<llvm::Triple::ArchType>(llvm::StringRef Str) {
+ using llvm::Triple;
+ return llvm::StringSwitch<Triple::ArchType>(Str)
+ .Case("arm", Triple::arm)
+ .Cases("arm64", "arm64e", Triple::aarch64)
+ .Case("mips", Triple::mips)
+ .Case("ppc", Triple::ppc)
+ .Case("ppc64", Triple::ppc64)
+ .Case("s390", Triple::systemz)
+ .Case("sparc", Triple::sparc)
+ .Case("sparcv9", Triple::sparcv9)
+ .Case("x86", Triple::x86)
+ .Case("x86_64", Triple::x86_64)
+ .Default(Triple::UnknownArch);
+}
+
+template<typename T>
+static T consume(llvm::StringRef &Str) {
+ llvm::StringRef Token;
+ std::tie(Token, Str) = getToken(Str);
+ return stringTo<T>(Token);
+}
+
+/// Return the number of hex digits needed to encode an (POD) object of a given
+/// type.
+template <typename T> static constexpr size_t hex_digits() {
+ return 2 * sizeof(T);
+}
+
+static UUID parseModuleId(llvm::Triple::OSType os, llvm::StringRef str) {
+ struct data_t {
+ using uuid_t = uint8_t[16];
+ uuid_t uuid;
+ llvm::support::ubig32_t age;
+ } data;
+ static_assert(sizeof(data) == 20, "");
+ // The textual module id encoding should be between 33 and 40 bytes long,
+ // depending on the size of the age field, which is of variable length.
+ // The first three chunks of the id are encoded in big endian, so we need to
+ // byte-swap those.
+ if (str.size() <= hex_digits<data_t::uuid_t>() ||
+ str.size() > hex_digits<data_t>())
+ return UUID();
+ if (!all_of(str, llvm::isHexDigit))
+ return UUID();
+
+ llvm::StringRef uuid_str = str.take_front(hex_digits<data_t::uuid_t>());
+ llvm::StringRef age_str = str.drop_front(hex_digits<data_t::uuid_t>());
+
+ llvm::copy(fromHex(uuid_str), data.uuid);
+ uint32_t age;
+ bool success = to_integer(age_str, age, 16);
+ assert(success);
+ (void)success;
+ data.age = age;
+
+ // On non-windows, the age field should always be zero, so we don't include to
+ // match the native uuid format of these platforms.
+ return UUID::fromData(&data, os == llvm::Triple::Win32 ? sizeof(data)
+ : sizeof(data.uuid));
+}
+
+llvm::Optional<Record::Kind> Record::classify(llvm::StringRef Line) {
+ Token Tok = consume<Token>(Line);
+ switch (Tok) {
+ case Token::Module:
+ return Record::Module;
+ case Token::Info:
+ return Record::Info;
+ case Token::File:
+ return Record::File;
+ case Token::Func:
+ return Record::Func;
+ case Token::Public:
+ return Record::Public;
+ case Token::Stack:
+ Tok = consume<Token>(Line);
+ switch (Tok) {
+ case Token::CFI:
+ return Record::StackCFI;
+ default:
+ return llvm::None;
+ }
+
+ case Token::Unknown:
+ // Optimistically assume that any unrecognised token means this is a line
+ // record, those don't have a special keyword and start directly with a
+ // hex number. CODE_ID should never be at the start of a line, but if it
+ // is, it can be treated the same way as a garbled line record.
+ return Record::Line;
+
+ case Token::CodeID:
+ case Token::CFI:
+ case Token::Init:
+ // These should never appear at the start of a valid record.
+ return llvm::None;
+ }
+ llvm_unreachable("Fully covered switch above!");
+}
+
+llvm::Optional<ModuleRecord> ModuleRecord::parse(llvm::StringRef Line) {
+ // MODULE Linux x86_64 E5894855C35DCCCCCCCCCCCCCCCCCCCC0 a.out
+ if (consume<Token>(Line) != Token::Module)
+ return llvm::None;
+
+ llvm::Triple::OSType OS = consume<llvm::Triple::OSType>(Line);
+ if (OS == llvm::Triple::UnknownOS)
+ return llvm::None;
+
+ llvm::Triple::ArchType Arch = consume<llvm::Triple::ArchType>(Line);
+ if (Arch == llvm::Triple::UnknownArch)
+ return llvm::None;
+
+ llvm::StringRef Str;
+ std::tie(Str, Line) = getToken(Line);
+ UUID ID = parseModuleId(OS, Str);
+ if (!ID)
+ return llvm::None;
+
+ return ModuleRecord(OS, Arch, std::move(ID));
+}
+
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const ModuleRecord &R) {
+ return OS << "MODULE " << llvm::Triple::getOSTypeName(R.OS) << " "
+ << llvm::Triple::getArchTypeName(R.Arch) << " "
+ << R.ID.GetAsString();
+}
+
+llvm::Optional<InfoRecord> InfoRecord::parse(llvm::StringRef Line) {
+ // INFO CODE_ID 554889E55DC3CCCCCCCCCCCCCCCCCCCC [a.exe]
+ if (consume<Token>(Line) != Token::Info)
+ return llvm::None;
+
+ if (consume<Token>(Line) != Token::CodeID)
+ return llvm::None;
+
+ llvm::StringRef Str;
+ std::tie(Str, Line) = getToken(Line);
+ // If we don't have any text following the code ID (e.g. on linux), we should
+ // use this as the UUID. Otherwise, we should revert back to the module ID.
+ UUID ID;
+ if (Line.trim().empty()) {
+ if (Str.empty() || ID.SetFromStringRef(Str, Str.size() / 2) != Str.size())
+ return llvm::None;
+ }
+ return InfoRecord(std::move(ID));
+}
+
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const InfoRecord &R) {
+ return OS << "INFO CODE_ID " << R.ID.GetAsString();
+}
+
+llvm::Optional<FileRecord> FileRecord::parse(llvm::StringRef Line) {
+ // FILE number name
+ if (consume<Token>(Line) != Token::File)
+ return llvm::None;
+
+ llvm::StringRef Str;
+ size_t Number;
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, Number))
+ return llvm::None;
+
+ llvm::StringRef Name = Line.trim();
+ if (Name.empty())
+ return llvm::None;
+
+ return FileRecord(Number, Name);
+}
+
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const FileRecord &R) {
+ return OS << "FILE " << R.Number << " " << R.Name;
+}
+
+static bool parsePublicOrFunc(llvm::StringRef Line, bool &Multiple,
+ lldb::addr_t &Address, lldb::addr_t *Size,
+ lldb::addr_t &ParamSize, llvm::StringRef &Name) {
+ // PUBLIC [m] address param_size name
+ // or
+ // FUNC [m] address size param_size name
+
+ Token Tok = Size ? Token::Func : Token::Public;
+
+ if (consume<Token>(Line) != Tok)
+ return false;
+
+ llvm::StringRef Str;
+ std::tie(Str, Line) = getToken(Line);
+ Multiple = Str == "m";
+
+ if (Multiple)
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, Address, 16))
+ return false;
+
+ if (Tok == Token::Func) {
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, *Size, 16))
+ return false;
+ }
+
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, ParamSize, 16))
+ return false;
+
+ Name = Line.trim();
+ if (Name.empty())
+ return false;
+
+ return true;
+}
+
+llvm::Optional<FuncRecord> FuncRecord::parse(llvm::StringRef Line) {
+ bool Multiple;
+ lldb::addr_t Address, Size, ParamSize;
+ llvm::StringRef Name;
+
+ if (parsePublicOrFunc(Line, Multiple, Address, &Size, ParamSize, Name))
+ return FuncRecord(Multiple, Address, Size, ParamSize, Name);
+
+ return llvm::None;
+}
+
+bool breakpad::operator==(const FuncRecord &L, const FuncRecord &R) {
+ return L.Multiple == R.Multiple && L.Address == R.Address &&
+ L.Size == R.Size && L.ParamSize == R.ParamSize && L.Name == R.Name;
+}
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const FuncRecord &R) {
+ return OS << llvm::formatv("FUNC {0}{1:x-} {2:x-} {3:x-} {4}",
+ R.Multiple ? "m " : "", R.Address, R.Size,
+ R.ParamSize, R.Name);
+}
+
+llvm::Optional<LineRecord> LineRecord::parse(llvm::StringRef Line) {
+ lldb::addr_t Address;
+ llvm::StringRef Str;
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, Address, 16))
+ return llvm::None;
+
+ lldb::addr_t Size;
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, Size, 16))
+ return llvm::None;
+
+ uint32_t LineNum;
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, LineNum))
+ return llvm::None;
+
+ size_t FileNum;
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, FileNum))
+ return llvm::None;
+
+ return LineRecord(Address, Size, LineNum, FileNum);
+}
+
+bool breakpad::operator==(const LineRecord &L, const LineRecord &R) {
+ return L.Address == R.Address && L.Size == R.Size && L.LineNum == R.LineNum &&
+ L.FileNum == R.FileNum;
+}
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const LineRecord &R) {
+ return OS << llvm::formatv("{0:x-} {1:x-} {2} {3}", R.Address, R.Size,
+ R.LineNum, R.FileNum);
+}
+
+llvm::Optional<PublicRecord> PublicRecord::parse(llvm::StringRef Line) {
+ bool Multiple;
+ lldb::addr_t Address, ParamSize;
+ llvm::StringRef Name;
+
+ if (parsePublicOrFunc(Line, Multiple, Address, nullptr, ParamSize, Name))
+ return PublicRecord(Multiple, Address, ParamSize, Name);
+
+ return llvm::None;
+}
+
+bool breakpad::operator==(const PublicRecord &L, const PublicRecord &R) {
+ return L.Multiple == R.Multiple && L.Address == R.Address &&
+ L.ParamSize == R.ParamSize && L.Name == R.Name;
+}
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const PublicRecord &R) {
+ return OS << llvm::formatv("PUBLIC {0}{1:x-} {2:x-} {3}",
+ R.Multiple ? "m " : "", R.Address, R.ParamSize,
+ R.Name);
+}
+
+llvm::Optional<StackCFIRecord> StackCFIRecord::parse(llvm::StringRef Line) {
+ // STACK CFI INIT address size reg1: expr1 reg2: expr2 ...
+ // or
+ // STACK CFI address reg1: expr1 reg2: expr2 ...
+ // No token in exprN ends with a colon.
+
+ if (consume<Token>(Line) != Token::Stack)
+ return llvm::None;
+ if (consume<Token>(Line) != Token::CFI)
+ return llvm::None;
+
+ llvm::StringRef Str;
+ std::tie(Str, Line) = getToken(Line);
+
+ bool IsInitRecord = stringTo<Token>(Str) == Token::Init;
+ if (IsInitRecord)
+ std::tie(Str, Line) = getToken(Line);
+
+ lldb::addr_t Address;
+ if (!to_integer(Str, Address, 16))
+ return llvm::None;
+
+ llvm::Optional<lldb::addr_t> Size;
+ if (IsInitRecord) {
+ Size.emplace();
+ std::tie(Str, Line) = getToken(Line);
+ if (!to_integer(Str, *Size, 16))
+ return llvm::None;
+ }
+
+ return StackCFIRecord(Address, Size, Line.trim());
+}
+
+bool breakpad::operator==(const StackCFIRecord &L, const StackCFIRecord &R) {
+ return L.Address == R.Address && L.Size == R.Size &&
+ L.UnwindRules == R.UnwindRules;
+}
+
+llvm::raw_ostream &breakpad::operator<<(llvm::raw_ostream &OS,
+ const StackCFIRecord &R) {
+ OS << "STACK CFI ";
+ if (R.Size)
+ OS << "INIT ";
+ OS << llvm::formatv("{0:x-} ", R.Address);
+ if (R.Size)
+ OS << llvm::formatv("{0:x-} ", *R.Size);
+ return OS << " " << R.UnwindRules;
+}
+
+llvm::StringRef breakpad::toString(Record::Kind K) {
+ switch (K) {
+ case Record::Module:
+ return "MODULE";
+ case Record::Info:
+ return "INFO";
+ case Record::File:
+ return "FILE";
+ case Record::Func:
+ return "FUNC";
+ case Record::Line:
+ return "LINE";
+ case Record::Public:
+ return "PUBLIC";
+ case Record::StackCFI:
+ return "STACK CFI";
+ }
+ llvm_unreachable("Unknown record kind!");
+}
diff --git a/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.h b/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.h
new file mode 100644
index 000000000000..5d5cdb319c10
--- /dev/null
+++ b/source/Plugins/ObjectFile/Breakpad/BreakpadRecords.h
@@ -0,0 +1,163 @@
+//===-- BreakpadRecords.h ------------------------------------- -*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLDB_PLUGINS_OBJECTFILE_BREAKPAD_BREAKPADRECORDS_H
+#define LLDB_PLUGINS_OBJECTFILE_BREAKPAD_BREAKPADRECORDS_H
+
+#include "lldb/Utility/UUID.h"
+#include "lldb/lldb-types.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/Triple.h"
+#include "llvm/Support/FormatProviders.h"
+
+namespace lldb_private {
+namespace breakpad {
+
+class Record {
+public:
+ enum Kind { Module, Info, File, Func, Line, Public, StackCFI };
+
+ /// Attempt to guess the kind of the record present in the argument without
+ /// doing a full parse. The returned kind will always be correct for valid
+ /// records, but the full parse can still fail in case of corrupted input.
+ static llvm::Optional<Kind> classify(llvm::StringRef Line);
+
+protected:
+ Record(Kind K) : TheKind(K) {}
+
+ ~Record() = default;
+
+public:
+ Kind getKind() { return TheKind; }
+
+private:
+ Kind TheKind;
+};
+
+llvm::StringRef toString(Record::Kind K);
+inline llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, Record::Kind K) {
+ OS << toString(K);
+ return OS;
+}
+
+class ModuleRecord : public Record {
+public:
+ static llvm::Optional<ModuleRecord> parse(llvm::StringRef Line);
+ ModuleRecord(llvm::Triple::OSType OS, llvm::Triple::ArchType Arch, UUID ID)
+ : Record(Module), OS(OS), Arch(Arch), ID(std::move(ID)) {}
+
+ llvm::Triple::OSType OS;
+ llvm::Triple::ArchType Arch;
+ UUID ID;
+};
+
+inline bool operator==(const ModuleRecord &L, const ModuleRecord &R) {
+ return L.OS == R.OS && L.Arch == R.Arch && L.ID == R.ID;
+}
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const ModuleRecord &R);
+
+class InfoRecord : public Record {
+public:
+ static llvm::Optional<InfoRecord> parse(llvm::StringRef Line);
+ InfoRecord(UUID ID) : Record(Info), ID(std::move(ID)) {}
+
+ UUID ID;
+};
+
+inline bool operator==(const InfoRecord &L, const InfoRecord &R) {
+ return L.ID == R.ID;
+}
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const InfoRecord &R);
+
+class FileRecord : public Record {
+public:
+ static llvm::Optional<FileRecord> parse(llvm::StringRef Line);
+ FileRecord(size_t Number, llvm::StringRef Name)
+ : Record(File), Number(Number), Name(Name) {}
+
+ size_t Number;
+ llvm::StringRef Name;
+};
+
+inline bool operator==(const FileRecord &L, const FileRecord &R) {
+ return L.Number == R.Number && L.Name == R.Name;
+}
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const FileRecord &R);
+
+class FuncRecord : public Record {
+public:
+ static llvm::Optional<FuncRecord> parse(llvm::StringRef Line);
+ FuncRecord(bool Multiple, lldb::addr_t Address, lldb::addr_t Size,
+ lldb::addr_t ParamSize, llvm::StringRef Name)
+ : Record(Module), Multiple(Multiple), Address(Address), Size(Size),
+ ParamSize(ParamSize), Name(Name) {}
+
+ bool Multiple;
+ lldb::addr_t Address;
+ lldb::addr_t Size;
+ lldb::addr_t ParamSize;
+ llvm::StringRef Name;
+};
+
+bool operator==(const FuncRecord &L, const FuncRecord &R);
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const FuncRecord &R);
+
+class LineRecord : public Record {
+public:
+ static llvm::Optional<LineRecord> parse(llvm::StringRef Line);
+ LineRecord(lldb::addr_t Address, lldb::addr_t Size, uint32_t LineNum,
+ size_t FileNum)
+ : Record(Line), Address(Address), Size(Size), LineNum(LineNum),
+ FileNum(FileNum) {}
+
+ lldb::addr_t Address;
+ lldb::addr_t Size;
+ uint32_t LineNum;
+ size_t FileNum;
+};
+
+bool operator==(const LineRecord &L, const LineRecord &R);
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const LineRecord &R);
+
+class PublicRecord : public Record {
+public:
+ static llvm::Optional<PublicRecord> parse(llvm::StringRef Line);
+ PublicRecord(bool Multiple, lldb::addr_t Address, lldb::addr_t ParamSize,
+ llvm::StringRef Name)
+ : Record(Module), Multiple(Multiple), Address(Address),
+ ParamSize(ParamSize), Name(Name) {}
+
+ bool Multiple;
+ lldb::addr_t Address;
+ lldb::addr_t ParamSize;
+ llvm::StringRef Name;
+};
+
+bool operator==(const PublicRecord &L, const PublicRecord &R);
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const PublicRecord &R);
+
+class StackCFIRecord : public Record {
+public:
+ static llvm::Optional<StackCFIRecord> parse(llvm::StringRef Line);
+ StackCFIRecord(lldb::addr_t Address, llvm::Optional<lldb::addr_t> Size,
+ llvm::StringRef UnwindRules)
+ : Record(StackCFI), Address(Address), Size(Size),
+ UnwindRules(UnwindRules) {}
+
+ lldb::addr_t Address;
+ llvm::Optional<lldb::addr_t> Size;
+ llvm::StringRef UnwindRules;
+};
+
+bool operator==(const StackCFIRecord &L, const StackCFIRecord &R);
+llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, const StackCFIRecord &R);
+
+} // namespace breakpad
+} // namespace lldb_private
+
+#endif // LLDB_PLUGINS_OBJECTFILE_BREAKPAD_BREAKPADRECORDS_H
diff --git a/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp b/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp
index 917025030ada..60dd9f9cecf0 100644
--- a/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp
+++ b/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp
@@ -1,18 +1,16 @@
//===-- ObjectFileBreakpad.cpp -------------------------------- -*- C++ -*-===//
//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// 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
//
//===----------------------------------------------------------------------===//
#include "Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h"
+#include "Plugins/ObjectFile/Breakpad/BreakpadRecords.h"
#include "lldb/Core/ModuleSpec.h"
#include "lldb/Core/PluginManager.h"
#include "lldb/Core/Section.h"
-#include "lldb/Utility/DataBuffer.h"
-#include "llvm/ADT/StringExtras.h"
using namespace lldb;
using namespace lldb_private;
@@ -24,164 +22,24 @@ struct Header {
UUID uuid;
static llvm::Optional<Header> parse(llvm::StringRef text);
};
-
-enum class Token { Unknown, Module, Info, File, Func, Public, Stack };
} // namespace
-static Token toToken(llvm::StringRef str) {
- return llvm::StringSwitch<Token>(str)
- .Case("MODULE", Token::Module)
- .Case("INFO", Token::Info)
- .Case("FILE", Token::File)
- .Case("FUNC", Token::Func)
- .Case("PUBLIC", Token::Public)
- .Case("STACK", Token::Stack)
- .Default(Token::Unknown);
-}
-
-static llvm::StringRef toString(Token t) {
- switch (t) {
- case Token::Unknown:
- return "";
- case Token::Module:
- return "MODULE";
- case Token::Info:
- return "INFO";
- case Token::File:
- return "FILE";
- case Token::Func:
- return "FUNC";
- case Token::Public:
- return "PUBLIC";
- case Token::Stack:
- return "STACK";
- }
- llvm_unreachable("Unknown token!");
-}
-
-static llvm::Triple::OSType toOS(llvm::StringRef str) {
- using llvm::Triple;
- return llvm::StringSwitch<Triple::OSType>(str)
- .Case("Linux", Triple::Linux)
- .Case("mac", Triple::MacOSX)
- .Case("windows", Triple::Win32)
- .Default(Triple::UnknownOS);
-}
-
-static llvm::Triple::ArchType toArch(llvm::StringRef str) {
- using llvm::Triple;
- return llvm::StringSwitch<Triple::ArchType>(str)
- .Case("arm", Triple::arm)
- .Case("arm64", Triple::aarch64)
- .Case("mips", Triple::mips)
- .Case("ppc", Triple::ppc)
- .Case("ppc64", Triple::ppc64)
- .Case("s390", Triple::systemz)
- .Case("sparc", Triple::sparc)
- .Case("sparcv9", Triple::sparcv9)
- .Case("x86", Triple::x86)
- .Case("x86_64", Triple::x86_64)
- .Default(Triple::UnknownArch);
-}
-
-static llvm::StringRef consume_front(llvm::StringRef &str, size_t n) {
- llvm::StringRef result = str.take_front(n);
- str = str.drop_front(n);
- return result;
-}
-
-static UUID parseModuleId(llvm::Triple::OSType os, llvm::StringRef str) {
- struct uuid_data {
- llvm::support::ulittle32_t uuid1;
- llvm::support::ulittle16_t uuid2[2];
- uint8_t uuid3[8];
- llvm::support::ulittle32_t age;
- } data;
- static_assert(sizeof(data) == 20, "");
- // The textual module id encoding should be between 33 and 40 bytes long,
- // depending on the size of the age field, which is of variable length.
- // The first three chunks of the id are encoded in big endian, so we need to
- // byte-swap those.
- if (str.size() < 33 || str.size() > 40)
- return UUID();
- uint32_t t;
- if (to_integer(consume_front(str, 8), t, 16))
- data.uuid1 = t;
- else
- return UUID();
- for (int i = 0; i < 2; ++i) {
- if (to_integer(consume_front(str, 4), t, 16))
- data.uuid2[i] = t;
- else
- return UUID();
- }
- for (int i = 0; i < 8; ++i) {
- if (!to_integer(consume_front(str, 2), data.uuid3[i], 16))
- return UUID();
- }
- if (to_integer(str, t, 16))
- data.age = t;
- else
- return UUID();
-
- // On non-windows, the age field should always be zero, so we don't include to
- // match the native uuid format of these platforms.
- return UUID::fromData(&data, os == llvm::Triple::Win32 ? 20 : 16);
-}
-
llvm::Optional<Header> Header::parse(llvm::StringRef text) {
- // A valid module should start with something like:
- // MODULE Linux x86_64 E5894855C35DCCCCCCCCCCCCCCCCCCCC0 a.out
- // optionally followed by
- // INFO CODE_ID 554889E55DC3CCCCCCCCCCCCCCCCCCCC [a.exe]
- llvm::StringRef token, line;
+ llvm::StringRef line;
std::tie(line, text) = text.split('\n');
- std::tie(token, line) = getToken(line);
- if (toToken(token) != Token::Module)
+ auto Module = ModuleRecord::parse(line);
+ if (!Module)
return llvm::None;
- std::tie(token, line) = getToken(line);
llvm::Triple triple;
- triple.setOS(toOS(token));
- if (triple.getOS() == llvm::Triple::UnknownOS)
- return llvm::None;
-
- std::tie(token, line) = getToken(line);
- triple.setArch(toArch(token));
- if (triple.getArch() == llvm::Triple::UnknownArch)
- return llvm::None;
-
- llvm::StringRef module_id;
- std::tie(module_id, line) = getToken(line);
+ triple.setArch(Module->Arch);
+ triple.setOS(Module->OS);
std::tie(line, text) = text.split('\n');
- std::tie(token, line) = getToken(line);
- if (token == "INFO") {
- std::tie(token, line) = getToken(line);
- if (token != "CODE_ID")
- return llvm::None;
- std::tie(token, line) = getToken(line);
- // If we don't have any text following the code id (e.g. on linux), we
- // should use the module id as UUID. Otherwise, we revert back to the module
- // id.
- if (line.trim().empty()) {
- UUID uuid;
- if (uuid.SetFromStringRef(token, token.size() / 2) != token.size())
- return llvm::None;
-
- return Header{ArchSpec(triple), uuid};
- }
- }
-
- // We reach here if we don't have a INFO CODE_ID section, or we chose not to
- // use it. In either case, we need to properly decode the module id, whose
- // fields are encoded in big-endian.
- UUID uuid = parseModuleId(triple.getOS(), module_id);
- if (!uuid)
- return llvm::None;
-
- return Header{ArchSpec(triple), uuid};
+ auto Info = InfoRecord::parse(line);
+ UUID uuid = Info && Info->ID ? Info->ID : Module->ID;
+ return Header{ArchSpec(triple), std::move(uuid)};
}
void ObjectFileBreakpad::Initialize() {
@@ -264,50 +122,45 @@ Symtab *ObjectFileBreakpad::GetSymtab() {
return nullptr;
}
-bool ObjectFileBreakpad::GetUUID(UUID *uuid) {
- *uuid = m_uuid;
- return true;
-}
-
void ObjectFileBreakpad::CreateSections(SectionList &unified_section_list) {
- if (m_sections_ap)
+ if (m_sections_up)
return;
- m_sections_ap = llvm::make_unique<SectionList>();
+ m_sections_up = llvm::make_unique<SectionList>();
- Token current_section = Token::Unknown;
+ llvm::Optional<Record::Kind> current_section;
offset_t section_start;
llvm::StringRef text = toStringRef(m_data.GetData());
uint32_t next_section_id = 1;
auto maybe_add_section = [&](const uint8_t *end_ptr) {
- if (current_section == Token::Unknown)
+ if (!current_section)
return; // We have been called before parsing the first line.
offset_t end_offset = end_ptr - m_data.GetDataStart();
auto section_sp = std::make_shared<Section>(
GetModule(), this, next_section_id++,
- ConstString(toString(current_section)), eSectionTypeOther,
+ ConstString(toString(*current_section)), eSectionTypeOther,
/*file_vm_addr*/ 0, /*vm_size*/ 0, section_start,
end_offset - section_start, /*log2align*/ 0, /*flags*/ 0);
- m_sections_ap->AddSection(section_sp);
+ m_sections_up->AddSection(section_sp);
unified_section_list.AddSection(section_sp);
};
while (!text.empty()) {
llvm::StringRef line;
std::tie(line, text) = text.split('\n');
- Token token = toToken(getToken(line).first);
- if (token == Token::Unknown) {
- // We assume this is a line record, which logically belongs to the Func
- // section. Errors will be handled when parsing the Func section.
- token = Token::Func;
+ llvm::Optional<Record::Kind> next_section = Record::classify(line);
+ if (next_section == Record::Line) {
+ // Line records logically belong to the preceding Func record, so we put
+ // them in the same section.
+ next_section = Record::Func;
}
- if (token == current_section)
+ if (next_section == current_section)
continue;
// Changing sections, finish off the previous one, if there was any.
maybe_add_section(line.bytes_begin());
// And start a new one.
- current_section = token;
+ current_section = next_section;
section_start = line.bytes_begin() - m_data.GetDataStart();
}
// Finally, add the last section.
diff --git a/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h b/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h
index ba2a3ad30e5f..e8885e0cc898 100644
--- a/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h
+++ b/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.h
@@ -1,9 +1,8 @@
//===-- ObjectFileBreakpad.h ---------------------------------- -*- C++ -*-===//
//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// 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
//
//===----------------------------------------------------------------------===//
@@ -12,16 +11,13 @@
#include "lldb/Symbol/ObjectFile.h"
#include "lldb/Utility/ArchSpec.h"
-#include "llvm/ADT/Triple.h"
namespace lldb_private {
namespace breakpad {
class ObjectFileBreakpad : public ObjectFile {
public:
- //------------------------------------------------------------------
// Static Functions
- //------------------------------------------------------------------
static void Initialize();
static void Terminate();
@@ -47,16 +43,12 @@ public:
lldb::offset_t length,
ModuleSpecList &specs);
- //------------------------------------------------------------------
// PluginInterface protocol
- //------------------------------------------------------------------
ConstString GetPluginName() override { return GetPluginNameStatic(); }
uint32_t GetPluginVersion() override { return 1; }
- //------------------------------------------------------------------
// ObjectFile Protocol.
- //------------------------------------------------------------------
bool ParseHeader() override;
@@ -84,7 +76,7 @@ public:
ArchSpec GetArchitecture() override { return m_arch; }
- bool GetUUID(UUID *uuid) override;
+ UUID GetUUID() override { return m_uuid; }
FileSpecList GetDebugSymbolFilePaths() override { return FileSpecList(); }