llvm-project/lld/COFF/SymbolTable.cpp

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

895 lines
28 KiB
C++
Raw Normal View History

//===- SymbolTable.cpp ----------------------------------------------------===//
//
// 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 "SymbolTable.h"
#include "COFFLinkerContext.h"
#include "Config.h"
#include "Driver.h"
#include "LTO.h"
#include "PDB.h"
#include "Symbols.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Timer.h"
#include "llvm/DebugInfo/DIContext.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/LTO/LTO.h"
#include "llvm/Object/WindowsMachineFlag.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <utility>
using namespace llvm;
namespace lld {
namespace coff {
StringRef ltrim1(StringRef s, const char *chars) {
if (!s.empty() && strchr(chars, s[0]))
return s.substr(1);
return s;
}
void SymbolTable::addFile(InputFile *file) {
log("Reading " + toString(file));
if (file->lazy) {
if (auto *f = dyn_cast<BitcodeFile>(file))
f->parseLazy();
else
cast<ObjFile>(file)->parseLazy();
} else {
file->parse();
if (auto *f = dyn_cast<ObjFile>(file)) {
ctx.objFileInstances.push_back(f);
} else if (auto *f = dyn_cast<BitcodeFile>(file)) {
ctx.bitcodeFileInstances.push_back(f);
} else if (auto *f = dyn_cast<ImportFile>(file)) {
ctx.importFileInstances.push_back(f);
}
}
MachineTypes mt = file->getMachineType();
if (config->machine == IMAGE_FILE_MACHINE_UNKNOWN) {
config->machine = mt;
} else if (mt != IMAGE_FILE_MACHINE_UNKNOWN && config->machine != mt) {
error(toString(file) + ": machine type " + machineToStr(mt) +
" conflicts with " + machineToStr(config->machine));
return;
COFF: Change the order of adding symbols to the symbol table. Previously, the order of adding symbols to the symbol table was simple. We have a list of all input files. We read each file from beginning of the list and add all symbols in it to the symbol table. This patch changes that order. Now all archive files are added to the symbol table first, and then all the other object files are added. This shouldn't change the behavior in single-threading, and make room to parallelize in multi-threading. In the first step, only lazy symbols are added to the symbol table because archives contain only Lazy symbols. Member object files found to be necessary are queued. In the second step, defined and undefined symbols are added from object files. Adding an undefined symbol to the symbol table may cause more member files to be added to the queue. We simply continue reading all object files until the queue is empty. Finally, new archive or object files may be added to the queues by object files' directive sections (which contain new command line options). The above process is repeated until we get no new files. Symbols defined both in object files and in archives can make results undeterministic. If an archive is read before an object, a new member file gets linked, while in the other way, no new file would be added. That is the most popular cause of an undeterministic result or linking failure as I observed. Separating phases of adding lazy symbols and undefined symbols makes that deterministic. Adding symbols in each phase should be parallelizable. llvm-svn: 241107
2015-07-01 03:35:21 +08:00
}
driver->parseDirectives(file);
}
static void errorOrWarn(const Twine &s) {
if (config->forceUnresolved)
warn(s);
else
error(s);
}
// Causes the file associated with a lazy symbol to be linked in.
static void forceLazy(Symbol *s) {
s->pendingArchiveLoad = true;
switch (s->kind()) {
case Symbol::Kind::LazyArchiveKind: {
auto *l = cast<LazyArchive>(s);
l->file->addMember(l->sym);
break;
}
case Symbol::Kind::LazyObjectKind: {
InputFile *file = cast<LazyObject>(s)->file;
file->ctx.symtab.addFile(file);
break;
}
[LLD] [COFF] Support linking directly against DLLs in MinGW mode GNU ld.bfd supports linking directly against DLLs without using an import library, and some projects have picked up on this habit. (There's no one single unsurmountable issue with using import libraries, but this is a regularly surfacing missing feature.) As long as one is linking by name (instead of by ordinal), the DLL export table contains most of the information needed. (One can inspect what section a symbol points at, to see if it's a function or data symbol. The practical implementation of this loops over all sections for each symbol, but as long as they're not very many, that should hopefully be tolerable performance wise.) One exception where the information in the DLL isn't entirely enough is on i386 with stdcall functions; depending on how they're done, the exported function name can be a plain undecorated name, while the import library would contain the full decorated symbol name. This issue is addressed separately in a different patch. This is implemented mimicing the structure of a regular import library, with one InputFile corresponding to the static archive that just adds lazy symbols, which then are fetched when they are needed. When such a symbol is fetched, we synthesize a coff_import_header structure in memory and create a regular ImportFile out of it. The implementation could be even smaller by just creating ImportFiles for every symbol available immediately, but that would have the drawback of actually ending up importing all symbols unless running with GC enabled (and mingw mode defaults to having it disabled for historical reasons). Differential Revision: https://reviews.llvm.org/D104530
2021-06-16 21:59:46 +08:00
case Symbol::Kind::LazyDLLSymbolKind: {
auto *l = cast<LazyDLLSymbol>(s);
l->file->makeImport(l->sym);
break;
}
default:
llvm_unreachable(
"symbol passed to forceLazy is not a LazyArchive or LazyObject");
}
}
// Returns the symbol in SC whose value is <= Addr that is closest to Addr.
// This is generally the global variable or function whose definition contains
// Addr.
static Symbol *getSymbol(SectionChunk *sc, uint32_t addr) {
DefinedRegular *candidate = nullptr;
for (Symbol *s : sc->file->getSymbols()) {
auto *d = dyn_cast_or_null<DefinedRegular>(s);
if (!d || !d->data || d->file != sc->file || d->getChunk() != sc ||
d->getValue() > addr ||
(candidate && d->getValue() < candidate->getValue()))
continue;
candidate = d;
}
return candidate;
}
static std::vector<std::string> getSymbolLocations(BitcodeFile *file) {
std::string res("\n>>> referenced by ");
StringRef source = file->obj->getSourceFileName();
if (!source.empty())
res += source.str() + "\n>>> ";
res += toString(file);
return {res};
}
static Optional<std::pair<StringRef, uint32_t>>
getFileLineDwarf(const SectionChunk *c, uint32_t addr) {
Optional<DILineInfo> optionalLineInfo =
c->file->getDILineInfo(addr, c->getSectionNumber() - 1);
if (!optionalLineInfo)
return None;
const DILineInfo &lineInfo = *optionalLineInfo;
if (lineInfo.FileName == DILineInfo::BadString)
return None;
return std::make_pair(saver().save(lineInfo.FileName), lineInfo.Line);
}
static Optional<std::pair<StringRef, uint32_t>>
getFileLine(const SectionChunk *c, uint32_t addr) {
// MinGW can optionally use codeview, even if the default is dwarf.
Optional<std::pair<StringRef, uint32_t>> fileLine =
getFileLineCodeView(c, addr);
// If codeview didn't yield any result, check dwarf in MinGW mode.
if (!fileLine && config->mingw)
fileLine = getFileLineDwarf(c, addr);
return fileLine;
}
// Given a file and the index of a symbol in that file, returns a description
// of all references to that symbol from that file. If no debug information is
// available, returns just the name of the file, else one string per actual
// reference as described in the debug info.
// Returns up to maxStrings string descriptions, along with the total number of
// locations found.
static std::pair<std::vector<std::string>, size_t>
getSymbolLocations(ObjFile *file, uint32_t symIndex, size_t maxStrings) {
struct Location {
Symbol *sym;
std::pair<StringRef, uint32_t> fileLine;
};
std::vector<Location> locations;
size_t numLocations = 0;
for (Chunk *c : file->getChunks()) {
auto *sc = dyn_cast<SectionChunk>(c);
if (!sc)
continue;
for (const coff_relocation &r : sc->getRelocs()) {
if (r.SymbolTableIndex != symIndex)
continue;
numLocations++;
if (locations.size() >= maxStrings)
continue;
Optional<std::pair<StringRef, uint32_t>> fileLine =
getFileLine(sc, r.VirtualAddress);
Symbol *sym = getSymbol(sc, r.VirtualAddress);
if (fileLine)
locations.push_back({sym, *fileLine});
else if (sym)
locations.push_back({sym, {"", 0}});
}
}
if (maxStrings == 0)
return std::make_pair(std::vector<std::string>(), numLocations);
if (numLocations == 0)
return std::make_pair(
std::vector<std::string>{"\n>>> referenced by " + toString(file)}, 1);
std::vector<std::string> symbolLocations(locations.size());
size_t i = 0;
for (Location loc : locations) {
llvm::raw_string_ostream os(symbolLocations[i++]);
os << "\n>>> referenced by ";
if (!loc.fileLine.first.empty())
os << loc.fileLine.first << ":" << loc.fileLine.second
<< "\n>>> ";
os << toString(file);
if (loc.sym)
os << ":(" << toString(*loc.sym) << ')';
}
return std::make_pair(symbolLocations, numLocations);
}
std::vector<std::string> getSymbolLocations(ObjFile *file, uint32_t symIndex) {
return getSymbolLocations(file, symIndex, SIZE_MAX).first;
}
static std::pair<std::vector<std::string>, size_t>
getSymbolLocations(InputFile *file, uint32_t symIndex, size_t maxStrings) {
if (auto *o = dyn_cast<ObjFile>(file))
return getSymbolLocations(o, symIndex, maxStrings);
if (auto *b = dyn_cast<BitcodeFile>(file)) {
std::vector<std::string> symbolLocations = getSymbolLocations(b);
size_t numLocations = symbolLocations.size();
if (symbolLocations.size() > maxStrings)
symbolLocations.resize(maxStrings);
return std::make_pair(symbolLocations, numLocations);
}
llvm_unreachable("unsupported file type passed to getSymbolLocations");
return std::make_pair(std::vector<std::string>(), (size_t)0);
}
// For an undefined symbol, stores all files referencing it and the index of
// the undefined symbol in each file.
struct UndefinedDiag {
Symbol *sym;
struct File {
InputFile *file;
uint32_t symIndex;
};
std::vector<File> files;
};
static void reportUndefinedSymbol(const UndefinedDiag &undefDiag) {
std::string out;
llvm::raw_string_ostream os(out);
os << "undefined symbol: " << toString(*undefDiag.sym);
const size_t maxUndefReferences = 3;
size_t numDisplayedRefs = 0, numRefs = 0;
for (const UndefinedDiag::File &ref : undefDiag.files) {
std::vector<std::string> symbolLocations;
size_t totalLocations = 0;
std::tie(symbolLocations, totalLocations) = getSymbolLocations(
ref.file, ref.symIndex, maxUndefReferences - numDisplayedRefs);
numRefs += totalLocations;
numDisplayedRefs += symbolLocations.size();
for (const std::string &s : symbolLocations) {
os << s;
}
}
if (numDisplayedRefs < numRefs)
os << "\n>>> referenced " << numRefs - numDisplayedRefs << " more times";
errorOrWarn(os.str());
}
void SymbolTable::loadMinGWSymbols() {
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
for (auto &i : symMap) {
Symbol *sym = i.second;
auto *undef = dyn_cast<Undefined>(sym);
if (!undef)
continue;
if (undef->getWeakAlias())
continue;
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
StringRef name = undef->getName();
if (config->machine == I386 && config->stdcallFixup) {
// Check if we can resolve an undefined decorated symbol by finding
2021-10-13 05:03:22 +08:00
// the intended target as an undecorated symbol (only with a leading
// underscore).
StringRef origName = name;
StringRef baseName = name;
// Trim down stdcall/fastcall/vectorcall symbols to the base name.
baseName = ltrim1(baseName, "_@");
baseName = baseName.substr(0, baseName.find('@'));
// Add a leading underscore, as it would be in cdecl form.
std::string newName = ("_" + baseName).str();
Symbol *l;
if (newName != origName && (l = find(newName)) != nullptr) {
// If we found a symbol and it is lazy; load it.
if (l->isLazy() && !l->pendingArchiveLoad) {
log("Loading lazy " + l->getName() + " from " +
l->getFile()->getName() + " for stdcall fixup");
forceLazy(l);
}
// If it's lazy or already defined, hook it up as weak alias.
if (l->isLazy() || isa<Defined>(l)) {
if (config->warnStdcallFixup)
warn("Resolving " + origName + " by linking to " + newName);
else
log("Resolving " + origName + " by linking to " + newName);
undef->weakAlias = l;
continue;
}
}
}
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
if (config->autoImport) {
if (name.startswith("__imp_"))
continue;
// If we have an undefined symbol, but we have a lazy symbol we could
// load, load it.
Symbol *l = find(("__imp_" + name).str());
if (!l || l->pendingArchiveLoad || !l->isLazy())
continue;
log("Loading lazy " + l->getName() + " from " + l->getFile()->getName() +
" for automatic import");
forceLazy(l);
}
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
}
}
Defined *SymbolTable::impSymbol(StringRef name) {
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
if (name.startswith("__imp_"))
return nullptr;
return dyn_cast_or_null<Defined>(find(("__imp_" + name).str()));
}
bool SymbolTable::handleMinGWAutomaticImport(Symbol *sym, StringRef name) {
Defined *imp = impSymbol(name);
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
if (!imp)
return false;
// Replace the reference directly to a variable with a reference
// to the import address table instead. This obviously isn't right,
// but we mark the symbol as isRuntimePseudoReloc, and a later pass
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
// will add runtime pseudo relocations for every relocation against
// this Symbol. The runtime pseudo relocation framework expects the
// reference itself to point at the IAT entry.
size_t impSize = 0;
if (isa<DefinedImportData>(imp)) {
log("Automatically importing " + name + " from " +
cast<DefinedImportData>(imp)->getDLLName());
impSize = sizeof(DefinedImportData);
} else if (isa<DefinedRegular>(imp)) {
log("Automatically importing " + name + " from " +
toString(cast<DefinedRegular>(imp)->file));
impSize = sizeof(DefinedRegular);
} else {
warn("unable to automatically import " + name + " from " + imp->getName() +
" from " + toString(cast<DefinedRegular>(imp)->file) +
"; unexpected symbol type");
return false;
}
sym->replaceKeepingName(imp, impSize);
sym->isRuntimePseudoReloc = true;
// There may exist symbols named .refptr.<name> which only consist
// of a single pointer to <name>. If it turns out <name> is
// automatically imported, we don't need to keep the .refptr.<name>
// pointer at all, but redirect all accesses to it to the IAT entry
// for __imp_<name> instead, and drop the whole .refptr.<name> chunk.
DefinedRegular *refptr =
dyn_cast_or_null<DefinedRegular>(find((".refptr." + name).str()));
if (refptr && refptr->getChunk()->getSize() == config->wordsize) {
SectionChunk *sc = dyn_cast_or_null<SectionChunk>(refptr->getChunk());
if (sc && sc->getRelocs().size() == 1 && *sc->symbols().begin() == sym) {
log("Replacing .refptr." + name + " with " + imp->getName());
refptr->getChunk()->live = false;
refptr->replaceKeepingName(imp, impSize);
}
}
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
return true;
}
/// Helper function for reportUnresolvable and resolveRemainingUndefines.
/// This function emits an "undefined symbol" diagnostic for each symbol in
/// undefs. If localImports is not nullptr, it also emits a "locally
/// defined symbol imported" diagnostic for symbols in localImports.
/// objFiles and bitcodeFiles (if not nullptr) are used to report where
/// undefined symbols are referenced.
static void reportProblemSymbols(
const COFFLinkerContext &ctx, const SmallPtrSetImpl<Symbol *> &undefs,
const DenseMap<Symbol *, Symbol *> *localImports, bool needBitcodeFiles) {
// Return early if there is nothing to report (which should be
// the common case).
if (undefs.empty() && (!localImports || localImports->empty()))
return;
for (Symbol *b : config->gcroot) {
if (undefs.count(b))
errorOrWarn("<root>: undefined symbol: " + toString(*b));
if (localImports)
if (Symbol *imp = localImports->lookup(b))
warn("<root>: locally defined symbol imported: " + toString(*imp) +
" (defined in " + toString(imp->getFile()) + ") [LNK4217]");
}
std::vector<UndefinedDiag> undefDiags;
DenseMap<Symbol *, int> firstDiag;
auto processFile = [&](InputFile *file, ArrayRef<Symbol *> symbols) {
uint32_t symIndex = (uint32_t)-1;
for (Symbol *sym : symbols) {
++symIndex;
if (!sym)
continue;
if (undefs.count(sym)) {
auto it = firstDiag.find(sym);
if (it == firstDiag.end()) {
firstDiag[sym] = undefDiags.size();
undefDiags.push_back({sym, {{file, symIndex}}});
} else {
undefDiags[it->second].files.push_back({file, symIndex});
}
}
if (localImports)
if (Symbol *imp = localImports->lookup(sym))
warn(toString(file) +
": locally defined symbol imported: " + toString(*imp) +
" (defined in " + toString(imp->getFile()) + ") [LNK4217]");
}
};
for (ObjFile *file : ctx.objFileInstances)
processFile(file, file->getSymbols());
if (needBitcodeFiles)
for (BitcodeFile *file : ctx.bitcodeFileInstances)
processFile(file, file->getSymbols());
for (const UndefinedDiag &undefDiag : undefDiags)
reportUndefinedSymbol(undefDiag);
}
void SymbolTable::reportUnresolvable() {
SmallPtrSet<Symbol *, 8> undefs;
for (auto &i : symMap) {
Symbol *sym = i.second;
auto *undef = dyn_cast<Undefined>(sym);
if (!undef || sym->deferUndefined)
continue;
if (undef->getWeakAlias())
continue;
StringRef name = undef->getName();
if (name.startswith("__imp_")) {
Symbol *imp = find(name.substr(strlen("__imp_")));
if (imp && isa<Defined>(imp))
continue;
}
if (name.contains("_PchSym_"))
continue;
if (config->autoImport && impSymbol(name))
continue;
undefs.insert(sym);
}
reportProblemSymbols(ctx, undefs,
/* localImports */ nullptr, true);
}
void SymbolTable::resolveRemainingUndefines() {
SmallPtrSet<Symbol *, 8> undefs;
DenseMap<Symbol *, Symbol *> localImports;
for (auto &i : symMap) {
Symbol *sym = i.second;
auto *undef = dyn_cast<Undefined>(sym);
if (!undef)
continue;
if (!sym->isUsedInRegularObj)
continue;
StringRef name = undef->getName();
// A weak alias may have been resolved, so check for that.
if (Defined *d = undef->getWeakAlias()) {
// We want to replace Sym with D. However, we can't just blindly
// copy sizeof(SymbolUnion) bytes from D to Sym because D may be an
// internal symbol, and internal symbols are stored as "unparented"
// Symbols. For that reason we need to check which type of symbol we
// are dealing with and copy the correct number of bytes.
if (isa<DefinedRegular>(d))
memcpy(sym, d, sizeof(DefinedRegular));
else if (isa<DefinedAbsolute>(d))
memcpy(sym, d, sizeof(DefinedAbsolute));
else
memcpy(sym, d, sizeof(SymbolUnion));
continue;
}
// If we can resolve a symbol by removing __imp_ prefix, do that.
// This odd rule is for compatibility with MSVC linker.
if (name.startswith("__imp_")) {
Symbol *imp = find(name.substr(strlen("__imp_")));
if (imp && isa<Defined>(imp)) {
auto *d = cast<Defined>(imp);
replaceSymbol<DefinedLocalImport>(sym, name, d);
localImportChunks.push_back(cast<DefinedLocalImport>(sym)->getChunk());
localImports[sym] = d;
continue;
}
}
// We don't want to report missing Microsoft precompiled headers symbols.
// A proper message will be emitted instead in PDBLinker::aquirePrecompObj
if (name.contains("_PchSym_"))
continue;
if (config->autoImport && handleMinGWAutomaticImport(sym, name))
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
continue;
// Remaining undefined symbols are not fatal if /force is specified.
// They are replaced with dummy defined symbols.
if (config->forceUnresolved)
replaceSymbol<DefinedAbsolute>(sym, name, 0);
undefs.insert(sym);
}
reportProblemSymbols(
ctx, undefs, config->warnLocallyDefinedImported ? &localImports : nullptr,
false);
}
std::pair<Symbol *, bool> SymbolTable::insert(StringRef name) {
bool inserted = false;
Symbol *&sym = symMap[CachedHashStringRef(name)];
if (!sym) {
sym = reinterpret_cast<Symbol *>(make<SymbolUnion>());
sym->isUsedInRegularObj = false;
sym->pendingArchiveLoad = false;
sym->canInline = true;
inserted = true;
}
return {sym, inserted};
COFF: Change the order of adding symbols to the symbol table. Previously, the order of adding symbols to the symbol table was simple. We have a list of all input files. We read each file from beginning of the list and add all symbols in it to the symbol table. This patch changes that order. Now all archive files are added to the symbol table first, and then all the other object files are added. This shouldn't change the behavior in single-threading, and make room to parallelize in multi-threading. In the first step, only lazy symbols are added to the symbol table because archives contain only Lazy symbols. Member object files found to be necessary are queued. In the second step, defined and undefined symbols are added from object files. Adding an undefined symbol to the symbol table may cause more member files to be added to the queue. We simply continue reading all object files until the queue is empty. Finally, new archive or object files may be added to the queues by object files' directive sections (which contain new command line options). The above process is repeated until we get no new files. Symbols defined both in object files and in archives can make results undeterministic. If an archive is read before an object, a new member file gets linked, while in the other way, no new file would be added. That is the most popular cause of an undeterministic result or linking failure as I observed. Separating phases of adding lazy symbols and undefined symbols makes that deterministic. Adding symbols in each phase should be parallelizable. llvm-svn: 241107
2015-07-01 03:35:21 +08:00
}
std::pair<Symbol *, bool> SymbolTable::insert(StringRef name, InputFile *file) {
std::pair<Symbol *, bool> result = insert(name);
if (!file || !isa<BitcodeFile>(file))
result.first->isUsedInRegularObj = true;
return result;
}
Symbol *SymbolTable::addUndefined(StringRef name, InputFile *f,
bool isWeakAlias) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(name, f);
if (wasInserted || (s->isLazy() && isWeakAlias)) {
replaceSymbol<Undefined>(s, name);
return s;
}
if (s->isLazy())
forceLazy(s);
return s;
}
void SymbolTable::addLazyArchive(ArchiveFile *f, const Archive::Symbol &sym) {
StringRef name = sym.getName();
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(name);
if (wasInserted) {
replaceSymbol<LazyArchive>(s, f, sym);
return;
}
auto *u = dyn_cast<Undefined>(s);
if (!u || u->weakAlias || s->pendingArchiveLoad)
return;
s->pendingArchiveLoad = true;
f->addMember(sym);
}
void SymbolTable::addLazyObject(InputFile *f, StringRef n) {
assert(f->lazy);
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, f);
if (wasInserted) {
replaceSymbol<LazyObject>(s, f, n);
return;
}
auto *u = dyn_cast<Undefined>(s);
if (!u || u->weakAlias || s->pendingArchiveLoad)
return;
s->pendingArchiveLoad = true;
f->lazy = false;
addFile(f);
}
[LLD] [COFF] Support linking directly against DLLs in MinGW mode GNU ld.bfd supports linking directly against DLLs without using an import library, and some projects have picked up on this habit. (There's no one single unsurmountable issue with using import libraries, but this is a regularly surfacing missing feature.) As long as one is linking by name (instead of by ordinal), the DLL export table contains most of the information needed. (One can inspect what section a symbol points at, to see if it's a function or data symbol. The practical implementation of this loops over all sections for each symbol, but as long as they're not very many, that should hopefully be tolerable performance wise.) One exception where the information in the DLL isn't entirely enough is on i386 with stdcall functions; depending on how they're done, the exported function name can be a plain undecorated name, while the import library would contain the full decorated symbol name. This issue is addressed separately in a different patch. This is implemented mimicing the structure of a regular import library, with one InputFile corresponding to the static archive that just adds lazy symbols, which then are fetched when they are needed. When such a symbol is fetched, we synthesize a coff_import_header structure in memory and create a regular ImportFile out of it. The implementation could be even smaller by just creating ImportFiles for every symbol available immediately, but that would have the drawback of actually ending up importing all symbols unless running with GC enabled (and mingw mode defaults to having it disabled for historical reasons). Differential Revision: https://reviews.llvm.org/D104530
2021-06-16 21:59:46 +08:00
void SymbolTable::addLazyDLLSymbol(DLLFile *f, DLLFile::Symbol *sym,
StringRef n) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n);
if (wasInserted) {
replaceSymbol<LazyDLLSymbol>(s, f, sym, n);
return;
}
auto *u = dyn_cast<Undefined>(s);
if (!u || u->weakAlias || s->pendingArchiveLoad)
return;
s->pendingArchiveLoad = true;
f->makeImport(sym);
}
static std::string getSourceLocationBitcode(BitcodeFile *file) {
std::string res("\n>>> defined at ");
StringRef source = file->obj->getSourceFileName();
if (!source.empty())
res += source.str() + "\n>>> ";
res += toString(file);
return res;
}
static std::string getSourceLocationObj(ObjFile *file, SectionChunk *sc,
uint32_t offset, StringRef name) {
Optional<std::pair<StringRef, uint32_t>> fileLine;
if (sc)
fileLine = getFileLine(sc, offset);
if (!fileLine)
fileLine = file->getVariableLocation(name);
std::string res;
llvm::raw_string_ostream os(res);
os << "\n>>> defined at ";
if (fileLine)
os << fileLine->first << ":" << fileLine->second << "\n>>> ";
os << toString(file);
return os.str();
}
static std::string getSourceLocation(InputFile *file, SectionChunk *sc,
uint32_t offset, StringRef name) {
if (!file)
return "";
if (auto *o = dyn_cast<ObjFile>(file))
return getSourceLocationObj(o, sc, offset, name);
if (auto *b = dyn_cast<BitcodeFile>(file))
return getSourceLocationBitcode(b);
return "\n>>> defined at " + toString(file);
}
// Construct and print an error message in the form of:
//
// lld-link: error: duplicate symbol: foo
// >>> defined at bar.c:30
// >>> bar.o
// >>> defined at baz.c:563
// >>> baz.o
void SymbolTable::reportDuplicate(Symbol *existing, InputFile *newFile,
SectionChunk *newSc,
uint32_t newSectionOffset) {
std::string msg;
llvm::raw_string_ostream os(msg);
os << "duplicate symbol: " << toString(*existing);
DefinedRegular *d = dyn_cast<DefinedRegular>(existing);
if (d && isa<ObjFile>(d->getFile())) {
os << getSourceLocation(d->getFile(), d->getChunk(), d->getValue(),
existing->getName());
} else {
os << getSourceLocation(existing->getFile(), nullptr, 0, "");
}
os << getSourceLocation(newFile, newSc, newSectionOffset,
existing->getName());
if (config->forceMultiple)
warn(os.str());
else
error(os.str());
}
Symbol *SymbolTable::addAbsolute(StringRef n, COFFSymbolRef sym) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, nullptr);
s->isUsedInRegularObj = true;
if (wasInserted || isa<Undefined>(s) || s->isLazy())
replaceSymbol<DefinedAbsolute>(s, n, sym);
else if (auto *da = dyn_cast<DefinedAbsolute>(s)) {
if (da->getVA() != sym.getValue())
reportDuplicate(s, nullptr);
} else if (!isa<DefinedCOFF>(s))
reportDuplicate(s, nullptr);
return s;
}
Symbol *SymbolTable::addAbsolute(StringRef n, uint64_t va) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, nullptr);
s->isUsedInRegularObj = true;
if (wasInserted || isa<Undefined>(s) || s->isLazy())
replaceSymbol<DefinedAbsolute>(s, n, va);
else if (auto *da = dyn_cast<DefinedAbsolute>(s)) {
if (da->getVA() != va)
reportDuplicate(s, nullptr);
} else if (!isa<DefinedCOFF>(s))
reportDuplicate(s, nullptr);
return s;
}
Symbol *SymbolTable::addSynthetic(StringRef n, Chunk *c) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, nullptr);
s->isUsedInRegularObj = true;
if (wasInserted || isa<Undefined>(s) || s->isLazy())
replaceSymbol<DefinedSynthetic>(s, n, c);
else if (!isa<DefinedCOFF>(s))
reportDuplicate(s, nullptr);
return s;
}
Symbol *SymbolTable::addRegular(InputFile *f, StringRef n,
const coff_symbol_generic *sym, SectionChunk *c,
uint32_t sectionOffset) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, f);
if (wasInserted || !isa<DefinedRegular>(s))
replaceSymbol<DefinedRegular>(s, f, n, /*IsCOMDAT*/ false,
/*IsExternal*/ true, sym, c);
else
reportDuplicate(s, f, c, sectionOffset);
return s;
}
2019-01-30 10:17:27 +08:00
std::pair<DefinedRegular *, bool>
SymbolTable::addComdat(InputFile *f, StringRef n,
const coff_symbol_generic *sym) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, f);
if (wasInserted || !isa<DefinedRegular>(s)) {
replaceSymbol<DefinedRegular>(s, f, n, /*IsCOMDAT*/ true,
/*IsExternal*/ true, sym, nullptr);
2019-01-30 10:17:27 +08:00
return {cast<DefinedRegular>(s), true};
}
2019-01-30 10:17:27 +08:00
auto *existingSymbol = cast<DefinedRegular>(s);
if (!existingSymbol->isCOMDAT)
reportDuplicate(s, f);
2019-01-30 10:17:27 +08:00
return {existingSymbol, false};
}
Symbol *SymbolTable::addCommon(InputFile *f, StringRef n, uint64_t size,
const coff_symbol_generic *sym, CommonChunk *c) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, f);
if (wasInserted || !isa<DefinedCOFF>(s))
replaceSymbol<DefinedCommon>(s, f, n, size, sym, c);
else if (auto *dc = dyn_cast<DefinedCommon>(s))
if (size > dc->getSize())
replaceSymbol<DefinedCommon>(s, f, n, size, sym, c);
return s;
}
Symbol *SymbolTable::addImportData(StringRef n, ImportFile *f) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(n, nullptr);
s->isUsedInRegularObj = true;
if (wasInserted || isa<Undefined>(s) || s->isLazy()) {
replaceSymbol<DefinedImportData>(s, n, f);
return s;
}
reportDuplicate(s, f);
return nullptr;
}
Symbol *SymbolTable::addImportThunk(StringRef name, DefinedImportData *id,
uint16_t machine) {
Symbol *s;
bool wasInserted;
std::tie(s, wasInserted) = insert(name, nullptr);
s->isUsedInRegularObj = true;
if (wasInserted || isa<Undefined>(s) || s->isLazy()) {
replaceSymbol<DefinedImportThunk>(s, name, id, machine);
return s;
}
reportDuplicate(s, id->file);
return nullptr;
}
void SymbolTable::addLibcall(StringRef name) {
Symbol *sym = findUnderscore(name);
if (!sym)
return;
if (auto *l = dyn_cast<LazyArchive>(sym)) {
MemoryBufferRef mb = l->getMemberBuffer();
if (isBitcode(mb))
addUndefined(sym->getName());
} else if (LazyObject *o = dyn_cast<LazyObject>(sym)) {
if (isBitcode(o->file->mb))
addUndefined(sym->getName());
}
}
std::vector<Chunk *> SymbolTable::getChunks() const {
std::vector<Chunk *> res;
for (ObjFile *file : ctx.objFileInstances) {
ArrayRef<Chunk *> v = file->getChunks();
res.insert(res.end(), v.begin(), v.end());
}
return res;
}
Symbol *SymbolTable::find(StringRef name) const {
return symMap.lookup(CachedHashStringRef(name));
}
Symbol *SymbolTable::findUnderscore(StringRef name) const {
if (config->machine == I386)
return find(("_" + name).str());
return find(name);
}
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
// Return all symbols that start with Prefix, possibly ignoring the first
// character of Prefix or the first character symbol.
std::vector<Symbol *> SymbolTable::getSymsWithPrefix(StringRef prefix) {
std::vector<Symbol *> syms;
for (auto pair : symMap) {
StringRef name = pair.first.val();
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
if (name.startswith(prefix) || name.startswith(prefix.drop_front()) ||
name.drop_front().startswith(prefix) ||
name.drop_front().startswith(prefix.drop_front())) {
syms.push_back(pair.second);
}
}
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
return syms;
}
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
Symbol *SymbolTable::findMangle(StringRef name) {
if (Symbol *sym = find(name))
if (!isa<Undefined>(sym))
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
return sym;
// Efficient fuzzy string lookup is impossible with a hash table, so iterate
// the symbol table once and collect all possibly matching symbols into this
// vector. Then compare each possibly matching symbol with each possible
// mangling.
std::vector<Symbol *> syms = getSymsWithPrefix(name);
auto findByPrefix = [&syms](const Twine &t) -> Symbol * {
std::string prefix = t.str();
for (auto *s : syms)
if (s->getName().startswith(prefix))
return s;
return nullptr;
};
// For non-x86, just look for C++ functions.
if (config->machine != I386)
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
return findByPrefix("?" + name + "@@Y");
if (!name.startswith("_"))
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
return nullptr;
// Search for x86 stdcall function.
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
if (Symbol *s = findByPrefix(name + "@"))
return s;
// Search for x86 fastcall function.
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
if (Symbol *s = findByPrefix("@" + name.substr(1) + "@"))
return s;
// Search for x86 vectorcall function.
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
if (Symbol *s = findByPrefix(name.substr(1) + "@@"))
return s;
// Search for x86 C++ non-member function.
[COFF] Fix /export:foo=bar when bar is a weak alias Summary: When handling exports from the command line or from .def files, the linker does a "fuzzy" string lookup to allow finding mangled symbols. However, when the symbol is re-exported under a new name, the linker has to transfer the decorations from the exported symbol over to the new name. This is implemented by taking the mangled symbol that was found in the object and replacing the original symbol name with the export name. Before this patch, LLD implemented the fuzzy search by adding an undefined symbol with the unmangled name, and then during symbol resolution, checking if similar mangled symbols had been added after the last round of symbol resolution. If so, LLD makes the original symbol a weak alias of the mangled symbol. Later, to get the original symbol name, LLD would look through the weak alias and forward it on to the import library writer, which copies the symbol decorations. This approach doesn't work when bar is itself a weak alias, as is the case in asan. It's especially bad when the aliasee of bar contains the string "bar", consider "bar_default". In this case, we would end up exporting the symbol "foo_default" when we should've exported just "foo". To fix this, don't look through weak aliases to find the mangled name. Save the mangled name earlier during fuzzy symbol lookup. Fixes PR42074 Reviewers: mstorsjo, ruiu Subscribers: thakis, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62984 llvm-svn: 362849
2019-06-08 06:05:12 +08:00
return findByPrefix("?" + name.substr(1) + "@@Y");
}
Symbol *SymbolTable::addUndefined(StringRef name) {
return addUndefined(name, nullptr, false);
}
void SymbolTable::compileBitcodeFiles() {
if (ctx.bitcodeFileInstances.empty())
return;
ScopedTimer t(ctx.ltoTimer);
lto.reset(new BitcodeCompiler());
for (BitcodeFile *f : ctx.bitcodeFileInstances)
lto->add(*f);
for (InputFile *newObj : lto->compile(ctx)) {
ObjFile *obj = cast<ObjFile>(newObj);
obj->parse();
ctx.objFileInstances.push_back(obj);
}
}
} // namespace coff
} // namespace lld