llvm-project/lld/ELF/DriverUtils.cpp

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

260 lines
9.0 KiB
C++
Raw Normal View History

//===- DriverUtils.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
//
//===----------------------------------------------------------------------===//
//
// This file contains utility functions for the driver. Because there
// are so many small functions, we created this separate file to make
// Driver.cpp less cluttered.
//
//===----------------------------------------------------------------------===//
#include "Driver.h"
#include "lld/Common/CommonLinkerContext.h"
#include "lld/Common/Reproduce.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Option/Option.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/Process.h"
#include "llvm/Support/TimeProfiler.h"
using namespace llvm;
using namespace llvm::sys;
using namespace llvm::opt;
using namespace lld;
using namespace lld::elf;
// Create OptTable
// Create prefix string literals used in Options.td
#define PREFIX(NAME, VALUE) const char *const NAME[] = VALUE;
#include "Options.inc"
#undef PREFIX
// Create table mapping all options defined in Options.td
static const opt::OptTable::Info optInfo[] = {
#define OPTION(X1, X2, ID, KIND, GROUP, ALIAS, X7, X8, X9, X10, X11, X12) \
{X1, X2, X10, X11, OPT_##ID, opt::Option::KIND##Class, \
X9, X8, OPT_##GROUP, OPT_##ALIAS, X7, X12},
#include "Options.inc"
#undef OPTION
};
ELFOptTable::ELFOptTable() : OptTable(optInfo) {}
// Set color diagnostics according to --color-diagnostics={auto,always,never}
// or --no-color-diagnostics flags.
static void handleColorDiagnostics(opt::InputArgList &args) {
auto *arg = args.getLastArg(OPT_color_diagnostics, OPT_color_diagnostics_eq,
OPT_no_color_diagnostics);
if (!arg)
return;
if (arg->getOption().getID() == OPT_color_diagnostics) {
lld::errs().enable_colors(true);
} else if (arg->getOption().getID() == OPT_no_color_diagnostics) {
lld::errs().enable_colors(false);
} else {
StringRef s = arg->getValue();
if (s == "always")
lld::errs().enable_colors(true);
else if (s == "never")
lld::errs().enable_colors(false);
else if (s != "auto")
error("unknown option: --color-diagnostics=" + s);
}
}
static cl::TokenizerCallback getQuotingStyle(opt::InputArgList &args) {
if (auto *arg = args.getLastArg(OPT_rsp_quoting)) {
StringRef s = arg->getValue();
if (s != "windows" && s != "posix")
error("invalid response file quoting: " + s);
if (s == "windows")
return cl::TokenizeWindowsCommandLine;
return cl::TokenizeGNUCommandLine;
}
if (Triple(sys::getProcessTriple()).isOSWindows())
return cl::TokenizeWindowsCommandLine;
return cl::TokenizeGNUCommandLine;
}
// Gold LTO plugin takes a `--plugin-opt foo=bar` option as an alias for
// `--plugin-opt=foo=bar`. We want to handle `--plugin-opt=foo=` as an
// option name and `bar` as a value. Unfortunately, OptParser cannot
// handle an option with a space in it.
//
// In this function, we concatenate command line arguments so that
// `--plugin-opt <foo>` is converted to `--plugin-opt=<foo>`. This is a
// bit hacky, but looks like it is still better than handling --plugin-opt
// options by hand.
static void concatLTOPluginOptions(SmallVectorImpl<const char *> &args) {
SmallVector<const char *, 256> v;
for (size_t i = 0, e = args.size(); i != e; ++i) {
StringRef s = args[i];
if ((s == "-plugin-opt" || s == "--plugin-opt") && i + 1 != e) {
v.push_back(saver().save(s + "=" + args[i + 1]).data());
++i;
} else {
v.push_back(args[i]);
}
}
args = std::move(v);
}
// Parses a given list of options.
opt::InputArgList ELFOptTable::parse(ArrayRef<const char *> argv) {
// Make InputArgList from string vectors.
unsigned missingIndex;
unsigned missingCount;
SmallVector<const char *, 256> vec(argv.data(), argv.data() + argv.size());
// We need to get the quoting style for response files before parsing all
// options so we parse here before and ignore all the options but
// --rsp-quoting.
opt::InputArgList args = this->ParseArgs(vec, missingIndex, missingCount);
// Expand response files (arguments in the form of @<filename>)
// and then parse the argument again.
cl::ExpandResponseFiles(saver(), getQuotingStyle(args), vec);
concatLTOPluginOptions(vec);
args = this->ParseArgs(vec, missingIndex, missingCount);
[Coding style change] Rename variables so that they start with a lowercase letter This patch is mechanically generated by clang-llvm-rename tool that I wrote using Clang Refactoring Engine just for creating this patch. You can see the source code of the tool at https://reviews.llvm.org/D64123. There's no manual post-processing; you can generate the same patch by re-running the tool against lld's code base. Here is the main discussion thread to change the LLVM coding style: https://lists.llvm.org/pipermail/llvm-dev/2019-February/130083.html In the discussion thread, I proposed we use lld as a testbed for variable naming scheme change, and this patch does that. I chose to rename variables so that they are in camelCase, just because that is a minimal change to make variables to start with a lowercase letter. Note to downstream patch maintainers: if you are maintaining a downstream lld repo, just rebasing ahead of this commit would cause massive merge conflicts because this patch essentially changes every line in the lld subdirectory. But there's a remedy. clang-llvm-rename tool is a batch tool, so you can rename variables in your downstream repo with the tool. Given that, here is how to rebase your repo to a commit after the mass renaming: 1. rebase to the commit just before the mass variable renaming, 2. apply the tool to your downstream repo to mass-rename variables locally, and 3. rebase again to the head. Most changes made by the tool should be identical for a downstream repo and for the head, so at the step 3, almost all changes should be merged and disappear. I'd expect that there would be some lines that you need to merge by hand, but that shouldn't be too many. Differential Revision: https://reviews.llvm.org/D64121 llvm-svn: 365595
2019-07-10 13:00:37 +08:00
handleColorDiagnostics(args);
if (missingCount)
error(Twine(args.getArgString(missingIndex)) + ": missing argument");
[Coding style change] Rename variables so that they start with a lowercase letter This patch is mechanically generated by clang-llvm-rename tool that I wrote using Clang Refactoring Engine just for creating this patch. You can see the source code of the tool at https://reviews.llvm.org/D64123. There's no manual post-processing; you can generate the same patch by re-running the tool against lld's code base. Here is the main discussion thread to change the LLVM coding style: https://lists.llvm.org/pipermail/llvm-dev/2019-February/130083.html In the discussion thread, I proposed we use lld as a testbed for variable naming scheme change, and this patch does that. I chose to rename variables so that they are in camelCase, just because that is a minimal change to make variables to start with a lowercase letter. Note to downstream patch maintainers: if you are maintaining a downstream lld repo, just rebasing ahead of this commit would cause massive merge conflicts because this patch essentially changes every line in the lld subdirectory. But there's a remedy. clang-llvm-rename tool is a batch tool, so you can rename variables in your downstream repo with the tool. Given that, here is how to rebase your repo to a commit after the mass renaming: 1. rebase to the commit just before the mass variable renaming, 2. apply the tool to your downstream repo to mass-rename variables locally, and 3. rebase again to the head. Most changes made by the tool should be identical for a downstream repo and for the head, so at the step 3, almost all changes should be merged and disappear. I'd expect that there would be some lines that you need to merge by hand, but that shouldn't be too many. Differential Revision: https://reviews.llvm.org/D64121 llvm-svn: 365595
2019-07-10 13:00:37 +08:00
for (opt::Arg *arg : args.filtered(OPT_UNKNOWN)) {
std::string nearest;
if (findNearest(arg->getAsString(args), nearest) > 1)
error("unknown argument '" + arg->getAsString(args) + "'");
else
error("unknown argument '" + arg->getAsString(args) +
"', did you mean '" + nearest + "'");
}
return args;
}
void elf::printHelp() {
ELFOptTable().printHelp(
lld::outs(), (config->progName + " [options] file...").str().c_str(),
"lld", false /*ShowHidden*/, true /*ShowAllAliases*/);
lld::outs() << "\n";
// Scripts generated by Libtool versions up to 2021-10 expect /: supported
// targets:.* elf/ in a message for the --help option. If it doesn't match,
// the scripts assume that the linker doesn't support very basic features
// such as shared libraries. Therefore, we need to print out at least "elf".
lld::outs() << config->progName << ": supported targets: elf\n";
}
static std::string rewritePath(StringRef s) {
if (fs::exists(s))
return relativeToRoot(s);
return std::string(s);
}
// Reconstructs command line arguments so that so that you can re-run
// the same command with the same inputs. This is for --reproduce.
std::string elf::createResponseFile(const opt::InputArgList &args) {
SmallString<0> data;
raw_svector_ostream os(data);
os << "--chroot .\n";
// Copy the command line to the output while rewriting paths.
for (auto *arg : args) {
switch (arg->getOption().getID()) {
case OPT_reproduce:
break;
case OPT_INPUT:
os << quote(rewritePath(arg->getValue())) << "\n";
break;
case OPT_o:
// If -o path contains directories, "lld @response.txt" will likely
// fail because the archive we are creating doesn't contain empty
// directories for the output path (-o doesn't create directories).
// Strip directories to prevent the issue.
os << "-o " << quote(path::filename(arg->getValue())) << "\n";
break;
case OPT_lto_sample_profile:
os << arg->getSpelling() << quote(rewritePath(arg->getValue())) << "\n";
break;
case OPT_call_graph_ordering_file:
case OPT_dynamic_list:
case OPT_just_symbols:
case OPT_library_path:
case OPT_retain_symbols_file:
case OPT_rpath:
case OPT_script:
case OPT_symbol_ordering_file:
case OPT_sysroot:
case OPT_version_script:
os << arg->getSpelling() << " " << quote(rewritePath(arg->getValue()))
<< "\n";
break;
default:
os << toString(*arg) << "\n";
}
}
return std::string(data.str());
}
// Find a file by concatenating given paths. If a resulting path
// starts with "=", the character is replaced with a --sysroot value.
static Optional<std::string> findFile(StringRef path1, const Twine &path2) {
SmallString<128> s;
if (path1.startswith("="))
path::append(s, config->sysroot, path1.substr(1), path2);
else
path::append(s, path1, path2);
if (fs::exists(s))
return std::string(s);
return None;
}
Optional<std::string> elf::findFromSearchPaths(StringRef path) {
for (StringRef dir : config->searchPaths)
if (Optional<std::string> s = findFile(dir, path))
return s;
return None;
}
[ELF] Implement Dependent Libraries Feature This patch implements a limited form of autolinking primarily designed to allow either the --dependent-library compiler option, or "comment lib" pragmas ( https://docs.microsoft.com/en-us/cpp/preprocessor/comment-c-cpp?view=vs-2017) in C/C++ e.g. #pragma comment(lib, "foo"), to cause an ELF linker to automatically add the specified library to the link when processing the input file generated by the compiler. Currently this extension is unique to LLVM and LLD. However, care has been taken to design this feature so that it could be supported by other ELF linkers. The design goals were to provide: - A simple linking model for developers to reason about. - The ability to to override autolinking from the linker command line. - Source code compatibility, where possible, with "comment lib" pragmas in other environments (MSVC in particular). Dependent library support is implemented differently for ELF platforms than on the other platforms. Primarily this difference is that on ELF we pass the dependent library specifiers directly to the linker without manipulating them. This is in contrast to other platforms where they are mapped to a specific linker option by the compiler. This difference is a result of the greater variety of ELF linkers and the fact that ELF linkers tend to handle libraries in a more complicated fashion than on other platforms. This forces us to defer handling the specifiers to the linker. In order to achieve a level of source code compatibility with other platforms we have restricted this feature to work with libraries that meet the following "reasonable" requirements: 1. There are no competing defined symbols in a given set of libraries, or if they exist, the program owner doesn't care which is linked to their program. 2. There may be circular dependencies between libraries. The binary representation is a mergeable string section (SHF_MERGE, SHF_STRINGS), called .deplibs, with custom type SHT_LLVM_DEPENDENT_LIBRARIES (0x6fff4c04). The compiler forms this section by concatenating the arguments of the "comment lib" pragmas and --dependent-library options in the order they are encountered. Partial (-r, -Ur) links are handled by concatenating .deplibs sections with the normal mergeable string section rules. As an example, #pragma comment(lib, "foo") would result in: .section ".deplibs","MS",@llvm_dependent_libraries,1 .asciz "foo" For LTO, equivalent information to the contents of a the .deplibs section can be retrieved by the LLD for bitcode input files. LLD processes the dependent library specifiers in the following way: 1. Dependent libraries which are found from the specifiers in .deplibs sections of relocatable object files are added when the linker decides to include that file (which could itself be in a library) in the link. Dependent libraries behave as if they were appended to the command line after all other options. As a consequence the set of dependent libraries are searched last to resolve symbols. 2. It is an error if a file cannot be found for a given specifier. 3. Any command line options in effect at the end of the command line parsing apply to the dependent libraries, e.g. --whole-archive. 4. The linker tries to add a library or relocatable object file from each of the strings in a .deplibs section by; first, handling the string as if it was specified on the command line; second, by looking for the string in each of the library search paths in turn; third, by looking for a lib<string>.a or lib<string>.so (depending on the current mode of the linker) in each of the library search paths. 5. A new command line option --no-dependent-libraries tells LLD to ignore the dependent libraries. Rationale for the above points: 1. Adding the dependent libraries last makes the process simple to understand from a developers perspective. All linkers are able to implement this scheme. 2. Error-ing for libraries that are not found seems like better behavior than failing the link during symbol resolution. 3. It seems useful for the user to be able to apply command line options which will affect all of the dependent libraries. There is a potential problem of surprise for developers, who might not realize that these options would apply to these "invisible" input files; however, despite the potential for surprise, this is easy for developers to reason about and gives developers the control that they may require. 4. This algorithm takes into account all of the different ways that ELF linkers find input files. The different search methods are tried by the linker in most obvious to least obvious order. 5. I considered adding finer grained control over which dependent libraries were ignored (e.g. MSVC has /nodefaultlib:<library>); however, I concluded that this is not necessary: if finer control is required developers can fall back to using the command line directly. RFC thread: http://lists.llvm.org/pipermail/llvm-dev/2019-March/131004.html. Differential Revision: https://reviews.llvm.org/D60274 llvm-svn: 360984
2019-05-17 11:44:15 +08:00
// This is for -l<basename>. We'll look for lib<basename>.so or lib<basename>.a from
// search paths.
Optional<std::string> elf::searchLibraryBaseName(StringRef name) {
for (StringRef dir : config->searchPaths) {
if (!config->isStatic)
if (Optional<std::string> s = findFile(dir, "lib" + name + ".so"))
return s;
if (Optional<std::string> s = findFile(dir, "lib" + name + ".a"))
return s;
}
return None;
}
[ELF] Implement Dependent Libraries Feature This patch implements a limited form of autolinking primarily designed to allow either the --dependent-library compiler option, or "comment lib" pragmas ( https://docs.microsoft.com/en-us/cpp/preprocessor/comment-c-cpp?view=vs-2017) in C/C++ e.g. #pragma comment(lib, "foo"), to cause an ELF linker to automatically add the specified library to the link when processing the input file generated by the compiler. Currently this extension is unique to LLVM and LLD. However, care has been taken to design this feature so that it could be supported by other ELF linkers. The design goals were to provide: - A simple linking model for developers to reason about. - The ability to to override autolinking from the linker command line. - Source code compatibility, where possible, with "comment lib" pragmas in other environments (MSVC in particular). Dependent library support is implemented differently for ELF platforms than on the other platforms. Primarily this difference is that on ELF we pass the dependent library specifiers directly to the linker without manipulating them. This is in contrast to other platforms where they are mapped to a specific linker option by the compiler. This difference is a result of the greater variety of ELF linkers and the fact that ELF linkers tend to handle libraries in a more complicated fashion than on other platforms. This forces us to defer handling the specifiers to the linker. In order to achieve a level of source code compatibility with other platforms we have restricted this feature to work with libraries that meet the following "reasonable" requirements: 1. There are no competing defined symbols in a given set of libraries, or if they exist, the program owner doesn't care which is linked to their program. 2. There may be circular dependencies between libraries. The binary representation is a mergeable string section (SHF_MERGE, SHF_STRINGS), called .deplibs, with custom type SHT_LLVM_DEPENDENT_LIBRARIES (0x6fff4c04). The compiler forms this section by concatenating the arguments of the "comment lib" pragmas and --dependent-library options in the order they are encountered. Partial (-r, -Ur) links are handled by concatenating .deplibs sections with the normal mergeable string section rules. As an example, #pragma comment(lib, "foo") would result in: .section ".deplibs","MS",@llvm_dependent_libraries,1 .asciz "foo" For LTO, equivalent information to the contents of a the .deplibs section can be retrieved by the LLD for bitcode input files. LLD processes the dependent library specifiers in the following way: 1. Dependent libraries which are found from the specifiers in .deplibs sections of relocatable object files are added when the linker decides to include that file (which could itself be in a library) in the link. Dependent libraries behave as if they were appended to the command line after all other options. As a consequence the set of dependent libraries are searched last to resolve symbols. 2. It is an error if a file cannot be found for a given specifier. 3. Any command line options in effect at the end of the command line parsing apply to the dependent libraries, e.g. --whole-archive. 4. The linker tries to add a library or relocatable object file from each of the strings in a .deplibs section by; first, handling the string as if it was specified on the command line; second, by looking for the string in each of the library search paths in turn; third, by looking for a lib<string>.a or lib<string>.so (depending on the current mode of the linker) in each of the library search paths. 5. A new command line option --no-dependent-libraries tells LLD to ignore the dependent libraries. Rationale for the above points: 1. Adding the dependent libraries last makes the process simple to understand from a developers perspective. All linkers are able to implement this scheme. 2. Error-ing for libraries that are not found seems like better behavior than failing the link during symbol resolution. 3. It seems useful for the user to be able to apply command line options which will affect all of the dependent libraries. There is a potential problem of surprise for developers, who might not realize that these options would apply to these "invisible" input files; however, despite the potential for surprise, this is easy for developers to reason about and gives developers the control that they may require. 4. This algorithm takes into account all of the different ways that ELF linkers find input files. The different search methods are tried by the linker in most obvious to least obvious order. 5. I considered adding finer grained control over which dependent libraries were ignored (e.g. MSVC has /nodefaultlib:<library>); however, I concluded that this is not necessary: if finer control is required developers can fall back to using the command line directly. RFC thread: http://lists.llvm.org/pipermail/llvm-dev/2019-March/131004.html. Differential Revision: https://reviews.llvm.org/D60274 llvm-svn: 360984
2019-05-17 11:44:15 +08:00
// This is for -l<namespec>.
Optional<std::string> elf::searchLibrary(StringRef name) {
llvm::TimeTraceScope timeScope("Locate library", name);
if (name.startswith(":"))
return findFromSearchPaths(name.substr(1));
return searchLibraryBaseName(name);
[ELF] Implement Dependent Libraries Feature This patch implements a limited form of autolinking primarily designed to allow either the --dependent-library compiler option, or "comment lib" pragmas ( https://docs.microsoft.com/en-us/cpp/preprocessor/comment-c-cpp?view=vs-2017) in C/C++ e.g. #pragma comment(lib, "foo"), to cause an ELF linker to automatically add the specified library to the link when processing the input file generated by the compiler. Currently this extension is unique to LLVM and LLD. However, care has been taken to design this feature so that it could be supported by other ELF linkers. The design goals were to provide: - A simple linking model for developers to reason about. - The ability to to override autolinking from the linker command line. - Source code compatibility, where possible, with "comment lib" pragmas in other environments (MSVC in particular). Dependent library support is implemented differently for ELF platforms than on the other platforms. Primarily this difference is that on ELF we pass the dependent library specifiers directly to the linker without manipulating them. This is in contrast to other platforms where they are mapped to a specific linker option by the compiler. This difference is a result of the greater variety of ELF linkers and the fact that ELF linkers tend to handle libraries in a more complicated fashion than on other platforms. This forces us to defer handling the specifiers to the linker. In order to achieve a level of source code compatibility with other platforms we have restricted this feature to work with libraries that meet the following "reasonable" requirements: 1. There are no competing defined symbols in a given set of libraries, or if they exist, the program owner doesn't care which is linked to their program. 2. There may be circular dependencies between libraries. The binary representation is a mergeable string section (SHF_MERGE, SHF_STRINGS), called .deplibs, with custom type SHT_LLVM_DEPENDENT_LIBRARIES (0x6fff4c04). The compiler forms this section by concatenating the arguments of the "comment lib" pragmas and --dependent-library options in the order they are encountered. Partial (-r, -Ur) links are handled by concatenating .deplibs sections with the normal mergeable string section rules. As an example, #pragma comment(lib, "foo") would result in: .section ".deplibs","MS",@llvm_dependent_libraries,1 .asciz "foo" For LTO, equivalent information to the contents of a the .deplibs section can be retrieved by the LLD for bitcode input files. LLD processes the dependent library specifiers in the following way: 1. Dependent libraries which are found from the specifiers in .deplibs sections of relocatable object files are added when the linker decides to include that file (which could itself be in a library) in the link. Dependent libraries behave as if they were appended to the command line after all other options. As a consequence the set of dependent libraries are searched last to resolve symbols. 2. It is an error if a file cannot be found for a given specifier. 3. Any command line options in effect at the end of the command line parsing apply to the dependent libraries, e.g. --whole-archive. 4. The linker tries to add a library or relocatable object file from each of the strings in a .deplibs section by; first, handling the string as if it was specified on the command line; second, by looking for the string in each of the library search paths in turn; third, by looking for a lib<string>.a or lib<string>.so (depending on the current mode of the linker) in each of the library search paths. 5. A new command line option --no-dependent-libraries tells LLD to ignore the dependent libraries. Rationale for the above points: 1. Adding the dependent libraries last makes the process simple to understand from a developers perspective. All linkers are able to implement this scheme. 2. Error-ing for libraries that are not found seems like better behavior than failing the link during symbol resolution. 3. It seems useful for the user to be able to apply command line options which will affect all of the dependent libraries. There is a potential problem of surprise for developers, who might not realize that these options would apply to these "invisible" input files; however, despite the potential for surprise, this is easy for developers to reason about and gives developers the control that they may require. 4. This algorithm takes into account all of the different ways that ELF linkers find input files. The different search methods are tried by the linker in most obvious to least obvious order. 5. I considered adding finer grained control over which dependent libraries were ignored (e.g. MSVC has /nodefaultlib:<library>); however, I concluded that this is not necessary: if finer control is required developers can fall back to using the command line directly. RFC thread: http://lists.llvm.org/pipermail/llvm-dev/2019-March/131004.html. Differential Revision: https://reviews.llvm.org/D60274 llvm-svn: 360984
2019-05-17 11:44:15 +08:00
}
// If a linker/version script doesn't exist in the current directory, we also
// look for the script in the '-L' search paths. This matches the behaviour of
// '-T', --version-script=, and linker script INPUT() command in ld.bfd.
Optional<std::string> elf::searchScript(StringRef name) {
if (fs::exists(name))
return name.str();
return findFromSearchPaths(name);
}