2019-03-01 14:49:51 +08:00
|
|
|
//===-- CrossWindows.cpp - Cross Windows Tool Chain -----------------------===//
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// 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
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "CrossWindows.h"
|
|
|
|
#include "CommonArgs.h"
|
|
|
|
#include "clang/Driver/Compilation.h"
|
|
|
|
#include "clang/Driver/Driver.h"
|
|
|
|
#include "clang/Driver/Options.h"
|
|
|
|
#include "clang/Driver/SanitizerArgs.h"
|
|
|
|
#include "llvm/Option/ArgList.h"
|
|
|
|
#include "llvm/Support/Path.h"
|
|
|
|
|
|
|
|
using namespace clang::driver;
|
|
|
|
using namespace clang::driver::toolchains;
|
|
|
|
|
|
|
|
using llvm::opt::ArgList;
|
2018-10-13 02:55:36 +08:00
|
|
|
using llvm::opt::ArgStringList;
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
|
|
|
|
void tools::CrossWindows::Assembler::ConstructJob(
|
|
|
|
Compilation &C, const JobAction &JA, const InputInfo &Output,
|
|
|
|
const InputInfoList &Inputs, const ArgList &Args,
|
|
|
|
const char *LinkingOutput) const {
|
|
|
|
claimNoWarnArgs(Args);
|
|
|
|
const auto &TC =
|
|
|
|
static_cast<const toolchains::CrossWindowsToolChain &>(getToolChain());
|
|
|
|
ArgStringList CmdArgs;
|
|
|
|
const char *Exec;
|
|
|
|
|
|
|
|
switch (TC.getArch()) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unsupported architecture");
|
|
|
|
case llvm::Triple::arm:
|
|
|
|
case llvm::Triple::thumb:
|
2017-08-14 03:42:17 +08:00
|
|
|
case llvm::Triple::aarch64:
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
break;
|
|
|
|
case llvm::Triple::x86:
|
|
|
|
CmdArgs.push_back("--32");
|
|
|
|
break;
|
|
|
|
case llvm::Triple::x86_64:
|
|
|
|
CmdArgs.push_back("--64");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
Args.AddAllArgValues(CmdArgs, options::OPT_Wa_COMMA, options::OPT_Xassembler);
|
|
|
|
|
|
|
|
CmdArgs.push_back("-o");
|
|
|
|
CmdArgs.push_back(Output.getFilename());
|
|
|
|
|
|
|
|
for (const auto &Input : Inputs)
|
|
|
|
CmdArgs.push_back(Input.getFilename());
|
|
|
|
|
|
|
|
const std::string Assembler = TC.GetProgramPath("as");
|
|
|
|
Exec = Args.MakeArgString(Assembler);
|
|
|
|
|
|
|
|
C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
|
|
|
|
}
|
|
|
|
|
|
|
|
void tools::CrossWindows::Linker::ConstructJob(
|
|
|
|
Compilation &C, const JobAction &JA, const InputInfo &Output,
|
|
|
|
const InputInfoList &Inputs, const ArgList &Args,
|
|
|
|
const char *LinkingOutput) const {
|
|
|
|
const auto &TC =
|
|
|
|
static_cast<const toolchains::CrossWindowsToolChain &>(getToolChain());
|
|
|
|
const llvm::Triple &T = TC.getTriple();
|
|
|
|
const Driver &D = TC.getDriver();
|
|
|
|
SmallString<128> EntryPoint;
|
|
|
|
ArgStringList CmdArgs;
|
|
|
|
const char *Exec;
|
|
|
|
|
|
|
|
// Silence warning for "clang -g foo.o -o foo"
|
|
|
|
Args.ClaimAllArgs(options::OPT_g_Group);
|
|
|
|
// and "clang -emit-llvm foo.o -o foo"
|
|
|
|
Args.ClaimAllArgs(options::OPT_emit_llvm);
|
|
|
|
// and for "clang -w foo.o -o foo"
|
|
|
|
Args.ClaimAllArgs(options::OPT_w);
|
|
|
|
// Other warning options are already handled somewhere else.
|
|
|
|
|
|
|
|
if (!D.SysRoot.empty())
|
|
|
|
CmdArgs.push_back(Args.MakeArgString("--sysroot=" + D.SysRoot));
|
|
|
|
|
|
|
|
if (Args.hasArg(options::OPT_pie))
|
|
|
|
CmdArgs.push_back("-pie");
|
|
|
|
if (Args.hasArg(options::OPT_rdynamic))
|
|
|
|
CmdArgs.push_back("-export-dynamic");
|
|
|
|
if (Args.hasArg(options::OPT_s))
|
|
|
|
CmdArgs.push_back("--strip-all");
|
|
|
|
|
|
|
|
CmdArgs.push_back("-m");
|
|
|
|
switch (TC.getArch()) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unsupported architecture");
|
|
|
|
case llvm::Triple::arm:
|
|
|
|
case llvm::Triple::thumb:
|
|
|
|
// FIXME: this is incorrect for WinCE
|
|
|
|
CmdArgs.push_back("thumb2pe");
|
|
|
|
break;
|
2017-08-14 03:42:17 +08:00
|
|
|
case llvm::Triple::aarch64:
|
|
|
|
CmdArgs.push_back("arm64pe");
|
|
|
|
break;
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
case llvm::Triple::x86:
|
|
|
|
CmdArgs.push_back("i386pe");
|
|
|
|
EntryPoint.append("_");
|
|
|
|
break;
|
|
|
|
case llvm::Triple::x86_64:
|
|
|
|
CmdArgs.push_back("i386pep");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Args.hasArg(options::OPT_shared)) {
|
|
|
|
switch (T.getArch()) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unsupported architecture");
|
2017-08-14 03:42:17 +08:00
|
|
|
case llvm::Triple::aarch64:
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
case llvm::Triple::arm:
|
|
|
|
case llvm::Triple::thumb:
|
|
|
|
case llvm::Triple::x86_64:
|
|
|
|
EntryPoint.append("_DllMainCRTStartup");
|
|
|
|
break;
|
|
|
|
case llvm::Triple::x86:
|
|
|
|
EntryPoint.append("_DllMainCRTStartup@12");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
CmdArgs.push_back("-shared");
|
2018-02-28 03:42:19 +08:00
|
|
|
CmdArgs.push_back(Args.hasArg(options::OPT_static) ? "-Bstatic"
|
|
|
|
: "-Bdynamic");
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
|
|
|
|
CmdArgs.push_back("--enable-auto-image-base");
|
|
|
|
|
|
|
|
CmdArgs.push_back("--entry");
|
|
|
|
CmdArgs.push_back(Args.MakeArgString(EntryPoint));
|
|
|
|
} else {
|
|
|
|
EntryPoint.append("mainCRTStartup");
|
|
|
|
|
|
|
|
CmdArgs.push_back(Args.hasArg(options::OPT_static) ? "-Bstatic"
|
|
|
|
: "-Bdynamic");
|
|
|
|
|
|
|
|
if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nostartfiles)) {
|
|
|
|
CmdArgs.push_back("--entry");
|
|
|
|
CmdArgs.push_back(Args.MakeArgString(EntryPoint));
|
|
|
|
}
|
|
|
|
|
|
|
|
// FIXME: handle subsystem
|
|
|
|
}
|
|
|
|
|
|
|
|
// NOTE: deal with multiple definitions on Windows (e.g. COMDAT)
|
|
|
|
CmdArgs.push_back("--allow-multiple-definition");
|
|
|
|
|
|
|
|
CmdArgs.push_back("-o");
|
|
|
|
CmdArgs.push_back(Output.getFilename());
|
|
|
|
|
|
|
|
if (Args.hasArg(options::OPT_shared) || Args.hasArg(options::OPT_rdynamic)) {
|
|
|
|
SmallString<261> ImpLib(Output.getFilename());
|
|
|
|
llvm::sys::path::replace_extension(ImpLib, ".lib");
|
|
|
|
|
|
|
|
CmdArgs.push_back("--out-implib");
|
|
|
|
CmdArgs.push_back(Args.MakeArgString(ImpLib));
|
|
|
|
}
|
|
|
|
|
|
|
|
Args.AddAllArgs(CmdArgs, options::OPT_L);
|
|
|
|
TC.AddFilePathLibArgs(Args, CmdArgs);
|
|
|
|
AddLinkerInputs(TC, Inputs, Args, CmdArgs, JA);
|
|
|
|
|
2017-07-26 02:02:57 +08:00
|
|
|
if (TC.ShouldLinkCXXStdlib(Args)) {
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
bool StaticCXX = Args.hasArg(options::OPT_static_libstdcxx) &&
|
|
|
|
!Args.hasArg(options::OPT_static);
|
|
|
|
if (StaticCXX)
|
|
|
|
CmdArgs.push_back("-Bstatic");
|
|
|
|
TC.AddCXXStdlibLibArgs(Args, CmdArgs);
|
|
|
|
if (StaticCXX)
|
|
|
|
CmdArgs.push_back("-Bdynamic");
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!Args.hasArg(options::OPT_nostdlib)) {
|
|
|
|
if (!Args.hasArg(options::OPT_nodefaultlibs)) {
|
|
|
|
// TODO handle /MT[d] /MD[d]
|
|
|
|
CmdArgs.push_back("-lmsvcrt");
|
|
|
|
AddRunTimeLibs(TC, D, CmdArgs, Args);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (TC.getSanitizerArgs().needsAsanRt()) {
|
|
|
|
// TODO handle /MT[d] /MD[d]
|
|
|
|
if (Args.hasArg(options::OPT_shared)) {
|
|
|
|
CmdArgs.push_back(TC.getCompilerRTArgString(Args, "asan_dll_thunk"));
|
|
|
|
} else {
|
|
|
|
for (const auto &Lib : {"asan_dynamic", "asan_dynamic_runtime_thunk"})
|
|
|
|
CmdArgs.push_back(TC.getCompilerRTArgString(Args, Lib));
|
|
|
|
// Make sure the dynamic runtime thunk is not optimized out at link time
|
|
|
|
// to ensure proper SEH handling.
|
|
|
|
CmdArgs.push_back(Args.MakeArgString("--undefined"));
|
|
|
|
CmdArgs.push_back(Args.MakeArgString(TC.getArch() == llvm::Triple::x86
|
|
|
|
? "___asan_seh_interceptor"
|
|
|
|
: "__asan_seh_interceptor"));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
Exec = Args.MakeArgString(TC.GetLinkerPath());
|
|
|
|
|
|
|
|
C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
|
|
|
|
}
|
|
|
|
|
|
|
|
CrossWindowsToolChain::CrossWindowsToolChain(const Driver &D,
|
|
|
|
const llvm::Triple &T,
|
|
|
|
const llvm::opt::ArgList &Args)
|
2017-09-22 12:01:12 +08:00
|
|
|
: Generic_GCC(D, T, Args) {}
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
|
2017-08-04 07:55:42 +08:00
|
|
|
bool CrossWindowsToolChain::IsUnwindTablesDefault(const ArgList &Args) const {
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
// FIXME: all non-x86 targets need unwind tables, however, LLVM currently does
|
|
|
|
// not know how to emit them.
|
|
|
|
return getArch() == llvm::Triple::x86_64;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool CrossWindowsToolChain::isPICDefault() const {
|
|
|
|
return getArch() == llvm::Triple::x86_64;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool CrossWindowsToolChain::isPIEDefault() const {
|
|
|
|
return getArch() == llvm::Triple::x86_64;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool CrossWindowsToolChain::isPICDefaultForced() const {
|
|
|
|
return getArch() == llvm::Triple::x86_64;
|
|
|
|
}
|
|
|
|
|
|
|
|
void CrossWindowsToolChain::
|
|
|
|
AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
|
|
|
|
llvm::opt::ArgStringList &CC1Args) const {
|
|
|
|
const Driver &D = getDriver();
|
|
|
|
const std::string &SysRoot = D.SysRoot;
|
|
|
|
|
2017-06-30 23:15:38 +08:00
|
|
|
auto AddSystemAfterIncludes = [&]() {
|
|
|
|
for (const auto &P : DriverArgs.getAllArgValues(options::OPT_isystem_after))
|
|
|
|
addSystemInclude(DriverArgs, CC1Args, P);
|
|
|
|
};
|
|
|
|
|
|
|
|
if (DriverArgs.hasArg(options::OPT_nostdinc)) {
|
|
|
|
AddSystemAfterIncludes();
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
return;
|
2017-06-30 23:15:38 +08:00
|
|
|
}
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
|
|
|
|
addSystemInclude(DriverArgs, CC1Args, SysRoot + "/usr/local/include");
|
|
|
|
if (!DriverArgs.hasArg(options::OPT_nobuiltininc)) {
|
|
|
|
SmallString<128> ResourceDir(D.ResourceDir);
|
|
|
|
llvm::sys::path::append(ResourceDir, "include");
|
|
|
|
addSystemInclude(DriverArgs, CC1Args, ResourceDir);
|
|
|
|
}
|
2017-06-30 23:15:38 +08:00
|
|
|
AddSystemAfterIncludes();
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
addExternCSystemInclude(DriverArgs, CC1Args, SysRoot + "/usr/include");
|
|
|
|
}
|
|
|
|
|
|
|
|
void CrossWindowsToolChain::
|
|
|
|
AddClangCXXStdlibIncludeArgs(const llvm::opt::ArgList &DriverArgs,
|
|
|
|
llvm::opt::ArgStringList &CC1Args) const {
|
|
|
|
const std::string &SysRoot = getDriver().SysRoot;
|
|
|
|
|
2017-06-30 23:15:38 +08:00
|
|
|
if (DriverArgs.hasArg(options::OPT_nostdinc) ||
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
DriverArgs.hasArg(options::OPT_nostdincxx))
|
|
|
|
return;
|
|
|
|
|
2017-09-22 12:01:12 +08:00
|
|
|
if (GetCXXStdlibType(DriverArgs) == ToolChain::CST_Libcxx)
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
addSystemInclude(DriverArgs, CC1Args, SysRoot + "/usr/include/c++/v1");
|
|
|
|
}
|
|
|
|
|
|
|
|
void CrossWindowsToolChain::
|
|
|
|
AddCXXStdlibLibArgs(const llvm::opt::ArgList &DriverArgs,
|
|
|
|
llvm::opt::ArgStringList &CC1Args) const {
|
2017-09-22 12:01:12 +08:00
|
|
|
if (GetCXXStdlibType(DriverArgs) == ToolChain::CST_Libcxx)
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
CC1Args.push_back("-lc++");
|
|
|
|
}
|
|
|
|
|
|
|
|
clang::SanitizerMask CrossWindowsToolChain::getSupportedSanitizers() const {
|
|
|
|
SanitizerMask Res = ToolChain::getSupportedSanitizers();
|
|
|
|
Res |= SanitizerKind::Address;
|
2019-04-12 22:14:58 +08:00
|
|
|
Res |= SanitizerKind::PointerCompare;
|
|
|
|
Res |= SanitizerKind::PointerSubtract;
|
[Driver] Consolidate tools and toolchains by target platform. (NFC)
Summary:
(This is a move-only refactoring patch. There are no functionality changes.)
This patch splits apart the Clang driver's tool and toolchain implementation
files. Each target platform toolchain is moved to its own file, along with the
closest-related tools. Each target platform toolchain has separate headers and
implementation files, so the hierarchy of classes is unchanged.
There are some remaining shared free functions, mostly from Tools.cpp. Several
of these move to their own architecture-specific files, similar to r296056. Some
of them are only used by a single target platform; since the tools and
toolchains are now together, some helpers now live in a platform-specific file.
The balance are helpers related to manipulating argument lists, so they are now
in a new file pair, CommonArgs.h and .cpp.
I've tried to cluster the code logically, which is fairly straightforward for
most of the target platforms and shared architectures. I think I've made
reasonable choices for these, as well as the various shared helpers; but of
course, I'm happy to hear feedback in the review.
There are some particular things I don't like about this patch, but haven't been
able to find a better overall solution. The first is the proliferation of files:
there are several files that are tiny because the toolchain is not very
different from its base (usually the Gnu tools/toolchain). I think this is
mostly a reflection of the true complexity, though, so it may not be "fixable"
in any reasonable sense. The second thing I don't like are the includes like
"../Something.h". I've avoided this largely by clustering into the current file
structure. However, a few of these includes remain, and in those cases it
doesn't make sense to me to sink an existing file any deeper.
Reviewers: rsmith, mehdi_amini, compnerd, rnk, javed.absar
Subscribers: emaste, jfb, danalbert, srhines, dschuff, jyknight, nemanjai, nhaehnle, mgorny, cfe-commits
Differential Revision: https://reviews.llvm.org/D30372
llvm-svn: 297250
2017-03-08 09:02:16 +08:00
|
|
|
return Res;
|
|
|
|
}
|
|
|
|
|
|
|
|
Tool *CrossWindowsToolChain::buildLinker() const {
|
|
|
|
return new tools::CrossWindows::Linker(*this);
|
|
|
|
}
|
|
|
|
|
|
|
|
Tool *CrossWindowsToolChain::buildAssembler() const {
|
|
|
|
return new tools::CrossWindows::Assembler(*this);
|
|
|
|
}
|