llvm-project/clang/lib/Basic/Targets/X86.h

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

899 lines
28 KiB
C
Raw Normal View History

//===--- X86.h - Declare X86 target feature support -------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file declares X86 TargetInfo objects.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_LIB_BASIC_TARGETS_X86_H
#define LLVM_CLANG_LIB_BASIC_TARGETS_X86_H
#include "OSTargets.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Basic/TargetOptions.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/X86TargetParser.h"
namespace clang {
namespace targets {
static const unsigned X86AddrSpaceMap[] = {
0, // Default
0, // opencl_global
0, // opencl_local
0, // opencl_constant
0, // opencl_private
0, // opencl_generic
0, // cuda_device
0, // cuda_constant
0, // cuda_shared
270, // ptr32_sptr
271, // ptr32_uptr
272 // ptr64
};
// X86 target abstract base class; x86-32 and x86-64 are very close, so
// most of the implementation can be shared.
class LLVM_LIBRARY_VISIBILITY X86TargetInfo : public TargetInfo {
enum X86SSEEnum {
NoSSE,
SSE1,
SSE2,
SSE3,
SSSE3,
SSE41,
SSE42,
AVX,
AVX2,
AVX512F
} SSELevel = NoSSE;
enum MMX3DNowEnum {
NoMMX3DNow,
MMX,
AMD3DNow,
AMD3DNowAthlon
} MMX3DNowLevel = NoMMX3DNow;
enum XOPEnum { NoXOP, SSE4A, FMA4, XOP } XOPLevel = NoXOP;
enum AddrSpace { ptr32_sptr = 270, ptr32_uptr = 271, ptr64 = 272 };
bool HasAES = false;
bool HasVAES = false;
bool HasPCLMUL = false;
bool HasVPCLMULQDQ = false;
bool HasGFNI = false;
bool HasLZCNT = false;
bool HasRDRND = false;
bool HasFSGSBASE = false;
bool HasBMI = false;
bool HasBMI2 = false;
bool HasPOPCNT = false;
bool HasRTM = false;
bool HasPRFCHW = false;
bool HasRDSEED = false;
bool HasADX = false;
bool HasTBM = false;
bool HasLWP = false;
bool HasFMA = false;
bool HasF16C = false;
bool HasAVX512CD = false;
bool HasAVX512VPOPCNTDQ = false;
bool HasAVX512VNNI = false;
bool HasAVX512BF16 = false;
bool HasAVX512ER = false;
bool HasAVX512PF = false;
bool HasAVX512DQ = false;
bool HasAVX512BITALG = false;
bool HasAVX512BW = false;
bool HasAVX512VL = false;
bool HasAVX512VBMI = false;
bool HasAVX512VBMI2 = false;
bool HasAVX512IFMA = false;
bool HasAVX512VP2INTERSECT = false;
bool HasSHA = false;
bool HasSHSTK = false;
bool HasSGX = false;
bool HasCX8 = false;
bool HasCX16 = false;
bool HasFXSR = false;
bool HasXSAVE = false;
bool HasXSAVEOPT = false;
bool HasXSAVEC = false;
bool HasXSAVES = false;
bool HasMWAITX = false;
bool HasCLZERO = false;
bool HasCLDEMOTE = false;
bool HasPCONFIG = false;
bool HasPKU = false;
bool HasCLFLUSHOPT = false;
bool HasCLWB = false;
bool HasMOVBE = false;
bool HasPREFETCHWT1 = false;
bool HasRDPID = false;
Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre.. Summary: First, we need to explain the core of the vulnerability. Note that this is a very incomplete description, please see the Project Zero blog post for details: https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html The basis for branch target injection is to direct speculative execution of the processor to some "gadget" of executable code by poisoning the prediction of indirect branches with the address of that gadget. The gadget in turn contains an operation that provides a side channel for reading data. Most commonly, this will look like a load of secret data followed by a branch on the loaded value and then a load of some predictable cache line. The attacker then uses timing of the processors cache to determine which direction the branch took *in the speculative execution*, and in turn what one bit of the loaded value was. Due to the nature of these timing side channels and the branch predictor on Intel processors, this allows an attacker to leak data only accessible to a privileged domain (like the kernel) back into an unprivileged domain. The goal is simple: avoid generating code which contains an indirect branch that could have its prediction poisoned by an attacker. In many cases, the compiler can simply use directed conditional branches and a small search tree. LLVM already has support for lowering switches in this way and the first step of this patch is to disable jump-table lowering of switches and introduce a pass to rewrite explicit indirectbr sequences into a switch over integers. However, there is no fully general alternative to indirect calls. We introduce a new construct we call a "retpoline" to implement indirect calls in a non-speculatable way. It can be thought of loosely as a trampoline for indirect calls which uses the RET instruction on x86. Further, we arrange for a specific call->ret sequence which ensures the processor predicts the return to go to a controlled, known location. The retpoline then "smashes" the return address pushed onto the stack by the call with the desired target of the original indirect call. The result is a predicted return to the next instruction after a call (which can be used to trap speculative execution within an infinite loop) and an actual indirect branch to an arbitrary address. On 64-bit x86 ABIs, this is especially easily done in the compiler by using a guaranteed scratch register to pass the target into this device. For 32-bit ABIs there isn't a guaranteed scratch register and so several different retpoline variants are introduced to use a scratch register if one is available in the calling convention and to otherwise use direct stack push/pop sequences to pass the target address. This "retpoline" mitigation is fully described in the following blog post: https://support.google.com/faqs/answer/7625886 We also support a target feature that disables emission of the retpoline thunk by the compiler to allow for custom thunks if users want them. These are particularly useful in environments like kernels that routinely do hot-patching on boot and want to hot-patch their thunk to different code sequences. They can write this custom thunk and use `-mretpoline-external-thunk` *in addition* to `-mretpoline`. In this case, on x86-64 thu thunk names must be: ``` __llvm_external_retpoline_r11 ``` or on 32-bit: ``` __llvm_external_retpoline_eax __llvm_external_retpoline_ecx __llvm_external_retpoline_edx __llvm_external_retpoline_push ``` And the target of the retpoline is passed in the named register, or in the case of the `push` suffix on the top of the stack via a `pushl` instruction. There is one other important source of indirect branches in x86 ELF binaries: the PLT. These patches also include support for LLD to generate PLT entries that perform a retpoline-style indirection. The only other indirect branches remaining that we are aware of are from precompiled runtimes (such as crt0.o and similar). The ones we have found are not really attackable, and so we have not focused on them here, but eventually these runtimes should also be replicated for retpoline-ed configurations for completeness. For kernels or other freestanding or fully static executables, the compiler switch `-mretpoline` is sufficient to fully mitigate this particular attack. For dynamic executables, you must compile *all* libraries with `-mretpoline` and additionally link the dynamic executable and all shared libraries with LLD and pass `-z retpolineplt` (or use similar functionality from some other linker). We strongly recommend also using `-z now` as non-lazy binding allows the retpoline-mitigated PLT to be substantially smaller. When manually apply similar transformations to `-mretpoline` to the Linux kernel we observed very small performance hits to applications running typical workloads, and relatively minor hits (approximately 2%) even for extremely syscall-heavy applications. This is largely due to the small number of indirect branches that occur in performance sensitive paths of the kernel. When using these patches on statically linked applications, especially C++ applications, you should expect to see a much more dramatic performance hit. For microbenchmarks that are switch, indirect-, or virtual-call heavy we have seen overheads ranging from 10% to 50%. However, real-world workloads exhibit substantially lower performance impact. Notably, techniques such as PGO and ThinLTO dramatically reduce the impact of hot indirect calls (by speculatively promoting them to direct calls) and allow optimized search trees to be used to lower switches. If you need to deploy these techniques in C++ applications, we *strongly* recommend that you ensure all hot call targets are statically linked (avoiding PLT indirection) and use both PGO and ThinLTO. Well tuned servers using all of these techniques saw 5% - 10% overhead from the use of retpoline. We will add detailed documentation covering these components in subsequent patches, but wanted to make the core functionality available as soon as possible. Happy for more code review, but we'd really like to get these patches landed and backported ASAP for obvious reasons. We're planning to backport this to both 6.0 and 5.0 release streams and get a 5.0 release with just this cherry picked ASAP for distros and vendors. This patch is the work of a number of people over the past month: Eric, Reid, Rui, and myself. I'm mailing it out as a single commit due to the time sensitive nature of landing this and the need to backport it. Huge thanks to everyone who helped out here, and everyone at Intel who helped out in discussions about how to craft this. Also, credit goes to Paul Turner (at Google, but not an LLVM contributor) for much of the underlying retpoline design. Reviewers: echristo, rnk, ruiu, craig.topper, DavidKreitzer Subscribers: sanjoy, emaste, mcrosier, mgorny, mehdi_amini, hiraditya, llvm-commits Differential Revision: https://reviews.llvm.org/D41723 llvm-svn: 323155
2018-01-23 06:05:25 +08:00
bool HasRetpolineExternalThunk = false;
bool HasLAHFSAHF = false;
bool HasWBNOINVD = false;
bool HasWAITPKG = false;
bool HasMOVDIRI = false;
bool HasMOVDIR64B = false;
bool HasPTWRITE = false;
bool HasINVPCID = false;
bool HasENQCMD = false;
bool HasSERIALIZE = false;
bool HasTSXLDTRK = false;
protected:
llvm::X86::CPUKind CPU = llvm::X86::CK_None;
enum FPMathKind { FP_Default, FP_SSE, FP_387 } FPMath = FP_Default;
public:
X86TargetInfo(const llvm::Triple &Triple, const TargetOptions &)
: TargetInfo(Triple) {
LongDoubleFormat = &llvm::APFloat::x87DoubleExtended();
AddrSpaceMap = &X86AddrSpaceMap;
}
const char *getLongDoubleMangling() const override {
return LongDoubleFormat == &llvm::APFloat::IEEEquad() ? "g" : "e";
}
unsigned getFloatEvalMethod() const override {
// X87 evaluates with 80 bits "long double" precision.
return SSELevel == NoSSE ? 2 : 0;
}
ArrayRef<const char *> getGCCRegNames() const override;
ArrayRef<TargetInfo::GCCRegAlias> getGCCRegAliases() const override {
return None;
}
ArrayRef<TargetInfo::AddlRegName> getGCCAddlRegNames() const override;
bool isSPRegName(StringRef RegName) const override {
return RegName.equals("esp") || RegName.equals("rsp");
}
bool validateCpuSupports(StringRef Name) const override;
bool validateCpuIs(StringRef Name) const override;
Implement cpu_dispatch/cpu_specific Multiversioning As documented here: https://software.intel.com/en-us/node/682969 and https://software.intel.com/en-us/node/523346. cpu_dispatch multiversioning is an ICC feature that provides for function multiversioning. This feature is implemented with two attributes: First, cpu_specific, which specifies the individual function versions. Second, cpu_dispatch, which specifies the location of the resolver function and the list of resolvable functions. This is valuable since it provides a mechanism where the resolver's TU can be specified in one location, and the individual implementions each in their own translation units. The goal of this patch is to be source-compatible with ICC, so this implementation diverges from the ICC implementation in a few ways: 1- Linux x86/64 only: This implementation uses ifuncs in order to properly dispatch functions. This is is a valuable performance benefit over the ICC implementation. A future patch will be provided to enable this feature on Windows, but it will obviously more closely fit ICC's implementation. 2- CPU Identification functions: ICC uses a set of custom functions to identify the feature list of the host processor. This patch uses the cpu_supports functionality in order to better align with 'target' multiversioning. 1- cpu_dispatch function def/decl: ICC's cpu_dispatch requires that the function marked cpu_dispatch be an empty definition. This patch supports that as well, however declarations are also permitted, since the linker will solve the issue of multiple emissions. Differential Revision: https://reviews.llvm.org/D47474 llvm-svn: 337552
2018-07-20 22:13:28 +08:00
bool validateCPUSpecificCPUDispatch(StringRef Name) const override;
char CPUSpecificManglingCharacter(StringRef Name) const override;
void getCPUSpecificCPUDispatchFeatures(
StringRef Name,
llvm::SmallVectorImpl<StringRef> &Features) const override;
Optional<unsigned> getCPUCacheLineSize() const override;
bool validateAsmConstraint(const char *&Name,
TargetInfo::ConstraintInfo &info) const override;
bool validateGlobalRegisterVariable(StringRef RegName, unsigned RegSize,
bool &HasSizeMismatch) const override {
// esp and ebp are the only 32-bit registers the x86 backend can currently
// handle.
if (RegName.equals("esp") || RegName.equals("ebp")) {
// Check that the register size is 32-bit.
HasSizeMismatch = RegSize != 32;
return true;
}
return false;
}
bool validateOutputSize(const llvm::StringMap<bool> &FeatureMap,
StringRef Constraint, unsigned Size) const override;
bool validateInputSize(const llvm::StringMap<bool> &FeatureMap,
StringRef Constraint, unsigned Size) const override;
virtual bool
checkCFProtectionReturnSupported(DiagnosticsEngine &Diags) const override {
return true;
};
virtual bool
checkCFProtectionBranchSupported(DiagnosticsEngine &Diags) const override {
return true;
};
virtual bool validateOperandSize(const llvm::StringMap<bool> &FeatureMap,
StringRef Constraint, unsigned Size) const;
std::string convertConstraint(const char *&Constraint) const override;
const char *getClobbers() const override {
return "~{dirflag},~{fpsr},~{flags}";
}
StringRef getConstraintRegister(StringRef Constraint,
StringRef Expression) const override {
StringRef::iterator I, E;
for (I = Constraint.begin(), E = Constraint.end(); I != E; ++I) {
if (isalpha(*I) || *I == '@')
break;
}
if (I == E)
return "";
switch (*I) {
// For the register constraints, return the matching register name
case 'a':
return "ax";
case 'b':
return "bx";
case 'c':
return "cx";
case 'd':
return "dx";
case 'S':
return "si";
case 'D':
return "di";
// In case the constraint is 'r' we need to return Expression
case 'r':
return Expression;
// Double letters Y<x> constraints
case 'Y':
if ((++I != E) && ((*I == '0') || (*I == 'z')))
return "xmm0";
break;
default:
break;
}
return "";
}
bool useFP16ConversionIntrinsics() const override {
return false;
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override;
static void setSSELevel(llvm::StringMap<bool> &Features, X86SSEEnum Level,
bool Enabled);
static void setMMXLevel(llvm::StringMap<bool> &Features, MMX3DNowEnum Level,
bool Enabled);
static void setXOPLevel(llvm::StringMap<bool> &Features, XOPEnum Level,
bool Enabled);
void setFeatureEnabled(llvm::StringMap<bool> &Features, StringRef Name,
bool Enabled) const override {
setFeatureEnabledImpl(Features, Name, Enabled);
}
// This exists purely to cut down on the number of virtual calls in
// initFeatureMap which calls this repeatedly.
static void setFeatureEnabledImpl(llvm::StringMap<bool> &Features,
StringRef Name, bool Enabled);
bool
initFeatureMap(llvm::StringMap<bool> &Features, DiagnosticsEngine &Diags,
StringRef CPU,
const std::vector<std::string> &FeaturesVec) const override;
bool isValidFeatureName(StringRef Name) const override;
bool hasFeature(StringRef Feature) const override;
bool handleTargetFeatures(std::vector<std::string> &Features,
DiagnosticsEngine &Diags) override;
StringRef getABI() const override {
if (getTriple().getArch() == llvm::Triple::x86_64 && SSELevel >= AVX512F)
return "avx512";
if (getTriple().getArch() == llvm::Triple::x86_64 && SSELevel >= AVX)
return "avx";
if (getTriple().getArch() == llvm::Triple::x86 &&
MMX3DNowLevel == NoMMX3DNow)
return "no-mmx";
return "";
}
bool isValidCPUName(StringRef Name) const override {
bool Only64Bit = getTriple().getArch() != llvm::Triple::x86;
return llvm::X86::parseArchX86(Name, Only64Bit) != llvm::X86::CK_None;
}
void fillValidCPUList(SmallVectorImpl<StringRef> &Values) const override;
bool setCPU(const std::string &Name) override {
bool Only64Bit = getTriple().getArch() != llvm::Triple::x86;
CPU = llvm::X86::parseArchX86(Name, Only64Bit);
return CPU != llvm::X86::CK_None;
}
unsigned multiVersionSortPriority(StringRef Name) const override;
bool setFPMath(StringRef Name) override;
CallingConvCheckResult checkCallingConvention(CallingConv CC) const override {
// Most of the non-ARM calling conventions are i386 conventions.
switch (CC) {
case CC_X86ThisCall:
case CC_X86FastCall:
case CC_X86StdCall:
case CC_X86VectorCall:
case CC_X86RegCall:
case CC_C:
case CC_PreserveMost:
case CC_Swift:
case CC_X86Pascal:
case CC_IntelOclBicc:
case CC_OpenCLKernel:
return CCCR_OK;
default:
return CCCR_Warning;
}
}
CallingConv getDefaultCallingConv() const override {
return CC_C;
}
bool hasSjLjLowering() const override { return true; }
void setSupportedOpenCLOpts() override {
getSupportedOpenCLOpts().supportAll();
}
uint64_t getPointerWidthV(unsigned AddrSpace) const override {
if (AddrSpace == ptr32_sptr || AddrSpace == ptr32_uptr)
return 32;
if (AddrSpace == ptr64)
return 64;
return PointerWidth;
}
uint64_t getPointerAlignV(unsigned AddrSpace) const override {
return getPointerWidthV(AddrSpace);
}
};
// X86-32 generic target
class LLVM_LIBRARY_VISIBILITY X86_32TargetInfo : public X86TargetInfo {
public:
X86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86TargetInfo(Triple, Opts) {
DoubleAlign = LongLongAlign = 32;
LongDoubleWidth = 96;
LongDoubleAlign = 32;
SuitableAlign = 128;
resetDataLayout("e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-f64:32:64-"
"f80:32-n8:16:32-S128");
SizeType = UnsignedInt;
PtrDiffType = SignedInt;
IntPtrType = SignedInt;
RegParmMax = 3;
// Use fpret for all types.
RealTypeUsesObjCFPRet =
((1 << TargetInfo::Float) | (1 << TargetInfo::Double) |
(1 << TargetInfo::LongDouble));
// x86-32 has atomics up to 8 bytes
MaxAtomicPromoteWidth = 64;
MaxAtomicInlineWidth = 32;
}
BuiltinVaListKind getBuiltinVaListKind() const override {
return TargetInfo::CharPtrBuiltinVaList;
}
int getEHDataRegisterNumber(unsigned RegNo) const override {
if (RegNo == 0)
return 0;
if (RegNo == 1)
return 2;
return -1;
}
bool validateOperandSize(const llvm::StringMap<bool> &FeatureMap,
StringRef Constraint, unsigned Size) const override {
switch (Constraint[0]) {
default:
break;
case 'R':
case 'q':
case 'Q':
case 'a':
case 'b':
case 'c':
case 'd':
case 'S':
case 'D':
return Size <= 32;
case 'A':
return Size <= 64;
}
return X86TargetInfo::validateOperandSize(FeatureMap, Constraint, Size);
}
void setMaxAtomicWidth() override {
if (hasFeature("cx8"))
MaxAtomicInlineWidth = 64;
}
ArrayRef<Builtin::Info> getTargetBuiltins() const override;
bool hasExtIntType() const override { return true; }
};
class LLVM_LIBRARY_VISIBILITY NetBSDI386TargetInfo
: public NetBSDTargetInfo<X86_32TargetInfo> {
public:
NetBSDI386TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: NetBSDTargetInfo<X86_32TargetInfo>(Triple, Opts) {}
unsigned getFloatEvalMethod() const override {
unsigned Major, Minor, Micro;
getTriple().getOSVersion(Major, Minor, Micro);
// New NetBSD uses the default rounding mode.
if (Major >= 7 || (Major == 6 && Minor == 99 && Micro >= 26) || Major == 0)
return X86_32TargetInfo::getFloatEvalMethod();
// NetBSD before 6.99.26 defaults to "double" rounding.
return 1;
}
};
class LLVM_LIBRARY_VISIBILITY OpenBSDI386TargetInfo
: public OpenBSDTargetInfo<X86_32TargetInfo> {
public:
OpenBSDI386TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: OpenBSDTargetInfo<X86_32TargetInfo>(Triple, Opts) {
SizeType = UnsignedLong;
IntPtrType = SignedLong;
PtrDiffType = SignedLong;
}
};
class LLVM_LIBRARY_VISIBILITY DarwinI386TargetInfo
: public DarwinTargetInfo<X86_32TargetInfo> {
public:
DarwinI386TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: DarwinTargetInfo<X86_32TargetInfo>(Triple, Opts) {
LongDoubleWidth = 128;
LongDoubleAlign = 128;
SuitableAlign = 128;
MaxVectorAlign = 256;
// The watchOS simulator uses the builtin bool type for Objective-C.
llvm::Triple T = llvm::Triple(Triple);
if (T.isWatchOS())
UseSignedCharForObjCBool = false;
SizeType = UnsignedLong;
IntPtrType = SignedLong;
resetDataLayout("e-m:o-p:32:32-p270:32:32-p271:32:32-p272:64:64-f64:32:64-"
"f80:128-n8:16:32-S128");
HasAlignMac68kSupport = true;
}
bool handleTargetFeatures(std::vector<std::string> &Features,
DiagnosticsEngine &Diags) override {
if (!DarwinTargetInfo<X86_32TargetInfo>::handleTargetFeatures(Features,
Diags))
return false;
// We now know the features we have: we can decide how to align vectors.
MaxVectorAlign =
hasFeature("avx512f") ? 512 : hasFeature("avx") ? 256 : 128;
return true;
}
};
// x86-32 Windows target
class LLVM_LIBRARY_VISIBILITY WindowsX86_32TargetInfo
: public WindowsTargetInfo<X86_32TargetInfo> {
public:
WindowsX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: WindowsTargetInfo<X86_32TargetInfo>(Triple, Opts) {
DoubleAlign = LongLongAlign = 64;
bool IsWinCOFF =
getTriple().isOSWindows() && getTriple().isOSBinFormatCOFF();
resetDataLayout(IsWinCOFF ? "e-m:x-p:32:32-p270:32:32-p271:32:32-p272:64:"
"64-i64:64-f80:32-n8:16:32-a:0:32-S32"
: "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:"
"64-i64:64-f80:32-n8:16:32-a:0:32-S32");
}
};
// x86-32 Windows Visual Studio target
class LLVM_LIBRARY_VISIBILITY MicrosoftX86_32TargetInfo
: public WindowsX86_32TargetInfo {
public:
MicrosoftX86_32TargetInfo(const llvm::Triple &Triple,
const TargetOptions &Opts)
: WindowsX86_32TargetInfo(Triple, Opts) {
LongDoubleWidth = LongDoubleAlign = 64;
LongDoubleFormat = &llvm::APFloat::IEEEdouble();
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
WindowsX86_32TargetInfo::getTargetDefines(Opts, Builder);
// The value of the following reflects processor type.
// 300=386, 400=486, 500=Pentium, 600=Blend (default)
// We lost the original triple, so we use the default.
Builder.defineMacro("_M_IX86", "600");
}
};
// x86-32 MinGW target
class LLVM_LIBRARY_VISIBILITY MinGWX86_32TargetInfo
: public WindowsX86_32TargetInfo {
public:
MinGWX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: WindowsX86_32TargetInfo(Triple, Opts) {
HasFloat128 = true;
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
WindowsX86_32TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("_X86_");
}
};
// x86-32 Cygwin target
class LLVM_LIBRARY_VISIBILITY CygwinX86_32TargetInfo : public X86_32TargetInfo {
public:
CygwinX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86_32TargetInfo(Triple, Opts) {
this->WCharType = TargetInfo::UnsignedShort;
DoubleAlign = LongLongAlign = 64;
resetDataLayout("e-m:x-p:32:32-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:"
"32-n8:16:32-a:0:32-S32");
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
X86_32TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("_X86_");
Builder.defineMacro("__CYGWIN__");
Builder.defineMacro("__CYGWIN32__");
addCygMingDefines(Opts, Builder);
DefineStd(Builder, "unix", Opts);
if (Opts.CPlusPlus)
Builder.defineMacro("_GNU_SOURCE");
}
};
// x86-32 Haiku target
class LLVM_LIBRARY_VISIBILITY HaikuX86_32TargetInfo
: public HaikuTargetInfo<X86_32TargetInfo> {
public:
HaikuX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: HaikuTargetInfo<X86_32TargetInfo>(Triple, Opts) {}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
HaikuTargetInfo<X86_32TargetInfo>::getTargetDefines(Opts, Builder);
Builder.defineMacro("__INTEL__");
}
};
// X86-32 MCU target
class LLVM_LIBRARY_VISIBILITY MCUX86_32TargetInfo : public X86_32TargetInfo {
public:
MCUX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86_32TargetInfo(Triple, Opts) {
LongDoubleWidth = 64;
LongDoubleFormat = &llvm::APFloat::IEEEdouble();
resetDataLayout("e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i64:32-f64:"
"32-f128:32-n8:16:32-a:0:32-S32");
WIntType = UnsignedInt;
}
CallingConvCheckResult checkCallingConvention(CallingConv CC) const override {
// On MCU we support only C calling convention.
return CC == CC_C ? CCCR_OK : CCCR_Warning;
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
X86_32TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("__iamcu");
Builder.defineMacro("__iamcu__");
}
bool allowsLargerPreferedTypeAlignment() const override { return false; }
};
// x86-32 RTEMS target
class LLVM_LIBRARY_VISIBILITY RTEMSX86_32TargetInfo : public X86_32TargetInfo {
public:
RTEMSX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86_32TargetInfo(Triple, Opts) {
SizeType = UnsignedLong;
IntPtrType = SignedLong;
PtrDiffType = SignedLong;
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
X86_32TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("__INTEL__");
Builder.defineMacro("__rtems__");
}
};
// x86-64 generic target
class LLVM_LIBRARY_VISIBILITY X86_64TargetInfo : public X86TargetInfo {
public:
X86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86TargetInfo(Triple, Opts) {
const bool IsX32 = getTriple().getEnvironment() == llvm::Triple::GNUX32;
bool IsWinCOFF =
getTriple().isOSWindows() && getTriple().isOSBinFormatCOFF();
LongWidth = LongAlign = PointerWidth = PointerAlign = IsX32 ? 32 : 64;
LongDoubleWidth = 128;
LongDoubleAlign = 128;
LargeArrayMinWidth = 128;
LargeArrayAlign = 128;
SuitableAlign = 128;
SizeType = IsX32 ? UnsignedInt : UnsignedLong;
PtrDiffType = IsX32 ? SignedInt : SignedLong;
IntPtrType = IsX32 ? SignedInt : SignedLong;
IntMaxType = IsX32 ? SignedLongLong : SignedLong;
Int64Type = IsX32 ? SignedLongLong : SignedLong;
RegParmMax = 6;
// Pointers are 32-bit in x32.
resetDataLayout(IsX32 ? "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-"
"i64:64-f80:128-n8:16:32:64-S128"
: IsWinCOFF ? "e-m:w-p270:32:32-p271:32:32-p272:64:"
"64-i64:64-f80:128-n8:16:32:64-S128"
: "e-m:e-p270:32:32-p271:32:32-p272:64:"
"64-i64:64-f80:128-n8:16:32:64-S128");
// Use fpret only for long double.
RealTypeUsesObjCFPRet = (1 << TargetInfo::LongDouble);
// Use fp2ret for _Complex long double.
ComplexLongDoubleUsesFP2Ret = true;
// Make __builtin_ms_va_list available.
HasBuiltinMSVaList = true;
// x86-64 has atomics up to 16 bytes.
MaxAtomicPromoteWidth = 128;
MaxAtomicInlineWidth = 64;
}
BuiltinVaListKind getBuiltinVaListKind() const override {
return TargetInfo::X86_64ABIBuiltinVaList;
}
int getEHDataRegisterNumber(unsigned RegNo) const override {
if (RegNo == 0)
return 0;
if (RegNo == 1)
return 1;
return -1;
}
CallingConvCheckResult checkCallingConvention(CallingConv CC) const override {
switch (CC) {
case CC_C:
case CC_Swift:
case CC_X86VectorCall:
case CC_IntelOclBicc:
case CC_Win64:
case CC_PreserveMost:
case CC_PreserveAll:
case CC_X86RegCall:
case CC_OpenCLKernel:
return CCCR_OK;
default:
return CCCR_Warning;
}
}
CallingConv getDefaultCallingConv() const override {
return CC_C;
}
// for x32 we need it here explicitly
bool hasInt128Type() const override { return true; }
unsigned getUnwindWordWidth() const override { return 64; }
unsigned getRegisterWidth() const override { return 64; }
bool validateGlobalRegisterVariable(StringRef RegName, unsigned RegSize,
bool &HasSizeMismatch) const override {
// rsp and rbp are the only 64-bit registers the x86 backend can currently
// handle.
if (RegName.equals("rsp") || RegName.equals("rbp")) {
// Check that the register size is 64-bit.
HasSizeMismatch = RegSize != 64;
return true;
}
// Check if the register is a 32-bit register the backend can handle.
return X86TargetInfo::validateGlobalRegisterVariable(RegName, RegSize,
HasSizeMismatch);
}
void setMaxAtomicWidth() override {
if (hasFeature("cx16"))
MaxAtomicInlineWidth = 128;
}
ArrayRef<Builtin::Info> getTargetBuiltins() const override;
bool hasExtIntType() const override { return true; }
};
// x86-64 Windows target
class LLVM_LIBRARY_VISIBILITY WindowsX86_64TargetInfo
: public WindowsTargetInfo<X86_64TargetInfo> {
public:
WindowsX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: WindowsTargetInfo<X86_64TargetInfo>(Triple, Opts) {
LongWidth = LongAlign = 32;
DoubleAlign = LongLongAlign = 64;
IntMaxType = SignedLongLong;
Int64Type = SignedLongLong;
SizeType = UnsignedLongLong;
PtrDiffType = SignedLongLong;
IntPtrType = SignedLongLong;
}
BuiltinVaListKind getBuiltinVaListKind() const override {
return TargetInfo::CharPtrBuiltinVaList;
}
CallingConvCheckResult checkCallingConvention(CallingConv CC) const override {
switch (CC) {
case CC_X86StdCall:
case CC_X86ThisCall:
case CC_X86FastCall:
return CCCR_Ignore;
case CC_C:
case CC_X86VectorCall:
case CC_IntelOclBicc:
case CC_PreserveMost:
case CC_PreserveAll:
case CC_X86_64SysV:
case CC_Swift:
case CC_X86RegCall:
case CC_OpenCLKernel:
return CCCR_OK;
default:
return CCCR_Warning;
}
}
};
// x86-64 Windows Visual Studio target
class LLVM_LIBRARY_VISIBILITY MicrosoftX86_64TargetInfo
: public WindowsX86_64TargetInfo {
public:
MicrosoftX86_64TargetInfo(const llvm::Triple &Triple,
const TargetOptions &Opts)
: WindowsX86_64TargetInfo(Triple, Opts) {
LongDoubleWidth = LongDoubleAlign = 64;
LongDoubleFormat = &llvm::APFloat::IEEEdouble();
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
WindowsX86_64TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("_M_X64", "100");
Builder.defineMacro("_M_AMD64", "100");
}
TargetInfo::CallingConvKind
getCallingConvKind(bool ClangABICompat4) const override {
return CCK_MicrosoftWin64;
}
};
// x86-64 MinGW target
class LLVM_LIBRARY_VISIBILITY MinGWX86_64TargetInfo
: public WindowsX86_64TargetInfo {
public:
MinGWX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: WindowsX86_64TargetInfo(Triple, Opts) {
// Mingw64 rounds long double size and alignment up to 16 bytes, but sticks
// with x86 FP ops. Weird.
LongDoubleWidth = LongDoubleAlign = 128;
LongDoubleFormat = &llvm::APFloat::x87DoubleExtended();
HasFloat128 = true;
}
};
// x86-64 Cygwin target
class LLVM_LIBRARY_VISIBILITY CygwinX86_64TargetInfo : public X86_64TargetInfo {
public:
CygwinX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: X86_64TargetInfo(Triple, Opts) {
this->WCharType = TargetInfo::UnsignedShort;
TLSSupported = false;
}
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override {
X86_64TargetInfo::getTargetDefines(Opts, Builder);
Builder.defineMacro("__x86_64__");
Builder.defineMacro("__CYGWIN__");
Builder.defineMacro("__CYGWIN64__");
addCygMingDefines(Opts, Builder);
DefineStd(Builder, "unix", Opts);
if (Opts.CPlusPlus)
Builder.defineMacro("_GNU_SOURCE");
}
};
class LLVM_LIBRARY_VISIBILITY DarwinX86_64TargetInfo
: public DarwinTargetInfo<X86_64TargetInfo> {
public:
DarwinX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: DarwinTargetInfo<X86_64TargetInfo>(Triple, Opts) {
Int64Type = SignedLongLong;
// The 64-bit iOS simulator uses the builtin bool type for Objective-C.
llvm::Triple T = llvm::Triple(Triple);
if (T.isiOS())
UseSignedCharForObjCBool = false;
resetDataLayout("e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:"
"16:32:64-S128");
}
bool handleTargetFeatures(std::vector<std::string> &Features,
DiagnosticsEngine &Diags) override {
if (!DarwinTargetInfo<X86_64TargetInfo>::handleTargetFeatures(Features,
Diags))
return false;
// We now know the features we have: we can decide how to align vectors.
MaxVectorAlign =
hasFeature("avx512f") ? 512 : hasFeature("avx") ? 256 : 128;
return true;
}
};
class LLVM_LIBRARY_VISIBILITY OpenBSDX86_64TargetInfo
: public OpenBSDTargetInfo<X86_64TargetInfo> {
public:
OpenBSDX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: OpenBSDTargetInfo<X86_64TargetInfo>(Triple, Opts) {
IntMaxType = SignedLongLong;
Int64Type = SignedLongLong;
}
};
// x86_32 Android target
class LLVM_LIBRARY_VISIBILITY AndroidX86_32TargetInfo
: public LinuxTargetInfo<X86_32TargetInfo> {
public:
AndroidX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: LinuxTargetInfo<X86_32TargetInfo>(Triple, Opts) {
SuitableAlign = 32;
LongDoubleWidth = 64;
LongDoubleFormat = &llvm::APFloat::IEEEdouble();
}
};
// x86_64 Android target
class LLVM_LIBRARY_VISIBILITY AndroidX86_64TargetInfo
: public LinuxTargetInfo<X86_64TargetInfo> {
public:
AndroidX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: LinuxTargetInfo<X86_64TargetInfo>(Triple, Opts) {
LongDoubleFormat = &llvm::APFloat::IEEEquad();
}
};
} // namespace targets
} // namespace clang
#endif // LLVM_CLANG_LIB_BASIC_TARGETS_X86_H