Driver: hoist the `wchar_t` handling to the driver

Move the logic for determining the `wchar_t` type information into the
driver.  Rather than passing the single bit of information of
`-fshort-wchar` indicate to the frontend the desired type of `wchar_t`
through a new `-cc1` option of `-fwchar-type` and indicate the
signedness through `-f{,no-}signed-wchar`.  This replicates the current
logic which was spread throughout Basic into the
`RenderCharacterOptions`.

Most of the changes to the tests are to ensure that the frontend uses
the correct type.  Add a new test set under `test/Driver/wchar_t.c` to
ensure that we calculate the proper types for the various cases.

llvm-svn: 315126

9 files changed, 71 insertions, 52 deletions

diff --git a/clang/lib/Basic/TargetInfo.cpp b/clang/lib/Basic/TargetInfo.cpp
index de26a67eac3..9b736d113d6 100644
--- a/clang/lib/Basic/TargetInfo.cpp
+++ b/clang/lib/Basic/TargetInfo.cpp
@@ -19,6 +19,7 @@
 #include "llvm/ADT/APFloat.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/TargetParser.h"
 #include <cstdlib>
 using namespace clang;
 
@@ -290,8 +291,15 @@ bool TargetInfo::isTypeSigned(IntType T) {
 void TargetInfo::adjust(LangOptions &Opts) {
   if (Opts.NoBitFieldTypeAlign)
     UseBitFieldTypeAlignment = false;
-  if (Opts.ShortWChar)
-    WCharType = UnsignedShort;
+
+  switch (Opts.WCharSize) {
+  default: llvm_unreachable("invalid wchar_t width");
+  case 0: break;
+  case 1: WCharType = Opts.WCharIsSigned ? SignedChar : UnsignedChar; break;
+  case 2: WCharType = Opts.WCharIsSigned ? SignedShort : UnsignedShort; break;
+  case 4: WCharType = Opts.WCharIsSigned ? SignedInt : UnsignedInt; break;
+  }
+
   if (Opts.AlignDouble) {
     DoubleAlign = LongLongAlign = 64;
     LongDoubleAlign = 64;
diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
index 2a85c89cbb3..e915d362b90 100644
--- a/clang/lib/Basic/Targets/AArch64.cpp
+++ b/clang/lib/Basic/Targets/AArch64.cpp
@@ -15,6 +15,7 @@
 #include "clang/Basic/TargetBuiltins.h"
 #include "clang/Basic/TargetInfo.h"
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/StringExtras.h"
 
 using namespace clang;
 using namespace clang::targets;
@@ -34,18 +35,19 @@ AArch64TargetInfo::AArch64TargetInfo(const llvm::Triple &Triple,
     : TargetInfo(Triple), ABI("aapcs") {
   if (getTriple().getOS() == llvm::Triple::NetBSD ||
       getTriple().getOS() == llvm::Triple::OpenBSD) {
-    WCharType = SignedInt;
-
     // NetBSD apparently prefers consistency across ARM targets to
     // consistency across 64-bit targets.
     Int64Type = SignedLongLong;
     IntMaxType = SignedLongLong;
   } else {
-    WCharType = UnsignedInt;
+    if (!getTriple().isOSDarwin())
+      WCharType = UnsignedInt;
+
     Int64Type = SignedLong;
     IntMaxType = SignedLong;
   }
 
+
   LongWidth = LongAlign = PointerWidth = PointerAlign = 64;
   MaxVectorAlign = 128;
   MaxAtomicInlineWidth = 128;
@@ -154,7 +156,8 @@ void AArch64TargetInfo::getTargetDefines(const LangOptions &Opts,
   if (Opts.UnsafeFPMath)
     Builder.defineMacro("__ARM_FP_FAST", "1");
 
-  Builder.defineMacro("__ARM_SIZEOF_WCHAR_T", Opts.ShortWChar ? "2" : "4");
+  Builder.defineMacro("__ARM_SIZEOF_WCHAR_T",
+                      llvm::utostr(Opts.WCharSize ? Opts.WCharSize : 4));
 
   Builder.defineMacro("__ARM_SIZEOF_MINIMAL_ENUM", Opts.ShortEnums ? "1" : "4");
 
@@ -420,7 +423,6 @@ WindowsARM64TargetInfo::WindowsARM64TargetInfo(const llvm::Triple &Triple,
 
   // This is an LLP64 platform.
   // int:4, long:4, long long:8, long double:8.
-  WCharType = UnsignedShort;
   IntWidth = IntAlign = 32;
   LongWidth = LongAlign = 32;
   DoubleAlign = LongLongAlign = 64;
@@ -502,7 +504,6 @@ DarwinAArch64TargetInfo::DarwinAArch64TargetInfo(const llvm::Triple &Triple,
                                                  const TargetOptions &Opts)
     : DarwinTargetInfo<AArch64leTargetInfo>(Triple, Opts) {
   Int64Type = SignedLongLong;
-  WCharType = SignedInt;
   UseSignedCharForObjCBool = false;
 
   LongDoubleWidth = LongDoubleAlign = SuitableAlign = 64;
diff --git a/clang/lib/Basic/Targets/ARM.cpp b/clang/lib/Basic/Targets/ARM.cpp
index b3e8007bcb1..92685fcd21c 100644
--- a/clang/lib/Basic/Targets/ARM.cpp
+++ b/clang/lib/Basic/Targets/ARM.cpp
@@ -36,20 +36,10 @@ void ARMTargetInfo::setABIAAPCS() {
   else
     SizeType = UnsignedInt;
 
-  switch (T.getOS()) {
-  case llvm::Triple::NetBSD:
-  case llvm::Triple::OpenBSD:
-    WCharType = SignedInt;
-    break;
-  case llvm::Triple::Win32:
-    WCharType = UnsignedShort;
-    break;
-  case llvm::Triple::Linux:
-  default:
-    // AAPCS 7.1.1, ARM-Linux ABI 2.4: type of wchar_t is unsigned int.
+  bool IsNetBSD = T.getOS() == llvm::Triple::NetBSD;
+  bool IsOpenBSD = T.getOS() == llvm::Triple::OpenBSD;
+  if (!T.isOSWindows() && !IsNetBSD && !IsOpenBSD)
     WCharType = UnsignedInt;
-    break;
-  }
 
   UseBitFieldTypeAlignment = true;
 
@@ -99,7 +89,6 @@ void ARMTargetInfo::setABIAPCS(bool IsAAPCS16) {
   else
     SizeType = UnsignedLong;
 
-  // Revert to using SignedInt on apcs-gnu to comply with existing behaviour.
   WCharType = SignedInt;
 
   // Do not respect the alignment of bit-field types when laying out
@@ -689,7 +678,8 @@ void ARMTargetInfo::getTargetDefines(const LangOptions &Opts,
                         "0x" + llvm::utohexstr(HW_FP & ~HW_FP_DP));
   }
 
-  Builder.defineMacro("__ARM_SIZEOF_WCHAR_T", Opts.ShortWChar ? "2" : "4");
+  Builder.defineMacro("__ARM_SIZEOF_WCHAR_T",
+                      llvm::utostr(Opts.WCharSize ? Opts.WCharSize : 4));
 
   Builder.defineMacro("__ARM_SIZEOF_MINIMAL_ENUM", Opts.ShortEnums ? "1" : "4");
 
@@ -932,7 +922,6 @@ void ARMbeTargetInfo::getTargetDefines(const LangOptions &Opts,
 WindowsARMTargetInfo::WindowsARMTargetInfo(const llvm::Triple &Triple,
                                            const TargetOptions &Opts)
     : WindowsTargetInfo<ARMleTargetInfo>(Triple, Opts), Triple(Triple) {
-  WCharType = UnsignedShort;
   SizeType = UnsignedInt;
 }
 
@@ -1023,8 +1012,8 @@ void MinGWARMTargetInfo::getTargetDefines(const LangOptions &Opts,
 CygwinARMTargetInfo::CygwinARMTargetInfo(const llvm::Triple &Triple,
                                          const TargetOptions &Opts)
     : ARMleTargetInfo(Triple, Opts) {
+  this->WCharType = TargetInfo::UnsignedShort;
   TLSSupported = false;
-  WCharType = UnsignedShort;
   DoubleAlign = LongLongAlign = 64;
   resetDataLayout("e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64");
 }
diff --git a/clang/lib/Basic/Targets/AVR.h b/clang/lib/Basic/Targets/AVR.h
index 679e639e745..3dfb84f7566 100644
--- a/clang/lib/Basic/Targets/AVR.h
+++ b/clang/lib/Basic/Targets/AVR.h
@@ -52,7 +52,6 @@ public:
     PtrDiffType = SignedInt;
     IntPtrType = SignedInt;
     Char16Type = UnsignedInt;
-    WCharType = SignedInt;
     WIntType = SignedInt;
     Char32Type = UnsignedLong;
     SigAtomicType = SignedChar;
diff --git a/clang/lib/Basic/Targets/OSTargets.h b/clang/lib/Basic/Targets/OSTargets.h
index ca84a875de1..c775fe32ee5 100644
--- a/clang/lib/Basic/Targets/OSTargets.h
+++ b/clang/lib/Basic/Targets/OSTargets.h
@@ -477,7 +477,7 @@ protected:
 public:
   PS4OSTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
       : OSTargetInfo<Target>(Triple, Opts) {
-    this->WCharType = this->UnsignedShort;
+    this->WCharType = TargetInfo::UnsignedShort;
 
     // On PS4, TLS variable cannot be aligned to more than 32 bytes (256 bits).
     this->MaxTLSAlign = 256;
@@ -561,7 +561,6 @@ protected:
 public:
   SolarisTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
       : OSTargetInfo<Target>(Triple, Opts) {
-    this->WCharType = this->SignedInt;
     // FIXME: WIntType should be SignedLong
   }
 };
@@ -628,7 +627,9 @@ protected:
 
 public:
   WindowsTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
-      : OSTargetInfo<Target>(Triple, Opts) {}
+      : OSTargetInfo<Target>(Triple, Opts) {
+    this->WCharType = TargetInfo::UnsignedShort;
+  }
 };
 
 template <typename Target>
diff --git a/clang/lib/Basic/Targets/X86.h b/clang/lib/Basic/Targets/X86.h
index 24d535a7333..38fb0c66f65 100644
--- a/clang/lib/Basic/Targets/X86.h
+++ b/clang/lib/Basic/Targets/X86.h
@@ -639,7 +639,6 @@ class LLVM_LIBRARY_VISIBILITY WindowsX86_32TargetInfo
 public:
   WindowsX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
       : WindowsTargetInfo<X86_32TargetInfo>(Triple, Opts) {
-    WCharType = UnsignedShort;
     DoubleAlign = LongLongAlign = 64;
     bool IsWinCOFF =
         getTriple().isOSWindows() && getTriple().isOSBinFormatCOFF();
@@ -700,7 +699,7 @@ class LLVM_LIBRARY_VISIBILITY CygwinX86_32TargetInfo : public X86_32TargetInfo {
 public:
   CygwinX86_32TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
       : X86_32TargetInfo(Triple, Opts) {
-    WCharType = UnsignedShort;
+    this->WCharType = TargetInfo::UnsignedShort;
     DoubleAlign = LongLongAlign = 64;
     resetDataLayout("e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32");
   }
@@ -886,7 +885,6 @@ class LLVM_LIBRARY_VISIBILITY WindowsX86_64TargetInfo
 public:
   WindowsX86_64TargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
       : WindowsTargetInfo<X86_64TargetInfo>(Triple, Opts) {
-    WCharType = UnsignedShort;
     LongWidth = LongAlign = 32;
     DoubleAlign = LongLongAlign = 64;
     IntMaxType = SignedLongLong;
@@ -979,8 +977,8 @@ 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;
-    WCharType = UnsignedShort;
   }
 
   void getTargetDefines(const LangOptions &Opts,
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 21937ef143d..6c285dec653 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -2601,6 +2601,33 @@ static void RenderModulesOptions(Compilation &C, const Driver &D,
   Args.AddLastArg(CmdArgs, options::OPT_fmodules_disable_diagnostic_validation);
 }
 
+static void RenderCharacterOptions(const ArgList &Args, const llvm::Triple &T,
+                                   ArgStringList &CmdArgs) {
+  // -fsigned-char is default.
+  if (const Arg *A = Args.getLastArg(options::OPT_fsigned_char,
+                                     options::OPT_fno_signed_char,
+                                     options::OPT_funsigned_char,
+                                     options::OPT_fno_unsigned_char)) {
+    if (A->getOption().matches(options::OPT_funsigned_char) ||
+        A->getOption().matches(options::OPT_fno_signed_char)) {
+      CmdArgs.push_back("-fno-signed-char");
+    }
+  } else if (!isSignedCharDefault(T)) {
+    CmdArgs.push_back("-fno-signed-char");
+  }
+
+  if (const Arg *A = Args.getLastArg(options::OPT_fshort_wchar,
+                                     options::OPT_fno_short_wchar)) {
+    if (A->getOption().matches(options::OPT_fshort_wchar)) {
+      CmdArgs.push_back("-fwchar-type=short");
+      CmdArgs.push_back("-fno-signed-wchar");
+    } else {
+      CmdArgs.push_back("-fwchar-type=int");
+      CmdArgs.push_back("-fsigned-wchar");
+    }
+  }
+}
+
 static void RenderObjCOptions(const ToolChain &TC, const Driver &D,
                               const llvm::Triple &T, const ArgList &Args,
                               ObjCRuntime &Runtime, bool InferCovariantReturns,
@@ -2991,6 +3018,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
           Inputs.size() == 1) &&
          "Unable to handle multiple inputs.");
 
+  const llvm::Triple *AuxTriple =
+      IsCuda ? getToolChain().getAuxTriple() : nullptr;
+
   bool IsWindowsGNU = RawTriple.isWindowsGNUEnvironment();
   bool IsWindowsCygnus = RawTriple.isWindowsCygwinEnvironment();
   bool IsWindowsMSVC = RawTriple.isWindowsMSVCEnvironment();
@@ -3000,7 +3030,6 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   // mode (i.e., getToolchain().getTriple() is NVPTX, not Windows), we need to
   // pass Windows-specific flags to cc1.
   if (IsCuda) {
-    const llvm::Triple *AuxTriple = getToolChain().getAuxTriple();
     IsWindowsMSVC |= AuxTriple && AuxTriple->isWindowsMSVCEnvironment();
     IsWindowsGNU |= AuxTriple && AuxTriple->isWindowsGNUEnvironment();
     IsWindowsCygnus |= AuxTriple && AuxTriple->isWindowsCygwinEnvironment();
@@ -4003,17 +4032,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                    getToolChain().getArch() == llvm::Triple::hexagon))
     CmdArgs.push_back("-fshort-enums");
 
-  // -fsigned-char is default.
-  if (Arg *A = Args.getLastArg(
-          options::OPT_fsigned_char, options::OPT_fno_signed_char,
-          options::OPT_funsigned_char, options::OPT_fno_unsigned_char)) {
-    if (A->getOption().matches(options::OPT_funsigned_char) ||
-        A->getOption().matches(options::OPT_fno_signed_char)) {
-      CmdArgs.push_back("-fno-signed-char");
-    }
-  } else if (!isSignedCharDefault(RawTriple)) {
-    CmdArgs.push_back("-fno-signed-char");
-  }
+  RenderCharacterOptions(Args, AuxTriple ? *AuxTriple : RawTriple, CmdArgs);
 
   // -fuse-cxa-atexit is default.
   if (!Args.hasFlag(
@@ -4182,12 +4201,6 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                     options::OPT_mno_constant_cfstrings))
     CmdArgs.push_back("-fno-constant-cfstrings");
 
-  // -fshort-wchar default varies depending on platform; only
-  // pass if specified.
-  if (Arg *A = Args.getLastArg(options::OPT_fshort_wchar,
-                               options::OPT_fno_short_wchar))
-    A->render(Args, CmdArgs);
-
   // -fno-pascal-strings is default, only pass non-default.
   if (Args.hasFlag(options::OPT_fpascal_strings,
                    options::OPT_fno_pascal_strings, false))
diff --git a/clang/lib/Frontend/CompilerInstance.cpp b/clang/lib/Frontend/CompilerInstance.cpp
index d97ebb0a0e4..32f1232bbe2 100644
--- a/clang/lib/Frontend/CompilerInstance.cpp
+++ b/clang/lib/Frontend/CompilerInstance.cpp
@@ -386,6 +386,7 @@ void CompilerInstance::createPreprocessor(TranslationUnitKind TUKind) {
       Invocation->getPreprocessorOptsPtr(), getDiagnostics(), getLangOpts(),
       getSourceManager(), getPCMCache(), *HeaderInfo, *this, PTHMgr,
       /*OwnsHeaderSearch=*/true, TUKind);
+  getTarget().adjust(getLangOpts());
   PP->Initialize(getTarget(), getAuxTarget());
 
   // Note that this is different then passing PTHMgr to Preprocessor's ctor.
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 37ba39dfd07..7114e654dab 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -2154,7 +2154,16 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
   Opts.ImplicitModules = !Args.hasArg(OPT_fno_implicit_modules);
   Opts.CharIsSigned = Opts.OpenCL || !Args.hasArg(OPT_fno_signed_char);
   Opts.WChar = Opts.CPlusPlus && !Args.hasArg(OPT_fno_wchar);
-  Opts.ShortWChar = Args.hasFlag(OPT_fshort_wchar, OPT_fno_short_wchar, false);
+  if (const Arg *A = Args.getLastArg(OPT_fwchar_type_EQ)) {
+    Opts.WCharSize = llvm::StringSwitch<unsigned>(A->getValue())
+                         .Case("char", 1)
+                         .Case("short", 2)
+                         .Case("int", 4)
+                         .Default(0);
+    if (Opts.WCharSize == 0)
+      Diags.Report(diag::err_fe_invalid_wchar_type) << A->getValue();
+  }
+  Opts.WCharIsSigned = Args.hasFlag(OPT_fsigned_wchar, OPT_fno_signed_wchar, true);
   Opts.ShortEnums = Args.hasArg(OPT_fshort_enums);
   Opts.Freestanding = Args.hasArg(OPT_ffreestanding);
   Opts.NoBuiltin = Args.hasArg(OPT_fno_builtin) || Opts.Freestanding;