[X86] Add support for __builtin_cpu_init

[craig.topper]

Summary

This adds builtin_cpu_init which will emit a call to cpu_indicator_init in libgcc or compiler-rt.

This is needed to support builtin_cpu_supports/builtin_cpu_is in an ifunc resolver.

[craig.topper]

Ping

[echristo]

One inline comment, but go ahead and commit after fixing that up.

lib/CodeGen/CGBuiltin.cpp

7292 ↗

(On Diff #109800)

I realize it makes sense to put this here because it doesn't require the setup, but let's go ahead and just put it in the switch statement below. I don't think avoiding the bit of setup/etc below is worth the inconsistency. :)

cfe/trunk/include/clang/Basic/BuiltinsX86.def

 #  define TARGET_HEADER_BUILTIN(ID, TYPE, ATTRS, HEADER, LANG, FEATURE) BUILTIN(ID, TYPE, ATTRS)
 #endif
 
 // FIXME: Are these nothrow/const?
 
 // Miscellaneous builtin for checking x86 cpu features.
 // TODO: Make this somewhat generic so that other backends
 // can use it?
+BUILTIN(__builtin_cpu_init, "v", "n")
 BUILTIN(__builtin_cpu_supports, "bcC*", "nc")
 BUILTIN(__builtin_cpu_is, "bcC*", "nc")
 
 // Undefined Values
 //
 TARGET_BUILTIN(__builtin_ia32_undef128, "V2d", "nc", "")
 TARGET_BUILTIN(__builtin_ia32_undef256, "V4d", "nc", "")
 TARGET_BUILTIN(__builtin_ia32_undef512, "V8d", "nc", "")

cfe/trunk/lib/CodeGen/CGBuiltin.cpp

static Value *EmitX86CpuIs(CodeGenFunction &CGF, const CallExpr *E) {
 
   // Check the value of the field against the requested value.
   return CGF.Builder.CreateICmpEQ(CpuValue,
                                   llvm::ConstantInt::get(Int32Ty, Value));
 }
 
 Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
                                            const CallExpr *E) {
-  if (BuiltinID == X86::BI__builtin_cpu_is)
-    return EmitX86CpuIs(*this, E);
-
   SmallVector<Value*, 4> Ops;
 
   // Find out if any arguments are required to be integer constant expressions.
   unsigned ICEArguments = 0;
   ASTContext::GetBuiltinTypeError Error;
   getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
   assert(Error == ASTContext::GE_None && "Should not codegen an error");
 
auto getVectorFCmpIR = [this, &Ops](CmpInst::Predicate Pred) {
     llvm::VectorType *FPVecTy = cast<llvm::VectorType>(Ops[0]->getType());
     llvm::VectorType *IntVecTy = llvm::VectorType::getInteger(FPVecTy);
     Value *Sext = Builder.CreateSExt(Cmp, IntVecTy);
     return Builder.CreateBitCast(Sext, FPVecTy);
   };
 
   switch (BuiltinID) {
   default: return nullptr;
+  case X86::BI__builtin_cpu_init: {
+    llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy,
+                                                      /*Variadic*/false);
+    llvm::Constant *Func = CGM.CreateRuntimeFunction(FTy,
+                                                     "__cpu_indicator_init");
+    return Builder.CreateCall(Func);
+  }
+  case X86::BI__builtin_cpu_is:
+    return EmitX86CpuIs(*this, E);
   case X86::BI__builtin_cpu_supports: {
     const Expr *FeatureExpr = E->getArg(0)->IgnoreParenCasts();
     StringRef FeatureStr = cast<StringLiteral>(FeatureExpr)->getString();
 
     // TODO: When/if this becomes more than x86 specific then use a TargetInfo
     // based mapping.
     // Processor features and mapping to processor feature value.
     enum X86Features {

cfe/trunk/test/CodeGen/builtin-cpu-supports.c

 // RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -emit-llvm < %s| FileCheck %s
 
 // Test that we have the structure definition, the gep offsets, the name of the
 // global, the bit grab, and the icmp correct.
 extern void a(const char *);
 
 int main() {
+  __builtin_cpu_init();
+
+  // CHECK: call void @__cpu_indicator_init
+
   if (__builtin_cpu_supports("sse4.2"))
     a("sse4.2");
 
   // CHECK: [[LOAD:%[^ ]+]] = load i32, i32* getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, { i32, i32, i32, [1 x i32] }* @__cpu_model, i32 0, i32 3, i32 0)
   // CHECK: [[AND:%[^ ]+]] = and i32 [[LOAD]], 256
   // CHECK: = icmp ne i32 [[AND]], 0
 
   return 0;
 }