Index: lib/CodeGen/TargetInfo.cpp
===================================================================
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -1969,14 +1969,21 @@
         Current = Integer;
       else if (Size <= 128)
         Lo = Hi = Integer;
-    } else if (ET == getContext().FloatTy)
+    } else if (ET == getContext().FloatTy) {
       Current = SSE;
-    else if (ET == getContext().DoubleTy ||
-             (ET == getContext().LongDoubleTy &&
-              getTarget().getTriple().isOSNaCl()))
+    } else if (ET == getContext().DoubleTy) {
       Lo = Hi = SSE;
-    else if (ET == getContext().LongDoubleTy)
-      Current = ComplexX87;
+    } else if (ET == getContext().LongDoubleTy) {
+      const llvm::fltSemantics *LDF = &getTarget().getLongDoubleFormat();
+      if (LDF == &llvm::APFloat::IEEEquad)
+        Current = Memory;
+      else if (LDF == &llvm::APFloat::x87DoubleExtended)
+        Current = ComplexX87;
+      else if (LDF == &llvm::APFloat::IEEEdouble)
+        Lo = Hi = SSE;
+      else
+        llvm_unreachable("unexpected long double representation!");
+    }
 
     // If this complex type crosses an eightbyte boundary then it
     // should be split.
@@ -2518,6 +2525,13 @@
 
 ABIArgInfo X86_64ABIInfo::
 classifyReturnType(QualType RetTy) const {
+  // TODO: Simplify classify to handle f128 according to AMD64 ABI.
+  if (const BuiltinType *BT = RetTy->getAs<BuiltinType>()) {
+     if (BT->getKind() == BuiltinType::LongDouble &&
+         &getTarget().getLongDoubleFormat() == &llvm::APFloat::IEEEquad)
+       return ABIArgInfo::getDirect(CGT.ConvertType(RetTy));
+  }
+
   // AMD64-ABI 3.2.3p4: Rule 1. Classify the return type with the
   // classification algorithm.
   X86_64ABIInfo::Class Lo, Hi;
@@ -2650,6 +2664,16 @@
   bool isNamedArg)
   const
 {
+  // TODO: Simplify classifyArgumentType to handle f128 according to AMD64 ABI.
+  if (const BuiltinType *BT = Ty->getAs<BuiltinType>()) {
+    if (BT->getKind() == BuiltinType::LongDouble &&
+        &getTarget().getLongDoubleFormat() == &llvm::APFloat::IEEEquad) {
+      neededInt = 0;
+      neededSSE = 1;
+      return ABIArgInfo::getDirect(CGT.ConvertType(Ty));
+    }
+  }
+
   Ty = useFirstFieldIfTransparentUnion(Ty);
 
   X86_64ABIInfo::Class Lo, Hi;
Index: test/CodeGen/x86_64-fp128.c
===================================================================
--- /dev/null
+++ test/CodeGen/x86_64-fp128.c
@@ -0,0 +1,116 @@
+// RUN: %clang_cc1 -triple x86_64-linux-android -emit-llvm -O -o - %s \
+// RUN:    | FileCheck %s --check-prefix=ANDROID --check-prefix=CHECK
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm -O -o - %s \
+// RUN:    | FileCheck %s --check-prefix=GNU --check-prefix=CHECK
+// RUN: %clang_cc1 -triple x86_64 -emit-llvm -O -o - %s \
+// RUN:    | FileCheck %s --check-prefix=GNU --check-prefix=CHECK
+
+// Android uses fp128 for long double but other x86_64 targets use x86_fp80.
+
+long double dataLD = 1.0L;
+// ANDROID: @dataLD = global fp128 0xL00000000000000003FFF000000000000, align 16
+// GNU: @dataLD = global x86_fp80 0xK3FFF8000000000000000, align 16
+
+long double _Complex dataLDC = {1.0L, 1.0L};
+// ANDROID: @dataLDC = global { fp128, fp128 } { fp128 0xL00000000000000003FFF000000000000, fp128 0xL00000000000000003FFF000000000000 }, align 16
+// GNU: @dataLDC = global { x86_fp80, x86_fp80 } { x86_fp80 0xK3FFF8000000000000000, x86_fp80 0xK3FFF8000000000000000 }, align 16
+
+long double TestLD(long double x) {
+  return x * x;
+// ANDROID: define fp128 @TestLD(fp128 %x)
+// GNU: define x86_fp80 @TestLD(x86_fp80 %x)
+}
+
+long double _Complex TestLDC(long double _Complex x) {
+  return x * x;
+// ANDROID: define void @TestLDC({ fp128, fp128 }* {{.*}}, { fp128, fp128 }* {{.*}} %x)
+// GNU: define { x86_fp80, x86_fp80 } @TestLDC({ x86_fp80, x86_fp80 }* {{.*}} %x)
+}
+
+typedef __builtin_va_list va_list;
+
+int TestGetVarInt(va_list ap) {
+  return __builtin_va_arg(ap, int);
+// Since int can be passed in memory or in register there is a branch and a phi.
+// CHECK:   define i32 @TestGetVarInt(
+// CHECK:   br
+// CHECK:   load {{.*}} %overflow_arg_area_p
+// CHECK:   = phi
+// CHECK:   ret i32
+}
+
+double TestGetVarDouble(va_list ap) {
+  return __builtin_va_arg(ap, double);
+// Since double can be passed in memory or in register there is a branch and a phi.
+// CHECK:   define double @TestGetVarDouble(
+// CHECK:   br
+// CHECK:   load {{.*}} %overflow_arg_area_p
+// CHECK:   = phi
+// CHECK:   ret double
+}
+
+long double TestGetVarLD(va_list ap) {
+  return __builtin_va_arg(ap, long double);
+// fp128 can be passed in memory or in register, but x86_fp80 is in memory.
+// ANDROID: define fp128 @TestGetVarLD(
+// GNU:     define x86_fp80 @TestGetVarLD(
+// ANDROID: br
+// GNU-NOT: br
+// CHECK:   load {{.*}} %overflow_arg_area_p
+// ANDROID: = phi
+// GNU-NOT: = phi
+// ANDROID: ret fp128
+// GNU:     ret x86_fp80
+}
+
+long double _Complex TestGetVarLDC(va_list ap) {
+  return __builtin_va_arg(ap, long double _Complex);
+// Pair of fp128 or x86_fp80 are passed as struct in memory.
+// ANDROID:   define void @TestGetVarLDC({ fp128, fp128 }* {{.*}}, %struct.__va_list_tag*
+// GNU:       define { x86_fp80, x86_fp80 } @TestGetVarLDC(
+// CHECK-NOT: br
+// CHECK:     load {{.*}} %overflow_arg_area_p
+// CHECK-NOT: phi
+// ANDROID:   ret void
+// GNU:       ret { x86_fp80, x86_fp80 }
+}
+
+void TestVarArg(const char *s, ...);
+
+void TestPassVarInt(int x) {
+  TestVarArg("A", x);
+// CHECK: define void @TestPassVarInt(i32 %x)
+// CHECK: call {{.*}} @TestVarArg(i8* {{.*}}, i32 %x)
+}
+
+void TestPassVarFloat(float x) {
+  TestVarArg("A", x);
+// CHECK: define void @TestPassVarFloat(float %x)
+// CHECK: call {{.*}} @TestVarArg(i8* {{.*}}, double %
+}
+
+void TestPassVarDouble(double x) {
+  TestVarArg("A", x);
+// CHECK: define void @TestPassVarDouble(double %x)
+// CHECK: call {{.*}} @TestVarArg(i8* {{.*}}, double %x
+}
+
+void TestPassVarLD(long double x) {
+  TestVarArg("A", x);
+// ANDROID: define void @TestPassVarLD(fp128 %x)
+// ANDROID: call {{.*}} @TestVarArg(i8* {{.*}}, fp128 %x
+// GNU: define void @TestPassVarLD(x86_fp80 %x)
+// GNU: call {{.*}} @TestVarArg(i8* {{.*}}, x86_fp80 %x
+}
+
+void TestPassVarLDC(long double _Complex x) {
+  TestVarArg("A", x);
+// ANDROID:      define void @TestPassVarLDC({ fp128, fp128 }* {{.*}} %x)
+// ANDROID:      store fp128 %x.{{.*}}, fp128* %
+// ANDROID-NEXT: store fp128 %x.{{.*}}, fp128* %
+// ANDROID-NEXT: call {{.*}} @TestVarArg(i8* {{.*}}, { fp128, fp128 }* {{.*}} %
+// GNU:          define void @TestPassVarLDC({ x86_fp80, x86_fp80 }* {{.*}} %x)
+// GNU:          store x86_fp80 %x.{{.*}}, x86_fp80* %
+// GNU-NEXT:     store x86_fp80 %x.{{.*}}, x86_fp80* %
+// GNGNU-NEXT:   call {{.*}} @TestVarArg(i8* {{.*}}, { x86_fp80, x86_fp80 }* {{.*}} %
+}