Index: include/clang/Basic/BuiltinsAArch64.def
===================================================================
--- include/clang/Basic/BuiltinsAArch64.def
+++ include/clang/Basic/BuiltinsAArch64.def
@@ -18,6 +18,10 @@
 #   define LANGBUILTIN(ID, TYPE, ATTRS, BUILTIN_LANG) BUILTIN(ID, TYPE, ATTRS)
 #endif
 
+#if defined(BUILTIN) && !defined(TARGET_HEADER_BUILTIN)
+#  define TARGET_HEADER_BUILTIN(ID, TYPE, ATTRS, HEADER, LANG, FEATURE) BUILTIN(ID, TYPE, ATTRS)
+#endif
+
 // In libgcc
 BUILTIN(__clear_cache, "vv*v*", "i")
 
@@ -85,5 +89,20 @@
 LANGBUILTIN(__iso_volatile_store32, "viD*i",     "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(__iso_volatile_store64, "vLLiD*LLi", "n", ALL_MS_LANGUAGES)
 
+TARGET_HEADER_BUILTIN(_BitScanForward, "UcUNi*UNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_BitScanReverse, "UcUNi*UNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_BitScanForward64, "UcUNi*ULLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_BitScanReverse64, "UcUNi*ULLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+
+TARGET_HEADER_BUILTIN(_InterlockedAnd64,         "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedDecrement64,   "LLiLLiD*",    "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedExchange64,    "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedExchangeAdd64, "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedExchangeSub64, "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedIncrement64,   "LLiLLiD*",    "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedOr64,          "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_InterlockedXor64,         "LLiLLiD*LLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+
 #undef BUILTIN
 #undef LANGBUILTIN
+#undef TARGET_HEADER_BUILTIN
Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -732,8 +732,8 @@
   return RValue::get(CS.getInstruction());
 }
 
-// Many of MSVC builtins are on both x64 and ARM; to avoid repeating code, we
-// handle them here.
+// Many of MSVC builtins are on x64, ARM and AArch64; to avoid repeating code,
+// we handle them here.
 enum class CodeGenFunction::MSVCIntrin {
   _BitScanForward,
   _BitScanReverse,
@@ -8385,6 +8385,28 @@
   case AArch64::BI__iso_volatile_store32:
   case AArch64::BI__iso_volatile_store64:
     return EmitISOVolatileStore(E);
+  case AArch64::BI_BitScanForward:
+  case AArch64::BI_BitScanForward64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanForward, E);
+  case AArch64::BI_BitScanReverse:
+  case AArch64::BI_BitScanReverse64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanReverse, E);
+  case AArch64::BI_InterlockedAnd64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedAnd, E);
+  case AArch64::BI_InterlockedExchange64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchange, E);
+  case AArch64::BI_InterlockedExchangeAdd64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeAdd, E);
+  case AArch64::BI_InterlockedExchangeSub64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeSub, E);
+  case AArch64::BI_InterlockedOr64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedOr, E);
+  case AArch64::BI_InterlockedXor64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedXor, E);
+  case AArch64::BI_InterlockedDecrement64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedDecrement, E);
+  case AArch64::BI_InterlockedIncrement64:
+    return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedIncrement, E);
   }
 }
 
Index: lib/Headers/intrin.h
===================================================================
--- lib/Headers/intrin.h
+++ lib/Headers/intrin.h
@@ -38,7 +38,7 @@
 #include <armintr.h>
 #endif
 
-#if defined(_M_ARM64)
+#if defined(__aarch64__)
 #include <arm64intr.h>
 #endif
 
@@ -299,7 +299,7 @@
 
 #endif /* __x86_64__ */
 
-#if defined(__x86_64__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__arm__) || defined(__aarch64__)
 
 static __inline__
 unsigned char _BitScanForward64(unsigned long *_Index, unsigned __int64 _Mask);
Index: test/CodeGen/ms-intrinsics.c
===================================================================
--- test/CodeGen/ms-intrinsics.c
+++ test/CodeGen/ms-intrinsics.c
@@ -7,6 +7,9 @@
 // RUN: %clang_cc1 -ffreestanding -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 \
 // RUN:         -triple x86_64--windows -Oz -emit-llvm -target-feature +cx16 %s -o - \
 // RUN:         | FileCheck %s --check-prefixes CHECK,CHECK-X64,CHECK-ARM-X64,CHECK-INTEL
+// RUN: %clang_cc1 -ffreestanding -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 \
+// RUN:         -triple aarch64-windows -Oz -emit-llvm %s -o - \
+// RUN:         | FileCheck %s --check-prefix CHECK-ARM-X64
 
 // intrin.h needs size_t, but -ffreestanding prevents us from getting it from
 // stddef.h.  Work around it with this typedef.
@@ -172,7 +175,7 @@
 // CHECK:   store i32 [[INDEX]], i32* %Index, align 4
 // CHECK:   br label %[[END_LABEL]]
 
-#if defined(__x86_64__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__arm__) || defined(__aarch64__)
 unsigned char test_BitScanForward64(unsigned long *Index, unsigned __int64 Mask) {
   return _BitScanForward64(Index, Mask);
 }
@@ -469,7 +472,7 @@
 // CHECK: ret i32 [[RESULT]]
 // CHECK: }
 
-#if defined(__x86_64__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__arm__) || defined(__aarch64__)
 __int64 test_InterlockedExchange64(__int64 volatile *value, __int64 mask) {
   return _InterlockedExchange64(value, mask);
 }
@@ -587,6 +590,7 @@
 }
 #endif
 
+#if !defined(__aarch64__)
 void test__fastfail() {
   __fastfail(42);
 }
@@ -597,4 +601,4 @@
 // Attributes come last.
 
 // CHECK: attributes #[[NORETURN]] = { noreturn{{.*}} }
-
+#endif