Index: include/clang/Basic/BuiltinsARM.def
===================================================================
--- include/clang/Basic/BuiltinsARM.def
+++ include/clang/Basic/BuiltinsARM.def
@@ -115,6 +115,14 @@
 LANGBUILTIN(__dmb, "vUi", "nc", ALL_MS_LANGUAGES)
 LANGBUILTIN(__dsb, "vUi", "nc", ALL_MS_LANGUAGES)
 LANGBUILTIN(__isb, "vUi", "nc", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load8,   "ccCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load16,  "ssCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load32,  "iiCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load64,  "LLiLLiCD*", "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store8,  "vcD*c",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store16, "vsD*s",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store32, "viD*i",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store64, "vLLiD*LLi", "n", ALL_MS_LANGUAGES)
 LANGBUILTIN(__ldrexd, "WiWiCD*", "", ALL_MS_LANGUAGES)
 LANGBUILTIN(_MoveFromCoprocessor, "UiIUiIUiIUiIUiIUi", "", ALL_MS_LANGUAGES)
 LANGBUILTIN(_MoveFromCoprocessor2, "UiIUiIUiIUiIUiIUi", "", ALL_MS_LANGUAGES)
Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -134,6 +134,36 @@
   return CGF.EmitLoadOfScalar(LV, E->getExprLoc());
 }
 
+static Value *EmitVolatileStore(CodeGenFunction &CGF, const CallExpr *E) {
+  Value *Address = CGF.EmitScalarExpr(E->getArg(0));
+  Value *Val = CGF.EmitScalarExpr(E->getArg(1));
+
+  LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getArg(1)->getType());
+  // Call the full version of EmitStoreOfScalar directly, to override the volatile
+  // flag without actually setting volatile in the type. This avoids
+  // LValueIsSuitableForInlineAtomic picking it up and transforming it into an
+  // atomic store.
+  CGF.EmitStoreOfScalar(Val, LV.getAddress(), true, LV.getType(),
+                        LV.getAlignmentSource(), LV.getTBAAInfo(), false,
+                        LV.getTBAABaseType(), LV.getTBAAOffset(),
+                        LV.isNontemporal());
+  return nullptr;
+}
+
+static Value *EmitVolatileLoad(CodeGenFunction &CGF, const CallExpr *E) {
+  Value *Address = CGF.EmitScalarExpr(E->getArg(0));
+
+  LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getType());
+  // Call the full version of EmitLoadOfScalar directly, to override the volatile
+  // flag without actually setting volatile in the type. This avoids
+  // LValueIsSuitableForInlineAtomic picking it up and transforming it into an
+  // atomic load.
+  return CGF.EmitLoadOfScalar(LV.getAddress(), true, LV.getType(),
+                              E->getExprLoc(), LV.getAlignmentSource(),
+                              LV.getTBAAInfo(), LV.getTBAABaseType(),
+                              LV.getTBAAOffset(), LV.isNontemporal());
+}
+
 static RValue EmitBinaryAtomic(CodeGenFunction &CGF,
                                llvm::AtomicRMWInst::BinOp Kind,
                                const CallExpr *E) {
@@ -2558,6 +2588,33 @@
     return RValue::get(V);
   }
 
+  switch (getTarget().getTriple().getArch()) {
+  case llvm::Triple::arm:
+  case llvm::Triple::armeb:
+  case llvm::Triple::thumb:
+  case llvm::Triple::thumbeb:
+    switch (BuiltinID) {
+    case ARM::BI__iso_volatile_load8:
+    case ARM::BI__iso_volatile_load16:
+    case ARM::BI__iso_volatile_load32:
+    case ARM::BI__iso_volatile_load64:
+      return RValue::get(EmitVolatileLoad(*this, E));
+    case ARM::BI__iso_volatile_store8:
+    case ARM::BI__iso_volatile_store16:
+    case ARM::BI__iso_volatile_store32:
+    case ARM::BI__iso_volatile_store64:
+      // EmitVolatileStore returns nullptr, but we want to
+      // return that RValue here. If handled via EmitTargetBuiltinExpr
+      // below, the returned Value *V will be nullptr, and we will
+      // continue on to declaring the builtin unsupported below, even
+      // though it was handled correctly.
+      return RValue::get(EmitVolatileStore(*this, E));
+    }
+    break;
+  default:
+    break;
+  }
+
   // See if we have a target specific builtin that needs to be lowered.
   if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E))
     return RValue::get(V);
Index: test/CodeGen/ms-volatile-arm.c
===================================================================
--- /dev/null
+++ test/CodeGen/ms-volatile-arm.c
@@ -0,0 +1,13 @@
+// REQUIRES: arm-registered-target
+// RUN: %clang_cc1 -triple thumbv7-win32 -emit-llvm -fms-extensions -fms-volatile -o - < %s | FileCheck %s
+
+void test1(int volatile *p, int v) {
+  __iso_volatile_store32(p, v);
+  // CHECK-LABEL: @test1
+  // CHECK: store volatile {{.*}}, {{.*}}
+}
+int test2(const int volatile *p) {
+  return __iso_volatile_load32(p);
+  // CHECK-LABEL: @test2
+  // CHECK: load volatile {{.*}}
+}