Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -982,6 +982,8 @@
   Flags<[CC1Option]>, HelpText<"Do not emit code to make initialization of local statics thread safe">;
 def fno_use_cxa_atexit : Flag<["-"], "fno-use-cxa-atexit">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Don't use __cxa_atexit for calling destructors">;
+def fno_cxx_static_destructors : Flag<["-"], "fno-cxx-static-destructors">, Group<f_clang_Group>,
+  Flags<[CC1Option]>, HelpText<"Don't register c++ exit time destructors">;
 def fno_use_init_array : Flag<["-"], "fno-use-init-array">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Don't use .init_array instead of .ctors">;
 def fno_unit_at_a_time : Flag<["-"], "fno-unit-at-a-time">, Group<f_Group>;
Index: include/clang/Frontend/CodeGenOptions.def
===================================================================
--- include/clang/Frontend/CodeGenOptions.def
+++ include/clang/Frontend/CodeGenOptions.def
@@ -40,6 +40,7 @@
 CODEGENOPT(CoverageNoFunctionNamesInData, 1, 0) ///< Do not include function names in GCDA files.
 CODEGENOPT(CoverageExitBlockBeforeBody, 1, 0) ///< Whether to emit the exit block before the body blocks in GCNO files.
 CODEGENOPT(CXAAtExit         , 1, 1) ///< Use __cxa_atexit for calling destructors.
+CODEGENOPT(CXXNoExitTimeDtor , 1, 0) ///< Do not register exit time destructors (skip calls to __cxa_atexit or atexit).
 CODEGENOPT(CXXCtorDtorAliases, 1, 0) ///< Emit complete ctors/dtors as linker
                                      ///< aliases to base ctors when possible.
 CODEGENOPT(DataSections      , 1, 0) ///< Set when -fdata-sections is enabled.
Index: lib/CodeGen/ItaniumCXXABI.cpp
===================================================================
--- lib/CodeGen/ItaniumCXXABI.cpp
+++ lib/CodeGen/ItaniumCXXABI.cpp
@@ -2132,6 +2132,10 @@
                                        const VarDecl &D,
                                        llvm::Constant *dtor,
                                        llvm::Constant *addr) {
+  // Do not register global dtor at all
+  if (CGM.getCodeGenOpts().CXXNoExitTimeDtor)
+    return;
+
   // Use __cxa_atexit if available.
   if (CGM.getCodeGenOpts().CXAAtExit)
     return emitGlobalDtorWithCXAAtExit(CGF, dtor, addr, D.getTLSKind());
Index: lib/Driver/Tools.cpp
===================================================================
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5963,6 +5963,9 @@
     CmdArgs.push_back("-fwhole-program-vtables");
   }
 
+  if (Args.hasArg(options::OPT_fno_cxx_static_destructors))
+    CmdArgs.push_back("-fno-cxx-static-destructors");
+
   // Finally add the compile command to the compilation.
   if (Args.hasArg(options::OPT__SLASH_fallback) &&
       Output.getType() == types::TY_Object &&
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -546,6 +546,7 @@
   Opts.AssumeSaneOperatorNew = !Args.hasArg(OPT_fno_assume_sane_operator_new);
   Opts.ObjCAutoRefCountExceptions = Args.hasArg(OPT_fobjc_arc_exceptions);
   Opts.CXAAtExit = !Args.hasArg(OPT_fno_use_cxa_atexit);
+  Opts.CXXNoExitTimeDtor = Args.hasArg(OPT_fno_cxx_static_destructors);
   Opts.CXXCtorDtorAliases = Args.hasArg(OPT_mconstructor_aliases);
   Opts.CodeModel = getCodeModel(Args, Diags);
   Opts.DebugPass = Args.getLastArgValue(OPT_mdebug_pass);
Index: test/CodeGenCXX/static-destructor.cpp
===================================================================
--- test/CodeGenCXX/static-destructor.cpp
+++ test/CodeGenCXX/static-destructor.cpp
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -triple=x86_64-pc-linux -emit-llvm -o - | FileCheck --check-prefix=X86 %s
+// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -emit-llvm -fno-cxx-static-destructors -o - | FileCheck --check-prefix=X86-NOATEXIT %s
 // RUN: %clang_cc1 %s -triple=wasm32 -emit-llvm -o - | FileCheck --check-prefix=WASM %s
 // RUN: %clang_cc1 %s -triple=armv7-apple-darwin9 -emit-llvm -o - | FileCheck --check-prefix=ARM %s
 
@@ -19,6 +20,11 @@
 // X86: define internal void @__cxx_global_var_init()
 // X86:   call i32 @__cxa_atexit(void (i8*)* bitcast (void (%class.Foo*)* @_ZN3FooD1Ev to void (i8*)*), i8* getelementptr inbounds (%class.Foo, %class.Foo* @global, i32 0, i32 0), i8* @__dso_handle)
 
+// X86 destructors have void return, and are registered directly with __cxa_atexit.
+// X86-NOATEXIT: define internal void @__cxx_global_var_init()
+// X86-NOATEXIT-NOT:   call i32 @__cxa_atexit(void (i8*)* bitcast (void (%class.Foo*)* @_ZN3FooD1Ev to void (i8*)*), i8* getelementptr inbounds (%class.Foo, %class.Foo* @global, i32 0, i32 0), i8* @__dso_handle)
+// X86-NOATEXIT-NOT:   declare i32 @__cxa_atexit(void (i8*)*, i8*, i8*)
+
 // ARM destructors return this, but can be registered directly with __cxa_atexit
 // because the calling conventions tolerate the mismatch.
 // ARM: define internal void @__cxx_global_var_init()