Index: llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
===================================================================
--- llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -1547,6 +1547,7 @@
   bool IsVarArg = CLI.IsVarArg;
   MachineFunction &MF = DAG.getMachineFunction();
   EVT PtrVT = getPointerTy(MF.getDataLayout());
+  LLVMContext &Ctx = *DAG.getContext();
 
   // Detect unsupported vector argument and return types.
   if (Subtarget.hasVector()) {
@@ -1556,7 +1557,7 @@
 
   // Analyze the operands of the call, assigning locations to each operand.
   SmallVector<CCValAssign, 16> ArgLocs;
-  SystemZCCState ArgCCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());
+  SystemZCCState ArgCCInfo(CallConv, IsVarArg, MF, ArgLocs, Ctx);
   ArgCCInfo.AnalyzeCallOperands(Outs, CC_SystemZ);
 
   // We don't support GuaranteedTailCallOpt, only automatically-detected
@@ -1581,7 +1582,17 @@
 
     if (VA.getLocInfo() == CCValAssign::Indirect) {
       // Store the argument in a stack slot and pass its address.
-      SDValue SpillSlot = DAG.CreateStackTemporary(Outs[I].ArgVT);
+      Type *OrigArgType = CLI.Args[Outs[I].OrigArgIndex].Ty;
+      EVT SlotVT = getValueType(MF.getDataLayout(), OrigArgType);
+      if (SlotVT.getSizeInBits() > 64 &&
+          getTypeAction(Ctx, SlotVT) == TypePromoteInteger) {
+        // Allocate the full stack space for a promoted (and split) argument.
+        MVT PartVT = getRegisterTypeForCallingConv(Ctx, CLI.CallConv, SlotVT);
+        unsigned N = getNumRegistersForCallingConv(Ctx, CLI.CallConv, SlotVT);
+        SlotVT = EVT::getIntegerVT(Ctx, PartVT.getSizeInBits() * N);
+      }
+      SDValue SpillSlot = DAG.CreateStackTemporary(SlotVT);
+
       int FI = cast<FrameIndexSDNode>(SpillSlot)->getIndex();
       MemOpChains.push_back(
           DAG.getStore(Chain, DL, ArgValue, SpillSlot,
@@ -1598,6 +1609,8 @@
         MemOpChains.push_back(
             DAG.getStore(Chain, DL, PartValue, Address,
                          MachinePointerInfo::getFixedStack(MF, FI)));
+        assert((PartOffset + PartValue.getValueType().getStoreSize() <=
+                SlotVT.getStoreSize()) && "Not enough space for argument part!");
         ++I;
       }
       ArgValue = SpillSlot;
@@ -1691,7 +1704,7 @@
 
   // Assign locations to each value returned by this call.
   SmallVector<CCValAssign, 16> RetLocs;
-  CCState RetCCInfo(CallConv, IsVarArg, MF, RetLocs, *DAG.getContext());
+  CCState RetCCInfo(CallConv, IsVarArg, MF, RetLocs, Ctx);
   RetCCInfo.AnalyzeCallResult(Ins, RetCC_SystemZ);
 
   // Copy all of the result registers out of their specified physreg.
Index: llvm/test/CodeGen/SystemZ/args-11.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/SystemZ/args-11.ll
@@ -0,0 +1,54 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; Test outgoing promoted arguments that are split (and passed by reference).
+;
+; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
+
+; The i96 arg is promoted to i128 and should get the full stack space.
+declare void @fn1(i96)
+define i32 @fn2() {
+; CHECK-LABEL: fn2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    stmg %r14, %r15, 112(%r15)
+; CHECK-NEXT:    .cfi_offset %r14, -48
+; CHECK-NEXT:    .cfi_offset %r15, -40
+; CHECK-NEXT:    aghi %r15, -184
+; CHECK-NEXT:    .cfi_def_cfa_offset 344
+; CHECK-NEXT:    mvhi 180(%r15), -1
+; CHECK-NEXT:    mvghi 168(%r15), 0
+; CHECK-NEXT:    la %r2, 160(%r15)
+; CHECK-NEXT:    mvghi 160(%r15), 0
+; CHECK-NEXT:    brasl %r14, fn1@PLT
+; CHECK-NEXT:    l %r2, 180(%r15)
+; CHECK-NEXT:    lmg %r14, %r15, 296(%r15)
+; CHECK-NEXT:    br %r14
+  %1 = alloca i32
+  store i32 -1, i32* %1
+  call void @fn1(i96 0)
+  %2 = load i32, i32* %1
+  ret i32 %2
+}
+
+declare void @fn3(i136)
+define i32 @fn4() {
+; CHECK-LABEL: fn4:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    stmg %r14, %r15, 112(%r15)
+; CHECK-NEXT:    .cfi_offset %r14, -48
+; CHECK-NEXT:    .cfi_offset %r15, -40
+; CHECK-NEXT:    aghi %r15, -192
+; CHECK-NEXT:    .cfi_def_cfa_offset 352
+; CHECK-NEXT:    mvhi 188(%r15), -1
+; CHECK-NEXT:    mvghi 176(%r15), 0
+; CHECK-NEXT:    mvghi 168(%r15), 0
+; CHECK-NEXT:    la %r2, 160(%r15)
+; CHECK-NEXT:    mvghi 160(%r15), 0
+; CHECK-NEXT:    brasl %r14, fn3@PLT
+; CHECK-NEXT:    l %r2, 188(%r15)
+; CHECK-NEXT:    lmg %r14, %r15, 304(%r15)
+; CHECK-NEXT:    br %r14
+  %1 = alloca i32
+  store i32 -1, i32* %1
+  call void @fn3(i136 0)
+  %2 = load i32, i32* %1
+  ret i32 %2
+}