diff --git a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
--- a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
@@ -257,6 +257,10 @@
       if (Reg.VGPR == ReservedVGPR) {
         MBB.removeLiveIn(ReservedVGPR);
         MBB.addLiveIn(LowestAvailableVGPR);
+
+        if (Reg.FI)
+          MF.getFrameInfo().RemoveStackObject(*Reg.FI);
+
         Optional<int> FI;
         if (FuncInfo->isCalleeSavedReg(CSRegs, LowestAvailableVGPR))
           FI = FrameInfo.CreateSpillStackObject(4, Align(4));
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -349,10 +349,21 @@
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   const SIRegisterInfo *TRI = ST.getRegisterInfo();
   SIMachineFunctionInfo *FuncInfo = MF.getInfo<SIMachineFunctionInfo>();
+  MachineRegisterInfo &MRI = MF.getRegInfo();
+  MachineFrameInfo &FrameInfo = MF.getFrameInfo();
+
+  const MCPhysReg *CSRegs = MRI.getCalleeSavedRegs();
 
   Register LaneVGPR = TRI->findUnusedRegister(
       MF.getRegInfo(), &AMDGPU::VGPR_32RegClass, MF, true);
-  SpillVGPRs.push_back(SGPRSpillVGPRCSR(LaneVGPR, None));
+
+  Optional<int> CSRSpillFI;
+  if ((FrameInfo.hasCalls() || !isEntryFunction()) && CSRegs &&
+      isCalleeSavedReg(CSRegs, LaneVGPR)) {
+    CSRSpillFI = FrameInfo.CreateSpillStackObject(4, Align(4));
+  }
+
+  SpillVGPRs.push_back(SGPRSpillVGPRCSR(LaneVGPR, CSRSpillFI));
   FuncInfo->VGPRReservedForSGPRSpill = LaneVGPR;
   return true;
 }
@@ -575,6 +586,9 @@
                                                    MachineFunction &MF) {
   for (auto *i = SpillVGPRs.begin(); i < SpillVGPRs.end(); i++) {
     if (i->VGPR == ReservedVGPR) {
+      if (i->FI)
+        MF.getFrameInfo().RemoveStackObject(*i->FI);
+
       SpillVGPRs.erase(i);
 
       for (MachineBasicBlock &MBB : MF) {
diff --git a/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll b/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll
--- a/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll
+++ b/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll
@@ -6,16 +6,20 @@
 }
 
 ; GCN-LABEL: {{^}}parent_func:
-; CHECK: 	v_writelane_b32 v255, s33, 2
-; CHECK: 	v_writelane_b32 v255, s30, 0
-; CHECK: 	v_writelane_b32 v255, s31, 1
+; CHECK:  buffer_store_dword v255, off, s[0:3], s32
+; CHECK:  v_writelane_b32 v255, s33, 2
+; CHECK:  v_writelane_b32 v255, s30, 0
+; CHECK:  v_writelane_b32 v255, s31, 1
 ; CHECK:  s_swappc_b64 s[30:31], s[4:5]
-; CHECK: 	v_readlane_b32 s4, v255, 0
+; CHECK:  v_readlane_b32 s4, v255, 0
 ; CHECK:  v_readlane_b32 s5, v255, 1
-; CHECK: 	v_readlane_b32 s33, v255, 2
+; CHECK:  v_readlane_b32 s33, v255, 2
 ; GCN: ; NumVgprs: 256
 
 define void @parent_func() #0 {
+  %alloca = alloca i32, align 4, addrspace(5)
+  store volatile i32 0, i32 addrspace(5)* %alloca
+
   call void asm sideeffect "",
   "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
   ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}