Index: llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
+++ llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
@@ -31,6 +31,7 @@
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/CommandLine.h"
@@ -1760,6 +1761,26 @@
   return E;
 }
 
+static MachineBasicBlock::iterator
+maybeMoveCFI(MachineInstr &MI, MachineBasicBlock::iterator MaybeCFI) {
+  if (MaybeCFI->getOpcode() != TargetOpcode::CFI_INSTRUCTION ||
+      !(MI.getFlag(MachineInstr::FrameSetup) ||
+        MI.getFlag(MachineInstr::FrameDestroy)) ||
+      getLdStBaseOp(MI).getReg() != AArch64::SP)
+    return MI.getParent()->end();
+
+  const MachineFunction &MF = *MI.getParent()->getParent();
+  unsigned CFIIndex = MaybeCFI->getOperand(0).getCFIIndex();
+  const MCCFIInstruction &CFI = MF.getFrameInstructions()[CFIIndex];
+  switch (CFI.getOperation()) {
+  case MCCFIInstruction::OpDefCfa:
+  case MCCFIInstruction::OpDefCfaOffset:
+    return MaybeCFI;
+  default:
+    return MI.getParent()->end();
+  }
+}
+
 MachineBasicBlock::iterator
 AArch64LoadStoreOpt::mergeUpdateInsn(MachineBasicBlock::iterator I,
                                      MachineBasicBlock::iterator Update,
@@ -1769,6 +1790,12 @@
          "Unexpected base register update instruction to merge!");
   MachineBasicBlock::iterator E = I->getParent()->end();
   MachineBasicBlock::iterator NextI = next_nodbg(I, E);
+
+  // If updating the SP and the following instruction is CFA offset related CFI
+  // instruction move it after the merged instruction.
+  MachineBasicBlock::iterator CFI =
+      IsPreIdx ? maybeMoveCFI(*Update, next_nodbg(Update, E)) : E;
+
   // Return the instruction following the merged instruction, which is
   // the instruction following our unmerged load. Unless that's the add/sub
   // instruction we're merging, in which case it's the one after that.
@@ -1806,7 +1833,10 @@
               .setMemRefs(I->memoperands())
               .setMIFlags(I->mergeFlagsWith(*Update));
   }
-  (void)MIB;
+  if (CFI != E) {
+    MachineBasicBlock *MBB = I->getParent();
+    MBB->splice(std::next(MIB.getInstr()->getIterator()), MBB, CFI);
+  }
 
   if (IsPreIdx) {
     ++NumPreFolded;
Index: llvm/test/CodeGen/AArch64/arm64-fp128.ll
===================================================================
--- llvm/test/CodeGen/AArch64/arm64-fp128.ll
+++ llvm/test/CodeGen/AArch64/arm64-fp128.ll
@@ -422,8 +422,8 @@
 define fp128 @test_neg(fp128 %in) {
 ; CHECK-LABEL: test_neg:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    str q0, [sp, #-16]!
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    ldrb w8, [sp, #15]
 ; CHECK-NEXT:    eor w8, w8, #0x80
 ; CHECK-NEXT:    strb w8, [sp, #15]
Index: llvm/test/CodeGen/AArch64/fcopysign.ll
===================================================================
--- llvm/test/CodeGen/AArch64/fcopysign.ll
+++ llvm/test/CodeGen/AArch64/fcopysign.ll
@@ -13,11 +13,11 @@
 define fp128 @copysign0() {
 ; CHECK-LABEL: copysign0:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    adrp x8, .LCPI0_0
 ; CHECK-NEXT:    ldr q0, [x8, :lo12:.LCPI0_0]
 ; CHECK-NEXT:    adrp x8, val_double
 ; CHECK-NEXT:    str q0, [sp, #-16]!
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    ldr x8, [x8, :lo12:val_double]
 ; CHECK-NEXT:    ldrb w9, [sp, #15]
 ; CHECK-NEXT:    and x8, x8, #0x8000000000000000
@@ -36,11 +36,11 @@
 define fp128@copysign1() {
 ; CHECK-LABEL: copysign1:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    adrp x8, val_fp128
 ; CHECK-NEXT:    ldr q0, [x8, :lo12:val_fp128]
 ; CHECK-NEXT:    adrp x8, val_float
 ; CHECK-NEXT:    str q0, [sp, #-16]!
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    ldr w8, [x8, :lo12:val_float]
 ; CHECK-NEXT:    ldrb w9, [sp, #15]
 ; CHECK-NEXT:    and w8, w8, #0x80000000
Index: llvm/test/CodeGen/AArch64/swifttail-call.ll
===================================================================
--- llvm/test/CodeGen/AArch64/swifttail-call.ll
+++ llvm/test/CodeGen/AArch64/swifttail-call.ll
@@ -36,6 +36,7 @@
   ret void
 
 ; COMMON: str {{x[0-9]+}}, [sp, #-16]!
+; COMMON-NEXT:	.cfi_def_cfa_offset 16
 ; COMMON-NEXT: b callee_stack8
 }
 
Index: llvm/test/CodeGen/AArch64/tail-call.ll
===================================================================
--- llvm/test/CodeGen/AArch64/tail-call.ll
+++ llvm/test/CodeGen/AArch64/tail-call.ll
@@ -36,6 +36,7 @@
   ret void
 
 ; COMMON: str {{x[0-9]+}}, [sp, #-16]!
+; COMMON-NEXT: .cfi_def_cfa_offset 16
 ; COMMON-NEXT: b callee_stack8
 }