diff --git a/llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp b/llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
--- a/llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
@@ -1763,6 +1763,11 @@
   return false;
 }
 
+static bool needsWinCFI(const MachineFunction *MF) {
+  return MF->getTarget().getMCAsmInfo()->usesWindowsCFI() &&
+         MF->getFunction().needsUnwindTableEntry();
+}
+
 MachineBasicBlock::iterator AArch64LoadStoreOpt::findMatchingUpdateInsnForward(
     MachineBasicBlock::iterator I, int UnscaledOffset, unsigned Limit) {
   MachineBasicBlock::iterator E = I->getParent()->end();
@@ -1803,14 +1808,11 @@
   // the memory access (I) and the increment (MBBI) can access the memory
   // region defined by [SP, MBBI].
   const bool BaseRegSP = BaseReg == AArch64::SP;
-  if (BaseRegSP) {
+  if (BaseRegSP && needsWinCFI(I->getMF())) {
     // FIXME: For now, we always block the optimization over SP in windows
     // targets as it requires to adjust the unwind/debug info, messing up
     // the unwind info can actually cause a miscompile.
-    const MCAsmInfo *MAI = I->getMF()->getTarget().getMCAsmInfo();
-    if (MAI->usesWindowsCFI() &&
-        I->getMF()->getFunction().needsUnwindTableEntry())
-      return E;
+    return E;
   }
 
   for (unsigned Count = 0; MBBI != E && Count < Limit;
@@ -1866,6 +1868,14 @@
     }
   }
 
+  const bool BaseRegSP = BaseReg == AArch64::SP;
+  if (BaseRegSP && needsWinCFI(I->getMF())) {
+    // FIXME: For now, we always block the optimization over SP in windows
+    // targets as it requires to adjust the unwind/debug info, messing up
+    // the unwind info can actually cause a miscompile.
+    return E;
+  }
+
   // Track which register units have been modified and used between the first
   // insn (inclusive) and the second insn.
   ModifiedRegUnits.clear();
diff --git a/llvm/test/CodeGen/AArch64/arm64-windows-calls.ll b/llvm/test/CodeGen/AArch64/arm64-windows-calls.ll
--- a/llvm/test/CodeGen/AArch64/arm64-windows-calls.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-windows-calls.ll
@@ -26,7 +26,10 @@
 entry:
 ; FIXME: Missed optimization, the entire SP push/pop could be removed
 ; CHECK-LABEL: f2
-; CHECK:         stp     xzr, xzr, [sp, #-16]!
+; CHECK:         sub     sp, sp, #16
+; CHECK-NEXT:    .seh_stackalloc 16
+; CHECK-NEXT:    .seh_endprologue
+; CHECK-NEXT:    stp     xzr, xzr, [sp]
 ; CHECK-NEXT:    mov     x0, xzr
 ; CHECK-NEXT:    mov     x1, xzr
 ; CHECK-NEXT:    .seh_startepilogue