Index: llvm/include/llvm/CodeGen/TargetLowering.h
===================================================================
--- llvm/include/llvm/CodeGen/TargetLowering.h
+++ llvm/include/llvm/CodeGen/TargetLowering.h
@@ -1185,7 +1185,7 @@
   /// to replace a call to llvm.memset. The value is set by the target at the
   /// performance threshold for such a replacement. If OptSize is true,
   /// return the limit for functions that have OptSize attribute.
-  unsigned getMaxStoresPerMemset(bool OptSize) const {
+  virtual unsigned getMaxStoresPerMemset(bool OptSize) const {
     return OptSize ? MaxStoresPerMemsetOptSize : MaxStoresPerMemset;
   }
 
@@ -1195,7 +1195,7 @@
   /// to replace a call to llvm.memcpy. The value is set by the target at the
   /// performance threshold for such a replacement. If OptSize is true,
   /// return the limit for functions that have OptSize attribute.
-  unsigned getMaxStoresPerMemcpy(bool OptSize) const {
+  virtual unsigned getMaxStoresPerMemcpy(bool OptSize) const {
     return OptSize ? MaxStoresPerMemcpyOptSize : MaxStoresPerMemcpy;
   }
 
@@ -1214,7 +1214,7 @@
   /// to replace a call to memcmp. The value is set by the target at the
   /// performance threshold for such a replacement. If OptSize is true,
   /// return the limit for functions that have OptSize attribute.
-  unsigned getMaxExpandSizeMemcmp(bool OptSize) const {
+  virtual unsigned getMaxExpandSizeMemcmp(bool OptSize) const {
     return OptSize ? MaxLoadsPerMemcmpOptSize : MaxLoadsPerMemcmp;
   }
 
@@ -1236,7 +1236,7 @@
   /// to replace a call to llvm.memmove. The value is set by the target at the
   /// performance threshold for such a replacement. If OptSize is true,
   /// return the limit for functions that have OptSize attribute.
-  unsigned getMaxStoresPerMemmove(bool OptSize) const {
+  virtual unsigned getMaxStoresPerMemmove(bool OptSize) const {
     return OptSize ? MaxStoresPerMemmoveOptSize : MaxStoresPerMemmove;
   }
 
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -238,6 +238,10 @@
 class AArch64TargetMachine;
 
 class AArch64TargetLowering : public TargetLowering {
+  /// Keep a pointer to the AArch64Subtarget around so that we can
+  /// make the right decision when generating code for different targets.
+  const AArch64Subtarget *Subtarget;
+
 public:
   explicit AArch64TargetLowering(const TargetMachine &TM,
                                  const AArch64Subtarget &STI);
@@ -266,6 +270,10 @@
                                       unsigned Align = 1,
                                       bool *Fast = nullptr) const override;
 
+  // In case of strict alignment, avoid an excessive number of byte wide stores.
+  unsigned getMaxStoresPerMemset(bool OptSize) const override;
+  unsigned getMaxStoresPerMemcpy(bool OptSize) const override;
+
   /// Provide custom lowering hooks for some operations.
   SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;
 
@@ -500,10 +508,6 @@
 private:
   bool isExtFreeImpl(const Instruction *Ext) const override;
 
-  /// Keep a pointer to the AArch64Subtarget around so that we can
-  /// make the right decision when generating code for different targets.
-  const AArch64Subtarget *Subtarget;
-
   void addTypeForNEON(MVT VT, MVT PromotedBitwiseVT);
   void addDRTypeForNEON(MVT VT);
   void addQRTypeForNEON(MVT VT);
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1065,6 +1065,19 @@
   return true;
 }
 
+// In case of strict alignment, avoid an excessive number of byte wide stores
+// for memset() and...
+unsigned AArch64TargetLowering::getMaxStoresPerMemset(bool OptSize) const {
+  return OptSize || Subtarget->requiresStrictAlign()
+         ? MaxStoresPerMemsetOptSize : MaxStoresPerMemset;
+}
+
+// memcpy().
+unsigned AArch64TargetLowering::getMaxStoresPerMemcpy(bool OptSize) const {
+  return OptSize || Subtarget->requiresStrictAlign()
+         ? MaxStoresPerMemcpyOptSize : MaxStoresPerMemcpy;
+}
+
 FastISel *
 AArch64TargetLowering::createFastISel(FunctionLoweringInfo &funcInfo,
                                       const TargetLibraryInfo *libInfo) const {
Index: llvm/test/CodeGen/AArch64/arm64-misaligned-memcpy-inline.ll
===================================================================
--- llvm/test/CodeGen/AArch64/arm64-misaligned-memcpy-inline.ll
+++ llvm/test/CodeGen/AArch64/arm64-misaligned-memcpy-inline.ll
@@ -1,6 +1,6 @@
 ; RUN: llc -mtriple=arm64-apple-ios -mattr=+strict-align < %s | FileCheck %s
 
-; Small (16-bytes here) unaligned memcpys should stay memcpy calls if
+; Small (16 bytes here) unaligned memcpy should stay memcpy call if
 ; strict-alignment is turned on.
 define void @t0(i8* %out, i8* %in) {
 ; CHECK-LABEL: t0:
@@ -11,4 +11,15 @@
   ret void
 }
 
+; Tiny (4 bytes here) unaligned memcpy could be inlined with byte sized
+; loads and stores if strict-alignment is turned on.
+define void @t1(i8* %out, i8* %in) {
+; CHECK-LABEL: t1:
+; CHECK: ldrb w{{[0-9]+}}, [x1]
+; CHECK: strb w{{[0-9]+}}, [x0]
+entry:
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 4, i1 false)
+  ret void
+}
+
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1)