diff --git a/llvm/include/llvm/CodeGen/TargetInstrInfo.h b/llvm/include/llvm/CodeGen/TargetInstrInfo.h
--- a/llvm/include/llvm/CodeGen/TargetInstrInfo.h
+++ b/llvm/include/llvm/CodeGen/TargetInstrInfo.h
@@ -1937,6 +1937,13 @@
     return Formatter.get();
   }
 
+  /// Returns the target-specific default value for tail duplication.
+  /// This value will be used if the tail-dup-size argument is not provided.
+  virtual unsigned
+  getTailDuplicateSizeOverride(CodeGenOpt::Level OptLevel) const {
+    return OptLevel >= CodeGenOpt::Aggressive ? 4 : 2;
+  }
+
 private:
   mutable std::unique_ptr<MIRFormatter> Formatter;
   unsigned CallFrameSetupOpcode, CallFrameDestroyOpcode;
diff --git a/llvm/lib/CodeGen/MachineBlockPlacement.cpp b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
--- a/llvm/lib/CodeGen/MachineBlockPlacement.cpp
+++ b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
@@ -3337,6 +3337,13 @@
       TailDupSize = TailDupPlacementAggressiveThreshold;
   }
 
+  // If there's no threshold provided through options, query the target
+  // information for a threshold instead.
+  if (TailDupPlacementThreshold.getNumOccurrences() == 0 &&
+      (PassConfig->getOptLevel() < CodeGenOpt::Aggressive ||
+       TailDupPlacementAggressiveThreshold.getNumOccurrences() == 0))
+    TailDupSize = TII->getTailDuplicateSizeOverride(PassConfig->getOptLevel());
+
   if (allowTailDupPlacement()) {
     MPDT = &getAnalysis<MachinePostDominatorTree>();
     bool OptForSize = MF.getFunction().hasOptSize() ||
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.h b/llvm/lib/Target/AArch64/AArch64InstrInfo.h
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.h
@@ -299,6 +299,9 @@
   Optional<ParamLoadedValue> describeLoadedValue(const MachineInstr &MI,
                                                  Register Reg) const override;
 
+  unsigned int
+  getTailDuplicateSizeOverride(CodeGenOpt::Level OptLevel) const override;
+
   static void decomposeStackOffsetForFrameOffsets(const StackOffset &Offset,
                                                   int64_t &NumBytes,
                                                   int64_t &NumPredicateVectors,
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -7183,6 +7183,11 @@
   return get(Opc).TSFlags & AArch64::InstrFlagIsWhile;
 }
 
+unsigned int AArch64InstrInfo::getTailDuplicateSizeOverride(
+    CodeGenOpt::Level OptLevel) const {
+  return OptLevel >= CodeGenOpt::Aggressive ? 6 : 2;
+}
+
 unsigned llvm::getBLRCallOpcode(const MachineFunction &MF) {
   if (MF.getSubtarget<AArch64Subtarget>().hardenSlsBlr())
     return AArch64::BLRNoIP;
diff --git a/llvm/test/CodeGen/AArch64/aarch64-tail-dup-size.ll b/llvm/test/CodeGen/AArch64/aarch64-tail-dup-size.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/aarch64-tail-dup-size.ll
@@ -0,0 +1,73 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-none-linux -O2 < %s | FileCheck %s --check-prefix=CHECK-O2
+; RUN: llc -mtriple=aarch64-none-linux -O3 < %s | FileCheck %s --check-prefix=CHECK-O3
+
+%struct.record = type { %struct.record*, i32, %union.anon }
+%union.anon = type { %struct.anon }
+%struct.anon = type { i32, i32, [31 x i8] }
+
+@Ptr_Glob = dso_local local_unnamed_addr global %struct.record* null, align 8
+@Int_Glob = dso_local local_unnamed_addr global i32 0, align 4
+
+define dso_local void @testcase(%struct.record** nocapture %Ptr_Ref_Par){
+; CHECK-O2-LABEL: testcase:
+; CHECK-O2:       // %bb.0: // %entry
+; CHECK-O2-NEXT:    adrp x8, Ptr_Glob
+; CHECK-O2-NEXT:    ldr x9, [x8, :lo12:Ptr_Glob]
+; CHECK-O2-NEXT:    cbz x9, .LBB0_2
+; CHECK-O2-NEXT:  // %bb.1: // %if.then
+; CHECK-O2-NEXT:    ldr x9, [x9]
+; CHECK-O2-NEXT:    str x9, [x0]
+; CHECK-O2-NEXT:    ldr x8, [x8, :lo12:Ptr_Glob]
+; CHECK-O2-NEXT:    b .LBB0_3
+; CHECK-O2-NEXT:  .LBB0_2:
+; CHECK-O2-NEXT:    mov x8, xzr
+; CHECK-O2-NEXT:  .LBB0_3: // %if.end
+; CHECK-O2-NEXT:    adrp x9, Int_Glob
+; CHECK-O2-NEXT:    ldr w1, [x9, :lo12:Int_Glob]
+; CHECK-O2-NEXT:    add x2, x8, #16 // =16
+; CHECK-O2-NEXT:    mov w0, #10
+; CHECK-O2-NEXT:    b externalfunc
+;
+; CHECK-O3-LABEL: testcase:
+; CHECK-O3:       // %bb.0: // %entry
+; CHECK-O3-NEXT:    adrp x8, Ptr_Glob
+; CHECK-O3-NEXT:    ldr x9, [x8, :lo12:Ptr_Glob]
+; CHECK-O3-NEXT:    cbz x9, .LBB0_2
+; CHECK-O3-NEXT:  // %bb.1: // %if.then
+; CHECK-O3-NEXT:    ldr x9, [x9]
+; CHECK-O3-NEXT:    str x9, [x0]
+; CHECK-O3-NEXT:    ldr x8, [x8, :lo12:Ptr_Glob]
+; CHECK-O3-NEXT:    adrp x9, Int_Glob
+; CHECK-O3-NEXT:    ldr w1, [x9, :lo12:Int_Glob]
+; CHECK-O3-NEXT:    add x2, x8, #16 // =16
+; CHECK-O3-NEXT:    mov w0, #10
+; CHECK-O3-NEXT:    b externalfunc
+; CHECK-O3-NEXT:  .LBB0_2:
+; CHECK-O3-NEXT:    mov x8, xzr
+; CHECK-O3-NEXT:    adrp x9, Int_Glob
+; CHECK-O3-NEXT:    ldr w1, [x9, :lo12:Int_Glob]
+; CHECK-O3-NEXT:    add x2, x8, #16 // =16
+; CHECK-O3-NEXT:    mov w0, #10
+; CHECK-O3-NEXT:    b externalfunc
+entry:
+  %0 = load %struct.record*, %struct.record** @Ptr_Glob, align 8
+  %cmp.not = icmp eq %struct.record* %0, null
+  br i1 %cmp.not, label %if.end, label %if.then
+
+if.then:                                          ; preds = %entry
+  %Ptr_Comp = getelementptr inbounds %struct.record, %struct.record* %0, i64 0, i32 0
+  %1 = load %struct.record*, %struct.record** %Ptr_Comp, align 8
+  store %struct.record* %1, %struct.record** %Ptr_Ref_Par, align 8
+  %.pre = load %struct.record*, %struct.record** @Ptr_Glob, align 8
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %entry
+  %2 = phi %struct.record* [ %.pre, %if.then ], [ null, %entry ]
+  %3 = load i32, i32* @Int_Glob, align 4
+  %Int_Comp = getelementptr inbounds %struct.record, %struct.record* %2, i64 0, i32 2, i32 0, i32 1
+  tail call void @externalfunc(i32 10, i32 %3, i32* nonnull %Int_Comp)
+  ret void
+}
+
+declare dso_local void @externalfunc(i32, i32, i32*)