diff --git a/llvm/lib/CodeGen/LivePhysRegs.cpp b/llvm/lib/CodeGen/LivePhysRegs.cpp
--- a/llvm/lib/CodeGen/LivePhysRegs.cpp
+++ b/llvm/lib/CodeGen/LivePhysRegs.cpp
@@ -276,6 +276,7 @@
   const MachineFunction &MF = *MBB.getParent();
   const MachineRegisterInfo &MRI = MF.getRegInfo();
   const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
+  const MachineFrameInfo &MFI = MF.getFrameInfo();
 
   // We walk through the block backwards and start with the live outs.
   LivePhysRegs LiveRegs;
@@ -294,6 +295,18 @@
       assert(Register::isPhysicalRegister(Reg));
 
       bool IsNotLive = LiveRegs.available(MRI, Reg);
+
+      // Special-case return instructions for cases when a return is not
+      // the last instruction in the block.
+      if (MI.isReturn() && MFI.isCalleeSavedInfoValid()) {
+        for (const CalleeSavedInfo &Info : MFI.getCalleeSavedInfo()) {
+          if (Info.getReg() == Reg) {
+            IsNotLive = !Info.isRestored();
+            break;
+          }
+        }
+      }
+
       MO->setIsDead(IsNotLive);
     }
 
diff --git a/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp b/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
--- a/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ b/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -43,6 +43,61 @@
 
 namespace {
 
+  class PostOrderLoopTraversal {
+    MachineLoop &ML;
+    MachineLoopInfo &MLI;
+    SmallPtrSet<MachineBasicBlock*, 4> Visited;
+    SmallVector<MachineBasicBlock*, 4> Order;
+
+  public:
+    PostOrderLoopTraversal(MachineLoop &ML, MachineLoopInfo &MLI)
+      : ML(ML), MLI(MLI) { }
+
+    const SmallVectorImpl<MachineBasicBlock*> &getOrder() const {
+      return Order;
+    }
+
+    // Visit all the blocks within the loop, as well as exit blocks and any
+    // blocks properly dominating the header.
+    void ProcessLoop() {
+      std::function<void(MachineBasicBlock*)> Search = [this, &Search]
+        (MachineBasicBlock *MBB) -> void {
+        if (Visited.count(MBB))
+          return;
+
+        Visited.insert(MBB);
+        for (auto *Succ : MBB->successors()) {
+          if (!ML.contains(Succ))
+            continue;
+          Search(Succ);
+        }
+        Order.push_back(MBB);
+      };
+
+      // Insert exit blocks.
+      SmallVector<MachineBasicBlock*, 2> ExitBlocks;
+      ML.getExitBlocks(ExitBlocks);
+      for (auto *MBB : ExitBlocks)
+        Order.push_back(MBB);
+
+      // Then add the loop body.
+      Search(ML.getHeader());
+
+      // Then try the preheader and its predecessors.
+      std::function<void(MachineBasicBlock*)> GetPredecessor =
+        [this, &GetPredecessor] (MachineBasicBlock *MBB) -> void {
+        Order.push_back(MBB);
+        if (MBB->pred_size() == 1)
+          GetPredecessor(*MBB->pred_begin());
+      };
+
+      if (auto *Preheader = ML.getLoopPreheader())
+        GetPredecessor(Preheader);
+      else if (auto *Preheader = MLI.findLoopPreheader(&ML, true))
+        GetPredecessor(Preheader);
+    }
+  };
+
   struct PredicatedMI {
     MachineInstr *MI = nullptr;
     SetVector<MachineInstr*> Predicates;
@@ -976,6 +1031,15 @@
       ConvertVPTBlocks(LoLoop);
     }
   }
+
+  PostOrderLoopTraversal DFS(*LoLoop.ML, *MLI);
+  DFS.ProcessLoop();
+  const SmallVectorImpl<MachineBasicBlock*> &PostOrder = DFS.getOrder();
+  for (auto *MBB : PostOrder)
+    recomputeLiveIns(*MBB);
+
+  for (auto *MBB : reverse(PostOrder))
+    recomputeLivenessFlags(*MBB);
 }
 
 bool ARMLowOverheadLoops::RevertNonLoops() {
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/disjoint-vcmp.mir
@@ -1,8 +1,8 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 # RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops --verify-machineinstrs %s -o - | FileCheck %s
+#
 --- |
   @mask = external global i16
-  ; Function Attrs: nofree norecurse nounwind
   define dso_local void @test(i32* noalias nocapture %arg, i32* noalias nocapture readonly %arg1, i32 %arg2, i32* noalias nocapture readonly %arg3) local_unnamed_addr #0 {
   bb:
     %tmp = icmp eq i32 %arg2, 0
@@ -16,8 +16,6 @@
     %mask.load = load i16, i16* %mask.gep9
     %conv.mask = zext i16 %mask.load to i32
     %invariant.mask = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %conv.mask)
-    %mask.insert = insertelement <4 x i32> undef, i32 %conv.mask, i32 0
-    %invariant.limits = shufflevector <4 x i32> %mask.insert, <4 x i32> undef, <4 x i32> zeroinitializer
     br i1 %tmp, label %bb27, label %bb3
 
   bb3:                                              ; preds = %bb
@@ -31,18 +29,20 @@
     %lsr.iv = phi i32* [ %scevgep, %bb9 ], [ %arg, %bb3 ]
     %tmp7 = phi i32 [ %tmp6, %bb3 ], [ %tmp12, %bb9 ]
     %tmp8 = phi i32 [ %arg2, %bb3 ], [ %tmp11, %bb9 ]
-    %lsr.iv47 = bitcast i32* %lsr.iv4 to <4 x i32>*
     %lsr.iv1 = bitcast i32* %lsr.iv to <4 x i32>*
     %lsr.iv24 = bitcast i32* %lsr.iv2 to <4 x i32>*
+    %lsr.iv47 = bitcast i32* %lsr.iv4 to <4 x i32>*
     %vctp = call <4 x i1> @llvm.arm.mve.vctp32(i32 %tmp8)
     %and = and <4 x i1> %vctp, %invariant.mask
     %tmp11 = sub i32 %tmp8, 4
     %tmp17 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv24, i32 4, <4 x i1> %and, <4 x i32> undef)
     %tmp22 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv1, i32 4, <4 x i1> %and, <4 x i32> undef)
     %tmp23 = mul nsw <4 x i32> %tmp22, %tmp17
-    %scevgep8 = getelementptr <4 x i32>, <4 x i32>* %lsr.iv47, i32 1
-    %load.limits = load <4 x i32>, <4 x i32>* %scevgep8
-    %bad.icmp = icmp ule <4 x i32> %load.limits, %invariant.limits
+    %scevgep2 = getelementptr <4 x i32>, <4 x i32>* %lsr.iv47, i32 1
+    %load.limits = load <4 x i32>, <4 x i32>* %scevgep2
+    %0 = insertelement <4 x i32> undef, i32 %conv.mask, i32 0
+    %1 = shufflevector <4 x i32> %0, <4 x i32> undef, <4 x i32> zeroinitializer
+    %bad.icmp = icmp ule <4 x i32> %load.limits, %1
     call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %tmp23, <4 x i32>* %lsr.iv1, i32 4, <4 x i1> %bad.icmp)
     %tmp12 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp7, i32 1)
     %tmp13 = icmp ne i32 %tmp12, 0
@@ -54,13 +54,12 @@
   bb27:                                             ; preds = %bb9, %bb
     ret void
   }
-  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #1
-  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #2
-  declare void @llvm.set.loop.iterations.i32(i32) #3
-  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
-  declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4
-  declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #4
-  declare void @llvm.stackprotector(i8*, i8**) #5
+  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
+  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
+  declare void @llvm.set.loop.iterations.i32(i32)
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
+  declare <4 x i1> @llvm.arm.mve.vctp32(i32)
+  declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32)
 
 ...
 ---
@@ -85,7 +84,7 @@
   hasStackMap:     false
   hasPatchPoint:   false
   stackSize:       20
-  offsetAdjustment: -12
+  offsetAdjustment: 0
   maxAlignment:    4
   adjustsStack:    false
   hasCalls:        false
@@ -110,7 +109,7 @@
       stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
       debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
   - { id: 3, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
-      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
+      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
       debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
   - { id: 4, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
       stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
@@ -122,37 +121,36 @@
   ; CHECK-LABEL: name: test
   ; CHECK: bb.0.bb:
   ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $r6, $lr
-  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   liveins: $r3, $r2, $r0, $r1, $r4, $r5, $r7, $lr
+  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 16
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
-  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -12
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -16
-  ; CHECK:   $r7 = frame-setup tADDrSPi $sp, 2, 14, $noreg
-  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
   ; CHECK:   $sp = frame-setup tSUBspi $sp, 1, 14, $noreg
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
   ; CHECK:   tCBZ $r2, %bb.3
   ; CHECK: bb.1.bb3:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $r3, $r2, $r0, $r1
   ; CHECK:   $r12 = t2MOVi16 target-flags(arm-lo16) @mask, 14, $noreg
-  ; CHECK:   renamable $lr = t2ADDri renamable $r2, 3, 14, $noreg, $noreg
+  ; CHECK:   renamable $r4, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg
   ; CHECK:   $r12 = t2MOVTi16 killed $r12, target-flags(arm-hi16) @mask, 14, $noreg
-  ; CHECK:   renamable $lr = t2BICri killed renamable $lr, 3, 14, $noreg, $noreg
-  ; CHECK:   renamable $r12 = t2LDRHi12 killed renamable $r12, 0, 14, $noreg :: (dereferenceable load 2 from %ir.mask.gep9)
-  ; CHECK:   renamable $lr = t2SUBri killed renamable $lr, 4, 14, $noreg, $noreg
+  ; CHECK:   renamable $r4 = t2BICri killed renamable $r4, 3, 14, $noreg, $noreg
+  ; CHECK:   renamable $r5 = t2LDRHi12 killed renamable $r12, 0, 14, $noreg :: (dereferenceable load 2 from %ir.mask.gep9)
+  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r4, 4, 14, $noreg, $noreg
   ; CHECK:   renamable $r4, dead $cpsr = tMOVi8 1, 14, $noreg
-  ; CHECK:   $vpr = VMSR_P0 $r12, 14, $noreg
-  ; CHECK:   renamable $q0 = MVE_VDUP32 killed renamable $r12, 0, $noreg, undef renamable $q0
+  ; CHECK:   $vpr = VMSR_P0 $r5, 14, $noreg
+  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $r12, 19, 14, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 16, 14, $noreg, $noreg
-  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14, $noreg, $noreg
   ; CHECK:   VSTR_P0_off killed renamable $vpr, $sp, 0, 14, $noreg :: (store 4 into %stack.0)
+  ; CHECK:   renamable $q0 = MVE_VDUP32 killed renamable $r5, 0, $noreg, undef renamable $q0
   ; CHECK:   $r3 = tMOVr $r0, 14, $noreg
-  ; CHECK:   $lr = t2DLS renamable $lr
+  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
-  ; CHECK:   liveins: $lr, $q0, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   liveins: $lr, $r2, $r12, $r0, $q0, $r1, $r3
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 2, implicit $vpr
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr
@@ -160,28 +158,26 @@
   ; CHECK:   renamable $r3, renamable $q2 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4)
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg
   ; CHECK:   renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
-  ; CHECK:   renamable $r12, renamable $q2 = MVE_VLDRWU32_pre killed renamable $r12, 16, 0, $noreg :: (load 16 from %ir.scevgep8, align 8)
-  ; CHECK:   renamable $vpr = MVE_VCMPu32 renamable $q0, killed renamable $q2, 2, 0, $noreg
-  ; CHECK:   MVE_VPST 8, implicit $vpr
+  ; CHECK:   renamable $r12, renamable $q2 = MVE_VLDRWU32_pre killed renamable $r12, 16, 0, $noreg :: (load 16 from %ir.scevgep2, align 8)
+  ; CHECK:   MVE_VPTv4u32 8, renamable $q0, killed renamable $q2, 2, implicit-def $vpr
   ; CHECK:   MVE_VSTRWU32 killed renamable $q1, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 4)
   ; CHECK:   $r0 = tMOVr $r3, 14, $noreg
-  ; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
   ; CHECK: bb.3.bb27:
   ; CHECK:   $sp = tADDspi $sp, 1, 14, $noreg
-  ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $r6, def $r7, def $pc
+  ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $r5, def $r7, def $pc
   bb.0.bb:
     successors: %bb.3(0x30000000), %bb.1(0x50000000)
-    liveins: $r0, $r1, $r2, $r3, $r4, $r6, $lr
+    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r7, $lr
 
-    frame-setup tPUSH 14, $noreg, killed $r4, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r7, killed $lr, implicit-def $sp, implicit $sp
     frame-setup CFI_INSTRUCTION def_cfa_offset 16
     frame-setup CFI_INSTRUCTION offset $lr, -4
     frame-setup CFI_INSTRUCTION offset $r7, -8
-    frame-setup CFI_INSTRUCTION offset $r6, -12
+    frame-setup CFI_INSTRUCTION offset $r5, -12
     frame-setup CFI_INSTRUCTION offset $r4, -16
-    $r7 = frame-setup tADDrSPi $sp, 2, 14, $noreg
-    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
     $sp = frame-setup tSUBspi $sp, 1, 14, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa_offset 20
     tCBZ $r2, %bb.3
 
   bb.1.bb3:
@@ -189,17 +185,17 @@
     liveins: $r0, $r1, $r2, $r3
 
     $r12 = t2MOVi16 target-flags(arm-lo16) @mask, 14, $noreg
-    renamable $lr = t2ADDri renamable $r2, 3, 14, $noreg, $noreg
+    renamable $r4, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg
     $r12 = t2MOVTi16 killed $r12, target-flags(arm-hi16) @mask, 14, $noreg
-    renamable $lr = t2BICri killed renamable $lr, 3, 14, $noreg, $noreg
-    renamable $r12 = t2LDRHi12 killed renamable $r12, 0, 14, $noreg :: (dereferenceable load 2 from %ir.mask.gep9)
-    renamable $lr = t2SUBri killed renamable $lr, 4, 14, $noreg, $noreg
+    renamable $r4 = t2BICri killed renamable $r4, 3, 14, $noreg, $noreg
+    renamable $r5 = t2LDRHi12 killed renamable $r12, 0, 14, $noreg :: (dereferenceable load 2 from %ir.mask.gep9)
+    renamable $r12 = t2SUBri killed renamable $r4, 4, 14, $noreg, $noreg
     renamable $r4, dead $cpsr = tMOVi8 1, 14, $noreg
-    $vpr = VMSR_P0 $r12, 14, $noreg
-    renamable $q0 = MVE_VDUP32 killed renamable $r12, 0, $noreg, undef renamable $q0
+    $vpr = VMSR_P0 $r5, 14, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $r12, 19, 14, $noreg, $noreg
     renamable $r12 = t2SUBri killed renamable $r3, 16, 14, $noreg, $noreg
-    renamable $lr = nuw nsw t2ADDrs killed renamable $r4, killed renamable $lr, 19, 14, $noreg, $noreg
     VSTR_P0_off killed renamable $vpr, $sp, 0, 14, $noreg :: (store 4 into %stack.0)
+    renamable $q0 = MVE_VDUP32 killed renamable $r5, 0, $noreg, undef renamable $q0
     $r3 = tMOVr $r0, 14, $noreg
     t2DoLoopStart renamable $lr
 
@@ -214,9 +210,8 @@
     renamable $r3, renamable $q2 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4)
     renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg
     renamable $q1 = nsw MVE_VMULi32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
-    renamable $r12, renamable $q2 = MVE_VLDRWU32_pre killed renamable $r12, 16, 0, $noreg :: (load 16 from %ir.scevgep8, align 8)
-    renamable $vpr = MVE_VCMPu32 renamable $q0, killed renamable $q2, 2, 0, $noreg
-    MVE_VPST 8, implicit $vpr
+    renamable $r12, renamable $q2 = MVE_VLDRWU32_pre killed renamable $r12, 16, 0, $noreg :: (load 16 from %ir.scevgep2, align 8)
+    MVE_VPTv4u32 8, renamable $q0, killed renamable $q2, 2, implicit-def $vpr
     MVE_VSTRWU32 killed renamable $q1, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 4)
     renamable $lr = t2LoopDec killed renamable $lr, 1
     $r0 = tMOVr $r3, 14, $noreg
@@ -225,6 +220,6 @@
 
   bb.3.bb27:
     $sp = tADDspi $sp, 1, 14, $noreg
-    tPOP_RET 14, $noreg, def $r4, def $r6, def $r7, def $pc
+    tPOP_RET 14, $noreg, def $r4, def $r5, def $r7, def $pc
 
 ...
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update.mir
@@ -6,7 +6,7 @@
 # CHECK:  bb.1.vector.body:
 # CHECK:    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
 # CHECK:    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
-# CHECK:    $lr = MVE_LETP renamable $lr, %bb.1
+# CHECK:    $lr = MVE_LETP killed renamable $lr, %bb.1
 
 --- |
   target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update2.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update2.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update2.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update2.mir
@@ -7,8 +7,8 @@
 # We shouldn't optimise away the SUB.
 
 # CHECK:  bb.1.vector.body:
-# CHECK:    renamable $r3, $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
-# CHECK:    $lr = MVE_LETP renamable $lr, %bb.1
+# CHECK:    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
+# CHECK:    $lr = MVE_LETP killed renamable $lr, %bb.1
 
 --- |
   target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update3.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update3.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update3.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/dont-remove-loop-update3.mir
@@ -8,7 +8,7 @@
 
 # CHECK:  bb.1.vector.body:
 # CHECK:    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
-# CHECK:    $lr = MVE_LETP renamable $lr, %bb.1
+# CHECK:    $lr = MVE_LETP killed renamable $lr, %bb.1
 
 --- |
   target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/loop-guards.ll
@@ -18,9 +18,9 @@
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.3
 ; CHECK: bb.1.while.body.preheader:
-; CHECK:   $lr = t2DLS renamable $lr
+; CHECK:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.2.while.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
 define void @ne_and_guard(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
@@ -51,9 +51,9 @@
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.3
 ; CHECK: bb.1.while.body.preheader:
-; CHECK:   $lr = t2DLS renamable $lr
+; CHECK:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.2.while.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
 define void @ne_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
@@ -86,9 +86,9 @@
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.3
 ; CHECK: bb.1.while.body.preheader:
-; CHECK:   $lr = t2DLS renamable $lr
+; CHECK:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.2.while.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
 define void @eq_preheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %brmerge.demorgan = and i1 %t1, %t2
@@ -121,9 +121,9 @@
 ; CHECK:   t2CMPri renamable $lr, 0
 ; CHECK:   tBcc %bb.3
 ; CHECK: bb.1.while.body.preheader:
-; CHECK:   $lr = t2DLS renamable $lr
+; CHECK:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.2.while.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
 define void @ne_prepreheader(i1 zeroext %t1, i1 zeroext %t2, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %cmp = icmp ne i32 %N, 0
@@ -152,9 +152,9 @@
 ; CHECK: be_ne
 ; CHECK: body:
 ; CHECK: bb.0.entry:
-; CHECK:   $lr = t2DLS renamable $lr
+; CHECK:   $lr = t2DLS killed renamable $lr
 ; CHECK: bb.1.do.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.1
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.1
 define void @be_ne(i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   %cmp = icmp ne i32 %N, 0
@@ -187,7 +187,7 @@
 ; CHECK: bb.1.do.body.preheader:
 ; CHECK:   $lr = tMOVr
 ; CHECK: bb.2.do.body:
-; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
 define void @ne_trip_count(i1 zeroext %t1, i32* nocapture %a, i32* nocapture readonly %b, i32 %N) {
 entry:
   br label %do.body.preheader
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-lr-terminator.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-lr-terminator.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-lr-terminator.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mov-lr-terminator.mir
@@ -100,7 +100,7 @@
   ; CHECK-LABEL: name: start_before_elems
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $lr
+  ; CHECK:   liveins: $r1, $r0, $r2, $r3, $r4, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -114,7 +114,7 @@
   ; CHECK:   $lr = MVE_DLSTP_32 renamable $r12
   ; CHECK: bb.1.vector.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   liveins: $lr, $r0, $r12, $r2, $r3, $r1
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r3, 14, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep45, align 1)
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r2, renamable $r3, 14, $noreg
@@ -123,7 +123,7 @@
   ; CHECK:   renamable $q1 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep23, align 1)
   ; CHECK:   renamable $q0 = nuw nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r0 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r0, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv1, align 4)
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.1
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
   ; CHECK: bb.2.for.cond.cleanup:
   ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $pc
   bb.0.entry:
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-def-before-start.mir
@@ -107,7 +107,7 @@
   ; CHECK-LABEL: name: start_before_elems
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $lr
+  ; CHECK:   liveins: $r1, $r0, $r2, $r3, $r4, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -122,7 +122,7 @@
   ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14, $noreg
   ; CHECK: bb.1.vector.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   liveins: $lr, $r0, $r12, $r2, $r3, $r1
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r3, 14, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep45, align 1)
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r2, renamable $r3, 14, $noreg
@@ -131,7 +131,7 @@
   ; CHECK:   renamable $q1 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep23, align 1)
   ; CHECK:   renamable $q0 = nuw nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r0 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r0, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv1, align 4)
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.1
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
   ; CHECK: bb.2.for.cond.cleanup:
   ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $pc
   bb.0.entry:
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/move-start-after-def.mir
@@ -105,7 +105,7 @@
   ; CHECK-LABEL: name: start_before_elems
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $lr
+  ; CHECK:   liveins: $r1, $r0, $r2, $r3, $r4, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -120,7 +120,7 @@
   ; CHECK:   $lr = MVE_DLSTP_32 renamable $r12
   ; CHECK: bb.1.vector.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   liveins: $lr, $r0, $r12, $r2, $r3, $r1
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r3, 14, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep45, align 1)
   ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r2, renamable $r3, 14, $noreg
@@ -129,7 +129,7 @@
   ; CHECK:   renamable $q1 = MVE_VLDRBU32 killed renamable $r4, 0, 0, $noreg :: (load 4 from %ir.scevgep23, align 1)
   ; CHECK:   renamable $q0 = nuw nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
   ; CHECK:   renamable $r0 = MVE_VSTRWU32_post killed renamable $q0, killed renamable $r0, 16, 0, killed $noreg :: (store 16 into %ir.lsr.iv1, align 4)
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.1
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
   ; CHECK: bb.2.for.cond.cleanup:
   ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $pc
   bb.0.entry:
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/unsafe-cpsr-loop-use.mir
@@ -94,7 +94,7 @@
   ; CHECK-LABEL: name: do_copy
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r7, $lr
+  ; CHECK:   liveins: $r2, $r1, $r7, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -102,18 +102,19 @@
   ; CHECK:   renamable $r0, dead $cpsr = tSUBi3 killed renamable $r1, 4, 14, $noreg
   ; CHECK:   renamable $r1, dead $cpsr = tSUBi3 killed renamable $r2, 4, 14, $noreg
   ; CHECK:   renamable $r2 = t2LSRri renamable $r0, 1, 14, $noreg, $noreg
-  ; CHECK:   $lr = tMOVr killed $r0, 14, $noreg
+  ; CHECK:   $lr = tMOVr $r0, 14, $noreg
   ; CHECK: bb.1.while.body:
   ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2
+  ; CHECK:   liveins: $lr, $r0, $r2, $r1
   ; CHECK:   renamable $r3, renamable $r1 = t2LDR_PRE killed renamable $r1, 4, 14, $noreg :: (load 4 from %ir.scevgep7)
   ; CHECK:   tCMPhir renamable $lr, renamable $r2, 14, $noreg, implicit-def $cpsr
   ; CHECK:   $lr = t2SUBri killed renamable $lr, 1, 14, $noreg, $noreg
   ; CHECK:   t2IT 2, 8, implicit-def $itstate
-  ; CHECK:   renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit renamable $r3, implicit killed $itstate
+  ; CHECK:   renamable $r3 = tLSRri $noreg, killed renamable $r3, 1, 2, killed $cpsr, implicit killed renamable $r3, implicit killed $itstate
   ; CHECK:   early-clobber renamable $r0 = t2STR_PRE killed renamable $r3, killed renamable $r0, 4, 14, $noreg :: (store 4 into %ir.scevgep4)
+  ; CHECK:   renamable $lr = tMOVr killed $lr, 14, $noreg
   ; CHECK:   t2CMPri $lr, 0, 14, $noreg, implicit-def $cpsr
-  ; CHECK:   tBcc %bb.1, 1, $cpsr
+  ; CHECK:   tBcc %bb.1, 1, killed $cpsr
   ; CHECK:   tB %bb.2, 14, $noreg
   ; CHECK: bb.2.while.end:
   ; CHECK:   $r0, dead $cpsr = tMOVi8 0, 14, $noreg
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt-2.mir
@@ -134,7 +134,7 @@
   ; CHECK-LABEL: name: test
   ; CHECK: bb.0.bb:
   ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $lr
+  ; CHECK:   liveins: $r1, $r2, $r0, $r3, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -145,7 +145,7 @@
   ; CHECK:   tCBZ $r2, %bb.3
   ; CHECK: bb.1.bb3:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $r1, $r2, $r0, $r3
   ; CHECK:   renamable $r12 = t2ADDri renamable $r2, 3, 14, $noreg, $noreg
   ; CHECK:   renamable $lr = t2MOVi 1, 14, $noreg, $noreg
   ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 3, 14, $noreg, $noreg
@@ -154,10 +154,10 @@
   ; CHECK:   VSTR_P0_off killed renamable $vpr, $sp, 0, 14, $noreg :: (store 4 into %stack.0)
   ; CHECK:   $r3 = tMOVr $r0, 14, $noreg
   ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 19, 14, $noreg, $noreg
-  ; CHECK:   $lr = t2DLS renamable $lr
+  ; CHECK:   $lr = t2DLS killed renamable $lr
   ; CHECK: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $lr, $r2, $r3, $r0, $r1
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $vpr = MVE_VCTP32 renamable $r2, 1, killed renamable $vpr
@@ -171,7 +171,7 @@
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 4, !tbaa !3)
   ; CHECK:   $r0 = tMOVr $r3, 14, $noreg
-  ; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
   ; CHECK: bb.3.bb27:
   ; CHECK:   $sp = tADDspi $sp, 1, 14, $noreg
   ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/vctp-in-vpt.mir
@@ -131,7 +131,7 @@
   ; CHECK-LABEL: name: test
   ; CHECK: bb.0.bb:
   ; CHECK:   successors: %bb.3(0x30000000), %bb.1(0x50000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $lr
+  ; CHECK:   liveins: $r0, $r2, $r1, $r3, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -142,14 +142,14 @@
   ; CHECK:   tCBZ $r2, %bb.3
   ; CHECK: bb.1.bb3:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $r0, $r2, $r1, $r3
   ; CHECK:   $vpr = VMSR_P0 killed $r3, 14, $noreg
   ; CHECK:   VSTR_P0_off killed renamable $vpr, $sp, 0, 14, $noreg :: (store 4 into %stack.0)
   ; CHECK:   $r3 = tMOVr $r0, 14, $noreg
-  ; CHECK:   $lr = MVE_DLSTP_32 renamable $r2
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r2
   ; CHECK: bb.2.bb9:
   ; CHECK:   successors: %bb.2(0x7c000000), %bb.3(0x04000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $lr, $r3, $r1, $r0
   ; CHECK:   renamable $vpr = VLDR_P0_off $sp, 0, 14, $noreg :: (load 4 from %stack.0)
   ; CHECK:   MVE_VPST 4, implicit $vpr
   ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4, !tbaa !3)
@@ -158,7 +158,7 @@
   ; CHECK:   MVE_VPST 8, implicit $vpr
   ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 4, !tbaa !3)
   ; CHECK:   $r0 = tMOVr $r3, 14, $noreg
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.2
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
   ; CHECK: bb.3.bb27:
   ; CHECK:   $sp = tADDspi $sp, 1, 14, $noreg
   ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/while.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/while.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/while.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/while.mir
@@ -1,6 +1,5 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 # RUN: llc -mtriple=thumbv8.1m.main -mattr=+lob %s -run-pass=arm-low-overhead-loops --verify-machineinstrs -o - | FileCheck %s
-
 # TODO: Remove the lr = tMOVr
 
 --- |
@@ -91,15 +90,15 @@
   ; CHECK-LABEL: name: copy
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.1(0x40000000), %bb.3(0x40000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r7, $lr
+  ; CHECK:   liveins: $r0, $r2, $r1, $r7, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
-  ; CHECK:   $lr = t2WLS $r2, %bb.3
+  ; CHECK:   dead $lr = t2WLS $r2, %bb.3
   ; CHECK: bb.1.while.body.preheader:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $r0, $r1, $r2
+  ; CHECK:   liveins: $r0, $r2, $r1
   ; CHECK:   renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 2, 14, $noreg
   ; CHECK:   renamable $r0, dead $cpsr = tSUBi8 killed renamable $r0, 2, 14, $noreg
   ; CHECK:   $lr = tMOVr killed $r2, 14, $noreg
@@ -108,7 +107,7 @@
   ; CHECK:   liveins: $lr, $r0, $r1
   ; CHECK:   renamable $r2, renamable $r1 = t2LDRH_PRE killed renamable $r1, 2, 14, $noreg :: (load 2 from %ir.scevgep4)
   ; CHECK:   early-clobber renamable $r0 = t2STRH_PRE killed renamable $r2, killed renamable $r0, 2, 14, $noreg :: (store 2 into %ir.scevgep7)
-  ; CHECK:   $lr = t2LEUpdate renamable $lr, %bb.2
+  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.2
   ; CHECK: bb.3.while.end:
   ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc
   bb.0.entry:
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir
@@ -199,11 +199,11 @@
   ; CHECK:   tB %bb.3, 14, $noreg
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $lr, $r1, $r2, $r3, $r0
   ; CHECK:   renamable $r12 = t2MOVi 0, 14, $noreg, $noreg
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.3(0x04000000), %bb.2(0x7c000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   liveins: $lr, $r12, $r2, $r3, $r0, $r1
   ; CHECK:   renamable $r4 = t2ADDrr renamable $r1, renamable $r12, 14, $noreg, $noreg
   ; CHECK:   renamable $q0 = MVE_VLDRBU8 killed renamable $r4, 0, 0, $noreg :: (load 16 from %ir.scevgep45, align 1)
   ; CHECK:   renamable $r4 = t2ADDrr renamable $r2, renamable $r12, 14, $noreg, $noreg
@@ -213,7 +213,7 @@
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14, $noreg
   ; CHECK:   renamable $q0 = MVE_VMULi8 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
   ; CHECK:   MVE_VSTRBU8 killed renamable $q0, killed renamable $r4, 0, 0, killed $noreg :: (store 16 into %ir.scevgep1, align 1)
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.2
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
   ; CHECK: bb.3.for.cond.cleanup:
   ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $pc
   bb.0.entry:
@@ -313,7 +313,7 @@
   ; CHECK-LABEL: name: test_wlstp16
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r7, $lr
+  ; CHECK:   liveins: $r1, $r3, $r0, $r2, $r7, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -322,7 +322,7 @@
   ; CHECK:   tB %bb.2, 14, $noreg
   ; CHECK: bb.1.vector.body:
   ; CHECK:   successors: %bb.2(0x04000000), %bb.1(0x7c000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   liveins: $lr, $r3, $r0, $r2, $r1
   ; CHECK:   renamable $q0 = MVE_VLDRHU16 renamable $r1, 0, 0, $noreg :: (load 16 from %ir.lsr.iv57, align 2)
   ; CHECK:   renamable $q1 = MVE_VLDRHU16 renamable $r2, 0, 0, $noreg :: (load 16 from %ir.lsr.iv24, align 2)
   ; CHECK:   renamable $q0 = MVE_VMULi16 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
@@ -331,7 +331,7 @@
   ; CHECK:   renamable $r2, dead $cpsr = tADDi8 killed renamable $r2, 16, 14, $noreg
   ; CHECK:   renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg
   ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 8, 14, $noreg
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.1
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
   ; CHECK: bb.2.for.cond.cleanup:
   ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc
   bb.0.entry:
@@ -422,7 +422,7 @@
   ; CHECK-LABEL: name: test_wlstp32
   ; CHECK: bb.0.entry:
   ; CHECK:   successors: %bb.4(0x40000000), %bb.1(0x40000000)
-  ; CHECK:   liveins: $r0, $r1, $r2, $r7, $lr
+  ; CHECK:   liveins: $r1, $r2, $r0, $r7, $lr
   ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
   ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
@@ -432,12 +432,12 @@
   ; CHECK:   tB %bb.4, 14, $noreg
   ; CHECK: bb.1.vector.ph:
   ; CHECK:   successors: %bb.2(0x80000000)
-  ; CHECK:   liveins: $lr, $r0, $r1, $r2
+  ; CHECK:   liveins: $r2, $r0, $lr, $r1
   ; CHECK:   renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
   ; CHECK: bb.2.vector.body:
   ; CHECK:   successors: %bb.3(0x04000000), %bb.2(0x7c000000)
-  ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
-  ; CHECK:   $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0
+  ; CHECK:   liveins: $r2, $r0, $lr, $r1, $q1
+  ; CHECK:   $q0 = MVE_VORR killed $q1, killed $q1, 0, $noreg, undef $q0
   ; CHECK:   renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 0, $noreg :: (load 16 from %ir.lsr.iv24, align 4)
   ; CHECK:   renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 0, killed $noreg :: (load 16 from %ir.lsr.iv1, align 4)
   ; CHECK:   $r3 = tMOVr $r2, 14, $noreg
@@ -446,10 +446,10 @@
   ; CHECK:   renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg
   ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed $r2, 4, 14, $noreg
   ; CHECK:   renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1
-  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.2
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.2
   ; CHECK: bb.3.middle.block:
   ; CHECK:   successors: %bb.4(0x80000000)
-  ; CHECK:   liveins: $q0, $q1, $r3
+  ; CHECK:   liveins: $q1, $q0, $r3
   ; CHECK:   renamable $vpr = MVE_VCTP32 killed renamable $r3, 0, $noreg
   ; CHECK:   renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr
   ; CHECK:   renamable $r12 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg