Index: llvm/lib/Target/ARM/MVETPAndVPTOptimisationsPass.cpp
===================================================================
--- llvm/lib/Target/ARM/MVETPAndVPTOptimisationsPass.cpp
+++ llvm/lib/Target/ARM/MVETPAndVPTOptimisationsPass.cpp
@@ -59,7 +59,7 @@
   }
 
 private:
-  bool RevertLoopWithCall(MachineLoop *ML);
+  bool MergeLoopEnd(MachineLoop *ML);
   bool ConvertTailPredLoop(MachineLoop *ML, MachineDominatorTree *DT);
   MachineInstr &ReplaceRegisterUseWithVPNOT(MachineBasicBlock &MBB,
                                             MachineInstr &Instr,
@@ -158,8 +158,15 @@
   return true;
 }
 
-bool MVETPAndVPTOptimisations::RevertLoopWithCall(MachineLoop *ML) {
-  LLVM_DEBUG(dbgs() << "RevertLoopWithCall on loop " << ML->getHeader()->getName()
+// This function converts loops with t2LoopEnd and t2LoopEnd instructions into
+// a single t2LoopEndDec instruction. To do that it needs to make sure that LR
+// will be valid to be used for the low overhead loop, which means nothing else
+// is using LR (especially calls) and there are no superfluous copies in the
+// loop. The t2LoopEndDec is a branching terminator that produces a value (the
+// decrement) around the loop edge, which means we need to be careful that they
+// will be valid to allocate without any spilling.
+bool MVETPAndVPTOptimisations::MergeLoopEnd(MachineLoop *ML) {
+  LLVM_DEBUG(dbgs() << "MergeLoopEnd on loop " << ML->getHeader()->getName()
                     << "\n");
 
   MachineInstr *LoopEnd, *LoopPhi, *LoopStart, *LoopDec;
@@ -180,7 +187,58 @@
     }
   }
 
-  return false;
+  // Remove any copies from the loop, to ensure the phi that remains is both
+  // simpler and contains no extra uses. Because t2LoopEndDec is a terminator
+  // that cannot spill, we need to be careful what remains in the loop.
+  Register PhiReg = LoopPhi->getOperand(0).getReg();
+  Register DecReg = LoopDec->getOperand(0).getReg();
+  Register StartReg = LoopStart->getOperand(0).getReg();
+  // Ensure the uses are expected, and collect any copies we want to remove.
+  SmallVector<MachineInstr *, 4> Copies;
+  auto CheckUsers = [&Copies](Register BaseReg,
+                              ArrayRef<MachineInstr *> ExpectedUsers,
+                              MachineRegisterInfo *MRI) {
+    SmallVector<Register, 4> Worklist;
+    Worklist.push_back(BaseReg);
+    while (!Worklist.empty()) {
+      Register Reg = Worklist.pop_back_val();
+      for (MachineInstr &MI : MRI->use_nodbg_instructions(Reg)) {
+        if (count(ExpectedUsers, &MI))
+          continue;
+        if (MI.getOpcode() != TargetOpcode::COPY ||
+            !MI.getOperand(0).getReg().isVirtual()) {
+          LLVM_DEBUG(dbgs() << "Extra users of register found: " << MI);
+          return false;
+        }
+        Worklist.push_back(MI.getOperand(0).getReg());
+        Copies.push_back(&MI);
+      }
+    }
+    return true;
+  };
+  if (!CheckUsers(PhiReg, {LoopDec}, MRI) ||
+      !CheckUsers(DecReg, {LoopPhi, LoopEnd}, MRI) ||
+      !CheckUsers(StartReg, {LoopPhi}, MRI))
+    return false;
+
+  MRI->constrainRegClass(StartReg, &ARM::GPRlrRegClass);
+  MRI->constrainRegClass(PhiReg, &ARM::GPRlrRegClass);
+  MRI->constrainRegClass(DecReg, &ARM::GPRlrRegClass);
+
+  if (LoopPhi->getOperand(2).getMBB() == ML->getLoopLatch()) {
+    LoopPhi->getOperand(3).setReg(StartReg);
+    LoopPhi->getOperand(1).setReg(DecReg);
+  } else {
+    LoopPhi->getOperand(1).setReg(StartReg);
+    LoopPhi->getOperand(3).setReg(DecReg);
+  }
+
+  LoopDec->getOperand(1).setReg(PhiReg);
+  LoopEnd->getOperand(0).setReg(DecReg);
+
+  for (auto *MI : Copies)
+    MI->eraseFromParent();
+  return true;
 }
 
 // Convert t2DoLoopStart to t2DoLoopStartTP if the loop contains VCTP
@@ -702,7 +760,7 @@
 
   bool Modified = false;
   for (MachineLoop *ML : MLI->getBase().getLoopsInPreorder()) {
-    Modified |= RevertLoopWithCall(ML);
+    Modified |= MergeLoopEnd(ML);
     Modified |= ConvertTailPredLoop(ML, DT);
   }
 
Index: llvm/test/CodeGen/Thumb2/LowOverheadLoops/count_dominates_start.mir
===================================================================
--- llvm/test/CodeGen/Thumb2/LowOverheadLoops/count_dominates_start.mir
+++ llvm/test/CodeGen/Thumb2/LowOverheadLoops/count_dominates_start.mir
@@ -123,33 +123,31 @@
   ; CHECK:   [[t2MOVi1:%[0-9]+]]:rgpr = t2MOVi 1, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   [[t2ADDrs:%[0-9]+]]:gprnopc = nuw nsw t2ADDrs [[t2MOVi1]], [[t2SUBri]], 27, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   [[COPY4:%[0-9]+]]:rgpr = COPY [[t2ADDrs]]
-  ; CHECK:   [[t2DoLoopStart:%[0-9]+]]:gprlr = t2DoLoopStart [[COPY4]]
   ; CHECK:   [[t2MOVi2:%[0-9]+]]:rgpr = t2MOVi 0, 14 /* CC::al */, $noreg, $noreg
   ; CHECK:   [[COPY5:%[0-9]+]]:gpr = COPY [[t2MOVi2]]
-  ; CHECK:   [[COPY6:%[0-9]+]]:gpr = COPY [[t2DoLoopStart]]
-  ; CHECK:   [[COPY7:%[0-9]+]]:gprnopc = COPY [[COPY]]
+  ; CHECK:   [[COPY6:%[0-9]+]]:rgpr = COPY [[COPY]]
+  ; CHECK:   [[t2DoLoopStartTP:%[0-9]+]]:gprlr = t2DoLoopStartTP [[COPY4]], [[COPY6]]
   ; CHECK: bb.3.vector.body:
   ; CHECK:   successors: %bb.3(0x7c000000), %bb.4(0x04000000)
   ; CHECK:   [[PHI:%[0-9]+]]:gprnopc = PHI [[COPY2]], %bb.2, %10, %bb.3
   ; CHECK:   [[PHI1:%[0-9]+]]:gprnopc = PHI [[COPY1]], %bb.2, %9, %bb.3
   ; CHECK:   [[PHI2:%[0-9]+]]:tgpreven = PHI [[COPY5]], %bb.2, %8, %bb.3
-  ; CHECK:   [[PHI3:%[0-9]+]]:gprlr = PHI [[COPY6]], %bb.2, %11, %bb.3
-  ; CHECK:   [[PHI4:%[0-9]+]]:rgpr = PHI [[COPY7]], %bb.2, %7, %bb.3
+  ; CHECK:   [[PHI3:%[0-9]+]]:gprlr = PHI [[t2DoLoopStartTP]], %bb.2, %33, %bb.3
+  ; CHECK:   [[PHI4:%[0-9]+]]:rgpr = PHI [[COPY6]], %bb.2, %7, %bb.3
   ; CHECK:   [[MVE_VCTP16_:%[0-9]+]]:vccr = MVE_VCTP16 [[PHI4]], 0, $noreg
   ; CHECK:   [[t2SUBri1:%[0-9]+]]:rgpr = t2SUBri [[PHI4]], 8, 14 /* CC::al */, $noreg, $noreg
-  ; CHECK:   [[COPY8:%[0-9]+]]:gpr = COPY [[t2SUBri1]]
+  ; CHECK:   [[COPY7:%[0-9]+]]:gpr = COPY [[t2SUBri1]]
   ; CHECK:   [[MVE_VLDRHU16_post:%[0-9]+]]:rgpr, [[MVE_VLDRHU16_post1:%[0-9]+]]:mqpr = MVE_VLDRHU16_post [[PHI]], 16, 1, [[MVE_VCTP16_]] :: (load 16 from %ir.lsr.iv35, align 2)
   ; CHECK:   [[MVE_VLDRHU16_post2:%[0-9]+]]:rgpr, [[MVE_VLDRHU16_post3:%[0-9]+]]:mqpr = MVE_VLDRHU16_post [[PHI1]], 16, 1, [[MVE_VCTP16_]] :: (load 16 from %ir.lsr.iv12, align 2)
   ; CHECK:   [[MVE_VMLADAVas16_:%[0-9]+]]:tgpreven = MVE_VMLADAVas16 [[PHI2]], killed [[MVE_VLDRHU16_post3]], killed [[MVE_VLDRHU16_post1]], 1, [[MVE_VCTP16_]]
-  ; CHECK:   [[COPY9:%[0-9]+]]:gpr = COPY [[MVE_VMLADAVas16_]]
-  ; CHECK:   [[COPY10:%[0-9]+]]:gpr = COPY [[MVE_VLDRHU16_post2]]
-  ; CHECK:   [[COPY11:%[0-9]+]]:gpr = COPY [[MVE_VLDRHU16_post]]
+  ; CHECK:   [[COPY8:%[0-9]+]]:gpr = COPY [[MVE_VMLADAVas16_]]
+  ; CHECK:   [[COPY9:%[0-9]+]]:gpr = COPY [[MVE_VLDRHU16_post2]]
+  ; CHECK:   [[COPY10:%[0-9]+]]:gpr = COPY [[MVE_VLDRHU16_post]]
   ; CHECK:   [[t2LoopDec:%[0-9]+]]:gprlr = t2LoopDec [[PHI3]], 1
-  ; CHECK:   [[COPY12:%[0-9]+]]:gpr = COPY [[t2LoopDec]]
   ; CHECK:   t2LoopEnd [[t2LoopDec]], %bb.3, implicit-def dead $cpsr
   ; CHECK:   t2B %bb.4, 14 /* CC::al */, $noreg
   ; CHECK: bb.4.for.cond.cleanup:
-  ; CHECK:   [[PHI5:%[0-9]+]]:gpr = PHI [[COPY3]], %bb.1, [[COPY9]], %bb.3
+  ; CHECK:   [[PHI5:%[0-9]+]]:gpr = PHI [[COPY3]], %bb.1, [[COPY8]], %bb.3
   ; CHECK:   $r0 = COPY [[PHI5]]
   ; CHECK:   tBX_RET 14 /* CC::al */, $noreg, implicit $r0
   bb.0.entry:
Index: llvm/test/CodeGen/Thumb2/mve-fma-loops.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-fma-loops.ll
+++ llvm/test/CodeGen/Thumb2/mve-fma-loops.ll
@@ -323,15 +323,16 @@
 define arm_aapcs_vfpcc void @fmss2(float* nocapture readonly %x, float* nocapture readonly %y, float* noalias nocapture %z, float %a, i32 %n) {
 ; CHECK-LABEL: fmss2:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    .save {r4, r5, r6, lr}
-; CHECK-NEXT:    push {r4, r5, r6, lr}
+; CHECK-NEXT:    .save {r4, lr}
+; CHECK-NEXT:    push {r4, lr}
 ; CHECK-NEXT:    cmp r3, #1
-; CHECK-NEXT:    blt .LBB5_3
-; CHECK-NEXT:  @ %bb.1: @ %vector.ph
-; CHECK-NEXT:    vmov r6, s0
-; CHECK-NEXT:    vdup.32 q0, r6
-; CHECK-NEXT:    mov.w r12, #0
+; CHECK-NEXT:    it lt
+; CHECK-NEXT:    poplt {r4, pc}
+; CHECK-NEXT:  .LBB5_1: @ %vector.ph
+; CHECK-NEXT:    vmov lr, s0
+; CHECK-NEXT:    vdup.32 q0, lr
 ; CHECK-NEXT:    vneg.f32 q0, q0
+; CHECK-NEXT:    mov.w r12, #0
 ; CHECK-NEXT:    dlstp.32 lr, r3
 ; CHECK-NEXT:  .LBB5_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
@@ -342,8 +343,8 @@
 ; CHECK-NEXT:    vfma.f32 q3, q2, q1
 ; CHECK-NEXT:    vstrw.32 q3, [r2], #16
 ; CHECK-NEXT:    letp lr, .LBB5_2
-; CHECK-NEXT:  .LBB5_3: @ %for.cond.cleanup
-; CHECK-NEXT:    pop {r4, r5, r6, pc}
+; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
+; CHECK-NEXT:    pop {r4, pc}
 entry:
   %cmp8 = icmp sgt i32 %n, 0
   br i1 %cmp8, label %vector.ph, label %for.cond.cleanup
Index: llvm/test/CodeGen/Thumb2/mve-gather-scatter-tailpred.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-gather-scatter-tailpred.ll
+++ llvm/test/CodeGen/Thumb2/mve-gather-scatter-tailpred.ll
@@ -157,10 +157,10 @@
 ; CHECK-NEXT:    vldrw.u32 q0, [r0]
 ; CHECK-NEXT:    movw lr, #1250
 ; CHECK-NEXT:    vmov.i32 q1, #0x0
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    vmov.i32 q2, #0x3
 ; CHECK-NEXT:    vadd.i32 q0, q0, r1
 ; CHECK-NEXT:    adds r1, r3, #4
-; CHECK-NEXT:    vmov.i32 q2, #0x3
+; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vctp.32 r3
@@ -231,65 +231,55 @@
 ; CHECK-NEXT:    cmp r2, #0
 ; CHECK-NEXT:    beq.w .LBB3_3
 ; CHECK-NEXT:  @ %bb.1: @ %vector.ph
-; CHECK-NEXT:    adds r3, r2, #3
-; CHECK-NEXT:    adr r7, .LCPI3_5
-; CHECK-NEXT:    bic r3, r3, #3
 ; CHECK-NEXT:    vmov.i32 q0, #0x8000
-; CHECK-NEXT:    sub.w r12, r3, #4
-; CHECK-NEXT:    movs r3, #1
-; CHECK-NEXT:    adr r6, .LCPI3_4
-; CHECK-NEXT:    adr r5, .LCPI3_3
-; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    adr r4, .LCPI3_2
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    adr r7, .LCPI3_5
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #160] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r7]
-; CHECK-NEXT:    adr.w r8, .LCPI3_1
-; CHECK-NEXT:    adr.w r12, .LCPI3_0
-; CHECK-NEXT:    adr r3, .LCPI3_6
+; CHECK-NEXT:    adr r6, .LCPI3_4
+; CHECK-NEXT:    adr r5, .LCPI3_3
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #176] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r6]
-; CHECK-NEXT:    vldrw.u32 q1, [r3]
-; CHECK-NEXT:    adr r3, .LCPI3_7
+; CHECK-NEXT:    adr r4, .LCPI3_2
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #144] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r5]
-; CHECK-NEXT:    adr r6, .LCPI3_10
-; CHECK-NEXT:    adr r7, .LCPI3_9
+; CHECK-NEXT:    adr.w r8, .LCPI3_1
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #128] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r4]
-; CHECK-NEXT:    vstrw.32 q1, [sp, #192] @ 16-byte Spill
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #112] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r8]
+; CHECK-NEXT:    adr.w r12, .LCPI3_0
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #96] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r12]
+; CHECK-NEXT:    adr r3, .LCPI3_6
+; CHECK-NEXT:    adr r6, .LCPI3_10
+; CHECK-NEXT:    vldrw.u32 q1, [r3]
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #80] @ 16-byte Spill
 ; CHECK-NEXT:    vmov.i32 q0, #0x7fff
+; CHECK-NEXT:    adr r3, .LCPI3_7
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #64] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
+; CHECK-NEXT:    adr r7, .LCPI3_9
 ; CHECK-NEXT:    adr r3, .LCPI3_8
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #48] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r6]
+; CHECK-NEXT:    vstrw.32 q1, [sp, #192] @ 16-byte Spill
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #32] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r7]
 ; CHECK-NEXT:    vstrw.32 q0, [sp, #16] @ 16-byte Spill
 ; CHECK-NEXT:    vldrw.u32 q0, [r3]
 ; CHECK-NEXT:    vstrw.32 q0, [sp] @ 16-byte Spill
+; CHECK-NEXT:    dlstp.32 lr, r2
 ; CHECK-NEXT:  .LBB3_2: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #192] @ 16-byte Reload
-; CHECK-NEXT:    vctp.32 r2
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrbt.u32 q4, [r0, q0]
+; CHECK-NEXT:    vldrb.u32 q4, [r0, q0]
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #176] @ 16-byte Reload
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrbt.u32 q7, [r0, q0]
+; CHECK-NEXT:    vldrb.u32 q7, [r0, q0]
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #144] @ 16-byte Reload
 ; CHECK-NEXT:    vldrw.u32 q5, [sp, #112] @ 16-byte Reload
-; CHECK-NEXT:    subs r2, #4
 ; CHECK-NEXT:    vmul.i32 q6, q7, q0
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #128] @ 16-byte Reload
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrbt.u32 q1, [r0, q5]
+; CHECK-NEXT:    vldrb.u32 q1, [r0, q5]
 ; CHECK-NEXT:    vldrw.u32 q2, [sp, #80] @ 16-byte Reload
 ; CHECK-NEXT:    vmul.i32 q3, q4, q0
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #96] @ 16-byte Reload
@@ -320,14 +310,12 @@
 ; CHECK-NEXT:    vadd.i32 q1, q1, q0
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #192] @ 16-byte Reload
 ; CHECK-NEXT:    vshr.u32 q1, q1, #16
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrbt.32 q1, [r1, q0]
+; CHECK-NEXT:    vstrb.32 q1, [r1, q0]
 ; CHECK-NEXT:    vldrw.u32 q0, [sp, #176] @ 16-byte Reload
-; CHECK-NEXT:    vpstt
-; CHECK-NEXT:    vstrbt.32 q2, [r1, q0]
-; CHECK-NEXT:    vstrbt.32 q6, [r1, q5]
+; CHECK-NEXT:    vstrb.32 q2, [r1, q0]
+; CHECK-NEXT:    vstrb.32 q6, [r1, q5]
 ; CHECK-NEXT:    adds r1, #12
-; CHECK-NEXT:    le lr, .LBB3_2
+; CHECK-NEXT:    letp lr, .LBB3_2
 ; CHECK-NEXT:  .LBB3_3: @ %for.cond.cleanup
 ; CHECK-NEXT:    add sp, #216
 ; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
Index: llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
+++ llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
@@ -9,32 +9,21 @@
 ; CHECK-NEXT:    .vsave {d8, d9}
 ; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    movs r6, #0
-; CHECK-NEXT:    mov r12, r1
 ; CHECK-NEXT:    vidup.u32 q2, r6, #1
-; CHECK-NEXT:    cmp r1, #4
-; CHECK-NEXT:    it ge
-; CHECK-NEXT:    movge.w r12, #4
-; CHECK-NEXT:    sub.w r6, r1, r12
-; CHECK-NEXT:    adds r6, #3
-; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    adr r4, .LCPI0_0
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    add.w lr, lr, r6, lsr #2
 ; CHECK-NEXT:    vldrw.u32 q1, [r4]
-; CHECK-NEXT:    dls lr, lr
 ; CHECK-NEXT:    vmov.i32 q3, #0x4
+; CHECK-NEXT:    dlstp.32 lr, r1
 ; CHECK-NEXT:    mov r12, r1
 ; CHECK-NEXT:  .LBB0_1: @ %do.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vctp.32 r12
-; CHECK-NEXT:    sub.w r12, r12, #4
-; CHECK-NEXT:    vpstttt
-; CHECK-NEXT:    vldrwt.u32 q4, [r0], #16
-; CHECK-NEXT:    vcmpt.f32 ge, q1, q4
+; CHECK-NEXT:    vldrw.u32 q4, [r0], #16
+; CHECK-NEXT:    vptt.f32 ge, q1, q4
 ; CHECK-NEXT:    vmovt q1, q4
 ; CHECK-NEXT:    vmovt q0, q2
 ; CHECK-NEXT:    vadd.i32 q2, q2, q3
-; CHECK-NEXT:    le lr, .LBB0_1
+; CHECK-NEXT:    letp lr, .LBB0_1
 ; CHECK-NEXT:  @ %bb.2: @ %do.end
 ; CHECK-NEXT:    vldr s8, .LCPI0_1
 ; CHECK-NEXT:    vdup.32 q3, r1