Index: lib/CodeGen/VirtRegMap.cpp
===================================================================
--- lib/CodeGen/VirtRegMap.cpp
+++ lib/CodeGen/VirtRegMap.cpp
@@ -406,6 +406,8 @@
     return;
 
   if (MI.isBundledWithPred() && !MI.isBundledWithSucc()) {
+    SmallVector<MachineInstr *, 2> MIs({&MI});
+
     // Only do this when the complete bundle is made out of COPYs.
     MachineBasicBlock &MBB = *MI.getParent();
     for (MachineBasicBlock::reverse_instr_iterator I =
@@ -413,16 +415,53 @@
          I != E && I->isBundledWithSucc(); ++I) {
       if (!I->isCopy())
         return;
+      MIs.push_back(&*I);
+    }
+    MachineInstr *FirstMI = MIs.back();
+
+    auto anyRegsAlias = [](const MachineInstr *Dst,
+                           ArrayRef<MachineInstr *> Srcs,
+                           const TargetRegisterInfo *TRI) {
+      for (const MachineInstr *Src : Srcs)
+        if (Src != Dst)
+          if (TRI->regsOverlap(Dst->getOperand(0).getReg(),
+                               Src->getOperand(1).getReg()))
+            return true;
+      return false;
+    };
+
+    // If any of the destination registers in the bundle of copies alias any of
+    // the source registers, try to schedule the instructions to avoid any
+    // clobbering.
+    for (int E = MIs.size(), PrevE; E > 1; PrevE = E) {
+      for (int I = E; I--; )
+        if (!anyRegsAlias(MIs[I], makeArrayRef(MIs).take_front(E), TRI)) {
+          if (I + 1 != E)
+            std::swap(MIs[I], MIs[E - 1]);
+          --E;
+        }
+      if (PrevE == E) {
+        MF->getFunction().getContext().emitError(
+            "register rewriting failed: cycle in copy bundle");
+        break;
+      }
     }
 
-    for (MachineBasicBlock::reverse_instr_iterator I = MI.getReverseIterator();
-         I->isBundledWithPred(); ) {
-      MachineInstr &MI = *I;
-      ++I;
+    MachineInstr *BundleStart = FirstMI;
+    for (MachineInstr *Inst : llvm::reverse(MIs)) {
+      // If instruction is in the middle of the bundle, move it before the
+      // bundle starts, otherwise, just unbundle it. When we get to the last
+      // instruction, the bundle will have been completely undone.
+      if (Inst != BundleStart) {
+        Inst->removeFromBundle();
+        MBB.insert(FirstMI->getIterator(), Inst);
+      } else if (Inst->isBundledWithSucc()) {
+        Inst->unbundleFromSucc();
+        BundleStart = &*std::next(Inst->getIterator());
+      }
 
-      MI.unbundleFromPred();
-      if (Indexes)
-        Indexes->insertMachineInstrInMaps(MI);
+      if (Indexes && Inst != FirstMI)
+        Indexes->insertMachineInstrInMaps(*Inst);
     }
   }
 }
Index: test/CodeGen/AArch64/overlapping-copy-bundle-cycle.mir
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/overlapping-copy-bundle-cycle.mir
@@ -0,0 +1,16 @@
+# RUN: not llc -mtriple=aarch64-apple-ios -run-pass=greedy -run-pass=virtregrewriter %s -o /dev/null 2>&1 | FileCheck %s
+
+# Check we don't infinitely loop on cycles in copy bundles.
+# CHECK: error: register rewriting failed: cycle in copy bundle
+
+---
+name: func0
+body: |
+  bb.0:
+    $x0 = IMPLICIT_DEF
+    $q0_q1_q2_q3 = IMPLICIT_DEF
+    $q1_q2_q3 = COPY $q0_q1_q2 {
+      $q2_q3_q4 = COPY $q1_q2_q3
+    }
+    ST4i64 $q1_q2_q3_q4, 0, $x0
+...
Index: test/CodeGen/AArch64/overlapping-copy-bundle.mir
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/overlapping-copy-bundle.mir
@@ -0,0 +1,80 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=aarch64-apple-ios -run-pass=greedy -run-pass=virtregrewriter %s -o - | FileCheck %s
+---
+name: func0
+body: |
+  bb.0:
+    ; Make sure we don't clobber q3 when we expand the bundle
+    ; CHECK-LABEL: name: func0
+    ; CHECK: $x0 = IMPLICIT_DEF
+    ; CHECK: $q0_q1_q2_q3 = IMPLICIT_DEF
+    ; CHECK: $q4 = COPY $q3
+    ; CHECK: $q1_q2_q3 = COPY $q0_q1_q2
+    ; CHECK: ST4i64 $q1_q2_q3_q4, 0, $x0
+    $x0 = IMPLICIT_DEF
+    $q0_q1_q2_q3 = IMPLICIT_DEF
+    $q1_q2_q3 = COPY $q0_q1_q2 {
+      $q4 = COPY $q3
+    }
+    ST4i64 $q1_q2_q3_q4, 0, $x0
+
+...
+---
+name: func1
+body: |
+  bb.0:
+    ; If it was already ordered, make sure we don't break it
+    ; CHECK-LABEL: name: func1
+    ; CHECK: $x0 = IMPLICIT_DEF
+    ; CHECK: $q0_q1_q2_q3 = IMPLICIT_DEF
+    ; CHECK: $q4 = COPY $q3
+    ; CHECK: $q1_q2_q3 = COPY $q0_q1_q2
+    ; CHECK: ST4i64 $q1_q2_q3_q4, 0, $x0
+    $x0 = IMPLICIT_DEF
+    $q0_q1_q2_q3 = IMPLICIT_DEF
+    $q4 = COPY $q3 {
+      $q1_q2_q3 = COPY $q0_q1_q2
+    }
+    ST4i64 $q1_q2_q3_q4, 0, $x0
+
+...
+---
+name: func2
+body: |
+  bb.0:
+    ; A bit less realistic, but check that we handle multiple nodes
+    ; CHECK-LABEL: name: func2
+    ; CHECK: $x0 = IMPLICIT_DEF
+    ; CHECK: $q0_q1_q2_q3 = IMPLICIT_DEF
+    ; CHECK: $q3 = COPY $q2
+    ; CHECK: $q4 = COPY $q1
+    ; CHECK: $q1_q2 = COPY $q0_q1
+    ; CHECK: ST4i64 $q1_q2_q3_q4, 0, $x0
+    $x0 = IMPLICIT_DEF
+    $q0_q1_q2_q3 = IMPLICIT_DEF
+    $q1_q2 = COPY $q0_q1 {
+      $q3 = COPY $q2
+      $q4 = COPY $q1
+    }
+    ST4i64 $q1_q2_q3_q4, 0, $x0
+
+...
+---
+name: func3
+body: |
+  bb.0:
+    ; If there was nothing wrong, don't change the order for no reason
+    ; CHECK-LABEL: name: func3
+    ; CHECK: $x0 = IMPLICIT_DEF
+    ; CHECK: $q1_q2_q3_q4 = IMPLICIT_DEF
+    ; CHECK: $q0_q1 = COPY $q1_q2
+    ; CHECK: $q2_q3 = COPY $q3_q4
+    ; CHECK: ST4i64 $q0_q1_q2_q3, 0, $x0
+    $x0 = IMPLICIT_DEF
+    $q1_q2_q3_q4 = IMPLICIT_DEF
+    $q0_q1 = COPY $q1_q2 {
+      $q2_q3 = COPY $q3_q4
+    }
+    ST4i64 $q0_q1_q2_q3, 0, $x0
+
+...