Index: llvm/lib/CodeGen/MacroFusion.cpp
===================================================================
--- llvm/lib/CodeGen/MacroFusion.cpp
+++ llvm/lib/CodeGen/MacroFusion.cpp
@@ -36,6 +36,24 @@
   return Dep.getKind() == SDep::Anti || Dep.getKind() == SDep::Output;
 }
 
+namespace {
+
+static SUnit *getPredClusterSU(const SUnit &SU) {
+  for (const SDep &SI : SU.Preds)
+    if (SI.isCluster())
+      return SI.getSUnit();
+
+  return nullptr;
+}
+
+static SUnit *getSuccClusterSU(const SUnit &SU) {
+  for (const SDep &SI : SU.Succs)
+    if (SI.isCluster())
+      return SI.getSUnit();
+
+  return nullptr;
+}
+
 static bool fuseInstructionPair(ScheduleDAGInstrs &DAG, SUnit &FirstSU,
                                 SUnit &SecondSU) {
   // Check that neither instr is already paired with another along the edge
@@ -73,27 +91,34 @@
 
   // Make data dependencies from the FirstSU also dependent on the SecondSU to
   // prevent them from being scheduled between the FirstSU and the SecondSU.
-  if (&SecondSU != &DAG.ExitSU)
+  SUnit *CurrentSU = &SecondSU;
+  while (CurrentSU && CurrentSU != &DAG.ExitSU) {
     for (const SDep &SI : FirstSU.Succs) {
       SUnit *SU = SI.getSUnit();
       if (SI.isWeak() || isHazard(SI) ||
-          SU == &DAG.ExitSU || SU == &SecondSU || SU->isPred(&SecondSU))
+          SU == &DAG.ExitSU || SU == CurrentSU ||
+          SU->isPred(CurrentSU))
         continue;
-      LLVM_DEBUG(dbgs() << "  Bind "; DAG.dumpNodeName(SecondSU);
+      LLVM_DEBUG(dbgs() << "  Bind "; DAG.dumpNodeName(*CurrentSU);
                  dbgs() << " - "; DAG.dumpNodeName(*SU); dbgs() << '\n';);
-      DAG.addEdge(SU, SDep(&SecondSU, SDep::Artificial));
+      DAG.addEdge(SU, SDep(CurrentSU, SDep::Artificial));
     }
 
+    CurrentSU = getSuccClusterSU(*CurrentSU);
+  }
+
   // Make the FirstSU also dependent on the dependencies of the SecondSU to
   // prevent them from being scheduled between the FirstSU and the SecondSU.
-  if (&FirstSU != &DAG.EntrySU) {
+  CurrentSU = &FirstSU;
+  while (CurrentSU && CurrentSU != &DAG.EntrySU) {
     for (const SDep &SI : SecondSU.Preds) {
       SUnit *SU = SI.getSUnit();
-      if (SI.isWeak() || isHazard(SI) || &FirstSU == SU || FirstSU.isSucc(SU))
+      if (SI.isWeak() || isHazard(SI) || CurrentSU == SU ||
+          CurrentSU->isSucc(SU))
         continue;
       LLVM_DEBUG(dbgs() << "  Bind "; DAG.dumpNodeName(*SU); dbgs() << " - ";
-                 DAG.dumpNodeName(FirstSU); dbgs() << '\n';);
-      DAG.addEdge(&FirstSU, SDep(SU, SDep::Artificial));
+                 DAG.dumpNodeName(*CurrentSU); dbgs() << '\n';);
+      DAG.addEdge(CurrentSU, SDep(SU, SDep::Artificial));
     }
     // ExitSU comes last by design, which acts like an implicit dependency
     // between ExitSU and any bottom root in the graph. We should transfer
@@ -101,17 +126,17 @@
     if (&SecondSU == &DAG.ExitSU) {
       for (SUnit &SU : DAG.SUnits) {
         if (SU.Succs.empty())
-          DAG.addEdge(&FirstSU, SDep(&SU, SDep::Artificial));
+          DAG.addEdge(CurrentSU, SDep(&SU, SDep::Artificial));
       }
     }
+
+    CurrentSU = getPredClusterSU(*CurrentSU);
   }
 
   ++NumFused;
   return true;
 }
 
-namespace {
-
 /// Post-process the DAG to create cluster edges between instrs that may
 /// be fused by the processor into a single operation.
 class MacroFusion : public ScheduleDAGMutation {
Index: llvm/test/CodeGen/AArch64/macro-fusion.ll
===================================================================
--- llvm/test/CodeGen/AArch64/macro-fusion.ll
+++ llvm/test/CodeGen/AArch64/macro-fusion.ll
@@ -10,6 +10,7 @@
 ; CHECK: Bind SU([[SU1:[0-9]+]]) - SU([[SU4]])
 ; CHECK: Macro fuse: SU([[SU5]]) - SU([[SU6:[0-9]+]])
 ; CHECK: Bind SU([[SU0:[0-9]+]]) - SU([[SU5]])
+; CHECK: Bind SU([[SU0:[0-9]+]]) - SU([[SU4]])
 ; CHECK: SU([[SU0]]):   %{{[0-9]+}}:gpr32 = COPY $w3
 ; CHECK: SU([[SU1]]):   %{{[0-9]+}}:gpr32 = COPY $w2
 ; CHECK: SU([[SU4]]):   %{{[0-9]+}}:gpr32 = nsw ADDWrr