Index: lib/CodeGen/BranchFolding.cpp
===================================================================
--- lib/CodeGen/BranchFolding.cpp
+++ lib/CodeGen/BranchFolding.cpp
@@ -31,6 +31,7 @@
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
@@ -372,6 +373,36 @@
   if (UpdateLiveIns) {
     NewDest->clearLiveIns();
     computeLiveIns(LiveRegs, *MRI, *NewDest);
+
+    // Need to traverse all predecessors, because some of them may not be
+    // among the blocks in SameTails. This could happen, for example, if one
+    // of the blocks in SameTails is used as the common tail.
+    for (MachineBasicBlock *Pred : NewDest->predecessors()) {
+      LivePhysRegs LiveOuts(*TRI);
+      LiveOuts.addLiveIns(*Pred);
+
+      // Actually recalculate the live-outs in Pred. This is necessary because
+      // removing an <undef> flag in mergeOperations can make the liveness info
+      // incorrect. The purpose of this code is to identify such cases and
+      // patch it with IMPLICIT_DEFs.
+      SmallVector<std::pair<unsigned, const MachineOperand*>, 2> Clobbers;
+      for (const MachineInstr &MI : *Pred) {
+        LiveOuts.stepForward(MI, Clobbers);
+        for (auto C : Clobbers)
+          if (C.second->isReg() && C.second->isDef() && C.second->isDead())
+            LiveOuts.removeReg(C.first);
+        Clobbers.clear();
+      }
+
+      for (const MachineBasicBlock::RegisterMaskPair &LI : NewDest->liveins()) {
+        if (!LiveOuts.available(*MRI, LI.PhysReg))
+          continue;
+        MachineBasicBlock::iterator At = Pred->getFirstTerminator();
+        const DebugLoc &dl = Pred->findDebugLoc(At);
+        BuildMI(*Pred, At, dl, TII->get(TargetOpcode::IMPLICIT_DEF),
+                LI.PhysReg);
+      }
+    }
   }
 
   ++NumTailMerge;
Index: test/CodeGen/Hexagon/branchfolder-insert-impdef.mir
===================================================================
--- /dev/null
+++ test/CodeGen/Hexagon/branchfolder-insert-impdef.mir
@@ -0,0 +1,43 @@
+# RUN: llc -march=hexagon -run-pass branch-folder %s -o - -verify-machineinstrs | FileCheck %s
+
+# Branch folding will perform tail merging of bb.1 and bb.2, and bb.2 will
+# become the common tail. The use of R0 in bb.2 is <undef> while the
+# corresponding use in bb.1 is not. The common tail will have the <undef>
+# flag removed, which will cause R0 to become a live-in to bb.2. The problem
+# is that R0 is not live-out from all predecessors of bb.2, namely is not
+# live-out from bb.0. To remedy that, the branch folder should add an
+# IMPLICIT_DEF to that block.
+
+# CHECK-LABEL: bb.0:
+# CHECK: %r0 = IMPLICIT_DEF
+# CHECK-LABEL: bb.1:
+# CHECK-LABEL: bb.2:
+# CHECK: liveins: %r0
+# CHECK: PS_storerhabs 0, %r0
+# CHECK: PS_jmpret
+
+---
+name: fred
+tracksRegLiveness: true
+
+body: |
+  bb.0:
+    successors: %bb.1, %bb.2
+      J2_jumpt undef %p0, %bb.2, implicit-def %pc
+      J2_jump %bb.1, implicit-def %pc
+
+  bb.1:
+    successors: %bb.3
+      %r0 = L2_loadruh_io undef %r1, 0
+      PS_storerhabs 0, killed %r0
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.2:
+    successors: %bb.3
+      PS_storerhabs 0, undef %r0
+      J2_jump %bb.3, implicit-def %pc
+
+  bb.3:
+      PS_jmpret killed %r31, implicit-def %pc
+...
+
Index: test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
===================================================================
--- test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
+++ test/CodeGen/Hexagon/livephysregs-lane-masks2.mir
@@ -13,13 +13,13 @@
 
 body: |
   bb.0:
-    liveins: %p2, %r0
+    liveins: %p0:0x1, %p2, %r0
     successors: %bb.1, %bb.2
         J2_jumpt killed %p2, %bb.1, implicit-def %pc
         J2_jump %bb.2, implicit-def %pc
 
   bb.1:
-    liveins: %r0, %r19
+    liveins: %p0:0x1, %r0, %r19
     successors: %bb.3
         %r2 = A2_tfrsi 4
         %r1 = COPY %r19
@@ -28,7 +28,7 @@
         J2_jump %bb.3, implicit-def %pc
 
   bb.2:
-    liveins: %r0, %r18
+    liveins: %p0:0x1, %r0, %r18
     successors: %bb.3
         %r2 = A2_tfrsi 5
         %r1 = L2_loadrh_io %r18, 0