Index: lib/CodeGen/LivePhysRegs.cpp
===================================================================
--- lib/CodeGen/LivePhysRegs.cpp
+++ lib/CodeGen/LivePhysRegs.cpp
@@ -205,14 +205,18 @@
 }
 
 void LivePhysRegs::addLiveOutsNoPristines(const MachineBasicBlock &MBB) {
-  if (!MBB.succ_empty()) {
-    // To get the live-outs we simply merge the live-ins of all successors.
-    for (const MachineBasicBlock *Succ : MBB.successors())
-      addBlockLiveIns(*Succ);
-  } else if (MBB.isReturnBlock()) {
-    // For the return block: Add all callee saved registers that are saved and
-    // restored (somewhere); This does not include callee saved registers that
-    // are unused and hence not saved and restored; they are called pristine.
+  // To get the live-outs we simply merge the live-ins of all successors.
+  for (const MachineBasicBlock *Succ : MBB.successors())
+    addBlockLiveIns(*Succ);
+  if (MBB.isReturnBlock()) {
+    // Return blocks are a special case because we currently don't mark up
+    // return instructions completely: specifically, there is no explicit
+    // use for callee-saved registers. So we add all callee saved registers
+    // that are saved and restored (somewhere). This does not include
+    // callee saved registers that are unused and hence not saved and
+    // restored; they are called pristine.
+    // FIXME: PEI should add explicit markings to return instructions
+    // instead of implicitly handling them here.
     const MachineFunction &MF = *MBB.getParent();
     const MachineFrameInfo &MFI = MF.getFrameInfo();
     if (MFI.isCalleeSavedInfoValid()) {
@@ -225,15 +229,8 @@
 
 void LivePhysRegs::addLiveOuts(const MachineBasicBlock &MBB) {
   const MachineFunction &MF = *MBB.getParent();
-  if (!MBB.succ_empty()) {
-    addPristines(MF);
-    addLiveOutsNoPristines(MBB);
-  } else if (MBB.isReturnBlock()) {
-    // For the return block: Add all callee saved registers.
-    const MachineFrameInfo &MFI = MF.getFrameInfo();
-    if (MFI.isCalleeSavedInfoValid())
-      addCalleeSavedRegs(*this, MF);
-  }
+  addPristines(MF);
+  addLiveOutsNoPristines(MBB);
 }
 
 void LivePhysRegs::addLiveIns(const MachineBasicBlock &MBB) {
Index: test/CodeGen/ARM/pr25838.ll
===================================================================
--- test/CodeGen/ARM/pr25838.ll
+++ test/CodeGen/ARM/pr25838.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s
+; RUN: llc -verify-machineinstrs < %s
 ; PR25838
 
 target triple = "armv7--linux-android"
Index: test/CodeGen/Thumb/stm-scavenging.ll
===================================================================
--- /dev/null
+++ test/CodeGen/Thumb/stm-scavenging.ll
@@ -0,0 +1,46 @@
+; RUN: llc < %s | FileCheck %s
+target triple = "thumbv6---gnueabi"
+
+; Use STM to save the three registers
+; CHECK-LABEL: use_stm:
+; CHECK: .save   {r7, lr}
+; CHECK: .setfp  r7, sp
+; CHECK: stm r3!, {r0, r1, r2}
+; CHECK: bl throws_1
+define void @use_stm(i32 %a, i32 %b, i32 %c, i32* %d) local_unnamed_addr noreturn "no-frame-pointer-elim"="true" {
+entry:
+  %arrayidx = getelementptr inbounds i32, i32* %d, i32 2
+  store i32 %a, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %d, i32 3
+  store i32 %b, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %d, i32 4
+  store i32 %c, i32* %arrayidx2, align 4
+  tail call void @throws_1(i32 %a, i32 %b, i32 %c) noreturn
+  unreachable
+}
+
+; Don't use STM: there is no available register to store
+; the address. We could transform this with some extra math, but
+; that currently isn't implemented.
+; CHECK-LABEL: no_stm:
+; CHECK: .save   {r7, lr}
+; CHECK: .setfp  r7, sp
+; CHECK: str r0,
+; CHECK: str r1,
+; CHECK: str r2,
+; CHECK: bl throws_2
+define void @no_stm(i32 %a, i32 %b, i32 %c, i32* %d) local_unnamed_addr noreturn "no-frame-pointer-elim"="true" {
+entry:
+  %arrayidx = getelementptr inbounds i32, i32* %d, i32 2
+  store i32 %a, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %d, i32 3
+  store i32 %b, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %d, i32 4
+  store i32 %c, i32* %arrayidx2, align 4
+  tail call void @throws_2(i32 %a, i32 %b, i32 %c, i32* %d) noreturn
+  unreachable
+}
+
+
+declare void @throws_1(i32, i32, i32) noreturn
+declare void @throws_2(i32, i32, i32, i32*) noreturn