Index: llvm/lib/Transforms/IPO/HotColdSplitting.cpp
===================================================================
--- llvm/lib/Transforms/IPO/HotColdSplitting.cpp
+++ llvm/lib/Transforms/IPO/HotColdSplitting.cpp
@@ -261,8 +261,8 @@
 
 private:
   bool shouldOutlineFrom(const Function &F) const;
-  const Function *outlineColdBlocks(Function &F, const DenseSetBB &ColdBlock,
-                                    DominatorTree *DT, PostDomTree *PDT);
+  void outlineColdBlocks(Function &F, const DenseSetBB &ColdBlock,
+                         DominatorTree *DT, PostDomTree *PDT);
   Function *extractColdRegion(const SmallVectorImpl<BasicBlock *> &Region,
                               DominatorTree *DT, BlockFrequencyInfo *BFI,
                               OptimizationRemarkEmitter &ORE);
@@ -380,10 +380,9 @@
 }
 
 // Return the function created after outlining, nullptr otherwise.
-const Function *HotColdSplitting::outlineColdBlocks(Function &F,
-                                                    const DenseSetBB &HotBlocks,
-                                                    DominatorTree *DT,
-                                                    PostDomTree *PDT) {
+void HotColdSplitting::outlineColdBlocks(Function &F,
+                                         const DenseSetBB &HotBlocks,
+                                         DominatorTree *DT, PostDomTree *PDT) {
   auto BFI = GetBFI(F);
   auto &ORE = (*GetORE)(F);
   // Walking the dominator tree allows us to find the largest
@@ -393,10 +392,16 @@
   // Early return if the beginning of the function has been marked cold,
   // otherwise all the function gets outlined.
   if (PSI->isColdBB(Begin, BFI) || !HotBlocks.count(Begin))
-    return nullptr;
+    return;
 
+  DenseSetBB OutlinedBBs;
   for (auto I = df_begin(Begin), E = df_end(Begin); I != E; ++I) {
     BasicBlock *BB = *I;
+
+    // Skip over outlined blocks.
+    if (OutlinedBBs.count(BB))
+      continue;
+
     if (PSI->isColdBB(BB, BFI) || !HotBlocks.count(BB)) {
       SmallVector<BasicBlock *, 4> ValidColdRegion, Region;
       BasicBlock *Exit = (*PDT)[BB]->getIDom()->getBlock();
@@ -411,6 +416,7 @@
         // Update Exit recursively to its dom-frontier.
         Exit = (*PDT)[Exit]->getIDom()->getBlock();
       }
+
       if (ExitColdRegion) {
         // Do not outline a region with only one block.
         if (ValidColdRegion.size() == 1)
@@ -418,12 +424,16 @@
 
         ++NumColdSESEFound;
         ValidColdRegion.push_back(ExitColdRegion);
-        // Candidate for outlining. FIXME: Continue outlining.
-        return extractColdRegion(ValidColdRegion, DT, BFI, ORE);
+
+        if (const Function *Outlined =
+                extractColdRegion(ValidColdRegion, DT, BFI, ORE)) {
+          OutlinedFunctions.insert(Outlined);
+          for (BasicBlock *I : ValidColdRegion)
+            OutlinedBBs.insert(I);
+        }
       }
     }
   }
-  return nullptr;
 }
 
 bool HotColdSplitting::run(Module &M) {
@@ -437,9 +447,7 @@
     if (EnableStaticAnalyis) // Static analysis of cold blocks.
       HotBlocks = getHotBlocks(F);
 
-    const Function *Outlined = outlineColdBlocks(F, HotBlocks, &DT, &PDT);
-    if (Outlined)
-      OutlinedFunctions.insert(Outlined);
+    outlineColdBlocks(F, HotBlocks, &DT, &PDT);
   }
   return true;
 }
Index: llvm/test/Transforms/HotColdSplit/split-cold-3.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/HotColdSplit/split-cold-3.ll
@@ -0,0 +1,50 @@
+; RUN: opt -hotcoldsplit -pass-remarks=hotcoldsplit < %s 2>&1 | FileCheck %s
+; RUN: opt -passes=hotcoldsplit -pass-remarks=hotcoldsplit < %s 2>&1 | FileCheck %s
+
+; CHECK: remark: <unknown>:0:0: fun split cold code into fun_B.else
+; CHECK: remark: <unknown>:0:0: fun split cold code into fun_A.else
+
+define void @fun() {
+entry:
+  br i1 undef, label %A.then, label %A.else
+
+A.else:
+  br label %A.then4
+
+A.then4:
+  br i1 undef, label %A.then5, label %A.end
+
+A.then5:
+  br label %A.cleanup
+
+A.end:
+  br label %A.cleanup
+
+A.cleanup:
+  %A.cleanup.dest.slot.0 = phi i32 [ 1, %A.then5 ], [ 0, %A.end ]
+  unreachable
+
+A.then:
+  br i1 undef, label %B.then, label %B.else
+
+B.then:
+  ret void
+
+B.else:
+  br label %B.then4
+
+B.then4:
+  br i1 undef, label %B.then5, label %B.end
+
+B.then5:
+  br label %B.cleanup
+
+B.end:
+  br label %B.cleanup
+
+B.cleanup:
+  %B.cleanup.dest.slot.0 = phi i32 [ 1, %B.then5 ], [ 0, %B.end ]
+  unreachable
+
+
+}