Index: lib/Transforms/Utils/CloneFunction.cpp
===================================================================
--- lib/Transforms/Utils/CloneFunction.cpp
+++ lib/Transforms/Utils/CloneFunction.cpp
@@ -475,11 +475,14 @@
   //
   // Defer PHI resolution until rest of function is resolved.
   SmallVector<const PHINode*, 16> PHIToResolve;
+  std::vector<const BasicBlock*> ReachableBBsInOldFunc;
   for (const BasicBlock &BI : *OldFunc) {
     Value *V = VMap.lookup(&BI);
     BasicBlock *NewBB = cast_or_null<BasicBlock>(V);
     if (!NewBB) continue;  // Dead block.
 
+    // This was a reachable BB from the StartingBB.
+    ReachableBBsInOldFunc.push_back(&BI);
     // Add the new block to the new function.
     NewFunc->getBasicBlockList().push_back(NewBB);
 
@@ -595,6 +598,18 @@
     if (isa<PHINode>(VMap[PHIToResolve[Idx]]))
       Worklist.insert(PHIToResolve[Idx]);
 
+  // In this second pass, we also add all instructions reachable from
+  // StartingInst.  This allows simplification of instructions that previously
+  // could not be simplified because they were not tied to any basic block.
+  for (auto &I: make_range(StartingInst->getIterator(), StartingBB->end()))
+     Worklist.insert(&I);
+
+  for (auto *BB: ReachableBBsInOldFunc) {
+    if (BB == StartingBB)
+      continue;
+    for (auto &I: *BB)
+      Worklist.insert(&I);
+  }
   // Note that we must test the size on each iteration, the worklist can grow.
   for (unsigned Idx = 0; Idx != Worklist.size(); ++Idx) {
     const Value *OrigV = Worklist[Idx];
Index: test/Transforms/Inline/inline_inv_group.ll
===================================================================
--- test/Transforms/Inline/inline_inv_group.ll
+++ test/Transforms/Inline/inline_inv_group.ll
@@ -4,14 +4,13 @@
 target triple = "x86_64-unknown-linux-gnu"
 
 define i8* @callee() alwaysinline {
-; CHECK-LABEL: define i8* @callee()
     %1 = call i8* @llvm.strip.invariant.group.p0i8(i8* null)
     ret i8* %1
 }
 
 define i8* @caller() {
 ; CHECK-LABEL: define i8* @caller()
-; CHECK-NEXT: call i8* @llvm.strip.invariant.group.p0i8(i8* null)
+; CHECK-NEXT: ret i8* null
     %1 = call i8* @callee()
     ret i8* %1
 }