Index: include/llvm/Transforms/Scalar/JumpThreading.h
===================================================================
--- include/llvm/Transforms/Scalar/JumpThreading.h
+++ include/llvm/Transforms/Scalar/JumpThreading.h
@@ -62,6 +62,7 @@
   std::unique_ptr<BlockFrequencyInfo> BFI;
   std::unique_ptr<BranchProbabilityInfo> BPI;
   bool HasProfileData = false;
+  Function *Fn;
 #ifdef NDEBUG
   SmallPtrSet<const BasicBlock *, 16> LoopHeaders;
 #else
Index: lib/Transforms/Scalar/JumpThreading.cpp
===================================================================
--- lib/Transforms/Scalar/JumpThreading.cpp
+++ lib/Transforms/Scalar/JumpThreading.cpp
@@ -168,6 +168,7 @@
   DEBUG(dbgs() << "Jump threading on function '" << F.getName() << "'\n");
   TLI = TLI_;
   LVI = LVI_;
+  Fn = &F;
   BFI.reset();
   BPI.reset();
   // When profile data is available, we need to update edge weights after
@@ -1182,11 +1183,6 @@
 bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB,
                                                ConstantPreference Preference,
                                                Instruction *CxtI) {
-  // If threading this would thread across a loop header, don't even try to
-  // thread the edge.
-  if (LoopHeaders.count(BB))
-    return false;
-
   PredValueInfoTy PredValues;
   if (!ComputeValueKnownInPredecessors(Cond, BB, PredValues, Preference, CxtI))
     return false;
@@ -1457,7 +1453,11 @@
 
   // If threading this would thread across a loop header, don't thread the edge.
   // See the comments above FindLoopHeaders for justifications and caveats.
-  if (LoopHeaders.count(BB)) {
+  //
+  // However, if we're threading a block to *itself*, we know we're creating
+  // a one block loop that must by definition by valid. Proceed in this case.
+  if (LoopHeaders.count(BB) &&
+      std::find(PredBBs.begin(), PredBBs.end(), SuccBB) == PredBBs.end()) {
     DEBUG(dbgs() << "  Not threading across loop header BB '" << BB->getName()
           << "' to dest BB '" << SuccBB->getName()
           << "' - it might create an irreducible loop!\n");
@@ -1593,6 +1593,10 @@
   // Update the edge weight from BB to SuccBB, which should be less than before.
   UpdateBlockFreqAndEdgeWeight(PredBB, BB, NewBB, SuccBB);
 
+  if (LoopHeaders.count(BB))
+    // We threaded over a loop header. Recalculate loop headers now.
+    FindLoopHeaders(*Fn);
+  
   // Threaded an edge!
   ++NumThreads;
   return true;
Index: test/Transforms/JumpThreading/singleblock-loop.ll
===================================================================
--- /dev/null
+++ test/Transforms/JumpThreading/singleblock-loop.ll
@@ -0,0 +1,28 @@
+; RUN: opt < %s -S -jump-threading | FileCheck %s
+
+; %i.0 can only take the value 2. If it gets incremented to 3, the loop will exit.
+; Jump threading must thread the %entry and backedge arcs directly to %while.body.
+
+; CHECK-LABEL: @f
+; CHECK: while.body: ; preds = %while.cond.thread, %while.cond
+define void @f() {
+entry:
+  br label %while.cond
+
+while.cond:                                       ; preds = %while.body, %entry
+  %i.0 = phi i32 [ 2, %entry ], [ %add.i.0, %while.body ]
+  %cmp = icmp slt i32 %i.0, 3
+  br i1 %cmp, label %while.body, label %return
+
+while.body:                                       ; preds = %while.cond
+  %add = add nsw i32 %i.0, 1
+  %call = call i32 @g()
+  %cmp3 = icmp eq i32 %call, 0
+  %add.i.0 = select i1 %cmp3, i32 %add, i32 %i.0
+  br label %while.cond
+
+return:
+  ret void
+}
+
+declare i32 @g()