Index: lib/Transforms/Utils/Local.cpp
===================================================================
--- lib/Transforms/Utils/Local.cpp
+++ lib/Transforms/Utils/Local.cpp
@@ -890,6 +890,17 @@
     }
   }
 
+  // If the unconditional branch we replaced contains llvm.loop metadata, we
+  // add the metadata to the branch instructions in the predecessors.
+  unsigned LoopMDKind = BB->getContext().getMDKindID("llvm.loop");
+  Instruction *TI = BB->getTerminator();
+  if (TI)
+    if (MDNode *LoopMD = TI->getMetadata(LoopMDKind))
+      for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
+        BasicBlock *Pred = *PI;
+        Pred->getTerminator()->setMetadata(LoopMDKind, LoopMD);
+      }
+
   // Everything that jumped to BB now goes to Succ.
   BB->replaceAllUsesWith(Succ);
   if (!Succ->hasName()) Succ->takeName(BB);
Index: lib/Transforms/Utils/LoopSimplify.cpp
===================================================================
--- lib/Transforms/Utils/LoopSimplify.cpp
+++ lib/Transforms/Utils/LoopSimplify.cpp
@@ -470,13 +470,21 @@
   }
 
   // Now that all of the PHI nodes have been inserted and adjusted, modify the
-  // backedge blocks to just to the BEBlock instead of the header.
+  // backedge blocks to jump to the BEBlock instead of the header.
+  // If one of the backedges has llvm.loop metadata attached, we remove
+  // it from the backedge and add it to BEBlock.
+  unsigned LoopMDKind = BEBlock->getContext().getMDKindID("llvm.loop");
+  MDNode *LoopMD = nullptr;
   for (unsigned i = 0, e = BackedgeBlocks.size(); i != e; ++i) {
     TerminatorInst *TI = BackedgeBlocks[i]->getTerminator();
+    if (!LoopMD)
+      LoopMD = TI->getMetadata(LoopMDKind);
+    TI->setMetadata(LoopMDKind, nullptr);
     for (unsigned Op = 0, e = TI->getNumSuccessors(); Op != e; ++Op)
       if (TI->getSuccessor(Op) == Header)
         TI->setSuccessor(Op, BEBlock);
   }
+  BEBlock->getTerminator()->setMetadata(LoopMDKind, LoopMD);
 
   //===--- Update all analyses which we must preserve now -----------------===//
 
Index: test/Transforms/LoopSimplify/preserve-llvm-loop-metadata.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopSimplify/preserve-llvm-loop-metadata.ll
@@ -0,0 +1,42 @@
+; RUN: opt -loop-simplify -S < %s | FileCheck %s
+
+define void @test1(i32 %n) {
+entry:
+  br label %while.cond
+
+while.cond:                                       ; preds = %if.then, %if.else, %entry
+  %count.0 = phi i32 [ 0, %entry ], [ %add, %if.then ], [ %add2, %if.else ]
+  %cmp = icmp ugt i32 %count.0, %n
+  br i1 %cmp, label %while.end, label %while.body
+
+while.body:                                       ; preds = %while.cond
+  %rem = and i32 %count.0, 1
+  %cmp1 = icmp eq i32 %rem, 0
+  br i1 %cmp1, label %if.then, label %if.else
+
+if.then:                                          ; preds = %while.body
+  %add = add i32 %count.0, 1
+  br label %while.cond, !llvm.loop !0
+
+if.else:                                          ; preds = %while.body
+  %add2 = add i32 %count.0, 2
+  br label %while.cond, !llvm.loop !0
+
+while.end:                                        ; preds = %while.cond
+  ret void
+}
+
+; CHECK: if.then
+; CHECK-NOT: br {{.*}}!llvm.loop{{.*}}
+
+; CHECK: while.cond.backedge:
+; CHECK: br label %while.cond, !llvm.loop !0
+
+; CHECK: if.else
+; CHECK-NOT: br {{.*}}!llvm.loop{{.*}}
+
+
+!0 = distinct !{!0, !1}
+!1 = !{!"llvm.loop.distribute.enable", i1 true}
+; CHECK: !0 = distinct !{!0, !1}
+; CHECK: !1 = !{!"llvm.loop.distribute.enable", i1 true}
Index: test/Transforms/SimplifyCFG/preserve-llvm-loop-metadata.ll
===================================================================
--- /dev/null
+++ test/Transforms/SimplifyCFG/preserve-llvm-loop-metadata.ll
@@ -0,0 +1,53 @@
+; RUN: opt -simplifycfg -S < %s | FileCheck %s
+
+define void @test1(i32 %n) #0 {
+entry:
+  %n.addr = alloca i32, align 4
+  %count = alloca i32, align 4
+  store i32 %n, i32* %n.addr, align 4
+  %0 = bitcast i32* %count to i8*
+  store i32 0, i32* %count, align 4
+  br label %while.cond
+
+while.cond:                                       ; preds = %if.end, %entry
+  %1 = load i32, i32* %count, align 4
+  %2 = load i32, i32* %n.addr, align 4
+  %cmp = icmp ule i32 %1, %2
+  br i1 %cmp, label %while.body, label %while.end
+
+while.body:                                       ; preds = %while.cond
+  %3 = load i32, i32* %count, align 4
+  %rem = urem i32 %3, 2
+  %cmp1 = icmp eq i32 %rem, 0
+  br i1 %cmp1, label %if.then, label %if.else
+
+if.then:                                          ; preds = %while.body
+  %4 = load i32, i32* %count, align 4
+  %add = add i32 %4, 1
+  store i32 %add, i32* %count, align 4
+  br label %if.end
+
+; CHECK: if.then:
+; CHECK:  br label %while.cond, !llvm.loop !0
+
+if.else:                                          ; preds = %while.body
+  %5 = load i32, i32* %count, align 4
+  %add2 = add i32 %5, 2
+  store i32 %add2, i32* %count, align 4
+  br label %if.end
+
+; CHECK: if.else:
+; CHECK:  br label %while.cond, !llvm.loop !0
+
+if.end:                                           ; preds = %if.else, %if.then
+  br label %while.cond, !llvm.loop !0
+
+while.end:                                        ; preds = %while.cond
+  %6 = bitcast i32* %count to i8*
+  ret void
+}
+
+!0 = distinct !{!0, !1}
+!1 = !{!"llvm.loop.distribute.enable", i1 true}
+; CHECK: !0 = distinct !{!0, !1}
+; CHECK: !1 = !{!"llvm.loop.distribute.enable", i1 true}