Index: llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp
+++ llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -5733,9 +5733,12 @@
   // header. (This is for early invocations before loop simplify and
   // vectorization to keep canonical loop forms for nested loops. These blocks
   // can be eliminated when the pass is invoked later in the back-end.)
+  // Note that if BB has only one predecessor then we do not introduce new
+  // backedge, so we can eliminate BB.
   bool NeedCanonicalLoop =
       Options.NeedCanonicalLoop &&
-      (LoopHeaders && (LoopHeaders->count(BB) || LoopHeaders->count(Succ)));
+      (LoopHeaders && !BB->getSinglePredecessor() &&
+       (LoopHeaders->count(BB) || LoopHeaders->count(Succ)));
   BasicBlock::iterator I = BB->getFirstNonPHIOrDbg()->getIterator();
   if (I->isTerminator() && BB != &BB->getParent()->getEntryBlock() &&
       !NeedCanonicalLoop && TryToSimplifyUncondBranchFromEmptyBlock(BB))
Index: llvm/trunk/test/Transforms/LoopUnroll/peel-loop.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopUnroll/peel-loop.ll
+++ llvm/trunk/test/Transforms/LoopUnroll/peel-loop.ll
@@ -19,10 +19,8 @@
 ; CHECK: store i32 2, i32* %[[INC2]], align 4
 ; CHECK: %[[CMP3:.*]] = icmp eq i32 %k, 3
 ; CHECK: br i1 %[[CMP3]], label %for.end, label %[[LOOP_PH:.*]]
-; CHECK: [[LOOP_PH]]:
-; CHECK: br label %[[LOOP:.*]]
-; CHECK: [[LOOP]]:
-; CHECK: %[[IV:.*]] = phi i32 [ 3, %[[LOOP_PH]] ], [ {{.*}}, %[[LOOP]] ]
+; CHECK: for.end:
+; CHECK: ret void
 
 define void @basic(i32* %p, i32 %k) #0 {
 entry:
@@ -68,11 +66,8 @@
 ; CHECK: store i32 2, i32* %[[INC2]], align 4
 ; CHECK: %[[CMP3:.*]] = icmp eq i32 %k, 3
 ; CHECK: br i1 %[[CMP3]], label %for.end, label %[[LOOP_PH:.*]]
-; CHECK: [[LOOP_PH]]:
-; CHECK: br label %[[LOOP:.*]]
-; CHECK: [[LOOP]]:
-; CHECK: %[[IV:.*]] = phi i32 [ 3, %[[LOOP_PH]] ], [ %[[IV:.*]], %[[LOOP]] ]
-; CHECK: %ret = phi i32 [ 0, %entry ], [ 1, %[[NEXT0]] ], [ 2, %[[NEXT1]] ], [ 3, %[[NEXT2]] ], [ %[[IV]], %[[LOOP]] ]
+; CHECK: for.end:
+; CHECK: %ret = phi i32 [ 0, %entry ], [ 1, %[[NEXT0]] ], [ 2, %[[NEXT1]] ], [ 3, %[[NEXT2]] ], [ %inc, %for.body ]
 ; CHECK: ret i32 %ret
 define i32 @output(i32* %p, i32 %k) #0 {
 entry:
Index: llvm/trunk/test/Transforms/LoopUnswitch/2015-06-17-Metadata.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopUnswitch/2015-06-17-Metadata.ll
+++ llvm/trunk/test/Transforms/LoopUnswitch/2015-06-17-Metadata.ll
@@ -16,7 +16,7 @@
   %cmp1 = icmp eq i32 %a, 12345
   br i1 %cmp1, label %if.then, label %if.else, !prof !0
 ; CHECK: %cmp1 = icmp eq i32 %a, 12345
-; CHECK-NEXT: br i1 %cmp1, label %for.body.preheader.split.us, label %for.body.preheader.split, !prof !0
+; CHECK-NEXT: br i1 %cmp1, label %for.body.us, label %for.body, !prof !0
 if.then:                                          ; preds = %for.body
 ; CHECK: for.body.us:
 ; CHECK: add nsw i32 %{{.*}}, 123
@@ -53,7 +53,7 @@
   br label %for.body
 ;CHECK: entry:
 ;CHECK-NEXT: %cmp1 = icmp eq i32 1, 2
-;CHECK-NEXT: br i1 %cmp1, label %entry.split, label %for.cond.cleanup.split, !prof !1
+;CHECK-NEXT: br i1 %cmp1, label %for.body, label %for.cond.cleanup.split, !prof !1
 ;CHECK: for.body:
 for.body:                                         ; preds = %for.inc, %entry
   %inc.i = phi i32 [ 0, %entry ], [ %inc, %if.then ]
Index: llvm/trunk/test/Transforms/LoopUnswitch/infinite-loop.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopUnswitch/infinite-loop.ll
+++ llvm/trunk/test/Transforms/LoopUnswitch/infinite-loop.ll
@@ -16,7 +16,7 @@
 ; CHECK-NEXT: br i1 %a, label %entry.split, label %abort0.split
 
 ; CHECK: entry.split:
-; CHECK-NEXT: br i1 %b, label %entry.split.split, label %abort1.split
+; CHECK-NEXT: br i1 %b, label %for.body, label %abort1.split
 
 ; CHECK: for.body:
 ; CHECK-NEXT: br label %for.body
Index: llvm/trunk/test/Transforms/SimplifyCFG/UncondBranchToHeader.ll
===================================================================
--- llvm/trunk/test/Transforms/SimplifyCFG/UncondBranchToHeader.ll
+++ llvm/trunk/test/Transforms/SimplifyCFG/UncondBranchToHeader.ll
@@ -0,0 +1,18 @@
+; RUN: opt < %s -simplifycfg -S | FileCheck %s
+
+; Check that we can get rid of empty block leading to header
+; if it does not introduce new edge.
+define i32 @test(i32 %c) {
+entry:
+  br label %header
+header:
+  %i = phi i32 [0, %entry], [%i.1, %backedge]
+  %i.1 = add i32 %i, 1
+  %cmp = icmp slt i32 %i.1, %c
+  br i1 %cmp, label %backedge, label %exit
+; CHECK-NOT: backedge:
+backedge:
+  br label %header
+exit:
+  ret i32 %i
+}