diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6483,9 +6483,10 @@
     // if-converted. This means that the block's instructions (aside from
     // stores and instructions that may divide by zero) will now be
     // unconditionally executed. For the scalar case, we may not always execute
-    // the predicated block. Thus, scale the block's cost by the probability of
-    // executing it.
-    if (VF.isScalar() && blockNeedsPredication(BB))
+    // the predicated block, if it is an if-else block. Thus, scale the block's
+    // cost by the probability of executing it. blockNeedsPredication from
+    // Legal is used so as to not include all blocks in tail folded loops.
+    if (VF.isScalar() && Legal->blockNeedsPredication(BB))
       BlockCost.first /= getReciprocalPredBlockProb();
 
     Cost.first += BlockCost.first;
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
--- a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
@@ -15,7 +15,7 @@
 ; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %add1, i32* %arrayidx2, align 4
 ; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction:   %exitcond.not = icmp eq i32 %add, %n
 ; CHECK-COST-NEXT: LV: Found an estimated cost of 0 for VF 1 For instruction:   br i1 %exitcond.not, label %exit.loopexit, label %for.body
-; CHECK-COST-NEXT: LV: Scalar loop costs: 2.
+; CHECK-COST-NEXT: LV: Scalar loop costs: 5.
 
 entry:
   %cmp8 = icmp sgt i32 %n, 0