2 files changed, 21 insertions, 7 deletions

diff --git a/llvm/lib/Transforms/Utils/BasicBlockUtils.cpp b/llvm/lib/Transforms/Utils/BasicBlockUtils.cpp
index aa7b933022c..a04092e54a9 100644
--- a/llvm/lib/Transforms/Utils/BasicBlockUtils.cpp
+++ b/llvm/lib/Transforms/Utils/BasicBlockUtils.cpp
@@ -566,7 +566,13 @@ BasicBlock *llvm::SplitBlockPredecessors(BasicBlock *BB,
 
   // The new block unconditionally branches to the old block.
   BranchInst *BI = BranchInst::Create(BB, NewBB);
-  BI->setDebugLoc(BB->getFirstNonPHIOrDbg()->getDebugLoc());
+  // Splitting the precedessors of a loop header creates a preheader block.
+  if (LI && LI->isLoopHeader(BB))
+    // Using the loop start line number prevents debuggers stepping into the
+    // loop body for this instruction.
+    BI->setDebugLoc(LI->getLoopFor(BB)->getStartLoc());
+  else
+    BI->setDebugLoc(BB->getFirstNonPHIOrDbg()->getDebugLoc());
 
   // Move the edges from Preds to point to NewBB instead of BB.
   for (unsigned i = 0, e = Preds.size(); i != e; ++i) {
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 4f043448e4e..806cd52cbc2 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2894,11 +2894,11 @@ BasicBlock *InnerLoopVectorizer::createVectorizedLoopSkeleton() {
         CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, Count,
                         CountRoundDown, "cmp.n", MiddleBlock->getTerminator());
 
-    // Provide correct stepping behaviour by using the same DebugLoc as the
-    // scalar loop latch branch cmp if it exists.
-    if (CmpInst *ScalarLatchCmp =
-            dyn_cast_or_null<CmpInst>(ScalarLatchBr->getCondition()))
-      cast<Instruction>(CmpN)->setDebugLoc(ScalarLatchCmp->getDebugLoc());
+    // Here we use the same DebugLoc as the scalar loop latch branch instead
+    // of the corresponding compare because they may have ended up with
+    // different line numbers and we want to avoid awkward line stepping while
+    // debugging. Eg. if the compare has got a line number inside the loop.
+    cast<Instruction>(CmpN)->setDebugLoc(ScalarLatchBr->getDebugLoc());
   }
 
   BranchInst *BrInst = BranchInst::Create(ExitBlock, ScalarPH, CmpN);
@@ -3631,7 +3631,15 @@ void InnerLoopVectorizer::fixReduction(PHINode *Phi) {
   // Reduce all of the unrolled parts into a single vector.
   Value *ReducedPartRdx = VectorLoopValueMap.getVectorValue(LoopExitInst, 0);
   unsigned Op = RecurrenceDescriptor::getRecurrenceBinOp(RK);
-  setDebugLocFromInst(Builder, ReducedPartRdx);
+
+  // The middle block terminator has already been assigned a DebugLoc here (the
+  // OrigLoop's single latch terminator). We want the whole middle block to
+  // appear to execute on this line because: (a) it is all compiler generated,
+  // (b) these instructions are always executed after evaluating the latch
+  // conditional branch, and (c) other passes may add new predecessors which
+  // terminate on this line. This is the easiest way to ensure we don't
+  // accidently cause an extra step back into the loop while debugging.
+  setDebugLocFromInst(Builder, LoopMiddleBlock->getTerminator());
   for (unsigned Part = 1; Part < UF; ++Part) {
     Value *RdxPart = VectorLoopValueMap.getVectorValue(LoopExitInst, Part);
     if (Op != Instruction::ICmp && Op != Instruction::FCmp)