[LoopUnroll] Fix potentially incorrect SCEV invalidation in UnrollRuntime

[mkazantsev]

Summary

Current runtime unrolling invalidates parent loop saying that it might have changed
after the inner loop has changed, but it doesn't bother to do the same to its parents.
With patch rL329047, SCEV becomes much smarter about calculation of exit counts for
outer loops. We might need to invalidate not only the immediate parent, but also
any of its parents as well.

There is no clear evidence that there is some miscompile happening because of this
(at least I don't have such test), but the common sense says that the current code
is wrong.

[chandlerc]

I think the existing testing of the fact that the parent needs invalidation makes perfect sense to switch to the more general API. Good spot. Feel free to commit.

llvm/trunk/lib/Transforms/Utils/LoopUnrollRuntime.cpp

if (UseEpilogRemainder) {
     LatchBR->setCondition(IdxCmp);
   } else {
     // Connect the prolog code to the original loop and update the
     // PHI functions.
     ConnectProlog(L, BECount, Count, PrologExit, LatchExit, PreHeader,
                   NewPreHeader, VMap, DT, LI, PreserveLCSSA);
   }
 
-  // If this loop is nested, then the loop unroller changes the code in the
-  // parent loop, so the Scalar Evolution pass needs to be run again.
-  if (Loop *ParentLoop = L->getParentLoop())
-    SE->forgetLoop(ParentLoop);
+  // If this loop is nested, then the loop unroller changes the code in the any
+  // of its parent loops, so the Scalar Evolution pass needs to be run again.
+  SE->forgetTopmostLoop(L);
 
   // Canonicalize to LoopSimplifyForm both original and remainder loops. We
   // cannot rely on the LoopUnrollPass to do this because it only does
   // canonicalization for parent/subloops and not the sibling loops.
   if (OtherExits.size() > 0) {
     // Generate dedicated exit blocks for the original loop, to preserve
     // LoopSimplifyForm.
     formDedicatedExitBlocks(L, DT, LI, PreserveLCSSA);