Index: llvm/lib/Transforms/Scalar/LoopFlatten.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LoopFlatten.cpp
+++ llvm/lib/Transforms/Scalar/LoopFlatten.cpp
@@ -679,7 +679,18 @@
   auto *AC = &AM.getResult<AssumptionAnalysis>(F);
   auto *TTI = &AM.getResult<TargetIRAnalysis>(F);
 
-  if (!Flatten(DT, LI, SE, AC, TTI))
+  bool Changed = false;
+
+  // The loop flattening pass requires loops to be in simplified form.
+  // Running this pass will simplify all loops,
+  // regardless of whether anything ends up being flattened.
+  for (auto &L : *LI)
+    Changed |=
+        simplifyLoop(L, DT, LI, SE, AC, nullptr, false /* PreserveLCSSA */);
+
+  Changed |= Flatten(DT, LI, SE, AC, TTI);
+
+  if (!Changed)
     return PreservedAnalyses::all();
 
   return PreservedAnalyses::none();
Index: llvm/test/Transforms/LoopFlatten/loop-flatten-simplify-cfg.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopFlatten/loop-flatten-simplify-cfg.ll
@@ -0,0 +1,82 @@
+;; This test was created to ensure that the LoopFlatten pass can
+;; operate on loops that are not in simplified form before applying the pass.
+;;
+;; It was generated by running following command:
+;; clang test.c -target aarch64-arm-none-eabi -Ofast -mllvm -enable-loop-flatten -fno-vectorize -fno-unroll-loops -S -emit-llvm -mllvm -opt-bisect-limit=50 -S -emit-llvm
+;; Where test.c:
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;
+;;void add(unsigned N, int *A, short val) {
+;; int i,j;
+;; for (i=0; i<N; i++)
+;;  for (j=0; j<N; j++)
+;;   A[i*N+j] += val;
+;;}
+;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+; RUN: opt < %s -S -loop-flatten  -simplifycfg -verify-loop-info -verify-dom-info -verify-scev -verify | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+
+define void @test(i32 %N, i32* nocapture %A, i16 %val) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[VAL:%.*]] to i32
+; CHECK-NEXT:    [[CMP_NOT:%.*]] = icmp eq i32 [[N:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP_NOT]], label [[FOR_END:%.*]], label [[FOR_COND_PREHEADER_PREHEADER:%.*]]
+; CHECK:       for.cond.preheader.preheader:
+; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[N]] to i64
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i32 [[N]] to i64
+; CHECK-NEXT:    [[FLATTEN_TRIPCOUNT:%.*]] = mul i64 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    br label [[FOR_COND_PREHEADER:%.*]]
+; CHECK:       for.cond.preheader:
+; CHECK-NEXT:    [[INDVAR1:%.*]] = phi i64 [ 0, [[FOR_COND_PREHEADER_PREHEADER]] ], [ [[INDVAR_NEXT2:%.*]], [[FOR_COND_PREHEADER]] ]
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc i64 [[INDVAR1]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[TMP2]], [[N]]
+; CHECK-NEXT:    [[FLATTEN_TRUNCIV:%.*]] = trunc i64 [[INDVAR1]] to i32
+; CHECK-NEXT:    [[TMP3:%.*]] = trunc i64 0 to i32
+; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[TMP3]], [[MUL]]
+; CHECK-NEXT:    [[IDXPROM:%.*]] = zext i32 [[FLATTEN_TRUNCIV]] to i64
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[IDXPROM]]
+; CHECK-NEXT:    [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP4]], [[CONV]]
+; CHECK-NEXT:    store i32 [[ADD4]], i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[INDVAR_NEXT:%.*]] = add i64 0, 1
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ult i64 [[INDVAR_NEXT]], [[TMP0]]
+; CHECK-NEXT:    [[INDVAR_NEXT2]] = add i64 [[INDVAR1]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[INDVAR_NEXT2]], [[FLATTEN_TRIPCOUNT]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND_PREHEADER]], label [[FOR_END]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %conv = sext i16 %val to i32
+  %cmp.not = icmp eq i32 %N, 0
+  br i1 %cmp.not, label %for.end, label %for.cond.preheader
+
+for.cond.preheader:
+  %i= phi i32 [ %inc6, %for.cond.for.inc_crit_edge ], [ 0, %entry ]
+  %mul = mul i32 %i, %N
+  br label %for.body
+
+for.body:
+  %j = phi i32 [ 0, %for.cond.preheader ], [ %inc, %for.body ]
+  %add = add i32 %j, %mul
+  %idxprom = zext i32 %add to i64
+  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %idxprom
+  %0 = load i32, i32* %arrayidx, align 4
+  %add4 = add nsw i32 %0, %conv
+  store i32 %add4, i32* %arrayidx, align 4
+  %inc = add nuw nsw i32 %j, 1
+  %cmp2 = icmp ult i32 %inc, %N
+  br i1 %cmp2, label %for.body, label %for.cond.for.inc_crit_edge
+
+for.cond.for.inc_crit_edge:
+  %inc6 = add nuw nsw i32 %i, 1
+  %cmp = icmp ult i32 %inc6, %N
+  br i1 %cmp, label %for.cond.preheader, label %for.end
+
+for.end:
+  ret void
+}