diff --git a/clang/test/OpenMP/cancel_codegen.cpp b/clang/test/OpenMP/cancel_codegen.cpp
--- a/clang/test/OpenMP/cancel_codegen.cpp
+++ b/clang/test/OpenMP/cancel_codegen.cpp
@@ -1324,14 +1324,6 @@
 // CHECK3-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    [[ARGC_ADDR:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    [[ARGV_ADDR:%.*]] = alloca i8**, align 8
-// CHECK3-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
-// CHECK3-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
@@ -1348,6 +1340,14 @@
 // CHECK3-NEXT:    store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
 // CHECK3-NEXT:    store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
 // CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
+// CHECK3-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
+// CHECK3-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK3-NEXT:    br label [[OMP_PARALLEL:%.*]]
 // CHECK3:       omp_parallel:
 // CHECK3-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8***)* @main..omp_par to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]], i8*** [[ARGV_ADDR]])
@@ -1951,14 +1951,6 @@
 // CHECK4-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    [[ARGC_ADDR:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    [[ARGV_ADDR:%.*]] = alloca i8**, align 8
-// CHECK4-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
-// CHECK4-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
@@ -1975,6 +1967,14 @@
 // CHECK4-NEXT:    store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
 // CHECK4-NEXT:    store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
 // CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
+// CHECK4-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
+// CHECK4-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK4-NEXT:    br label [[OMP_PARALLEL:%.*]]
 // CHECK4:       omp_parallel:
 // CHECK4-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8***)* @main..omp_par to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]], i8*** [[ARGV_ADDR]])
@@ -3818,14 +3818,6 @@
 // CHECK9-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    [[ARGC_ADDR:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    [[ARGV_ADDR:%.*]] = alloca i8**, align 8
-// CHECK9-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
-// CHECK9-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
@@ -3842,6 +3834,14 @@
 // CHECK9-NEXT:    store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
 // CHECK9-NEXT:    store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
 // CHECK9-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
+// CHECK9-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
+// CHECK9-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK9-NEXT:    br label [[OMP_PARALLEL:%.*]]
 // CHECK9:       omp_parallel:
 // CHECK9-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8***)* @main..omp_par to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]], i8*** [[ARGV_ADDR]])
@@ -4445,14 +4445,6 @@
 // CHECK10-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    [[ARGC_ADDR:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    [[ARGV_ADDR:%.*]] = alloca i8**, align 8
-// CHECK10-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
-// CHECK10-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    [[DOTOMP_IV:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    [[TMP:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
@@ -4469,6 +4461,14 @@
 // CHECK10-NEXT:    store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
 // CHECK10-NEXT:    store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
 // CHECK10-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
+// CHECK10-NEXT:    [[P_LASTITER:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_LOWERBOUND:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_UPPERBOUND:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_STRIDE:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_LASTITER27:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_LOWERBOUND28:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_UPPERBOUND29:%.*]] = alloca i32, align 4
+// CHECK10-NEXT:    [[P_STRIDE30:%.*]] = alloca i32, align 4
 // CHECK10-NEXT:    br label [[OMP_PARALLEL:%.*]]
 // CHECK10:       omp_parallel:
 // CHECK10-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8***)* @main..omp_par to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]], i8*** [[ARGV_ADDR]])
diff --git a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
--- a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -993,6 +993,8 @@
   Value *ST = ConstantInt::get(I32Ty, 1);
   llvm::CanonicalLoopInfo *LoopInfo = createCanonicalLoop(
       Loc, LoopBodyGenCB, LB, UB, ST, true, false, AllocaIP, "section_loop");
+  Builder.SetInsertPoint(AllocaIP.getBlock()->getTerminator());
+  AllocaIP = Builder.saveIP();
   InsertPointTy AfterIP =
       applyStaticWorkshareLoop(Loc.DL, LoopInfo, AllocaIP, true);
   BasicBlock *LoopAfterBB = AfterIP.getBlock();
diff --git a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
--- a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
+++ b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
@@ -3487,6 +3487,37 @@
   EXPECT_TRUE(isSimpleBinaryReduction(Bitcast, FnReductionBB, &Opcode));
 }
 
+TEST_F(OpenMPIRBuilderTest, CreateSectionsSimple) {
+  using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
+  using BodyGenCallbackTy = llvm::OpenMPIRBuilder::StorableBodyGenCallbackTy;
+  OpenMPIRBuilder OMPBuilder(*M);
+  OMPBuilder.initialize();
+  F->setName("func");
+  IRBuilder<> Builder(BB);
+  OpenMPIRBuilder::LocationDescription Loc({Builder.saveIP(), DL});
+  llvm::SmallVector<BodyGenCallbackTy, 4> SectionCBVector;
+  llvm::SmallVector<BasicBlock *, 4> CaseBBs;
+
+  auto FiniCB = [&](InsertPointTy IP) {};
+  auto SectionCB = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP,
+                       BasicBlock &FiniBB) {
+    Builder.restoreIP(CodeGenIP);
+    Builder.CreateBr(&FiniBB);
+  };
+  SectionCBVector.push_back(SectionCB);
+
+  auto PrivCB = [](InsertPointTy AllocaIP, InsertPointTy CodeGenIP,
+                   llvm::Value &, llvm::Value &Val,
+                   llvm::Value *&ReplVal) { return CodeGenIP; };
+  IRBuilder<>::InsertPoint AllocaIP(&F->getEntryBlock(),
+                                    F->getEntryBlock().getFirstInsertionPt());
+  Builder.restoreIP(OMPBuilder.createSections(Loc, AllocaIP, SectionCBVector,
+                                              PrivCB, FiniCB, false, false));
+  Builder.CreateRetVoid(); // Required at the end of the function
+  EXPECT_NE(F->getEntryBlock().getTerminator(), nullptr);
+  EXPECT_FALSE(verifyModule(*M, &errs()));
+}
+
 TEST_F(OpenMPIRBuilderTest, CreateSections) {
   using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
   using BodyGenCallbackTy = llvm::OpenMPIRBuilder::StorableBodyGenCallbackTy;
@@ -3607,6 +3638,7 @@
 
   ASSERT_EQ(NumBodiesGenerated, 2U);
   ASSERT_EQ(NumFiniCBCalls, 1U);
+  EXPECT_FALSE(verifyModule(*M, &errs()));
 }
 
 TEST_F(OpenMPIRBuilderTest, CreateOffloadMaptypes) {