diff --git a/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp b/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
--- a/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
@@ -87,6 +87,7 @@
 #include "llvm/IR/Value.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
+#include "llvm/Support/Alignment.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -205,6 +206,14 @@
              "to results."),
     cl::Hidden, cl::init(true));
 
+// TODO: This default value follows MSan. DFSan may use a different value.
+static cl::opt<int> ClInstrumentationWithCallThreshold(
+    "dfsan-instrumentation-with-call-threshold",
+    cl::desc("If the function being instrumented requires more than "
+             "this number of origin stores, use callbacks instead of "
+             "inline checks (-1 means never use callbacks)."),
+    cl::Hidden, cl::init(3500));
+
 // Controls how to track origins.
 // * 0: do not track origins.
 // * 1: track origins at memory store operations.
@@ -427,6 +436,7 @@
   FunctionCallee DFSanMaybeStoreOriginFn;
   SmallPtrSet<Value *, 16> DFSanRuntimeFunctions;
   MDNode *ColdCallWeights;
+  MDNode *OriginStoreWeights;
   DFSanABIList ABIList;
   DenseMap<Value *, Function *> UnwrappedFnMap;
   AttrBuilder ReadOnlyNoneAttrs;
@@ -434,8 +444,8 @@
 
   Value *getShadowOffset(Value *Addr, IRBuilder<> &IRB);
   Value *getShadowAddress(Value *Addr, Instruction *Pos);
-  // std::pair<Value *, Value *>
-  // getShadowOriginAddress(Value *Addr, Align InstAlignment, Instruction *Pos);
+  std::pair<Value *, Value *>
+  getShadowOriginAddress(Value *Addr, Align InstAlignment, Instruction *Pos);
   bool isInstrumented(const Function *F);
   bool isInstrumented(const GlobalAlias *GA);
   FunctionType *getArgsFunctionType(FunctionType *T);
@@ -508,6 +518,8 @@
   DenseMap<Value *, Value *> ValShadowMap;
   DenseMap<Value *, Value *> ValOriginMap;
   DenseMap<AllocaInst *, AllocaInst *> AllocaShadowMap;
+  DenseMap<AllocaInst *, AllocaInst *> AllocaOriginMap;
+
   std::vector<std::pair<PHINode *, PHINode *>> PHIFixups;
   DenseSet<Instruction *> SkipInsts;
   std::vector<Value *> NonZeroChecks;
@@ -576,8 +588,9 @@
   Value *combineOperandShadows(Instruction *Inst);
   Value *loadShadow(Value *ShadowAddr, uint64_t Size, uint64_t Align,
                     Instruction *Pos);
-  void storePrimitiveShadow(Value *Addr, uint64_t Size, Align Alignment,
-                            Value *PrimitiveShadow, Instruction *Pos);
+  void storePrimitiveShadowOrigin(Value *Addr, uint64_t Size,
+                                  Align InstAlignment, Value *PrimitiveShadow,
+                                  Value *Origin, Instruction *Pos);
   /// Applies PrimitiveShadow to all primitive subtypes of T, returning
   /// the expanded shadow value.
   ///
@@ -595,6 +608,8 @@
   /// CTP(other types, PS) = PS
   Value *collapseToPrimitiveShadow(Value *Shadow, Instruction *Pos);
 
+  void incNumOfOriginStores();
+
   void storeZeroPrimitiveShadow(Value *Addr, uint64_t Size, Align ShadowAlign,
                                 Instruction *Pos);
 
@@ -619,6 +634,34 @@
   /// The fast path of loading shadow in fast-16-label mode.
   Value *loadFast16ShadowFast(Value *ShadowAddr, uint64_t Size,
                               Align ShadowAlign, Instruction *Pos);
+
+  /// Returns a chain at the current stack with previous origin V.
+  Value *updateOrigin(Value *V, IRBuilder<> &IRB);
+
+  /// Creates an Intptr = Origin | Origin << 32 if Intptr's size is 64. Returns
+  /// Origin otherwise.
+  Value *originToIntptr(IRBuilder<> &IRB, Value *Origin);
+
+  /// Stores Origin into the address range [OriginAddr, OriginAddr + Size).
+  void paintOrigin(IRBuilder<> &IRB, Value *Origin, Value *OriginAddr,
+                   uint64_t Size, Align Alignment);
+
+  /// Stores Origin in terms of its Shadow value.
+  /// * Do not write origins for zero shadows because we do not trace origins
+  ///   for untainted sinks.
+  /// * Use __dfsan_maybe_store_origin if there are too many origin store
+  ///   instrumentations.
+  void storeOrigin(Instruction *Pos, Value *Addr, uint64_t Size, Value *Shadow,
+                   Value *Origin, Value *OriginAddr, Align InstAlignment);
+
+  /// Convert a scalar value to an i1 by comparing with 0.
+  Value *convertToBool(Value *V, IRBuilder<> &IRB, const Twine &name = "");
+
+  Align getOriginAlign(Align InstAlignment);
+
+  bool shouldInstrumentationWithCall();
+
+  int NumOfOriginStores = 0;
 };
 
 class DFSanVisitor : public InstVisitor<DFSanVisitor> {
@@ -824,6 +867,13 @@
   llvm_unreachable("Unexpected shadow type");
 }
 
+void DFSanFunction::incNumOfOriginStores() { ++NumOfOriginStores; }
+
+bool DFSanFunction::shouldInstrumentationWithCall() {
+  return ClInstrumentationWithCallThreshold >= 0 &&
+         NumOfOriginStores >= ClInstrumentationWithCallThreshold;
+}
+
 Value *DFSanFunction::expandFromPrimitiveShadow(Type *T, Value *PrimitiveShadow,
                                                 Instruction *Pos) {
   Type *ShadowTy = DFS.getShadowTy(T);
@@ -993,6 +1043,7 @@
                         /*isVarArg=*/false);
 
   ColdCallWeights = MDBuilder(*Ctx).createBranchWeights(1, 1000);
+  OriginStoreWeights = MDBuilder(*Ctx).createBranchWeights(1, 1000);
   return true;
 }
 
@@ -1689,7 +1740,7 @@
   return IRB.CreateAnd(IRB.CreatePtrToInt(Addr, IntptrTy),
                        IRB.CreatePtrToInt(ShadowPtrMaskValue, IntptrTy));
 }
-/*
+
 std::pair<Value *, Value *>
 DataFlowSanitizer::getShadowOriginAddress(Value *Addr, Align InstAlignment,
                                           Instruction *Pos) {
@@ -1712,7 +1763,7 @@
   }
   return {ShadowPtr, OriginPtr};
 }
-*/
+
 Value *DataFlowSanitizer::getShadowAddress(Value *Addr, Instruction *Pos) {
   // Returns (Addr & shadow_mask) x 2
   IRBuilder<> IRB(Pos);
@@ -1886,6 +1937,11 @@
   return Align(Alignment.value() * DFS.ShadowWidthBytes);
 }
 
+Align DFSanFunction::getOriginAlign(Align InstAlignment) {
+  const Align Alignment = llvm::assumeAligned(InstAlignment.value());
+  return Align(std::max(kMinOriginAlignment, Alignment));
+}
+
 Value *DFSanFunction::loadFast16ShadowFast(Value *ShadowAddr, uint64_t Size,
                                            Align ShadowAlign,
                                            Instruction *Pos) {
@@ -2097,6 +2153,97 @@
   }
 }
 
+Value *DFSanFunction::updateOrigin(Value *V, IRBuilder<> &IRB) {
+  if (!DFS.shouldTrackOrigins())
+    return V;
+  return IRB.CreateCall(DFS.DFSanChainOriginFn, V);
+}
+
+Value *DFSanFunction::originToIntptr(IRBuilder<> &IRB, Value *Origin) {
+  const unsigned OriginSize = DataFlowSanitizer::OriginWidthBytes;
+  const DataLayout &DL = F->getParent()->getDataLayout();
+  unsigned IntptrSize = DL.getTypeStoreSize(DFS.IntptrTy);
+  if (IntptrSize == OriginSize)
+    return Origin;
+  assert(IntptrSize == OriginSize * 2);
+  Origin = IRB.CreateIntCast(Origin, DFS.IntptrTy, /* isSigned */ false);
+  return IRB.CreateOr(Origin, IRB.CreateShl(Origin, OriginSize * 8));
+}
+
+void DFSanFunction::paintOrigin(IRBuilder<> &IRB, Value *Origin,
+                                Value *OriginAddr, uint64_t Size,
+                                Align Alignment) {
+  const unsigned OriginSize = DataFlowSanitizer::OriginWidthBytes;
+  const DataLayout &DL = F->getParent()->getDataLayout();
+  const Align IntptrAlignment = DL.getABITypeAlign(DFS.IntptrTy);
+  unsigned IntptrSize = DL.getTypeStoreSize(DFS.IntptrTy);
+  assert(IntptrAlignment >= kMinOriginAlignment);
+  assert(IntptrSize >= OriginSize);
+
+  unsigned Ofs = 0;
+  Align CurrentAlignment = Alignment;
+  if (Alignment >= IntptrAlignment && IntptrSize > OriginSize) {
+    Value *IntptrOrigin = originToIntptr(IRB, Origin);
+    Value *IntptrOriginPtr =
+        IRB.CreatePointerCast(OriginAddr, PointerType::get(DFS.IntptrTy, 0));
+    for (unsigned I = 0; I < Size / IntptrSize; ++I) {
+      Value *Ptr = I ? IRB.CreateConstGEP1_32(DFS.IntptrTy, IntptrOriginPtr, I)
+                     : IntptrOriginPtr;
+      IRB.CreateAlignedStore(IntptrOrigin, Ptr, CurrentAlignment);
+      Ofs += IntptrSize / OriginSize;
+      CurrentAlignment = IntptrAlignment;
+    }
+  }
+
+  for (unsigned I = Ofs; I < (Size + OriginSize - 1) / OriginSize; ++I) {
+    Value *GEP =
+        I ? IRB.CreateConstGEP1_32(DFS.OriginTy, OriginAddr, I) : OriginAddr;
+    IRB.CreateAlignedStore(Origin, GEP, CurrentAlignment);
+    CurrentAlignment = kMinOriginAlignment;
+  }
+}
+
+Value *DFSanFunction::convertToBool(Value *V, IRBuilder<> &IRB,
+                                    const Twine &name) {
+  Type *VTy = V->getType();
+  assert(VTy->isIntegerTy());
+  if (VTy->getIntegerBitWidth() == 1)
+    // Just converting a bool to a bool, so do nothing.
+    return V;
+  return IRB.CreateICmpNE(V, ConstantInt::get(VTy, 0), name);
+}
+
+void DFSanFunction::storeOrigin(Instruction *Pos, Value *Addr, uint64_t Size,
+                                Value *Shadow, Value *Origin, Value *OriginAddr,
+                                Align InstAlignment) {
+  // Do not write origins for zero shadows because we do not trace origins for
+  // untainted sinks.
+  const Align OriginAlignment = getOriginAlign(InstAlignment);
+  Value *CollapsedShadow = collapseToPrimitiveShadow(Shadow, Pos);
+  IRBuilder<> IRB(Pos);
+  if (auto *ConstantShadow = dyn_cast<Constant>(CollapsedShadow)) {
+    if (!ConstantShadow->isZeroValue())
+      paintOrigin(IRB, updateOrigin(Origin, IRB), OriginAddr, Size,
+                  OriginAlignment);
+    return;
+  }
+
+  if (shouldInstrumentationWithCall()) {
+    IRB.CreateCall(DFS.DFSanMaybeStoreOriginFn,
+                   {CollapsedShadow,
+                    IRB.CreatePointerCast(Addr, IRB.getInt8PtrTy()),
+                    ConstantInt::get(DFS.IntptrTy, Size), Origin});
+  } else {
+    Value *Cmp = convertToBool(CollapsedShadow, IRB, "_dfscmp");
+    Instruction *CheckTerm = SplitBlockAndInsertIfThen(
+        Cmp, &*IRB.GetInsertPoint(), false, DFS.OriginStoreWeights, &DT);
+    IRBuilder<> IRBNew(CheckTerm);
+    paintOrigin(IRBNew, updateOrigin(Origin, IRBNew), OriginAddr, Size,
+                OriginAlignment);
+    incNumOfOriginStores();
+  }
+}
+
 void DFSanFunction::storeZeroPrimitiveShadow(Value *Addr, uint64_t Size,
                                              Align ShadowAlign,
                                              Instruction *Pos) {
@@ -2111,30 +2258,46 @@
   // Do not write origins for 0 shadows because we do not trace origins for
   // untainted sinks.
 }
-void DFSanFunction::storePrimitiveShadow(Value *Addr, uint64_t Size,
-                                         Align Alignment,
-                                         Value *PrimitiveShadow,
-                                         Instruction *Pos) {
+
+void DFSanFunction::storePrimitiveShadowOrigin(Value *Addr, uint64_t Size,
+                                               Align InstAlignment,
+                                               Value *PrimitiveShadow,
+                                               Value *Origin,
+                                               Instruction *Pos) {
+  const bool ShouldTrackOrigins = DFS.shouldTrackOrigins() && Origin;
+
   if (AllocaInst *AI = dyn_cast<AllocaInst>(Addr)) {
-    const auto i = AllocaShadowMap.find(AI);
-    if (i != AllocaShadowMap.end()) {
+    const auto SI = AllocaShadowMap.find(AI);
+    if (SI != AllocaShadowMap.end()) {
       IRBuilder<> IRB(Pos);
-      IRB.CreateStore(PrimitiveShadow, i->second);
+      IRB.CreateStore(PrimitiveShadow, SI->second);
+
+      // Do not write origins for 0 shadows because we do not trace origins for
+      // untainted sinks.
+      if (ShouldTrackOrigins && !DFS.isZeroShadow(PrimitiveShadow)) {
+        const auto OI = AllocaOriginMap.find(AI);
+        assert(OI != AllocaOriginMap.end() && Origin);
+        IRB.CreateStore(Origin, OI->second);
+      }
       return;
     }
   }
 
-  const Align ShadowAlign(Alignment.value() * DFS.ShadowWidthBytes);
+  const Align ShadowAlign = getShadowAlign(InstAlignment);
   if (DFS.isZeroShadow(PrimitiveShadow)) {
     storeZeroPrimitiveShadow(Addr, Size, ShadowAlign, Pos);
     return;
   }
 
   IRBuilder<> IRB(Pos);
-  Value *ShadowAddr = DFS.getShadowAddress(Addr, Pos);
+  Value *ShadowAddr, *OriginAddr;
+  std::tie(ShadowAddr, OriginAddr) =
+      DFS.getShadowOriginAddress(Addr, InstAlignment, Pos);
+
   const unsigned ShadowVecSize = 128 / DFS.ShadowWidthBits;
   uint64_t Offset = 0;
-  if (Size >= ShadowVecSize) {
+  uint64_t LeftSize = Size;
+  if (LeftSize >= ShadowVecSize) {
     auto *ShadowVecTy =
         FixedVectorType::get(DFS.PrimitiveShadowTy, ShadowVecSize);
     Value *ShadowVec = UndefValue::get(ShadowVecTy);
@@ -2149,18 +2312,23 @@
       Value *CurShadowVecAddr =
           IRB.CreateConstGEP1_32(ShadowVecTy, ShadowVecAddr, Offset);
       IRB.CreateAlignedStore(ShadowVec, CurShadowVecAddr, ShadowAlign);
-      Size -= ShadowVecSize;
+      LeftSize -= ShadowVecSize;
       ++Offset;
-    } while (Size >= ShadowVecSize);
+    } while (LeftSize >= ShadowVecSize);
     Offset *= ShadowVecSize;
   }
-  while (Size > 0) {
+  while (LeftSize > 0) {
     Value *CurShadowAddr =
         IRB.CreateConstGEP1_32(DFS.PrimitiveShadowTy, ShadowAddr, Offset);
     IRB.CreateAlignedStore(PrimitiveShadow, CurShadowAddr, ShadowAlign);
-    --Size;
+    --LeftSize;
     ++Offset;
   }
+
+  if (ShouldTrackOrigins) {
+    storeOrigin(Pos, Addr, Size, PrimitiveShadow, Origin, OriginAddr,
+                InstAlignment);
+  }
 }
 
 static AtomicOrdering addReleaseOrdering(AtomicOrdering AO) {
@@ -2195,19 +2363,36 @@
   if (SI.isAtomic())
     SI.setOrdering(addReleaseOrdering(SI.getOrdering()));
 
-  const Align Alignment = ClPreserveAlignment ? SI.getAlign() : Align(1);
+  const bool ShouldTrackOrigins =
+      DFSF.DFS.shouldTrackOrigins() && !SI.isAtomic();
+  std::vector<Value *> Shadows;
+  std::vector<Value *> Origins;
 
   Value *Shadow =
       SI.isAtomic() ? DFSF.DFS.getZeroShadow(Val) : DFSF.getShadow(Val);
+
+  if (ShouldTrackOrigins) {
+    Shadows.push_back(Shadow);
+    Origins.push_back(DFSF.getOrigin(Val));
+  }
+
   Value *PrimitiveShadow;
   if (ClCombinePointerLabelsOnStore) {
     Value *PtrShadow = DFSF.getShadow(SI.getPointerOperand());
+    if (ShouldTrackOrigins) {
+      Shadows.push_back(PtrShadow);
+      Origins.push_back(DFSF.getOrigin(SI.getPointerOperand()));
+    }
     PrimitiveShadow = DFSF.combineShadows(Shadow, PtrShadow, &SI);
   } else {
     PrimitiveShadow = DFSF.collapseToPrimitiveShadow(Shadow, &SI);
   }
-  DFSF.storePrimitiveShadow(SI.getPointerOperand(), Size, Alignment,
-                            PrimitiveShadow, &SI);
+  Value *Origin = nullptr;
+  if (ShouldTrackOrigins) {
+    Origin = DFSF.combineOrigins(Shadows, Origins, &SI);
+  }
+  DFSF.storePrimitiveShadowOrigin(SI.getPointerOperand(), Size, SI.getAlign(),
+                                  PrimitiveShadow, Origin, &SI);
   if (ClEventCallbacks) {
     IRBuilder<> IRB(&SI);
     Value *Addr8 = IRB.CreateBitCast(SI.getPointerOperand(), DFSF.DFS.Int8Ptr);
@@ -2327,8 +2512,13 @@
   if (AllLoadsStores) {
     IRBuilder<> IRB(&I);
     DFSF.AllocaShadowMap[&I] = IRB.CreateAlloca(DFSF.DFS.PrimitiveShadowTy);
+    if (DFSF.DFS.shouldTrackOrigins()) {
+      DFSF.AllocaOriginMap[&I] =
+          IRB.CreateAlloca(DFSF.DFS.OriginTy, nullptr, "_dfsa");
+    }
   }
   DFSF.setShadow(&I, DFSF.DFS.ZeroPrimitiveShadow);
+  DFSF.setOrigin(&I, DFSF.DFS.ZeroOrigin);
 }
 
 void DFSanVisitor::visitSelectInst(SelectInst &I) {
diff --git a/llvm/test/Instrumentation/DataFlowSanitizer/origin_ldst.ll b/llvm/test/Instrumentation/DataFlowSanitizer/origin_ldst.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Instrumentation/DataFlowSanitizer/origin_ldst.ll
@@ -0,0 +1,169 @@
+; RUN: opt < %s -dfsan -dfsan-track-origins=1 -dfsan-fast-16-labels=true -S | FileCheck %s --check-prefix=CHECK
+; RUN: opt < %s -dfsan -dfsan-track-origins=1 -dfsan-fast-16-labels=true -dfsan-combine-pointer-labels-on-store=true -S | FileCheck %s --check-prefix=COMBINE_STORE_PTR
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @store_zero_to_non_escaped_alloca() {
+  ; CHECK: @"dfs$store_zero_to_non_escaped_alloca"
+  ; CHECK-NEXT: [[A:%.*]] = alloca i16, align 2
+  ; CHECK-NEXT: %_dfsa = alloca i32, align 4
+  ; CHECK-NEXT: %p = alloca i16, align 2
+  ; CHECK-NEXT: store i16 0, i16* [[A]], align 2
+  ; CHECK-NEXT: store i16 1, i16* %p, align 2
+  ; CHECK-NEXT: ret void
+  
+  %p = alloca i16
+  store i16 1, i16* %p
+  ret void
+}
+
+define void @store_nonzero_to_non_escaped_alloca(i16 %a) {
+  ; CHECK: @"dfs$store_nonzero_to_non_escaped_alloca"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 0), align 4
+  ; CHECK: %_dfsa = alloca i32, align 4
+  ; CHECK: store i32 [[AO]], i32* %_dfsa, align 4
+  
+  %p = alloca i16
+  store i16 %a, i16* %p
+  ret void
+}
+
+define i16* @store_zero_to_escaped_alloca() {
+  ; CHECK: @"dfs$store_zero_to_escaped_alloca"
+  ; CHECK: [[SA:%.*]] = bitcast i16* {{.*}} to i32*
+  ; CHECK_NEXT: store i32 0, i32* [[SA]], align 4
+  ; CHECK_NEXT: store i16 1, i16* %p, align 2
+  ; CHECK_NEXT: store i16 0, i16* bitcast ([100 x i64]* @__dfsan_retval_tls to i16*), align 2
+  
+  ; COMBINE_STORE_PTR: @"dfs$store_zero_to_escaped_alloca"
+  ; COMBINE_STORE_PTR: [[SA:%.*]] = bitcast i16* {{.*}} to i32*
+  ; COMBINE_STORE_PTR_NEXT: store i32 0, i32* [[SA]], align 4
+  ; COMBINE_STORE_PTR_NEXT: store i16 1, i16* %p, align 2
+  ; COMBINE_STORE_PTR_NEXT: store i16 0, i16* bitcast ([100 x i64]* @__dfsan_retval_tls to i16*), align 2
+
+  %p = alloca i16
+  store i16 1, i16* %p
+  ret i16* %p
+}
+
+define i16* @store_nonzero_to_escaped_alloca(i16 %a) {
+  ; CHECK: @"dfs$store_nonzero_to_escaped_alloca"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 0), align 4
+  ; CHECK: [[AS:%.*]] = load i16, i16* bitcast ([100 x i64]* @__dfsan_arg_tls to i16*), align 2
+  ; CHECK: [[INTP:%.*]] = ptrtoint {{.*}} %p to i64
+  ; CHECK: [[OFFSET:%.*]] = and i64 [[INTP]], -123145302310913
+  ; CHECK: [[ORIGIN_OFFSET:%.*]] = add i64 [[OFFSET]], 35184372088832
+  ; CHECK: [[ORIGIN_ADDR:%.*]] = and i64 [[ORIGIN_OFFSET]], -4
+  ; CHECK: [[ORIGIN_PTR:%.*]] = inttoptr i64 [[ORIGIN_ADDR]] to i32*
+  ; CHECK: %_dfscmp = icmp ne i16 [[AS]], 0
+  ; CHECK: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; CHECK: [[L1]]:
+  ; CHECK: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[AO]])
+  ; CHECK: store i32 [[NO]], i32* [[ORIGIN_PTR]], align 4
+  ; CHECK: br label %[[L2]]
+  ; CHECK: [[L2]]:
+  ; CHECK: store i16 %a, i16* %p, align 2
+  
+  ; COMBINE_STORE_PTR: @"dfs$store_nonzero_to_escaped_alloca"
+  ; COMBINE_STORE_PTR: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 0), align 4
+  ; COMBINE_STORE_PTR: [[AS:%.*]] = load i16, i16* bitcast ([100 x i64]* @__dfsan_arg_tls to i16*), align 2
+  ; COMBINE_STORE_PTR: [[INTP:%.*]] = ptrtoint {{.*}} %p to i64
+  ; COMBINE_STORE_PTR: [[OFFSET:%.*]] = and i64 [[INTP]], -123145302310913
+  ; COMBINE_STORE_PTR: [[ORIGIN_OFFSET:%.*]] = add i64 [[OFFSET]], 35184372088832
+  ; COMBINE_STORE_PTR: [[ORIGIN_ADDR:%.*]] = and i64 [[ORIGIN_OFFSET]], -4
+  ; COMBINE_STORE_PTR: [[ORIGIN_PTR:%.*]] = inttoptr i64 [[ORIGIN_ADDR]] to i32*
+  ; COMBINE_STORE_PTR: %_dfscmp = icmp ne i16 [[AS]], 0
+  ; COMBINE_STORE_PTR: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; COMBINE_STORE_PTR: [[L1]]:
+  ; COMBINE_STORE_PTR: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[AO]])
+  ; COMBINE_STORE_PTR: store i32 [[NO]], i32* [[ORIGIN_PTR]], align 4
+  ; COMBINE_STORE_PTR: br label %[[L2]]
+  ; COMBINE_STORE_PTR: [[L2]]:
+  ; COMBINE_STORE_PTR: store i16 %a, i16* %p, align 2
+  
+  %p = alloca i16
+  store i16 %a, i16* %p
+  ret i16* %p
+}
+
+define void @store64_align8(i64* %p, i64 %a) {
+  ; CHECK: @"dfs$store64_align8"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 1), align 4
+  ; CHECK: [[AS:%.*]] = load i16, i16* inttoptr (i64 add (i64 ptrtoint ([100 x i64]* @__dfsan_arg_tls to i64), i64 2) to i16*), align 2
+  ; CHECK: %_dfscmp = icmp ne i16 [[AS]], 0
+  ; CHECK: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; CHECK: [[L1]]:
+  ; CHECK: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[AO]])
+  ; CHECK: [[NO_ZEXT:%.*]] = zext i32 [[NO]] to i64
+  ; CHECK: [[NO_SHL:%.*]] = shl i64 [[NO_ZEXT]], 32
+  ; CHECK: [[NO2:%.*]] = or i64 [[NO_ZEXT]], [[NO_SHL]]
+  ; CHECK: [[O_PTR:%.*]] = bitcast i32* {{.*}} to i64*
+  ; CHECK: store i64 [[NO2]], i64* [[O_PTR]], align 8
+  ; CHECK: br label %[[L2]]
+  ; CHECK: [[L2]]:
+  ; CHECK: store i64 %a, i64* %p, align 8
+  
+  ; COMBINE_STORE_PTR: @"dfs$store64_align8"
+  ; COMBINE_STORE_PTR: [[PO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 0), align 4
+  ; COMBINE_STORE_PTR: [[PS:%.*]] = load i16, i16* bitcast ([100 x i64]* @__dfsan_arg_tls to i16*), align 2
+  ; COMBINE_STORE_PTR: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 1), align 4
+  ; COMBINE_STORE_PTR: [[AS:%.*]] = load i16, i16* inttoptr (i64 add (i64 ptrtoint ([100 x i64]* @__dfsan_arg_tls to i64), i64 2) to i16*), align 2
+  ; COMBINE_STORE_PTR: [[MS:%.*]] = or i16 [[AS]], [[PS]]
+  ; COMBINE_STORE_PTR: [[NE:%.*]] = icmp ne i16 [[PS]], 0
+  ; COMBINE_STORE_PTR: [[MO:%.*]] = select i1 [[NE]], i32 [[PO]], i32 [[AO]]
+  ; COMBINE_STORE_PTR: %_dfscmp = icmp ne i16 [[MS]], 0
+  ; COMBINE_STORE_PTR: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; COMBINE_STORE_PTR: [[L1]]:
+  ; COMBINE_STORE_PTR: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[MO]])
+  ; COMBINE_STORE_PTR: [[NO_ZEXT:%.*]] = zext i32 [[NO]] to i64
+  ; COMBINE_STORE_PTR: [[NO_SHL:%.*]] = shl i64 [[NO_ZEXT]], 32
+  ; COMBINE_STORE_PTR: [[NO2:%.*]] = or i64 [[NO_ZEXT]], [[NO_SHL]]
+  ; COMBINE_STORE_PTR: [[O_PTR:%.*]] = bitcast i32* {{.*}} to i64*
+  ; COMBINE_STORE_PTR: store i64 [[NO2]], i64* [[O_PTR]], align 8
+  ; COMBINE_STORE_PTR: br label %[[L2]]
+  ; COMBINE_STORE_PTR: [[L2]]:
+  ; COMBINE_STORE_PTR: store i64 %a, i64* %p, align 8
+  
+  store i64 %a, i64* %p
+  ret void
+}
+
+define void @store64_align2(i64* %p, i64 %a) {
+  ; CHECK: @"dfs$store64_align2"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 1), align 4
+  ; CHECK: [[AS:%.*]] = load i16, i16* inttoptr (i64 add (i64 ptrtoint ([100 x i64]* @__dfsan_arg_tls to i64), i64 2) to i16*), align 2
+  ; CHECK: %_dfscmp = icmp ne i16 [[AS]], 0
+  ; CHECK: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; CHECK: [[L1]]:
+  ; CHECK: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[AO]])
+  ; CHECK: store i32 [[NO]], i32* [[O_PTR0:%.*]], align 4
+  ; CHECK: [[O_PTR1:%.*]] = getelementptr i32, i32* [[O_PTR0]], i32 1
+  ; CHECK: store i32 [[NO]], i32* [[O_PTR1]], align 4
+  ; CHECK: [[L2]]:
+  ; CHECK: store i64 %a, i64* %p, align 2
+  
+  store i64 %a, i64* %p, align 2
+  ret void
+}
+
+define void @store96_align8(i96* %p, i96 %a) {
+  ; CHECK: @"dfs$store96_align8"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 1), align 4
+  ; CHECK: [[AS:%.*]] = load i16, i16* inttoptr (i64 add (i64 ptrtoint ([100 x i64]* @__dfsan_arg_tls to i64), i64 2) to i16*), align 2
+  ; CHECK: %_dfscmp = icmp ne i16 [[AS]], 0
+  ; CHECK: br i1 %_dfscmp, label %[[L1:.*]], label %[[L2:.*]],
+  ; CHECK: [[L1]]:
+  ; CHECK: [[NO:%.*]] = call i32 @__dfsan_chain_origin(i32 [[AO]])
+  ; CHECK: [[NO_ZEXT:%.*]] = zext i32 [[NO]] to i64
+  ; CHECK: [[NO_SHL:%.*]] = shl i64 [[NO_ZEXT]], 32
+  ; CHECK: [[NO2:%.*]] = or i64 [[NO_ZEXT]], [[NO_SHL]]
+  ; CHECK: [[O_PTR64:%.*]] = bitcast i32* [[O_PTR0:%.*]] to i64*
+  ; CHECK: store i64 [[NO2]], i64* [[O_PTR64]], align 8
+  ; CHECK: [[O_PTR1:%.*]] = getelementptr i32, i32* [[O_PTR0]], i32 2
+  ; CHECK: store i32 [[NO]], i32* [[O_PTR1]], align 8
+  ; CHECK: [[L2]]:
+  ; CHECK: store i96 %a, i96* %p, align 8
+  
+  store i96 %a, i96* %p, align 8
+  ret void
+}
diff --git a/llvm/test/Instrumentation/DataFlowSanitizer/origin_store_threshold.ll b/llvm/test/Instrumentation/DataFlowSanitizer/origin_store_threshold.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Instrumentation/DataFlowSanitizer/origin_store_threshold.ll
@@ -0,0 +1,18 @@
+; RUN: opt < %s -dfsan -dfsan-track-origins=1 -dfsan-fast-16-labels=true -dfsan-instrumentation-with-call-threshold=0 -S | FileCheck %s --check-prefix=CHECK
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @store_threshold([2 x i64]* %p, [2 x i64] %a) {
+  ; CHECK: @"dfs$store_threshold"
+  ; CHECK: [[AO:%.*]] = load i32, i32* getelementptr inbounds ([200 x i32], [200 x i32]* @__dfsan_arg_origin_tls, i64 0, i64 1), align 4
+  ; CHECK: [[AS:%.*]] = load [2 x i16], [2 x i16]* inttoptr (i64 add (i64 ptrtoint ([100 x i64]* @__dfsan_arg_tls to i64), i64 2) to [2 x i16]*), align 2
+  ; CHECK: [[AS0:%.*]] = extractvalue [2 x i16] [[AS]], 0
+  ; CHECK: [[AS1:%.*]] = extractvalue [2 x i16] [[AS]], 1
+  ; CHECK: [[AS01:%.*]] = or i16 [[AS0]], [[AS1]]
+  ; CHECK: [[ADDR:%.*]] = bitcast [2 x i64]* %p to i8*
+  ; CHECK: call void @__dfsan_maybe_store_origin(i16 [[AS01]], i8* [[ADDR]], i64 16, i32 [[AO]])
+  ; CHECK: store [2 x i64] %a, [2 x i64]* %p, align 8
+
+  store [2 x i64] %a, [2 x i64]* %p
+  ret void
+}