diff --git a/llvm/lib/IR/Attributes.cpp b/llvm/lib/IR/Attributes.cpp
@@ -88,6 +88,12 @@ Attribute Attribute::getWithStackAlignment(LLVMContext &Context,
   return get(Context, StackAlignment, Align);
 }
 
+Attribute Attribute::getWithDereferenceableBytes(LLVMContext &Context,
+                                                uint64_t Bytes) {
+  assert(Bytes && "Bytes must be non-zero.");
+  return get(Context, Dereferenceable, Bytes);
+}
+
 //===----------------------------------------------------------------------===//
 // Attribute Accessor Methods
 //===----------------------------------------------------------------------===//
@@ -156,6 +162,14 @@ unsigned Attribute::getStackAlignment() const {
   return pImpl->getValueAsInt();
 }
 
+/// This returns the number of dereferenceable bytes.
+uint64_t Attribute::getDereferenceableBytes() const {
+  assert(hasAttribute(Attribute::Dereferenceable) &&
+         "Trying to get dereferenceable bytes from "
+         "non-dereferenceable attribute!");
+  return pImpl->getValueAsInt();
+}
+
 std::string Attribute::getAsString(bool InAttrGrp) const {
   if (!pImpl) return "";
 
@@ -263,6 +277,20 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
     return Result;
   }
 
+  if (hasAttribute(Attribute::Dereferenceable)) {
+    std::string Result;
+    Result += "dereferenceable";
+    if (InAttrGrp) {
+      Result += "=";
+      Result += utostr(getValueAsInt());
+    } else {
+      Result += "(";
+      Result += utostr(getValueAsInt());
+      Result += ")";
+    }
+    return Result;
+  }
+
   // Convert target-dependent attributes to strings of the form:
   //
   //   "kind"
@@ -398,6 +426,8 @@ uint64_t AttributeImpl::getAttrMask(Attribute::AttrKind Val) {
   case Attribute::InAlloca:        return 1ULL << 43;
   case Attribute::NonNull:         return 1ULL << 44;
   case Attribute::JumpTable:       return 1ULL << 45;
+  case Attribute::Dereferenceable:
+    llvm_unreachable("dereferenceable attribute not supported in raw format");
   }
   llvm_unreachable("Unsupported attribute type");
 }
@@ -482,6 +512,13 @@ unsigned AttributeSetNode::getStackAlignment() const {
   return 0;
 }
 
+uint64_t AttributeSetNode::getDereferenceableBytes() const {
+  for (iterator I = begin(), E = end(); I != E; ++I)
+    if (I->hasAttribute(Attribute::Dereferenceable))
+      return I->getDereferenceableBytes();
+  return 0;
+}
+
 std::string AttributeSetNode::getAsString(bool InAttrGrp) const {
   std::string Str;
   for (iterator I = begin(), E = end(); I != E; ++I) {
@@ -515,6 +552,8 @@ uint64_t AttributeSetImpl::Raw(unsigned Index) const {
         Mask |= (Log2_32(ASN->getAlignment()) + 1) << 16;
       else if (Kind == Attribute::StackAlignment)
         Mask |= (Log2_32(ASN->getStackAlignment()) + 1) << 26;
+      else if (Kind == Attribute::Dereferenceable)
+        llvm_unreachable("dereferenceable not supported in bit mask");
       else
         Mask |= AttributeImpl::getAttrMask(Kind);
     }
@@ -620,6 +659,10 @@ AttributeSet AttributeSet::get(LLVMContext &C, unsigned Index,
     else if (Kind == Attribute::StackAlignment)
       Attrs.push_back(std::make_pair(Index, Attribute::
                               getWithStackAlignment(C, B.getStackAlignment())));
+    else if (Kind == Attribute::Dereferenceable)
+      Attrs.push_back(std::make_pair(Index,
+                                     Attribute::getWithDereferenceableBytes(C,
+                                       B.getDereferenceableBytes())));
     else
       Attrs.push_back(std::make_pair(Index, Attribute::get(C, Kind)));
   }
@@ -877,6 +920,11 @@ unsigned AttributeSet::getStackAlignment(unsigned Index) const {
   return ASN ? ASN->getStackAlignment() : 0;
 }
 
+uint64_t AttributeSet::getDereferenceableBytes(unsigned Index) const {
+  AttributeSetNode *ASN = getAttributes(Index);
+  return ASN ? ASN->getDereferenceableBytes() : 0;
+}
+
 std::string AttributeSet::getAsString(unsigned Index,
                                       bool InAttrGrp) const {
   AttributeSetNode *ASN = getAttributes(Index);
@@ -956,7 +1004,7 @@ void AttributeSet::dump() const {
 //===----------------------------------------------------------------------===//
 
 AttrBuilder::AttrBuilder(AttributeSet AS, unsigned Index)
-  : Attrs(0), Alignment(0), StackAlignment(0) {
+  : Attrs(0), Alignment(0), StackAlignment(0), DerefBytes(0) {
   AttributeSetImpl *pImpl = AS.pImpl;
   if (!pImpl) return;
 
@@ -973,13 +1021,14 @@ AttrBuilder::AttrBuilder(AttributeSet AS, unsigned Index)
 
 void AttrBuilder::clear() {
   Attrs.reset();
-  Alignment = StackAlignment = 0;
+  Alignment = StackAlignment = DerefBytes = 0;
 }
 
 AttrBuilder &AttrBuilder::addAttribute(Attribute::AttrKind Val) {
   assert((unsigned)Val < Attribute::EndAttrKinds && "Attribute out of range!");
   assert(Val != Attribute::Alignment && Val != Attribute::StackAlignment &&
-         "Adding alignment attribute without adding alignment value!");
+         Val != Attribute::Dereferenceable &&
+         "Adding integer attribute without adding a value!");
   Attrs[Val] = true;
   return *this;
 }
@@ -997,6 +1046,8 @@ AttrBuilder &AttrBuilder::addAttribute(Attribute Attr) {
     Alignment = Attr.getAlignment();
   else if (Kind == Attribute::StackAlignment)
     StackAlignment = Attr.getStackAlignment();
+  else if (Kind == Attribute::Dereferenceable)
+    DerefBytes = Attr.getDereferenceableBytes();
   return *this;
 }
 
@@ -1013,6 +1064,8 @@ AttrBuilder &AttrBuilder::removeAttribute(Attribute::AttrKind Val) {
     Alignment = 0;
   else if (Val == Attribute::StackAlignment)
     StackAlignment = 0;
+  else if (Val == Attribute::Dereferenceable)
+    DerefBytes = 0;
 
   return *this;
 }
@@ -1037,6 +1090,8 @@ AttrBuilder &AttrBuilder::removeAttributes(AttributeSet A, uint64_t Index) {
         Alignment = 0;
       else if (Kind == Attribute::StackAlignment)
         StackAlignment = 0;
+      else if (Kind == Attribute::Dereferenceable)
+        DerefBytes = 0;
     } else {
       assert(Attr.isStringAttribute() && "Invalid attribute type!");
       std::map<std::string, std::string>::iterator
@@ -1079,6 +1134,14 @@ AttrBuilder &AttrBuilder::addStackAlignmentAttr(unsigned Align) {
   return *this;
 }
 
+AttrBuilder &AttrBuilder::addDereferenceableAttr(uint64_t Bytes) {
+  if (Bytes == 0) return *this;
+
+  Attrs[Attribute::Dereferenceable] = true;
+  DerefBytes = Bytes;
+  return *this;
+}
+
 AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   // FIXME: What if both have alignments, but they don't match?!
   if (!Alignment)
@@ -1087,6 +1150,9 @@ AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   if (!StackAlignment)
     StackAlignment = B.StackAlignment;
 
+  if (!DerefBytes)
+    DerefBytes = B.DerefBytes;
+
   Attrs |= B.Attrs;
 
   for (td_const_iterator I = B.TargetDepAttrs.begin(),
@@ -1142,7 +1208,8 @@ bool AttrBuilder::operator==(const AttrBuilder &B) {
     if (B.TargetDepAttrs.find(I->first) == B.TargetDepAttrs.end())
       return false;
 
-  return Alignment == B.Alignment && StackAlignment == B.StackAlignment;
+  return Alignment == B.Alignment && StackAlignment == B.StackAlignment &&
+         DerefBytes == B.DerefBytes;
 }
 
 AttrBuilder &AttrBuilder::addRawValue(uint64_t Val) {
@@ -1151,6 +1218,8 @@ AttrBuilder &AttrBuilder::addRawValue(uint64_t Val) {
 
   for (Attribute::AttrKind I = Attribute::None; I != Attribute::EndAttrKinds;
        I = Attribute::AttrKind(I + 1)) {
+    if (I == Attribute::Dereferenceable)
+      continue;
     if (uint64_t A = (Val & AttributeImpl::getAttrMask(I))) {
       Attrs[I] = true;
 
@@ -1184,6 +1253,7 @@ AttributeSet AttributeFuncs::typeIncompatible(Type *Ty, uint64_t Index) {
       .addAttribute(Attribute::NoAlias)
       .addAttribute(Attribute::NoCapture)
       .addAttribute(Attribute::NonNull)
+      .addDereferenceableAttr(1) // the int here is ignored
       .addAttribute(Attribute::ReadNone)
       .addAttribute(Attribute::ReadOnly)
       .addAttribute(Attribute::StructRet)

diff --git a/llvm/lib/IR/Function.cpp b/llvm/lib/IR/Function.cpp
@@ -77,11 +77,17 @@ unsigned Argument::getArgNo() const {
 }
 
 /// hasNonNullAttr - Return true if this argument has the nonnull attribute on
-/// it in its containing function.
+/// it in its containing function. Also returns true if at least one byte is
+/// known to be dereferenceable and the pointer is in addrspace(0).
 bool Argument::hasNonNullAttr() const {
   if (!getType()->isPointerTy()) return false;
-  return getParent()->getAttributes().
-    hasAttribute(getArgNo()+1, Attribute::NonNull);
+  if (getParent()->getAttributes().
+        hasAttribute(getArgNo()+1, Attribute::NonNull))
+    return true;
+  else if (getDereferenceableBytes() > 0 &&
+           getType()->getPointerAddressSpace() == 0)
+    return true;
+  return false;
 }
 
 /// hasByValAttr - Return true if this argument has the byval attribute on it
@@ -113,6 +119,12 @@ unsigned Argument::getParamAlignment() const {
 
 }
 
+uint64_t Argument::getDereferenceableBytes() const {
+  assert(getType()->isPointerTy() &&
+         "Only pointers have dereferenceable bytes");
+  return getParent()->getDereferenceableBytes(getArgNo()+1);
+}
+
 /// hasNestAttr - Return true if this argument has the nest attribute on
 /// it in its containing function.
 bool Argument::hasNestAttr() const {

diff --git a/llvm/lib/IR/Value.cpp b/llvm/lib/IR/Value.cpp
@@ -15,6 +15,7 @@
 #include "LLVMContextImpl.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallString.h"
+#include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
@@ -504,9 +505,29 @@ static bool isDereferenceablePointer(const Value *V, const DataLayout *DL,
   if (const GlobalVariable *GV = dyn_cast<GlobalVariable>(V))
     return !GV->hasExternalWeakLinkage();
 
-  // byval arguments are ok.
-  if (const Argument *A = dyn_cast<Argument>(V))
-    return A->hasByValAttr();
+  // byval arguments are okay. Arguments specifically marked as
+  // dereferenceable are okay too.
+  if (const Argument *A = dyn_cast<Argument>(V)) {
+    if (A->hasByValAttr())
+      return true;
+    else if (uint64_t Bytes = A->getDereferenceableBytes()) {
+      Type *Ty = V->getType()->getPointerElementType();
+      if (Ty->isSized() && DL && DL->getTypeStoreSize(Ty) <= Bytes)
+        return true;
+    }
+
+    return false;
+  }
+
+  // Return values from call sites specifically marked as dereferenceable are
+  // also okay.
+  if (ImmutableCallSite CS = V) {
+    if (uint64_t Bytes = CS.getDereferenceableBytes(0)) {
+      Type *Ty = V->getType()->getPointerElementType();
+      if (Ty->isSized() && DL && DL->getTypeStoreSize(Ty) <= Bytes)
+        return true;
+    }
+  }
 
   // For GEPs, determine if the indexing lands within the allocated object.
   if (const GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {

diff --git a/llvm/test/Bitcode/attributes.ll b/llvm/test/Bitcode/attributes.ll
@@ -229,6 +229,16 @@ define void @f38() unnamed_addr jumptable {
     unreachable
 }
 
+define dereferenceable(2) i8* @f39(i8* dereferenceable(1) %a) {
+; CHECK: define dereferenceable(2) i8* @f39(i8* dereferenceable(1) %a) {
+        ret i8* %a
+}
+
+define dereferenceable(18446744073709551606) i8* @f40(i8* dereferenceable(18446744073709551615) %a) {
+; CHECK: define dereferenceable(18446744073709551606) i8* @f40(i8* dereferenceable(18446744073709551615) %a) {
+        ret i8* %a
+}
+
 ; CHECK: attributes #0 = { noreturn }
 ; CHECK: attributes #1 = { nounwind }
 ; CHECK: attributes #2 = { readnone }

diff --git a/llvm/test/Transforms/InstSimplify/compare.ll b/llvm/test/Transforms/InstSimplify/compare.ll
@@ -874,6 +874,21 @@ define i1 @nonnull_arg(i32* nonnull %i) {
 ; CHECK: ret i1 false
 }
 
+define i1 @nonnull_deref_arg(i32* dereferenceable(4) %i) {
+  %cmp = icmp eq i32* %i, null
+  ret i1 %cmp
+; CHECK-LABEL: @nonnull_deref_arg
+; CHECK: ret i1 false
+}
+
+define i1 @nonnull_deref_as_arg(i32 addrspace(1)* dereferenceable(4) %i) {
+  %cmp = icmp eq i32 addrspace(1)* %i, null
+  ret i1 %cmp
+; CHECK-LABEL: @nonnull_deref_as_arg
+; CHECK: icmp
+; CHECK ret
+}
+
 declare nonnull i32* @returns_nonnull_helper()
 define i1 @returns_nonnull() {
   %call = call nonnull i32* @returns_nonnull_helper()
@@ -883,6 +898,25 @@ define i1 @returns_nonnull() {
 ; CHECK: ret i1 false
 }
 
+declare dereferenceable(4) i32* @returns_nonnull_deref_helper()
+define i1 @returns_nonnull_deref() {
+  %call = call dereferenceable(4) i32* @returns_nonnull_deref_helper()
+  %cmp = icmp eq i32* %call, null
+  ret i1 %cmp
+; CHECK-LABEL: @returns_nonnull_deref
+; CHECK: ret i1 false
+}
+
+declare dereferenceable(4) i32 addrspace(1)* @returns_nonnull_deref_as_helper()
+define i1 @returns_nonnull_as_deref() {
+  %call = call dereferenceable(4) i32 addrspace(1)* @returns_nonnull_deref_as_helper()
+  %cmp = icmp eq i32 addrspace(1)* %call, null
+  ret i1 %cmp
+; CHECK-LABEL: @returns_nonnull_as_deref
+; CHECK: icmp
+; CHECK: ret
+}
+
 ; If a bit is known to be zero for A and known to be one for B,
 ; then A and B cannot be equal.
 define i1 @icmp_eq_const(i32 %a) nounwind {

diff --git a/llvm/test/Transforms/LICM/hoist-deref-load.ll b/llvm/test/Transforms/LICM/hoist-deref-load.ll
@@ -0,0 +1,86 @@
+; RUN: opt -S -basicaa -licm < %s | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; This test represents the following function:
+; void test1(int * __restrict__ a, int * __restrict__ b, int &c, int n) {
+;   for (int i = 0; i < n; ++i)
+;     if (a[i] > 0)
+;       a[i] = c*b[i];
+; }
+; and we want to hoist the load of %c out of the loop. This can be done only
+; because the dereferenceable attribute is on %c.
+
+; CHECK-LABEL: @test1
+; CHECK: load i32* %c, align 4
+; CHECK: for.body:
+
+define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull dereferenceable(4) %c, i32 %n) #0 {
+entry:
+  %cmp11 = icmp sgt i32 %n, 0
+  br i1 %cmp11, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.inc
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %cmp1 = icmp sgt i32 %0, 0
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %1 = load i32* %c, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %2 = load i32* %arrayidx3, align 4
+  %mul = mul nsw i32 %2, %1
+  store i32 %mul, i32* %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.inc, %entry
+  ret void
+}
+
+; This is the same as @test1, but without the dereferenceable attribute on %c.
+; Without this attribute, we should not hoist the load of %c.
+
+; CHECK-LABEL: @test2
+; CHECK: if.then:
+; CHECK: load i32* %c, align 4
+
+define void @test2(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull %c, i32 %n) #0 {
+entry:
+  %cmp11 = icmp sgt i32 %n, 0
+  br i1 %cmp11, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.inc
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %cmp1 = icmp sgt i32 %0, 0
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %1 = load i32* %c, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %2 = load i32* %arrayidx3, align 4
+  %mul = mul nsw i32 %2, %1
+  store i32 %mul, i32* %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.inc, %entry
+  ret void
+}
+
+attributes #0 = { nounwind uwtable }
+