[IR] Introduce a dereferenceable_or_null(N) attribute.

Summary:
If a pointer is marked as dereferenceable_or_null(N), LLVM assumes it
is either `null` or `dereferenceable(N)` or both.  This change only
introduces the attribute and adds a token test case for the `llvm-as`
/ `llvm-dis`.  It does not hook up other parts of the optimizer to
actually exploit the attribute -- those changes will come later.

For pointers in address space 0, `dereferenceable(N)` is now exactly
equivalent to `dereferenceable_or_null(N)` && `nonnull`.  For other
address spaces, `dereferenceable(N)` is potentially weaker than
`dereferenceable_or_null(N)` && `nonnull` (since we could have a null
`dereferenceable(N)` pointer).

The motivating case for this change is Java (and other managed
languages), where pointers are either `null` or dereferenceable up to
some usually known-at-compile-time constant offset.

Reviewers: rafael, hfinkel

Reviewed By: hfinkel

Subscribers: nicholas, llvm-commits

Differential Revision: http://reviews.llvm.org/D8650

llvm-svn: 235132

10 files changed, 121 insertions, 30 deletions

diff --git a/llvm/lib/AsmParser/LLLexer.cpp b/llvm/lib/AsmParser/LLLexer.cpp
index 3bf090a4b33..a72f713c490 100644
--- a/llvm/lib/AsmParser/LLLexer.cpp
+++ b/llvm/lib/AsmParser/LLLexer.cpp
@@ -598,6 +598,7 @@ lltok::Kind LLLexer::LexIdentifier() {
   KEYWORD(inalloca);
   KEYWORD(cold);
   KEYWORD(dereferenceable);
+  KEYWORD(dereferenceable_or_null);
   KEYWORD(inlinehint);
   KEYWORD(inreg);
   KEYWORD(jumptable);
diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 64ed2a2b7e3..2b306dbd642 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -976,6 +976,7 @@ bool LLParser::ParseFnAttributeValuePairs(AttrBuilder &B,
       break;
     case lltok::kw_byval:
     case lltok::kw_dereferenceable:
+    case lltok::kw_dereferenceable_or_null:
     case lltok::kw_inalloca:
     case lltok::kw_nest:
     case lltok::kw_noalias:
@@ -1220,11 +1221,18 @@ bool LLParser::ParseOptionalParamAttrs(AttrBuilder &B) {
     case lltok::kw_byval:           B.addAttribute(Attribute::ByVal); break;
     case lltok::kw_dereferenceable: {
       uint64_t Bytes;
-      if (ParseOptionalDereferenceableBytes(Bytes))
+      if (ParseOptionalDerefAttrBytes(lltok::kw_dereferenceable, Bytes))
         return true;
       B.addDereferenceableAttr(Bytes);
       continue;
     }
+    case lltok::kw_dereferenceable_or_null: {
+      uint64_t Bytes;
+      if (ParseOptionalDerefAttrBytes(lltok::kw_dereferenceable_or_null, Bytes))
+        return true;
+      B.addDereferenceableOrNullAttr(Bytes);
+      continue;
+    }
     case lltok::kw_inalloca:        B.addAttribute(Attribute::InAlloca); break;
     case lltok::kw_inreg:           B.addAttribute(Attribute::InReg); break;
     case lltok::kw_nest:            B.addAttribute(Attribute::Nest); break;
@@ -1284,11 +1292,18 @@ bool LLParser::ParseOptionalReturnAttrs(AttrBuilder &B) {
       return HaveError;
     case lltok::kw_dereferenceable: {
       uint64_t Bytes;
-      if (ParseOptionalDereferenceableBytes(Bytes))
+      if (ParseOptionalDerefAttrBytes(lltok::kw_dereferenceable, Bytes))
         return true;
       B.addDereferenceableAttr(Bytes);
       continue;
     }
+    case lltok::kw_dereferenceable_or_null: {
+      uint64_t Bytes;
+      if (ParseOptionalDerefAttrBytes(lltok::kw_dereferenceable_or_null, Bytes))
+        return true;
+      B.addDereferenceableOrNullAttr(Bytes);
+      continue;
+    }
     case lltok::kw_inreg:           B.addAttribute(Attribute::InReg); break;
     case lltok::kw_noalias:         B.addAttribute(Attribute::NoAlias); break;
     case lltok::kw_nonnull:         B.addAttribute(Attribute::NonNull); break;
@@ -1516,12 +1531,19 @@ bool LLParser::ParseOptionalAlignment(unsigned &Alignment) {
   return false;
 }
 
-/// ParseOptionalDereferenceableBytes
+/// ParseOptionalDerefAttrBytes
 ///   ::= /* empty */
-///   ::= 'dereferenceable' '(' 4 ')'
-bool LLParser::ParseOptionalDereferenceableBytes(uint64_t &Bytes) {
+///   ::= AttrKind '(' 4 ')'
+///
+/// where AttrKind is either 'dereferenceable' or 'dereferenceable_or_null'.
+bool LLParser::ParseOptionalDerefAttrBytes(lltok::Kind AttrKind,
+                                           uint64_t &Bytes) {
+  assert((AttrKind == lltok::kw_dereferenceable ||
+          AttrKind == lltok::kw_dereferenceable_or_null) &&
+         "contract!");
+
   Bytes = 0;
-  if (!EatIfPresent(lltok::kw_dereferenceable))
+  if (!EatIfPresent(AttrKind))
     return false;
   LocTy ParenLoc = Lex.getLoc();
   if (!EatIfPresent(lltok::lparen))
diff --git a/llvm/lib/AsmParser/LLParser.h b/llvm/lib/AsmParser/LLParser.h
index 5e92e570e72..117cdcba255 100644
--- a/llvm/lib/AsmParser/LLParser.h
+++ b/llvm/lib/AsmParser/LLParser.h
@@ -223,7 +223,7 @@ namespace llvm {
     bool ParseOptionalDLLStorageClass(unsigned &DLLStorageClass);
     bool ParseOptionalCallingConv(unsigned &CC);
     bool ParseOptionalAlignment(unsigned &Alignment);
-    bool ParseOptionalDereferenceableBytes(uint64_t &Bytes);
+    bool ParseOptionalDerefAttrBytes(lltok::Kind AttrKind, uint64_t &Bytes);
     bool ParseScopeAndOrdering(bool isAtomic, SynchronizationScope &Scope,
                                AtomicOrdering &Ordering);
     bool ParseOrdering(AtomicOrdering &Ordering);
diff --git a/llvm/lib/AsmParser/LLToken.h b/llvm/lib/AsmParser/LLToken.h
index a7aa17c37cc..2bdc53b3e2e 100644
--- a/llvm/lib/AsmParser/LLToken.h
+++ b/llvm/lib/AsmParser/LLToken.h
@@ -106,6 +106,7 @@ namespace lltok {
     kw_inalloca,
     kw_cold,
     kw_dereferenceable,
+    kw_dereferenceable_or_null,
     kw_inlinehint,
     kw_inreg,
     kw_jumptable,
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index 6caec344d1f..5366f5fb4ea 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -1098,6 +1098,8 @@ static Attribute::AttrKind GetAttrFromCode(uint64_t Code) {
     return Attribute::NonNull;
   case bitc::ATTR_KIND_DEREFERENCEABLE:
     return Attribute::Dereferenceable;
+  case bitc::ATTR_KIND_DEREFERENCEABLE_OR_NULL:
+    return Attribute::DereferenceableOrNull;
   case bitc::ATTR_KIND_NO_RED_ZONE:
     return Attribute::NoRedZone;
   case bitc::ATTR_KIND_NO_RETURN:
@@ -1214,6 +1216,8 @@ std::error_code BitcodeReader::ParseAttributeGroupBlock() {
             B.addStackAlignmentAttr(Record[++i]);
           else if (Kind == Attribute::Dereferenceable)
             B.addDereferenceableAttr(Record[++i]);
+          else if (Kind == Attribute::DereferenceableOrNull)
+            B.addDereferenceableOrNullAttr(Record[++i]);
         } else {                     // String attribute
           assert((Record[i] == 3 || Record[i] == 4) &&
                  "Invalid attribute group entry");
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 743ffe3cb1f..aa4a6a4c28a 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -200,6 +200,8 @@ static uint64_t getAttrKindEncoding(Attribute::AttrKind Kind) {
     return bitc::ATTR_KIND_NON_NULL;
   case Attribute::Dereferenceable:
     return bitc::ATTR_KIND_DEREFERENCEABLE;
+  case Attribute::DereferenceableOrNull:
+    return bitc::ATTR_KIND_DEREFERENCEABLE_OR_NULL;
   case Attribute::NoRedZone:
     return bitc::ATTR_KIND_NO_RED_ZONE;
   case Attribute::NoReturn:
diff --git a/llvm/lib/IR/AttributeImpl.h b/llvm/lib/IR/AttributeImpl.h
index 199c3187205..d544689abec 100644
--- a/llvm/lib/IR/AttributeImpl.h
+++ b/llvm/lib/IR/AttributeImpl.h
@@ -115,10 +115,10 @@ class IntAttributeImpl : public EnumAttributeImpl {
 public:
   IntAttributeImpl(Attribute::AttrKind Kind, uint64_t Val)
       : EnumAttributeImpl(IntAttrEntry, Kind), Val(Val) {
-    assert(
-        (Kind == Attribute::Alignment || Kind == Attribute::StackAlignment ||
-         Kind == Attribute::Dereferenceable) &&
-        "Wrong kind for int attribute!");
+    assert((Kind == Attribute::Alignment || Kind == Attribute::StackAlignment ||
+            Kind == Attribute::Dereferenceable ||
+            Kind == Attribute::DereferenceableOrNull) &&
+           "Wrong kind for int attribute!");
   }
 
   uint64_t getValue() const { return Val; }
diff --git a/llvm/lib/IR/Attributes.cpp b/llvm/lib/IR/Attributes.cpp
index 52cc71018e5..be5b74f59a2 100644
--- a/llvm/lib/IR/Attributes.cpp
+++ b/llvm/lib/IR/Attributes.cpp
@@ -94,6 +94,12 @@ Attribute Attribute::getWithDereferenceableBytes(LLVMContext &Context,
   return get(Context, Dereferenceable, Bytes);
 }
 
+Attribute Attribute::getWithDereferenceableOrNullBytes(LLVMContext &Context,
+                                                       uint64_t Bytes) {
+  assert(Bytes && "Bytes must be non-zero.");
+  return get(Context, DereferenceableOrNull, Bytes);
+}
+
 //===----------------------------------------------------------------------===//
 // Attribute Accessor Methods
 //===----------------------------------------------------------------------===//
@@ -170,6 +176,13 @@ uint64_t Attribute::getDereferenceableBytes() const {
   return pImpl->getValueAsInt();
 }
 
+uint64_t Attribute::getDereferenceableOrNullBytes() const {
+  assert(hasAttribute(Attribute::DereferenceableOrNull) &&
+         "Trying to get dereferenceable bytes from "
+         "non-dereferenceable attribute!");
+  return pImpl->getValueAsInt();
+}
+
 std::string Attribute::getAsString(bool InAttrGrp) const {
   if (!pImpl) return "";
 
@@ -263,9 +276,9 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
     return Result;
   }
 
-  if (hasAttribute(Attribute::StackAlignment)) {
+  auto AttrWithBytesToString = [&](const char *Name) {
     std::string Result;
-    Result += "alignstack";
+    Result += Name;
     if (InAttrGrp) {
       Result += "=";
       Result += utostr(getValueAsInt());
@@ -275,21 +288,16 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
       Result += ")";
     }
     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;
-  }
+  if (hasAttribute(Attribute::StackAlignment))
+    return AttrWithBytesToString("alignstack");
+
+  if (hasAttribute(Attribute::Dereferenceable))
+    return AttrWithBytesToString("dereferenceable");
+
+  if (hasAttribute(Attribute::DereferenceableOrNull))
+    return AttrWithBytesToString("dereferenceable_or_null");
 
   // Convert target-dependent attributes to strings of the form:
   //
@@ -428,6 +436,11 @@ uint64_t AttributeImpl::getAttrMask(Attribute::AttrKind Val) {
   case Attribute::JumpTable:       return 1ULL << 45;
   case Attribute::Dereferenceable:
     llvm_unreachable("dereferenceable attribute not supported in raw format");
+    break;
+  case Attribute::DereferenceableOrNull:
+    llvm_unreachable("dereferenceable_or_null attribute not supported in raw "
+                     "format");
+    break;
   }
   llvm_unreachable("Unsupported attribute type");
 }
@@ -663,6 +676,10 @@ AttributeSet AttributeSet::get(LLVMContext &C, unsigned Index,
       Attrs.push_back(std::make_pair(Index,
                                      Attribute::getWithDereferenceableBytes(C,
                                        B.getDereferenceableBytes())));
+    else if (Kind == Attribute::DereferenceableOrNull)
+      Attrs.push_back(
+          std::make_pair(Index, Attribute::getWithDereferenceableOrNullBytes(
+                                    C, B.getDereferenceableOrNullBytes())));
     else
       Attrs.push_back(std::make_pair(Index, Attribute::get(C, Kind)));
   }
@@ -842,6 +859,14 @@ AttributeSet AttributeSet::addDereferenceableAttr(LLVMContext &C, unsigned Index
   return addAttributes(C, Index, AttributeSet::get(C, Index, B));
 }
 
+AttributeSet AttributeSet::addDereferenceableOrNullAttr(LLVMContext &C,
+                                                        unsigned Index,
+                                                        uint64_t Bytes) const {
+  llvm::AttrBuilder B;
+  B.addDereferenceableOrNullAttr(Bytes);
+  return addAttributes(C, Index, AttributeSet::get(C, Index, B));
+}
+
 //===----------------------------------------------------------------------===//
 // AttributeSet Accessor Methods
 //===----------------------------------------------------------------------===//
@@ -1011,7 +1036,8 @@ void AttributeSet::dump() const {
 //===----------------------------------------------------------------------===//
 
 AttrBuilder::AttrBuilder(AttributeSet AS, unsigned Index)
-  : Attrs(0), Alignment(0), StackAlignment(0), DerefBytes(0) {
+    : Attrs(0), Alignment(0), StackAlignment(0), DerefBytes(0),
+      DerefOrNullBytes(0) {
   AttributeSetImpl *pImpl = AS.pImpl;
   if (!pImpl) return;
 
@@ -1028,7 +1054,7 @@ AttrBuilder::AttrBuilder(AttributeSet AS, unsigned Index)
 
 void AttrBuilder::clear() {
   Attrs.reset();
-  Alignment = StackAlignment = DerefBytes = 0;
+  Alignment = StackAlignment = DerefBytes = DerefOrNullBytes = 0;
 }
 
 AttrBuilder &AttrBuilder::addAttribute(Attribute::AttrKind Val) {
@@ -1055,6 +1081,8 @@ AttrBuilder &AttrBuilder::addAttribute(Attribute Attr) {
     StackAlignment = Attr.getStackAlignment();
   else if (Kind == Attribute::Dereferenceable)
     DerefBytes = Attr.getDereferenceableBytes();
+  else if (Kind == Attribute::DereferenceableOrNull)
+    DerefOrNullBytes = Attr.getDereferenceableOrNullBytes();
   return *this;
 }
 
@@ -1073,6 +1101,8 @@ AttrBuilder &AttrBuilder::removeAttribute(Attribute::AttrKind Val) {
     StackAlignment = 0;
   else if (Val == Attribute::Dereferenceable)
     DerefBytes = 0;
+  else if (Val == Attribute::DereferenceableOrNull)
+    DerefOrNullBytes = 0;
 
   return *this;
 }
@@ -1099,6 +1129,8 @@ AttrBuilder &AttrBuilder::removeAttributes(AttributeSet A, uint64_t Index) {
         StackAlignment = 0;
       else if (Kind == Attribute::Dereferenceable)
         DerefBytes = 0;
+      else if (Kind == Attribute::DereferenceableOrNull)
+        DerefOrNullBytes = 0;
     } else {
       assert(Attr.isStringAttribute() && "Invalid attribute type!");
       std::map<std::string, std::string>::iterator
@@ -1149,6 +1181,15 @@ AttrBuilder &AttrBuilder::addDereferenceableAttr(uint64_t Bytes) {
   return *this;
 }
 
+AttrBuilder &AttrBuilder::addDereferenceableOrNullAttr(uint64_t Bytes) {
+  if (Bytes == 0)
+    return *this;
+
+  Attrs[Attribute::DereferenceableOrNull] = true;
+  DerefOrNullBytes = Bytes;
+  return *this;
+}
+
 AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   // FIXME: What if both have alignments, but they don't match?!
   if (!Alignment)
@@ -1225,7 +1266,8 @@ AttrBuilder &AttrBuilder::addRawValue(uint64_t Val) {
 
   for (Attribute::AttrKind I = Attribute::None; I != Attribute::EndAttrKinds;
        I = Attribute::AttrKind(I + 1)) {
-    if (I == Attribute::Dereferenceable)
+    if (I == Attribute::Dereferenceable ||
+        I == Attribute::DereferenceableOrNull)
       continue;
     if (uint64_t A = (Val & AttributeImpl::getAttrMask(I))) {
       Attrs[I] = true;
@@ -1261,6 +1303,7 @@ AttributeSet AttributeFuncs::typeIncompatible(Type *Ty, uint64_t Index) {
       .addAttribute(Attribute::NoCapture)
       .addAttribute(Attribute::NonNull)
       .addDereferenceableAttr(1) // the int here is ignored
+      .addDereferenceableOrNullAttr(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
index 8275cc692a6..d3a09348220 100644
--- a/llvm/lib/IR/Function.cpp
+++ b/llvm/lib/IR/Function.cpp
@@ -348,6 +348,12 @@ void Function::addDereferenceableAttr(unsigned i, uint64_t Bytes) {
   setAttributes(PAL);
 }
 
+void Function::addDereferenceableOrNullAttr(unsigned i, uint64_t Bytes) {
+  AttributeSet PAL = getAttributes();
+  PAL = PAL.addDereferenceableOrNullAttr(getContext(), i, Bytes);
+  setAttributes(PAL);
+}
+
 // Maintain the GC name for each function in an on-the-side table. This saves
 // allocating an additional word in Function for programs which do not use GC
 // (i.e., most programs) at the cost of increased overhead for clients which do
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index 8e3ddaa4b1b..85b7521f316 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -352,6 +352,12 @@ void CallInst::addDereferenceableAttr(unsigned i, uint64_t Bytes) {
   setAttributes(PAL);
 }
 
+void CallInst::addDereferenceableOrNullAttr(unsigned i, uint64_t Bytes) {
+  AttributeSet PAL = getAttributes();
+  PAL = PAL.addDereferenceableOrNullAttr(getContext(), i, Bytes);
+  setAttributes(PAL);
+}
+
 bool CallInst::hasFnAttrImpl(Attribute::AttrKind A) const {
   if (AttributeList.hasAttribute(AttributeSet::FunctionIndex, A))
     return true;
@@ -617,6 +623,12 @@ void InvokeInst::addDereferenceableAttr(unsigned i, uint64_t Bytes) {
   setAttributes(PAL);
 }
 
+void InvokeInst::addDereferenceableOrNullAttr(unsigned i, uint64_t Bytes) {
+  AttributeSet PAL = getAttributes();
+  PAL = PAL.addDereferenceableOrNullAttr(getContext(), i, Bytes);
+  setAttributes(PAL);
+}
+
 LandingPadInst *InvokeInst::getLandingPadInst() const {
   return cast<LandingPadInst>(getUnwindDest()->getFirstNonPHI());
 }