MS ABI: Implement /volatile:ms

The /volatile:ms semantics turn volatile loads and stores into atomic
acquire and release operations.  This distinction is important because
volatile memory operations do not form a happens-before relationship
with non-atomic memory.  This means that a volatile store is not
sufficient for implementing a mutex unlock routine.

Differential Revision: http://reviews.llvm.org/D7580

llvm-svn: 229082

6 files changed, 81 insertions, 13 deletions

diff --git a/clang/lib/CodeGen/CGAtomic.cpp b/clang/lib/CodeGen/CGAtomic.cpp
index 927195083d4..a0b6073f6bf 100644
--- a/clang/lib/CodeGen/CGAtomic.cpp
+++ b/clang/lib/CodeGen/CGAtomic.cpp
@@ -1006,9 +1006,45 @@ RValue AtomicInfo::convertIntToValue(llvm::Value *IntVal,
   return convertTempToRValue(Temp, ResultSlot, Loc);
 }
 
+/// An LValue is a candidate for having its loads and stores be made atomic if
+/// we are operating under /volatile:ms *and* the LValue itself is volatile and
+/// performing such an operation can be performed without a libcall.
+bool CodeGenFunction::LValueIsSuitableForInlineAtomic(LValue LV) {
+  AtomicInfo AI(*this, LV);
+  bool IsVolatile = LV.isVolatile() || hasVolatileMember(LV.getType());
+  // An atomic is inline if we don't need to use a libcall.
+  bool AtomicIsInline = !AI.shouldUseLibcall();
+  return CGM.getCodeGenOpts().MSVolatile && IsVolatile && AtomicIsInline;
+}
+
+/// An type is a candidate for having its loads and stores be made atomic if
+/// we are operating under /volatile:ms *and* we know the access is volatile and
+/// performing such an operation can be performed without a libcall.
+bool CodeGenFunction::typeIsSuitableForInlineAtomic(QualType Ty,
+                                                    bool IsVolatile) const {
+  // An atomic is inline if we don't need to use a libcall (e.g. it is builtin).
+  bool AtomicIsInline = getContext().getTargetInfo().hasBuiltinAtomic(
+      getContext().getTypeSize(Ty), getContext().getTypeAlign(Ty));
+  return CGM.getCodeGenOpts().MSVolatile && IsVolatile && AtomicIsInline;
+}
+
+RValue CodeGenFunction::EmitAtomicLoad(LValue LV, SourceLocation SL,
+                                       AggValueSlot Slot) {
+  llvm::AtomicOrdering AO;
+  bool IsVolatile = LV.isVolatileQualified();
+  if (LV.getType()->isAtomicType()) {
+    AO = llvm::SequentiallyConsistent;
+  } else {
+    AO = llvm::Acquire;
+    IsVolatile = true;
+  }
+  return EmitAtomicLoad(LV, SL, AO, IsVolatile, Slot);
+}
+
 /// Emit a load from an l-value of atomic type.  Note that the r-value
 /// we produce is an r-value of the atomic *value* type.
 RValue CodeGenFunction::EmitAtomicLoad(LValue src, SourceLocation loc,
+                                       llvm::AtomicOrdering AO, bool IsVolatile,
                                        AggValueSlot resultSlot) {
   AtomicInfo atomics(*this, src);
   LValue LVal = atomics.getAtomicLValue();
@@ -1060,11 +1096,11 @@ RValue CodeGenFunction::EmitAtomicLoad(LValue src, SourceLocation loc,
   // Okay, we're doing this natively.
   llvm::Value *addr = atomics.emitCastToAtomicIntPointer(SrcAddr);
   llvm::LoadInst *load = Builder.CreateLoad(addr, "atomic-load");
-  load->setAtomic(llvm::SequentiallyConsistent);
+  load->setAtomic(AO);
 
   // Other decoration.
   load->setAlignment(src.getAlignment().getQuantity());
-  if (src.isVolatileQualified())
+  if (IsVolatile)
     load->setVolatile(true);
   if (src.getTBAAInfo())
     CGM.DecorateInstruction(load, src.getTBAAInfo());
@@ -1161,12 +1197,27 @@ llvm::Value *AtomicInfo::convertRValueToInt(RValue RVal) const {
                                        getAtomicAlignment().getQuantity());
 }
 
+void CodeGenFunction::EmitAtomicStore(RValue rvalue, LValue lvalue,
+                                      bool isInit) {
+  bool IsVolatile = lvalue.isVolatileQualified();
+  llvm::AtomicOrdering AO;
+  if (lvalue.getType()->isAtomicType()) {
+    AO = llvm::SequentiallyConsistent;
+  } else {
+    AO = llvm::Release;
+    IsVolatile = true;
+  }
+  return EmitAtomicStore(rvalue, lvalue, AO, IsVolatile, isInit);
+}
+
 /// Emit a store to an l-value of atomic type.
 ///
 /// Note that the r-value is expected to be an r-value *of the atomic
 /// type*; this means that for aggregate r-values, it should include
 /// storage for any padding that was necessary.
-void CodeGenFunction::EmitAtomicStore(RValue rvalue, LValue dest, bool isInit) {
+void CodeGenFunction::EmitAtomicStore(RValue rvalue, LValue dest,
+                                      llvm::AtomicOrdering AO, bool IsVolatile,
+                                      bool isInit) {
   // If this is an aggregate r-value, it should agree in type except
   // maybe for address-space qualification.
   assert(!rvalue.isAggregate() ||
@@ -1209,11 +1260,11 @@ void CodeGenFunction::EmitAtomicStore(RValue rvalue, LValue dest, bool isInit) {
   llvm::StoreInst *store = Builder.CreateStore(intValue, addr);
 
   // Initializations don't need to be atomic.
-  if (!isInit) store->setAtomic(llvm::SequentiallyConsistent);
+  if (!isInit) store->setAtomic(AO);
 
   // Other decoration.
   store->setAlignment(dest.getAlignment().getQuantity());
-  if (dest.isVolatileQualified())
+  if (IsVolatile)
     store->setVolatile(true);
   if (dest.getTBAAInfo())
     CGM.DecorateInstruction(store, dest.getTBAAInfo());
diff --git a/clang/lib/CodeGen/CGExpr.cpp b/clang/lib/CodeGen/CGExpr.cpp
index 568f949c342..18aa262160b 100644
--- a/clang/lib/CodeGen/CGExpr.cpp
+++ b/clang/lib/CodeGen/CGExpr.cpp
@@ -1136,7 +1136,7 @@ llvm::Value *CodeGenFunction::EmitLoadOfScalar(llvm::Value *Addr, bool Volatile,
   }
 
   // Atomic operations have to be done on integral types.
-  if (Ty->isAtomicType()) {
+  if (Ty->isAtomicType() || typeIsSuitableForInlineAtomic(Ty, Volatile)) {
     LValue lvalue = LValue::MakeAddr(Addr, Ty,
                                      CharUnits::fromQuantity(Alignment),
                                      getContext(), TBAAInfo);
@@ -1255,7 +1255,8 @@ void CodeGenFunction::EmitStoreOfScalar(llvm::Value *Value, llvm::Value *Addr,
 
   Value = EmitToMemory(Value, Ty);
 
-  if (Ty->isAtomicType()) {
+  if (Ty->isAtomicType() ||
+      (!isInit && typeIsSuitableForInlineAtomic(Ty, Volatile))) {
     EmitAtomicStore(RValue::get(Value),
                     LValue::MakeAddr(Addr, Ty,
                                      CharUnits::fromQuantity(Alignment),
diff --git a/clang/lib/CodeGen/CGExprAgg.cpp b/clang/lib/CodeGen/CGExprAgg.cpp
index 80b16dd5ba3..dd2da23cd85 100644
--- a/clang/lib/CodeGen/CGExprAgg.cpp
+++ b/clang/lib/CodeGen/CGExprAgg.cpp
@@ -212,7 +212,7 @@ void AggExprEmitter::EmitAggLoadOfLValue(const Expr *E) {
   LValue LV = CGF.EmitLValue(E);
 
   // If the type of the l-value is atomic, then do an atomic load.
-  if (LV.getType()->isAtomicType()) {
+  if (LV.getType()->isAtomicType() || CGF.LValueIsSuitableForInlineAtomic(LV)) {
     CGF.EmitAtomicLoad(LV, E->getExprLoc(), Dest);
     return;
   }
@@ -865,7 +865,8 @@ void AggExprEmitter::VisitBinAssign(const BinaryOperator *E) {
     LValue LHS = CGF.EmitCheckedLValue(E->getLHS(), CodeGenFunction::TCK_Store);
 
     // That copy is an atomic copy if the LHS is atomic.
-    if (LHS.getType()->isAtomicType()) {
+    if (LHS.getType()->isAtomicType() ||
+        CGF.LValueIsSuitableForInlineAtomic(LHS)) {
       CGF.EmitAtomicStore(Dest.asRValue(), LHS, /*isInit*/ false);
       return;
     }
@@ -882,7 +883,8 @@ void AggExprEmitter::VisitBinAssign(const BinaryOperator *E) {
 
   // If we have an atomic type, evaluate into the destination and then
   // do an atomic copy.
-  if (LHS.getType()->isAtomicType()) {
+  if (LHS.getType()->isAtomicType() ||
+      CGF.LValueIsSuitableForInlineAtomic(LHS)) {
     EnsureDest(E->getRHS()->getType());
     Visit(E->getRHS());
     CGF.EmitAtomicStore(Dest.asRValue(), LHS, /*isInit*/ false);
diff --git a/clang/lib/CodeGen/CGExprComplex.cpp b/clang/lib/CodeGen/CGExprComplex.cpp
index ceec85a9a89..1fea5a127c0 100644
--- a/clang/lib/CodeGen/CGExprComplex.cpp
+++ b/clang/lib/CodeGen/CGExprComplex.cpp
@@ -336,7 +336,8 @@ ComplexPairTy ComplexExprEmitter::EmitLoadOfLValue(LValue lvalue,
 /// specified value pointer.
 void ComplexExprEmitter::EmitStoreOfComplex(ComplexPairTy Val, LValue lvalue,
                                             bool isInit) {
-  if (lvalue.getType()->isAtomicType())
+  if (lvalue.getType()->isAtomicType() ||
+      (!isInit && CGF.LValueIsSuitableForInlineAtomic(lvalue)))
     return CGF.EmitAtomicStore(RValue::getComplex(Val), lvalue, isInit);
 
   llvm::Value *Ptr = lvalue.getAddress();
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp
index b4dcadc5fdc..6b3faa14162 100644
--- a/clang/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp
@@ -829,8 +829,11 @@ static void EmitOMPAtomicReadExpr(CodeGenFunction &CGF, bool IsSeqCst,
   assert(X->isLValue() && "X of 'omp atomic read' is not lvalue");
   LValue XLValue = CGF.EmitLValue(X);
   LValue VLValue = CGF.EmitLValue(V);
-  RValue Res = XLValue.isGlobalReg() ? CGF.EmitLoadOfLValue(XLValue, Loc)
-                                     : CGF.EmitAtomicLoad(XLValue, Loc);
+  RValue Res = XLValue.isGlobalReg()
+                   ? CGF.EmitLoadOfLValue(XLValue, Loc)
+                   : CGF.EmitAtomicLoad(XLValue, Loc,
+                                        IsSeqCst ? llvm::SequentiallyConsistent
+                                                 : llvm::Monotonic);
   // OpenMP, 2.12.6, atomic Construct
   // Any atomic construct with a seq_cst clause forces the atomically
   // performed operation to include an implicit flush operation without a
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 12f066bf171..ea8166b2827 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -2147,11 +2147,21 @@ public:
 
   void EmitAtomicInit(Expr *E, LValue lvalue);
 
+  bool LValueIsSuitableForInlineAtomic(LValue Src);
+  bool typeIsSuitableForInlineAtomic(QualType Ty, bool IsVolatile) const;
+
+  RValue EmitAtomicLoad(LValue LV, SourceLocation SL,
+                        AggValueSlot Slot = AggValueSlot::ignored());
+
   RValue EmitAtomicLoad(LValue lvalue, SourceLocation loc,
+                        llvm::AtomicOrdering AO, bool IsVolatile = false,
                         AggValueSlot slot = AggValueSlot::ignored());
 
   void EmitAtomicStore(RValue rvalue, LValue lvalue, bool isInit);
 
+  void EmitAtomicStore(RValue rvalue, LValue lvalue, llvm::AtomicOrdering AO,
+                       bool IsVolatile, bool isInit);
+
   std::pair<RValue, RValue> EmitAtomicCompareExchange(
       LValue Obj, RValue Expected, RValue Desired, SourceLocation Loc,
       llvm::AtomicOrdering Success = llvm::SequentiallyConsistent,