Support __iso_volatile_load8 etc on aarch64-win32.

These intrinsics are used by MSVC's header files on AArch64 Windows as
well as AArch32, so we should support them for both targets. I've
factored them out of CodeGenFunction::EmitARMBuiltinExpr into separate
functions that EmitAArch64BuiltinExpr can call as well.

Reviewers: javed.absar, mstorsjo

Reviewed By: mstorsjo

Subscribers: kristof.beyls, cfe-commits

Differential Revision: https://reviews.llvm.org/D47476

llvm-svn: 333513

4 files changed, 69 insertions, 26 deletions

diff --git a/clang/include/clang/Basic/BuiltinsAArch64.def b/clang/include/clang/Basic/BuiltinsAArch64.def
index 55a4f70176d..f902accfa61 100644
--- a/clang/include/clang/Basic/BuiltinsAArch64.def
+++ b/clang/include/clang/Basic/BuiltinsAArch64.def
@@ -69,5 +69,15 @@ LANGBUILTIN(__dmb, "vUi", "nc", ALL_MS_LANGUAGES)
 LANGBUILTIN(__dsb, "vUi", "nc", ALL_MS_LANGUAGES)
 LANGBUILTIN(__isb, "vUi", "nc", ALL_MS_LANGUAGES)
 
+// MSVC intrinsics for volatile but non-acquire/release loads and stores
+LANGBUILTIN(__iso_volatile_load8,   "ccCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load16,  "ssCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load32,  "iiCD*",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_load64,  "LLiLLiCD*", "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store8,  "vcD*c",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store16, "vsD*s",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store32, "viD*i",     "n", ALL_MS_LANGUAGES)
+LANGBUILTIN(__iso_volatile_store64, "vLLiD*LLi", "n", ALL_MS_LANGUAGES)
+
 #undef BUILTIN
 #undef LANGBUILTIN
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index d75c7e32b7e..d4b11659667 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -5179,6 +5179,34 @@ static bool HasExtraNeonArgument(unsigned BuiltinID) {
   return true;
 }
 
+Value *CodeGenFunction::EmitISOVolatileLoad(const CallExpr *E) {
+  Value *Ptr = EmitScalarExpr(E->getArg(0));
+  QualType ElTy = E->getArg(0)->getType()->getPointeeType();
+  CharUnits LoadSize = getContext().getTypeSizeInChars(ElTy);
+  llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
+                                           LoadSize.getQuantity() * 8);
+  Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
+  llvm::LoadInst *Load =
+    Builder.CreateAlignedLoad(Ptr, LoadSize);
+  Load->setVolatile(true);
+  return Load;
+}
+
+Value *CodeGenFunction::EmitISOVolatileStore(const CallExpr *E) {
+  Value *Ptr = EmitScalarExpr(E->getArg(0));
+  Value *Value = EmitScalarExpr(E->getArg(1));
+  QualType ElTy = E->getArg(0)->getType()->getPointeeType();
+  CharUnits StoreSize = getContext().getTypeSizeInChars(ElTy);
+  llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
+                                           StoreSize.getQuantity() * 8);
+  Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
+  llvm::StoreInst *Store =
+    Builder.CreateAlignedStore(Value, Ptr,
+                               StoreSize);
+  Store->setVolatile(true);
+  return Store;
+}
+
 Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
                                            const CallExpr *E,
                                            llvm::Triple::ArchType Arch) {
@@ -5421,35 +5449,13 @@ Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
   case ARM::BI__iso_volatile_load8:
   case ARM::BI__iso_volatile_load16:
   case ARM::BI__iso_volatile_load32:
-  case ARM::BI__iso_volatile_load64: {
-    Value *Ptr = EmitScalarExpr(E->getArg(0));
-    QualType ElTy = E->getArg(0)->getType()->getPointeeType();
-    CharUnits LoadSize = getContext().getTypeSizeInChars(ElTy);
-    llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
-                                             LoadSize.getQuantity() * 8);
-    Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
-    llvm::LoadInst *Load =
-      Builder.CreateAlignedLoad(Ptr, LoadSize);
-    Load->setVolatile(true);
-    return Load;
-  }
+  case ARM::BI__iso_volatile_load64:
+    return EmitISOVolatileLoad(E);
   case ARM::BI__iso_volatile_store8:
   case ARM::BI__iso_volatile_store16:
   case ARM::BI__iso_volatile_store32:
-  case ARM::BI__iso_volatile_store64: {
-    Value *Ptr = EmitScalarExpr(E->getArg(0));
-    Value *Value = EmitScalarExpr(E->getArg(1));
-    QualType ElTy = E->getArg(0)->getType()->getPointeeType();
-    CharUnits StoreSize = getContext().getTypeSizeInChars(ElTy);
-    llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
-                                             StoreSize.getQuantity() * 8);
-    Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
-    llvm::StoreInst *Store =
-      Builder.CreateAlignedStore(Value, Ptr,
-                                 StoreSize);
-    Store->setVolatile(true);
-    return Store;
-  }
+  case ARM::BI__iso_volatile_store64:
+    return EmitISOVolatileStore(E);
   }
 
   if (BuiltinID == ARM::BI__builtin_arm_clrex) {
@@ -8199,6 +8205,16 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Int = Intrinsic::aarch64_neon_suqadd;
     return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vuqadd");
   }
+  case AArch64::BI__iso_volatile_load8:
+  case AArch64::BI__iso_volatile_load16:
+  case AArch64::BI__iso_volatile_load32:
+  case AArch64::BI__iso_volatile_load64:
+    return EmitISOVolatileLoad(E);
+  case AArch64::BI__iso_volatile_store8:
+  case AArch64::BI__iso_volatile_store16:
+  case AArch64::BI__iso_volatile_store32:
+  case AArch64::BI__iso_volatile_store64:
+    return EmitISOVolatileStore(E);
   }
 }
 
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 1cd952cb4a6..56b07e5f853 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -3541,6 +3541,10 @@ public:
                                          SmallVectorImpl<llvm::Value *> &Ops,
                                          Address PtrOp0, Address PtrOp1,
                                          llvm::Triple::ArchType Arch);
+
+  llvm::Value *EmitISOVolatileLoad(const CallExpr *E);
+  llvm::Value *EmitISOVolatileStore(const CallExpr *E);
+
   llvm::Function *LookupNeonLLVMIntrinsic(unsigned IntrinsicID,
                                           unsigned Modifier, llvm::Type *ArgTy,
                                           const CallExpr *E);
diff --git a/clang/test/CodeGen/ms-volatile-aarch64.c b/clang/test/CodeGen/ms-volatile-aarch64.c
new file mode 100644
index 00000000000..2a139f5139f
--- /dev/null
+++ b/clang/test/CodeGen/ms-volatile-aarch64.c
@@ -0,0 +1,13 @@
+// REQUIRES: aarch64-registered-target
+// RUN: %clang_cc1 -triple aarch64-win32 -emit-llvm -fms-extensions -fms-volatile -o - < %s | FileCheck %s
+
+void test1(int volatile *p, int v) {
+  __iso_volatile_store32(p, v);
+  // CHECK-LABEL: @test1
+  // CHECK: store volatile {{.*}}, {{.*}}
+}
+int test2(const int volatile *p) {
+  return __iso_volatile_load32(p);
+  // CHECK-LABEL: @test2
+  // CHECK: load volatile {{.*}}
+}