[ARM] Support constant pools in data when generating execute-only code.

labrinea · labrinea · commit c582d6e13338 · 2017-06-14T13:22:41.000Z
The ARM backend asserts against constant pool lowering when it generates execute-only code in order to prevent the generation of constant pools in the text section. It appears that target independent optimizations might generate DAG nodes that represent constant pools. By lowering such nodes as global addresses we don't violate the semantics of execute-only code and also it is guaranteed that execute-only behaves correct with the position-independent addressing modes that support execute-only code. Differential Revision: https://reviews.llvm.org/D33773 llvm-svn: 305387
diff --git a/llvm/lib/Target/ARM/ARMAsmPrinter.cpp b/llvm/lib/Target/ARM/ARMAsmPrinter.cpp
@@ -1504,6 +1504,9 @@ void ARMAsmPrinter::EmitInstruction(const MachineInstr *MI) {
     return;
   }
   case ARM::CONSTPOOL_ENTRY: {
+    if (Subtarget->genExecuteOnly())
+      llvm_unreachable("execute-only should not generate constant pools");
+
     /// CONSTPOOL_ENTRY - This instruction represents a floating constant pool
     /// in the function.  The first operand is the ID# for this instruction, the
     /// second is the index into the MachineConstantPool that this is, the third
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -2669,12 +2669,34 @@ static SDValue LowerWRITE_REGISTER(SDValue Op, SelectionDAG &DAG) {
 // Select(N) returns N. So the raw TargetGlobalAddress nodes, etc. can only
 // be used to form addressing mode. These wrapped nodes will be selected
 // into MOVi.
-static SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) {
+SDValue ARMTargetLowering::LowerConstantPool(SDValue Op,
+                                             SelectionDAG &DAG) const {
   EVT PtrVT = Op.getValueType();
   // FIXME there is no actual debug info here
   SDLoc dl(Op);
   ConstantPoolSDNode *CP = cast<ConstantPoolSDNode>(Op);
   SDValue Res;
+
+  // When generating execute-only code Constant Pools must be promoted to the
+  // global data section. It's a bit ugly that we can't share them across basic
+  // blocks, but this way we guarantee that execute-only behaves correct with
+  // position-independent addressing modes.
+  if (Subtarget->genExecuteOnly()) {
+    auto AFI = DAG.getMachineFunction().getInfo<ARMFunctionInfo>();
+    auto T = const_cast<Type*>(CP->getType());
+    auto C = const_cast<Constant*>(CP->getConstVal());
+    auto M = const_cast<Module*>(DAG.getMachineFunction().
+                                 getFunction()->getParent());
+    auto L = Twine(DAG.getDataLayout().getPrivateGlobalPrefix()) + "CP" +
+             Twine(DAG.getMachineFunction().getFunctionNumber()) + "_" +
+             Twine(AFI->createPICLabelUId());
+    auto GV = new GlobalVariable(*M, T, /*isConstant=*/true,
+                                 GlobalVariable::InternalLinkage, C, L);
+    SDValue GA = DAG.getTargetGlobalAddress(dyn_cast<GlobalValue>(GV),
+                                            dl, PtrVT);
+    return LowerGlobalAddress(GA, DAG);
+  }
+
   if (CP->isMachineConstantPoolEntry())
     Res = DAG.getTargetConstantPool(CP->getMachineCPVal(), PtrVT,
                                     CP->getAlignment());
@@ -3118,6 +3140,19 @@ static bool isReadOnly(const GlobalValue *GV) {
          isa<Function>(GV);
 }
 
+SDValue ARMTargetLowering::LowerGlobalAddress(SDValue Op,
+                                              SelectionDAG &DAG) const {
+  switch (Subtarget->getTargetTriple().getObjectFormat()) {
+  default: llvm_unreachable("unknown object format");
+  case Triple::COFF:
+    return LowerGlobalAddressWindows(Op, DAG);
+  case Triple::ELF:
+    return LowerGlobalAddressELF(Op, DAG);
+  case Triple::MachO:
+    return LowerGlobalAddressDarwin(Op, DAG);
+  }
+}
+
 SDValue ARMTargetLowering::LowerGlobalAddressELF(SDValue Op,
                                                  SelectionDAG &DAG) const {
   EVT PtrVT = getPointerTy(DAG.getDataLayout());
@@ -7634,21 +7669,9 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   switch (Op.getOpcode()) {
   default: llvm_unreachable("Don't know how to custom lower this!");
   case ISD::WRITE_REGISTER: return LowerWRITE_REGISTER(Op, DAG);
-  case ISD::ConstantPool:
-    if (Subtarget->genExecuteOnly())
-      llvm_unreachable("execute-only should not generate constant pools");
-    return LowerConstantPool(Op, DAG);
+  case ISD::ConstantPool: return LowerConstantPool(Op, DAG);
   case ISD::BlockAddress:  return LowerBlockAddress(Op, DAG);
-  case ISD::GlobalAddress:
-    switch (Subtarget->getTargetTriple().getObjectFormat()) {
-    default: llvm_unreachable("unknown object format");
-    case Triple::COFF:
-      return LowerGlobalAddressWindows(Op, DAG);
-    case Triple::ELF:
-      return LowerGlobalAddressELF(Op, DAG);
-    case Triple::MachO:
-      return LowerGlobalAddressDarwin(Op, DAG);
-    }
+  case ISD::GlobalAddress: return LowerGlobalAddress(Op, DAG);
   case ISD::GlobalTLSAddress: return LowerGlobalTLSAddress(Op, DAG);
   case ISD::SELECT:        return LowerSELECT(Op, DAG);
   case ISD::SELECT_CC:     return LowerSELECT_CC(Op, DAG);
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.h b/llvm/lib/Target/ARM/ARMISelLowering.h
@@ -601,6 +601,8 @@ class InstrItineraryData;
     SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG,
                                     const ARMSubtarget *Subtarget) const;
     SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerGlobalAddressDarwin(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerGlobalAddressELF(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerGlobalAddressWindows(SDValue Op, SelectionDAG &DAG) const;
diff --git a/llvm/test/CodeGen/ARM/constantfp.ll b/llvm/test/CodeGen/ARM/constantfp.ll
@@ -11,6 +11,9 @@
 ; RUN: llc -mtriple=thumbv7meb -arm-execute-only -mcpu=cortex-m4 %s -o - \
 ; RUN: | FileCheck --check-prefix=CHECK-XO-FLOAT --check-prefix=CHECK-XO-DOUBLE-BE %s
 
+; RUN: llc -mtriple=thumbv7m -arm-execute-only -mcpu=cortex-m4 -relocation-model=ropi %s -o - \
+; RUN: | FileCheck --check-prefix=CHECK-XO-ROPI %s
+
 ; RUN: llc -mtriple=thumbv8m.main -mattr=fp-armv8 %s -o - \
 ; RUN: | FileCheck --check-prefix=CHECK-NO-XO %s
 
@@ -20,6 +23,8 @@
 ; RUN: llc -mtriple=thumbv8m.maineb -arm-execute-only -mattr=fp-armv8 %s -o - \
 ; RUN: | FileCheck --check-prefix=CHECK-XO-FLOAT --check-prefix=CHECK-XO-DOUBLE-BE %s
 
+; RUN: llc -mtriple=thumbv8m.main -arm-execute-only -mattr=fp-armv8 -relocation-model=ropi %s -o - \
+; RUN: | FileCheck --check-prefix=CHECK-XO-ROPI %s
 
 define arm_aapcs_vfpcc float @test_vmov_f32() {
 ; CHECK-LABEL: test_vmov_f32:
@@ -176,3 +181,48 @@ define arm_aapcs_vfpcc double @lower_const_f64_xo() {
 ; CHECK-XO-DOUBLE-BE-NOT: vldr
   ret double 3.140000e-01
 }
+
+; This is a target independent optimization, performed by the
+; DAG Combiner, which promotes floating point literals into
+; constant pools:
+;
+; (a cond b) ? 1.0f : 2.0f -> load (ConstPoolAddr + ((a cond b) ? 0 : 4)
+;
+; We need to make sure that the constant pools are placed in
+; the data section when generating execute-only code:
+
+define arm_aapcs_vfpcc float @lower_fpconst_select(float %f) {
+
+; CHECK-NO-XO-LABEL: lower_fpconst_select
+; CHECK-NO-XO: adr [[REG:r[0-9]+]], [[LABEL:.?LCPI[0-9]+_[0-9]+]]
+; CHECK-NO-XO: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-NO-XO-NOT: .rodata
+; CHECK-NO-XO: [[LABEL]]:
+; CHECK-NO-XO: .long   1335165689
+; CHECK-NO-XO: .long   1307470632
+
+; CHECK-XO-FLOAT-LABEL: lower_fpconst_select
+; CHECK-XO-FLOAT: movw [[REG:r[0-9]+]], :lower16:[[LABEL:.?LCP[0-9]+_[0-9]+]]
+; CHECK-XO-FLOAT: movt [[REG]], :upper16:[[LABEL]]
+; CHECK-XO-FLOAT: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-XO-FLOAT: .rodata
+; CHECK-XO-FLOAT-NOT: .text
+; CHECK-XO-FLOAT: [[LABEL]]:
+; CHECK-XO-FLOAT: .long   1335165689
+; CHECK-XO-FLOAT: .long   1307470632
+
+; CHECK-XO-ROPI-LABEL: lower_fpconst_select
+; CHECK-XO-ROPI: movw [[REG:r[0-9]+]], :lower16:([[LABEL1:.?LCP[0-9]+_[0-9]+]]-([[LABEL2:.?LPC[0-9]+_[0-9]+]]+4))
+; CHECK-XO-ROPI: movt [[REG]], :upper16:([[LABEL1]]-([[LABEL2]]+4))
+; CHECK-XO-ROPI: [[LABEL2]]:
+; CHECK-XO-ROPI: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-XO-ROPI: .rodata
+; CHECK-XO-ROPI-NOT: .text
+; CHECK-XO-ROPI: [[LABEL1]]:
+; CHECK-XO-ROPI: .long   1335165689
+; CHECK-XO-ROPI: .long   1307470632
+
+  %cmp = fcmp nnan oeq float %f, 0.000000e+00
+  %sel = select i1 %cmp, float 5.000000e+08, float 5.000000e+09
+  ret float %sel
+}
