[arm-fast-isel] Add support for vararg function calls.

llvm-svn: 160500
This commit is contained in:
Jush Lu 2012-07-19 09:49:00 +00:00
parent 7acdc1738f
commit e67e07b901
3 changed files with 84 additions and 32 deletions

View File

@ -193,18 +193,21 @@ class ARMFastISel : public FastISel {
// Call handling routines.
private:
CCAssignFn *CCAssignFnForCall(CallingConv::ID CC, bool Return);
CCAssignFn *CCAssignFnForCall(CallingConv::ID CC,
bool Return,
bool isVarArg);
bool ProcessCallArgs(SmallVectorImpl<Value*> &Args,
SmallVectorImpl<unsigned> &ArgRegs,
SmallVectorImpl<MVT> &ArgVTs,
SmallVectorImpl<ISD::ArgFlagsTy> &ArgFlags,
SmallVectorImpl<unsigned> &RegArgs,
CallingConv::ID CC,
unsigned &NumBytes);
unsigned &NumBytes,
bool isVarArg);
unsigned getLibcallReg(const Twine &Name);
bool FinishCall(MVT RetVT, SmallVectorImpl<unsigned> &UsedRegs,
const Instruction *I, CallingConv::ID CC,
unsigned &NumBytes);
unsigned &NumBytes, bool isVarArg);
bool ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call);
// OptionalDef handling routines.
@ -1807,10 +1810,11 @@ bool ARMFastISel::SelectBinaryFPOp(const Instruction *I, unsigned ISDOpcode) {
// Call Handling Code
// This is largely taken directly from CCAssignFnForNode - we don't support
// varargs in FastISel so that part has been removed.
// This is largely taken directly from CCAssignFnForNode
// TODO: We may not support all of this.
CCAssignFn *ARMFastISel::CCAssignFnForCall(CallingConv::ID CC, bool Return) {
CCAssignFn *ARMFastISel::CCAssignFnForCall(CallingConv::ID CC,
bool Return,
bool isVarArg) {
switch (CC) {
default:
llvm_unreachable("Unsupported calling convention");
@ -1823,14 +1827,17 @@ CCAssignFn *ARMFastISel::CCAssignFnForCall(CallingConv::ID CC, bool Return) {
// Use target triple & subtarget features to do actual dispatch.
if (Subtarget->isAAPCS_ABI()) {
if (Subtarget->hasVFP2() &&
TM.Options.FloatABIType == FloatABI::Hard)
TM.Options.FloatABIType == FloatABI::Hard && !isVarArg)
return (Return ? RetCC_ARM_AAPCS_VFP: CC_ARM_AAPCS_VFP);
else
return (Return ? RetCC_ARM_AAPCS: CC_ARM_AAPCS);
} else
return (Return ? RetCC_ARM_APCS: CC_ARM_APCS);
case CallingConv::ARM_AAPCS_VFP:
return (Return ? RetCC_ARM_AAPCS_VFP: CC_ARM_AAPCS_VFP);
if (!isVarArg)
return (Return ? RetCC_ARM_AAPCS_VFP: CC_ARM_AAPCS_VFP);
// Fall through to soft float variant, variadic functions don't
// use hard floating point ABI.
case CallingConv::ARM_AAPCS:
return (Return ? RetCC_ARM_AAPCS: CC_ARM_AAPCS);
case CallingConv::ARM_APCS:
@ -1844,10 +1851,12 @@ bool ARMFastISel::ProcessCallArgs(SmallVectorImpl<Value*> &Args,
SmallVectorImpl<ISD::ArgFlagsTy> &ArgFlags,
SmallVectorImpl<unsigned> &RegArgs,
CallingConv::ID CC,
unsigned &NumBytes) {
unsigned &NumBytes,
bool isVarArg) {
SmallVector<CCValAssign, 16> ArgLocs;
CCState CCInfo(CC, false, *FuncInfo.MF, TM, ArgLocs, *Context);
CCInfo.AnalyzeCallOperands(ArgVTs, ArgFlags, CCAssignFnForCall(CC, false));
CCState CCInfo(CC, isVarArg, *FuncInfo.MF, TM, ArgLocs, *Context);
CCInfo.AnalyzeCallOperands(ArgVTs, ArgFlags,
CCAssignFnForCall(CC, false, isVarArg));
// Check that we can handle all of the arguments. If we can't, then bail out
// now before we add code to the MBB.
@ -1979,7 +1988,7 @@ bool ARMFastISel::ProcessCallArgs(SmallVectorImpl<Value*> &Args,
bool ARMFastISel::FinishCall(MVT RetVT, SmallVectorImpl<unsigned> &UsedRegs,
const Instruction *I, CallingConv::ID CC,
unsigned &NumBytes) {
unsigned &NumBytes, bool isVarArg) {
// Issue CALLSEQ_END
unsigned AdjStackUp = TII.getCallFrameDestroyOpcode();
AddOptionalDefs(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
@ -1989,8 +1998,8 @@ bool ARMFastISel::FinishCall(MVT RetVT, SmallVectorImpl<unsigned> &UsedRegs,
// Now the return value.
if (RetVT != MVT::isVoid) {
SmallVector<CCValAssign, 16> RVLocs;
CCState CCInfo(CC, false, *FuncInfo.MF, TM, RVLocs, *Context);
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true));
CCState CCInfo(CC, isVarArg, *FuncInfo.MF, TM, RVLocs, *Context);
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true, isVarArg));
// Copy all of the result registers out of their specified physreg.
if (RVLocs.size() == 2 && RetVT == MVT::f64) {
@ -2039,9 +2048,6 @@ bool ARMFastISel::SelectRet(const Instruction *I) {
if (!FuncInfo.CanLowerReturn)
return false;
if (F.isVarArg())
return false;
CallingConv::ID CC = F.getCallingConv();
if (Ret->getNumOperands() > 0) {
SmallVector<ISD::OutputArg, 4> Outs;
@ -2051,7 +2057,8 @@ bool ARMFastISel::SelectRet(const Instruction *I) {
// Analyze operands of the call, assigning locations to each operand.
SmallVector<CCValAssign, 16> ValLocs;
CCState CCInfo(CC, F.isVarArg(), *FuncInfo.MF, TM, ValLocs,I->getContext());
CCInfo.AnalyzeReturn(Outs, CCAssignFnForCall(CC, true /* is Ret */));
CCInfo.AnalyzeReturn(Outs, CCAssignFnForCall(CC, true /* is Ret */,
F.isVarArg()));
const Value *RV = Ret->getOperand(0);
unsigned Reg = getRegForValue(RV);
@ -2143,7 +2150,7 @@ bool ARMFastISel::ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call) {
if (RetVT != MVT::isVoid && RetVT != MVT::i32) {
SmallVector<CCValAssign, 16> RVLocs;
CCState CCInfo(CC, false, *FuncInfo.MF, TM, RVLocs, *Context);
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true));
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true, false));
if (RVLocs.size() >= 2 && RetVT != MVT::f64)
return false;
}
@ -2179,7 +2186,8 @@ bool ARMFastISel::ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call) {
// Handle the arguments now that we've gotten them.
SmallVector<unsigned, 4> RegArgs;
unsigned NumBytes;
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags, RegArgs, CC, NumBytes))
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags,
RegArgs, CC, NumBytes, false))
return false;
unsigned CalleeReg = 0;
@ -2218,7 +2226,7 @@ bool ARMFastISel::ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call) {
// Finish off the call including any return values.
SmallVector<unsigned, 4> UsedRegs;
if (!FinishCall(RetVT, UsedRegs, I, CC, NumBytes)) return false;
if (!FinishCall(RetVT, UsedRegs, I, CC, NumBytes, false)) return false;
// Set all unused physreg defs as dead.
static_cast<MachineInstr *>(MIB)->setPhysRegsDeadExcept(UsedRegs, TRI);
@ -2240,11 +2248,9 @@ bool ARMFastISel::SelectCall(const Instruction *I,
// TODO: Avoid some calling conventions?
// Let SDISel handle vararg functions.
PointerType *PT = cast<PointerType>(CS.getCalledValue()->getType());
FunctionType *FTy = cast<FunctionType>(PT->getElementType());
if (FTy->isVarArg())
return false;
bool isVarArg = FTy->isVarArg();
// Handle *simple* calls for now.
Type *RetTy = I->getType();
@ -2259,8 +2265,8 @@ bool ARMFastISel::SelectCall(const Instruction *I,
if (RetVT != MVT::isVoid && RetVT != MVT::i1 && RetVT != MVT::i8 &&
RetVT != MVT::i16 && RetVT != MVT::i32) {
SmallVector<CCValAssign, 16> RVLocs;
CCState CCInfo(CC, false, *FuncInfo.MF, TM, RVLocs, *Context);
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true));
CCState CCInfo(CC, isVarArg, *FuncInfo.MF, TM, RVLocs, *Context);
CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC, true, isVarArg));
if (RVLocs.size() >= 2 && RetVT != MVT::f64)
return false;
}
@ -2318,7 +2324,8 @@ bool ARMFastISel::SelectCall(const Instruction *I,
// Handle the arguments now that we've gotten them.
SmallVector<unsigned, 4> RegArgs;
unsigned NumBytes;
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags, RegArgs, CC, NumBytes))
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags,
RegArgs, CC, NumBytes, isVarArg))
return false;
bool UseReg = false;
@ -2370,7 +2377,8 @@ bool ARMFastISel::SelectCall(const Instruction *I,
// Finish off the call including any return values.
SmallVector<unsigned, 4> UsedRegs;
if (!FinishCall(RetVT, UsedRegs, I, CC, NumBytes)) return false;
if (!FinishCall(RetVT, UsedRegs, I, CC, NumBytes, isVarArg))
return false;
// Set all unused physreg defs as dead.
static_cast<MachineInstr *>(MIB)->setPhysRegsDeadExcept(UsedRegs, TRI);

View File

@ -178,3 +178,46 @@ entry:
%tmp1 = udiv i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
define i32 @VarArg() nounwind {
entry:
%i = alloca i32, align 4
%j = alloca i32, align 4
%k = alloca i32, align 4
%m = alloca i32, align 4
%n = alloca i32, align 4
%tmp = alloca i32, align 4
%0 = load i32* %i, align 4
%1 = load i32* %j, align 4
%2 = load i32* %k, align 4
%3 = load i32* %m, align 4
%4 = load i32* %n, align 4
; ARM: VarArg
; ARM: mov r7, sp
; ARM: movw r0, #5
; ARM: ldr r1, [r7, #-4]
; ARM: ldr r2, [r7, #-8]
; ARM: ldr r3, [r7, #-12]
; ARM: ldr r9, [sp, #16]
; ARM: ldr r12, [sp, #12]
; ARM: str r9, [sp]
; ARM: str r12, [sp, #4]
; ARM: bl _CallVariadic
; THUMB: mov r7, sp
; THUMB: movs r0, #5
; THUMB: movt r0, #0
; THUMB: ldr r1, [sp, #28]
; THUMB: ldr r2, [sp, #24]
; THUMB: ldr r3, [sp, #20]
; THUMB: ldr.w r9, [sp, #16]
; THUMB: ldr.w r12, [sp, #12]
; THUMB: str.w r9, [sp]
; THUMB: str.w r12, [sp, #4]
; THUMB: bl _CallVariadic
%call = call i32 (i32, ...)* @CallVariadic(i32 5, i32 %0, i32 %1, i32 %2, i32 %3, i32 %4)
store i32 %call, i32* %tmp, align 4
%5 = load i32* %tmp, align 4
ret i32 %5
}
declare i32 @CallVariadic(i32, ...)

View File

@ -3,17 +3,18 @@ target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-
target triple = "thumbv7-apple-ios0.0.0"
; This test case would clobber the outgoing call arguments by writing to the
; emergency spill slot at [sp, #4] without adjusting the stack pointer first.
; emergency spill slots at [sp, #4] or [sp, #8] without adjusting the stack
; pointer first.
; CHECK: main
; CHECK: vmov.f64
; Adjust SP for the large call
; CHECK: sub sp,
; CHECK: mov [[FR:r[0-9]+]], sp
; Store to call frame + #4
; CHECK: str{{.*\[}}[[FR]], #4]
; Store to call frame + #8
; CHECK: vstr{{.*\[}}sp, #8]
; Don't clobber that store until the call.
; CHECK-NOT: [sp, #4]
; CHECK-NOT: [sp, #8]
; CHECK: variadic
define i32 @main() ssp {