| //=- AArch64CallingConv.td - Calling Conventions for AArch64 -*- tablegen -*-=// | |
| // | |
| // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. | |
| // See https://llvm.org/LICENSE.txt for license information. | |
| // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | |
| // | |
| //===----------------------------------------------------------------------===// | |
| // | |
| // This describes the calling conventions for AArch64 architecture. | |
| // | |
| //===----------------------------------------------------------------------===// | |
| /// CCIfBigEndian - Match only if we're in big endian mode. | |
| class CCIfBigEndian<CCAction A> : | |
| CCIf<"State.getMachineFunction().getDataLayout().isBigEndian()", A>; | |
| class CCIfILP32<CCAction A> : | |
| CCIf<"State.getMachineFunction().getDataLayout().getPointerSize() == 4", A>; | |
| //===----------------------------------------------------------------------===// | |
| // ARM AAPCS64 Calling Convention | |
| //===----------------------------------------------------------------------===// | |
| let Entry = 1 in | |
| def CC_AArch64_AAPCS : CallingConv<[ | |
| CCIfType<[iPTR], CCBitConvertToType<i64>>, | |
| CCIfType<[v2f32], CCBitConvertToType<v2i32>>, | |
| CCIfType<[v2f64, v4f32], CCBitConvertToType<v2i64>>, | |
| // Big endian vectors must be passed as if they were 1-element vectors so that | |
| // their lanes are in a consistent order. | |
| CCIfBigEndian<CCIfType<[v2i32, v2f32, v4i16, v4f16, v4bf16, v8i8], | |
| CCBitConvertToType<f64>>>, | |
| CCIfBigEndian<CCIfType<[v2i64, v2f64, v4i32, v4f32, v8i16, v8f16, v8bf16, v16i8], | |
| CCBitConvertToType<f128>>>, | |
| // In AAPCS, an SRet is passed in X8, not X0 like a normal pointer parameter. | |
| // However, on windows, in some circumstances, the SRet is passed in X0 or X1 | |
| // instead. The presence of the inreg attribute indicates that SRet is | |
| // passed in the alternative register (X0 or X1), not X8: | |
| // - X0 for non-instance methods. | |
| // - X1 for instance methods. | |
| // The "sret" attribute identifies indirect returns. | |
| // The "inreg" attribute identifies non-aggregate types. | |
| // The position of the "sret" attribute identifies instance/non-instance | |
| // methods. | |
| // "sret" on argument 0 means non-instance methods. | |
| // "sret" on argument 1 means instance methods. | |
| CCIfInReg<CCIfType<[i64], | |
| CCIfSRet<CCIfType<[i64], CCAssignToReg<[X0, X1]>>>>>, | |
| CCIfSRet<CCIfType<[i64], CCAssignToReg<[X8]>>>, | |
| // Put ByVal arguments directly on the stack. Minimum size and alignment of a | |
| // slot is 64-bit. | |
| CCIfByVal<CCPassByVal<8, 8>>, | |
| // The 'nest' parameter, if any, is passed in X18. | |
| // Darwin uses X18 as the platform register and hence 'nest' isn't currently | |
| // supported there. | |
| CCIfNest<CCAssignToReg<[X18]>>, | |
| // Pass SwiftSelf in a callee saved register. | |
| CCIfSwiftSelf<CCIfType<[i64], CCAssignToReg<[X20]>>>, | |
| // A SwiftError is passed in X21. | |
| CCIfSwiftError<CCIfType<[i64], CCAssignToReg<[X21]>>>, | |
| // Pass SwiftAsync in an otherwise callee saved register so that it will be | |
| // preserved for normal function calls. | |
| CCIfSwiftAsync<CCIfType<[i64], CCAssignToReg<[X22]>>>, | |
| CCIfConsecutiveRegs<CCCustom<"CC_AArch64_Custom_Block">>, | |
| CCIfType<[nxv16i8, nxv8i16, nxv4i32, nxv2i64, nxv2f16, nxv4f16, nxv8f16, | |
| nxv2bf16, nxv4bf16, nxv8bf16, nxv2f32, nxv4f32, nxv2f64], | |
| CCAssignToReg<[Z0, Z1, Z2, Z3, Z4, Z5, Z6, Z7]>>, | |
| CCIfType<[nxv16i8, nxv8i16, nxv4i32, nxv2i64, nxv2f16, nxv4f16, nxv8f16, | |
| nxv2bf16, nxv4bf16, nxv8bf16, nxv2f32, nxv4f32, nxv2f64], | |
| CCPassIndirect<i64>>, | |
| CCIfType<[nxv1i1, nxv2i1, nxv4i1, nxv8i1, nxv16i1], | |
| CCAssignToReg<[P0, P1, P2, P3]>>, | |
| CCIfType<[nxv1i1, nxv2i1, nxv4i1, nxv8i1, nxv16i1], | |
| CCPassIndirect<i64>>, | |
| // Handle i1, i8, i16, i32, i64, f32, f64 and v2f64 by passing in registers, | |
| // up to eight each of GPR and FPR. | |
| CCIfType<[i1, i8, i16], CCPromoteToType<i32>>, | |
| CCIfType<[i32], CCAssignToReg<[W0, W1, W2, W3, W4, W5, W6, W7]>>, | |
| // i128 is split to two i64s, we can't fit half to register X7. | |
| CCIfType<[i64], CCIfSplit<CCAssignToRegWithShadow<[X0, X2, X4, X6], | |
| [X0, X1, X3, X5]>>>, | |
| // i128 is split to two i64s, and its stack alignment is 16 bytes. | |
| CCIfType<[i64], CCIfSplit<CCAssignToStackWithShadow<8, 16, [X7]>>>, | |
| CCIfType<[i64], CCAssignToReg<[X0, X1, X2, X3, X4, X5, X6, X7]>>, | |
| CCIfType<[f16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[bf16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7]>>, | |
| CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[v1i64, v2i32, v4i16, v8i8, v1f64, v2f32, v4f16, v4bf16], | |
| CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[f128, v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToReg<[Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7]>>, | |
| // If more than will fit in registers, pass them on the stack instead. | |
| CCIfType<[i1, i8, i16, f16, bf16], CCAssignToStack<8, 8>>, | |
| CCIfType<[i32, f32], CCAssignToStack<8, 8>>, | |
| CCIfType<[i64, f64, v1f64, v2f32, v1i64, v2i32, v4i16, v8i8, v4f16, v4bf16], | |
| CCAssignToStack<8, 8>>, | |
| CCIfType<[f128, v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToStack<16, 16>> | |
| ]>; | |
| let Entry = 1 in | |
| def RetCC_AArch64_AAPCS : CallingConv<[ | |
| CCIfType<[iPTR], CCBitConvertToType<i64>>, | |
| CCIfType<[v2f32], CCBitConvertToType<v2i32>>, | |
| CCIfType<[v2f64, v4f32], CCBitConvertToType<v2i64>>, | |
| CCIfConsecutiveRegs<CCCustom<"CC_AArch64_Custom_Block">>, | |
| CCIfSwiftError<CCIfType<[i64], CCAssignToReg<[X21]>>>, | |
| // Big endian vectors must be passed as if they were 1-element vectors so that | |
| // their lanes are in a consistent order. | |
| CCIfBigEndian<CCIfType<[v2i32, v2f32, v4i16, v4f16, v4bf16, v8i8], | |
| CCBitConvertToType<f64>>>, | |
| CCIfBigEndian<CCIfType<[v2i64, v2f64, v4i32, v4f32, v8i16, v8f16, v8bf16, v16i8], | |
| CCBitConvertToType<f128>>>, | |
| CCIfType<[i1, i8, i16], CCPromoteToType<i32>>, | |
| CCIfType<[i32], CCAssignToReg<[W0, W1, W2, W3, W4, W5, W6, W7]>>, | |
| CCIfType<[i64], CCAssignToReg<[X0, X1, X2, X3, X4, X5, X6, X7]>>, | |
| CCIfType<[f16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[bf16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7]>>, | |
| CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[v1i64, v2i32, v4i16, v8i8, v1f64, v2f32, v4f16, v4bf16], | |
| CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[f128, v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToReg<[Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7]>>, | |
| CCIfType<[nxv16i8, nxv8i16, nxv4i32, nxv2i64, nxv2f16, nxv4f16, nxv8f16, | |
| nxv2bf16, nxv4bf16, nxv8bf16, nxv2f32, nxv4f32, nxv2f64], | |
| CCAssignToReg<[Z0, Z1, Z2, Z3, Z4, Z5, Z6, Z7]>>, | |
| CCIfType<[nxv1i1, nxv2i1, nxv4i1, nxv8i1, nxv16i1], | |
| CCAssignToReg<[P0, P1, P2, P3]>> | |
| ]>; | |
| // Vararg functions on windows pass floats in integer registers | |
| let Entry = 1 in | |
| def CC_AArch64_Win64_VarArg : CallingConv<[ | |
| CCIfType<[f16, bf16], CCBitConvertToType<i16>>, | |
| CCIfType<[f32], CCBitConvertToType<i32>>, | |
| CCIfType<[f64], CCBitConvertToType<i64>>, | |
| CCDelegateTo<CC_AArch64_AAPCS> | |
| ]>; | |
| // Vararg functions on Arm64EC ABI use a different convention, using | |
| // a stack layout compatible with the x64 calling convention. | |
| let Entry = 1 in | |
| def CC_AArch64_Arm64EC_VarArg : CallingConv<[ | |
| // Convert small floating-point values to integer. | |
| CCIfType<[f16, bf16], CCBitConvertToType<i16>>, | |
| CCIfType<[f32], CCBitConvertToType<i32>>, | |
| CCIfType<[f64, v1f64, v1i64, v2f32, v2i32, v4i16, v4f16, v4bf16, v8i8, iPTR], | |
| CCBitConvertToType<i64>>, | |
| // Larger floating-point/vector values are passed indirectly. | |
| CCIfType<[f128, v2f64, v2i64, v4i32, v4f32, v8i16, v8f16, v8bf16, v16i8], | |
| CCPassIndirect<i64>>, | |
| CCIfType<[nxv16i8, nxv8i16, nxv4i32, nxv2i64, nxv2f16, nxv4f16, nxv8f16, | |
| nxv2bf16, nxv4bf16, nxv8bf16, nxv2f32, nxv4f32, nxv2f64], | |
| CCPassIndirect<i64>>, | |
| CCIfType<[nxv2i1, nxv4i1, nxv8i1, nxv16i1], | |
| CCPassIndirect<i64>>, | |
| // Handle SRet. See comment in CC_AArch64_AAPCS. | |
| CCIfInReg<CCIfType<[i64], | |
| CCIfSRet<CCIfType<[i64], CCAssignToReg<[X0, X1]>>>>>, | |
| CCIfSRet<CCIfType<[i64], CCAssignToReg<[X8]>>>, | |
| // Put ByVal arguments directly on the stack. Minimum size and alignment of a | |
| // slot is 64-bit. (Shouldn't normally come up; the Microsoft ABI doesn't | |
| // use byval.) | |
| CCIfByVal<CCPassByVal<8, 8>>, | |
| // Promote small integers to i32 | |
| CCIfType<[i1, i8, i16], CCPromoteToType<i32>>, | |
| // Pass first four arguments in x0-x3. | |
| CCIfType<[i32], CCAssignToReg<[W0, W1, W2, W3]>>, | |
| CCIfType<[i64], CCAssignToReg<[X0, X1, X2, X3]>>, | |
| // Put remaining arguments on stack. | |
| CCIfType<[i32, i64], CCAssignToStack<8, 8>>, | |
| ]>; | |
| // Windows Control Flow Guard checks take a single argument (the target function | |
| // address) and have no return value. | |
| let Entry = 1 in | |
| def CC_AArch64_Win64_CFGuard_Check : CallingConv<[ | |
| CCIfType<[i64], CCAssignToReg<[X15]>> | |
| ]>; | |
| // Darwin uses a calling convention which differs in only two ways | |
| // from the standard one at this level: | |
| // + i128s (i.e. split i64s) don't need even registers. | |
| // + Stack slots are sized as needed rather than being at least 64-bit. | |
| let Entry = 1 in | |
| def CC_AArch64_DarwinPCS : CallingConv<[ | |
| CCIfType<[iPTR], CCBitConvertToType<i64>>, | |
| CCIfType<[v2f32], CCBitConvertToType<v2i32>>, | |
| CCIfType<[v2f64, v4f32, f128], CCBitConvertToType<v2i64>>, | |
| // An SRet is passed in X8, not X0 like a normal pointer parameter. | |
| CCIfSRet<CCIfType<[i64], CCAssignToReg<[X8]>>>, | |
| // Put ByVal arguments directly on the stack. Minimum size and alignment of a | |
| // slot is 64-bit. | |
| CCIfByVal<CCPassByVal<8, 8>>, | |
| // Pass SwiftSelf in a callee saved register. | |
| CCIfSwiftSelf<CCIfType<[i64], CCAssignToReg<[X20]>>>, | |
| // A SwiftError is passed in X21. | |
| CCIfSwiftError<CCIfType<[i64], CCAssignToReg<[X21]>>>, | |
| // Pass SwiftAsync in an otherwise callee saved register so that it will be | |
| // preserved for normal function calls. | |
| CCIfSwiftAsync<CCIfType<[i64], CCAssignToReg<[X22]>>>, | |
| CCIfConsecutiveRegs<CCCustom<"CC_AArch64_Custom_Block">>, | |
| // Handle i1, i8, i16, i32, i64, f32, f64 and v2f64 by passing in registers, | |
| // up to eight each of GPR and FPR. | |
| CCIfType<[i1, i8, i16], CCPromoteToType<i32>>, | |
| CCIfType<[i32], CCAssignToReg<[W0, W1, W2, W3, W4, W5, W6, W7]>>, | |
| // i128 is split to two i64s, we can't fit half to register X7. | |
| CCIfType<[i64], | |
| CCIfSplit<CCAssignToReg<[X0, X1, X2, X3, X4, X5, X6]>>>, | |
| // i128 is split to two i64s, and its stack alignment is 16 bytes. | |
| CCIfType<[i64], CCIfSplit<CCAssignToStackWithShadow<8, 16, [X7]>>>, | |
| CCIfType<[i64], CCAssignToReg<[X0, X1, X2, X3, X4, X5, X6, X7]>>, | |
| CCIfType<[f16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[bf16], CCAssignToReg<[H0, H1, H2, H3, H4, H5, H6, H7]>>, | |
| CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7]>>, | |
| CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[v1i64, v2i32, v4i16, v8i8, v1f64, v2f32, v4f16, v4bf16], | |
| CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, | |
| CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToReg<[Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7]>>, | |
| // If more than will fit in registers, pass them on the stack instead. | |
| CCIf<"ValVT == MVT::i1 || ValVT == MVT::i8", CCAssignToStack<1, 1>>, | |
| CCIf<"ValVT == MVT::i16 || ValVT == MVT::f16 || ValVT == MVT::bf16", | |
| CCAssignToStack<2, 2>>, | |
| CCIfType<[i32, f32], CCAssignToStack<4, 4>>, | |
| // Re-demote pointers to 32-bits so we don't end up storing 64-bit | |
| // values and clobbering neighbouring stack locations. Not very pretty. | |
| CCIfPtr<CCIfILP32<CCTruncToType<i32>>>, | |
| CCIfPtr<CCIfILP32<CCAssignToStack<4, 4>>>, | |
| CCIfType<[i64, f64, v1f64, v2f32, v1i64, v2i32, v4i16, v8i8, v4f16, v4bf16], | |
| CCAssignToStack<8, 8>>, | |
| CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToStack<16, 16>> | |
| ]>; | |
| let Entry = 1 in | |
| def CC_AArch64_DarwinPCS_VarArg : CallingConv<[ | |
| CCIfType<[iPTR], CCBitConvertToType<i64>>, | |
| CCIfType<[v2f32], CCBitConvertToType<v2i32>>, | |
| CCIfType<[v2f64, v4f32, f128], CCBitConvertToType<v2i64>>, | |
| CCIfConsecutiveRegs<CCCustom<"CC_AArch64_Custom_Stack_Block">>, | |
| // Handle all scalar types as either i64 or f64. | |
| CCIfType<[i8, i16, i32], CCPromoteToType<i64>>, | |
| CCIfType<[f16, bf16, f32], CCPromoteToType<f64>>, | |
| // Everything is on the stack. | |
| // i128 is split to two i64s, and its stack alignment is 16 bytes. | |
| CCIfType<[i64], CCIfSplit<CCAssignToStack<8, 16>>>, | |
| CCIfType<[i64, f64, v1i64, v2i32, v4i16, v8i8, v1f64, v2f32, v4f16, v4bf16], | |
| CCAssignToStack<8, 8>>, | |
| CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToStack<16, 16>> | |
| ]>; | |
| // In the ILP32 world, the minimum stack slot size is 4 bytes. Otherwise the | |
| // same as the normal Darwin VarArgs handling. | |
| let Entry = 1 in | |
| def CC_AArch64_DarwinPCS_ILP32_VarArg : CallingConv<[ | |
| CCIfType<[v2f32], CCBitConvertToType<v2i32>>, | |
| CCIfType<[v2f64, v4f32, f128], CCBitConvertToType<v2i64>>, | |
| // Handle all scalar types as either i32 or f32. | |
| CCIfType<[i8, i16], CCPromoteToType<i32>>, | |
| CCIfType<[f16, bf16], CCPromoteToType<f32>>, | |
| // Everything is on the stack. | |
| // i128 is split to two i64s, and its stack alignment is 16 bytes. | |
| CCIfPtr<CCIfILP32<CCTruncToType<i32>>>, | |
| CCIfType<[i32, f32], CCAssignToStack<4, 4>>, | |
| CCIfType<[i64], CCIfSplit<CCAssignToStack<8, 16>>>, | |
| CCIfType<[i64, f64, v1i64, v2i32, v4i16, v8i8, v1f64, v2f32, v4f16, v4bf16], | |
| CCAssignToStack<8, 8>>, | |
| CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, v2f64, v8f16, v8bf16], | |
| CCAssignToStack<16, 16>> | |
| ]>; | |
| // The WebKit_JS calling convention only passes the first argument (the callee) | |
| // in register and the remaining arguments on stack. We allow 32bit stack slots, | |
| // so that WebKit can write partial values in the stack and define the other | |
| // 32bit quantity as undef. | |
| let Entry = 1 in | |
| def CC_AArch64_WebKit_JS : CallingConv<[ | |
| // Handle i1, i8, i16, i32, and i64 passing in register X0 (W0). | |
| CCIfType<[i1, i8, i16], CCPromoteToType<i32>>, | |
| CCIfType<[i32], CCAssignToReg<[W0]>>, | |
| CCIfType<[i64], CCAssignToReg<[X0]>>, | |
| // Pass the remaining arguments on the stack instead. | |
| CCIfType<[i32, f32], CCAssignToStack<4, 4>>, | |
| CCIfType<[i64, f64], CCAssignToStack<8, 8>> | |
| ]>; | |
| let Entry = 1 in | |
| def RetCC_AArch64_WebKit_JS : CallingConv<[ | |
| CCIfType<[i32], CCAssignToReg<[W0, W1, W2, W3, W4, W5, W6, W7]>>, | |
| CCIfType<[i64], CCAssignToReg<[X0, X1, X2, X3, X4, X5, X6, X7]>>, | |
| CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7]>>, | |
| CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>> | |
| ]>; | |
| //===----------------------------------------------------------------------===// | |
| // ARM64 Calling Convention for GHC | |
| //===----------------------------------------------------------------------===// | |
| // This calling convention is specific to the Glasgow Haskell Compiler. | |
| // The only documentation is the GHC source code, specifically the C header | |
| // file: | |
| // | |
| // https://github.com/ghc/ghc/blob/master/includes/stg/MachRegs.h | |
| // | |
| // which defines the registers for the Spineless Tagless G-Machine (STG) that | |
| // GHC uses to implement lazy evaluation. The generic STG machine has a set of | |
| // registers which are mapped to appropriate set of architecture specific | |
| // registers for each CPU architecture. | |
| // | |
| // The STG Machine is documented here: | |
| // | |
| // https://ghc.haskell.org/trac/ghc/wiki/Commentary/Compiler/GeneratedCode | |
| // | |
| // The AArch64 register mapping is under the heading "The ARMv8/AArch64 ABI | |
| // register mapping". | |
| let Entry = 1 in | |
| def CC_AArch64_GHC : CallingConv<[ | |
| CCIfType<[iPTR], CCBitConvertToType<i64>>, | |
| // Handle all vector types as either f64 or v2f64. | |
| CCIfType<[v1i64, v2i32, v4i16, v8i8, v2f32], CCBitConvertToType<f64>>, | |
| CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, f128], CCBitConvertToType<v2f64>>, | |
| CCIfType<[v2f64], CCAssignToReg<[Q4, Q5]>>, | |
| CCIfType<[f32], CCAssignToReg<[S8, S9, S10, S11]>>, | |
| CCIfType<[f64], CCAssignToReg<[D12, D13, D14, D15]>>, | |
| // Promote i8/i16/i32 arguments to i64. | |
| CCIfType<[i8, i16, i32], CCPromoteToType<i64>>, | |
| // Pass in STG registers: Base, Sp, Hp, R1, R2, R3, R4, R5, R6, SpLim | |
| CCIfType<[i64], CCAssignToReg<[X19, X20, X21, X22, X23, X24, X25, X26, X27, X28]>> | |
| ]>; | |
| // The order of the callee-saves in this file is important, because the | |
| // FrameLowering code will use this order to determine the layout the | |
| // callee-save area in the stack frame. As can be observed below, Darwin | |
| // requires the frame-record (LR, FP) to be at the top the callee-save area, | |
| // whereas for other platforms they are at the bottom. | |
| // FIXME: LR is only callee-saved in the sense that *we* preserve it and are | |
| // presumably a callee to someone. External functions may not do so, but this | |
| // is currently safe since BL has LR as an implicit-def and what happens after a | |
| // tail call doesn't matter. | |
| // | |
| // It would be better to model its preservation semantics properly (create a | |
| // vreg on entry, use it in RET & tail call generation; make that vreg def if we | |
| // end up saving LR as part of a call frame). Watch this space... | |
| def CSR_AArch64_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24, | |
| X25, X26, X27, X28, LR, FP, | |
| D8, D9, D10, D11, | |
| D12, D13, D14, D15)>; | |
| // A variant for treating X18 as callee saved, when interfacing with | |
| // code that needs X18 to be preserved. | |
| def CSR_AArch64_AAPCS_X18 : CalleeSavedRegs<(add X18, CSR_AArch64_AAPCS)>; | |
| // Win64 has unwinding codes for an (FP,LR) pair, save_fplr and save_fplr_x. | |
| // We put FP before LR, so that frame lowering logic generates (FP,LR) pairs, | |
| // and not (LR,FP) pairs. | |
| def CSR_Win_AArch64_AAPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24, | |
| X25, X26, X27, X28, FP, LR, | |
| D8, D9, D10, D11, | |
| D12, D13, D14, D15)>; | |
| // The Control Flow Guard check call uses a custom calling convention that also | |
| // preserves X0-X8 and Q0-Q7. | |
| def CSR_Win_AArch64_CFGuard_Check : CalleeSavedRegs<(add CSR_Win_AArch64_AAPCS, | |
| (sequence "X%u", 0, 8), | |
| (sequence "Q%u", 0, 7))>; | |
| // AArch64 PCS for vector functions (VPCS) | |
| // must (additionally) preserve full Q8-Q23 registers | |
| def CSR_AArch64_AAVPCS : CalleeSavedRegs<(add X19, X20, X21, X22, X23, X24, | |
| X25, X26, X27, X28, LR, FP, | |
| (sequence "Q%u", 8, 23))>; | |
| // Functions taking SVE arguments or returning an SVE type | |
| // must (additionally) preserve full Z8-Z23 and predicate registers P4-P15 | |
| def CSR_AArch64_SVE_AAPCS : CalleeSavedRegs<(add (sequence "Z%u", 8, 23), | |
| (sequence "P%u", 4, 15), | |
| X19, X20, X21, X22, X23, X24, | |
| X25, X26, X27, X28, LR, FP)>; | |
| // SME ABI support routines such as __arm_tpidr2_save/restore preserve most registers. | |
| def CSR_AArch64_SME_ABI_Support_Routines_PreserveMost_From_X0 | |
| : CalleeSavedRegs<(add (sequence "Z%u", 0, 31), | |
| (sequence "P%u", 0, 15), | |
| (sequence "X%u", 0, 13), | |
| (sequence "X%u",19, 28), | |
| LR, FP)>; | |
| // SME ABI support routines __arm_sme_state preserves most registers. | |
| def CSR_AArch64_SME_ABI_Support_Routines_PreserveMost_From_X2 | |
| : CalleeSavedRegs<(add (sequence "Z%u", 0, 31), | |
| (sequence "P%u", 0, 15), | |
| (sequence "X%u", 2, 15), | |
| (sequence "X%u",19, 28), | |
| LR, FP)>; | |
| // The SMSTART/SMSTOP instructions preserve only GPR registers. | |
| def CSR_AArch64_SMStartStop : CalleeSavedRegs<(add (sequence "X%u", 0, 28), | |
| LR, FP)>; | |
| def CSR_AArch64_AAPCS_SwiftTail | |
| : CalleeSavedRegs<(sub CSR_AArch64_AAPCS, X20, X22)>; | |
| // Constructors and destructors return 'this' in the iOS 64-bit C++ ABI; since | |
| // 'this' and the pointer return value are both passed in X0 in these cases, | |
| // this can be partially modelled by treating X0 as a callee-saved register; | |
| // only the resulting RegMask is used; the SaveList is ignored | |
| // | |
| // (For generic ARM 64-bit ABI code, clang will not generate constructors or | |
| // destructors with 'this' returns, so this RegMask will not be used in that | |
| // case) | |
| def CSR_AArch64_AAPCS_ThisReturn : CalleeSavedRegs<(add CSR_AArch64_AAPCS, X0)>; | |
| def CSR_AArch64_AAPCS_SwiftError | |
| : CalleeSavedRegs<(sub CSR_AArch64_AAPCS, X21)>; | |
| // The ELF stub used for TLS-descriptor access saves every feasible | |
| // register. Only X0 and LR are clobbered. | |
| def CSR_AArch64_TLS_ELF | |
| : CalleeSavedRegs<(add (sequence "X%u", 1, 28), FP, | |
| (sequence "Q%u", 0, 31))>; | |
| def CSR_AArch64_AllRegs | |
| : CalleeSavedRegs<(add (sequence "W%u", 0, 30), WSP, | |
| (sequence "X%u", 0, 28), FP, LR, SP, | |
| (sequence "B%u", 0, 31), (sequence "H%u", 0, 31), | |
| (sequence "S%u", 0, 31), (sequence "D%u", 0, 31), | |
| (sequence "Q%u", 0, 31))>; | |
| def CSR_AArch64_NoRegs : CalleeSavedRegs<(add)>; | |
| def CSR_AArch64_RT_MostRegs : CalleeSavedRegs<(add CSR_AArch64_AAPCS, | |
| (sequence "X%u", 9, 15))>; | |
| def CSR_AArch64_StackProbe_Windows | |
| : CalleeSavedRegs<(add (sequence "X%u", 0, 15), | |
| (sequence "X%u", 18, 28), FP, SP, | |
| (sequence "Q%u", 0, 31))>; | |
| // Darwin variants of AAPCS. | |
| // Darwin puts the frame-record at the top of the callee-save area. | |
| def CSR_Darwin_AArch64_AAPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, X22, | |
| X23, X24, X25, X26, X27, X28, | |
| D8, D9, D10, D11, | |
| D12, D13, D14, D15)>; | |
| def CSR_Darwin_AArch64_AAVPCS : CalleeSavedRegs<(add LR, FP, X19, X20, X21, | |
| X22, X23, X24, X25, X26, X27, | |
| X28, (sequence "Q%u", 8, 23))>; | |
| // For Windows calling convention on a non-windows OS, where X18 is treated | |
| // as reserved, back up X18 when entering non-windows code (marked with the | |
| // Windows calling convention) and restore when returning regardless of | |
| // whether the individual function uses it - it might call other functions | |
| // that clobber it. | |
| def CSR_Darwin_AArch64_AAPCS_Win64 | |
| : CalleeSavedRegs<(add CSR_Darwin_AArch64_AAPCS, X18)>; | |
| def CSR_Darwin_AArch64_AAPCS_ThisReturn | |
| : CalleeSavedRegs<(add CSR_Darwin_AArch64_AAPCS, X0)>; | |
| def CSR_Darwin_AArch64_AAPCS_SwiftError | |
| : CalleeSavedRegs<(sub CSR_Darwin_AArch64_AAPCS, X21)>; | |
| def CSR_Darwin_AArch64_AAPCS_SwiftTail | |
| : CalleeSavedRegs<(sub CSR_Darwin_AArch64_AAPCS, X20, X22)>; | |
| // The function used by Darwin to obtain the address of a thread-local variable | |
| // guarantees more than a normal AAPCS function. x16 and x17 are used on the | |
| // fast path for calculation, but other registers except X0 (argument/return) | |
| // and LR (it is a call, after all) are preserved. | |
| def CSR_Darwin_AArch64_TLS | |
| : CalleeSavedRegs<(add (sub (sequence "X%u", 1, 28), X16, X17), | |
| FP, | |
| (sequence "Q%u", 0, 31))>; | |
| // We can only handle a register pair with adjacent registers, the register pair | |
| // should belong to the same class as well. Since the access function on the | |
| // fast path calls a function that follows CSR_Darwin_AArch64_TLS, | |
| // CSR_Darwin_AArch64_CXX_TLS should be a subset of CSR_Darwin_AArch64_TLS. | |
| def CSR_Darwin_AArch64_CXX_TLS | |
| : CalleeSavedRegs<(add CSR_Darwin_AArch64_AAPCS, | |
| (sub (sequence "X%u", 1, 28), X9, X15, X16, X17, X18, X19), | |
| (sequence "D%u", 0, 31))>; | |
| // CSRs that are handled by prologue, epilogue. | |
| def CSR_Darwin_AArch64_CXX_TLS_PE | |
| : CalleeSavedRegs<(add LR, FP)>; | |
| // CSRs that are handled explicitly via copies. | |
| def CSR_Darwin_AArch64_CXX_TLS_ViaCopy | |
| : CalleeSavedRegs<(sub CSR_Darwin_AArch64_CXX_TLS, LR, FP)>; | |
| def CSR_Darwin_AArch64_RT_MostRegs | |
| : CalleeSavedRegs<(add CSR_Darwin_AArch64_AAPCS, (sequence "X%u", 9, 15))>; | |
| // Variants of the standard calling conventions for shadow call stack. | |
| // These all preserve x18 in addition to any other registers. | |
| def CSR_AArch64_NoRegs_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_NoRegs, X18)>; | |
| def CSR_AArch64_AllRegs_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_AllRegs, X18)>; | |
| def CSR_AArch64_AAPCS_SwiftError_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_AAPCS_SwiftError, X18)>; | |
| def CSR_AArch64_RT_MostRegs_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_RT_MostRegs, X18)>; | |
| def CSR_AArch64_AAVPCS_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_AAVPCS, X18)>; | |
| def CSR_AArch64_SVE_AAPCS_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_SVE_AAPCS, X18)>; | |
| def CSR_AArch64_AAPCS_SCS | |
| : CalleeSavedRegs<(add CSR_AArch64_AAPCS, X18)>; |