aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Target/ARM/ARMCallingConv.td
blob: a6dbe563a4ab7dcc3d2d9ebdc3b2f85b5676788a (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
//===-- ARMCallingConv.td - Calling Conventions for ARM ----*- 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 ARM architecture.
//===----------------------------------------------------------------------===//

/// CCIfAlign - Match of the original alignment of the arg
class CCIfAlign<string Align, CCAction A>:
  CCIf<!strconcat("ArgFlags.getNonZeroOrigAlign() == ", Align), A>;

//===----------------------------------------------------------------------===//
// ARM APCS Calling Convention
//===----------------------------------------------------------------------===//
let Entry = 1 in
def CC_ARM_APCS : CallingConv<[

  // Handles byval parameters.
  CCIfByVal<CCPassByVal<4, 4>>,

  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is passed in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  // f64 and v2f64 are passed in adjacent GPRs, possibly split onto the stack
  CCIfType<[f64, v2f64], CCCustom<"CC_ARM_APCS_Custom_f64">>,

  CCIfType<[f32], CCBitConvertToType<i32>>,
  CCIfType<[i32], CCAssignToReg<[R0, R1, R2, R3]>>,

  CCIfType<[i32], CCAssignToStack<4, 4>>,
  CCIfType<[f64], CCAssignToStack<8, 4>>,
  CCIfType<[v2f64], CCAssignToStack<16, 4>>
]>;

let Entry = 1 in
def RetCC_ARM_APCS : CallingConv<[
  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
  CCIfType<[f32], CCBitConvertToType<i32>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is returned in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  CCIfType<[f64, v2f64], CCCustom<"RetCC_ARM_APCS_Custom_f64">>,

  CCIfType<[i32], CCAssignToReg<[R0, R1, R2, R3]>>,
  CCIfType<[i64], CCAssignToRegWithShadow<[R0, R2], [R1, R3]>>
]>;

//===----------------------------------------------------------------------===//
// ARM APCS Calling Convention for FastCC (when VFP2 or later is available)
//===----------------------------------------------------------------------===//
let Entry = 1 in
def FastCC_ARM_APCS : CallingConv<[
  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
                                 S9, S10, S11, S12, S13, S14, S15]>>,

  // CPRCs may be allocated to co-processor registers or the stack - they
  // may never be allocated to core registers.
  CCIfType<[f32], CCAssignToStackWithShadow<4, 4, [Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToStackWithShadow<8, 4, [Q0, Q1, Q2, Q3]>>,
  CCIfType<[v2f64], CCAssignToStackWithShadow<16, 4, [Q0, Q1, Q2, Q3]>>,

  CCDelegateTo<CC_ARM_APCS>
]>;

let Entry = 1 in
def RetFastCC_ARM_APCS : CallingConv<[
  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
                                 S9, S10, S11, S12, S13, S14, S15]>>,
  CCDelegateTo<RetCC_ARM_APCS>
]>;

//===----------------------------------------------------------------------===//
// ARM APCS Calling Convention for GHC
//===----------------------------------------------------------------------===//

let Entry = 1 in
def CC_ARM_APCS_GHC : CallingConv<[
  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  CCIfType<[v2f64], CCAssignToReg<[Q4, Q5]>>,
  CCIfType<[f64], CCAssignToReg<[D8, D9, D10, D11]>>,
  CCIfType<[f32], CCAssignToReg<[S16, S17, S18, S19, S20, S21, S22, S23]>>,

  // Promote i8/i16 arguments to i32.
  CCIfType<[i8, i16], CCPromoteToType<i32>>,

  // Pass in STG registers: Base, Sp, Hp, R1, R2, R3, R4, SpLim
  CCIfType<[i32], CCAssignToReg<[R4, R5, R6, R7, R8, R9, R10, R11]>>
]>;

//===----------------------------------------------------------------------===//
// ARM AAPCS (EABI) Calling Convention, common parts
//===----------------------------------------------------------------------===//

def CC_ARM_AAPCS_Common : CallingConv<[

  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,

  // i64/f64 is passed in even pairs of GPRs
  // i64 is 8-aligned i32 here, so we may need to eat R1 as a pad register
  // (and the same is true for f64 if VFP is not enabled)
  CCIfType<[i32], CCIfAlign<"8", CCAssignToRegWithShadow<[R0, R2], [R0, R1]>>>,
  CCIfType<[i32], CCIf<"ArgFlags.getNonZeroOrigAlign() != Align(8)",
                       CCAssignToReg<[R0, R1, R2, R3]>>>,

  CCIfType<[i32], CCIfAlign<"8", CCAssignToStackWithShadow<4, 8, [R0, R1, R2, R3]>>>,
  CCIfType<[i32], CCAssignToStackWithShadow<4, 4, [R0, R1, R2, R3]>>,
  CCIfType<[f16, bf16, f32], CCAssignToStackWithShadow<4, 4, [Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToStackWithShadow<8, 8, [Q0, Q1, Q2, Q3]>>,
  CCIfType<[v2f64], CCIfAlign<"16",
           CCAssignToStackWithShadow<16, 16, [Q0, Q1, Q2, Q3]>>>,
  CCIfType<[v2f64], CCAssignToStackWithShadow<16, 8, [Q0, Q1, Q2, Q3]>>
]>;

def RetCC_ARM_AAPCS_Common : CallingConv<[
  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
  CCIfType<[i32], CCAssignToReg<[R0, R1, R2, R3]>>,
  CCIfType<[i64], CCAssignToRegWithShadow<[R0, R2], [R1, R3]>>
]>;

//===----------------------------------------------------------------------===//
// ARM AAPCS (EABI) Calling Convention
//===----------------------------------------------------------------------===//

let Entry = 1 in
def CC_ARM_AAPCS : CallingConv<[
  // Handles byval parameters.
  CCIfByVal<CCPassByVal<4, 4>>,

  // The 'nest' parameter, if any, is passed in R12.
  CCIfNest<CCAssignToReg<[R12]>>,

  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is passed in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  CCIfType<[f64, v2f64], CCCustom<"CC_ARM_AAPCS_Custom_f64">>,
  CCIfType<[f32], CCBitConvertToType<i32>>,
  CCIfType<[f16, bf16], CCCustom<"CC_ARM_AAPCS_Custom_f16">>,
  CCDelegateTo<CC_ARM_AAPCS_Common>
]>;

let Entry = 1 in
def RetCC_ARM_AAPCS : CallingConv<[
  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is returned in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  CCIfType<[f64, v2f64], CCCustom<"RetCC_ARM_AAPCS_Custom_f64">>,
  CCIfType<[f32], CCBitConvertToType<i32>>,
  CCIfType<[f16, bf16], CCCustom<"CC_ARM_AAPCS_Custom_f16">>,

  CCDelegateTo<RetCC_ARM_AAPCS_Common>
]>;

//===----------------------------------------------------------------------===//
// ARM AAPCS-VFP (EABI) Calling Convention
// Also used for FastCC (when VFP2 or later is available)
//===----------------------------------------------------------------------===//

let Entry = 1 in
def CC_ARM_AAPCS_VFP : CallingConv<[
  // Handles byval parameters.
  CCIfByVal<CCPassByVal<4, 4>>,

  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is passed in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  // HFAs are passed in a contiguous block of registers, or on the stack
  CCIfConsecutiveRegs<CCCustom<"CC_ARM_AAPCS_Custom_Aggregate">>,

  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
                                 S9, S10, S11, S12, S13, S14, S15]>>,
  CCIfType<[f16, bf16], CCCustom<"CC_ARM_AAPCS_VFP_Custom_f16">>,
  CCDelegateTo<CC_ARM_AAPCS_Common>
]>;

let Entry = 1 in
def RetCC_ARM_AAPCS_VFP : CallingConv<[
  // Handle all vector types as either f64 or v2f64.
  CCIfType<[v1i64, v2i32, v4i16, v4f16, v4bf16, v8i8, v2f32], CCBitConvertToType<f64>>,
  CCIfType<[v2i64, v4i32, v8i16, v8f16, v8bf16, v16i8, v4f32], CCBitConvertToType<v2f64>>,

  // Pass SwiftSelf in a callee saved register.
  CCIfSwiftSelf<CCIfType<[i32], CCAssignToReg<[R10]>>>,

  // A SwiftError is returned in R8.
  CCIfSwiftError<CCIfType<[i32], CCAssignToReg<[R8]>>>,

  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
                                 S9, S10, S11, S12, S13, S14, S15]>>,
  CCIfType<[f16, bf16], CCCustom<"CC_ARM_AAPCS_VFP_Custom_f16">>,
  CCDelegateTo<RetCC_ARM_AAPCS_Common>
]>;


// Windows Control Flow Guard checks take a single argument (the target function
// address) and have no return value.
let Entry = 1 in
def CC_ARM_Win32_CFGuard_Check : CallingConv<[
  CCIfType<[i32], CCAssignToReg<[R0]>>
]>;



//===----------------------------------------------------------------------===//
// Callee-saved register lists.
//===----------------------------------------------------------------------===//

def CSR_NoRegs : CalleeSavedRegs<(add)>;
def CSR_FPRegs : CalleeSavedRegs<(add (sequence "D%u", 0, 31))>;

def CSR_AAPCS : CalleeSavedRegs<(add LR, R11, R10, R9, R8, R7, R6, R5, R4,
                                     (sequence "D%u", 15, 8))>;

// The Windows Control Flow Guard Check function preserves the same registers as
// AAPCS, and also preserves all floating point registers.
def CSR_Win_AAPCS_CFGuard_Check : CalleeSavedRegs<(add LR, R11, R10, R9, R8, R7,
                                     R6, R5, R4, (sequence "D%u", 15, 0))>;

// R8 is used to pass swifterror, remove it from CSR.
def CSR_AAPCS_SwiftError : CalleeSavedRegs<(sub CSR_AAPCS, R8)>;

// R10 is used to pass swiftself, remove it from CSR.
def CSR_AAPCS_SwiftTail : CalleeSavedRegs<(sub CSR_AAPCS, R10)>;

// The order of callee-saved registers needs to match the order we actually push
// them in FrameLowering, because this order is what's used by
// PrologEpilogInserter to allocate frame index slots. So when R7 is the frame
// pointer, we use this AAPCS alternative.
def CSR_AAPCS_SplitPush : CalleeSavedRegs<(add LR, R7, R6, R5, R4,
                                               R11, R10, R9, R8,
                                               (sequence "D%u", 15, 8))>;

// R8 is used to pass swifterror, remove it from CSR.
def CSR_AAPCS_SplitPush_SwiftError : CalleeSavedRegs<(sub CSR_AAPCS_SplitPush,
                                                      R8)>;

// R10 is used to pass swifterror, remove it from CSR.
def CSR_AAPCS_SplitPush_SwiftTail : CalleeSavedRegs<(sub CSR_AAPCS_SplitPush,
                                                     R10)>;

// Constructors and destructors return 'this' in the ARM C++ ABI; since 'this'
// and the pointer return value are both passed in R0 in these cases, this can
// be partially modelled by treating R0 as a callee-saved register
// Only the resulting RegMask is used; the SaveList is ignored
def CSR_AAPCS_ThisReturn : CalleeSavedRegs<(add LR, R11, R10, R9, R8, R7, R6,
                                            R5, R4, (sequence "D%u", 15, 8),
                                            R0)>;

// iOS ABI deviates from ARM standard ABI. R9 is not a callee-saved register.
// Also save R7-R4 first to match the stack frame fixed spill areas.
def CSR_iOS : CalleeSavedRegs<(add LR, R7, R6, R5, R4, (sub CSR_AAPCS, R9))>;

// R8 is used to pass swifterror, remove it from CSR.
def CSR_iOS_SwiftError : CalleeSavedRegs<(sub CSR_iOS, R8)>;

// R10 is used to pass swiftself, remove it from CSR.
def CSR_iOS_SwiftTail : CalleeSavedRegs<(sub CSR_iOS, R10)>;

def CSR_iOS_ThisReturn : CalleeSavedRegs<(add LR, R7, R6, R5, R4,
                                         (sub CSR_AAPCS_ThisReturn, R9))>;

def CSR_iOS_TLSCall
    : CalleeSavedRegs<(add LR, SP, (sub(sequence "R%u", 12, 1), R9, R12),
                      (sequence "D%u", 31, 0))>;

// C++ TLS access function saves all registers except SP. Try to match
// the order of CSRs in CSR_iOS.
def CSR_iOS_CXX_TLS : CalleeSavedRegs<(add CSR_iOS, (sequence "R%u", 12, 1),
                                           (sequence "D%u", 31, 0))>;

// CSRs that are handled by prologue, epilogue.
def CSR_iOS_CXX_TLS_PE : CalleeSavedRegs<(add LR, R12, R11, R7, R5, R4)>;

// CSRs that are handled explicitly via copies.
def CSR_iOS_CXX_TLS_ViaCopy : CalleeSavedRegs<(sub CSR_iOS_CXX_TLS,
                                                   CSR_iOS_CXX_TLS_PE)>;

// The "interrupt" attribute is used to generate code that is acceptable in
// exception-handlers of various kinds. It makes us use a different return
// instruction (handled elsewhere) and affects which registers we must return to
// our "caller" in the same state as we receive them.

// For most interrupts, all registers except SP and LR are shared with
// user-space. We mark LR to be saved anyway, since this is what the ARM backend
// generally does rather than tracking its liveness as a normal register.
def CSR_GenericInt : CalleeSavedRegs<(add LR, (sequence "R%u", 12, 0))>;

// The fast interrupt handlers have more private state and get their own copies
// of R8-R12, in addition to SP and LR. As before, mark LR for saving too.

// FIXME: we mark R11 as callee-saved since it's often the frame-pointer, and
// current frame lowering expects to encounter it while processing callee-saved
// registers.
def CSR_FIQ : CalleeSavedRegs<(add LR, R11, (sequence "R%u", 7, 0))>;