DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Git (4fb54ed484)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
use crate::builder::Builder;
use crate::context::CodegenCx;
use crate::llvm;
use crate::type_::Type;
use crate::type_of::LayoutLlvmExt;
use crate::value::Value;

use rustc_ast::ast::LlvmAsmDialect;
use rustc_ast::ast::{InlineAsmOptions, InlineAsmTemplatePiece};
use rustc_codegen_ssa::mir::operand::OperandValue;
use rustc_codegen_ssa::mir::place::PlaceRef;
use rustc_codegen_ssa::traits::*;
use rustc_data_structures::fx::FxHashMap;
use rustc_hir as hir;
use rustc_middle::span_bug;
use rustc_middle::ty::layout::TyAndLayout;
use rustc_span::{Pos, Span};
use rustc_target::abi::*;
use rustc_target::asm::*;

use libc::{c_char, c_uint};
use log::debug;

impl AsmBuilderMethods<'tcx> for Builder<'a, 'll, 'tcx> {
    fn codegen_llvm_inline_asm(
        &mut self,
        ia: &hir::LlvmInlineAsmInner,
        outputs: Vec<PlaceRef<'tcx, &'ll Value>>,
        mut inputs: Vec<&'ll Value>,
        span: Span,
    ) -> bool {
        let mut ext_constraints = vec![];
        let mut output_types = vec![];

        // Prepare the output operands
        let mut indirect_outputs = vec![];
        for (i, (out, &place)) in ia.outputs.iter().zip(&outputs).enumerate() {
            if out.is_rw {
                let operand = self.load_operand(place);
                if let OperandValue::Immediate(_) = operand.val {
                    inputs.push(operand.immediate());
                }
                ext_constraints.push(i.to_string());
            }
            if out.is_indirect {
                let operand = self.load_operand(place);
                if let OperandValue::Immediate(_) = operand.val {
                    indirect_outputs.push(operand.immediate());
                }
            } else {
                output_types.push(place.layout.llvm_type(self.cx));
            }
        }
        if !indirect_outputs.is_empty() {
            indirect_outputs.extend_from_slice(&inputs);
            inputs = indirect_outputs;
        }

        let clobbers = ia.clobbers.iter().map(|s| format!("~{{{}}}", &s));

        // Default per-arch clobbers
        // Basically what clang does
        let arch_clobbers = match &self.sess().target.target.arch[..] {
            "x86" | "x86_64" => vec!["~{dirflag}", "~{fpsr}", "~{flags}"],
            "mips" | "mips64" => vec!["~{$1}"],
            _ => Vec::new(),
        };

        let all_constraints = ia
            .outputs
            .iter()
            .map(|out| out.constraint.to_string())
            .chain(ia.inputs.iter().map(|s| s.to_string()))
            .chain(ext_constraints)
            .chain(clobbers)
            .chain(arch_clobbers.iter().map(|s| (*s).to_string()))
            .collect::<Vec<String>>()
            .join(",");

        debug!("Asm Constraints: {}", &all_constraints);

        // Depending on how many outputs we have, the return type is different
        let num_outputs = output_types.len();
        let output_type = match num_outputs {
            0 => self.type_void(),
            1 => output_types[0],
            _ => self.type_struct(&output_types, false),
        };

        let asm = ia.asm.as_str();
        let r = inline_asm_call(
            self,
            &asm,
            &all_constraints,
            &inputs,
            output_type,
            ia.volatile,
            ia.alignstack,
            ia.dialect,
            &[span],
        );
        if r.is_none() {
            return false;
        }
        let r = r.unwrap();

        // Again, based on how many outputs we have
        let outputs = ia.outputs.iter().zip(&outputs).filter(|&(ref o, _)| !o.is_indirect);
        for (i, (_, &place)) in outputs.enumerate() {
            let v = if num_outputs == 1 { r } else { self.extract_value(r, i as u64) };
            OperandValue::Immediate(v).store(self, place);
        }

        true
    }

    fn codegen_inline_asm(
        &mut self,
        template: &[InlineAsmTemplatePiece],
        operands: &[InlineAsmOperandRef<'tcx, Self>],
        options: InlineAsmOptions,
        line_spans: &[Span],
    ) {
        let asm_arch = self.tcx.sess.asm_arch.unwrap();

        // Collect the types of output operands
        let mut constraints = vec![];
        let mut output_types = vec![];
        let mut op_idx = FxHashMap::default();
        for (idx, op) in operands.iter().enumerate() {
            match *op {
                InlineAsmOperandRef::Out { reg, late, place } => {
                    let ty = if let Some(place) = place {
                        llvm_fixup_output_type(self.cx, reg.reg_class(), &place.layout)
                    } else {
                        // If the output is discarded, we don't really care what
                        // type is used. We're just using this to tell LLVM to
                        // reserve the register.
                        dummy_output_type(self.cx, reg.reg_class())
                    };
                    output_types.push(ty);
                    op_idx.insert(idx, constraints.len());
                    let prefix = if late { "=" } else { "=&" };
                    constraints.push(format!("{}{}", prefix, reg_to_llvm(reg)));
                }
                InlineAsmOperandRef::InOut { reg, late, in_value, out_place } => {
                    let ty = if let Some(ref out_place) = out_place {
                        llvm_fixup_output_type(self.cx, reg.reg_class(), &out_place.layout)
                    } else {
                        // LLVM required tied operands to have the same type,
                        // so we just use the type of the input.
                        llvm_fixup_output_type(self.cx, reg.reg_class(), &in_value.layout)
                    };
                    output_types.push(ty);
                    op_idx.insert(idx, constraints.len());
                    let prefix = if late { "=" } else { "=&" };
                    constraints.push(format!("{}{}", prefix, reg_to_llvm(reg)));
                }
                _ => {}
            }
        }

        // Collect input operands
        let mut inputs = vec![];
        for (idx, op) in operands.iter().enumerate() {
            match *op {
                InlineAsmOperandRef::In { reg, value } => {
                    let value =
                        llvm_fixup_input(self, value.immediate(), reg.reg_class(), &value.layout);
                    inputs.push(value);
                    op_idx.insert(idx, constraints.len());
                    constraints.push(reg_to_llvm(reg));
                }
                InlineAsmOperandRef::InOut { reg, late: _, in_value, out_place: _ } => {
                    let value = llvm_fixup_input(
                        self,
                        in_value.immediate(),
                        reg.reg_class(),
                        &in_value.layout,
                    );
                    inputs.push(value);
                    constraints.push(format!("{}", op_idx[&idx]));
                }
                InlineAsmOperandRef::SymFn { instance } => {
                    inputs.push(self.cx.get_fn(instance));
                    op_idx.insert(idx, constraints.len());
                    constraints.push("s".to_string());
                }
                InlineAsmOperandRef::SymStatic { def_id } => {
                    inputs.push(self.cx.get_static(def_id));
                    op_idx.insert(idx, constraints.len());
                    constraints.push("s".to_string());
                }
                _ => {}
            }
        }

        // Build the template string
        let mut template_str = String::new();
        for piece in template {
            match *piece {
                InlineAsmTemplatePiece::String(ref s) => {
                    if s.contains('$') {
                        for c in s.chars() {
                            if c == '$' {
                                template_str.push_str("$$");
                            } else {
                                template_str.push(c);
                            }
                        }
                    } else {
                        template_str.push_str(s)
                    }
                }
                InlineAsmTemplatePiece::Placeholder { operand_idx, modifier, span: _ } => {
                    match operands[operand_idx] {
                        InlineAsmOperandRef::In { reg, .. }
                        | InlineAsmOperandRef::Out { reg, .. }
                        | InlineAsmOperandRef::InOut { reg, .. } => {
                            let modifier = modifier_to_llvm(asm_arch, reg.reg_class(), modifier);
                            if let Some(modifier) = modifier {
                                template_str.push_str(&format!(
                                    "${{{}:{}}}",
                                    op_idx[&operand_idx], modifier
                                ));
                            } else {
                                template_str.push_str(&format!("${{{}}}", op_idx[&operand_idx]));
                            }
                        }
                        InlineAsmOperandRef::Const { ref string } => {
                            // Const operands get injected directly into the template
                            template_str.push_str(string);
                        }
                        InlineAsmOperandRef::SymFn { .. }
                        | InlineAsmOperandRef::SymStatic { .. } => {
                            // Only emit the raw symbol name
                            template_str.push_str(&format!("${{{}:c}}", op_idx[&operand_idx]));
                        }
                    }
                }
            }
        }

        if !options.contains(InlineAsmOptions::PRESERVES_FLAGS) {
            match asm_arch {
                InlineAsmArch::AArch64 | InlineAsmArch::Arm => {
                    constraints.push("~{cc}".to_string());
                }
                InlineAsmArch::X86 | InlineAsmArch::X86_64 => {
                    constraints.extend_from_slice(&[
                        "~{dirflag}".to_string(),
                        "~{fpsr}".to_string(),
                        "~{flags}".to_string(),
                    ]);
                }
                InlineAsmArch::RiscV32 | InlineAsmArch::RiscV64 => {}
                InlineAsmArch::Nvptx64 => {}
            }
        }
        if !options.contains(InlineAsmOptions::NOMEM) {
            // This is actually ignored by LLVM, but it's probably best to keep
            // it just in case. LLVM instead uses the ReadOnly/ReadNone
            // attributes on the call instruction to optimize.
            constraints.push("~{memory}".to_string());
        }
        let volatile = !options.contains(InlineAsmOptions::PURE);
        let alignstack = !options.contains(InlineAsmOptions::NOSTACK);
        let output_type = match &output_types[..] {
            [] => self.type_void(),
            [ty] => ty,
            tys => self.type_struct(&tys, false),
        };
        let dialect = match asm_arch {
            InlineAsmArch::X86 | InlineAsmArch::X86_64
                if !options.contains(InlineAsmOptions::ATT_SYNTAX) =>
            {
                LlvmAsmDialect::Intel
            }
            _ => LlvmAsmDialect::Att,
        };
        let result = inline_asm_call(
            self,
            &template_str,
            &constraints.join(","),
            &inputs,
            output_type,
            volatile,
            alignstack,
            dialect,
            line_spans,
        )
        .unwrap_or_else(|| span_bug!(line_spans[0], "LLVM asm constraint validation failed"));

        if options.contains(InlineAsmOptions::PURE) {
            if options.contains(InlineAsmOptions::NOMEM) {
                llvm::Attribute::ReadNone.apply_callsite(llvm::AttributePlace::Function, result);
            } else if options.contains(InlineAsmOptions::READONLY) {
                llvm::Attribute::ReadOnly.apply_callsite(llvm::AttributePlace::Function, result);
            }
        } else {
            if options.contains(InlineAsmOptions::NOMEM) {
                llvm::Attribute::InaccessibleMemOnly
                    .apply_callsite(llvm::AttributePlace::Function, result);
            } else {
                // LLVM doesn't have an attribute to represent ReadOnly + SideEffect
            }
        }

        // Write results to outputs
        for (idx, op) in operands.iter().enumerate() {
            if let InlineAsmOperandRef::Out { reg, place: Some(place), .. }
            | InlineAsmOperandRef::InOut { reg, out_place: Some(place), .. } = *op
            {
                let value = if output_types.len() == 1 {
                    result
                } else {
                    self.extract_value(result, op_idx[&idx] as u64)
                };
                let value = llvm_fixup_output(self, value, reg.reg_class(), &place.layout);
                OperandValue::Immediate(value).store(self, place);
            }
        }
    }
}

impl AsmMethods for CodegenCx<'ll, 'tcx> {
    fn codegen_global_asm(&self, ga: &hir::GlobalAsm) {
        let asm = ga.asm.as_str();
        unsafe {
            llvm::LLVMRustAppendModuleInlineAsm(self.llmod, asm.as_ptr().cast(), asm.len());
        }
    }
}

fn inline_asm_call(
    bx: &mut Builder<'a, 'll, 'tcx>,
    asm: &str,
    cons: &str,
    inputs: &[&'ll Value],
    output: &'ll llvm::Type,
    volatile: bool,
    alignstack: bool,
    dia: LlvmAsmDialect,
    line_spans: &[Span],
) -> Option<&'ll Value> {
    let volatile = if volatile { llvm::True } else { llvm::False };
    let alignstack = if alignstack { llvm::True } else { llvm::False };

    let argtys = inputs
        .iter()
        .map(|v| {
            debug!("Asm Input Type: {:?}", *v);
            bx.cx.val_ty(*v)
        })
        .collect::<Vec<_>>();

    debug!("Asm Output Type: {:?}", output);
    let fty = bx.cx.type_func(&argtys[..], output);
    unsafe {
        // Ask LLVM to verify that the constraints are well-formed.
        let constraints_ok = llvm::LLVMRustInlineAsmVerify(fty, cons.as_ptr().cast(), cons.len());
        debug!("constraint verification result: {:?}", constraints_ok);
        if constraints_ok {
            let v = llvm::LLVMRustInlineAsm(
                fty,
                asm.as_ptr().cast(),
                asm.len(),
                cons.as_ptr().cast(),
                cons.len(),
                volatile,
                alignstack,
                llvm::AsmDialect::from_generic(dia),
            );
            let call = bx.call(v, inputs, None);

            // Store mark in a metadata node so we can map LLVM errors
            // back to source locations.  See #17552.
            let key = "srcloc";
            let kind = llvm::LLVMGetMDKindIDInContext(
                bx.llcx,
                key.as_ptr() as *const c_char,
                key.len() as c_uint,
            );

            // srcloc contains one integer for each line of assembly code.
            // Unfortunately this isn't enough to encode a full span so instead
            // we just encode the start position of each line.
            // FIXME: Figure out a way to pass the entire line spans.
            let mut srcloc = vec![];
            if dia == LlvmAsmDialect::Intel && line_spans.len() > 1 {
                // LLVM inserts an extra line to add the ".intel_syntax", so add
                // a dummy srcloc entry for it.
                //
                // Don't do this if we only have 1 line span since that may be
                // due to the asm template string coming from a macro. LLVM will
                // default to the first srcloc for lines that don't have an
                // associated srcloc.
                srcloc.push(bx.const_i32(0));
            }
            srcloc.extend(line_spans.iter().map(|span| bx.const_i32(span.lo().to_u32() as i32)));
            let md = llvm::LLVMMDNodeInContext(bx.llcx, srcloc.as_ptr(), srcloc.len() as u32);
            llvm::LLVMSetMetadata(call, kind, md);

            Some(call)
        } else {
            // LLVM has detected an issue with our constraints, bail out
            None
        }
    }
}

/// Converts a register class to an LLVM constraint code.
fn reg_to_llvm(reg: InlineAsmRegOrRegClass) -> String {
    match reg {
        InlineAsmRegOrRegClass::Reg(reg) => format!("{{{}}}", reg.name()),
        InlineAsmRegOrRegClass::RegClass(reg) => match reg {
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::reg) => "r",
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg) => "w",
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16) => "x",
            InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg) => "r",
            InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg_thumb) => "l",
            InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg)
            | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low16)
            | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low8) => "t",
            InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg_low16)
            | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low8)
            | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low4) => "x",
            InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg)
            | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg) => "w",
            InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg16) => "h",
            InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg32) => "r",
            InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg64) => "l",
            InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::reg) => "r",
            InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::freg) => "f",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::reg) => "r",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd) => "Q",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_byte) => "q",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::xmm_reg)
            | InlineAsmRegClass::X86(X86InlineAsmRegClass::ymm_reg) => "x",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::zmm_reg) => "v",
            InlineAsmRegClass::X86(X86InlineAsmRegClass::kreg) => "^Yk",
        }
        .to_string(),
    }
}

/// Converts a modifier into LLVM's equivalent modifier.
fn modifier_to_llvm(
    arch: InlineAsmArch,
    reg: InlineAsmRegClass,
    modifier: Option<char>,
) -> Option<char> {
    match reg {
        InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::reg) => modifier,
        InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg)
        | InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16) => {
            if modifier == Some('v') { None } else { modifier }
        }
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg_thumb) => None,
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg_low16) => None,
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low16)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low8) => Some('P'),
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low8)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low4) => {
            if modifier.is_none() {
                Some('q')
            } else {
                modifier
            }
        }
        InlineAsmRegClass::Nvptx(_) => None,
        InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::reg)
        | InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::freg) => None,
        InlineAsmRegClass::X86(X86InlineAsmRegClass::reg)
        | InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd) => match modifier {
            None if arch == InlineAsmArch::X86_64 => Some('q'),
            None => Some('k'),
            Some('l') => Some('b'),
            Some('h') => Some('h'),
            Some('x') => Some('w'),
            Some('e') => Some('k'),
            Some('r') => Some('q'),
            _ => unreachable!(),
        },
        InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_byte) => None,
        InlineAsmRegClass::X86(reg @ X86InlineAsmRegClass::xmm_reg)
        | InlineAsmRegClass::X86(reg @ X86InlineAsmRegClass::ymm_reg)
        | InlineAsmRegClass::X86(reg @ X86InlineAsmRegClass::zmm_reg) => match (reg, modifier) {
            (X86InlineAsmRegClass::xmm_reg, None) => Some('x'),
            (X86InlineAsmRegClass::ymm_reg, None) => Some('t'),
            (X86InlineAsmRegClass::zmm_reg, None) => Some('g'),
            (_, Some('x')) => Some('x'),
            (_, Some('y')) => Some('t'),
            (_, Some('z')) => Some('g'),
            _ => unreachable!(),
        },
        InlineAsmRegClass::X86(X86InlineAsmRegClass::kreg) => None,
    }
}

/// Type to use for outputs that are discarded. It doesn't really matter what
/// the type is, as long as it is valid for the constraint code.
fn dummy_output_type(cx: &CodegenCx<'ll, 'tcx>, reg: InlineAsmRegClass) -> &'ll Type {
    match reg {
        InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::reg) => cx.type_i32(),
        InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg)
        | InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16) => {
            cx.type_vector(cx.type_i64(), 2)
        }
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::reg_thumb) => cx.type_i32(),
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::sreg_low16) => cx.type_f32(),
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low16)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::dreg_low8) => cx.type_f64(),
        InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low8)
        | InlineAsmRegClass::Arm(ArmInlineAsmRegClass::qreg_low4) => {
            cx.type_vector(cx.type_i64(), 2)
        }
        InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg16) => cx.type_i16(),
        InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg32) => cx.type_i32(),
        InlineAsmRegClass::Nvptx(NvptxInlineAsmRegClass::reg64) => cx.type_i64(),
        InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::reg) => cx.type_i32(),
        InlineAsmRegClass::RiscV(RiscVInlineAsmRegClass::freg) => cx.type_f32(),
        InlineAsmRegClass::X86(X86InlineAsmRegClass::reg)
        | InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd) => cx.type_i32(),
        InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_byte) => cx.type_i8(),
        InlineAsmRegClass::X86(X86InlineAsmRegClass::xmm_reg)
        | InlineAsmRegClass::X86(X86InlineAsmRegClass::ymm_reg)
        | InlineAsmRegClass::X86(X86InlineAsmRegClass::zmm_reg) => cx.type_f32(),
        InlineAsmRegClass::X86(X86InlineAsmRegClass::kreg) => cx.type_i16(),
    }
}

/// Helper function to get the LLVM type for a Scalar. Pointers are returned as
/// the equivalent integer type.
fn llvm_asm_scalar_type(cx: &CodegenCx<'ll, 'tcx>, scalar: &Scalar) -> &'ll Type {
    match scalar.value {
        Primitive::Int(Integer::I8, _) => cx.type_i8(),
        Primitive::Int(Integer::I16, _) => cx.type_i16(),
        Primitive::Int(Integer::I32, _) => cx.type_i32(),
        Primitive::Int(Integer::I64, _) => cx.type_i64(),
        Primitive::F32 => cx.type_f32(),
        Primitive::F64 => cx.type_f64(),
        Primitive::Pointer => cx.type_isize(),
        _ => unreachable!(),
    }
}

/// Fix up an input value to work around LLVM bugs.
fn llvm_fixup_input(
    bx: &mut Builder<'a, 'll, 'tcx>,
    mut value: &'ll Value,
    reg: InlineAsmRegClass,
    layout: &TyAndLayout<'tcx>,
) -> &'ll Value {
    match (reg, &layout.abi) {
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg), Abi::Scalar(s)) => {
            if let Primitive::Int(Integer::I8, _) = s.value {
                let vec_ty = bx.cx.type_vector(bx.cx.type_i8(), 8);
                bx.insert_element(bx.const_undef(vec_ty), value, bx.const_i32(0))
            } else {
                value
            }
        }
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16), Abi::Scalar(s)) => {
            let elem_ty = llvm_asm_scalar_type(bx.cx, s);
            let count = 16 / layout.size.bytes();
            let vec_ty = bx.cx.type_vector(elem_ty, count);
            if let Primitive::Pointer = s.value {
                value = bx.ptrtoint(value, bx.cx.type_isize());
            }
            bx.insert_element(bx.const_undef(vec_ty), value, bx.const_i32(0))
        }
        (
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16),
            Abi::Vector { element, count },
        ) if layout.size.bytes() == 8 => {
            let elem_ty = llvm_asm_scalar_type(bx.cx, element);
            let vec_ty = bx.cx.type_vector(elem_ty, *count);
            let indices: Vec<_> = (0..count * 2).map(|x| bx.const_i32(x as i32)).collect();
            bx.shuffle_vector(value, bx.const_undef(vec_ty), bx.const_vector(&indices))
        }
        (InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd), Abi::Scalar(s))
            if s.value == Primitive::F64 =>
        {
            bx.bitcast(value, bx.cx.type_i64())
        }
        (
            InlineAsmRegClass::X86(X86InlineAsmRegClass::xmm_reg | X86InlineAsmRegClass::zmm_reg),
            Abi::Vector { .. },
        ) if layout.size.bytes() == 64 => bx.bitcast(value, bx.cx.type_vector(bx.cx.type_f64(), 8)),
        (
            InlineAsmRegClass::Arm(
                ArmInlineAsmRegClass::sreg_low16
                | ArmInlineAsmRegClass::dreg_low8
                | ArmInlineAsmRegClass::qreg_low4
                | ArmInlineAsmRegClass::dreg
                | ArmInlineAsmRegClass::qreg,
            ),
            Abi::Scalar(s),
        ) => {
            if let Primitive::Int(Integer::I32, _) = s.value {
                bx.bitcast(value, bx.cx.type_f32())
            } else {
                value
            }
        }
        _ => value,
    }
}

/// Fix up an output value to work around LLVM bugs.
fn llvm_fixup_output(
    bx: &mut Builder<'a, 'll, 'tcx>,
    mut value: &'ll Value,
    reg: InlineAsmRegClass,
    layout: &TyAndLayout<'tcx>,
) -> &'ll Value {
    match (reg, &layout.abi) {
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg), Abi::Scalar(s)) => {
            if let Primitive::Int(Integer::I8, _) = s.value {
                bx.extract_element(value, bx.const_i32(0))
            } else {
                value
            }
        }
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16), Abi::Scalar(s)) => {
            value = bx.extract_element(value, bx.const_i32(0));
            if let Primitive::Pointer = s.value {
                value = bx.inttoptr(value, layout.llvm_type(bx.cx));
            }
            value
        }
        (
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16),
            Abi::Vector { element, count },
        ) if layout.size.bytes() == 8 => {
            let elem_ty = llvm_asm_scalar_type(bx.cx, element);
            let vec_ty = bx.cx.type_vector(elem_ty, *count * 2);
            let indices: Vec<_> = (0..*count).map(|x| bx.const_i32(x as i32)).collect();
            bx.shuffle_vector(value, bx.const_undef(vec_ty), bx.const_vector(&indices))
        }
        (InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd), Abi::Scalar(s))
            if s.value == Primitive::F64 =>
        {
            bx.bitcast(value, bx.cx.type_f64())
        }
        (
            InlineAsmRegClass::X86(X86InlineAsmRegClass::xmm_reg | X86InlineAsmRegClass::zmm_reg),
            Abi::Vector { .. },
        ) if layout.size.bytes() == 64 => bx.bitcast(value, layout.llvm_type(bx.cx)),
        (
            InlineAsmRegClass::Arm(
                ArmInlineAsmRegClass::sreg_low16
                | ArmInlineAsmRegClass::dreg_low8
                | ArmInlineAsmRegClass::qreg_low4
                | ArmInlineAsmRegClass::dreg
                | ArmInlineAsmRegClass::qreg,
            ),
            Abi::Scalar(s),
        ) => {
            if let Primitive::Int(Integer::I32, _) = s.value {
                bx.bitcast(value, bx.cx.type_i32())
            } else {
                value
            }
        }
        _ => value,
    }
}

/// Output type to use for llvm_fixup_output.
fn llvm_fixup_output_type(
    cx: &CodegenCx<'ll, 'tcx>,
    reg: InlineAsmRegClass,
    layout: &TyAndLayout<'tcx>,
) -> &'ll Type {
    match (reg, &layout.abi) {
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg), Abi::Scalar(s)) => {
            if let Primitive::Int(Integer::I8, _) = s.value {
                cx.type_vector(cx.type_i8(), 8)
            } else {
                layout.llvm_type(cx)
            }
        }
        (InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16), Abi::Scalar(s)) => {
            let elem_ty = llvm_asm_scalar_type(cx, s);
            let count = 16 / layout.size.bytes();
            cx.type_vector(elem_ty, count)
        }
        (
            InlineAsmRegClass::AArch64(AArch64InlineAsmRegClass::vreg_low16),
            Abi::Vector { element, count },
        ) if layout.size.bytes() == 8 => {
            let elem_ty = llvm_asm_scalar_type(cx, element);
            cx.type_vector(elem_ty, count * 2)
        }
        (InlineAsmRegClass::X86(X86InlineAsmRegClass::reg_abcd), Abi::Scalar(s))
            if s.value == Primitive::F64 =>
        {
            cx.type_i64()
        }
        (
            InlineAsmRegClass::X86(X86InlineAsmRegClass::xmm_reg | X86InlineAsmRegClass::zmm_reg),
            Abi::Vector { .. },
        ) if layout.size.bytes() == 64 => cx.type_vector(cx.type_f64(), 8),
        (
            InlineAsmRegClass::Arm(
                ArmInlineAsmRegClass::sreg_low16
                | ArmInlineAsmRegClass::dreg_low8
                | ArmInlineAsmRegClass::qreg_low4
                | ArmInlineAsmRegClass::dreg
                | ArmInlineAsmRegClass::qreg,
            ),
            Abi::Scalar(s),
        ) => {
            if let Primitive::Int(Integer::I32, _) = s.value {
                cx.type_f32()
            } else {
                layout.llvm_type(cx)
            }
        }
        _ => layout.llvm_type(cx),
    }
}